Method and system for providing satellite image purchase service based on language model

Abstract

The present invention relates to a method and system for providing a satellite image purchase service based on a language model. The present invention is characterized by specifying the type of a user query, and searching and interpreting a satellite image by using an agent corresponding to the specifedc user query. Specifically, the system for providing a satellite image purchase service, according to the present invention, may search a database for a satellite image related to a user query when the user query related to the satellite image is received, and generate and provide an answer suitable for a query intention of a user by using a found satellite image and a large language model (LLM).

Description

Method and System for Providing Language Model-Based Satellite Imagery Purchase Services

[0001] The present invention relates to a method and system for providing a language model-based satellite imagery purchasing service.

[0002] Recently, there has been a surge in cases of achieving outstanding results in various fields such as speech recognition, image recognition, natural language processing, and autonomous driving through artificial intelligence, particularly deep learning which extracts data characteristics using deep neural network structures.

[0003] Along with the advancement of such deep learning technology, Generative AI technology has recently been attracting attention. More specifically, Generative AI models can generate new data in various forms, such as text, images, and voice, from given data, offering a different dimension of application possibilities compared to simply classifying or predicting existing data.

[0004] In other words, as it has become possible to automatically generate sentences, images, and voices that were previously generated by humans using generative artificial intelligence models, services using generative artificial intelligence (e.g., ChatGPT) have demonstrated the responsiveness and accuracy that differentiate them from existing chatbot services, and are receiving great attention worldwide.

[0005] Meanwhile, due to advancements in satellite technology, the utilization of satellites is becoming increasingly important in fields such as Earth observation, weather forecasting, and communications. Through sensors and cameras, satellites collect various forms of data, including high-definition images and video, geographical information, and environmental data, and can provide diverse information about the Earth in real time.

[0006] Along with the advancement of such satellite technology, there has recently been a surge in research and attempts to integrate artificial intelligence technology with satellite data for utilization in various fields. The analysis and processing of large volumes of images, video, and data collected from satellites are critical; in particular, high-resolution satellite imagery is being utilized effectively in diverse areas such as agriculture, disaster management, urban planning, and environmental monitoring.

[0007] As such, research to integrate artificial intelligence technology is actively underway in the satellite sector. Consequently, there is a need for methods to provide a wider range of satellite-related services by utilizing generative AI models.

[0008] The present invention relates to a method and system for providing a service that allows purchasing satellite imagery using natural language.

[0009] More specifically, the present invention relates to a method and system for providing a service that allows searching for and purchasing satellite images using a language model-based chatbot.

[0010] Furthermore, the present invention relates to a method and system for interpreting and providing satellite images through a language model.

[0011] To solve the problem described above, the method for providing a language model-based satellite imagery purchase service according to the present invention may include: receiving a user query related to satellite imagery purchase through a service page; specifying a query type corresponding to the user query among a plurality of query types classified based on the perspective of satellite imagery purchase; searching for at least one satellite imagery associated with the user query using a specific agent corresponding to the query type among a plurality of agents of a large language model; interpreting the searched satellite imagery through the specific agent to generate an answer to the user query; and providing the searched satellite imagery and the answer to the service page.

[0012] Furthermore, among the plurality of query types, the first type of user query corresponds to a question related to a specific satellite platform, and among the plurality of agents, the first agent processing the first type of user query can search for at least one satellite image captured by the specific satellite system from the satellite image DB and generate the answer using descriptive information describing the specific satellite platform.

[0013] Furthermore, among the plurality of query types above, the user query of the second type may include at least one search condition information among the satellite image capture area information, the satellite image capture date information, the satellite image cloud ratio information, the satellite image ROi (Region Of Interest) size information, the satellite image resolution information, and the satellite image provider information.

[0014] Furthermore, among the plurality of agents, the second agent processing the second type of user query can search for a plurality of satellite images corresponding to the search condition information from the satellite image DB and generate the answer describing a list including the plurality of satellite images.

[0015] Furthermore, among the plurality of query types, the third type of user query is related to a specific event, and among the plurality of agents, the third agent processing the third type of user query can search for news articles related to the specific event and search for satellite images of associated locations related to the news articles from the satellite image DB.

[0016] Furthermore, the above third agent can generate the above answer related to the above specific event using the above searched news article.

[0017] Furthermore, the service page may include a chat area where the user query is entered, a search area where search condition information for searching the satellite image is entered, and a preview area where the searched satellite image is provided.

[0018] Furthermore, the service page may further include a step of providing additional information regarding the user query, and in the step of providing additional information, the weather conditions of the searched satellite image may be analyzed, and an additional answer including the weather conditions information may be generated and provided to the chat area.

[0019] Meanwhile, the language model-based satellite image purchase service providing system according to the present invention may include a communication unit that receives a user query related to satellite image purchase through a service page, and a control unit that identifies a query type corresponding to the user query among a plurality of query types classified based on the perspective of satellite image purchase, searches for at least one satellite image associated with the user query using a specific agent corresponding to the query type among a plurality of agents of a large language model, interprets the searched satellite image through the specific agent to generate an answer to the user query, and provides the searched satellite image and the answer to the service page.

[0020] Meanwhile, the program according to the present invention is a program that is executed by one or more processes in an electronic device and is stored on a computer-readable recording medium, and may include instructions for performing the steps of: receiving a user query related to the purchase of satellite imagery through a service page; specifying a query type corresponding to the user query among a plurality of query types classified based on the perspective of the purchase of satellite imagery; searching for at least one satellite imagery associated with the user query using a specific agent corresponding to the query type among a plurality of agents of a large language model; interpreting the searched satellite imagery through the specific agent to generate an answer to the user query; and providing the searched satellite imagery and the answer to the service page.

