system

Abstract

We provide the system. [Solution] A means of analyzing user-generated natural language preferences and extracting condition items, A means for searching for matching information from multiple databases based on extracted criteria, A means of integrating surrounding environmental information based on search results and generating visualization data, A means of interactively presenting integrated information to the user, 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 performed by at least one processor, the method including 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 a conventional rental property search system, it has been difficult for a user to search for a property based on a desired lifestyle, and in particular, a search considering surrounding facilities and regional characteristics has not been realistic. For this reason, the user has had to spend a great deal of time and effort to find an ideal property. In addition, there has been no method for visually unifying search results or an appropriate means for virtually experiencing detailed information about a property.

Means for Solving the Problems

[0005] This invention provides means for analyzing user-submitted natural language preferences and extracting criteria, as well as means for searching for information from multiple databases based on these criteria, thereby enabling more accurate property searches. Furthermore, by providing means for integrating surrounding environment information based on search results and generating visualized data, it enables users to intuitively understand property information. In addition, it provides a filtering function that allows users to narrow down the criteria through interaction with the user, and means for generating virtual viewing data that can be visually confirmed on the terminal, supporting a comfortable and efficient property search.

[0006] A "user" is an individual or group that uses the system to search for and select rental properties.

[0007] "Natural language" refers to the language forms that users use on a daily basis and the language forms used as input to a system.

[0008] "Condition items" are specific search criteria extracted from the user's desired conditions.

[0009] A "database" is an information system that stores and manages information such as property details, surrounding facilities, and regional characteristics.

[0010] "Surrounding environment information" refers to information about elements such as facilities, transportation, and regional characteristics that exist around the property.

[0011] "Visualized data" refers to data generated to visually represent a property and its surrounding information.

[0012] "Interaction" refers to the exchange of information between a user and a system.

[0013] A "filtering function" is a system feature that narrows down search results based on user criteria.

[0014] "Virtual interior view" refers to the provision of visual information for users to virtually experience the details of a property.

[0015] "Terminal" refers to a device for users to access and operate the system, including computers and smartphones.

Brief Description of Drawings

[0016] [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 multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple 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 combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Embodiment for Carrying out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] 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.

[0020] 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.

[0021] 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, and the like.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention is a system that efficiently proposes rental properties that best match the user's needs by analyzing the user's input of desired conditions in natural language through their terminal. This system works in conjunction with multiple databases centered around a server to provide users with comprehensive property information.

[0038] First, the user uses a device to input their desired conditions in natural language through a chatbot-style interface. For example, by entering conditions such as "an apartment near a train station where pets are allowed," the user's specific request is transmitted to the system.

[0039] The server processes the input natural language through text analysis and clearly extracts the required criteria. Based on these analysis results, the server accesses multiple databases to search for property information that matches the criteria. The information includes a wide range of details such as property overview, location, surrounding facilities, and regional characteristics, and it is also possible to obtain information using external APIs as needed.

[0040] After integrating the search results, the server processes the data in a visually easy-to-understand format and presents it to the user's device in map or list format. This allows the user to intuitively understand the geographical location of the property and surrounding facilities.

[0041] Furthermore, users can utilize filtering options to narrow down their search criteria through interaction. For example, by specifying additional conditions such as budget or room size, they can obtain more detailed property information.

[0042] Ultimately, for properties that users are interested in, a means of virtual viewing is provided. The server generates a 3D model of the property's interior, enabling a virtual tour on the user's device. This feature allows users to conduct detailed observation and analysis without actually visiting the property.

[0043] According to embodiments of the present invention, the process of searching for rental properties is significantly streamlined, allowing users to easily find properties that suit their lifestyle.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] Users use their devices to input their desired rental conditions in natural language. Through the chatbot interface, they communicate their requests to the system, such as "I'm looking for a pet-friendly apartment within walking distance of the station."

[0047] Step 2:

[0048] The server analyzes the received natural language input and uses natural language processing techniques to extract conditional items. Here, specific requirements based on the user's preferences (e.g., within walking distance of a train station, pet-friendly, apartment) are identified.

[0049] Step 3:

[0050] Based on the extracted conditions, the server accesses its internal database and, if necessary, external APIs to search for corresponding property information. The search generates and executes queries to filter properties that match the user's desired criteria.

[0051] Step 4:

[0052] The server integrates property information obtained from search results and collects and integrates additional information, including surrounding facilities and regional characteristics. The integrated data is then prepared to be presented to the user as visual information.

[0053] Step 5:

[0054] The server sends visualized information to the user's terminal, which the user then views on the terminal in map or list format. Here, the location of the property and its relationship to surrounding facilities are displayed in an intuitive manner.

[0055] Step 6:

[0056] Users can further refine their search criteria using filtering options based on the information provided on their device. This allows them to specify additional conditions, such as budget or room size, to narrow down the options even further.

[0057] Step 7:

[0058] Finally, the user selects the option to virtually tour the properties they are interested in. The server generates a 3D model of the selected property and provides the data so that the user can virtually tour its details through their device.

[0059] Through this series of steps, users can efficiently find rental properties that meet their desired conditions.

[0060] (Example 1)

[0061] 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."

[0062] When searching for rental properties, it is difficult for users to accurately and efficiently reflect their desired conditions and quickly find the best option from a vast amount of property information. Furthermore, there are limited ways to thoroughly understand properties that are far away and difficult to view in person. Therefore, there is a need for a system that can quickly and intuitively suggest the best properties based on the user's desired conditions and provide detailed information, thereby improving the efficiency of the rental property search.

[0063] 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.

[0064] In this invention, the server includes means for analyzing natural language conditions from the user and extracting elements; means for searching for relevant information from multiple information databases based on the extracted elements; means for integrating environmental information based on the search results and generating visualization data; means for generating a three-dimensional model of a selected physical location using virtual reality technology and making it displayable on a terminal; and means for generating prompt text for the generated technology model as needed and using it as input. As a result, users can easily find the optimal rental property based on their desired conditions and intuitively understand the details of the property remotely through virtual viewings.

[0065] "User" refers to the person who operates the system and receives information.

[0066] "Natural language" refers to the forms of language that humans use on a daily basis, and the text that is analyzed in computer processing.

[0067] "Elements" refer to individual conditions necessary for searching and evaluation, which are extracted during the process of analyzing the user's desired conditions.

[0068] An "information database" refers to a collection of structured data that a system accesses and uses to retrieve necessary property information.

[0069] "Related information" refers to information about matching properties and environments that are retrieved from the database based on the user's desired conditions.

[0070] "Environmental information" refers to information about the surrounding characteristics and area of ​​a property, and is a factor that should be considered when choosing a property.

[0071] "Visualized data" refers to a data format that is visually organized so that users can intuitively understand the information.

[0072] "Virtual reality technology" refers to technology that allows users to experience a three-dimensional space created by a computer program.

[0073] A "three-dimensional model" refers to data in a virtual space that represents the interior and exterior of a property in three dimensions.

[0074] A "generative technology model" refers to a model that autonomously generates and provides information using technologies such as artificial intelligence.

[0075] A "prompt statement" refers to a sentence that specifies the instructions or conditions that are input into a generative technology model.

[0076] This system aims to provide optimal rental property information based on the user's desired conditions entered in natural language via a terminal. The system's core is a server, which is linked to multiple databases. The server utilizes natural language processing libraries such as "spaCy" and "BERT" to analyze the conditions entered by the user.

[0077] When a user enters conditions such as "apartments near a train station where pets are allowed" through the chatbot interface on their device, the information is first sent to the server. The server performs text analysis and extracts the condition items. This analysis breaks down the input natural language into its constituent elements and converts them into the required format.

[0078] Next, the server uses the extracted criteria to search the database. SQL and NoSQL technologies are used for the search, and additional information can be obtained from external APIs (e.g., map service APIs) as needed. This makes it possible to thoroughly gather information that meets the user's needs.

[0079] The acquired information is integrated by the server and visualized using a data visualization library (e.g., D3.js). The generated visualization data is sent to the user's device and presented intuitively in map or list format. This allows the user to easily understand the surrounding environment and the geographical location of the property.

[0080] In addition, users can use filtering functions to refine and modify their search criteria. This allows them to narrow down their search by budget, room size, and other factors. Furthermore, the server generates a 3D model of the property selected by the user using virtual reality technology and delivers it to the device in the form of a virtual tour. This technology uses WebGL, allowing users to view the interior in detail without actually visiting the property.

[0081] As a concrete example, the prompt message sent to the generating AI model is in the format of "I'm looking for a 1LDK apartment in Tokyo that's pet-friendly, near a train station, and has a rent of 50,000 yen or less." By sending this prompt, the model returns the most suitable property information. By integrating these technologies, the system allows users to efficiently find properties that best match their preferences.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The user enters their desired conditions in natural language via their device. An example of this input might be "apartments near a train station where pets are allowed." This data is configured by the user on their device and sent to the server. In this process, the user's request is initialized and a query to the system is initiated.

[0085] Step 2:

[0086] The server receives natural language input from the user and parses it using a natural language processing library (e.g., spaCy, BERT). This parse extracts conditional items. The received text is tokenized, relevant keywords and phrases are identified, and they are converted into a format for use in database searches. The output is a structured list of searchable conditional items.

[0087] Step 3:

[0088] The server searches the information database using the extracted conditions. SQL and NoSQL technologies are used to search for property information that matches the conditions, and it is also possible to retrieve supplementary information from external APIs (e.g., map service APIs). The input is a list of condition items, and the output is property information that matches the conditions. This process includes collecting property overviews, location information, and regional characteristics data.

[0089] Step 4:

[0090] The server integrates the search results and formats them as visualized data using a data visualization library (e.g., D3.js). It generates maps and list formats that visually represent location information and related property information. The input is a collection of property information, and the output is a visualized dataset presented to the user.

[0091] Step 5:

[0092] The user reviews the visualization data received from the server via their device and uses filtering to narrow down the criteria. Additional conditions, such as budget and room size, can be specified through further interaction. This operation improves the accuracy of the visualization data. Inputs are the visualization data and additional conditions, and output is the filtered and revised information.

[0093] Step 6:

[0094] The server generates a 3D model of the property selected by the user using virtual reality technology. Using WebGL technology, the internal structure of the property is reproduced in 3D and sent to the terminal. This allows the user to conduct a virtual tour. Inputs are property information and visualization requests, and output is the 3D model experienced by the user.

[0095] Step 7:

[0096] If necessary, the server generates prompt sentences for the generative technology model and uses them as input. A concrete example of a prompt might be, "I'm looking for a 1LDK apartment in Tokyo that's pet-friendly, near a train station, and has a rent of 50,000 yen or less." The prompt sentences are analyzed by the generative AI model and used to obtain additional recommendations. The input is the user's conditions and situation, and the output is recommendations and additional information.

[0097] (Application Example 1)

[0098] 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."

[0099] Traditional rental property search systems require users to physically visit properties, which is time-consuming and costly. Furthermore, it's often difficult to select properties based on detailed criteria, and real-time information about the surrounding environment is often unavailable. In this context, there is a need for a method that allows users to efficiently and intuitively select properties from the comfort of their homes.

[0100] 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.

[0101] In this invention, the server includes means for analyzing user-defined natural language preferences and extracting condition items, means for searching for matching information from multiple data records based on the extracted condition items, and means for generating visualization data for a virtual viewing of an item, which can be visually confirmed on a terminal. This allows users to select properties based on detailed conditions from the comfort of their homes, and further enables them to visually confirm the surrounding environment in real time through the virtual viewing mode.

[0102] A "user" is an individual or legal entity that uses an information system to search for rental properties.

[0103] "Natural language" refers to the forms of words and sentences that humans use on a daily basis, and it is a linguistic form from which conditions are extracted through computer analysis.

[0104] "Desired conditions" refer to the specific features and requirements that the user seeks in a rental property, including location, price, and amenities.

[0105] "Condition items" are classified elements that the system identifies and uses to perform specific database searches, based on the user's desired conditions.

[0106] "Data records" refer to information sources where information related to rental properties is stored, and serve as the foundation for systems to search for that information.

[0107] "Matching information" refers to properties and related data that match the user's criteria and are information that suits the user's needs.

[0108] "Virtual viewing" is a method that allows users to visually experience the interior of a property using information technology without physically visiting the property.

[0109] "Visualized data" refers to data presented in a format that is easy for users to intuitively understand, and includes maps and 3D models.

[0110] The system that realizes this invention efficiently provides rental property information according to the user's requests. The following describes an embodiment of this system.

[0111] The server receives the user's desired conditions entered in natural language using a terminal. Using a standard server computer as hardware and the Google® Cloud Natural Language API as software, the server analyzes the entered natural language and extracts specific condition items. This ensures that the user's desired conditions are clearly understood.

[0112] The extracted criteria are searched across multiple databases by the server to collect relevant information. This information includes detailed data on rental properties and surrounding environment information, and is important for generating visualization data.

