system

Abstract

We provide the system. [Solution] A means for analyzing the search term entered by the user and breaking it down into its constituent elements, A means for collecting relevant evaluation information and attribute information based on the aforementioned components, A means for generating an emotion score based on the collected evaluation information and for identifying attributes based on the attribute information, A means for selecting the relevant information asset based on the aforementioned sentiment score and attribute, A means for presenting the selected information assets to the user, A means for generating a list based on user evaluation from the aforementioned presented information assets, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years' information assets, a huge amount of digital content is provided, but it is difficult for users to find information reflecting their ambiguous search intentions. In particular, when using ambiguous search terms, there is a lack of means for efficiently accessing information suitable for the user's intentions. Solving this problem is required.

Means for Solving the Problems

[0005] This invention provides a means for analyzing ambiguous search terms entered by a user and identifying their constituent elements. This allows for the collection of evaluation and attribute information based on the search terms, and the generation of an emotional score using emotional analysis technology. Furthermore, it provides a system that enables the selection and presentation of relevant information assets to the user based on the generated emotional score and collected attribute information. This solves the problem of efficiently selecting and presenting information that is appropriate to the user's intent.

[0006] A "search term" is a phrase or word that a user enters to find information assets.

[0007] "Components" refer to the individual elements or categories extracted when analyzing search terms.

[0008] "Evaluation information" refers to data that includes sentiment evaluations and reviews related to information assets.

[0009] "Attribute information" refers to information that indicates metadata such as the characteristics and categories of an information asset.

[0010] An "emotional score" is a numerical representation of the emotional evaluation of an information asset, derived from evaluation data.

[0011] "Information assets" refer to digital content and data that users are interested in.

[0012] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0013] A "database" is a system or place for organizing, storing, searching, and retrieving information.

[0014] A "system" is a configuration in which multiple elements work together to perform a specific function. [Brief explanation of the drawing]

[0015] [Figure 1] It 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. [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.

Embodiments for Carrying Out the Invention

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a tagged 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.

[0019] In the following embodiments, a tagged RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a tagged 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, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is a system for users to efficiently search for information assets. This system operates using ambiguous search terms entered by the user through a terminal. When a user searches for information assets, they enter search terms on the terminal.

[0037] The server receives search terms submitted by users and analyzes them using natural language processing techniques. As a result of the analysis, several elements that make up the search terms are identified. Next, the server collects relevant evaluation and attribute information from external databases and APIs based on these elements.

[0038] The server performs sentiment analysis on the collected data and generates a sentiment score for each information asset. Simultaneously, it uses attribute information to check whether the information asset meets specific criteria. Information assets with high sentiment scores or those that meet the attribute criteria are selected and provided to the user.

[0039] The terminal displays a list of relevant information assets received from the server to the user. Based on the displayed information, the user can view details, purchase specific information assets, or browse them. This process allows the user to quickly find the information assets they are looking for.

[0040] For example, if a user enters the search terms "moving story, medical-themed movie," the server analyzes this and identifies its constituent elements: "moving," "medical," and "movie." Next, the server collects evaluation and attribute information based on these elements and calculates an emotional score for each. Then, it identifies movies that are both "moving" and have a "medical-related theme," and presents them to the user's device. The user can then select a movie that interests them from the presented results and view its details.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user enters a search term into the search bar on their device and sends a search request.

[0044] Step 2:

[0045] The server receives the search term sent from the user's terminal. This search term is analyzed by a natural language processing engine, and its constituent elements are extracted. Elements such as "emotional," "medical," and "film" are identified.

[0046] Step 3:

[0047] Based on the identified components, the server collects relevant evaluation and attribute information via external databases and APIs. This collection includes review comments and metadata for each information asset.

[0048] Step 4:

[0049] The server performs sentiment analysis on the collected evaluation information. It analyzes each review comment to calculate a sentiment score and aggregates it for each information asset.

[0050] Step 5:

[0051] The server checks whether each information asset meets the search criteria based on the collected attribute information. It then performs filtering to narrow down the results to "related to medicine" and "movies."

[0052] Step 6:

[0053] The server selects information assets with high sentiment scores and attribute matching rates from the filtered data, and then ranks the results.

[0054] Step 7:

[0055] The server sends the selection results to the user's terminal. The terminal displays the received list of information assets to the user.

[0056] Step 8:

[0057] Users can view details of the information assets presented through their devices, select those that interest them, and purchase or view them.

[0058] (Example 1)

[0059] 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."

[0060] In today's information-saturated world, users find it difficult to quickly and accurately find the information resources they need from the vast amount of data available. Furthermore, there is a need for a system that can provide highly accurate search results even with vague search terms. However, current technology faces the challenge of providing sufficient relevant information in response to vague user input.

[0061] 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.

[0062] In this invention, the server includes means for analyzing a search term entered by a user and breaking it down into meaningful components; means for collecting relevant evaluation information and attribute information from external sources based on the components; and means for generating an emotion index based on the evaluation information collected using emotion analysis technology and identifying attributes that satisfy predetermined conditions based on the attribute information. This makes it possible to quickly and accurately select and provide relevant information resources even when a user enters an ambiguous search term.

[0063] A "search term" is a linguistic keyword that a user enters when searching for information resources.

[0064] A "constituent element" is the smallest meaningful unit obtained as a result of analyzing a search term.

[0065] "Evaluation information" refers to data related to user reviews, scores, and other evaluations of information resources.

[0066] "Attribute information" refers to data about the characteristics of an information resource, such as its properties or category.

[0067] An "emotional index" is a numerical value or indicator that represents the intensity or nature of emotions towards an information resource, generated using emotion analysis techniques.

[0068] An "external information source" refers to an information provider, including external databases and programming interfaces that a server accesses to collect information.

[0069] This invention is a system aimed at efficiently finding the information resources that users are looking for. This system operates based on ambiguous search terms transmitted by the user from their terminal and provides information resources quickly and accurately.

[0070] The server processes the user's search terms received via the terminal. The search terms are broken down into their constituent elements using natural language processing techniques. Specifically, the server uses natural language processing libraries such as SpaCy and Google® Cloud NLP API to perform these processes.

[0071] Furthermore, the server collects evaluation and attribute information from external sources based on the identified components. These sources include publicly available databases and programming interfaces. Here, procedures for collecting information are executed using programming languages ​​such as Python.

[0072] The server performs sentiment analysis on the collected data. Using libraries such as TextBlob and NLTK, it calculates sentiment indicators and determines whether the information resources meet predetermined criteria. This process makes it possible to avoid false information and misunderstandings and provide users with useful information.

[0073] For example, if a user enters the search terms "moving stories, medical-themed movies," the server extracts elements such as "moving," "medical," and "movie," and collects and analyzes related information. As a result, a list of relevant movies is displayed on the user's device. This allows the user to quickly find movies that interest them and view their details.

[0074] An example of a prompt to input into the generative AI model would be, "Please recommend movies with inspiring stories and medical themes." This prompt would allow the system to quickly search for relevant movies and recommend titles to the user.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The user accesses the system through a terminal and enters vague search terms into the search field. For example, they might enter the text, "moving stories, medical-themed movies." This entered search term is then output as data sent to the server.

[0078] Step 2:

[0079] The server receives the search term sent from the terminal. Using the received search term as input, it performs analysis using a natural language processing library (e.g., SpaCy or Google Cloud NLP API). Through this analysis, the search term is broken down into components such as "emotional," "medical," and "movie," and these components are output.

[0080] Step 3:

[0081] The server takes the disassembled components as input and accesses external databases and APIs (e.g., publicly available movie database APIs) to collect relevant rating and attribute information. This collection results in outputting data such as movie reviews and attributes of information resources.

[0082] Step 4:

[0083] Using the collected evaluation information as input, the server generates sentiment indicators for each information resource using a sentiment analysis library (e.g., TextBlob or NLTK). As a result of this sentiment analysis, a sentiment score for each information resource is output.

[0084] Step 5:

[0085] The server uses the generated emotion score and collected attribute information as input to select information resources that meet predetermined conditions (e.g., "emotional" and "medical-related"). As a result of this selection process, the relevant movies and other information resources are output.

[0086] Step 6:

[0087] The server organizes the selected information resources in JSON format and sends them to the terminal. The terminal receives this data and displays it to the user in a list format. The displayed information includes the title, evaluation score, and related attributes.

[0088] Step 7:

[0089] Users select information resources that interest them from those displayed on their device and view their details. After viewing the details, users can either watch the selected movie or conduct further research.

[0090] (Application Example 1)

[0091] 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."

[0092] In today's information and communication environment, a vast amount of content is available, but it is difficult for users to quickly and accurately find the optimal information assets that meet their needs. In this situation, there is a need for a system that allows users to easily obtain the information they truly want simply by using concise and vague search terms.

[0093] 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.

[0094] In this invention, the server includes means for analyzing the search term entered by the user and breaking it down into its constituent elements, means for collecting relevant evaluation information and attribute information based on the constituent elements, and means for generating a sentiment score based on the collected evaluation information and identifying attributes based on the attribute information. This enables the user to efficiently and effectively select the most suitable information assets from their ambiguous search intent, and as a result, to quickly access the expected content.

[0095] A "user" is someone who has the purpose of searching for specific information assets through an information processing system.

[0096] A "search term" is a linguistic expression that a user enters when searching for information assets.

[0097] A "constituent element" is a semantic unit obtained by analyzing a search term, and is a fundamental element that forms the basis of information gathering.

[0098] "Evaluation information" refers to data on past reputation and evaluations of information assets.

[0099] "Attribute information" refers to data that indicates the characteristics and features associated with an information asset.

[0100] An "emotional score" is an index that quantifies the public's emotional tendencies towards information assets.

[0101] "Information assets" is a concept that includes various media such as movies, music, and books that users try to find through searches.

[0102] "Presentation" refers to the act of providing analyzed and selected information assets to users in a visible format.

[0103] A "list" refers to a list of information assets selected based on user evaluations and other factors.

[0104] The present invention relates to a system configured for users to efficiently search for information assets. Embodiments include the following configurations:

[0105] The server receives search terms entered by the user through the terminal. These search terms are broken down into their constituent elements using natural language processing techniques. Specifically, natural language processing libraries such as NLTK and spaCy are used to analyze the search terms. This allows for the breakdown of vague search terms, such as "I want to relax music," into constituent elements like "relax" and "music."

[0106] Based on the analyzed components, the server collects relevant evaluation and attribute information from external sources. These sources could include various APIs, such as the Spotify API for music. Based on this data, a sentiment analysis tool (such as TextBlob or VADER Sentiment) generates a sentiment score.

[0107] Based on the generated sentiment score and attributes, the server selects information assets that meet the user's request and presents them to the user's device. The presented information assets are organized based on the user's evaluation and presented as a list. This allows the user to view details of the information assets in a way that aligns with their interests.

[0108] For example, if a user enters "music to relax" as a search term, the server analyzes this search term, collects relevant music with relaxing effects, evaluates the emotional score, and presents the user with a list of appropriate music. This process can be adapted more flexibly to user requests by utilizing generative AI models.

[0109] An example of a prompt might be, "The user is looking for music to help them relax. Please list music that is highly related to relaxation." The system should respond quickly to such prompts.

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The user uses a device to enter search terms and sends them to the server. The entered search terms are vague keywords that include the user's subjective preferences.

[0113] Step 2:

[0114] The server receives the incoming search term and analyzes it using natural language processing. At this stage, libraries such as NLTK and spaCy are used to break down the search term into its constituent elements. The input is the search term, and the output is a list of its constituent elements.

[0115] Step 3:

[0116] The server collects relevant evaluation and attribute information based on the obtained components. This process is performed using external APIs (e.g., various database APIs), resulting in data sets of components as input and evaluation and attribute information as output.

[0117] Step 4:

[0118] The server generates sentiment scores using sentiment analysis tools (such as TextBlob or VADER Sentiment) based on the collected evaluation information. At this stage, the emotional tendencies towards each information asset are quantified, with evaluation information as input and sentiment scores as output.