[0021] The method and system for providing a language model-based satellite imagery purchase service according to the present invention receives a user query related to satellite imagery purchase through a service page and can provide an environment in which the user searches for and orders satellite images using natural language.

[0022] Furthermore, the method and system for providing a language model-based satellite imagery purchasing service according to the present invention can identify a query type corresponding to the user query among a plurality of query types classified based on the satellite imagery purchasing perspective, and search for at least one satellite imagery associated with the user query by using a specific agent corresponding to the query type among a plurality of agents of a large language model. The present invention can search for satellite imagery optimized for the user query and provide related information.

[0023] Furthermore, the method and system for providing a language model-based satellite image purchasing service according to the present invention interprets the satellite image retrieved through the specific agent to generate an answer to the user query, and the user can check the quality of the satellite image before purchasing.

[0024] Furthermore, the method and system for providing a language model-based satellite image purchase service according to the present invention can improve satisfaction and reliability by providing the searched satellite image and the answer on a service page to verify whether the satellite image desired by the user is correct and preventing the user from purchasing unnecessary satellite images.

[0025] FIGS. 1, FIGS. 2a, and FIGS. 2b are conceptual diagrams for illustrating a satellite information-based raw material supply chain monitoring system according to the present invention.

[0026] FIG. 3 is a flowchart illustrating a method for providing a language model-based satellite image purchasing service according to the present invention.

[0027] FIGS. 4a and FIGS. 4b are conceptual diagrams for explaining service pages provided by a language model-based satellite image purchasing service providing system according to the present invention.

[0028] FIGS. 5, FIGS. 6, FIGS. 7, FIGS. 8, FIGS. 9a, and FIGS. 9b are conceptual diagrams illustrating a method for providing a satellite image purchasing service according to a user query in the present invention.

[0029] Hereinafter, embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Identical or similar components are assigned the same reference number regardless of the drawing symbols, and redundant descriptions thereof will be omitted. The suffixes "module" and "part" used for components in the following description are assigned or used interchangeably solely for the ease of drafting the specification and do not have distinct meanings or roles in themselves. Furthermore, in describing the embodiments disclosed in this specification, if it is determined that a detailed description of related prior art could obscure the essence of the embodiments disclosed in this specification, such detailed description will be omitted. Additionally, the attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification; the technical concept disclosed in this specification is not limited by the attached drawings, and it should be understood that they include all modifications, equivalents, and substitutions that fall within the spirit and technical scope of the present invention.

[0030] Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but said components are not limited by said terms. These terms are used solely for the purpose of distinguishing one component from another.

[0031] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between.

[0032] A singular expression includes a plural expression unless the context clearly indicates otherwise.

[0033] In this application, terms such as “comprising” or “having” are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0034] The present invention relates to a method and system for providing a language model-based satellite imagery purchasing service. The language model-based satellite imagery purchasing service providing system according to the present invention performs response generation based on Generative Artificial Intelligence (Generative AI) or a Large Language Model (LLM), and may be referred to as an LLM-based satellite imagery purchasing platform or PlanetChat Client. For convenience of explanation, the system will be referred to as a “satellite imagery purchasing service providing system” in the following description.

[0035] The present invention supports users in purchasing desired satellite imagery. If users cannot preview satellite imagery before purchasing, they may purchase unnecessary imagery or abandon the purchase. However, if a preview of the satellite imagery is provided, users can obtain the imagery by capturing the preview screen, thereby eliminating the need for purchase.

[0036] In the present invention, interactive information regarding satellite images can be provided through a large language model that interprets satellite images, thereby supporting the purchase of satellite images by users. In particular, the present invention introduces a chatbot-based conversational service to provide an environment in which users can search for and order satellite images using natural language.

[0037] More specifically, the satellite image purchasing service providing system according to the present invention may be a system that, upon receiving a user query (or query) related to a satellite and / or satellite image (or image), searches for a satellite image related to the user query from a database (or repository), and uses the searched satellite image and a large-scale language model (LLM) to generate and provide an answer that matches the user's query intent.

[0038] Here, “satellite imagery” refers to images recorded by a detector (or sensor (e.g., image sensor, camera, etc.)) mounted on an artificial satellite, and in a broad sense may include space photographs taken by a camera.

[0039] Furthermore, the satellite imagery purchase service providing system according to the present invention may be a system that, upon receiving a user query related to a satellite and / or satellite imagery, searches for satellite imagery related to the user query from a database (or repository), and generates and provides an answer matching the user's query intent using an analysis result based on the analysis of the searched satellite imagery and a large-scale language model. More specific details regarding this will be described later.

[0040] Meanwhile, the satellite image purchasing service providing system according to the present invention aims to analyze satellite data in response to a user request and provide information desired by the user (e.g., information corresponding to the user's query intent, satellite image) through a conversational artificial intelligence chatbot.

[0041] Hereinafter, we will examine this in more detail together with the attached drawings. FIGS. 1, 2a, and 2b are conceptual diagrams for explaining a satellite information-based raw material supply chain monitoring system according to the present invention. FIGS. 3 is a flowchart for explaining a method for providing a language model-based satellite image purchasing service according to the present invention, FIGS. 4a and 4b are conceptual diagrams for explaining service pages provided by a language model-based satellite image purchasing service providing system according to the present invention, and FIGS. 5, 6, 7, 8, 9a, and 9b are conceptual diagrams for explaining a method for providing a satellite image purchasing service according to a user query in the present invention.

[0042] As illustrated in FIG. 1, the satellite image purchasing service providing system (100) according to the present invention may include at least one of an input unit (110), an output unit (120), a communication unit (130), a storage unit (140), and a control unit (150).