[0113] Once matching information is integrated, the server uses Unity to generate 3D models of the items and converts them into visualization data for virtual viewings. This visualization data is then transferred to the terminal and presented to the user in a usable format. Specifically, users can use their smartphones to explore the property in detail in virtual reality mode, gaining an intuitive understanding of the surrounding environment and property details.

[0114] For example, if a user enters "I'm looking for a detached house with a large garden," the server automatically searches for properties that match that requirement and allows the user to visually experience the size and layout of the garden using a 3D model. In this case, an example of a prompt message would be "I'd like a house with a large garden. Please show me properties that suit me."

[0115] In this way, users can explore rental properties and gain a deep understanding of their characteristics from the comfort of their own homes. This system will allow users to efficiently find their ideal property.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The user enters their desired conditions in natural language using their device. For example, the user might enter a request such as "a pet-friendly apartment near a train station" into the chatbot. The input data is sent from the device to the server as natural language text.

[0119] Step 2:

[0120] The server analyzes the received natural language input. During this process, it uses the Google Cloud Natural Language API to process the data and extract desired conditions from the text. The input is natural language text data, and the output is a set of extracted condition items.

[0121] Step 3:

[0122] The server searches the database using the extracted criteria. It accesses multiple databases and performs data calculations to search for rental property information based on the criteria. The input is a set of criteria, and the output is a list of candidate properties.

[0123] Step 4:

[0124] The server integrates surrounding environment information from search results and generates visualization data. It uses Unity to create 3D models of properties and performs data processing to create visualization data compatible with virtual viewings. The input is a list of candidate properties, and the output is visualization data including 3D models.

[0125] Step 5:

[0126] The generated visualization data is sent from the server to the terminal. The terminal interactively presents property information to the user, enabling the user to take a virtual reality tour. The input is the visualization data, and the output is the property information and virtual tour experience displayed on the terminal.

[0127] 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.

[0128] This invention is a property suggestion system that takes into account the user's psychological factors, enabling more appropriate property searches based on the user's requirements. This system incorporates an emotion engine that recognizes and analyzes emotions through the user's natural language input, and by adding emotional nuances to the conditions requested by the user, it can achieve more satisfying results.

[0129] First, the user enters their desired conditions in natural language using their device. During this process, the emotion engine analyzes the user's emotions (e.g., joy, sadness, anxiety) in real time. For example, input such as "I want an apartment where there is little noise and I can live quietly" can detect the user's stress levels and desire for calm.

[0130] The server generates a search query using the analyzed sentiment data along with the specified criteria. This query filters and searches for properties that best match the user's desired conditions and sentiments through an internal database and an external API. In this case, property information that guarantees a quiet environment is given priority.

[0131] Search results are integrated for visualization, and the presentation method is adjusted according to the user's emotional state. For example, a calming color scheme is used to present information, enhancing the sense of anticipation for living in a peaceful environment.

[0132] Furthermore, users can add or modify conditions using an interactive filtering function. The emotion engine also operates during this filtering process, adjusting the filtering method according to the user's emotions.

[0133] Finally, for properties that pique the user's interest, a virtual viewing option allows for more detailed examination. Here too, the emotion engine monitors the user's reactions and further personalizes the information presented.

[0134] As a result, this system enables emotionally sensitive property recommendations and improves the user experience. By integrating user emotions into its approach, users can efficiently find properties that better suit them, resulting in higher satisfaction.

[0135] The following describes the processing flow.

[0136] Step 1:

[0137] Users use their devices to input their desired property criteria in natural language. At this time, an emotion engine recognizes the user's emotions in real time from their input and analyzes the emotions they are feeling when entering their criteria. This emotion data is then used for subsequent processing.

[0138] Step 2:

[0139] The server extracts conditional items from the user's natural language. This utilizes natural language processing technology to extract the specific conditions the user desires (e.g., quiet place, pet-friendly). Simultaneously, the results of the emotion engine analysis are also obtained, and the user's emotional state (e.g., want to feel safe, want to avoid stress) is integrated as supplementary information.

[0140] Step 3:

[0141] The server generates a search query based on the extracted criteria and sentiment information, and searches for relevant property information using the property database and external APIs. At this stage, it prioritizes filtering for properties that highlight a specific sentiment (e.g., properties with a prominent peaceful environment).

[0142] Step 4:

[0143] The server organizes the acquired property information and generates visualization data to present it to the user in an emotionally sensitive visual way. For example, if the user is in a mood to relax, the screen's color scheme and design will be expressed in a tone that reflects that emotion.

[0144] Step 5:

[0145] Users can view property information displayed on their device and further refine their search using the filtering function. During this process, the emotion engine continuously analyzes the user's reactions and incorporates this information into the presentation of filtering options.

[0146] Step 6:

[0147] For properties that the user is particularly interested in, the server provides virtual viewing data, allowing the user to visually check the details on their device. Throughout this process, information is presented based on the user's emotional state, striving to enhance user satisfaction.

[0148] Through this series of steps, the emotion engine is integrated into the entire system, enabling personalized property recommendations that take user emotions into account.

[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 property search systems simply suggested properties based on criteria without considering the user's emotions or psychological factors. Therefore, it was difficult to enhance the user's subjective satisfaction, resulting in a limited user experience. Furthermore, they were unable to provide interactive feedback that responded to the user's emotions, making it difficult to deliver optimized search results.

[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 desired conditions in natural language from the user and extracting condition items; means for analyzing the extracted condition items and the user's emotions and dynamically generating a search query based on the user's emotional state; and means for searching for matching information from multiple data storages using the generated search query. This enables optimal property suggestions that integrate the user's emotions and conditions.

[0154] "Natural language" refers to linguistic expressions used to express desires, based on the language forms that users use on a daily basis.

[0155] "Condition items" are indicators that are analyzed from the user's natural language input and specifically indicate their wishes and requirements regarding the property.

[0156] "Emotion analysis" is a process that recognizes the emotions contained in the user's natural language input and quantifies the user's psychological state.

[0157] A "search query" is a set of instructions generated based on the user's preferences and emotional state, used to retrieve relevant information from data storage.

[0158] "Data storage" refers to a data storage system that holds property information and related surrounding data, and provides information in response to search queries.

[0159] "Visualization" is the process of organizing acquired information into a format that is easy for users to understand and representing it visually.

[0160] A "user-emotion-responsive approach" is a method that adjusts search results and presentation methods to best suit the user's emotions.

[0161] "Interactive presentation" refers to a function that allows users to interact with and respond to the information presented, enabling two-way use of the information.

[0162] This invention relates to a property recommendation system that takes into account the user's psychological factors, and the system operates between a server, a terminal, and the user. The user inputs their desired property conditions into the terminal using natural language. This natural language input is analyzed by an emotion analysis engine, which interprets the user's emotions. This emotion analysis engine is, for example, software that uses emotion recognition algorithms and natural language processing technology.

[0163] The terminal processes text data entered by the user in real time and sends sentiment data to the server. The server searches for information in data storage using dynamically generated search queries based on the sentiment data and the user's preferences. Data storage is an accessible pool of information based on internal databases and external information provision services.

[0164] The retrieved search results are visualized by the server according to the user's emotional state and sent to the device. The device displays the results to the user using calming colors and designs, and the user can interact with the presented information. This interaction incorporates further sentiment analysis, and filtering methods are performed according to the user's emotions.

[0165] For example, if a user enters "I want to find a quiet place with little noise," the emotion engine analyzes the user's desire for "peace of mind" and "relaxation." Based on this, the server identifies properties that guarantee a quiet environment and presents them to the user as a priority.

[0166] An example of a prompt message is: "Analyze the user's emotions and extract the property features they desire. Input: 'I want to live in a quiet environment with no noise.'"

[0167] With this configuration, the present invention has the effect of improving the subjective satisfaction of users and realizing more efficient and personalized property recommendations.

[0168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0169] Step 1:

[0170] The user uses a device to input their desired property conditions in natural language. The device receives this input and sends it as text data to the sentiment analysis engine. A possible specific input might be, "I want to find a quiet place with little noise." The output is text data in a format that the sentiment analysis engine can process.

[0171] Step 2:

[0172] The device's emotion analysis engine analyzes received text data and evaluates the user's emotions. The input is the user's natural language text, and the analysis algorithm determines the emotional state (e.g., reassured, relaxed, stressed). The output is metadata indicating this emotional state. For example, the emotion "reassured" might be extracted.

[0173] Step 3:

[0174] The server generates a search query from the received sentiment metadata and user preferences. Specifically, it dynamically constructs a query to prioritize properties that offer a quiet environment based on the sentiment state and conditional items. The input is the analyzed sentiment and conditional items, and the output is the search query to be executed in data storage.

[0175] Step 4:

[0176] The server uses the generated search query to search for matching information from the data storage. This search process accesses internal databases and external APIs to retrieve property information that matches the user's desired criteria. The input is a dynamically generated search query, and the output is a filtered list of property information.

[0177] Step 5:

[0178] The server integrates search results as visual data and generates information presented through an interface tailored to the user's emotional state. Input includes search results, which are visualized using reassuring color schemes and designs. Output is the visualized data sent to the terminal.

[0179] Step 6:

[0180] Users view visualized property information on their device and interactively modify or add criteria. The device then performs sentiment analysis again in response to these actions, re-filtering the criteria. The input is the user's actions, and the output is the updated search query. For example, the condition "more green places" might be added.

[0181] Step 7:

[0182] When a user expresses interest in a particular property, the server provides virtual tour data for that property and performs sentiment analysis tailored to the user's reactions. The input is the user's selection when starting the virtual tour, and the output is customized visual data based on the user's reactions.

[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 online shopping systems have the problem of lower user satisfaction because they cannot suggest products that take into account the user's psychological and emotional factors. Furthermore, it is difficult to implement interactive filtering and visual representations that respond to user emotions, making it challenging to suggest products that meet individual user needs.

[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 user-defined natural language preferences and extracting condition items and emotion data; means for searching for matching information from multiple databases based on the extracted condition items and emotion data; and means for integrating surrounding environment information based on the search results and generating visualization data corresponding to the emotion. This enables personalized product suggestions that take the user's emotions into consideration.

[0188] "Desired conditions in natural language" refers to the conditions that the user desires, entered using everyday language.

[0189] "Condition items" are specific elements or criteria extracted from the user's desired conditions.

[0190] "Emotional data" refers to information that represents the psychological state and emotional tendencies of a user, analyzed from their input.

[0191] A "database" is an electronic record system for systematically collecting and managing information.

[0192] "Surrounding environment information" refers to information that indicates external conditions and characteristics related to the product or service in question.

[0193] "Interactive presentation" means that information is displayed in a way that allows the user and the system to influence each other.

[0194] A "filtering method" is a technique for selecting information that meets specific criteria from a large amount of data.

[0195] "Visualized data" refers to data that has been processed to represent information visually.

[0196] "Virtual preview" is a technology that simulates information in a way that closely resembles the actual visual experience.

[0197] The system that realizes this invention mainly consists of a server, a user terminal, and an emotion analysis engine. First, the user inputs their desired conditions into the terminal using natural language, and this is sent to the server. This terminal should preferably be a high-performance smartphone or smart glasses.

[0198] The server analyzes the input natural language data and extracts conditional items and sentiment data. This uses software such as AWS® Comprehend as the sentiment analysis engine. The analyzed data is sent as queries to multiple databases, and matching information is collected. This database is an electronic record system for systematically managing product and related information.

[0199] Next, the server integrates the collected information with the user's emotional data to generate visualization data that reflects their emotions. This visualization data is created using the latest visualization technologies in human-computer interaction.

[0200] The generated visualization data is presented interactively on the device in a way that adapts to the user's emotions. The user can use this visualization to select products and, if necessary, further refine their search criteria through filtering functions.

[0201] For example, if a user seeking relaxation enters "I want calming interior design" into their device, the emotion analysis engine extracts the emotion of relaxation, and the server filters interior products that match this. As a result, the visualized data will highlight calming designs with nature themes, such as green and wood tones.

[0202] An example of a prompt for a generative AI model might be: "We are looking for products that make the user feel relaxed. Please list products that evoke a feeling of relaxation based on the emotion analysis results."

[0203] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0204] Step 1:

[0205] Users use devices such as smartphones or smart glasses to input their desired conditions in natural language. This input text is sent to the server. For example, if the input is "a comfortable sofa," the text data is sent to the server as output.

[0206] Step 2:

[0207] The server sends the received natural language text to an emotion analysis engine to extract emotion data. Using AWS Comprehend, it analyzes emotions such as "relaxed" in the text and obtains emotion data as output.

[0208] Step 3:

[0209] The server queries the product database based on the extracted criteria ("sofa") and emotion data ("relaxed") to find matching product information. The input is the criteria and emotion, and the output is a list of products that fit them.

[0210] Step 4:

[0211] The server integrates surrounding environment information from the search results and generates emotion-responsive visualization data. Using visualization tools, the collected results are presented in calming colors and designs. The generated visualization data is then output.

[0212] Step 5:

[0213] The server sends this visualization data to the user's device and presents it in an interactive format that is appropriate to their emotions. This allows the user to select products based on the visualized information.