[0119] Step 5:

[0120] The server selects the information asset that best suits the user's preferences from all candidates based on sentiment scores and attribute information. The input is sentiment scores and attribute information, and the output is a list of the optimal information assets.

[0121] Step 6:

[0122] The selected information assets are presented to the user via the terminal. The user can review the list and view details of the information assets that interest them. The output at this stage is a list of information assets organized in a way that is visible to the user.

[0123] 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.

[0124] This invention provides a more personalized search experience by not only analyzing the search terms entered by the user, but also recognizing the user's emotional state using an emotion engine and incorporating the results into the search process. This system improves user satisfaction by selecting and presenting information assets using not only user input but also the user's emotional data.

[0125] The user enters search terms through the device, and the emotion engine analyzes their current emotional state based on biometric information (such as heart rate and facial expressions) and past input history. Sensors that acquire the user's biometric information in real time are used to analyze the emotional state, thereby quantifying the user's emotional state.

[0126] The server receives this data and analyzes both the search terms and the user's emotional state. First, the search terms are broken down into their constituent parts using natural language processing. Then, the server applies filters that take the user's emotional state into account and collects relevant evaluation and attribute information from an external database. It calculates an emotional score for the evaluation information using sentiment analysis techniques and refines the search criteria based on the collected attribute information.

[0127] As a concrete example, consider a scenario where a user searches for "movies with inspiring stories and medical themes," and the emotion engine determines that the user is currently in an emotional state of wanting to be "encouraged." The server analyzes this information, prioritizes selecting movies that particularly emphasize uplifting elements, and creates a ranking based on emotion scores. This selected list of movies is then sent to the user's device, allowing the user to immediately access information assets that match their current mood.

[0128] By presenting information assets in this way, taking into account the user's emotional state, it becomes possible to provide an experience not found in conventional search systems. This can improve search accuracy and user satisfaction.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The user uses their device to enter a specific search term into the search bar and submits a search request.

[0132] Step 2:

[0133] Simultaneously, the emotion engine collects the user's biometric information. This data includes heart rate and facial expression data, and analyzes the user's emotional state in real time.

[0134] Step 3:

[0135] The server processes the search terms and sentiment data received from the user's terminal. First, the search terms are analyzed using natural language processing techniques, and the keywords are broken down into their constituent elements.

[0136] Step 4:

[0137] The server takes into account the user's emotional state, as analyzed by the emotion engine, and sets up filters to prioritize the collection of information related to that emotion.

[0138] Step 5:

[0139] The server uses external databases and APIs to collect relevant evaluation and attribute information based on the analyzed components. In particular, it collects information that best matches the user's current emotional state.

[0140] Step 6:

[0141] The server calculates a sentiment score from the collected evaluation information and filters out potential information assets based on this score.

[0142] Step 7:

[0143] The server ranks information assets based on sentiment scores and attribute matching rates, and identifies content that is appropriate for the user's emotional state.

[0144] Step 8:

[0145] The server lists the selected information assets and sends them to the user's terminal. The terminal receives this information and displays it on the user's screen.

[0146] Step 9:

[0147] Users can view the presented information assets and then check the details of information that interests them, or purchase / view it.

[0148] This entire process allows users to quickly obtain information that matches their current emotional state, not just through simple keyword searches.

[0149] (Example 2)

[0150] 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".

[0151] Traditional search systems only present information based on the user's entered search terms, failing to provide information tailored to the user's emotional state. This results in users not receiving information that matches their current emotional state, leading to a lower level of satisfaction with their search experience.

[0152] 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.

[0153] In this invention, the server includes means for analyzing a search term entered by the user and breaking it down into its constituent elements, means for collecting relevant evaluation information and attribute information based on the constituent elements and the user's emotional state, and means for analyzing the emotional state from the user's biometric information and generating an emotional score considering the results. This makes it possible to select relevant information assets according to the user's emotional state and provide a more personalized search experience.

[0154] A "user" refers to an individual or organization that uses this system to retrieve information.

[0155] A "search term" refers to the words or phrases that a user enters when searching for information.

[0156] "Components" refer to the main words and phrases extracted during the process of analyzing search terms.

[0157] "Emotional state" refers to the user's psychological or emotional state, which is analyzed based on the user's biometric information and past history.

[0158] "Evaluation information" refers to opinions and evaluations related to specific information assets collected from external data storage devices.

[0159] "Attribute information" refers to the characteristics and features associated with an information asset.

[0160] An "emotional score" is a numerical representation of the emotional value of an information asset, calculated while taking into account the user's emotional state.

[0161] "Information assets" refer to a collection of information selected for presentation to users.

[0162] "Natural language processing technology" refers to the techniques and methodologies used to enable computers to understand human language.

[0163] "Emotional analysis technology" refers to technology that analyzes a user's emotional state based on biometric information and text data.

[0164] An "external data storage device" refers to an external database or information system that a system accesses to collect information.

[0165] This invention provides a system that enables personalized information retrieval based on search terms entered by the user. This system operates through the collaborative efforts of the user, terminal, and server.

[0166] The user enters search terms through an interface built into the device. The device utilizes devices such as a heart rate sensor and a facial recognition camera to obtain the user's biometric information. This information is transmitted to the server in real time.

[0167] The server analyzes the received search terms using natural language processing techniques and breaks them down into their constituent elements. It also uses sentiment analysis techniques to analyze the user's emotional state based on biometric information sent from the terminal. This emotional state functions as a filter to select information assets that match the user's search objectives.

[0168] Furthermore, the server collects relevant evaluation and attribute information from an external data storage device based on its components and emotional state. Based on this information, it generates an emotional score and selects the appropriate information assets. The selected information assets are ranked in a way that suits the user's emotional needs and presented to the terminal.

[0169] For example, if a user enters "movies with an emotional story and a medical theme," and the emotion analysis technology determines that the user is in a state of wanting to be encouraged, the server will prioritize selecting movies that particularly emphasize encouraging elements. The list of movies obtained through this selection process will then be quickly provided to the user for viewing.

[0170] An example of a prompt would be: "The emotion engine has analyzed that the user is currently in an emotional state of 'wanting encouragement.' In this state, generate a list of movies that emphasize the encouraging aspect for the search query 'inspirational stories, medical-themed movies.'"

[0171] Thus, the present invention enables information retrieval that takes into account the user's emotional state, providing a more satisfying search experience than before.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The user enters search terms through the terminal. The entered search terms are specific phrases such as "moving stories, medical-themed movies." The terminal sends the search terms to the server and also uses sensors to acquire biometric information such as the user's heart rate and facial expressions. This biometric information is sent to the server as input data to analyze the user's emotional state.

[0175] Step 2:

[0176] The server receives the search term and biometric information. Next, it analyzes the received search term using natural language processing techniques and breaks it down into its constituent elements. In this process, the search term is divided into meaningful words such as "emotional," "story," "medical," and "movie," and these are used as the basis data for analysis. At the same time, the server applies emotion analysis techniques based on the biometric information to determine whether the user is in an emotional state such as "wanting to be encouraged." The result of this determination is an important output value that will influence future search conditions.

[0177] Step 3:

[0178] Based on the analyzed components and emotional states, the server collects relevant evaluation and attribute information from an external data storage device. Specifically, the server sends queries to the database via an API to retrieve evaluation and attribute information. In this process, the evaluation information includes information related to "emotional," "medical," and "encouraging." Data processing is performed on the collected data to calculate an emotional score, yielding important output that can be used as a selection criterion for information assets.

[0179] Step 4:

[0180] The server selects relevant information assets based on sentiment scores and collected attribute information. This process aims to rank the collected movie list based on sentiment scores, placing the content most suitable for users seeking encouragement at the top. This ranking information is output in list format and ready to be presented to the user visually.

[0181] Step 5:

[0182] The server sends the selected information assets to the user's terminal. The terminal displays the received movie list on the screen, allowing the user to select their desired movie. Through this list, the user can browse stories that match their emotional state from the selected movies. This provides a highly satisfying search experience.

[0183] (Application Example 2)

[0184] 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".

[0185] Traditional search systems present information assets based solely on the search terms entered by the user, failing to provide personalized results that take into account the user's emotional state, sometimes resulting in the presentation of inappropriate information. In particular, content distribution services are required to provide content that matches the user's current emotional state, but presenting appropriate search results based on emotion remains a challenge.

[0186] 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.

[0187] In this invention, the server includes means for analyzing the search terms entered by the user and breaking them down into their constituent elements, means for generating an emotional score and identifying attributes based on attribute information, and means for analyzing the user's emotional state in real time. This makes it possible to select and provide the user with the most suitable content based on the user's current emotional state.

[0188] A "search term" is a keyword or phrase that a user enters to find information.

[0189] "Components" are individual elements or parts obtained by analyzing a search term.

[0190] "Evaluation information" refers to data that represents the characteristics and quality related to information assets.

[0191] "Attribute information" refers to data defined by the characteristics and features associated with an information asset.

[0192] An "emotion score" is an evaluation metric that quantifies a user's emotional state.

[0193] "Biometric information" refers to data about the user's body, such as heart rate and facial expressions.

[0194] A "sensor" is a device that acquires physical data, and in this context, it is used to collect biological information.

[0195] "Information assets" refer to digital content and information provided to users as search results.

[0196] "Real-time" refers to a situation where processing or reactions occur almost instantly.

[0197] "Content" refers to media and information provided to users, such as movies and TV dramas.

[0198] This invention is a system comprising a user terminal, a server, and biometric sensors. The user inputs a specific search term via the terminal, and the system analyzes it. The analysis breaks down the search term into its constituent elements and collects relevant evaluation and attribute information. An emotion score is generated from the collected information, and the user's emotional state is analyzed in real time based on data obtained from the user's biometric information. Sensors used include those that measure heart rate and facial expressions, such as cameras and heart rate sensors.

[0199] The server selects information assets based on the user's sentiment score and attribute information, and presents them to the user's device. This makes it possible to provide optimal content that matches the user's current sentiment. The server uses natural language processing technology to analyze its components. Content selection is achieved by narrowing down the information based on the sentiment score and attribute information.

[0200] For example, if a user inputs "comedy movie" and the emotion engine analyzes that the user is "feeling stressed," it will prioritize recommending comedy movies that have a stress-reducing effect. An example of a prompt to input into the generative AI model is, "When the user's emotional state is stressed, please suggest a relaxing movie."

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] The user enters a search term using the terminal. The search term represents a genre of interest, such as "comedy movies." This input serves as the starting point for the next processing step.

[0204] Step 2:

[0205] The terminal sends the entered search term to the server. The server receives the search term and uses natural language processing technology to break it down into its constituent elements. This process performs semantic analysis of the term, forming a foundation for a more detailed understanding of the user's intent.

[0206] Step 3:

[0207] The server collects relevant evaluation and attribute information from an external database based on its components. This allows it to gather information on the characteristics and past evaluations of content related to the search terms, which is then used for subsequent processing.

[0208] Step 4:

[0209] The server generates an emotional score using the collected evaluation information. Here, the evaluation information and the user's emotional state are quantified by the generated score. This score is calculated through data processing and is used to select content that matches the user's emotional state.

[0210] Step 5:

[0211] Sensors installed in the user's device collect biometric information in real time and transmit it to a server. Data such as heart rate and facial expressions are used for emotion analysis. This input clarifies the user's emotional state.

[0212] Step 6:

[0213] The server analyzes the user's emotional state using a generative AI model based on the acquired biometric information. The analysis results indicate the user's current psychological situation and are used to generate prompt messages.

[0214] Step 7:

[0215] The server selects information assets based on emotion scores and emotion analysis results obtained from biometric information. Appropriate data processing and filtering are performed to determine the most suitable recommended content for the user's state.

[0216] Step 8:

[0217] The selected information assets are displayed on the user's device. The user can view content optimized for their current emotions. For example, if stress is detected, a comedy movie with stress-reducing effects will be recommended.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] [Second Embodiment]

[0222] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0223] 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.