[0043] Although not described, the satellite image purchasing service providing system (100) according to the present invention may include one or more processors, and such processors may include one or more general-purpose processors and / or one or more special-purpose processors (e.g., digital signal processors, tensor processing units (TPUs), graphics processing units (GPUs), neural network processing units (NPUs), application integrated circuits, application semiconductors (ASICs), etc.). One or more processors may be configured to execute instructions, computer-readable instructions, and / or other instructions described herein that are stored (or included) in the storage unit (140). The satellite image purchasing service providing system and method according to the present invention may perform data processing described below in cooperation with memory and at least one processor. The processor may perform a series of operations and data processing using data and information stored in memory. In this case, memory may be a component of the storage unit (140).

[0044] Meanwhile, the input unit (110) can be configured in various ways as a means of data input. For example, the input unit (110) can be configured to receive user input. The input unit (110) can be configured to receive user input from a user terminal (10). Here, “receiving input” may mean receiving an input signal (or selection signal) corresponding to the user’s input based on input made by the user through the input unit configuration provided in the user terminal (10).

[0045] The input unit (110) may also be referred to as a user interface module. The input unit (110) may include a touch screen, a computer mouse, a keyboard, a keypad, a touchpad, a trackball, a joystick, a voice recognition module, or other similar devices. However, the present invention does not limit the type of input unit (110). Furthermore, in the present invention, the input unit (110) does not necessarily refer to a hardware means, but can be understood as a channel for receiving input from a user.

[0046] Here, user input may include satellite imagery, text, image (or video), voice, etc. In this case, the satellite imagery purchase service providing system (100) may further include a module that converts voice into text.

[0047] Next, the output unit (120) can output information through an output unit configuration (e.g., a display unit, a touch screen, a speaker, etc.) provided in a user terminal (10) linked to the satellite image purchase service providing system (100) according to the present invention. For example, the output unit (120) can output a page (or service page, 1000) linked to the satellite image purchase service providing system (100) according to the present invention to the display unit of the user terminal (10). In addition, the output unit (120) does not necessarily mean a hardware means, but can be understood as a channel for outputting results to a user.

[0048] Next, the communication unit (130) may be connected via a wireless or wired network to a user terminal (10), an LLM server (or artificial intelligence server, 20), a satellite image DB (30), a central server, an external server, a device, and at least one network, etc., to receive or transmit overall data and information necessary for the operation of the satellite image purchase service provision system (100) according to the present invention.

[0049] In this case, the communication unit (130) may include one or more communication modules to enable wireless and / or wired communication between the satellite image purchasing service providing system (100) and the user terminal (10), between the satellite image purchasing service providing system (100) and the artificial intelligence server (20), and between the satellite image purchasing service providing system (100) and the satellite image DB (30). Additionally, the communication unit (130) may include one or more communication modules to connect the satellite image purchasing service providing system (100) to one or more networks.

[0050] Here, the user terminal (10) may include at least one of a mobile phone, a smartphone, a notebook computer, a laptop computer, a slate PC, a tablet PC, an ultrabook, a desktop computer, a digital broadcasting terminal, a PDA (personal digital assistants), a PMP (portable multimedia player), a navigation device, and a wearable device (e.g., a smartwatch, a smart glass, a head-mounted display).

[0051] Furthermore, the communication unit (130) can support various communication methods according to the communication standards of the communicating device.

[0052] For example, the communication unit (130) may be configured to communicate with a communication target using at least one of the following technologies: WLAN (Wireless LAN), Wi-Fi (Wireless-Fidelity), Wi-Fi (Wireless Fidelity) Direct, DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband), WiMAX (World Interoperability for Microwave Access), HSDPA (High Speed ​​Downlink Packet Access), HSUPA (High Speed ​​Uplink Packet Access), LTE (Long Term Evolution), LTE-A (Long Term Evolution-Advanced), 5G (5th Generation Mobile Telecommunication), Bluetooth (Bluetooth™ Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra-Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus).

[0053] Meanwhile, the storage unit (140) serves to store various data related to the present invention and may include one or more non-transient computer-readable storage media that can be read and / or accessed by at least one of one or more processors.

[0054] One or more computer-readable storage media may include volatile and / or non-volatile storage components, such as optical, magnetic, organic, or other memory or disk storage devices. In some examples, the storage unit (140) may be implemented using a single physical device (e.g., one optical, magnetic, organic, or other memory or disk storage device), whereas in other examples, the storage unit (140) may be implemented using two or more physical devices.

[0055] The storage unit (140) may include computer-readable instructions and additional data. The storage unit (140) may include a storage necessary to perform at least some of the methods, scenarios, and techniques described herein and / or at least some of the functions of the device and network.

[0056] Furthermore, at least a portion of the storage unit (140) may be a cloud storage or a cloud server. At least a portion of the data corresponding to user input received from the input unit (110) and the training data may be stored in the storage unit (140).

[0057] That is, the storage unit (140) is sufficient as a space where information necessary for the operation of the satellite image purchase service provision system (100) according to the present invention is stored, and it can be understood that there are no restrictions on the physical space.

[0058] Meanwhile, the control unit (150) can perform the role of controlling the overall operation of the satellite image purchase service provision system (100) related to the present invention. The control unit (150) can process signals, data, information, etc. that are input or output through the components described above, or perform a series of data processing to provide or process appropriate information and functions to the user.

[0059] When the control unit (150) receives a user query related to a satellite and / or satellite image, it can retrieve at least one satellite image related to the user query from the storage unit (140) and / or at least one storage and / or satellite image DB.