[0214] Step 6:

[0215] Users can further refine their criteria using the interactive filtering function. As a result, they send the new criteria back to the server and receive updated results.

[0216] Step 7:

[0217] Finally, the user reviews the details of the selected product and performs a virtual preview as needed. The preview displays simulated visual information of the specified product.

[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 that efficiently proposes rental properties that best match the user's needs by analyzing the user's input of desired conditions in natural language through their terminal. This system works in conjunction with multiple databases centered around a server to provide users with comprehensive property information.

[0235] First, the user uses a device to input their desired conditions in natural language through a chatbot-style interface. For example, by entering conditions such as "an apartment near a train station where pets are allowed," the user's specific request is transmitted to the system.

[0236] The server processes the input natural language through text analysis and clearly extracts the required criteria. Based on these analysis results, the server accesses multiple databases to search for property information that matches the criteria. The information includes a wide range of details such as property overview, location, surrounding facilities, and regional characteristics, and it is also possible to obtain information using external APIs as needed.

[0237] After integrating the search results, the server processes the data in a visually easy-to-understand format and presents it to the user's device in map or list format. This allows the user to intuitively understand the geographical location of the property and surrounding facilities.

[0238] Furthermore, users can utilize filtering options to narrow down their search criteria through interaction. For example, by specifying additional conditions such as budget or room size, they can obtain more detailed property information.

[0239] Ultimately, for properties that users are interested in, a means of virtual viewing is provided. The server generates a 3D model of the property's interior, enabling a virtual tour on the user's device. This feature allows users to conduct detailed observation and analysis without actually visiting the property.

[0240] According to embodiments of the present invention, the process of searching for rental properties is significantly streamlined, allowing users to easily find properties that suit their lifestyle.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] Users use their devices to input their desired rental conditions in natural language. Through the chatbot interface, they communicate their requests to the system, such as "I'm looking for a pet-friendly apartment within walking distance of the station."

[0244] Step 2:

[0245] The server analyzes the received natural language input and uses natural language processing techniques to extract conditional items. Here, specific requirements based on the user's preferences (e.g., within walking distance of a train station, pet-friendly, apartment) are identified.

[0246] Step 3:

[0247] Based on the extracted conditions, the server accesses its internal database and, if necessary, external APIs to search for corresponding property information. The search generates and executes queries to filter properties that match the user's desired criteria.

[0248] Step 4:

[0249] The server integrates property information obtained from search results and collects and integrates additional information, including surrounding facilities and regional characteristics. The integrated data is then prepared to be presented to the user as visual information.

[0250] Step 5:

[0251] The server sends visualized information to the user's terminal, which the user then views on the terminal in map or list format. Here, the location of the property and its relationship to surrounding facilities are displayed in an intuitive manner.

[0252] Step 6:

[0253] Users can further refine their search criteria using filtering options based on the information provided on their device. This allows them to specify additional conditions, such as budget or room size, to narrow down the options even further.

[0254] Step 7:

[0255] Finally, the user selects the option to virtually tour the properties they are interested in. The server generates a 3D model of the selected property and provides the data so that the user can virtually tour its details through their device.

[0256] Through this series of steps, users can efficiently find rental properties that meet their desired conditions.

[0257] (Example 1)

[0258] 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."

[0259] When searching for rental properties, it is difficult for users to accurately and efficiently reflect their desired conditions and quickly find the best option from a vast amount of property information. Furthermore, there are limited ways to thoroughly understand properties that are far away and difficult to view in person. Therefore, there is a need for a system that can quickly and intuitively suggest the best properties based on the user's desired conditions and provide detailed information, thereby improving the efficiency of the rental property search.

[0260] 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.

[0261] In this invention, the server includes means for analyzing natural language conditions from the user and extracting elements; means for searching for relevant information from multiple information databases based on the extracted elements; means for integrating environmental information based on the search results and generating visualization data; means for generating a three-dimensional model of a selected physical location using virtual reality technology and making it displayable on a terminal; and means for generating prompt text for the generated technology model as needed and using it as input. As a result, users can easily find the optimal rental property based on their desired conditions and intuitively understand the details of the property remotely through virtual viewings.

[0262] "User" refers to the person who operates the system and receives information.

[0263] "Natural language" refers to the forms of language that humans use on a daily basis, and the text that is analyzed in computer processing.

[0264] "Elements" refer to individual conditions necessary for searching and evaluation, which are extracted during the process of analyzing the user's desired conditions.

[0265] An "information database" refers to a collection of structured data that a system accesses and uses to retrieve necessary property information.

[0266] "Related information" refers to information about matching properties and environments that are retrieved from the database based on the user's desired conditions.

[0267] "Environmental information" refers to information about the surrounding characteristics and area of ​​a property, and is a factor that should be considered when choosing a property.

[0268] "Visualized data" refers to a data format that is visually organized so that users can intuitively understand the information.

[0269] "Virtual reality technology" refers to technology that allows users to experience a three-dimensional space created by a computer program.

[0270] A "three-dimensional model" refers to data in a virtual space that represents the interior and exterior of a property in three dimensions.

[0271] A "generative technology model" refers to a model that autonomously generates and provides information using technologies such as artificial intelligence.

[0272] A "prompt statement" refers to a sentence that specifies the instructions or conditions that are input into a generative technology model.

[0273] This system aims to provide optimal rental property information based on the user's desired conditions entered in natural language via a terminal. The system's core is a server, which is linked to multiple databases. The server utilizes natural language processing libraries such as "spaCy" and "BERT" to analyze the conditions entered by the user.

[0274] When a user enters conditions such as "apartments near a train station where pets are allowed" through the chatbot interface on their device, the information is first sent to the server. The server performs text analysis and extracts the condition items. This analysis breaks down the input natural language into its constituent elements and converts them into the required format.

[0275] Next, the server uses the extracted criteria to search the database. SQL and NoSQL technologies are used for the search, and additional information can be obtained from external APIs (e.g., map service APIs) as needed. This makes it possible to thoroughly gather information that meets the user's needs.

[0276] The acquired information is integrated by the server and visualized using a data visualization library (e.g., D3.js). The generated visualization data is sent to the user's device and presented intuitively in map or list format. This allows the user to easily understand the surrounding environment and the geographical location of the property.

[0277] In addition, users can use filtering functions to refine and modify their search criteria. This allows them to narrow down their search by budget, room size, and other factors. Furthermore, the server generates a 3D model of the property selected by the user using virtual reality technology and delivers it to the device in the form of a virtual tour. This technology uses WebGL, allowing users to view the interior in detail without actually visiting the property.

[0278] As a specific example, the prompt text for the generative AI model is in the form of "Looking for a 1LDK apartment near a station in Tokyo with a pet allowance of within 50,000 yen". By sending this prompt, the model will return optimal property information. By integrating these technologies, the system enables users to efficiently find properties closest to their wishes.

[0279] The flow of the specific process in Example 1 will be described using FIG. 11.

[0280] Step 1:

[0281] The user inputs the desired conditions in natural language through the terminal. An example of this input is "An apartment near a station where pets can be kept". This data is composed by the user on the terminal and sent to the server. In this process, the user's request is initialized and a query to the system is started.

[0282] Step 2:

[0283] The server receives the natural language input by the user and analyzes it using a natural language processing library (e.g., spaCy, BERT). Through this analysis, the conditional items are extracted. The received text is tokenized, relevant keywords and phrases are identified, and they are converted into a form for use in database search. The output is a list of structured searchable conditional items.

[0284] Step 3:

[0285] The server searches the information database using the extracted conditions. SQL or NoSQL technologies are used to search for property information that matches the conditions, and it is also possible to obtain supplementary information from external APIs (e.g., map service APIs). The input is a list of conditional items, and the output is property information that matches the conditions. This process includes the collection of property summaries, location information, and regional characteristic data.

[0286] Step 4:

[0287] The server integrates the search results and formats them as visualization data using a data visualization library (e.g., D3.js). Maps or list formats that visually represent location information and related property information are generated. The input is a set of property information, and the output is a visualized dataset presented to the user.

[0288] Step 5:

[0289] The user checks the visualization data received from the server through the terminal and uses filtering to narrow down the conditions. Additional conditions such as budget and room size can be specified through additional interactions. This operation improves the accuracy of the visualization data. The input is the visualization data and additional conditions, and the output is the filtered revised information.

[0290] Step 6:

[0291] The server generates a three-dimensional model for the property selected by the user using virtual reality technology. Using WebGL technology, the internal structure of the property is reproduced in three dimensions and sent to the terminal. As a result, the user can perform a virtual tour. The input is property information and a visualization request, and the output is a three-dimensional model experienced by the user.

[0292] Step 7:

[0293] If necessary, the server generates a prompt sentence for the generation technology model and utilizes it as an input. As a specific example, a prompt such as "Looking for a 1LDK with a rent of less than 50,000 yen near a station in Tokyo and allowing pets" can be considered. The prompt sentence is analyzed by the generation AI model and used to obtain additional recommendations. The input is the user's conditions and situation, and the output is recommendations and additional information.

[0294] (Application Example 1)

[0295] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0296] Traditional rental property search systems require users to physically visit properties, which is time-consuming and costly. Furthermore, it's often difficult to select properties based on detailed criteria, and real-time information about the surrounding environment is often unavailable. In this context, there is a need for a method that allows users to efficiently and intuitively select properties from the comfort of their homes.

[0297] 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.

[0298] In this invention, the server includes means for analyzing user-defined natural language preferences and extracting condition items, means for searching for matching information from multiple data records based on the extracted condition items, and means for generating visualization data for a virtual viewing of an item, which can be visually confirmed on a terminal. This allows users to select properties based on detailed conditions from the comfort of their homes, and further enables them to visually confirm the surrounding environment in real time through the virtual viewing mode.

[0299] A "user" is an individual or legal entity that uses an information system to search for rental properties.

[0300] "Natural language" refers to the forms of words and sentences that humans use on a daily basis, and it is a linguistic form from which conditions are extracted through computer analysis.

[0301] "Desired conditions" refer to the specific features and requirements that the user seeks in a rental property, including location, price, and amenities.

[0302] "Condition items" are classified elements that the system identifies and uses to perform specific database searches, based on the user's desired conditions.

[0303] "Data recording" is an information source where information related to rental properties is stored and serves as the basis for the system to search for information.

[0304] "Matched information" refers to properties and related data that meet the user's condition items and is information that conforms to the user's needs.

[0305] "Virtual interior view" is a means that enables a user to visually experience the interior of a property using information technology without physically visiting the property.

[0306] "Visualization data" is a form of data provided in a format that is intuitive and easy for users to understand, including maps and 3D models.

[0307] The system that realizes this invention efficiently provides rental property information according to the user's requests. Hereinafter, embodiments of the system will be described.

[0308] The server receives the desired conditions input by the user in natural language using a terminal. As hardware, a general server computer is used, and by utilizing the Google Cloud Natural Language API as software, the input natural language is analyzed to extract specific condition items. Thereby, the user's desired conditions are clearly determined.

[0309] The extracted condition items are searched by the server across multiple databases to collect the corresponding information. This information includes detailed data of rental properties and surrounding environment information and is important for generating visualization data.

[0310] Once matching information is integrated, the server uses Unity to generate 3D models of the items and converts them into visualization data for virtual viewings. This visualization data is then transferred to the terminal and presented to the user in a usable format. Specifically, users can use their smartphones to explore the property in detail in virtual reality mode, gaining an intuitive understanding of the surrounding environment and property details.

[0311] For example, if a user enters "I'm looking for a detached house with a large garden," the server automatically searches for properties that match that requirement and allows the user to visually experience the size and layout of the garden using a 3D model. In this case, an example of a prompt message would be "I'd like a house with a large garden. Please show me properties that suit me."

[0312] In this way, users can explore rental properties and gain a deep understanding of their characteristics from the comfort of their own homes. This system will allow users to efficiently find their ideal property.

[0313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0314] Step 1:

[0315] The user enters their desired conditions in natural language using their device. For example, the user might enter a request such as "a pet-friendly apartment near a train station" into the chatbot. The input data is sent from the device to the server as natural language text.

[0316] Step 2:

[0317] The server analyzes the received natural language input. During this process, it uses the Google Cloud Natural Language API to process the data and extract desired conditions from the text. The input is natural language text data, and the output is a set of extracted condition items.

[0318] Step 3:

[0319] The server searches the database using the extracted criteria. It accesses multiple databases and performs data calculations to search for rental property information based on the criteria. The input is a set of criteria, and the output is a list of candidate properties.

[0320] Step 4:

[0321] The server integrates surrounding environment information from search results and generates visualization data. It uses Unity to create 3D models of properties and performs data processing to create visualization data compatible with virtual viewings. The input is a list of candidate properties, and the output is visualization data including 3D models.

[0322] Step 5:

[0323] The generated visualization data is sent from the server to the terminal. The terminal interactively presents property information to the user, enabling the user to take a virtual reality tour. The input is the visualization data, and the output is the property information and virtual tour experience displayed on the terminal.

[0324] 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.