[0224] 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).

[0225] 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.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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".

[0234] This invention is a system for users to efficiently search for information assets. This system operates using ambiguous search terms entered by the user through a terminal. When a user searches for information assets, they enter search terms on the terminal.

[0235] The server receives search terms submitted by users and analyzes them using natural language processing techniques. As a result of the analysis, several elements that make up the search terms are identified. Next, the server collects relevant evaluation and attribute information from external databases and APIs based on these elements.

[0236] The server performs sentiment analysis on the collected data and generates a sentiment score for each information asset. Simultaneously, it uses attribute information to check whether the information asset meets specific criteria. Information assets with high sentiment scores or those that meet the attribute criteria are selected and provided to the user.

[0237] The terminal displays a list of relevant information assets received from the server to the user. Based on the displayed information, the user can view details, purchase specific information assets, or browse them. This process allows the user to quickly find the information assets they are looking for.

[0238] For example, if a user enters the search terms "moving story, medical-themed movie," the server analyzes this and identifies its constituent elements: "moving," "medical," and "movie." Next, the server collects evaluation and attribute information based on these elements and calculates an emotional score for each. Then, it identifies movies that are both "moving" and have a "medical-related theme," and presents them to the user's device. The user can then select a movie that interests them from the presented results and view its details.

[0239] The following describes the processing flow.

[0240] Step 1:

[0241] The user enters a search term into the search bar on their device and sends a search request.

[0242] Step 2:

[0243] The server receives the search term sent from the user's terminal. This search term is analyzed by a natural language processing engine, and its constituent elements are extracted. Elements such as "emotional," "medical," and "film" are identified.

[0244] Step 3:

[0245] Based on the identified components, the server collects relevant evaluation and attribute information via external databases and APIs. This collection includes review comments and metadata for each information asset.

[0246] Step 4:

[0247] The server performs sentiment analysis on the collected evaluation information. It analyzes each review comment to calculate a sentiment score and aggregates it for each information asset.

[0248] Step 5:

[0249] The server checks whether each information asset meets the search criteria based on the collected attribute information. It then performs filtering to narrow down the results to "related to medicine" and "movies."

[0250] Step 6:

[0251] The server selects information assets with high sentiment scores and attribute matching rates from the filtered data, and then ranks the results.

[0252] Step 7:

[0253] The server sends the selection results to the user's terminal. The terminal displays the received list of information assets to the user.

[0254] Step 8:

[0255] Users can view details of the information assets presented through their devices, select those that interest them, and purchase or view them.

[0256] (Example 1)

[0257] 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".

[0258] In today's information-saturated world, users find it difficult to quickly and accurately find the information resources they need from the vast amount of data available. Furthermore, there is a need for a system that can provide highly accurate search results even with vague search terms. However, current technology faces the challenge of providing sufficient relevant information in response to vague user input.

[0259] 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.

[0260] In this invention, the server includes means for analyzing a search term entered by a user and breaking it down into meaningful components; means for collecting relevant evaluation information and attribute information from external sources based on the components; and means for generating an emotion index based on the evaluation information collected using emotion analysis technology and identifying attributes that satisfy predetermined conditions based on the attribute information. This makes it possible to quickly and accurately select and provide relevant information resources even when a user enters an ambiguous search term.

[0261] A "search term" is a linguistic keyword that a user enters when searching for information resources.

[0262] A "constituent element" is the smallest meaningful unit obtained as a result of analyzing a search term.

[0263] "Evaluation information" refers to data related to user reviews, scores, and other evaluations of information resources.

[0264] "Attribute information" refers to data about the characteristics of an information resource, such as its properties or category.

[0265] An "emotional index" is a numerical value or indicator that represents the intensity or nature of emotions towards an information resource, generated using emotion analysis techniques.

[0266] An "external information source" refers to an information provider, including external databases and programming interfaces that a server accesses to collect information.

[0267] This invention is a system aimed at efficiently finding the information resources that users are looking for. This system operates based on ambiguous search terms transmitted by the user from their terminal and provides information resources quickly and accurately.

[0268] The server processes the user's search terms received via the terminal. The search terms are broken down into their constituent elements using natural language processing techniques. Specifically, the server uses natural language processing libraries such as SpaCy and Google Cloud NLP API to perform these processes.

[0269] Furthermore, the server collects evaluation and attribute information from external sources based on the identified components. These sources include publicly available databases and programming interfaces. Here, procedures for collecting information are executed using programming languages ​​such as Python.

[0270] The server performs sentiment analysis on the collected data. Using libraries such as TextBlob and NLTK, it calculates sentiment indicators and determines whether the information resources meet predetermined criteria. This process makes it possible to avoid false information and misunderstandings and provide users with useful information.

[0271] For example, if a user enters the search terms "moving stories, medical-themed movies," the server extracts elements such as "moving," "medical," and "movie," and collects and analyzes related information. As a result, a list of relevant movies is displayed on the user's device. This allows the user to quickly find movies that interest them and view their details.

[0272] An example of a prompt to input into the generative AI model would be, "Please recommend movies with inspiring stories and medical themes." This prompt would allow the system to quickly search for relevant movies and recommend titles to the user.

[0273] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0274] Step 1:

[0275] The user accesses the system through a terminal and enters vague search terms into the search field. For example, they might enter the text, "moving stories, medical-themed movies." This entered search term is then output as data sent to the server.

[0276] Step 2:

[0277] The server receives the search term sent from the terminal. Using the received search term as input, it performs analysis using a natural language processing library (e.g., SpaCy or Google Cloud NLP API). Through this analysis, the search term is broken down into components such as "emotional," "medical," and "movie," and these components are output.

[0278] Step 3:

[0279] The server takes the disassembled components as input and accesses external databases and APIs (e.g., publicly available movie database APIs) to collect relevant rating and attribute information. This collection results in outputting data such as movie reviews and attributes of information resources.

[0280] Step 4:

[0281] Using the collected evaluation information as input, the server generates sentiment indicators for each information resource using a sentiment analysis library (e.g., TextBlob or NLTK). As a result of this sentiment analysis, a sentiment score for each information resource is output.

[0282] Step 5:

[0283] The server uses the generated emotion score and the collected attribute information as input to select information resources that meet predetermined conditions (e.g., "moving" and "medical-related"). As a result of this selection process, corresponding movies and other information resources are output.

[0284] Step 6:

[0285] The server organizes the selected information resources in JSON format and sends them to the terminal. The terminal receives this transmitted data and displays it to the user in a list format. The displayed information includes the title, evaluation score, and related attributes.

[0286] Step 7:

[0287] The user selects the information resources of interest from the information resources displayed on the terminal and checks the details. By checking the detailed information, the user can watch the selected movie or conduct further detailed investigations.

[0288] (Application Example 1)

[0289] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0290] In the modern information and communication environment, a huge amount of content is provided, but it is difficult for users to quickly and accurately find the optimal information assets that meet their needs. In such a situation, there is a need for a system that can easily obtain the information that users really want by simply using concise and ambiguous search terms.

[0291] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0292] In this invention, the server includes means for analyzing the search term entered by the user and breaking it down into its constituent elements, means for collecting relevant evaluation information and attribute information based on the constituent elements, and means for generating a sentiment score based on the collected evaluation information and identifying attributes based on the attribute information. This enables the user to efficiently and effectively select the most suitable information assets from their ambiguous search intent, and as a result, to quickly access the expected content.

[0293] A "user" is someone who has the purpose of searching for specific information assets through an information processing system.

[0294] A "search term" is a linguistic expression that a user enters when searching for information assets.

[0295] A "constituent element" is a semantic unit obtained by analyzing a search term, and is a fundamental element that forms the basis of information gathering.

[0296] "Evaluation information" refers to data on past reputation and evaluations of information assets.

[0297] "Attribute information" refers to data that indicates the characteristics and features associated with an information asset.

[0298] An "emotional score" is an index that quantifies the public's emotional tendencies towards information assets.

[0299] "Information assets" is a concept that includes various media such as movies, music, and books that users try to find through searches.

[0300] "Presentation" refers to the act of providing analyzed and selected information assets to users in a visible format.

[0301] A "list" refers to a list of information assets selected based on user evaluations and other factors.

[0302] The present invention relates to a system configured for a user to efficiently search for information assets. In an embodiment, it includes the following configuration.

[0303] The server receives the search term input by the user through the terminal. This search term is decomposed into components by using natural language processing technology. In specific processing, natural language processing libraries such as NLTK or spaCy are used to analyze the search term. As a result, an ambiguous search term such as "want to relax music" is decomposed into components such as "relax" and "music".

[0304] Based on the analyzed components, the server collects relevant evaluation information and attribute information from external information sources. As information sources, various APIs can be considered, for example, Spotify API for music. Based on this data, sentiment scores are generated by sentiment analysis tools (such as TextBlob or VADER Sentiment).

[0305] Based on the generated sentiment scores and attributes, the server selects information assets corresponding to the user's request and presents them to the user's terminal. The presented information assets are sorted based on the user's evaluation and presented as a list. As a result, the user can check the details of the information assets in a form that suits their interests.

[0306] As a specific example, when the user enters "want to relax music" as a search term, the server analyzes this search term, collects music with a related relaxation effect, evaluates the sentiment score, and presents appropriate music to the user as a list. Such a process can flexibly adapt to the user's request by utilizing a generative AI model.

[0307] As an example of a prompt sentence, "The user is looking for music to relax. Please list up music highly related to relaxation." can be considered. In response to such a prompt, the system responds quickly.

[0308] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0309] Step 1:

[0310] The user uses a device to enter search terms and sends them to the server. The entered search terms are vague keywords that include the user's subjective preferences.

[0311] Step 2:

[0312] The server receives the incoming search term and analyzes it using natural language processing. At this stage, libraries such as NLTK and spaCy are used to break down the search term into its constituent elements. The input is the search term, and the output is a list of its constituent elements.

[0313] Step 3:

[0314] The server collects relevant evaluation and attribute information based on the obtained components. This process is performed using external APIs (e.g., various database APIs), resulting in data sets of components as input and evaluation and attribute information as output.

[0315] Step 4:

[0316] The server generates sentiment scores using sentiment analysis tools (such as TextBlob or VADER Sentiment) based on the collected evaluation information. At this stage, the emotional tendencies towards each information asset are quantified, with evaluation information as input and sentiment scores as output.

[0317] Step 5:

[0318] The server selects the information asset that best suits the user's preferences from all candidates based on sentiment scores and attribute information. The input is sentiment scores and attribute information, and the output is a list of the optimal information assets.

[0319] Step 6:

[0320] The selected information assets are presented to the user via the terminal. The user can review the list and view details of the information assets that interest them. The output at this stage is a list of information assets organized in a way that is visible to the user.

[0321] 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.

[0322] This invention provides a more personalized search experience by not only analyzing the search terms entered by the user, but also recognizing the user's emotional state using an emotion engine and incorporating the results into the search process. This system improves user satisfaction by selecting and presenting information assets using not only user input but also the user's emotional data.

[0323] The user enters search terms through the device, and the emotion engine analyzes their current emotional state based on biometric information (such as heart rate and facial expressions) and past input history. Sensors that acquire the user's biometric information in real time are used to analyze the emotional state, thereby quantifying the user's emotional state.

[0324] The server receives this data and analyzes both the search terms and the user's emotional state. First, the search terms are broken down into their constituent parts using natural language processing. Then, the server applies filters that take the user's emotional state into account and collects relevant evaluation and attribute information from an external database. It calculates an emotional score for the evaluation information using sentiment analysis techniques and refines the search criteria based on the collected attribute information.

[0325] As a concrete example, consider a scenario where a user searches for "movies with inspiring stories and medical themes," and the emotion engine determines that the user is currently in an emotional state of wanting to be "encouraged." The server analyzes this information, prioritizes selecting movies that particularly emphasize uplifting elements, and creates a ranking based on emotion scores. This selected list of movies is then sent to the user's device, allowing the user to immediately access information assets that match their current mood.