[0060] The control unit (150) can generate an answer to a user query and provide it to the user by using the retrieved satellite imagery and a large-scale language model (160). In this case, the control unit (150) can provide at least one satellite imagery used (or referenced) to generate an answer to the user query along with the answer to the user.

[0061] In this case, the control unit (150) can use a large language model (160) provided by the LLM server (20).

[0062] As illustrated in FIG. 2a, the control unit (150) can transmit a service request corresponding to a user query to the LLM-server. The LLM-server can query data from at least one of the Cloud Optimized GeoTIFF (COG) Database and MongoDB. The Cloud Optimized GeoTIFF (COG) Database is a raster data file format that stores geospatial information such as satellite images or map data. And unlike relational databases that store MongoDB data in rows and columns, it stores data as key-value pairs.

[0063] As illustrated in FIG. 2b, the LLM-server may include a plurality of agents (161, 162, 163). The LLM-server may include a Search Agent (161), a Cloud Agent (162), and a News Agent (163). In the present invention, the plurality of agents (161, 162, 163) may also be referred to as a multi-agent system. The LLM-server may generate an answer to a user query based on at least one of the plurality of agents (161, 162, 163). The LLM-server may call a tool necessary to generate an answer using the output of the plurality of agents (161, 162, 163). The LLM-server may generate and provide an answer to a user query using the called tool.

[0064] In the present invention, an agent may refer to an independent module (or software component) that runs to perform a specific purpose in a Large Language Model (LLM) or LLM-server. An agent may be designed to perform predefined functions or roles. For example, an agent may include a Search Agent that performs searches, a Cloud Agent that processes cloud distribution or weather data from satellite imagery, and a News Agent that processes news data. Multiple such agents may cooperate to form a multi-agent system, and one or more may be selectively called upon according to a user query to perform data retrieval, analysis, and response generation.

[0065] In the present invention, a satellite image purchasing service can be provided based on a large language model of an LLM-server. This large language model can be described as a large language model (160) which is a component of the system (100) according to the present invention. That is, in the present invention, the large language model (160) is described without being restricted by physical space.

[0066] When a user query related to a satellite and / or satellite image is received, the control unit (150) may search for at least one satellite image related to the user query from the storage unit (140) and / or at least one storage and / or satellite image DB (30), and generate an answer to the user query and provide it to the user by using the analysis result based on the analysis of the searched satellite image and a large-scale language model (160). In this case, the control unit (150) may provide at least one of the satellite image, location information, and map used (or referenced) to generate the answer to the user query along with the answer to the user.

[0067] The control unit (150) can analyze (or interpret) the quality of the satellite image, the weather conditions of the satellite image, and whether the satellite image contains clouds or other weather phenomena.

[0068] In addition, the analysis result (or interpretation result) based on the analysis of satellite imagery may be related to at least one of the following: satellite imagery and coordinate search results, satellite orbit prediction results, satellite position information lookup results, spectral index calculation (or output), and object detection and segmentation results. However, the analysis result based on the analysis of satellite imagery in the present invention is not necessarily limited to the examples mentioned.

[0069] The control unit (150) may include at least one model (or module) used to generate an answer to a user query (or analyze satellite images according to the user query). In the present invention, the model may be configured to perform a specific function and output a result value according to the result of the performance. Additionally, in the present invention, the model may also be understood as a “tool.” In this case, the tool may include a function or algorithm for performing a specific task.

[0070] In one embodiment, when a user query includes content related to vehicle detection in a satellite image, the control unit (150) may use the first model (170) to detect vehicles included in the satellite image and provide the user with an answer including content related to the number of detected vehicles. The first model (170) may be an object detection model that has been trained to detect at least one object.

[0071] In another embodiment, if a user query includes content related to the NDVI (vegetation index) analysis of a specific area (or region) included in a satellite image, the control unit (150) may use the second model (180) to analyze the vegetation index of the specific area and provide the user with an answer that includes content related to the analysis result of the vegetation index. The second model (180) may be a spectral index analysis model that has been trained to produce information related to the spectral index analysis result through analysis of the image.

[0072] However, the model used to generate an answer to a user query in the present invention is not necessarily limited to the mentioned model, and may include other models in addition to the first model (170) and the second model (180). It is obvious that the model used to generate an answer to a user query in the present invention may be one or a plurality of models, and may be changed in various ways depending on the case.

[0073] Meanwhile, the satellite image purchasing service provision system (100) according to the present invention may be implemented in the form of various platforms such as an application, software, or a website. For convenience of explanation, the present specification does not limit the form in which the satellite image purchasing service provision system (100) is implemented to any one form. The satellite image purchasing service provision system (100) according to the present invention may also be named a “conversational artificial intelligence chatbot service provision platform.”

[0074] In the present invention, a process of receiving a user query related to the purchase of satellite imagery through a service page may be performed (S310, see FIG. 3).

[0075] As illustrated in FIG. 4a, the control unit (150) can provide a service page (1000) to a user terminal (10) that includes at least one of a search area (search panel, 1010), a chat area (Chat panel, 1020), and a preview area (satellite image panel, 1030).

[0076] The search area (or search panel, 1010) may be configured to input various search condition information required for searching satellite images. The search area (1010) may be configured to input at least one of the following search condition information: region information (1011) where the satellite image to be searched was taken, date information (date information, 1021) where the satellite image was taken, cloud ratio information (or cloud coverage or cloud degree, 1013) where the cloud occupies the satellite image, satellite image resolution information (1014), and satellite image provider information (satellite device, satellite image provider, etc., 1015).

[0077] A chatbot-based conversational service may be provided in the chat area (1020). The control unit (150) may receive a chat message (1021) from a user through the chat area (1020). The control unit (150) may provide a response to the chat message (1021) through the chat area (1020) using a large language model (160).