[0325] This invention is a property suggestion system that takes into account the user's psychological factors, enabling more appropriate property searches based on the user's requirements. This system incorporates an emotion engine that recognizes and analyzes emotions through the user's natural language input, and by adding emotional nuances to the conditions requested by the user, it can achieve more satisfying results.

[0326] First, the user enters their desired conditions in natural language using their device. During this process, the emotion engine analyzes the user's emotions (e.g., joy, sadness, anxiety) in real time. For example, input such as "I want an apartment where there is little noise and I can live quietly" can detect the user's stress levels and desire for calm.

[0327] The server generates a search query using the analyzed sentiment data along with the specified criteria. This query filters and searches for properties that best match the user's desired conditions and sentiments through an internal database and an external API. In this case, property information that guarantees a quiet environment is given priority.

[0328] Search results are integrated for visualization, and the presentation method is adjusted according to the user's emotional state. For example, a calming color scheme is used to present information, enhancing the sense of anticipation for living in a peaceful environment.

[0329] Furthermore, users can add or modify conditions using an interactive filtering function. The emotion engine also operates during this filtering process, adjusting the filtering method according to the user's emotions.

[0330] Finally, for properties that pique the user's interest, a virtual viewing option allows for more detailed examination. Here too, the emotion engine monitors the user's reactions and further personalizes the information presented.

[0331] As a result, this system enables emotionally sensitive property recommendations and improves the user experience. By integrating user emotions into its approach, users can efficiently find properties that better suit them, resulting in higher satisfaction.

[0332] The following describes the processing flow.

[0333] Step 1:

[0334] Users use their devices to input their desired property criteria in natural language. At this time, an emotion engine recognizes the user's emotions in real time from their input and analyzes the emotions they are feeling when entering their criteria. This emotion data is then used for subsequent processing.

[0335] Step 2:

[0336] The server extracts conditional items from the user's natural language. This utilizes natural language processing technology to extract the specific conditions the user desires (e.g., quiet place, pet-friendly). Simultaneously, the results of the emotion engine analysis are also obtained, and the user's emotional state (e.g., want to feel safe, want to avoid stress) is integrated as supplementary information.

[0337] Step 3:

[0338] The server generates a search query based on the extracted criteria and sentiment information, and searches for relevant property information using the property database and external APIs. At this stage, it prioritizes filtering for properties that highlight a specific sentiment (e.g., properties with a prominent peaceful environment).

[0339] Step 4:

[0340] The server organizes the acquired property information and generates visualization data to present it to the user in an emotionally sensitive visual way. For example, if the user is in a mood to relax, the screen's color scheme and design will be expressed in a tone that reflects that emotion.

[0341] Step 5:

[0342] Users can view property information displayed on their device and further refine their search using the filtering function. During this process, the emotion engine continuously analyzes the user's reactions and incorporates this information into the presentation of filtering options.

[0343] Step 6:

[0344] For properties that the user is particularly interested in, the server provides virtual viewing data, allowing the user to visually check the details on their device. Throughout this process, information is presented based on the user's emotional state, striving to enhance user satisfaction.

[0345] Through this series of steps, the emotion engine is integrated into the entire system, enabling personalized property recommendations that take user emotions into account.

[0346] (Example 2)

[0347] 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".

[0348] Traditional property search systems simply suggested properties based on criteria without considering the user's emotions or psychological factors. Therefore, it was difficult to enhance the user's subjective satisfaction, resulting in a limited user experience. Furthermore, they were unable to provide interactive feedback that responded to the user's emotions, making it difficult to deliver optimized search results.

[0349] 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.

[0350] In this invention, the server includes means for analyzing desired conditions in natural language from the user and extracting condition items; means for analyzing the extracted condition items and the user's emotions and dynamically generating a search query based on the user's emotional state; and means for searching for matching information from multiple data storages using the generated search query. This enables optimal property suggestions that integrate the user's emotions and conditions.

[0351] "Natural language" refers to linguistic expressions used to express desires, based on the language forms that users use on a daily basis.

[0352] "Condition items" are indicators that are analyzed from the user's natural language input and specifically indicate their wishes and requirements regarding the property.

[0353] "Emotion analysis" is a process that recognizes the emotions contained in the user's natural language input and quantifies the user's psychological state.

[0354] A "search query" is a set of instructions generated based on the user's preferences and emotional state, used to retrieve relevant information from data storage.

[0355] "Data storage" refers to a data storage system that holds property information and related surrounding data, and provides information in response to search queries.

[0356] "Visualization" is the process of organizing acquired information into a format that is easy for users to understand and representing it visually.

[0357] A "user-emotion-responsive approach" is a method that adjusts search results and presentation methods to best suit the user's emotions.

[0358] "Interactive presentation" refers to a function that allows users to interact with and respond to the information presented, enabling two-way use of the information.

[0359] This invention relates to a property recommendation system that takes into account the user's psychological factors, and the system operates between a server, a terminal, and the user. The user inputs their desired property conditions into the terminal using natural language. This natural language input is analyzed by an emotion analysis engine, which interprets the user's emotions. This emotion analysis engine is, for example, software that uses emotion recognition algorithms and natural language processing technology.

[0360] The terminal processes text data entered by the user in real time and sends sentiment data to the server. The server searches for information in data storage using dynamically generated search queries based on the sentiment data and the user's preferences. Data storage is an accessible pool of information based on internal databases and external information provision services.

[0361] The retrieved search results are visualized by the server according to the user's emotional state and sent to the device. The device displays the results to the user using calming colors and designs, and the user can interact with the presented information. This interaction incorporates further sentiment analysis, and filtering methods are performed according to the user's emotions.

[0362] For example, if a user enters "I want to find a quiet place with little noise," the emotion engine analyzes the user's desire for "peace of mind" and "relaxation." Based on this, the server identifies properties that guarantee a quiet environment and presents them to the user as a priority.

[0363] An example of a prompt message is: "Analyze the user's emotions and extract the property features they desire. Input: 'I want to live in a quiet environment with no noise.'"

[0364] With this configuration, the present invention has the effect of improving the subjective satisfaction of users and realizing more efficient and personalized property recommendations.

[0365] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0366] Step 1:

[0367] The user uses a device to input their desired property conditions in natural language. The device receives this input and sends it as text data to the sentiment analysis engine. A possible specific input might be, "I want to find a quiet place with little noise." The output is text data in a format that the sentiment analysis engine can process.

[0368] Step 2:

[0369] The device's emotion analysis engine analyzes received text data and evaluates the user's emotions. The input is the user's natural language text, and the analysis algorithm determines the emotional state (e.g., reassured, relaxed, stressed). The output is metadata indicating this emotional state. For example, the emotion "reassured" might be extracted.

[0370] Step 3:

[0371] The server generates a search query from the received sentiment metadata and user preferences. Specifically, it dynamically constructs a query to prioritize properties that offer a quiet environment based on the sentiment state and conditional items. The input is the analyzed sentiment and conditional items, and the output is the search query to be executed in data storage.

[0372] Step 4:

[0373] The server uses the generated search query to search for matching information from the data storage. This search process accesses internal databases and external APIs to retrieve property information that matches the user's desired criteria. The input is a dynamically generated search query, and the output is a filtered list of property information.

[0374] Step 5:

[0375] The server integrates search results as visual data and generates information presented through an interface tailored to the user's emotional state. Input includes search results, which are visualized using reassuring color schemes and designs. Output is the visualized data sent to the terminal.

[0376] Step 6:

[0377] Users view visualized property information on their device and interactively modify or add criteria. The device then performs sentiment analysis again in response to these actions, re-filtering the criteria. The input is the user's actions, and the output is the updated search query. For example, the condition "more green places" might be added.

[0378] Step 7:

[0379] When a user expresses interest in a particular property, the server provides virtual tour data for that property and performs sentiment analysis tailored to the user's reactions. The input is the user's selection when starting the virtual tour, and the output is customized visual data based on the user's reactions.

[0380] (Application Example 2)

[0381] 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."

[0382] Traditional online shopping systems have the problem of lower user satisfaction because they cannot suggest products that take into account the user's psychological and emotional factors. Furthermore, it is difficult to implement interactive filtering and visual representations that respond to user emotions, making it challenging to suggest products that meet individual user needs.

[0383] 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.

[0384] In this invention, the server includes means for analyzing user-defined natural language preferences and extracting condition items and emotion data; means for searching for matching information from multiple databases based on the extracted condition items and emotion data; and means for integrating surrounding environment information based on the search results and generating visualization data corresponding to the emotion. This enables personalized product suggestions that take the user's emotions into consideration.

[0385] "Desired conditions in natural language" refers to the conditions that the user desires, entered using everyday language.

[0386] "Condition items" are specific elements or criteria extracted from the user's desired conditions.

[0387] "Emotional data" refers to information that represents the psychological state and emotional tendencies of a user, analyzed from their input.

[0388] A "database" is an electronic record system for systematically collecting and managing information.

[0389] "Surrounding environment information" refers to information that indicates external conditions and characteristics related to the product or service in question.

[0390] "Interactive presentation" means that information is displayed in a way that allows the user and the system to influence each other.

[0391] A "filtering method" is a technique for selecting information that meets specific criteria from a large amount of data.

[0392] "Visualized data" refers to data that has been processed to represent information visually.

[0393] "Virtual preview" is a technology that simulates information in a way that closely resembles the actual visual experience.

[0394] The system that realizes this invention mainly consists of a server, a user terminal, and an emotion analysis engine. First, the user inputs their desired conditions into the terminal using natural language, and this is sent to the server. This terminal should preferably be a high-performance smartphone or smart glasses.

[0395] The server analyzes the input natural language data and extracts conditional items and sentiment data. This uses software such as AWS Comprehend as the sentiment analysis engine. The analyzed data is sent as queries to multiple databases, and matching information is collected. This database is an electronic record system for systematically managing products and related information.

[0396] Next, the server integrates the collected information with the user's emotional data to generate visualization data that reflects their emotions. This visualization data is created using the latest visualization technologies in human-computer interaction.

[0397] The generated visualization data is presented interactively on the device in a way that adapts to the user's emotions. The user can use this visualization to select products and, if necessary, further refine their search criteria through filtering functions.

[0398] For example, if a user seeking relaxation enters "I want calming interior design" into their device, the emotion analysis engine extracts the emotion of relaxation, and the server filters interior products that match this. As a result, the visualized data will highlight calming designs with nature themes, such as green and wood tones.

[0399] An example of a prompt for a generative AI model might be: "We are looking for products that make the user feel relaxed. Please list products that evoke a feeling of relaxation based on the emotion analysis results."

[0400] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0401] Step 1:

[0402] Users use devices such as smartphones or smart glasses to input their desired conditions in natural language. This input text is sent to the server. For example, if the input is "a comfortable sofa," the text data is sent to the server as output.

[0403] Step 2:

[0404] The server sends the received natural language text to an emotion analysis engine to extract emotion data. Using AWS Comprehend, it analyzes emotions such as "relaxed" in the text and obtains emotion data as output.

[0405] Step 3:

[0406] The server queries the product database based on the extracted criteria ("sofa") and emotion data ("relaxed") to find matching product information. The input is the criteria and emotion, and the output is a list of products that fit them.

[0407] Step 4:

[0408] The server integrates surrounding environment information from the search results and generates emotion-responsive visualization data. Using visualization tools, the collected results are presented in calming colors and designs. The generated visualization data is then output.

[0409] Step 5:

[0410] The server sends this visualization data to the user's device and presents it in an interactive format that is appropriate to their emotions. This allows the user to select products based on the visualized information.

[0411] Step 6:

[0412] Users can further refine their criteria using the interactive filtering function. As a result, they send the new criteria back to the server and receive updated results.

[0413] Step 7:

[0414] Finally, the user reviews the details of the selected product and performs a virtual preview as needed. The preview displays simulated visual information of the specified product.

[0415] 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.

[0416] 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.

[0417] 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.

[0418] [Third Embodiment]

[0419] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0420] 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.

[0421] 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).

[0422] 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.

[0423] 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.

[0424] 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).

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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".

[0431] This invention is a system that efficiently proposes rental properties that best match the user's needs by analyzing the user's input of desired conditions in natural language through their terminal. This system works in conjunction with multiple databases centered around a server to provide users with comprehensive property information.

[0432] First, the user uses a device to input their desired conditions in natural language through a chatbot-style interface. For example, by entering conditions such as "an apartment near a train station where pets are allowed," the user's specific request is transmitted to the system.

[0433] The server processes the input natural language through text analysis and clearly extracts the required criteria. Based on these analysis results, the server accesses multiple databases to search for property information that matches the criteria. The information includes a wide range of details such as property overview, location, surrounding facilities, and regional characteristics, and it is also possible to obtain information using external APIs as needed.

[0434] After integrating the search results, the server processes the data in a visually easy-to-understand format and presents it to the user's device in map or list format. This allows the user to intuitively understand the geographical location of the property and surrounding facilities.

[0435] Furthermore, users can utilize filtering options to narrow down their search criteria through interaction. For example, by specifying additional conditions such as budget or room size, they can obtain more detailed property information.