[0326] By presenting information assets in this way, taking into account the user's emotional state, it becomes possible to provide an experience not found in conventional search systems. This can improve search accuracy and user satisfaction.

[0327] The following describes the processing flow.

[0328] Step 1:

[0329] The user uses their device to enter a specific search term into the search bar and submits a search request.

[0330] Step 2:

[0331] Simultaneously, the emotion engine collects the user's biometric information. This data includes heart rate and facial expression data, and analyzes the user's emotional state in real time.

[0332] Step 3:

[0333] The server processes the search terms and sentiment data received from the user's terminal. First, the search terms are analyzed using natural language processing techniques, and the keywords are broken down into their constituent elements.

[0334] Step 4:

[0335] The server takes into account the user's emotional state, as analyzed by the emotion engine, and sets up filters to prioritize the collection of information related to that emotion.

[0336] Step 5:

[0337] The server uses external databases and APIs to collect relevant evaluation and attribute information based on the analyzed components. In particular, it collects information that best matches the user's current emotional state.

[0338] Step 6:

[0339] The server calculates a sentiment score from the collected evaluation information and filters out potential information assets based on this score.

[0340] Step 7:

[0341] The server ranks information assets based on sentiment scores and attribute matching rates, and identifies content that is appropriate for the user's emotional state.

[0342] Step 8:

[0343] The server lists the selected information assets and sends them to the user's terminal. The terminal receives this information and displays it on the user's screen.

[0344] Step 9:

[0345] Users can view the presented information assets and then check the details of information that interests them, or purchase / view it.

[0346] This entire process allows users to quickly obtain information that matches their current emotional state, not just through simple keyword searches.

[0347] (Example 2)

[0348] 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".

[0349] Traditional search systems only present information based on the user's entered search terms, failing to provide information tailored to the user's emotional state. This results in users not receiving information that matches their current emotional state, leading to a lower level of satisfaction with their search experience.

[0350] 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.

[0351] In this invention, the server includes means for analyzing a search term entered by the user and breaking it down into its constituent elements, means for collecting relevant evaluation information and attribute information based on the constituent elements and the user's emotional state, and means for analyzing the emotional state from the user's biometric information and generating an emotional score considering the results. This makes it possible to select relevant information assets according to the user's emotional state and provide a more personalized search experience.

[0352] A "user" refers to an individual or organization that uses this system to retrieve information.

[0353] A "search term" refers to the words or phrases that a user enters when searching for information.

[0354] "Components" refer to the main words and phrases extracted during the process of analyzing search terms.

[0355] "Emotional state" refers to the user's psychological or emotional state, which is analyzed based on the user's biometric information and past history.

[0356] "Evaluation information" refers to opinions and evaluations related to specific information assets collected from external data storage devices.

[0357] "Attribute information" refers to the characteristics and features associated with an information asset.

[0358] An "emotional score" is a numerical representation of the emotional value of an information asset, calculated while taking into account the user's emotional state.

[0359] "Information assets" refer to a collection of information selected for presentation to users.

[0360] "Natural language processing technology" refers to the techniques and methodologies used to enable computers to understand human language.

[0361] "Emotional analysis technology" refers to technology that analyzes a user's emotional state based on biometric information and text data.

[0362] An "external data storage device" refers to an external database or information system that a system accesses to collect information.

[0363] This invention provides a system that enables personalized information retrieval based on search terms entered by the user. This system operates through the collaborative efforts of the user, terminal, and server.

[0364] The user enters search terms through an interface built into the device. The device utilizes devices such as a heart rate sensor and a facial recognition camera to obtain the user's biometric information. This information is transmitted to the server in real time.

[0365] The server analyzes the received search terms using natural language processing techniques and breaks them down into their constituent elements. It also uses sentiment analysis techniques to analyze the user's emotional state based on biometric information sent from the terminal. This emotional state functions as a filter to select information assets that match the user's search objectives.

[0366] Furthermore, the server collects relevant evaluation and attribute information from an external data storage device based on its components and emotional state. Based on this information, it generates an emotional score and selects the appropriate information assets. The selected information assets are ranked in a way that suits the user's emotional needs and presented to the terminal.

[0367] For example, if a user enters "movies with an emotional story and a medical theme," and the emotion analysis technology determines that the user is in a state of wanting to be encouraged, the server will prioritize selecting movies that particularly emphasize encouraging elements. The list of movies obtained through this selection process will then be quickly provided to the user for viewing.

[0368] An example of a prompt would be: "The emotion engine has analyzed that the user is currently in an emotional state of 'wanting encouragement.' In this state, generate a list of movies that emphasize the encouraging aspect for the search query 'inspirational stories, medical-themed movies.'"

[0369] Thus, the present invention enables information retrieval that takes into account the user's emotional state, providing a more satisfying search experience than before.

[0370] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0371] Step 1:

[0372] The user enters search terms through the terminal. The entered search terms are specific phrases such as "moving stories, medical-themed movies." The terminal sends the search terms to the server and also uses sensors to acquire biometric information such as the user's heart rate and facial expressions. This biometric information is sent to the server as input data to analyze the user's emotional state.

[0373] Step 2:

[0374] The server receives the search term and biometric information. Next, it analyzes the received search term using natural language processing techniques and breaks it down into its constituent elements. In this process, the search term is divided into meaningful words such as "emotional," "story," "medical," and "movie," and these are used as the basis data for analysis. At the same time, the server applies emotion analysis techniques based on the biometric information to determine whether the user is in an emotional state such as "wanting to be encouraged." The result of this determination is an important output value that will influence future search conditions.

[0375] Step 3:

[0376] Based on the analyzed components and emotional states, the server collects relevant evaluation and attribute information from an external data storage device. Specifically, the server sends queries to the database via an API to retrieve evaluation and attribute information. In this process, the evaluation information includes information related to "emotional," "medical," and "encouraging." Data processing is performed on the collected data to calculate an emotional score, yielding important output that can be used as a selection criterion for information assets.

[0377] Step 4:

[0378] The server selects relevant information assets based on sentiment scores and collected attribute information. This process aims to rank the collected movie list based on sentiment scores, placing the content most suitable for users seeking encouragement at the top. This ranking information is output in list format and ready to be presented to the user visually.

[0379] Step 5:

[0380] The server sends the selected information assets to the user's terminal. The terminal displays the received movie list on the screen, allowing the user to select their desired movie. Through this list, the user can browse stories that match their emotional state from the selected movies. This provides a highly satisfying search experience.

[0381] (Application Example 2)

[0382] 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."

[0383] Traditional search systems present information assets based solely on the search terms entered by the user, failing to provide personalized results that take into account the user's emotional state, sometimes resulting in the presentation of inappropriate information. In particular, content distribution services are required to provide content that matches the user's current emotional state, but presenting appropriate search results based on emotion remains a challenge.

[0384] 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.

[0385] In this invention, the server includes means for analyzing the search terms entered by the user and breaking them down into their constituent elements, means for generating an emotional score and identifying attributes based on attribute information, and means for analyzing the user's emotional state in real time. This makes it possible to select and provide the user with the most suitable content based on the user's current emotional state.

[0386] A "search term" is a keyword or phrase that a user enters to find information.

[0387] "Components" are individual elements or parts obtained by analyzing a search term.

[0388] "Evaluation information" refers to data that represents the characteristics and quality related to information assets.

[0389] "Attribute information" refers to data defined by the characteristics and features associated with an information asset.

[0390] An "emotion score" is an evaluation metric that quantifies a user's emotional state.

[0391] "Biometric information" refers to data about the user's body, such as heart rate and facial expressions.

[0392] A "sensor" is a device that acquires physical data, and in this context, it is used to collect biological information.

[0393] "Information assets" refer to digital content and information provided to users as search results.

[0394] "Real-time" refers to a situation where processing or reactions occur almost instantly.

[0395] "Content" refers to media and information provided to users, such as movies and TV dramas.

[0396] This invention is a system comprising a user terminal, a server, and biometric sensors. The user inputs a specific search term via the terminal, and the system analyzes it. The analysis breaks down the search term into its constituent elements and collects relevant evaluation and attribute information. An emotion score is generated from the collected information, and the user's emotional state is analyzed in real time based on data obtained from the user's biometric information. Sensors used include those that measure heart rate and facial expressions, such as cameras and heart rate sensors.

[0397] The server selects information assets based on the user's sentiment score and attribute information, and presents them to the user's device. This makes it possible to provide optimal content that matches the user's current sentiment. The server uses natural language processing technology to analyze its components. Content selection is achieved by narrowing down the information based on the sentiment score and attribute information.

[0398] For example, if a user inputs "comedy movie" and the emotion engine analyzes that the user is "feeling stressed," it will prioritize recommending comedy movies that have a stress-reducing effect. An example of a prompt to input into the generative AI model is, "When the user's emotional state is stressed, please suggest a relaxing movie."

[0399] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0400] Step 1:

[0401] The user enters a search term using the terminal. The search term represents a genre of interest, such as "comedy movies." This input serves as the starting point for the next processing step.

[0402] Step 2:

[0403] The terminal sends the entered search term to the server. The server receives the search term and uses natural language processing technology to break it down into its constituent elements. This process performs semantic analysis of the term, forming a foundation for a more detailed understanding of the user's intent.

[0404] Step 3:

[0405] The server collects relevant evaluation and attribute information from an external database based on its components. This allows it to gather information on the characteristics and past evaluations of content related to the search terms, which is then used for subsequent processing.

[0406] Step 4:

[0407] The server generates an emotional score using the collected evaluation information. Here, the evaluation information and the user's emotional state are quantified by the generated score. This score is calculated through data processing and is used to select content that matches the user's emotional state.

[0408] Step 5:

[0409] Sensors installed in the user's device collect biometric information in real time and transmit it to a server. Data such as heart rate and facial expressions are used for emotion analysis. This input clarifies the user's emotional state.

[0410] Step 6:

[0411] The server analyzes the user's emotional state using a generative AI model based on the acquired biometric information. The analysis results indicate the user's current psychological situation and are used to generate prompt messages.

[0412] Step 7:

[0413] The server selects information assets based on emotion scores and emotion analysis results obtained from biometric information. Appropriate data processing and filtering are performed to determine the most suitable recommended content for the user's state.

[0414] Step 8:

[0415] The selected information assets are displayed on the user's device. The user can view content optimized for their current emotions. For example, if stress is detected, a comedy movie with stress-reducing effects will be recommended.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] [Third Embodiment]

[0420] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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".

[0432] This invention is a system for users to efficiently search for information assets. This system operates using ambiguous search terms entered by the user through a terminal. When a user searches for information assets, they enter search terms on the terminal.

[0433] The server receives search terms submitted by users and analyzes them using natural language processing techniques. As a result of the analysis, several elements that make up the search terms are identified. Next, the server collects relevant evaluation and attribute information from external databases and APIs based on these elements.

[0434] The server performs sentiment analysis on the collected data and generates a sentiment score for each information asset. Simultaneously, it uses attribute information to check whether the information asset meets specific criteria. Information assets with high sentiment scores or those that meet the attribute criteria are selected and provided to the user.

[0435] The terminal displays a list of relevant information assets received from the server to the user. Based on the displayed information, the user can view details, purchase specific information assets, or browse them. This process allows the user to quickly find the information assets they are looking for.

[0436] For example, if a user enters the search terms "moving story, medical-themed movie," the server analyzes this and identifies its constituent elements: "moving," "medical," and "movie." Next, the server collects evaluation and attribute information based on these elements and calculates an emotional score for each. Then, it identifies movies that are both "moving" and have a "medical-related theme," and presents them to the user's device. The user can then select a movie that interests them from the presented results and view its details.

[0437] The following describes the processing flow.

[0438] Step 1:

[0439] The user enters a search term into the search bar on their device and sends a search request.

[0440] Step 2:

[0441] The server receives the search term sent from the user's terminal. This search term is analyzed by a natural language processing engine, and its constituent elements are extracted. Elements such as "emotional," "medical," and "film" are identified.

