Method for providing route guidance and device for performing same

Abstract

A method for providing route guidance is disclosed. According to an embodiment, the method may include the operations of: obtaining at least one image of a turn point included in a traveling route of a vehicle; generating a prompt on the basis of the at least one image and a turning direction of the vehicle; and outputting a turning guidance message generated by inputting the prompt to a generative model.

Description

Method for guiding a path and device for performing the same

[0001] The following disclosure relates to a method for guiding a path and an apparatus for performing the same.

[0002] A navigation device can generate an optimized driving route to a vehicle's destination and provide guidance. At points where the vehicle must change direction, such as intersections or junctions, the navigation device can provide turn-by-turn (TBT) guidance. TBT guidance may enable the driver to drive stably to the destination without deviating from the route by providing the navigation device with step-by-step instructions regarding the next turn.

[0003] On the other hand, because each driver has a different sense of distance, distance-based TBT guidance may be difficult for drivers to gauge and may not be intuitive regarding how much distance remains to the turn point.

[0004] The background technology described above is possessed or acquired by the inventor in the process of deriving the content of the disclosure of the present application, and cannot necessarily be considered as prior art disclosed to the general public prior to the filing of this application.

[0005] One embodiment may provide a technology that generates a rotation guidance message using a real image of a rotation point through an artificial intelligence model.

[0006] One embodiment can provide a rotation guidance message that allows the user to easily recognize the turning point.

[0007] However, technical challenges are not limited to the technical challenges described above, and other technical challenges may exist.

[0008] A method according to one embodiment may include the operation of acquiring at least one image of a turn point included in a driving path of a vehicle, the operation of generating a prompt based on the at least one image and the turning direction of the vehicle, and the operation of inputting the prompt into a generative model to output a generated turning guidance message.

[0009] According to one embodiment, the at least one image may include an image taken at at least one location close to the direction change point.

[0010] According to one embodiment, the at least one image may include a road view image, a virtual tour image, and aerial photography.

[0011] According to one embodiment, the operation of generating the prompt may include extracting a feature from at least one image and generating the prompt including a prompt portion corresponding to the feature and the rotation direction of the vehicle.

[0012] According to one embodiment, the operation of outputting the rotation guidance message may include the operation of generating a rotation guidance message candidate corresponding to each of the at least one image based on the prompt, the operation of verifying the validity of the rotation guidance message candidate based on map data, and the operation of selecting a rotation guidance message to be output from the rotation guidance message candidate based on the remaining distance to the turning point of the vehicle.

[0013] According to one embodiment, the operation of verifying the validity of the rotation guidance message candidate may include verifying whether the feature point is associated with the driving path according to the rotation guidance message candidate based on the map data.

[0014] According to one embodiment, a computer-readable recording medium storing one or more computer programs may include instructions for performing the method in a processor.

[0015] A device according to one embodiment may include at least one processor. The device may include a memory containing instructions. Based on the instructions being executed individually or collectively by the at least one processor, the device may acquire at least one image of a turn point included in a driving route of a vehicle, generate a prompt based on the at least one image and the turning direction of the vehicle, and input the prompt into a generative model to output a generated turn guidance message.

[0016] According to one embodiment, the at least one image may include an image taken at at least one location close to the direction change point.

[0017] According to one embodiment, the at least one image may include a road view image, a virtual tour image, and aerial photography.

[0018] According to one embodiment, based on the instructions being executed individually or collectively by the at least one processor, the device may be able to extract a feature from the at least one image and generate the prompt, which includes a prompt portion corresponding to the feature and the rotation direction of the vehicle.

[0019] According to one embodiment, based on the instructions being executed individually or collectively by the at least one processor, the device may generate a turn guidance message candidate corresponding to each of the at least one image based on the prompt, verify the validity of the turn guidance message candidate based on map data, and select a turn guidance message to be output from the turn guidance message candidate based on the remaining distance to the turning point of the vehicle.

[0020] According to one embodiment, based on the instructions being executed individually or collectively by the at least one processor, the device may verify whether the feature point is associated with the driving path according to the rotation guidance message candidate based on the map data.

[0021] In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0022] FIG. 1 is a drawing for explaining a navigation system according to one embodiment.

[0023] Figure 2 is a diagram illustrating distance-based TBT guidance.

[0024] FIG. 3 is a diagram illustrating the operation of acquiring an image of a direction change point according to one embodiment.

[0025] FIG. 4 is a diagram illustrating the operation of generating a rotation guidance message according to one embodiment.

[0026] FIG. 5 is a flowchart illustrating a method according to one embodiment.