[0436] Ultimately, for properties that users are interested in, a means of virtual viewing is provided. The server generates a 3D model of the property's interior, enabling a virtual tour on the user's device. This feature allows users to conduct detailed observation and analysis without actually visiting the property.

[0437] According to embodiments of the present invention, the process of searching for rental properties is significantly streamlined, allowing users to easily find properties that suit their lifestyle.

[0438] The following describes the processing flow.

[0439] Step 1:

[0440] Users use their devices to input their desired rental conditions in natural language. Through the chatbot interface, they communicate their requests to the system, such as "I'm looking for a pet-friendly apartment within walking distance of the station."

[0441] Step 2:

[0442] The server analyzes the received natural language input and uses natural language processing techniques to extract conditional items. Here, specific requirements based on the user's preferences (e.g., within walking distance of a train station, pet-friendly, apartment) are identified.

[0443] Step 3:

[0444] Based on the extracted conditions, the server accesses its internal database and, if necessary, external APIs to search for corresponding property information. The search generates and executes queries to filter properties that match the user's desired criteria.

[0445] Step 4:

[0446] The server integrates property information obtained from search results and collects and integrates additional information, including surrounding facilities and regional characteristics. The integrated data is then prepared to be presented to the user as visual information.

[0447] Step 5:

[0448] The server sends visualized information to the user's terminal, which the user then views on the terminal in map or list format. Here, the location of the property and its relationship to surrounding facilities are displayed in an intuitive manner.

[0449] Step 6:

[0450] Users can further refine their search criteria using filtering options based on the information provided on their device. This allows them to specify additional conditions, such as budget or room size, to narrow down the options even further.

[0451] Step 7:

[0452] Finally, the user selects the option to virtually tour the properties they are interested in. The server generates a 3D model of the selected property and provides the data so that the user can virtually tour its details through their device.

[0453] Through this series of steps, users can efficiently find rental properties that meet their desired conditions.

[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] When searching for rental properties, it is difficult for users to accurately and efficiently reflect their desired conditions and quickly find the best option from a vast amount of property information. Furthermore, there are limited ways to thoroughly understand properties that are far away and difficult to view in person. Therefore, there is a need for a system that can quickly and intuitively suggest the best properties based on the user's desired conditions and provide detailed information, thereby improving the efficiency of the rental property search.

[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 natural language conditions from the user and extracting elements; means for searching for relevant information from multiple information databases based on the extracted elements; means for integrating environmental information based on the search results and generating visualization data; means for generating a three-dimensional model of a selected physical location using virtual reality technology and making it displayable on a terminal; and means for generating prompt text for the generated technology model as needed and using it as input. As a result, users can easily find the optimal rental property based on their desired conditions and intuitively understand the details of the property remotely through virtual viewings.

[0459] "User" refers to the person who operates the system and receives information.

[0460] "Natural language" refers to the forms of language that humans use on a daily basis, and the text that is analyzed in computer processing.

[0461] "Elements" refer to individual conditions necessary for searching and evaluation, which are extracted during the process of analyzing the user's desired conditions.

[0462] An "information database" refers to a collection of structured data that a system accesses and uses to retrieve necessary property information.

[0463] "Related information" refers to information about matching properties and environments that are retrieved from the database based on the user's desired conditions.

[0464] "Environmental information" refers to information about the surrounding characteristics and area of ​​a property, and is a factor that should be considered when choosing a property.

[0465] "Visualized data" refers to a data format that is visually organized so that users can intuitively understand the information.

[0466] "Virtual reality technology" refers to technology that allows users to experience a three-dimensional space created by a computer program.

[0467] A "three-dimensional model" refers to data in a virtual space that represents the interior and exterior of a property in three dimensions.

[0468] A "generative technology model" refers to a model that autonomously generates and provides information using technologies such as artificial intelligence.

[0469] A "prompt statement" refers to a sentence that specifies the instructions or conditions that are input into a generative technology model.

[0470] This system aims to provide optimal rental property information based on the user's desired conditions entered in natural language via a terminal. The system's core is a server, which is linked to multiple databases. The server utilizes natural language processing libraries such as "spaCy" and "BERT" to analyze the conditions entered by the user.

[0471] When a user enters conditions such as "apartments near a train station where pets are allowed" through the chatbot interface on their device, the information is first sent to the server. The server performs text analysis and extracts the condition items. This analysis breaks down the input natural language into its constituent elements and converts them into the required format.

[0472] Next, the server uses the extracted criteria to search the database. SQL and NoSQL technologies are used for the search, and additional information can be obtained from external APIs (e.g., map service APIs) as needed. This makes it possible to thoroughly gather information that meets the user's needs.

[0473] The acquired information is integrated by the server and visualized using a data visualization library (e.g., D3.js). The generated visualization data is sent to the user's device and presented intuitively in map or list format. This allows the user to easily understand the surrounding environment and the geographical location of the property.

[0474] In addition, users can use filtering functions to refine and modify their search criteria. This allows them to narrow down their search by budget, room size, and other factors. Furthermore, the server generates a 3D model of the property selected by the user using virtual reality technology and delivers it to the device in the form of a virtual tour. This technology uses WebGL, allowing users to view the interior in detail without actually visiting the property.

[0475] As a concrete example, the prompt message sent to the generating AI model is in the format of "I'm looking for a 1LDK apartment in Tokyo that's pet-friendly, near a train station, and has a rent of 50,000 yen or less." By sending this prompt, the model returns the most suitable property information. By integrating these technologies, the system allows users to efficiently find properties that best match their preferences.

[0476] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0477] Step 1:

[0478] The user enters their desired conditions in natural language via their device. An example of this input might be "apartments near a train station where pets are allowed." This data is configured by the user on their device and sent to the server. In this process, the user's request is initialized and a query to the system is initiated.

[0479] Step 2:

[0480] The server receives natural language input from the user and parses it using a natural language processing library (e.g., spaCy, BERT). This parse extracts conditional items. The received text is tokenized, relevant keywords and phrases are identified, and they are converted into a format for use in database searches. The output is a structured list of searchable conditional items.

[0481] Step 3:

[0482] The server searches the information database using the extracted conditions. SQL and NoSQL technologies are used to search for property information that matches the conditions, and it is also possible to retrieve supplementary information from external APIs (e.g., map service APIs). The input is a list of condition items, and the output is property information that matches the conditions. This process includes collecting property overviews, location information, and regional characteristics data.

[0483] Step 4:

[0484] The server integrates the search results and formats them as visualized data using a data visualization library (e.g., D3.js). It generates maps and list formats that visually represent location information and related property information. The input is a collection of property information, and the output is a visualized dataset presented to the user.

[0485] Step 5:

[0486] The user reviews the visualization data received from the server via their device and uses filtering to narrow down the criteria. Additional conditions, such as budget and room size, can be specified through further interaction. This operation improves the accuracy of the visualization data. Inputs are the visualization data and additional conditions, and output is the filtered and revised information.

[0487] Step 6:

[0488] The server generates a 3D model of the property selected by the user using virtual reality technology. Using WebGL technology, the internal structure of the property is reproduced in 3D and sent to the terminal. This allows the user to conduct a virtual tour. Inputs are property information and visualization requests, and output is the 3D model experienced by the user.

[0489] Step 7:

[0490] If necessary, the server generates prompt sentences for the generative technology model and uses them as input. A concrete example of a prompt might be, "I'm looking for a 1LDK apartment in Tokyo that's pet-friendly, near a train station, and has a rent of 50,000 yen or less." The prompt sentences are analyzed by the generative AI model and used to obtain additional recommendations. The input is the user's conditions and situation, and the output is recommendations and additional information.

[0491] (Application Example 1)

[0492] 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."

[0493] Traditional rental property search systems require users to physically visit properties, which is time-consuming and costly. Furthermore, it's often difficult to select properties based on detailed criteria, and real-time information about the surrounding environment is often unavailable. In this context, there is a need for a method that allows users to efficiently and intuitively select properties from the comfort of their homes.

[0494] 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.

[0495] In this invention, the server includes means for analyzing user-defined natural language preferences and extracting condition items, means for searching for matching information from multiple data records based on the extracted condition items, and means for generating visualization data for a virtual viewing of an item, which can be visually confirmed on a terminal. This allows users to select properties based on detailed conditions from the comfort of their homes, and further enables them to visually confirm the surrounding environment in real time through the virtual viewing mode.

[0496] A "user" is an individual or legal entity that uses an information system to search for rental properties.

[0497] "Natural language" refers to the forms of words and sentences that humans use on a daily basis, and it is a linguistic form from which conditions are extracted through computer analysis.

[0498] "Desired conditions" refer to the specific features and requirements that the user seeks in a rental property, including location, price, and amenities.

[0499] "Condition items" are classified elements that the system identifies and uses to perform specific database searches, based on the user's desired conditions.

[0500] "Data records" refer to information sources where information related to rental properties is stored, and serve as the foundation for systems to search for that information.

[0501] "Matching information" refers to properties and related data that match the user's criteria and are information that suits the user's needs.

[0502] "Virtual viewing" is a method that allows users to visually experience the interior of a property using information technology without physically visiting the property.

[0503] "Visualized data" refers to data presented in a format that is easy for users to intuitively understand, and includes maps and 3D models.

[0504] The system that realizes this invention efficiently provides rental property information according to the user's requests. The following describes an embodiment of this system.

[0505] The server receives the user's desired conditions entered in natural language using a terminal. Using a standard server computer as hardware and the Google Cloud Natural Language API as software, the server analyzes the entered natural language and extracts specific condition items. This ensures a clear understanding of the user's desired conditions.

[0506] The extracted criteria are searched across multiple databases by the server to collect relevant information. This information includes detailed data on rental properties and surrounding environment information, and is important for generating visualization data.

[0507] Once matching information is integrated, the server uses Unity to generate 3D models of the items and converts them into visualization data for virtual viewings. This visualization data is then transferred to the terminal and presented to the user in a usable format. Specifically, users can use their smartphones to explore the property in detail in virtual reality mode, gaining an intuitive understanding of the surrounding environment and property details.

[0508] For example, if a user enters "I'm looking for a detached house with a large garden," the server automatically searches for properties that match that requirement and allows the user to visually experience the size and layout of the garden using a 3D model. In this case, an example of a prompt message would be "I'd like a house with a large garden. Please show me properties that suit me."

[0509] In this way, users can explore rental properties and gain a deep understanding of their characteristics from the comfort of their own homes. This system will allow users to efficiently find their ideal property.

[0510] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0511] Step 1:

[0512] The user enters their desired conditions in natural language using their device. For example, the user might enter a request such as "a pet-friendly apartment near a train station" into the chatbot. The input data is sent from the device to the server as natural language text.

[0513] Step 2:

[0514] The server analyzes the received natural language input. During this process, it uses the Google Cloud Natural Language API to process the data and extract desired conditions from the text. The input is natural language text data, and the output is a set of extracted condition items.

[0515] Step 3:

[0516] The server searches the database using the extracted criteria. It accesses multiple databases and performs data calculations to search for rental property information based on the criteria. The input is a set of criteria, and the output is a list of candidate properties.

[0517] Step 4:

[0518] The server integrates surrounding environment information from search results and generates visualization data. It uses Unity to create 3D models of properties and performs data processing to create visualization data compatible with virtual viewings. The input is a list of candidate properties, and the output is visualization data including 3D models.

[0519] Step 5:

[0520] The generated visualization data is sent from the server to the terminal. The terminal interactively presents property information to the user, enabling the user to take a virtual reality tour. The input is the visualization data, and the output is the property information and virtual tour experience displayed on the terminal.

[0521] 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.

[0522] This invention is a property suggestion system that takes into account the user's psychological factors, enabling more appropriate property searches based on the user's requirements. This system incorporates an emotion engine that recognizes and analyzes emotions through the user's natural language input, and by adding emotional nuances to the conditions requested by the user, it can achieve more satisfying results.

[0523] First, the user enters their desired conditions in natural language using their device. During this process, the emotion engine analyzes the user's emotions (e.g., joy, sadness, anxiety) in real time. For example, input such as "I want an apartment where there is little noise and I can live quietly" can detect the user's stress levels and desire for calm.

[0524] The server generates a search query using the analyzed sentiment data along with the specified criteria. This query filters and searches for properties that best match the user's desired conditions and sentiments through an internal database and an external API. In this case, property information that guarantees a quiet environment is given priority.

[0525] Search results are integrated for visualization, and the presentation method is adjusted according to the user's emotional state. For example, a calming color scheme is used to present information, enhancing the sense of anticipation for living in a peaceful environment.

[0526] Furthermore, users can add or modify conditions using an interactive filtering function. The emotion engine also operates during this filtering process, adjusting the filtering method according to the user's emotions.

[0527] Finally, for properties that pique the user's interest, a virtual viewing option allows for more detailed examination. Here too, the emotion engine monitors the user's reactions and further personalizes the information presented.

[0528] As a result, this system enables emotionally sensitive property recommendations and improves the user experience. By integrating user emotions into its approach, users can efficiently find properties that better suit them, resulting in higher satisfaction.