[0078] The control unit (150) can search for satellite images using search condition information entered through the search area (1010). The control unit (150) can analyze (or interpret) the searched satellite images and provide the analysis results to the chat area (1020) through a chatbot. The searched satellite images can also be provided to the preview area (1030).

[0079] Furthermore, the control unit (150) can receive a user query related to satellite image search through the chat area (1020). When the chat message contains a user query related to satellite image search, the control unit (150) can search for a satellite image corresponding to the user query (e.g., “Show me an image of an area with many cherry blossoms”) in the DB. The control unit (150) can analyze (or interpret) the searched satellite image and generate an answer to the user query using the analysis result.

[0080] The control unit (150) can generate an answer by analyzing (interpreting) the weather conditions or weather phenomena of the satellite image. In addition, the control unit (150) can provide additional information related to the searched satellite image by utilizing events or environmental characteristics of the region corresponding to the satellite image.

[0081] The control unit (150) can search for satellite images using search conditions and user queries together. The control unit (150) can also analyze satellite images and generate answers using search conditions and user queries.

[0082] However, for the convenience of explanation, the present invention will describe a method for providing a satellite imagery purchase service based on user queries.

[0083] The control unit (150) can perform different methods for searching satellite images, analyzing searched satellite images, and generating answers depending on the content (perspective) of the user query. That is, the control unit (150) can provide a satellite image purchasing service through different data processing depending on the content (perspective) of the user query. More details will be described later.

[0084] The control unit (150) can provide an answer to the chat area (1020) and provide a searched satellite image (1031) to the preview area (1030). The control unit (150) can display at least a portion of the searched satellite image (1031) in the preview area (1030). In this case, the control unit (150) can provide only a portion of the satellite image (1031) corresponding to the answer to the preview area (1030).

[0085] The user can check the answers provided in the chat area (1020) and the satellite image (1031) provided in the preview area (1030) and decide to purchase the satellite image.

[0086] As illustrated in FIG. 4b, the control unit (150) may provide a satellite image group (1110, 1120, 1130) containing a preview satellite image to a service page (1000). The satellite image group (1110, 1120, 1130) may include at least one satellite image corresponding to a user query. Each of the satellite image groups (1110, 1120, 1130) may include different satellite images. Each of the first satellite image group (1110), the second satellite image group (1120), and the third satellite image group (1130) has in common that they include a preview satellite image (1031) and a satellite image corresponding to a user query. However, the first satellite image group (1110), the second satellite image group (1120), and the third satellite image group (1130) may differ in at least one of the following: location information, shooting date information (or shooting period information), resolution information, cloud ratio information, and image provider information. For example, let us assume that a user requests a search for satellite images taken in 2024 with a cloud ratio of less than 10%. The first satellite image group (1110) may include satellite images of Pangyo Station taken in 2024, and the second satellite image group (1120) may include satellite images of Namyangju taken. The user may purchase all (1110a) or select and purchase (1100b) the satellite image groups they wish to purchase.

[0087] In the present invention, a process of specifying the type of user query based on the perspective of purchasing satellite imagery can be performed (S320, see FIG. 3).

[0088] The control unit (150) can specify a user query as one of a plurality of predefined query types. The control unit (150) can classify the user query as one of the plurality of query types depending on what perspective it has regarding the purchase of satellite imagery.

[0089] In the present invention, the perspective on purchasing satellite imagery can be understood as the major criteria, interests, or purposes considered by a user when purchasing satellite imagery. In the present invention, depending on the perspective on purchasing satellite imagery, a plurality of query types may be predefined.

[0090] As illustrated in FIG. 5, among a plurality of query types, the first query type (or the first type of user query or the first type of user question, 510) may include general questions. The control unit (150) may specify the user query as the first query type (or the first type of user query) if the user query corresponds to a general question, particularly a question related to satellite imagery (satellite device, satellite platform, satellite platform, etc.). For example, the control unit (150) may specify the user query “tell me about Sentinel-2 Satellite” as the first query type (the second type of user query, 520).

[0091] Among a plurality of query types, the second query type (or the first type of user query or the second type of user question, 520) may include satellite image search condition information. The satellite image search condition information may include at least one of satellite image capture area information, satellite image capture date information, satellite image cloud ratio information, satellite image ROI (Region Of Interest) size information, satellite image resolution information, and satellite image provider information. For example, the control unit (150) may specify the user query “Can I get data for the Brooklyn Bridge from SkySat with small ROI and cloud-free?” as the second query type (the second type of user query, 520).

[0092] Among the multiple query types, the third query type (or the third type of user query or the third type of user question, 530) may include content related to news articles. The control unit (150) may specify the user query as the third query type (the third type of user query, 530) if the user query is associated with the occurrence of a specific event (e.g., wildfire, flood, cherry blossom blooming, etc.). For example, the control unit (150) may specify “Where the recent wildfire have occurred?” as the third query type (the third type of user query, 530).

[0093] In the present invention, a process of searching for at least one satellite image associated with a user query can be performed by using a specific agent corresponding to a query type among a plurality of agents of a large language model (S330, see FIG. 3).

[0094] The large language model (160) may include a plurality of agents that process user queries. As illustrated in FIG. 5, the large language model (160) may include at least one of a first agent (Search Agent, 161) that processes a first type of user query (510), a second agent (Cloud Agent, 162) that processes a second type of user query (520), and a third agent (News Agent, 163) that processes a third type of user query (530).

[0095] Each of the multiple agents (161, 162, 163) may have a different method of searching for satellite images from the satellite image DB (30) and a different method of generating an answer to a user query using the satellite images.