[0027] FIG. 6 is a flowchart illustrating a method according to one embodiment.

[0028] FIG. 7 is a schematic block diagram of an electronic device according to one embodiment.

[0029] Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, actual implementations are not limited to the specific embodiments disclosed, and the scope of this specification includes modifications, equivalents, or substitutions included in the technical concept described by the embodiments.

[0030] Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component.

[0031] When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or joined to that other component, or that there may be other components in between.

[0032] Singular expressions include plural expressions unless the context clearly indicates otherwise. In this document, phrases such as “A or B,” “at least one of A and B,” “at least one of A or B,” “A, B or C,” “at least one of A, B and C,” and “at least one of A, B, or C” may each include any one of the items listed together with the corresponding phrase, or all possible combinations thereof. In this specification, terms such as “comprising” or “having” are intended to designate the existence of the described feature, number, step, action, component, part, or combination thereof, 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.

[0033] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this specification.

[0034] As used herein, the term "module" may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be a component formed integrally, or a minimum unit of said component or a part thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0035] As used in this document, the term "part" refers to software or hardware components, such as FPGAs or ASICs, and the "part" performs certain roles. However, the meaning of "part" is not limited to software or hardware. The "part" may be configured to reside in an addressable storage medium or configured to operate one or more processors. For example, the "part" may include components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." Furthermore, the components and "parts" may be implemented to operate one or more CPUs within a device or secure multimedia card. Additionally, '~part' may include one or more processors.

[0036] Hereinafter, embodiments will be described in detail with reference to the attached drawings. In the description with reference to the attached drawings, identical components are given the same reference numeral regardless of the drawing number, and redundant descriptions thereof will be omitted.

[0037]

[0038] FIG. 1 is a drawing for explaining a navigation system according to one embodiment.

[0039] Referring to FIG. 1, according to one embodiment, a navigation system (10) may include a navigation device (100), a vehicle (110), and a server (130). The navigation device (100) may include a device that reflects the real-time location of the vehicle (110) on a map and provides a route from the current location of the vehicle (110) to a destination. The navigation device (100) may be installed inside the vehicle (110) or implemented through an end-device (e.g., a terminal such as a smartphone or tablet PC) of a user (e.g., a user of the vehicle (110)). For example, the navigation device (100) may include an electronic device (e.g., a terminal) on which a navigation device and / or a navigation application is installed, which is installed on the dashboard of the vehicle (110). A vehicle (e.g., vehicle (110)) means a vehicle capable of transporting goods and / or people, and may include, for example, a car, train, ship, boat, aircraft, kickboard and / or bicycle. A server (130) may collect information necessary for route generation, such as road conditions, accident information, and traffic conditions. The server (130) may transmit the collected information to a navigation device (100). The navigation device (100) may obtain the location of the vehicle (110) through a location tracking module installed in the vehicle (110) (e.g., a module such as a GPS (global positioning system) module, a GNSS (global navigation satellite system) module, or an INS (inertial navigation system) module). The navigation device (100) may generate a route based on the location of the vehicle (110). The navigation device (100) can guide a user (e.g., user of a vehicle (110)) to a route through a display.

[0040] According to one embodiment, a navigation device (100) may provide a turn guidance message (e.g., turn-by-turn guidance) for a turn point included in the driving route of a vehicle (e.g., vehicle (110)). The turn guidance message may be provided in real time at each turn point while the vehicle (110) is moving. For example, the navigation device (100) may provide the turn guidance message to a user (e.g., user of the vehicle (110)) in response to the vehicle (110) approaching a turn point. The turn guidance message may include the remaining distance to the turn point and the direction of turn. The direction of turn of the vehicle (110) may be the direction in which the vehicle (110) must turn at the turn point. For example, the direction of turn of the vehicle (110) may include information regarding the angle at which the vehicle (110) must change steering, such as turning right, turning left, entering at one o'clock, or entering at three o'clock. The navigation device (100) can generate a rotation guidance message using a generative model. The generative model may be located inside and / or outside the navigation device (100) (e.g., a server (130)).

[0041] According to one embodiment, the navigation device (100) may acquire at least one image of a turning point included in the driving path. For example, the navigation device (100) may acquire at least one image of a turning point from a server (130). The at least one image of a turning point may include an image taken at least one location close to the turning point. The at least one image of a turning point may include a road view image, a virtual tour image, and aerial photography. Note that at least one image may include any type of image captured through a camera installed on the vehicle (e.g., a front camera, a rear camera, a surround view camera, a side mirror camera), and that road view images, virtual tour images, and aerial photographs are merely examples. The navigation device (100) may generate a prompt based on at least one image of a turning point and the turning direction of the vehicle (110). The navigation device (100) may input the prompt into a generative model and output a generated turning guidance message.