[0442] Step 3:

[0443] Based on the identified components, the server collects relevant evaluation and attribute information via external databases and APIs. This collection includes review comments and metadata for each information asset.

[0444] Step 4:

[0445] The server performs sentiment analysis on the collected evaluation information. It analyzes each review comment to calculate a sentiment score and aggregates it for each information asset.

[0446] Step 5:

[0447] The server checks whether each information asset meets the search criteria based on the collected attribute information. It then performs filtering to narrow down the results to "related to medicine" and "movies."

[0448] Step 6:

[0449] The server selects information assets with high sentiment scores and attribute matching rates from the filtered data, and then ranks the results.

[0450] Step 7:

[0451] The server sends the selection results to the user's terminal. The terminal displays the received list of information assets to the user.

[0452] Step 8:

[0453] Users can view details of the information assets presented through their devices, select those that interest them, and purchase or view them.

[0454] (Example 1)

[0455] 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."

[0456] In today's information-saturated world, users find it difficult to quickly and accurately find the information resources they need from the vast amount of data available. Furthermore, there is a need for a system that can provide highly accurate search results even with vague search terms. However, current technology faces the challenge of providing sufficient relevant information in response to vague user input.

[0457] 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.

[0458] In this invention, the server includes means for analyzing a search term entered by a user and breaking it down into meaningful components; means for collecting relevant evaluation information and attribute information from external sources based on the components; and means for generating an emotion index based on the evaluation information collected using emotion analysis technology and identifying attributes that satisfy predetermined conditions based on the attribute information. This makes it possible to quickly and accurately select and provide relevant information resources even when a user enters an ambiguous search term.

[0459] A "search term" is a linguistic keyword that a user enters when searching for information resources.

[0460] A "constituent element" is the smallest meaningful unit obtained as a result of analyzing a search term.

[0461] "Evaluation information" refers to data related to user reviews, scores, and other evaluations of information resources.

[0462] "Attribute information" refers to data about the characteristics of an information resource, such as its properties or category.

[0463] An "emotional index" is a numerical value or indicator that represents the intensity or nature of emotions towards an information resource, generated using emotion analysis techniques.

[0464] An "external information source" refers to an information provider, including external databases and programming interfaces that a server accesses to collect information.

[0465] This invention is a system aimed at efficiently finding the information resources that users are looking for. This system operates based on ambiguous search terms transmitted by the user from their terminal and provides information resources quickly and accurately.

[0466] The server processes the user's search terms received via the terminal. The search terms are broken down into their constituent elements using natural language processing techniques. Specifically, the server uses natural language processing libraries such as SpaCy and Google Cloud NLP API to perform these processes.

[0467] Furthermore, the server collects evaluation and attribute information from external sources based on the identified components. These sources include publicly available databases and programming interfaces. Here, procedures for collecting information are executed using programming languages ​​such as Python.

[0468] The server performs sentiment analysis on the collected data. Using libraries such as TextBlob and NLTK, it calculates sentiment indicators and determines whether the information resources meet predetermined criteria. This process makes it possible to avoid false information and misunderstandings and provide users with useful information.

[0469] For example, if a user enters the search terms "moving stories, medical-themed movies," the server extracts elements such as "moving," "medical," and "movie," and collects and analyzes related information. As a result, a list of relevant movies is displayed on the user's device. This allows the user to quickly find movies that interest them and view their details.

[0470] An example of a prompt to input into the generative AI model would be, "Please recommend movies with inspiring stories and medical themes." This prompt would allow the system to quickly search for relevant movies and recommend titles to the user.

[0471] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0472] Step 1:

[0473] The user accesses the system through a terminal and enters vague search terms into the search field. For example, they might enter the text, "moving stories, medical-themed movies." This entered search term is then output as data sent to the server.

[0474] Step 2:

[0475] The server receives the search term sent from the terminal. Using the received search term as input, it performs analysis using a natural language processing library (e.g., SpaCy or Google Cloud NLP API). Through this analysis, the search term is broken down into components such as "emotional," "medical," and "movie," and these components are output.

[0476] Step 3:

[0477] The server takes the disassembled components as input and accesses external databases and APIs (e.g., publicly available movie database APIs) to collect relevant rating and attribute information. This collection results in outputting data such as movie reviews and attributes of information resources.

[0478] Step 4:

[0479] Using the collected evaluation information as input, the server generates sentiment indicators for each information resource using a sentiment analysis library (e.g., TextBlob or NLTK). As a result of this sentiment analysis, a sentiment score for each information resource is output.

[0480] Step 5:

[0481] The server uses the generated emotion score and collected attribute information as input to select information resources that meet predetermined conditions (e.g., "emotional" and "medical-related"). As a result of this selection process, the relevant movies and other information resources are output.

[0482] Step 6:

[0483] The server organizes the selected information resources in JSON format and sends them to the terminal. The terminal receives this data and displays it to the user in a list format. The displayed information includes the title, evaluation score, and related attributes.

[0484] Step 7:

[0485] Users select information resources that interest them from those displayed on their device and view their details. After viewing the details, users can either watch the selected movie or conduct further research.

[0486] (Application Example 1)

[0487] 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."

[0488] In today's information and communication environment, a vast amount of content is available, but it is difficult for users to quickly and accurately find the optimal information assets that meet their needs. In this situation, there is a need for a system that allows users to easily obtain the information they truly want simply by using concise and vague search terms.

[0489] 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.

[0490] In this invention, the server includes means for analyzing the search term entered by the user and breaking it down into its constituent elements, means for collecting relevant evaluation information and attribute information based on the constituent elements, and means for generating a sentiment score based on the collected evaluation information and identifying attributes based on the attribute information. This enables the user to efficiently and effectively select the most suitable information assets from their ambiguous search intent, and as a result, to quickly access the expected content.

[0491] A "user" is someone who has the purpose of searching for specific information assets through an information processing system.

[0492] A "search term" is a linguistic expression that a user enters when searching for information assets.

[0493] A "constituent element" is a semantic unit obtained by analyzing a search term, and is a fundamental element that forms the basis of information gathering.

[0494] "Evaluation information" refers to data on past reputation and evaluations of information assets.

[0495] "Attribute information" refers to data that indicates the characteristics and features associated with an information asset.

[0496] An "emotional score" is an index that quantifies the public's emotional tendencies towards information assets.

[0497] "Information assets" is a concept that includes various media such as movies, music, and books that users try to find through searches.

[0498] "Presentation" refers to the act of providing analyzed and selected information assets to users in a visible format.

[0499] A "list" refers to a list of information assets selected based on user evaluations and other factors.

[0500] The present invention relates to a system configured for users to efficiently search for information assets. Embodiments include the following configurations:

[0501] The server receives search terms entered by the user through the terminal. These search terms are broken down into their constituent elements using natural language processing techniques. Specifically, natural language processing libraries such as NLTK and spaCy are used to analyze the search terms. This allows for the breakdown of vague search terms, such as "I want to relax music," into constituent elements like "relax" and "music."

[0502] Based on the analyzed components, the server collects relevant evaluation and attribute information from external sources. These sources could include various APIs, such as the Spotify API for music. Based on this data, a sentiment analysis tool (such as TextBlob or VADER Sentiment) generates a sentiment score.

[0503] Based on the generated sentiment score and attributes, the server selects information assets that meet the user's request and presents them to the user's device. The presented information assets are organized based on the user's evaluation and presented as a list. This allows the user to view details of the information assets in a way that aligns with their interests.

[0504] For example, if a user enters "music to relax" as a search term, the server analyzes this search term, collects relevant music with relaxing effects, evaluates the emotional score, and presents the user with a list of appropriate music. This process can be adapted more flexibly to user requests by utilizing generative AI models.

[0505] An example of a prompt might be, "The user is looking for music to help them relax. Please list music that is highly related to relaxation." The system should respond quickly to such prompts.

[0506] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0507] Step 1:

[0508] The user uses a device to enter search terms and sends them to the server. The entered search terms are vague keywords that include the user's subjective preferences.

[0509] Step 2:

[0510] The server receives the incoming search term and analyzes it using natural language processing. At this stage, libraries such as NLTK and spaCy are used to break down the search term into its constituent elements. The input is the search term, and the output is a list of its constituent elements.

[0511] Step 3:

[0512] The server collects relevant evaluation and attribute information based on the obtained components. This process is performed using external APIs (e.g., various database APIs), resulting in data sets of components as input and evaluation and attribute information as output.

[0513] Step 4:

[0514] The server generates sentiment scores using sentiment analysis tools (such as TextBlob or VADER Sentiment) based on the collected evaluation information. At this stage, the emotional tendencies towards each information asset are quantified, with evaluation information as input and sentiment scores as output.

[0515] Step 5:

[0516] The server selects the information asset that best suits the user's preferences from all candidates based on sentiment scores and attribute information. The input is sentiment scores and attribute information, and the output is a list of the optimal information assets.

[0517] Step 6:

[0518] The selected information assets are presented to the user via the terminal. The user can review the list and view details of the information assets that interest them. The output at this stage is a list of information assets organized in a way that is visible to the user.

[0519] 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.

[0520] This invention provides a more personalized search experience by not only analyzing the search terms entered by the user, but also recognizing the user's emotional state using an emotion engine and incorporating the results into the search process. This system improves user satisfaction by selecting and presenting information assets using not only user input but also the user's emotional data.

[0521] The user enters search terms through the device, and the emotion engine analyzes their current emotional state based on biometric information (such as heart rate and facial expressions) and past input history. Sensors that acquire the user's biometric information in real time are used to analyze the emotional state, thereby quantifying the user's emotional state.

[0522] The server receives this data and analyzes both the search terms and the user's emotional state. First, the search terms are broken down into their constituent parts using natural language processing. Then, the server applies filters that take the user's emotional state into account and collects relevant evaluation and attribute information from an external database. It calculates an emotional score for the evaluation information using sentiment analysis techniques and refines the search criteria based on the collected attribute information.

[0523] As a concrete example, consider a scenario where a user searches for "movies with inspiring stories and medical themes," and the emotion engine determines that the user is currently in an emotional state of wanting to be "encouraged." The server analyzes this information, prioritizes selecting movies that particularly emphasize uplifting elements, and creates a ranking based on emotion scores. This selected list of movies is then sent to the user's device, allowing the user to immediately access information assets that match their current mood.

[0524] By presenting information assets in this way, taking into account the user's emotional state, it becomes possible to provide an experience not found in conventional search systems. This can improve search accuracy and user satisfaction.

[0525] The following describes the processing flow.

[0526] Step 1:

[0527] The user uses their device to enter a specific search term into the search bar and submits a search request.

[0528] Step 2:

[0529] Simultaneously, the emotion engine collects the user's biometric information. This data includes heart rate and facial expression data, and analyzes the user's emotional state in real time.

[0530] Step 3:

[0531] The server processes the search terms and sentiment data received from the user's terminal. First, the search terms are analyzed using natural language processing techniques, and the keywords are broken down into their constituent elements.

[0532] Step 4:

[0533] The server takes into account the user's emotional state, as analyzed by the emotion engine, and sets up filters to prioritize the collection of information related to that emotion.

[0534] Step 5:

[0535] The server uses external databases and APIs to collect relevant evaluation and attribute information based on the analyzed components. In particular, it collects information that best matches the user's current emotional state.

[0536] Step 6:

[0537] The server calculates a sentiment score from the collected evaluation information and filters out potential information assets based on this score.

[0538] Step 7:

[0539] The server ranks information assets based on sentiment scores and attribute matching rates, and identifies content that is appropriate for the user's emotional state.

[0540] Step 8:

[0541] The server lists the selected information assets and sends them to the user's terminal. The terminal receives this information and displays it on the user's screen.

[0542] Step 9:

[0543] Users can view the presented information assets and then check the details of information that interests them, or purchase / view it.

[0544] This entire process allows users to quickly obtain information that matches their current emotional state, not just through simple keyword searches.

[0545] (Example 2)

[0546] 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."