[0096] A first agent (Search Agent, 161) can process a first type of user query (510) corresponding to a general question (in particular, a question related to a satellite or a question related to a specific satellite system). The first agent (161) can search for at least one satellite image taken from a specific satellite or a specific satellite system from the satellite image DB (30). For example, the control unit (150) can search for a satellite image taken from “SENTINEL-2 SATELLITE” from the satellite image DB (30).

[0097] The second agent (Cloud Agent, 162) can process a second type of user query (520) that includes search condition information. The second agent (162) can search for a plurality of satellite images corresponding to the search condition information from the satellite image DB (30).

[0098] As previously explained, the search condition information may include at least one of satellite image capture area information, satellite image capture date information, satellite image cloud ratio information, satellite image ROi (Region Of Interest) size information, satellite image resolution information, and satellite image provider information.

[0099] For example, let’s assume that a user query includes the expressions “small roi” and “than 5 percent cloud coverage?”. The second agent (162) can interpret the user query and search for “satellite images without clouds in a small roi area” from the satellite image DB.

[0100] A third agent (News Agent, 163) can process a third type of user query related to a specific event. The third agent (163) can search for news articles related to a specific event. The third agent (163) can search for at least one news article related to a specific event from an external server capable of searching for news articles (e.g., news article server, portal server, etc.).

[0101] The third agent (163) can identify associated locations related to the searched news article. The third agent (163) can identify associated locations by extracting location data included in the news article. Additionally, the third agent (163) can identify associated locations through analysis of the news article content.

[0102] The third agent (163) can search for satellite images of associated locations from the satellite image DB (30).

[0103] In this case, the third agent (163) can further specify the date on which a specific event occurred from at least one of the user query and news article. The third agent (163) can search the satellite image DB (30) for satellite images of the associated location taken on the date on which the specific event occurred.

[0104] The third agent (163) can search for multiple news articles related to a specific event and extract multiple related locations from the multiple news articles. The third agent (163) can also search for satellite images of each of the multiple related locations from the satellite image DB (30).

[0105] The control unit (150) can connect a user query with any one of a plurality of agents (161, 162, 163) according to the user query type. The control unit (150) can call a specific agent corresponding to the user query type and process the user query as input to the specific agent.

[0106] The control unit (150) can generate prompts (510a, 520a, 530a) containing user queries. The control unit (150) can process the prompts (510a, 520a, 530a) as input for a specific agent. The control unit (150) can configure the prompts (510a, 520a, 530a) differently depending on the type of user query.

[0107] In the present invention, a process of interpreting satellite images retrieved through a specific agent to generate an answer to a user query may be performed (S340, see FIG. 3). In addition, in the present invention, a process of providing the retrieved satellite images and the answer to a service page may be performed (S350, see FIG. 3).

[0108] The control unit (150) can generate an answer to a user query using a specific agent. The control unit (150) can control the specific agent to generate an answer to a user query using the retrieved satellite image.

[0109] Each of the multiple agents (161, 162, 163) may have a different method of searching for satellite images from the satellite image DB (30) and a different method of generating an answer to a user query using the satellite images.

[0110] As illustrated in FIG. 5, a first agent (Search Agent, 161) can generate a first type of answer (600) for a first type of user query. The first agent (161) can generate an answer for a user query such that it includes descriptive information describing a specific satellite platform.

[0111] The answer generated by the first agent (161) may include at least one of mission information of a specific satellite platform, function information provided by a specific satellite platform, resolution information of satellite images taken by a specific satellite platform, and shooting range of a specific satellite platform.

[0112] As illustrated in FIG. 6, the control unit (150) can provide a first type of answer (600) to the service page (1000) in response to a first type of user query (510). The control unit (150) can provide an answer message (610) containing descriptive information of a specific satellite platform to the chat area (1020). For example, the control unit (150) can provide “information about the Sentinel-2 satellite” corresponding to a first type of user query (e.g., “Can i know what is Sentinel-2 satellite?, 510”) in the chat area (1020) as an answer message (620). The control unit (150) can also provide satellite images (620) taken from a specific satellite platform in the preview area (1030). The control unit (150) can provide additional information about the satellite images (620) provided in the preview area (1030) even if no additional user query is entered. More details will be described later.

[0113] The second agent (Cloud Agent, 162) can generate a second type of answer (700) for a second type of user query (520).

[0114] As illustrated in FIG. 7, the second agent (162) can generate at least one of an answer message (710), an image list (720), a searched satellite image (730), and a region of interest (740) as a second type of answer (700). The control unit (150) can provide the second type of answer (700) generated through the second agent (162) to the service page (1000).

[0115] The control unit (150) can provide a response message (710) containing guidance information (e.g., “We have retrieved all the requests data. Please review the data list on the right.”) that guides the image list (720) to the chat area (1020). Additionally, the control unit (150) can provide quality information of the satellite image analyzed based on condition information through the chat area (1020). For example, the control unit (150) can provide a response message to the chat area (1020) that includes quality information such as the region (location), shooting date, resolution, ROI, cloud ratio, and image provider of the satellite image.

[0116] The control unit (150) may provide a video list (720) around the chat area (1020). The video list (720) may include a plurality of satellite image items searched based on condition information. The plurality of items may include at least one of a thumbnail of each of the plurality of satellite images, the region (place) of the satellite image, the date of capture, the resolution, the ROI, the cloud ratio, and the image provider.