[0042] According to one embodiment, the navigation device (100) can generate a turn guidance message in real time based on the position of the vehicle (110). The navigation device (100) can obtain at least one image of the turn point from the server (130) in response to the vehicle (110) entering a preparation section for the turn point (e.g., preparation section (320) of FIG. 3). The preparation section is a section located at a predetermined distance from the turn point and may be a section that the navigation device (100) prepares to generate a turn guidance message. In response to the vehicle (110) entering the preparation section (e.g., preparation section (320)), the navigation device (100) can obtain information such as the position of the vehicle (110), speed, remaining distance to the turn point, and remaining path to the turn point (e.g., path column). The navigation device (100) can generate a prompt based on at least one image of a turning point and the turning direction of the vehicle (110). The navigation device (100) can input the prompt into a generative model and output a generated turning guidance message.

[0043] According to one embodiment, a navigation device (100) may extract turning points included in the driving path to the destination of a vehicle (110) and pre-generate turning guidance messages to be provided at each turning point. For turning points included in a digital map, the navigation device (100) may pre-generate turning guidance messages based on at least one image and the turning direction of the vehicle (110) and store them in a database (DB). The navigation device (100) may generate a prompt based on at least one image of a turning point and the turning direction of the vehicle (110) at the turning point. The navigation device (100) may obtain at least one image of a turning point from a server (130). The navigation device (100) may input the prompt into a generative model to obtain the generated turning guidance message. The navigation device (100) may store the generated turning guidance message in the database (DB). The database may be located inside and / or outside the navigation device (100) (e.g., a server (130)). The navigation device (100) may generate a driving path from the current location of the vehicle (110) to the destination in response to the input of the destination of the vehicle (110). The navigation device (100) may extract turning points included in the driving path of the vehicle (110). The navigation device (100) may obtain a turn guidance message for each turning point from the database (DB). The navigation device (100) may obtain and output a corresponding turn guidance message from the database in response to the vehicle (110) approaching a turning point.The navigation device (100) may update a prompt for generating an image and / or a turn guidance message in response to failing to generate a valid turn guidance message for a turn point or failing to acquire a suitable image for a turn point. The navigation device (100) may additionally acquire an image of the turn point or modify a prompt for generating a turn guidance message in response to a discrepancy between the actual driving path and the turn guidance message generated for the turn point, or failing to acquire an image capable of generating a turn guidance message for the turn point. The navigation device (100) may store the updated turn guidance message in a database and output the updated turn guidance message at the corresponding turn point.

[0044] According to one embodiment, each constituent entity (e.g., navigation device (100), vehicle (110), and server (130)) can perform communication using a network (not shown). For example, the network may include a Local Area Network (LAN), a Wide Area Network (WAN), a Value Added Network (VAN), a mobile radio communication network, a satellite communication network, and combinations thereof. The network is a comprehensive data communication network that enables each constituent entity (e.g., navigation device (100), vehicle (110), and server (130)) to communicate seamlessly with one another, and may include wired internet, wireless internet, and mobile wireless communication networks. In addition, wireless communication networks may include, for example, Wi-Fi, Bluetooth, Bluetooth Low Energy, Zigbee, Wi-Fi Direct (WFD), Ultra-Wideband (UWB), Infrared Data Association (IrDA), and Near Field Communication (NFC), but are not limited to these.

[0045]

[0046] Figure 2 is a diagram illustrating distance-based TBT guidance.

[0047] Referring to FIG. 2, according to one embodiment, a navigation device (e.g., the navigation device (100) of FIG. 1) can provide TBT guidance to a vehicle (210) (e.g., the vehicle (110) of FIG. 1). The navigation device (100) can generate a driving path from the current location of the vehicle (210) to the destination in response to the vehicle (210) having its destination entered. The navigation device (100) can extract turning points included in the driving path (e.g., turning points such as intersections, forks, and junctions). The navigation device (100) can obtain information such as the turning direction of the vehicle (210) at the turning points and lane information, and generate TBT guidance. The navigation device (100) can generate a time to provide TBT guidance and / or a script for TBT guidance based on information about each turning point (e.g., information such as road grade). The navigation device (100) can generate a turn guidance message (e.g., turn guidance message (201)) based on the distance to the turning point. For example, the navigation device (100) can generate a turn guidance message (201), such as "Drive to the right highway entrance about 300m ahead," in response to the vehicle (210) approaching 300m before the turning point. The navigation device (100) can provide at least one turn guidance message in response to the vehicle (210) approaching a determined distance to the turning point. For example, the navigation device (100) can provide a turn guidance message corresponding to each point in response to the vehicle (210) approaching a turning point at a distance of 700 meters, 300 meters, and 100 meters.