[0529] The following describes the processing flow.

[0530] Step 1:

[0531] Users use their devices to input their desired property criteria in natural language. At this time, an emotion engine recognizes the user's emotions in real time from their input and analyzes the emotions they are feeling when entering their criteria. This emotion data is then used for subsequent processing.

[0532] Step 2:

[0533] The server extracts conditional items from the user's natural language. This utilizes natural language processing technology to extract the specific conditions the user desires (e.g., quiet place, pet-friendly). Simultaneously, the results of the emotion engine analysis are also obtained, and the user's emotional state (e.g., want to feel safe, want to avoid stress) is integrated as supplementary information.

[0534] Step 3:

[0535] The server generates a search query based on the extracted criteria and sentiment information, and searches for relevant property information using the property database and external APIs. At this stage, it prioritizes filtering for properties that highlight a specific sentiment (e.g., properties with a prominent peaceful environment).

[0536] Step 4:

[0537] The server organizes the acquired property information and generates visualization data to present it to the user in an emotionally sensitive visual way. For example, if the user is in a mood to relax, the screen's color scheme and design will be expressed in a tone that reflects that emotion.

[0538] Step 5:

[0539] Users can view property information displayed on their device and further refine their search using the filtering function. During this process, the emotion engine continuously analyzes the user's reactions and incorporates this information into the presentation of filtering options.

[0540] Step 6:

[0541] For properties that the user is particularly interested in, the server provides virtual viewing data, allowing the user to visually check the details on their device. Throughout this process, information is presented based on the user's emotional state, striving to enhance user satisfaction.

[0542] Through this series of steps, the emotion engine is integrated into the entire system, enabling personalized property recommendations that take user emotions into account.

[0543] (Example 2)

[0544] 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."

[0545] Traditional property search systems simply suggested properties based on criteria without considering the user's emotions or psychological factors. Therefore, it was difficult to enhance the user's subjective satisfaction, resulting in a limited user experience. Furthermore, they were unable to provide interactive feedback that responded to the user's emotions, making it difficult to deliver optimized search results.

[0546] 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.

[0547] In this invention, the server includes means for analyzing desired conditions in natural language from the user and extracting condition items; means for analyzing the extracted condition items and the user's emotions and dynamically generating a search query based on the user's emotional state; and means for searching for matching information from multiple data storages using the generated search query. This enables optimal property suggestions that integrate the user's emotions and conditions.

[0548] "Natural language" refers to linguistic expressions used to express desires, based on the language forms that users use on a daily basis.

[0549] "Condition items" are indicators that are analyzed from the user's natural language input and specifically indicate their wishes and requirements regarding the property.

[0550] "Emotion analysis" is a process that recognizes the emotions contained in the user's natural language input and quantifies the user's psychological state.

[0551] A "search query" is a set of instructions generated based on the user's preferences and emotional state, used to retrieve relevant information from data storage.

[0552] "Data storage" refers to a data storage system that holds property information and related surrounding data, and provides information in response to search queries.

[0553] "Visualization" is the process of organizing acquired information into a format that is easy for users to understand and representing it visually.

[0554] A "user-emotion-responsive approach" is a method that adjusts search results and presentation methods to best suit the user's emotions.

[0555] "Interactive presentation" refers to a function that allows users to interact with and respond to the information presented, enabling two-way use of the information.

[0556] This invention relates to a property recommendation system that takes into account the user's psychological factors, and the system operates between a server, a terminal, and the user. The user inputs their desired property conditions into the terminal using natural language. This natural language input is analyzed by an emotion analysis engine, which interprets the user's emotions. This emotion analysis engine is, for example, software that uses emotion recognition algorithms and natural language processing technology.

[0557] The terminal processes text data entered by the user in real time and sends sentiment data to the server. The server searches for information in data storage using dynamically generated search queries based on the sentiment data and the user's preferences. Data storage is an accessible pool of information based on internal databases and external information provision services.

[0558] The retrieved search results are visualized by the server according to the user's emotional state and sent to the device. The device displays the results to the user using calming colors and designs, and the user can interact with the presented information. This interaction incorporates further sentiment analysis, and filtering methods are performed according to the user's emotions.

[0559] For example, if a user enters "I want to find a quiet place with little noise," the emotion engine analyzes the user's desire for "peace of mind" and "relaxation." Based on this, the server identifies properties that guarantee a quiet environment and presents them to the user as a priority.

[0560] An example of a prompt message is: "Analyze the user's emotions and extract the property features they desire. Input: 'I want to live in a quiet environment with no noise.'"

[0561] With this configuration, the present invention has the effect of improving the subjective satisfaction of users and realizing more efficient and personalized property recommendations.

[0562] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0563] Step 1:

[0564] The user uses a device to input their desired property conditions in natural language. The device receives this input and sends it as text data to the sentiment analysis engine. A possible specific input might be, "I want to find a quiet place with little noise." The output is text data in a format that the sentiment analysis engine can process.

[0565] Step 2:

[0566] The device's emotion analysis engine analyzes received text data and evaluates the user's emotions. The input is the user's natural language text, and the analysis algorithm determines the emotional state (e.g., reassured, relaxed, stressed). The output is metadata indicating this emotional state. For example, the emotion "reassured" might be extracted.

[0567] Step 3:

[0568] The server generates a search query from the received sentiment metadata and user preferences. Specifically, it dynamically constructs a query to prioritize properties that offer a quiet environment based on the sentiment state and conditional items. The input is the analyzed sentiment and conditional items, and the output is the search query to be executed in data storage.

[0569] Step 4:

[0570] The server uses the generated search query to search for matching information from the data storage. This search process accesses internal databases and external APIs to retrieve property information that matches the user's desired criteria. The input is a dynamically generated search query, and the output is a filtered list of property information.

[0571] Step 5:

[0572] The server integrates search results as visual data and generates information presented through an interface tailored to the user's emotional state. Input includes search results, which are visualized using reassuring color schemes and designs. Output is the visualized data sent to the terminal.

[0573] Step 6:

[0574] Users view visualized property information on their device and interactively modify or add criteria. The device then performs sentiment analysis again in response to these actions, re-filtering the criteria. The input is the user's actions, and the output is the updated search query. For example, the condition "more green places" might be added.

[0575] Step 7:

[0576] When a user expresses interest in a particular property, the server provides virtual tour data for that property and performs sentiment analysis tailored to the user's reactions. The input is the user's selection when starting the virtual tour, and the output is customized visual data based on the user's reactions.

[0577] (Application Example 2)

[0578] 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."

[0579] Traditional online shopping systems have the problem of lower user satisfaction because they cannot suggest products that take into account the user's psychological and emotional factors. Furthermore, it is difficult to implement interactive filtering and visual representations that respond to user emotions, making it challenging to suggest products that meet individual user needs.

[0580] 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.

[0581] In this invention, the server includes means for analyzing user-defined natural language preferences and extracting condition items and emotion data; means for searching for matching information from multiple databases based on the extracted condition items and emotion data; and means for integrating surrounding environment information based on the search results and generating visualization data corresponding to the emotion. This enables personalized product suggestions that take the user's emotions into consideration.

[0582] "Desired conditions in natural language" refers to the conditions that the user desires, entered using everyday language.

[0583] "Condition items" are specific elements or criteria extracted from the user's desired conditions.

[0584] "Emotional data" refers to information that represents the psychological state and emotional tendencies of a user, analyzed from their input.

[0585] A "database" is an electronic record system for systematically collecting and managing information.

[0586] "Surrounding environment information" refers to information that indicates external conditions and characteristics related to the product or service in question.

[0587] "Interactive presentation" means that information is displayed in a way that allows the user and the system to influence each other.

[0588] A "filtering method" is a technique for selecting information that meets specific criteria from a large amount of data.

[0589] "Visualized data" refers to data that has been processed to represent information visually.

[0590] "Virtual preview" is a technology that simulates information in a way that closely resembles the actual visual experience.

[0591] The system that realizes this invention mainly consists of a server, a user terminal, and an emotion analysis engine. First, the user inputs their desired conditions into the terminal using natural language, and this is sent to the server. This terminal should preferably be a high-performance smartphone or smart glasses.

[0592] The server analyzes the input natural language data and extracts conditional items and sentiment data. This uses software such as AWS Comprehend as the sentiment analysis engine. The analyzed data is sent as queries to multiple databases, and matching information is collected. This database is an electronic record system for systematically managing products and related information.

[0593] Next, the server integrates the collected information with the user's emotional data to generate visualization data that reflects their emotions. This visualization data is created using the latest visualization technologies in human-computer interaction.

[0594] The generated visualization data is presented interactively on the device in a way that adapts to the user's emotions. The user can use this visualization to select products and, if necessary, further refine their search criteria through filtering functions.

[0595] For example, if a user seeking relaxation enters "I want calming interior design" into their device, the emotion analysis engine extracts the emotion of relaxation, and the server filters interior products that match this. As a result, the visualized data will highlight calming designs with nature themes, such as green and wood tones.

[0596] An example of a prompt for a generative AI model might be: "We are looking for products that make the user feel relaxed. Please list products that evoke a feeling of relaxation based on the emotion analysis results."

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

[0598] Step 1:

[0599] Users use devices such as smartphones or smart glasses to input their desired conditions in natural language. This input text is sent to the server. For example, if the input is "a comfortable sofa," the text data is sent to the server as output.

[0600] Step 2:

[0601] The server sends the received natural language text to an emotion analysis engine to extract emotion data. Using AWS Comprehend, it analyzes emotions such as "relaxed" in the text and obtains emotion data as output.

[0602] Step 3:

[0603] The server queries the product database based on the extracted criteria ("sofa") and emotion data ("relaxed") to find matching product information. The input is the criteria and emotion, and the output is a list of products that fit them.

[0604] Step 4:

[0605] The server integrates surrounding environment information from the search results and generates emotion-responsive visualization data. Using visualization tools, the collected results are presented in calming colors and designs. The generated visualization data is then output.

[0606] Step 5:

[0607] The server sends this visualization data to the user's device and presents it in an interactive format that is appropriate to their emotions. This allows the user to select products based on the visualized information.

[0608] Step 6:

[0609] Users can further refine their criteria using the interactive filtering function. As a result, they send the new criteria back to the server and receive updated results.

[0610] Step 7:

[0611] Finally, the user reviews the details of the selected product and performs a virtual preview as needed. The preview displays simulated visual information of the specified product.

[0612] 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.

[0613] 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.

[0614] 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.

[0615] [Fourth Embodiment]

[0616] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0617] 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.

[0618] 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).

[0619] 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.

[0620] 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.

[0621] 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).

[0622] 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.

[0623] 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.

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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".

[0629] This invention is a system that efficiently proposes rental properties that best match the user's needs by analyzing the user's input of desired conditions in natural language through their terminal. This system works in conjunction with multiple databases centered around a server to provide users with comprehensive property information.

[0630] First, the user uses a device to input their desired conditions in natural language through a chatbot-style interface. For example, by entering conditions such as "an apartment near a train station where pets are allowed," the user's specific request is transmitted to the system.

[0631] The server processes the input natural language through text analysis and clearly extracts the required criteria. Based on these analysis results, the server accesses multiple databases to search for property information that matches the criteria. The information includes a wide range of details such as property overview, location, surrounding facilities, and regional characteristics, and it is also possible to obtain information using external APIs as needed.

[0632] After integrating the search results, the server processes the data in a visually easy-to-understand format and presents it to the user's device in map or list format. This allows the user to intuitively understand the geographical location of the property and surrounding facilities.

[0633] Furthermore, users can utilize filtering options to narrow down their search criteria through interaction. For example, by specifying additional conditions such as budget or room size, they can obtain more detailed property information.

[0634] Ultimately, for properties that users are interested in, a means of virtual viewing is provided. The server generates a 3D model of the property's interior, enabling a virtual tour on the user's device. This feature allows users to conduct detailed observation and analysis without actually visiting the property.

[0635] According to embodiments of the present invention, the process of searching for rental properties is significantly streamlined, allowing users to easily find properties that suit their lifestyle.

[0636] The following describes the processing flow.

[0637] Step 1:

[0638] Users use their devices to input their desired rental conditions in natural language. Through the chatbot interface, they communicate their requests to the system, such as "I'm looking for a pet-friendly apartment within walking distance of the station."

[0639] Step 2:

[0640] The server analyzes the received natural language input and uses natural language processing techniques to extract conditional items. Here, specific requirements based on the user's preferences (e.g., within walking distance of a train station, pet-friendly, apartment) are identified.

[0641] Step 3:

[0642] Based on the extracted conditions, the server accesses its internal database and, if necessary, external APIs to search for corresponding property information. The search generates and executes queries to filter properties that match the user's desired criteria.

[0643] Step 4:

[0644] The server integrates property information obtained from search results and collects and integrates additional information, including surrounding facilities and regional characteristics. The integrated data is then prepared to be presented to the user as visual information.