[0117] The control unit (150) can provide one of the satellite images (730) among the multiple satellite images searched based on search condition information to the preview area (1030). The control unit (150) can highlight (highlight) the region of interest (740) corresponding to the user query in the preview area (1030). The region of interest (740) can be rendered on the satellite image (730) as a square of the size of the region of interest (roi) that fits the range requested in the user query. For example, the LLM can interpret the expressions “roi”? and “than 5 percent cloud coverage”? in the second type of user query and highlight “image without clouds in a narrow roi region” as the region of interest (740).

[0118] The control unit (150) can provide a satellite image and a region of interest corresponding to a specific item in the preview area (1030) in conjunction with the selection of a specific item in the image list (720). The control unit (150) can also provide a reply message containing quality information of the satellite image corresponding to the specific item in the chat area (1020).

[0119] A third agent (News Agent, 163) can generate a third type of answer (800) for a third type of user query. The third agent (163) can search for news articles related to a specific event. And the third agent (163) can generate an answer related to a specific event using the searched news articles.

[0120] As illustrated in FIG. 8, the control unit (150) can provide a third type of response generated by the third agent (163) to the service page (1000). The control unit (150) can provide a response message (810) containing a response related to a specific event to the chat area (1020).

[0121] The answer related to a specific event may include at least one of the following: an article title retrieved from the third agent (163), information on a place associated with the retrieved article (country or address), date information associated with the retrieved article or the specific event (date information), summary information of the retrieved article, content information of the retrieved article, and the relevance between the specific event and the retrieved article.

[0122] The control unit (150) may provide a news article list (820) around the chat area (1020). The news article list (820) may include at least one searched news article item. The news article item may include at least one of a thumbnail of the news article, a thumbnail of a satellite image associated with the news article, an article title, an associated location, a date taken, a resolution, ROI, a cloud ratio, and an image provider.

[0123] The control unit (150) can provide a satellite image (830) related to a specific event to the preview area (1030). The control unit (150) can provide a satellite image corresponding to a specific item to the preview area (1030) in conjunction with the selection of a specific item in the news article list (820).

[0124] Meanwhile, the control unit (150) can analyze and provide the weather conditions of the satellite image that the user intends to purchase, even without a user's question. The control unit (150) analyzes whether the satellite image contains clouds or other weather phenomena and provides this information in advance, allowing the user to make an accurate decision to purchase the satellite image.

[0125] The control unit (150) can analyze the weather conditions of the satellite image searched using a user query and provide additional information regarding the user query. That is, the control unit (150) can analyze the weather conditions of the satellite image provided on the service page (1000) and provide additional answers. In the following description, to avoid confusion of terminology, the satellite image will be referred to as the “satellite image to be purchased.”

[0126] As illustrated in FIG. 9a, the control unit (150) can provide weather condition information of the satellite image to be purchased (e.g., snow, rain, cloud ratio, other weather phenomena other than clouds, etc.) as an additional answer (931) even if the user does not enter an additional user query, in order to induce the user to decide to purchase the satellite image to be purchased.

[0127] The control unit (150) can provide additional information (930) using the satellite image to be purchased while providing the first answer (921) to the user query (911). The control unit (150) can generate a prompt (920) for analyzing the weather conditions of the satellite image to be purchased. The control unit (150) can obtain additional information by processing this prompt (920) as input to a large language model (160).

[0128] The control unit (150) can generate a prompt (920) using at least one of a user query (911), a satellite image to be purchased, and a response (921) to the user query. The control unit (150) can also specify one of the multiple agents (161, 162, 163) of the large language model (160) to be used for an additional response by using at least one of the user query (911), a satellite image to be purchased, and a response (921) to the user query.

[0129] The control unit (150) can identify a satellite image different from the satellite image to be purchased from the satellite image DB as a recommended satellite image (932, 933). The control unit (150) can identify the recommended satellite image (921, 933) based on at least one of the user query and weather condition information for the purchased satellite image.

[0130] For example, the control unit (150) may specify the satellite image (932) taken on a different day as the recommended satellite image based on the fact that the cloud ratio included in the satellite image (932) taken on a different day by the same satellite at the same location as the satellite image to be purchased is lower than that of the satellite image to be purchased. As another example, the control unit (150) may recommend the satellite image (933) taken on a different location by the same satellite on the same day as the satellite image to be purchased as the recommended satellite image.

[0131] The control unit (150) can generate and provide additional answers including the reasons for the recommendation of the recommended satellite images (932, 933) using a large language model (160). The reasons for the recommendation may include at least one of the weather condition information of the satellite image to be purchased and the recommended satellite image, the shooting location, the shooting date, the resolution, ROI, the cloud ratio, and the image provider.

[0132] Meanwhile, the control unit (150) can provide additional information by using at least one of the events and environmental characteristics of a specific region using a large language model (160).

[0133] The control unit (150) can extract keywords for providing additional information from a user query. The control unit (150) can expand the keywords. The control unit (150) can expand the keywords so that satellite images different from the search for satellite images to be purchased are searched. The control unit (150) can generate expanded keywords to reflect either local events or local environmental characteristics. The control unit (150) can generate a prompt (950) for providing additional information using the keywords and expanded keywords.

[0134] For example, as illustrated in FIG. 9b, the control unit (150) can extract “Brooklynese” as a keyword from a user query (941). The control unit (150) can identify extended keywords that reflect events in the Brooklyn area (e.g., festivals, marine debris collection, etc.) and environmental characteristics (e.g., “cherry blossoms,” “raw materials,” “ocean currents,” “ships”). The control unit (150) can generate a prompt (950) that includes a query such as “Show me a video of the Brooklyn area with lots of cherry blossoms.”

[0135] The control unit (150) can process the prompt (950) as input to the large language model (160). The control unit (150) can use the large language model (160) to obtain additional information (960) in which a specific region includes at least one of an event and an environmental characteristic. The additional information (960) may include recommended satellite images (962, 963) and a response message (961) including the reason for the recommendation of the recommended satellite images. Since the method for generating additional information is the same as the method described above, a detailed description will be omitted.