[0048] Conventional navigation systems provide turn guidance messages to users by extracting turn points on the driving path of a vehicle (210) and outputting TBT guidance at predetermined distances for each turn point. Since each driver has a different sense of distance, this distance-based TBT guidance may not be intuitive because it can be difficult to gauge how much distance remains to the actual turn point. Additionally, because it is difficult to determine the time to turn based on the driving speed of the vehicle (210), the driver may experience the inconvenience of having to identify the turn point by referring to the navigation screen rather than the road ahead.

[0049]

[0050] FIG. 3 is a diagram illustrating the operation of acquiring an image of a direction change point according to one embodiment.

[0051] Referring to FIG. 3, according to one embodiment, a navigation device (e.g., the navigation device (100) of FIG. 1) may provide a turn guidance message for a turning point (350) included in a driving path (301) to a destination of a vehicle (310) (e.g., the vehicle (110) of FIG. 1). The turning point (350) may include a point where the vehicle (310) must change direction, such as an intersection, a fork in the road, or a branching point. The navigation device (100) may provide a turn guidance message in response to the vehicle (310) approaching the turning point (350) by a predetermined distance. For example, the navigation device (100) may provide a turn guidance message in response to the vehicle (310) entering a proximity section (340). The proximity section (340) may be a section within a predetermined distance from the turning point (350) included in the driving path (301). For example, the proximity section (340) may include a section close to the turning point (350) such that the driver of the vehicle (310) can visually recognize the turning point (350). The navigation device (100) may generate a prompt to generate a turn guidance message in response to the vehicle (310) entering the preparation section (320). The operation of the navigation device (100) generating the turn guidance message will be described in detail later with reference to FIG. 4. The preparation section (320) is a section located at a predetermined distance from the turning point (350) and may be a section that the navigation device (100) prepares to generate the turn guidance message. In response to the vehicle (310) entering the preparation section (320), the navigation device (100) may determine at least one location (e.g., candidate locations (341-343)) close to the turning point (350).

[0052] According to one embodiment, the navigation device (100) may acquire at least one image of a turning point (350) included in the driving path (301) of the vehicle (310). The at least one image may include an image taken at a candidate location (341–343) which is at least one location close to the turning point (350). The navigation device (100) may set a target location (370) that the vehicle (310) may be located at after turning. The target location (370) may include at least one location that the vehicle (310) may be located at after driving a predetermined distance (e.g., n meters, provided that n is a positive number) on the road after the turning point (350). The navigation device (100) generates a heading angle looking toward the target location (370) from candidate locations (341–343) and can obtain at least one image taken at the angle looking toward the target location (370) from each candidate location (e.g., candidate locations (341–343)) from a server (e.g., server (130) of FIG. 1). For example, the navigation device (100) can obtain images such as a road view image, a virtual tour image, and aerial photography from the server (130) in the direction looking toward the target location (370) from candidate locations (341–343) via an API (application program interface). Note that the types of images that the navigation device (100) can obtain from the server (130) are not limited to the above examples. For example, the navigation device (100) can obtain all types of street images taken for map creation and / or autonomous driving learning from the server (130). For example, the images that the navigation device (100) can obtain may include all types of images taken through a camera installed on the vehicle (310).The navigation device (100) can preprocess an image obtained from the server (130). For example, the navigation device (100) can process the obtained image by cropping it to a predetermined size and / or desired area, thereby making the direction change points more limited.

[0053] According to one embodiment, the navigation device (100) may generate a turn guidance message for a turn point (350) in advance and store it in a database, and output the turn guidance message in response to the vehicle (310) entering the proximity section (340). The navigation device (100) may extract a turn point (e.g., turn point (350)) from a digital map and obtain at least one image for the turn point (e.g., turn point (350)). The navigation device (100) may input a prompt for generating a turn guidance message for a turn point (e.g., turn point (350)) into a generative model and store the generated turn guidance message in a database (DB). The navigation device (100) may obtain a corresponding turn guidance message from the database in response to the vehicle (310) entering the proximity section (340) and output the turn guidance message.

[0054]

[0055] FIG. 4 is a diagram illustrating the operation of generating a rotation guidance message according to one embodiment.