[0645] Step 5:

[0646] The server sends visualized information to the user's terminal, which the user then views on the terminal in map or list format. Here, the location of the property and its relationship to surrounding facilities are displayed in an intuitive manner.

[0647] Step 6:

[0648] Users can further refine their search criteria using filtering options based on the information provided on their device. This allows them to specify additional conditions, such as budget or room size, to narrow down the options even further.

[0649] Step 7:

[0650] Finally, the user selects the option to virtually tour the properties they are interested in. The server generates a 3D model of the selected property and provides the data so that the user can virtually tour its details through their device.

[0651] Through this series of steps, users can efficiently find rental properties that meet their desired conditions.

[0652] (Example 1)

[0653] 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".

[0654] When searching for rental properties, it is difficult for users to accurately and efficiently reflect their desired conditions and quickly find the best option from a vast amount of property information. Furthermore, there are limited ways to thoroughly understand properties that are far away and difficult to view in person. Therefore, there is a need for a system that can quickly and intuitively suggest the best properties based on the user's desired conditions and provide detailed information, thereby improving the efficiency of the rental property search.

[0655] 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.

[0656] In this invention, the server includes means for analyzing natural language conditions from the user and extracting elements; means for searching for relevant information from multiple information databases based on the extracted elements; means for integrating environmental information based on the search results and generating visualization data; means for generating a three-dimensional model of a selected physical location using virtual reality technology and making it displayable on a terminal; and means for generating prompt text for the generated technology model as needed and using it as input. As a result, users can easily find the optimal rental property based on their desired conditions and intuitively understand the details of the property remotely through virtual viewings.

[0657] "User" refers to the person who operates the system and receives information.

[0658] "Natural language" refers to the forms of language that humans use on a daily basis, and the text that is analyzed in computer processing.

[0659] "Elements" refer to individual conditions necessary for searching and evaluation, which are extracted during the process of analyzing the user's desired conditions.

[0660] An "information database" refers to a collection of structured data that a system accesses and uses to retrieve necessary property information.

[0661] "Related information" refers to information about matching properties and environments that are retrieved from the database based on the user's desired conditions.

[0662] "Environmental information" refers to information about the surrounding characteristics and area of ​​a property, and is a factor that should be considered when choosing a property.

[0663] "Visualized data" refers to a data format that is visually organized so that users can intuitively understand the information.

[0664] "Virtual reality technology" refers to technology that allows users to experience a three-dimensional space created by a computer program.

[0665] A "three-dimensional model" refers to data in a virtual space that represents the interior and exterior of a property in three dimensions.

[0666] A "generative technology model" refers to a model that autonomously generates and provides information using technologies such as artificial intelligence.

[0667] A "prompt statement" refers to a sentence that specifies the instructions or conditions that are input into a generative technology model.

[0668] This system aims to provide optimal rental property information based on the user's desired conditions entered in natural language via a terminal. The system's core is a server, which is linked to multiple databases. The server utilizes natural language processing libraries such as "spaCy" and "BERT" to analyze the conditions entered by the user.

[0669] When a user enters conditions such as "apartments near a train station where pets are allowed" through the chatbot interface on their device, the information is first sent to the server. The server performs text analysis and extracts the condition items. This analysis breaks down the input natural language into its constituent elements and converts them into the required format.

[0670] Next, the server uses the extracted criteria to search the database. SQL and NoSQL technologies are used for the search, and additional information can be obtained from external APIs (e.g., map service APIs) as needed. This makes it possible to thoroughly gather information that meets the user's needs.

[0671] The acquired information is integrated by the server and visualized using a data visualization library (e.g., D3.js). The generated visualization data is sent to the user's device and presented intuitively in map or list format. This allows the user to easily understand the surrounding environment and the geographical location of the property.

[0672] In addition, users can use filtering functions to refine and modify their search criteria. This allows them to narrow down their search by budget, room size, and other factors. Furthermore, the server generates a 3D model of the property selected by the user using virtual reality technology and delivers it to the device in the form of a virtual tour. This technology uses WebGL, allowing users to view the interior in detail without actually visiting the property.

[0673] As a concrete example, the prompt message sent to the generating AI model is in the format of "I'm looking for a 1LDK apartment in Tokyo that's pet-friendly, near a train station, and has a rent of 50,000 yen or less." By sending this prompt, the model returns the most suitable property information. By integrating these technologies, the system allows users to efficiently find properties that best match their preferences.

[0674] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0675] Step 1:

[0676] The user enters their desired conditions in natural language via their device. An example of this input might be "apartments near a train station where pets are allowed." This data is configured by the user on their device and sent to the server. In this process, the user's request is initialized and a query to the system is initiated.

[0677] Step 2:

[0678] The server receives natural language input from the user and parses it using a natural language processing library (e.g., spaCy, BERT). This parse extracts conditional items. The received text is tokenized, relevant keywords and phrases are identified, and they are converted into a format for use in database searches. The output is a structured list of searchable conditional items.

[0679] Step 3:

[0680] The server searches the information database using the extracted conditions. SQL and NoSQL technologies are used to search for property information that matches the conditions, and it is also possible to retrieve supplementary information from external APIs (e.g., map service APIs). The input is a list of condition items, and the output is property information that matches the conditions. This process includes collecting property overviews, location information, and regional characteristics data.

[0681] Step 4:

[0682] The server integrates the search results and formats them as visualized data using a data visualization library (e.g., D3.js). It generates maps and list formats that visually represent location information and related property information. The input is a collection of property information, and the output is a visualized dataset presented to the user.

[0683] Step 5:

[0684] The user reviews the visualization data received from the server via their device and uses filtering to narrow down the criteria. Additional conditions, such as budget and room size, can be specified through further interaction. This operation improves the accuracy of the visualization data. Inputs are the visualization data and additional conditions, and output is the filtered and revised information.

[0685] Step 6:

[0686] The server generates a 3D model of the property selected by the user using virtual reality technology. Using WebGL technology, the internal structure of the property is reproduced in 3D and sent to the terminal. This allows the user to conduct a virtual tour. Inputs are property information and visualization requests, and output is the 3D model experienced by the user.

[0687] Step 7:

[0688] If necessary, the server generates prompt sentences for the generative technology model and uses them as input. A concrete example of a prompt might be, "I'm looking for a 1LDK apartment in Tokyo that's pet-friendly, near a train station, and has a rent of 50,000 yen or less." The prompt sentences are analyzed by the generative AI model and used to obtain additional recommendations. The input is the user's conditions and situation, and the output is recommendations and additional information.

[0689] (Application Example 1)

[0690] 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".

[0691] Traditional rental property search systems require users to physically visit properties, which is time-consuming and costly. Furthermore, it's often difficult to select properties based on detailed criteria, and real-time information about the surrounding environment is often unavailable. In this context, there is a need for a method that allows users to efficiently and intuitively select properties from the comfort of their homes.

[0692] 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.

[0693] In this invention, the server includes means for analyzing user-defined natural language preferences and extracting condition items, means for searching for matching information from multiple data records based on the extracted condition items, and means for generating visualization data for a virtual viewing of an item, which can be visually confirmed on a terminal. This allows users to select properties based on detailed conditions from the comfort of their homes, and further enables them to visually confirm the surrounding environment in real time through the virtual viewing mode.

[0694] A "user" is an individual or legal entity that uses an information system to search for rental properties.

[0695] "Natural language" refers to the forms of words and sentences that humans use on a daily basis, and it is a linguistic form from which conditions are extracted through computer analysis.

[0696] "Desired conditions" refer to the specific features and requirements that the user seeks in a rental property, including location, price, and amenities.

[0697] "Condition items" are classified elements that the system identifies and uses to perform specific database searches, based on the user's desired conditions.

[0698] "Data records" refer to information sources where information related to rental properties is stored, and serve as the foundation for systems to search for that information.

[0699] "Matching information" refers to properties and related data that match the user's criteria and are information that suits the user's needs.

[0700] "Virtual viewing" is a method that allows users to visually experience the interior of a property using information technology without physically visiting the property.

[0701] "Visualized data" refers to data presented in a format that is easy for users to intuitively understand, and includes maps and 3D models.

[0702] The system that realizes this invention efficiently provides rental property information according to the user's requests. The following describes an embodiment of this system.

[0703] The server receives the user's desired conditions entered in natural language using a terminal. Using a standard server computer as hardware and the Google Cloud Natural Language API as software, the server analyzes the entered natural language and extracts specific condition items. This ensures a clear understanding of the user's desired conditions.

[0704] The extracted criteria are searched across multiple databases by the server to collect relevant information. This information includes detailed data on rental properties and surrounding environment information, and is important for generating visualization data.

[0705] Once matching information is integrated, the server uses Unity to generate 3D models of the items and converts them into visualization data for virtual viewings. This visualization data is then transferred to the terminal and presented to the user in a usable format. Specifically, users can use their smartphones to explore the property in detail in virtual reality mode, gaining an intuitive understanding of the surrounding environment and property details.

[0706] For example, if a user enters "I'm looking for a detached house with a large garden," the server automatically searches for properties that match that requirement and allows the user to visually experience the size and layout of the garden using a 3D model. In this case, an example of a prompt message would be "I'd like a house with a large garden. Please show me properties that suit me."

[0707] In this way, users can explore rental properties and gain a deep understanding of their characteristics from the comfort of their own homes. This system will allow users to efficiently find their ideal property.

[0708] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0709] Step 1:

[0710] The user enters their desired conditions in natural language using their device. For example, the user might enter a request such as "a pet-friendly apartment near a train station" into the chatbot. The input data is sent from the device to the server as natural language text.

[0711] Step 2:

[0712] The server analyzes the received natural language input. During this process, it uses the Google Cloud Natural Language API to process the data and extract desired conditions from the text. The input is natural language text data, and the output is a set of extracted condition items.

[0713] Step 3:

[0714] The server searches the database using the extracted criteria. It accesses multiple databases and performs data calculations to search for rental property information based on the criteria. The input is a set of criteria, and the output is a list of candidate properties.

[0715] Step 4:

[0716] The server integrates surrounding environment information from search results and generates visualization data. It uses Unity to create 3D models of properties and performs data processing to create visualization data compatible with virtual viewings. The input is a list of candidate properties, and the output is visualization data including 3D models.

[0717] Step 5:

[0718] The generated visualization data is sent from the server to the terminal. The terminal interactively presents property information to the user, enabling the user to take a virtual reality tour. The input is the visualization data, and the output is the property information and virtual tour experience displayed on the terminal.

[0719] 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.

[0720] This invention is a property suggestion system that takes into account the user's psychological factors, enabling more appropriate property searches based on the user's requirements. This system incorporates an emotion engine that recognizes and analyzes emotions through the user's natural language input, and by adding emotional nuances to the conditions requested by the user, it can achieve more satisfying results.

[0721] First, the user enters their desired conditions in natural language using their device. During this process, the emotion engine analyzes the user's emotions (e.g., joy, sadness, anxiety) in real time. For example, input such as "I want an apartment where there is little noise and I can live quietly" can detect the user's stress levels and desire for calm.

[0722] The server generates a search query using the analyzed sentiment data along with the specified criteria. This query filters and searches for properties that best match the user's desired conditions and sentiments through an internal database and an external API. In this case, property information that guarantees a quiet environment is given priority.

[0723] Search results are integrated for visualization, and the presentation method is adjusted according to the user's emotional state. For example, a calming color scheme is used to present information, enhancing the sense of anticipation for living in a peaceful environment.

[0724] Furthermore, users can add or modify conditions using an interactive filtering function. The emotion engine also operates during this filtering process, adjusting the filtering method according to the user's emotions.

[0725] Finally, for properties that pique the user's interest, a virtual viewing option allows for more detailed examination. Here too, the emotion engine monitors the user's reactions and further personalizes the information presented.

[0726] As a result, this system enables emotionally sensitive property recommendations and improves the user experience. By integrating user emotions into its approach, users can efficiently find properties that better suit them, resulting in higher satisfaction.

[0727] The following describes the processing flow.

[0728] Step 1:

[0729] Users use their devices to input their desired property criteria in natural language. At this time, an emotion engine recognizes the user's emotions in real time from their input and analyzes the emotions they are feeling when entering their criteria. This emotion data is then used for subsequent processing.

[0730] Step 2:

[0731] The server extracts conditional items from the user's natural language. This utilizes natural language processing technology to extract the specific conditions the user desires (e.g., quiet place, pet-friendly). Simultaneously, the results of the emotion engine analysis are also obtained, and the user's emotional state (e.g., want to feel safe, want to avoid stress) is integrated as supplementary information.

[0732] Step 3:

[0733] The server generates a search query based on the extracted criteria and sentiment information, and searches for relevant property information using the property database and external APIs. At this stage, it prioritizes filtering for properties that highlight a specific sentiment (e.g., properties with a prominent peaceful environment).

[0734] Step 4:

[0735] The server organizes the acquired property information and generates visualization data to present it to the user in an emotionally sensitive visual way. For example, if the user is in a mood to relax, the screen's color scheme and design will be expressed in a tone that reflects that emotion.