[0547] Traditional search systems only present information based on the user's entered search terms, failing to provide information tailored to the user's emotional state. This results in users not receiving information that matches their current emotional state, leading to a lower level of satisfaction with their search experience.

[0548] 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.

[0549] In this invention, the server includes means for analyzing a search term entered by the user and breaking it down into its constituent elements, means for collecting relevant evaluation information and attribute information based on the constituent elements and the user's emotional state, and means for analyzing the emotional state from the user's biometric information and generating an emotional score considering the results. This makes it possible to select relevant information assets according to the user's emotional state and provide a more personalized search experience.

[0550] A "user" refers to an individual or organization that uses this system to retrieve information.

[0551] A "search term" refers to the words or phrases that a user enters when searching for information.

[0552] "Components" refer to the main words and phrases extracted during the process of analyzing search terms.

[0553] "Emotional state" refers to the user's psychological or emotional state, which is analyzed based on the user's biometric information and past history.

[0554] "Evaluation information" refers to opinions and evaluations related to specific information assets collected from external data storage devices.

[0555] "Attribute information" refers to the characteristics and features associated with an information asset.

[0556] An "emotional score" is a numerical representation of the emotional value of an information asset, calculated while taking into account the user's emotional state.

[0557] "Information assets" refer to a collection of information selected for presentation to users.

[0558] "Natural language processing technology" refers to the techniques and methodologies used to enable computers to understand human language.

[0559] "Emotional analysis technology" refers to technology that analyzes a user's emotional state based on biometric information and text data.

[0560] An "external data storage device" refers to an external database or information system that a system accesses to collect information.

[0561] This invention provides a system that enables personalized information retrieval based on search terms entered by the user. This system operates through the collaborative efforts of the user, terminal, and server.

[0562] The user enters search terms through an interface built into the device. The device utilizes devices such as a heart rate sensor and a facial recognition camera to obtain the user's biometric information. This information is transmitted to the server in real time.

[0563] The server analyzes the received search terms using natural language processing techniques and breaks them down into their constituent elements. It also uses sentiment analysis techniques to analyze the user's emotional state based on biometric information sent from the terminal. This emotional state functions as a filter to select information assets that match the user's search objectives.

[0564] Furthermore, the server collects relevant evaluation and attribute information from an external data storage device based on its components and emotional state. Based on this information, it generates an emotional score and selects the appropriate information assets. The selected information assets are ranked in a way that suits the user's emotional needs and presented to the terminal.

[0565] For example, if a user enters "movies with an emotional story and a medical theme," and the emotion analysis technology determines that the user is in a state of wanting to be encouraged, the server will prioritize selecting movies that particularly emphasize encouraging elements. The list of movies obtained through this selection process will then be quickly provided to the user for viewing.

[0566] An example of a prompt would be: "The emotion engine has analyzed that the user is currently in an emotional state of 'wanting encouragement.' In this state, generate a list of movies that emphasize the encouraging aspect for the search query 'inspirational stories, medical-themed movies.'"

[0567] Thus, the present invention enables information retrieval that takes into account the user's emotional state, providing a more satisfying search experience than before.

[0568] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0569] Step 1:

[0570] The user enters search terms through the terminal. The entered search terms are specific phrases such as "moving stories, medical-themed movies." The terminal sends the search terms to the server and also uses sensors to acquire biometric information such as the user's heart rate and facial expressions. This biometric information is sent to the server as input data to analyze the user's emotional state.

[0571] Step 2:

[0572] The server receives the search term and biometric information. Next, it analyzes the received search term using natural language processing techniques and breaks it down into its constituent elements. In this process, the search term is divided into meaningful words such as "emotional," "story," "medical," and "movie," and these are used as the basis data for analysis. At the same time, the server applies emotion analysis techniques based on the biometric information to determine whether the user is in an emotional state such as "wanting to be encouraged." The result of this determination is an important output value that will influence future search conditions.

[0573] Step 3:

[0574] Based on the analyzed components and emotional states, the server collects relevant evaluation and attribute information from an external data storage device. Specifically, the server sends queries to the database via an API to retrieve evaluation and attribute information. In this process, the evaluation information includes information related to "emotional," "medical," and "encouraging." Data processing is performed on the collected data to calculate an emotional score, yielding important output that can be used as a selection criterion for information assets.

[0575] Step 4:

[0576] The server selects relevant information assets based on sentiment scores and collected attribute information. This process aims to rank the collected movie list based on sentiment scores, placing the content most suitable for users seeking encouragement at the top. This ranking information is output in list format and ready to be presented to the user visually.

[0577] Step 5:

[0578] The server sends the selected information assets to the user's terminal. The terminal displays the received movie list on the screen, allowing the user to select their desired movie. Through this list, the user can browse stories that match their emotional state from the selected movies. This provides a highly satisfying search experience.

[0579] (Application Example 2)

[0580] 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."

[0581] Traditional search systems present information assets based solely on the search terms entered by the user, failing to provide personalized results that take into account the user's emotional state, sometimes resulting in the presentation of inappropriate information. In particular, content distribution services are required to provide content that matches the user's current emotional state, but presenting appropriate search results based on emotion remains a challenge.

[0582] 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.

[0583] In this invention, the server includes means for analyzing the search terms entered by the user and breaking them down into their constituent elements, means for generating an emotional score and identifying attributes based on attribute information, and means for analyzing the user's emotional state in real time. This makes it possible to select and provide the user with the most suitable content based on the user's current emotional state.

[0584] A "search term" is a keyword or phrase that a user enters to find information.

[0585] "Components" are individual elements or parts obtained by analyzing a search term.

[0586] "Evaluation information" refers to data that represents the characteristics and quality related to information assets.

[0587] "Attribute information" refers to data defined by the characteristics and features associated with an information asset.

[0588] An "emotion score" is an evaluation metric that quantifies a user's emotional state.

[0589] "Biometric information" refers to data about the user's body, such as heart rate and facial expressions.

[0590] A "sensor" is a device that acquires physical data, and in this context, it is used to collect biological information.

[0591] "Information assets" refer to digital content and information provided to users as search results.

[0592] "Real-time" refers to a situation where processing or reactions occur almost instantly.

[0593] "Content" refers to media and information provided to users, such as movies and TV dramas.

[0594] This invention is a system comprising a user terminal, a server, and biometric sensors. The user inputs a specific search term via the terminal, and the system analyzes it. The analysis breaks down the search term into its constituent elements and collects relevant evaluation and attribute information. An emotion score is generated from the collected information, and the user's emotional state is analyzed in real time based on data obtained from the user's biometric information. Sensors used include those that measure heart rate and facial expressions, such as cameras and heart rate sensors.

[0595] The server selects information assets based on the user's sentiment score and attribute information, and presents them to the user's device. This makes it possible to provide optimal content that matches the user's current sentiment. The server uses natural language processing technology to analyze its components. Content selection is achieved by narrowing down the information based on the sentiment score and attribute information.

[0596] For example, if a user inputs "comedy movie" and the emotion engine analyzes that the user is "feeling stressed," it will prioritize recommending comedy movies that have a stress-reducing effect. An example of a prompt to input into the generative AI model is, "When the user's emotional state is stressed, please suggest a relaxing movie."

[0597] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0598] Step 1:

[0599] The user enters a search term using the terminal. The search term represents a genre of interest, such as "comedy movies." This input serves as the starting point for the next processing step.

[0600] Step 2:

[0601] The terminal sends the entered search term to the server. The server receives the search term and uses natural language processing technology to break it down into its constituent elements. This process performs semantic analysis of the term, forming a foundation for a more detailed understanding of the user's intent.

[0602] Step 3:

[0603] The server collects relevant evaluation and attribute information from an external database based on its components. This allows it to gather information on the characteristics and past evaluations of content related to the search terms, which is then used for subsequent processing.

[0604] Step 4:

[0605] The server generates an emotional score using the collected evaluation information. Here, the evaluation information and the user's emotional state are quantified by the generated score. This score is calculated through data processing and is used to select content that matches the user's emotional state.

[0606] Step 5:

[0607] Sensors installed in the user's device collect biometric information in real time and transmit it to a server. Data such as heart rate and facial expressions are used for emotion analysis. This input clarifies the user's emotional state.

[0608] Step 6:

[0609] The server analyzes the user's emotional state using a generative AI model based on the acquired biometric information. The analysis results indicate the user's current psychological situation and are used to generate prompt messages.

[0610] Step 7:

[0611] The server selects information assets based on emotion scores and emotion analysis results obtained from biometric information. Appropriate data processing and filtering are performed to determine the most suitable recommended content for the user's state.

[0612] Step 8:

[0613] The selected information assets are displayed on the user's device. The user can view content optimized for their current emotions. For example, if stress is detected, a comedy movie with stress-reducing effects will be recommended.

[0614] 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.

[0615] 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.

[0616] 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.

[0617] [Fourth Embodiment]

[0618] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0619] 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.

[0620] 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).

[0621] 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.

[0622] 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.

[0623] 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).

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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".

[0631] This invention is a system for users to efficiently search for information assets. This system operates using ambiguous search terms entered by the user through a terminal. When a user searches for information assets, they enter search terms on the terminal.

[0632] The server receives search terms submitted by users and analyzes them using natural language processing techniques. As a result of the analysis, several elements that make up the search terms are identified. Next, the server collects relevant evaluation and attribute information from external databases and APIs based on these elements.

[0633] The server performs sentiment analysis on the collected data and generates a sentiment score for each information asset. Simultaneously, it uses attribute information to check whether the information asset meets specific criteria. Information assets with high sentiment scores or those that meet the attribute criteria are selected and provided to the user.

[0634] The terminal displays a list of relevant information assets received from the server to the user. Based on the displayed information, the user can view details, purchase specific information assets, or browse them. This process allows the user to quickly find the information assets they are looking for.

[0635] For example, if a user enters the search terms "moving story, medical-themed movie," the server analyzes this and identifies its constituent elements: "moving," "medical," and "movie." Next, the server collects evaluation and attribute information based on these elements and calculates an emotional score for each. Then, it identifies movies that are both "moving" and have a "medical-related theme," and presents them to the user's device. The user can then select a movie that interests them from the presented results and view its details.

[0636] The following describes the processing flow.

[0637] Step 1:

[0638] The user enters a search term into the search bar on their device and sends a search request.

[0639] Step 2:

[0640] The server receives the search term sent from the user's terminal. This search term is analyzed by a natural language processing engine, and its constituent elements are extracted. Elements such as "emotional," "medical," and "film" are identified.

[0641] Step 3:

[0642] Based on the identified components, the server collects relevant evaluation and attribute information via external databases and APIs. This collection includes review comments and metadata for each information asset.

[0643] Step 4:

[0644] The server performs sentiment analysis on the collected evaluation information. It analyzes each review comment to calculate a sentiment score and aggregates it for each information asset.

[0645] Step 5:

[0646] The server checks whether each information asset meets the search criteria based on the collected attribute information. It then performs filtering to narrow down the results to "related to medicine" and "movies."

[0647] Step 6:

[0648] The server selects information assets with high sentiment scores and attribute matching rates from the filtered data, and then ranks the results.

[0649] Step 7:

[0650] The server sends the selection results to the user's terminal. The terminal displays the received list of information assets to the user.

[0651] Step 8:

[0652] Users can view details of the information assets presented through their devices, select those that interest them, and purchase or view them.

[0653] (Example 1)

[0654] 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".

[0655] In today's information-saturated world, users find it difficult to quickly and accurately find the information resources they need from the vast amount of data available. Furthermore, there is a need for a system that can provide highly accurate search results even with vague search terms. However, current technology faces the challenge of providing sufficient relevant information in response to vague user input.

[0656] 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.

[0657] In this invention, the server includes means for analyzing a search term entered by a user and breaking it down into meaningful components; means for collecting relevant evaluation information and attribute information from external sources based on the components; and means for generating an emotion index based on the evaluation information collected using emotion analysis technology and identifying attributes that satisfy predetermined conditions based on the attribute information. This makes it possible to quickly and accurately select and provide relevant information resources even when a user enters an ambiguous search term.