[0056] Referring to FIG. 4, according to one embodiment, FIG. 4 may be intended to explain the operation of a navigation device (100) described with reference to FIG. 1 to 3 generating a turn guidance message for a turn point (e.g., a turn point (350) in FIG. 3). The navigation device (100) may dynamically generate a turn guidance message for a turn point using a generative model (e.g., model (440)). The navigation device (100) may generate a turn guidance message for a turn point included on a map in advance using a generative model (e.g., model (440)) and store it in a database. The navigation device (100) may generate a prompt based on at least one image (e.g., image (401)) and the direction of rotation of the vehicle (e.g., the direction of rotation of the vehicle (403)). At least one image (e.g., image (401)) may include at least one image of a turning point described with reference to FIGS. 1 to 3. For example, image (401) may be an image taken at an angle looking toward the intersection that is the turning point from at least one location (e.g., candidate location (341) in FIG. 3) that is close to the turning point. For example, image (401) may include a plurality of consecutive images taken at an angle looking toward the intersection that is the turning point from a plurality of candidate locations (e.g., candidate location (341) to candidate location (343) in FIG. 3). The navigation device (100) may extract a feature from at least one image (e.g., image (401)). The feature may include a point of interest (POI) contained within the image (e.g., image (401)). A POI is a part of an image (e.g., image (401)) that contains information and / or features that a user might notice, and may include elements such as buildings, landmarks, and signs.Note that the feature points that the navigation device (100) can extract from at least one image capturing a turning point are not limited thereto. The navigation device (100) can extract feature points from at least one image (e.g., image (401)). The navigation device (100) can extract feature points from each of a plurality of images captured in succession. The navigation device (100) can extract feature points from a plurality of images when driving on a road with a complex structure and / or when it is determined that it is difficult to generate a turning guidance message based on feature points extracted from a single image. For example, the navigation device (100) can extract elements such as buildings, landmarks, and signs that can serve as feature points from each of a plurality of images captured at a plurality of candidate locations. The navigation device (100) can extract feature points by excluding dynamic objects (e.g., other vehicles, people) included in the image (e.g., image (401)). Even if dynamic objects are located around the turning point at the time the image (401) is captured, they are not always located around the turning point when the vehicle (e.g., the vehicle (110) of FIG. 1) turns, so if they are used to generate a turning guidance message, they can cause confusion to the user. For this reason, the navigation device (100) can extract feature points from the image (401) excluding dynamic objects. For example, the navigation device (100) can extract features such as a sign containing the text 'XX Coffee', a sign containing the text 'YY Mart', and a crosswalk included in the image (401).

[0057] According to one embodiment, a navigation device (100) may generate a prompt that includes a prompt portion corresponding to a feature point extracted from an image (e.g., image (401)) and a vehicle's rotation direction (403). The vehicle's rotation direction (403) may be the direction in which the vehicle (e.g., vehicle (110) of FIG. 1) turns at a turning point. The prompt may include a guidance script to be input into a generative model. The navigation device (100) may generate a prompt based on information such as the vehicle's rotation direction (403) and road grade. For example, the navigation device (100) may generate a prompt such as, "Generate a right turn guidance message based on a feature point that can be extracted from the image (401). However, do not consider objects whose position can be dynamically changed." For example, the navigation device (100) may generate a prompt such as, "Generate a step-by-step guidance message based on a feature point that can be extracted from continuously captured images." However, you can generate a prompt such as 'Please do not consider objects whose positions can change dynamically.'

[0058] According to one embodiment, the navigation device (100) can input a prompt into a generative model (e.g., model (440)). The model (440) may include a generative artificial intelligence model such as a large language model (LLM) or a large multimodal model (LMM). The model (440) may be located inside and / or outside the navigation device (100) (e.g., the server (130) of FIG. 1). The model (440) can generate a turn guidance message based on the prompt. For example, the model (440) can generate a turn guidance message based on the prompt, such as, "Turn right before crossing the crosswalk where the XX Coffee and YY Mart signs are visible. You should turn right when the XX Coffee building is on the right." For example, the model (440) can generate a turn guidance message based on feature points extracted from each of a plurality of images, such as, "Turn around at the point where the statue is visible past the overpass. You should enter the second alley."

[0059] According to one embodiment, the navigation device (100) can verify the validity of a turn guidance message based on map data. The navigation device (100) can verify the validity of a turn guidance message by verifying whether a feature point is associated with the driving path according to the turn guidance message. For example, regarding a turn guidance message such as "Turn right before crossing the crosswalk where the XX Coffee and YY Mart signs are visible. You can turn right when the XX Coffee building is on the right," the navigation device (100) can verify the validity of the turn guidance message by performing a search for the turning point in the map data and confirming whether 'XX Coffee', 'YY Mart', and the crosswalk actually exist. For example, the navigation device (100) can verify the validity of the turn guidance message by performing a search for the turning point in the map data for the generated turn guidance message, such as "Turn after passing the overpass at the point where the statue is visible. You just need to enter the second alley.", and by checking whether there is actually a 'statue' after passing the 'overpass' and whether it is appropriate to drive by entering the 'second alley' at the point where the 'statue' is visible.