[0736] Step 5:

[0737] Users can view property information displayed on their device and further refine their search using the filtering function. During this process, the emotion engine continuously analyzes the user's reactions and incorporates this information into the presentation of filtering options.

[0738] Step 6:

[0739] For properties that the user is particularly interested in, the server provides virtual viewing data, allowing the user to visually check the details on their device. Throughout this process, information is presented based on the user's emotional state, striving to enhance user satisfaction.

[0740] Through this series of steps, the emotion engine is integrated into the entire system, enabling personalized property recommendations that take user emotions into account.

[0741] (Example 2)

[0742] 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".

[0743] Traditional property search systems simply suggested properties based on criteria without considering the user's emotions or psychological factors. Therefore, it was difficult to enhance the user's subjective satisfaction, resulting in a limited user experience. Furthermore, they were unable to provide interactive feedback that responded to the user's emotions, making it difficult to deliver optimized search results.

[0744] 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.

[0745] In this invention, the server includes means for analyzing desired conditions in natural language from the user and extracting condition items; means for analyzing the extracted condition items and the user's emotions and dynamically generating a search query based on the user's emotional state; and means for searching for matching information from multiple data storages using the generated search query. This enables optimal property suggestions that integrate the user's emotions and conditions.

[0746] "Natural language" refers to linguistic expressions used to express desires, based on the language forms that users use on a daily basis.

[0747] "Condition items" are indicators that are analyzed from the user's natural language input and specifically indicate their wishes and requirements regarding the property.

[0748] "Emotion analysis" is a process that recognizes the emotions contained in the user's natural language input and quantifies the user's psychological state.

[0749] A "search query" is a set of instructions generated based on the user's preferences and emotional state, used to retrieve relevant information from data storage.

[0750] "Data storage" refers to a data storage system that holds property information and related surrounding data, and provides information in response to search queries.

[0751] "Visualization" is the process of organizing acquired information into a format that is easy for users to understand and representing it visually.

[0752] A "user-emotion-responsive approach" is a method that adjusts search results and presentation methods to best suit the user's emotions.

[0753] "Interactive presentation" refers to a function that allows users to interact with and respond to the information presented, enabling two-way use of the information.

[0754] This invention relates to a property recommendation system that takes into account the user's psychological factors, and the system operates between a server, a terminal, and the user. The user inputs their desired property conditions into the terminal using natural language. This natural language input is analyzed by an emotion analysis engine, which interprets the user's emotions. This emotion analysis engine is, for example, software that uses emotion recognition algorithms and natural language processing technology.

[0755] The terminal processes text data entered by the user in real time and sends sentiment data to the server. The server searches for information in data storage using dynamically generated search queries based on the sentiment data and the user's preferences. Data storage is an accessible pool of information based on internal databases and external information provision services.

[0756] The retrieved search results are visualized by the server according to the user's emotional state and sent to the device. The device displays the results to the user using calming colors and designs, and the user can interact with the presented information. This interaction incorporates further sentiment analysis, and filtering methods are performed according to the user's emotions.

[0757] For example, if a user enters "I want to find a quiet place with little noise," the emotion engine analyzes the user's desire for "peace of mind" and "relaxation." Based on this, the server identifies properties that guarantee a quiet environment and presents them to the user as a priority.

[0758] An example of a prompt message is: "Analyze the user's emotions and extract the property features they desire. Input: 'I want to live in a quiet environment with no noise.'"

[0759] With this configuration, the present invention has the effect of improving the subjective satisfaction of users and realizing more efficient and personalized property recommendations.

[0760] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0761] Step 1:

[0762] The user uses a device to input their desired property conditions in natural language. The device receives this input and sends it as text data to the sentiment analysis engine. A possible specific input might be, "I want to find a quiet place with little noise." The output is text data in a format that the sentiment analysis engine can process.

[0763] Step 2:

[0764] The device's emotion analysis engine analyzes received text data and evaluates the user's emotions. The input is the user's natural language text, and the analysis algorithm determines the emotional state (e.g., reassured, relaxed, stressed). The output is metadata indicating this emotional state. For example, the emotion "reassured" might be extracted.

[0765] Step 3:

[0766] The server generates a search query from the received sentiment metadata and user preferences. Specifically, it dynamically constructs a query to prioritize properties that offer a quiet environment based on the sentiment state and conditional items. The input is the analyzed sentiment and conditional items, and the output is the search query to be executed in data storage.

[0767] Step 4:

[0768] The server uses the generated search query to search for matching information from the data storage. This search process accesses internal databases and external APIs to retrieve property information that matches the user's desired criteria. The input is a dynamically generated search query, and the output is a filtered list of property information.

[0769] Step 5:

[0770] The server integrates search results as visual data and generates information presented through an interface tailored to the user's emotional state. Input includes search results, which are visualized using reassuring color schemes and designs. Output is the visualized data sent to the terminal.

[0771] Step 6:

[0772] Users view visualized property information on their device and interactively modify or add criteria. The device then performs sentiment analysis again in response to these actions, re-filtering the criteria. The input is the user's actions, and the output is the updated search query. For example, the condition "more green places" might be added.

[0773] Step 7:

[0774] When a user expresses interest in a particular property, the server provides virtual tour data for that property and performs sentiment analysis tailored to the user's reactions. The input is the user's selection when starting the virtual tour, and the output is customized visual data based on the user's reactions.

[0775] (Application Example 2)

[0776] 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".

[0777] Traditional online shopping systems have the problem of lower user satisfaction because they cannot suggest products that take into account the user's psychological and emotional factors. Furthermore, it is difficult to implement interactive filtering and visual representations that respond to user emotions, making it challenging to suggest products that meet individual user needs.

[0778] 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.

[0779] In this invention, the server includes means for analyzing user-defined natural language preferences and extracting condition items and emotion data; means for searching for matching information from multiple databases based on the extracted condition items and emotion data; and means for integrating surrounding environment information based on the search results and generating visualization data corresponding to the emotion. This enables personalized product suggestions that take the user's emotions into consideration.

[0780] "Desired conditions in natural language" refers to the conditions that the user desires, entered using everyday language.

[0781] "Condition items" are specific elements or criteria extracted from the user's desired conditions.

[0782] "Emotional data" refers to information that represents the psychological state and emotional tendencies of a user, analyzed from their input.

[0783] A "database" is an electronic record system for systematically collecting and managing information.

[0784] "Surrounding environment information" refers to information that indicates external conditions and characteristics related to the product or service in question.

[0785] "Interactive presentation" means that information is displayed in a way that allows the user and the system to influence each other.

[0786] A "filtering method" is a technique for selecting information that meets specific criteria from a large amount of data.

[0787] "Visualized data" refers to data that has been processed to represent information visually.

[0788] "Virtual preview" is a technology that simulates information in a way that closely resembles the actual visual experience.

[0789] The system that realizes this invention mainly consists of a server, a user terminal, and an emotion analysis engine. First, the user inputs their desired conditions into the terminal using natural language, and this is sent to the server. This terminal should preferably be a high-performance smartphone or smart glasses.

[0790] The server analyzes the input natural language data and extracts conditional items and sentiment data. This uses software such as AWS Comprehend as the sentiment analysis engine. The analyzed data is sent as queries to multiple databases, and matching information is collected. This database is an electronic record system for systematically managing products and related information.

[0791] Next, the server integrates the collected information with the user's emotional data to generate visualization data that reflects their emotions. This visualization data is created using the latest visualization technologies in human-computer interaction.

[0792] The generated visualization data is presented interactively on the device in a way that adapts to the user's emotions. The user can use this visualization to select products and, if necessary, further refine their search criteria through filtering functions.

[0793] For example, if a user seeking relaxation enters "I want calming interior design" into their device, the emotion analysis engine extracts the emotion of relaxation, and the server filters interior products that match this. As a result, the visualized data will highlight calming designs with nature themes, such as green and wood tones.

[0794] An example of a prompt for a generative AI model might be: "We are looking for products that make the user feel relaxed. Please list products that evoke a feeling of relaxation based on the emotion analysis results."

[0795] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0796] Step 1:

[0797] Users use devices such as smartphones or smart glasses to input their desired conditions in natural language. This input text is sent to the server. For example, if the input is "a comfortable sofa," the text data is sent to the server as output.

[0798] Step 2:

[0799] The server sends the received natural language text to an emotion analysis engine to extract emotion data. Using AWS Comprehend, it analyzes emotions such as "relaxed" in the text and obtains emotion data as output.

[0800] Step 3:

[0801] The server queries the product database based on the extracted criteria ("sofa") and emotion data ("relaxed") to find matching product information. The input is the criteria and emotion, and the output is a list of products that fit them.

[0802] Step 4:

[0803] The server integrates surrounding environment information from the search results and generates emotion-responsive visualization data. Using visualization tools, the collected results are presented in calming colors and designs. The generated visualization data is then output.

[0804] Step 5:

[0805] The server sends this visualization data to the user's device and presents it in an interactive format that is appropriate to their emotions. This allows the user to select products based on the visualized information.

[0806] Step 6:

[0807] Users can further refine their criteria using the interactive filtering function. As a result, they send the new criteria back to the server and receive updated results.

[0808] Step 7:

[0809] Finally, the user reviews the details of the selected product and performs a virtual preview as needed. The preview displays simulated visual information of the specified product.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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."

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0831] The following is further disclosed regarding the embodiments described above.

[0832] (Claim 1)

[0833] A means of analyzing user-generated natural language preferences and extracting condition items,

[0834] A means for searching for matching information from multiple databases based on extracted criteria,

[0835] A means of integrating surrounding environmental information based on search results and generating visualization data,

[0836] A means of interactively presenting integrated information to the user,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] The system according to claim 1, comprising means for providing a filtering function that narrows down conditions through user interaction.

[0840] (Claim 3)

[0841] The system according to claim 1, comprising means for generating virtual viewing data for a specified property and visually confirming it on a terminal.

[0842] "Example 1"

[0843] (Claim 1)

[0844] A means of analyzing natural language conditions from users and extracting elements,

[0845] A means for searching for related information from multiple information databases based on extracted elements,

[0846] A means of integrating environmental information based on exploration results to generate visualization data,

[0847] A means of presenting the generated visualization data to the user's terminal,

[0848] A means for generating a three-dimensional model of a selected physical location using virtual reality technology and making it displayable on a terminal,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, comprising means for providing a filtering method that refines conditions through user interaction.

[0852] (Claim 3)

[0853] The system according to claim 1, comprising means for generating prompt statements for a generation technology model as needed and utilizing them as input.

[0854] "Application Example 1"

[0855] (Claim 1)

[0856] A means of analyzing user-generated natural language preferences and extracting condition items,

[0857] A means for searching for matching information from multiple data records based on extracted condition items,

[0858] A means of integrating surrounding characteristic information based on search results and generating visualization data,

[0859] A means of interactively presenting integrated information to the user,

[0860] A means to generate visualization data of a virtual viewing of an item and to visually confirm it on a terminal,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, comprising means for providing a selection function that narrows down conditions through user interaction.

[0864] (Claim 3)

[0865] The system according to claim 1, comprising means for enabling a user to visually explore surrounding characteristic information in a virtual reality mode.

[0866] "Example 2 of combining an emotion engine"

[0867] (Claim 1)

[0868] A means of analyzing user-generated natural language preferences and extracting condition items,

[0869] A means for analyzing extracted conditional items and user sentiment, and dynamically generating search queries based on the user's emotional state,

[0870] A means of searching for matching information from multiple data storages using a generated search query,

[0871] A means of integrating surrounding environmental data based on search results and generating data for visualization,

[0872] A means of interactively presenting integrated information in a way that responds to the user's emotional state,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, which provides a filtering function that takes into account the user's emotional state and includes means for narrowing down conditions through user interaction.

[0876] (Claim 3)

[0877] The system according to claim 1, comprising means for generating virtual viewing data, taking into account the sentiment analysis results regarding a specified property, and for visually confirming it on a terminal device.

[0878] "Application example 2 when combining with an emotional engine"

[0879] (Claim 1)

[0880] A means for analyzing user preferences expressed in natural language and extracting condition items and sentiment data,

[0881] A means for searching for matching information from multiple databases based on extracted conditional items and sentiment data,

[0882] A means of integrating surrounding environmental information based on search results and generating visualization data that responds to emotions,

[0883] A means of presenting integrated information interactively, adapted to the user's emotions,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, further comprising means for providing a function to narrow down conditions through user interaction and adjust the filtering method according to sentiment data.

[0887] (Claim 3)

[0888] The system according to claim 1, comprising means for generating virtual preview data for specified information and visually confirming it on a terminal. [Explanation of Symbols]

[0889] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of analyzing user-generated natural language preferences and extracting condition items, A means for searching for matching information from multiple databases based on extracted criteria, A means of integrating surrounding environmental information based on search results and generating visualization data, A means of interactively presenting integrated information to the user, A system that includes this.

2. The system according to claim 1, comprising means for providing a filtering function that narrows down conditions through user interaction.

3. The system according to claim 1, comprising means for generating virtual viewing data for a specified property and visually confirming it on a terminal.

Images