[0658] A "search term" is a linguistic keyword that a user enters when searching for information resources.

[0659] A "constituent element" is the smallest meaningful unit obtained as a result of analyzing a search term.

[0660] "Evaluation information" refers to data related to user reviews, scores, and other evaluations of information resources.

[0661] "Attribute information" refers to data about the characteristics of an information resource, such as its properties or category.

[0662] An "emotional index" is a numerical value or indicator that represents the intensity or nature of emotions towards an information resource, generated using emotion analysis techniques.

[0663] An "external information source" refers to an information provider, including external databases and programming interfaces that a server accesses to collect information.

[0664] This invention is a system aimed at efficiently finding the information resources that users are looking for. This system operates based on ambiguous search terms transmitted by the user from their terminal and provides information resources quickly and accurately.

[0665] The server processes the user's search terms received via the terminal. The search terms are broken down into their constituent elements using natural language processing techniques. Specifically, the server uses natural language processing libraries such as SpaCy and Google Cloud NLP API to perform these processes.

[0666] Furthermore, the server collects evaluation and attribute information from external sources based on the identified components. These sources include publicly available databases and programming interfaces. Here, procedures for collecting information are executed using programming languages ​​such as Python.

[0667] The server performs sentiment analysis on the collected data. Using libraries such as TextBlob and NLTK, it calculates sentiment indicators and determines whether the information resources meet predetermined criteria. This process makes it possible to avoid false information and misunderstandings and provide users with useful information.

[0668] For example, if a user enters the search terms "moving stories, medical-themed movies," the server extracts elements such as "moving," "medical," and "movie," and collects and analyzes related information. As a result, a list of relevant movies is displayed on the user's device. This allows the user to quickly find movies that interest them and view their details.

[0669] An example of a prompt to input into the generative AI model would be, "Please recommend movies with inspiring stories and medical themes." This prompt would allow the system to quickly search for relevant movies and recommend titles to the user.

[0670] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0671] Step 1:

[0672] The user accesses the system through a terminal and enters vague search terms into the search field. For example, they might enter the text, "moving stories, medical-themed movies." This entered search term is then output as data sent to the server.

[0673] Step 2:

[0674] The server receives the search term sent from the terminal. Using the received search term as input, it performs analysis using a natural language processing library (e.g., SpaCy or Google Cloud NLP API). Through this analysis, the search term is broken down into components such as "emotional," "medical," and "movie," and these components are output.

[0675] Step 3:

[0676] The server takes the disassembled components as input and accesses external databases and APIs (e.g., publicly available movie database APIs) to collect relevant rating and attribute information. This collection results in outputting data such as movie reviews and attributes of information resources.

[0677] Step 4:

[0678] Using the collected evaluation information as input, the server generates sentiment indicators for each information resource using a sentiment analysis library (e.g., TextBlob or NLTK). As a result of this sentiment analysis, a sentiment score for each information resource is output.

[0679] Step 5:

[0680] The server uses the generated emotion score and collected attribute information as input to select information resources that meet predetermined conditions (e.g., "emotional" and "medical-related"). As a result of this selection process, the relevant movies and other information resources are output.

[0681] Step 6:

[0682] The server organizes the selected information resources in JSON format and sends them to the terminal. The terminal receives this data and displays it to the user in a list format. The displayed information includes the title, evaluation score, and related attributes.

[0683] Step 7:

[0684] Users select information resources that interest them from those displayed on their device and view their details. After viewing the details, users can either watch the selected movie or conduct further research.

[0685] (Application Example 1)

[0686] 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".

[0687] In today's information and communication environment, a vast amount of content is available, but it is difficult for users to quickly and accurately find the optimal information assets that meet their needs. In this situation, there is a need for a system that allows users to easily obtain the information they truly want simply by using concise and vague search terms.

[0688] 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.

[0689] In this invention, the server includes means for analyzing the search term entered by the user and breaking it down into its constituent elements, means for collecting relevant evaluation information and attribute information based on the constituent elements, and means for generating a sentiment score based on the collected evaluation information and identifying attributes based on the attribute information. This enables the user to efficiently and effectively select the most suitable information assets from their ambiguous search intent, and as a result, to quickly access the expected content.

[0690] A "user" is someone who has the purpose of searching for specific information assets through an information processing system.

[0691] A "search term" is a linguistic expression that a user enters when searching for information assets.

[0692] A "constituent element" is a semantic unit obtained by analyzing a search term, and is a fundamental element that forms the basis of information gathering.

[0693] "Evaluation information" refers to data on past reputation and evaluations of information assets.

[0694] "Attribute information" refers to data that indicates the characteristics and features associated with an information asset.

[0695] An "emotional score" is an index that quantifies the public's emotional tendencies towards information assets.

[0696] "Information assets" is a concept that includes various media such as movies, music, and books that users try to find through searches.

[0697] "Presentation" refers to the act of providing analyzed and selected information assets to users in a visible format.

[0698] A "list" refers to a list of information assets selected based on user evaluations and other factors.

[0699] The present invention relates to a system configured for users to efficiently search for information assets. Embodiments include the following configurations:

[0700] The server receives search terms entered by the user through the terminal. These search terms are broken down into their constituent elements using natural language processing techniques. Specifically, natural language processing libraries such as NLTK and spaCy are used to analyze the search terms. This allows for the breakdown of vague search terms, such as "I want to relax music," into constituent elements like "relax" and "music."

[0701] Based on the analyzed components, the server collects relevant evaluation and attribute information from external sources. These sources could include various APIs, such as the Spotify API for music. Based on this data, a sentiment analysis tool (such as TextBlob or VADER Sentiment) generates a sentiment score.

[0702] Based on the generated sentiment score and attributes, the server selects information assets that meet the user's request and presents them to the user's device. The presented information assets are organized based on the user's evaluation and presented as a list. This allows the user to view details of the information assets in a way that aligns with their interests.

[0703] For example, if a user enters "music to relax" as a search term, the server analyzes this search term, collects relevant music with relaxing effects, evaluates the emotional score, and presents the user with a list of appropriate music. This process can be adapted more flexibly to user requests by utilizing generative AI models.

[0704] An example of a prompt might be, "The user is looking for music to help them relax. Please list music that is highly related to relaxation." The system should respond quickly to such prompts.

[0705] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0706] Step 1:

[0707] The user uses a device to enter search terms and sends them to the server. The entered search terms are vague keywords that include the user's subjective preferences.

[0708] Step 2:

[0709] The server receives the incoming search term and analyzes it using natural language processing. At this stage, libraries such as NLTK and spaCy are used to break down the search term into its constituent elements. The input is the search term, and the output is a list of its constituent elements.

[0710] Step 3:

[0711] The server collects relevant evaluation and attribute information based on the obtained components. This process is performed using external APIs (e.g., various database APIs), resulting in data sets of components as input and evaluation and attribute information as output.

[0712] Step 4:

[0713] The server generates sentiment scores using sentiment analysis tools (such as TextBlob or VADER Sentiment) based on the collected evaluation information. At this stage, the emotional tendencies towards each information asset are quantified, with evaluation information as input and sentiment scores as output.

[0714] Step 5:

[0715] The server selects the information asset that best suits the user's preferences from all candidates based on sentiment scores and attribute information. The input is sentiment scores and attribute information, and the output is a list of the optimal information assets.

[0716] Step 6:

[0717] The selected information assets are presented to the user via the terminal. The user can review the list and view details of the information assets that interest them. The output at this stage is a list of information assets organized in a way that is visible to the user.

[0718] 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.

[0719] This invention provides a more personalized search experience by not only analyzing the search terms entered by the user, but also recognizing the user's emotional state using an emotion engine and incorporating the results into the search process. This system improves user satisfaction by selecting and presenting information assets using not only user input but also the user's emotional data.

[0720] The user enters search terms through the device, and the emotion engine analyzes their current emotional state based on biometric information (such as heart rate and facial expressions) and past input history. Sensors that acquire the user's biometric information in real time are used to analyze the emotional state, thereby quantifying the user's emotional state.

[0721] The server receives this data and analyzes both the search terms and the user's emotional state. First, the search terms are broken down into their constituent parts using natural language processing. Then, the server applies filters that take the user's emotional state into account and collects relevant evaluation and attribute information from an external database. It calculates an emotional score for the evaluation information using sentiment analysis techniques and refines the search criteria based on the collected attribute information.

[0722] As a concrete example, consider a scenario where a user searches for "movies with inspiring stories and medical themes," and the emotion engine determines that the user is currently in an emotional state of wanting to be "encouraged." The server analyzes this information, prioritizes selecting movies that particularly emphasize uplifting elements, and creates a ranking based on emotion scores. This selected list of movies is then sent to the user's device, allowing the user to immediately access information assets that match their current mood.

[0723] By presenting information assets in this way, taking into account the user's emotional state, it becomes possible to provide an experience not found in conventional search systems. This can improve search accuracy and user satisfaction.

[0724] The following describes the processing flow.

[0725] Step 1:

[0726] The user uses their device to enter a specific search term into the search bar and submits a search request.

[0727] Step 2:

[0728] Simultaneously, the emotion engine collects the user's biometric information. This data includes heart rate and facial expression data, and analyzes the user's emotional state in real time.

[0729] Step 3:

[0730] The server processes the search terms and sentiment data received from the user's terminal. First, the search terms are analyzed using natural language processing techniques, and the keywords are broken down into their constituent elements.

[0731] Step 4:

[0732] The server takes into account the user's emotional state, as analyzed by the emotion engine, and sets up filters to prioritize the collection of information related to that emotion.

[0733] Step 5:

[0734] The server uses external databases and APIs to collect relevant evaluation and attribute information based on the analyzed components. In particular, it collects information that best matches the user's current emotional state.

[0735] Step 6:

[0736] The server calculates a sentiment score from the collected evaluation information and filters out potential information assets based on this score.

[0737] Step 7:

[0738] The server ranks information assets based on sentiment scores and attribute matching rates, and identifies content that is appropriate for the user's emotional state.

[0739] Step 8:

[0740] The server lists the selected information assets and sends them to the user's terminal. The terminal receives this information and displays it on the user's screen.

[0741] Step 9:

[0742] Users can view the presented information assets and then check the details of information that interests them, or purchase / view it.

[0743] This entire process allows users to quickly obtain information that matches their current emotional state, not just through simple keyword searches.

[0744] (Example 2)

[0745] 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".

[0746] Traditional search systems only present information based on the user's entered search terms, failing to provide information tailored to the user's emotional state. This results in users not receiving information that matches their current emotional state, leading to a lower level of satisfaction with their search experience.

[0747] 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.

[0748] In this invention, the server includes means for analyzing a search term entered by the user and breaking it down into its constituent elements, means for collecting relevant evaluation information and attribute information based on the constituent elements and the user's emotional state, and means for analyzing the emotional state from the user's biometric information and generating an emotional score considering the results. This makes it possible to select relevant information assets according to the user's emotional state and provide a more personalized search experience.

[0749] A "user" refers to an individual or organization that uses this system to retrieve information.

[0750] A "search term" refers to the words or phrases that a user enters when searching for information.

[0751] "Components" refer to the main words and phrases extracted during the process of analyzing search terms.

[0752] "Emotional state" refers to the user's psychological or emotional state, which is analyzed based on the user's biometric information and past history.

[0753] "Evaluation information" refers to opinions and evaluations related to specific information assets collected from external data storage devices.

[0754] "Attribute information" refers to the characteristics and features associated with an information asset.

[0755] An "emotional score" is a numerical representation of the emotional value of an information asset, calculated while taking into account the user's emotional state.

[0756] "Information assets" refer to a collection of information selected for presentation to users.

[0757] "Natural language processing technology" refers to the techniques and methodologies used to enable computers to understand human language.

[0758] "Emotional analysis technology" refers to technology that analyzes a user's emotional state based on biometric information and text data.