[0060] According to one embodiment, the navigation device (100) can output a generated turn guidance message. The navigation device (100) can output a validated turn guidance message. The navigation device (100) can determine a point in time to start outputting the turn guidance message based on the length of the turn guidance message. For example, the navigation device (100) can determine a point in time to start outputting the turn guidance message based on the speed of the vehicle, the position of the vehicle, and the length of the turn guidance message. The navigation device (100) can determine a point in time to start outputting the turn guidance message so that the output of the turn guidance message can be terminated at or before the point in time when the vehicle passes the point where the image used to generate the turn guidance message (e.g., image (401)) was taken (e.g., at least one of candidate location (341) to candidate location (343) in FIG. 3). For example, the navigation device (100) can provide a turn guidance message to the vehicle such that the output of the turn guidance message, such as “Turn right before crossing the crosswalk where the XX Coffee and YY Mart signs are visible,” ends when the vehicle passes a candidate location (341) where “XX Coffee” and “YY Mart” are visible, or before. The navigation device (100) can provide a turn guidance message generated based on feature points that may be included in the driver’s field of vision at the actual turn point, rather than just providing the remaining distance to the turn point and the direction of turn, thereby allowing the driver to more intuitively grasp the turn point and drive stably.For convenience of explanation, FIG. 4 describes only a rotation guidance message generated based on an image (e.g., image (401)) taken at a single location, but the operation of the navigation device (100) outputting a rotation guidance message generated based on each of a plurality of images will be described in detail with reference to FIG. 5.

[0061] According to one embodiment, the navigation device (100) may provide distance-based turn guidance in response to a failure to generate a turn guidance message. The navigation device (100) may provide distance-based turn guidance based on the remaining distance in response to a determination that an image of a turn point cannot be obtained or that the generated turn guidance message is invalid. In response to a failure to generate a turn guidance message, the navigation device (100) may obtain an image of the corresponding turn point through a camera installed in the vehicle (110). The navigation device (100) may transmit the image of the turn point obtained through the camera installed in the vehicle (110) to a server (130). The server (130) may update the image of the turn point received from the navigation device (110) with the image of the corresponding turn point. The navigation device (100) may subsequently use the image updated in the server (130) together with or as a replacement for the existing image when generating a turn guidance message for the same turning point.

[0062]

[0063] FIG. 5 is a flowchart illustrating a method according to one embodiment.

[0064] Referring to FIG. 5, according to one embodiment, operations 510 to 580 may be operations performed by the navigation device (100) of FIG. 1 described with reference to FIG. 1 to FIG. 4.

[0065] According to one embodiment, operations 510 to 580 can be understood as being performed in a processor (e.g., processor (730) of FIG. 7) of a navigation device (100) (e.g., electronic device (700) of FIG. 7) described with reference to FIG. 1.

[0066] In operation 510, the navigation device (100) can obtain information about the real-time location, speed, and driving path to the turning point (e.g., turning point (350) in FIG. 3) of the vehicle (e.g., vehicle (110) of FIG. 1).

[0067] In operation 520, the navigation device (100) may extract at least one location near a turning point (e.g., turning point (350) in FIG. 3) and generate a directional angle. In response to the vehicle (110) entering a preparation section (e.g., preparation section (320) in FIG. 3) for a turning point (e.g., turning point (350)), the navigation device (100) may extract at least one location near the turning point (e.g., candidate locations (341–343) in FIG. 3) and generate a directional angle for a target location (e.g., target location (370) in FIG. 3) after the turning point at the extracted location. The directional angle may be an angle of view from each candidate location (e.g., candidate locations (341–343)) toward the target location (370), which is the location after the turning point.

[0068] In operation 530, the navigation device (100) can determine whether it has acquired at least one image of a turning point. The navigation device (100) can determine whether it has acquired at least one image suitable for generating a turn guidance message for a turning point. The navigation device (100) can determine whether the image of the turning point captured at each candidate location (e.g., candidate locations (341–343)) is of a suitable level for generating a turn guidance message. For example, the navigation device (100) can determine whether it has acquired at least one image suitable for generating a turn guidance message by analyzing factors such as the resolution of the image corresponding to each candidate location (341–343) and feature points of the turning point included in the image. The navigation device (100) can perform operation 540 in response to acquiring at least one image of the turning point. The navigation device (100) can perform operation 520 in response to failing to acquire at least one image of a turning point.