[0136] The method and system for providing a language model-based satellite imagery purchase service according to the present invention receives a user query related to satellite imagery purchase through a service page and can provide an environment in which the user searches for and orders satellite images using natural language.

[0137] Furthermore, the method and system for providing a language model-based satellite imagery purchasing service according to the present invention can identify a query type corresponding to the user query among a plurality of query types classified based on the satellite imagery purchasing perspective, and search for at least one satellite imagery associated with the user query by using a specific agent corresponding to the query type among a plurality of agents of a large language model. The present invention can search for satellite imagery optimized for the user query and provide related information.

[0138] Furthermore, the method and system for providing a language model-based satellite image purchasing service according to the present invention interprets the satellite image retrieved through the specific agent to generate an answer to the user query, and the user can check the quality of the satellite image before purchasing.

[0139] Furthermore, the method and system for providing a language model-based satellite image purchase service according to the present invention can improve satisfaction and reliability by providing the searched satellite image and the answer on a service page to verify whether the satellite image desired by the user is correct and preventing the user from purchasing unnecessary satellite images.

[0140] Meanwhile, computer-readable media include all types of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable media include HDD (Hard Disk Drive), SSD (Solid State Disk), SSD (Silicon Disk Drive), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0141] Furthermore, the computer-readable medium may be a server or cloud storage that includes a storage and is accessible to an electronic device via communication. In this case, the computer may download the program according to the present invention from the server or cloud storage via wired or wireless communication.

[0142] Furthermore, in the present invention, the computer described above is an electronic device equipped with a processor, namely a CPU (Central Processing Unit), and no special limitations are placed on its type.

[0143] Meanwhile, the above detailed description should not be interpreted restrictively in all respects but should be considered exemplary. The scope of the invention should be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the invention are included within the scope of the invention.

Claims

1. A step of receiving a user query related to satellite image purchase through a service page; A step of specifying a query type corresponding to the user query among a plurality of query types classified based on the above satellite image purchasing perspective; A step of searching for at least one satellite image associated with the user query using a specific agent corresponding to the query type among a plurality of agents of a large language model; A step of interpreting the satellite image retrieved through the specific agent above to generate an answer to the user query; and A method for providing a language model-based satellite image purchasing service, characterized by including the step of providing the searched satellite image and the answer on the service page.

2. In Paragraph 1, Among the above plurality of query types, the first type of user query corresponds to a question related to a specific satellite platform, and Among the plurality of agents above, the first agent processing the user query of the first type is, A method for providing a language model-based satellite image purchasing service, characterized by searching for at least one satellite image taken by the specific satellite system from a satellite image DB and generating the answer using descriptive information describing the specific satellite platform.

3. In Paragraph 2, Among the above plurality of query types, the user query of the second type is, A method for providing a language model-based satellite image purchasing service, characterized by including at least one search condition information among the satellite image capture area information, the satellite image capture date information, the satellite image cloud ratio information, the satellite image ROi (Region Of Interest) size information, the satellite image resolution information, and the satellite image provider information.

4. In Paragraph 3, Among the plurality of agents above, the second agent processing the second type of user query is, A method for providing a language model-based satellite image purchasing service, characterized by searching for a plurality of satellite images corresponding to the search condition information from the above satellite image DB, and generating the above answer describing a list including the plurality of satellite images.

5. In Paragraph 4, Among the above plurality of query types, the third type of user query is related to a specific event, and Among the plurality of agents above, the third agent processing the user query of the third type is, Search for news articles related to the specific event mentioned above, and A method for providing a language model-based satellite image purchasing service characterized by searching for satellite images of associated locations related to the news article from the above satellite image DB.

6. In Paragraph 5, The above third agent is, A method for providing a language model-based satellite imagery purchasing service characterized by generating the answer related to the specific event using the searched news article.

7. In Paragraph 1, The above service page is, The chat area where the above user query is entered, A search area where search condition information for the above-mentioned satellite image search is entered, and A method for providing a language model-based satellite image purchasing service characterized by including a preview area where the above-mentioned searched satellite image is provided.

8. In Paragraph 7, The above service page further includes a step of providing additional information regarding the above user query, and In the step of providing the above additional information, A method for providing a language model-based satellite image purchasing service characterized by analyzing the weather conditions of the searched satellite image and generating an additional answer including the weather condition information and providing it to the chat area.

9. A communication unit that receives a user query related to the purchase of satellite imagery through a service page; and Identifying a query type corresponding to the user query among a plurality of query types classified based on the above satellite imagery purchasing perspective, and Using a specific agent corresponding to the query type among multiple agents of a large language model, at least one satellite image associated with the user query is searched, and Interpreting the satellite image retrieved through the specific agent above to generate an answer to the user query, and A method for providing a language model-based satellite image purchasing service, characterized by including a control unit on the above-mentioned service page that provides the above-mentioned searched satellite image and the above-mentioned answer.

10. A program that is executed by one or more processes in an electronic device and stored on a computer-readable recording medium, The above program is, A step of receiving a user query related to satellite image purchase through a service page; A step of specifying a query type corresponding to the user query among a plurality of query types classified based on the above satellite image purchasing perspective; A step of searching for at least one satellite image associated with the user query using a specific agent corresponding to the query type among a plurality of agents of a large language model; A step of interpreting the satellite image retrieved through the specific agent above to generate an answer to the user query; and A program characterized by including commands on the above service page that perform the step of providing the above-searched satellite image and the above-searched answer.

Images