[0759] An "external data storage device" refers to an external database or information system that a system accesses to collect information.

[0760] This invention provides a system that enables personalized information retrieval based on search terms entered by the user. This system operates through the collaborative efforts of the user, terminal, and server.

[0761] The user enters search terms through an interface built into the device. The device utilizes devices such as a heart rate sensor and a facial recognition camera to obtain the user's biometric information. This information is transmitted to the server in real time.

[0762] The server analyzes the received search terms using natural language processing techniques and breaks them down into their constituent elements. It also uses sentiment analysis techniques to analyze the user's emotional state based on biometric information sent from the terminal. This emotional state functions as a filter to select information assets that match the user's search objectives.

[0763] Furthermore, the server collects relevant evaluation and attribute information from an external data storage device based on its components and emotional state. Based on this information, it generates an emotional score and selects the appropriate information assets. The selected information assets are ranked in a way that suits the user's emotional needs and presented to the terminal.

[0764] For example, if a user enters "movies with an emotional story and a medical theme," and the emotion analysis technology determines that the user is in a state of wanting to be encouraged, the server will prioritize selecting movies that particularly emphasize encouraging elements. The list of movies obtained through this selection process will then be quickly provided to the user for viewing.

[0765] An example of a prompt would be: "The emotion engine has analyzed that the user is currently in an emotional state of 'wanting encouragement.' In this state, generate a list of movies that emphasize the encouraging aspect for the search query 'inspirational stories, medical-themed movies.'"

[0766] Thus, the present invention enables information retrieval that takes into account the user's emotional state, providing a more satisfying search experience than before.

[0767] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0768] Step 1:

[0769] The user enters search terms through the terminal. The entered search terms are specific phrases such as "moving stories, medical-themed movies." The terminal sends the search terms to the server and also uses sensors to acquire biometric information such as the user's heart rate and facial expressions. This biometric information is sent to the server as input data to analyze the user's emotional state.

[0770] Step 2:

[0771] The server receives the search term and biometric information. Next, it analyzes the received search term using natural language processing techniques and breaks it down into its constituent elements. In this process, the search term is divided into meaningful words such as "emotional," "story," "medical," and "movie," and these are used as the basis data for analysis. At the same time, the server applies emotion analysis techniques based on the biometric information to determine whether the user is in an emotional state such as "wanting to be encouraged." The result of this determination is an important output value that will influence future search conditions.

[0772] Step 3:

[0773] Based on the analyzed components and emotional states, the server collects relevant evaluation and attribute information from an external data storage device. Specifically, the server sends queries to the database via an API to retrieve evaluation and attribute information. In this process, the evaluation information includes information related to "emotional," "medical," and "encouraging." Data processing is performed on the collected data to calculate an emotional score, yielding important output that can be used as a selection criterion for information assets.

[0774] Step 4:

[0775] The server selects relevant information assets based on sentiment scores and collected attribute information. This process aims to rank the collected movie list based on sentiment scores, placing the content most suitable for users seeking encouragement at the top. This ranking information is output in list format and ready to be presented to the user visually.

[0776] Step 5:

[0777] The server sends the selected information assets to the user's terminal. The terminal displays the received movie list on the screen, allowing the user to select their desired movie. Through this list, the user can browse stories that match their emotional state from the selected movies. This provides a highly satisfying search experience.

[0778] (Application Example 2)

[0779] 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".

[0780] Traditional search systems present information assets based solely on the search terms entered by the user, failing to provide personalized results that take into account the user's emotional state, sometimes resulting in the presentation of inappropriate information. In particular, content distribution services are required to provide content that matches the user's current emotional state, but presenting appropriate search results based on emotion remains a challenge.

[0781] 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.

[0782] In this invention, the server includes means for analyzing the search terms entered by the user and breaking them down into their constituent elements, means for generating an emotional score and identifying attributes based on attribute information, and means for analyzing the user's emotional state in real time. This makes it possible to select and provide the user with the most suitable content based on the user's current emotional state.

[0783] A "search term" is a keyword or phrase that a user enters to find information.

[0784] "Components" are individual elements or parts obtained by analyzing a search term.

[0785] "Evaluation information" refers to data that represents the characteristics and quality related to information assets.

[0786] "Attribute information" refers to data defined by the characteristics and features associated with an information asset.

[0787] An "emotion score" is an evaluation metric that quantifies a user's emotional state.

[0788] "Biometric information" refers to data about the user's body, such as heart rate and facial expressions.

[0789] A "sensor" is a device that acquires physical data, and in this context, it is used to collect biological information.

[0790] "Information assets" refer to digital content and information provided to users as search results.

[0791] "Real-time" refers to a situation where processing or reactions occur almost instantly.

[0792] "Content" refers to media and information provided to users, such as movies and TV dramas.

[0793] This invention is a system comprising a user terminal, a server, and biometric sensors. The user inputs a specific search term via the terminal, and the system analyzes it. The analysis breaks down the search term into its constituent elements and collects relevant evaluation and attribute information. An emotion score is generated from the collected information, and the user's emotional state is analyzed in real time based on data obtained from the user's biometric information. Sensors used include those that measure heart rate and facial expressions, such as cameras and heart rate sensors.

[0794] The server selects information assets based on the user's sentiment score and attribute information, and presents them to the user's device. This makes it possible to provide optimal content that matches the user's current sentiment. The server uses natural language processing technology to analyze its components. Content selection is achieved by narrowing down the information based on the sentiment score and attribute information.

[0795] For example, if a user inputs "comedy movie" and the emotion engine analyzes that the user is "feeling stressed," it will prioritize recommending comedy movies that have a stress-reducing effect. An example of a prompt to input into the generative AI model is, "When the user's emotional state is stressed, please suggest a relaxing movie."

[0796] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0797] Step 1:

[0798] The user enters a search term using the terminal. The search term represents a genre of interest, such as "comedy movies." This input serves as the starting point for the next processing step.

[0799] Step 2:

[0800] The terminal sends the entered search term to the server. The server receives the search term and uses natural language processing technology to break it down into its constituent elements. This process performs semantic analysis of the term, forming a foundation for a more detailed understanding of the user's intent.

[0801] Step 3:

[0802] The server collects relevant evaluation and attribute information from an external database based on its components. This allows it to gather information on the characteristics and past evaluations of content related to the search terms, which is then used for subsequent processing.

[0803] Step 4:

[0804] The server generates an emotional score using the collected evaluation information. Here, the evaluation information and the user's emotional state are quantified by the generated score. This score is calculated through data processing and is used to select content that matches the user's emotional state.

[0805] Step 5:

[0806] Sensors installed in the user's device collect biometric information in real time and transmit it to a server. Data such as heart rate and facial expressions are used for emotion analysis. This input clarifies the user's emotional state.

[0807] Step 6:

[0808] The server analyzes the user's emotional state using a generative AI model based on the acquired biometric information. The analysis results indicate the user's current psychological situation and are used to generate prompt messages.

[0809] Step 7:

[0810] The server selects information assets based on emotion scores and emotion analysis results obtained from biometric information. Appropriate data processing and filtering are performed to determine the most suitable recommended content for the user's state.

[0811] Step 8:

[0812] The selected information assets are displayed on the user's device. The user can view content optimized for their current emotions. For example, if stress is detected, a comedy movie with stress-reducing effects will be recommended.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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."

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] The following is further disclosed regarding the embodiments described above.

[0835] (Claim 1)

[0836] A means for analyzing the search term entered by the user and breaking it down into its constituent elements,

[0837] A means for collecting relevant evaluation information and attribute information based on the aforementioned components,

[0838] A means for generating an emotion score based on the collected evaluation information and for identifying attributes based on the attribute information,

[0839] A means for selecting the relevant information asset based on the aforementioned sentiment score and attribute,

[0840] A means for presenting the selected information assets to the user,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, characterized in that natural language processing technology is used to generate the aforementioned sentiment score.

[0844] (Claim 3)

[0845] The system according to claim 1, characterized in that the aforementioned evaluation information or attribute information is obtained from an external database.

[0846] "Example 1"

[0847] (Claim 1)

[0848] A means of analyzing the search terms entered by the user and breaking them down into meaningful components,

[0849] A means for collecting relevant evaluation information and attribute information from external sources based on the aforementioned components,

[0850] A means for generating an emotional index based on the evaluation information collected using emotion analysis technology, and for identifying an attribute that satisfies predetermined conditions based on the attribute information,

[0851] A means for selecting relevant information resources based on the aforementioned sentiment indicators and attributes, and providing them to the user in data format,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, characterized in that natural language processing technology is used to generate the aforementioned sentiment index.

[0855] (Claim 3)

[0856] The system according to claim 1, characterized in that the aforementioned evaluation information or attribute information is obtained from an external information source via a programming interface.

[0857] "Application Example 1"

[0858] (Claim 1)

[0859] A means for analyzing the search term entered by the user and breaking it down into its constituent elements,

[0860] A means for collecting relevant evaluation information and attribute information based on the aforementioned components,

[0861] A means for generating an emotion score based on the collected evaluation information and for identifying attributes based on the attribute information,

[0862] A means for selecting the relevant information asset based on the aforementioned sentiment score and attribute,

[0863] A means for presenting the selected information assets to the user,

[0864] A means for generating a list based on user evaluation from the aforementioned presented information assets,

[0865] A system that includes this.

[0866] (Claim 2)

[0867] The system according to claim 1, characterized in that natural language processing technology is used to generate the aforementioned sentiment score.

[0868] (Claim 3)

[0869] The system according to claim 1, characterized in that the aforementioned evaluation information or attribute information is obtained from an external source.

[0870] "Example 2 of combining an emotion engine"

[0871] (Claim 1)

[0872] A means for analyzing the search term entered by the user and breaking it down into its constituent elements,

[0873] A means for collecting relevant evaluation information and attribute information based on the aforementioned components and the user's emotional state,

[0874] A means for analyzing a user's emotional state from their biometric information and generating an emotional score considering the results,

[0875] A means for selecting the relevant information asset based on the aforementioned components, emotional score, and attribute information,

[0876] A means for presenting the selected information assets to the user,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, characterized in that natural language processing technology and sentiment analysis technology are used to generate the aforementioned sentiment score.

[0880] (Claim 3)

[0881] The system according to claim 1, characterized in that the aforementioned evaluation information or attribute information is obtained from an external data storage device.

[0882] "Application example 2 when combining with an emotional engine"

[0883] (Claim 1)

[0884] A means for analyzing the search term entered by the user and breaking it down into its constituent elements,

[0885] A means for collecting relevant evaluation information and attribute information based on the aforementioned components,

[0886] A means for generating an emotion score based on the collected evaluation information and for identifying attributes based on the attribute information,

[0887] A means for selecting the relevant information asset based on the aforementioned sentiment score and attribute,

[0888] A means for presenting the selected information assets to the user and adjusting the proposal results based on the user's emotional state,

[0889] A means of analyzing a user's emotional state in real time using sensors that acquire biometric information,

[0890] A means for selecting and presenting appropriate content based on the aforementioned emotional state,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, characterized in that natural language processing technology is used to generate the aforementioned emotion score, and further includes incorporating an emotional state that is updated in real time.

[0894] (Claim 3)

[0895] The system according to claim 1, characterized in that the aforementioned evaluation information or attribute information is obtained from an external database. [Explanation of symbols]

[0896] 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 for analyzing the search term entered by the user and breaking it down into its constituent elements, A means for collecting relevant evaluation information and attribute information based on the aforementioned components, A means for generating an emotion score based on the collected evaluation information and for identifying attributes based on the attribute information, A means for selecting the relevant information asset based on the aforementioned sentiment score and attribute, A means for presenting the selected information assets to the user, A means for generating a list based on user evaluation from the aforementioned presented information assets, A system that includes this.

2. The system according to claim 1, characterized in that natural language processing technology is used to generate the aforementioned sentiment score.

3. The system according to claim 1, characterized in that the aforementioned evaluation information or attribute information is obtained from an external information source.

Images