[0069] In operation 540, the navigation device (100) can generate a prompt including a prompt portion corresponding to a feature point extracted from an image and a rotation direction. The navigation device (100) can generate a prompt based on each image and rotation direction corresponding to at least one candidate location (e.g., candidate locations (341–343)) adjacent to a direction change point (e.g., direction change point (350)).

[0070] In operation 550, the navigation device (100) can generate rotation guidance message candidates. The navigation device (100) can generate rotation guidance message candidates corresponding to each of at least one image based on a prompt. The rotation guidance message candidates may be output by inputting a prompt into a model (e.g., the model (440) of FIG. 4).

[0071] In operation 560, the navigation device (100) can verify the validity of a candidate turn guidance message. The navigation device (100) can verify the validity of a candidate turn guidance message by verifying, based on map data, whether a feature point is actually associated with a driving path according to the candidate turn guidance message. For example, the navigation device (100) can verify whether a feature point included in an image of a turning point (350) taken at each candidate location (e.g., candidate locations (341–343)) is associated with a turning point in the actual map data. The navigation device (100) can store only the candidate turn guidance message verified as valid as a candidate turn guidance message to be output. The navigation device (100) can perform operation 570 in response to determining that a candidate turn guidance message is valid. The navigation device (100) can perform operation 520 in response to determining that a candidate rotation guidance message is invalid.

[0072] In operation 570, the navigation device (100) can select a turn guidance message to output from among the turn guidance message candidates based on the remaining distance to the turn point (e.g., turn point (350)) of the vehicle (e.g., vehicle (110)). The navigation device (100) can select the most suitable turn guidance message from among the turn guidance message candidates determined to be valid based on the remaining distance to the turn point (e.g., turn point (350)) of the vehicle (110). For example, the navigation device (100) can select the most suitable turn guidance message based on the remaining distance from the position of the vehicle (110) at the time of outputting the turn guidance message to the turn point (350) and the speed of the vehicle (110).

[0073] In operation 580, the navigation device (100) can output a rotation guidance message.

[0074] Operations 510 through 580 may be performed sequentially, but are not limited thereto. For example, two or more operations may be performed in parallel.

[0075]

[0076] FIG. 6 is a flowchart illustrating a method according to one embodiment.

[0077] Referring to FIG. 6, according to one embodiment, operations 610 to 650 may be operations performed by the navigation device (100) of FIG. 1 described with reference to FIG. 1 to FIG. 5.

[0078] According to one embodiment, operations 610 to 650 may be understood to be performed in a processor (e.g., processor (730) of FIG. 7) of a navigation device (100) (e.g., electronic device (700) of FIG. 7) described with reference to FIG. 1.

[0079] In operation 610, the navigation device (100) can acquire at least one image of a turning point included in the driving path of a vehicle (e.g., vehicle (110) of FIG. 1). The navigation device (100) can acquire at least one image of a turning point from a server (130) in response to the vehicle (110) entering a preparation section for a turning point (e.g., preparation section (320) of FIG. 3). The navigation device (100) can acquire at least one image of a turning point included in a digital map from a server (e.g., server (130) of FIG. 1).

[0080] In operation 630, the navigation device (100) can generate a prompt based on at least one image and the rotation direction of the vehicle (e.g., the vehicle (110) of FIG. 1).

[0081] In operation 650, the navigation device (100) can output a turn guidance message generated by inputting a prompt into a generative model. The navigation device (100) can store the turn guidance message generated by inputting a prompt into a generative model in a database. The navigation device (100) can obtain and output a turn guidance message from the database in response to the vehicle (110) approaching a turning point.

[0082] Operations 610 through 650 may be performed sequentially, but are not limited thereto. For example, two or more operations may be performed in parallel.

[0083]

[0084] FIG. 7 is a schematic block diagram of an electronic device according to one embodiment.

[0085] Referring to FIG. 7, according to one embodiment, an electronic device (700) (e.g., a navigation device (100) of FIG. 1) may include a memory (710) and a processor (730).

[0086] The memory (710) can store instructions (or programs) executable by the processor (730). For example, the instructions may include instructions for executing the operation of the processor (730) and / or the operation of each component of the processor (730).

[0087] The memory (710) may include one or more computer-readable storage media. The memory (710) may include non-volatile storage devices (e.g., magnetic hard disc, optical disc, floppy disc, flash memory, EPROM (electrically programmable memories), EEPROM (electrically erasable and programmable)).

[0088] The memory (710) may be a non-transitory medium. The term "non-transitory" may indicate that the storage medium is not implemented by a carrier wave or a propagated signal. However, the term "non-transitory" should not be interpreted as meaning that the memory (710) is immobile.

[0089] The processor (730) can process data stored in memory (710). The processor (730) can execute computer-readable code (e.g., software) stored in memory (710) and instructions triggered by the processor (730).

[0090] The processor (730) may be a data processing device implemented in hardware having a circuit having a physical structure for executing desired operations. For example, the desired operations may include code or instructions included in a program.

[0091] For example, a data processing device implemented in hardware may include a microprocessor, a central processing unit, a processor core, a multi-core processor, a multiprocessor, an Application-Specific Integrated Circuit (ASIC), and a Field Programmable Gate Array (FPGA).

[0092] The processor (730) can cause the electronic device (700) to perform one or more operations by executing code and / or instructions stored in memory (710). The operations performed by the electronic device (700) may be substantially the same as the operations performed by the navigation device (100) described with reference to FIGS. 1 through 7. Such redundant descriptions are omitted.

[0093]

[0094] The embodiments described above may be implemented as hardware components, software components, and / or combinations of hardware and software components. For example, the devices, methods, and components described in the embodiments may be implemented using a general-purpose computer or a special-purpose computer, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. In addition, other processing configurations, such as parallel processors, are also possible.

[0095] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or instruct the processing unit independently or collectively. Software and / or data may be stored on any type of machine, component, physical device, virtual equipment, computer storage medium, or device so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on computer-readable recording media.

[0096] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may store program instructions, data files, data structures, etc., either alone or in combination, and the program instructions recorded on the medium may be those specifically designed and configured for the embodiment or may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0097] The hardware device described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0098] Although the embodiments have been described above with reference to the limited drawings, those skilled in the art can apply various technical modifications and variations based thereon. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0099] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

1. An action of acquiring at least one image of a turn point included in the driving route of a vehicle; An operation to generate a prompt based on at least one image and the rotation direction of the vehicle; and The operation of outputting a rotation guidance message generated by inputting the above prompt into a generative model. including, method.

2. In Paragraph 1, The above at least one image is, An image taken at at least one location close to the aforementioned turning point including, method.

3. In Paragraph 1, The above at least one image is, Road view images, virtual tour images, and aerial photography including, method.

4. In Paragraph 1, The operation of generating the above prompt is, The operation of extracting features from at least one image; and Operation of generating the prompt including the above feature point and the prompt portion corresponding to the rotation direction of the vehicle including, method.

5. In Paragraph 4, The operation of outputting the above rotation guidance message is, Based on the above prompt, the operation of generating a rotation guidance message candidate corresponding to each of the at least one image; An operation to verify the validity of the rotation guidance message candidate based on map data; and Operation of selecting a turn guidance message to be output from the turn guidance message candidates based on the remaining distance to the turning point of the vehicle. including, method.

6. In Paragraph 5, The operation of validating the validity of the above rotation guidance message candidate is, Based on the above map data, an operation to verify whether the feature point is associated with the driving path according to the above rotation guidance message candidate. including, method.

7. A computer program stored on a computer-readable recording medium in combination with hardware to execute the method of any one of claims 1 through 6.

8. In the device, At least one processor; and memory that stores instructions Includes, Based on the above instructions being executed individually or collectively by the at least one processor, the device, At least one image of a turn point included in the vehicle's driving route is acquired, and Based on the above at least one image and the rotation direction of the vehicle, a prompt is generated, and Inputting the above prompt into a generative model to output a generated rotation guidance message, device.

9. In Paragraph 8, The above at least one image is, An image taken at at least one location close to the aforementioned turning point including, device.

10. In Paragraph 8, The above at least one image is, Road view images, virtual tour images, and aerial photography including, device.

11. In Paragraph 8, Based on the above instructions being executed individually or collectively by the at least one processor, the device, Extracting feature points from at least one image, and Generating the prompt including the prompt portion corresponding to the above feature point and the rotation direction of the vehicle, device.

12. In Paragraph 11, Based on the above instructions being executed individually or collectively by the at least one processor, the device, Based on the above prompt, generate rotation guidance message candidates corresponding to each of the at least one image, and Based on map data, the validity of the above rotation guidance message candidate is verified, and Selecting a turn guidance message to be output from the turn guidance message candidates based on the remaining distance to the turning point of the vehicle. device.

13. In Paragraph 12, Based on the above instructions being executed individually or collectively by the at least one processor, the device, Based on the above map data, verifying whether the feature point is associated with the driving path according to the above rotation guidance message candidate, device.

Images