Target passenger identifying and prompting method and device and vehicle

Abstract

The invention relates to the technical field of intelligent traffic, and discloses a target passenger identification and prompting method and device and a vehicle, and the method comprises the steps: obtaining the identity information of a target passenger related to the vehicle from a server, obtaining the vehicle exterior environment data collected by an environment collection device, and extracting the facial features of a pedestrian from the vehicle exterior environment data, and when the extracted facial features of all pedestrians have a target pedestrian whose facial feature is matched with the facial feature of the target passenger, determining the target pedestrian as the target passenger, calculating the position information of the target passenger, and prompting a driver of the identity information and the position information of the target passenger. A driver identifies a target passenger in an environment, automatically identifies the target passenger in an environment outside a vehicle, and prompts information of the target passenger to a user, so that the user directly identifies the passenger in the environment based on the prompted information, the workload of the driver is reduced, the time for the driver to reach the position of the passenger is shortened, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a target passenger identification and prompting method, device and vehicle. Background Art

[0002] In specific situations (such as when an online ride-hailing driver is looking for a target passenger), a vehicle may need to quickly and accurately identify the target passenger. Traditional methods of finding the target passenger mostly rely on vague location descriptions provided by the passenger and the driver's own observations. For example, a passenger tells the driver to wait at the entrance of a large shopping mall, but there is a large flow of people around the mall and the landmarks are unclear. The driver needs to identify each pedestrian one by one. This process is time-consuming and labor-intensive, and is easily affected by environmental factors. The recognition accuracy is difficult to guarantee, which not only increases the driver's workload, but may also cause passengers to wait too long, reducing the user experience. Summary of the Invention

[0003] In view of this, the present invention provides a target passenger identification and prompting method, device and vehicle to solve the problem that the methods of finding target passengers mostly rely on the vague location description provided by the passengers and the driver's own observation, which is time-consuming and labor-intensive, and is easily affected by environmental factors, and the recognition accuracy is difficult to guarantee.

[0004] In a first aspect, the present invention provides a target passenger identification and prompting method, the method comprising: obtaining identity information of a target passenger associated with a vehicle from a server; obtaining external environment data collected by an environment collection device, and extracting pedestrian features from the external environment data, the pedestrian features including at least facial features; when there is a target pedestrian whose facial features match the facial features of the target passenger among all the extracted pedestrian facial features, determining the target pedestrian as the target passenger, and calculating the location information of the target passenger; prompting the driver with the identity information and location information of the target passenger for the driver to identify the target passenger in the environment.

[0005] The target passenger identification and prompting method provided by the present invention obtains the identity information of the target passenger related to the vehicle from a server, obtains the vehicle's external environment data collected by the environment collection device, and extracts the facial features of the pedestrian from the vehicle's external environment data. When there is a target pedestrian whose facial features match the facial features of the target passenger among all the extracted pedestrian facial features, the target pedestrian is determined as the target passenger, and the target passenger's position information is calculated. The driver is prompted with the target passenger's identity information and position information, which is used for the driver to identify the target passenger in the environment, realizes automatic identification of the target passenger in the vehicle's external environment, and prompts the user with the target passenger's information so that the user can directly identify the passenger in the environment based on the prompted information, thereby reducing the driver's workload, shortening the time it takes for the driver to reach the passenger's position, and improving the user experience.

[0006] In an optional embodiment, the following steps are used to determine whether there is a target pedestrian among all pedestrians whose facial features match the facial features of the target passenger: calculating the similarity between the facial features of all pedestrians and the facial features of the target passenger; and determining as the target pedestrian a pedestrian whose facial features have a similarity with the facial features of the target passenger that is greater than a preset similarity threshold.

[0007] The present invention identifies multiple pedestrians with similarities greater than a preset similarity threshold as target pedestrians. The driver can accurately identify the target passenger based on other non-facial features, preventing the automatic facial feature recognition from being incorrectly affected by other factors, which would affect the driver's efficiency in picking up passengers.

[0008] In an optional embodiment, the identity information also includes identity authentication information. The server stores a database of identity information corresponding to all passengers whose information has been entered. The identity authentication information corresponds one-to-one to facial features. The target pedestrian is determined as the target passenger, including: based on the facial features of the target pedestrian, filtering out the corresponding first identity authentication information from the database stored in the server; comparing the first identity authentication information with the identity authentication information of the target passenger; if the first identity authentication information is successfully compared with the identity authentication information of the target passenger, the target pedestrian is determined as the target passenger.

[0009] After identifying the target pedestrian based on facial features, the present invention also needs to compare the identity verification information bound to the facial features in the database with the identity verification information of the target passenger. Only after the comparison is successful, the target pedestrian is determined as the target passenger to ensure that the target passenger is identified accurately.

[0010] In an optional embodiment, the identity information also includes a target pick-up point, and the method further includes: if there is no target pedestrian among all the extracted facial features of the pedestrians whose facial features match the facial features of the target passenger, or the comparison between the first identity authentication information and the identity authentication information of the target passenger fails, then outputting to the driver information indicating that there is currently no target passenger, or, if the calculated relative distance between the current location of the target passenger and the target pick-up point is greater than a preset distance threshold, then outputting to the driver information indicating that the target passenger has deviated from the target pick-up point, and providing a communication interaction portal for contacting the target passenger on the vehicle screen.

[0011] The present invention is designed with a warning system. Aiming at emergency situations, a sound and display warning system is designed to arouse the driver's high alertness and ensure that the driver takes action quickly and safely.

[0012] In an optional embodiment, the environment collection device includes an external camera, and the external environment video collected by the external camera is displayed on the vehicle screen. The prompting of the driver's target passenger's identity information and location information includes: displaying the target passenger's identity information and location information on the vehicle screen, and / or broadcasting voice prompt information, and the voice prompt information is used to prompt the driver of the target passenger's location information.

[0013] The present invention realizes clear and definite information display and voice prompts, so that the driver can quickly locate the target passenger, reduce the time of searching for the passenger, and improve the recording efficiency of the vehicle.

[0014] In an optional embodiment, displaying the identity information and location information of the target passenger on the vehicle screen includes: classifying the identity information and location information of the target passenger according to a preset hierarchical display rule; displaying the classified identity information and location information of the target passenger on the vehicle screen according to the preset hierarchical display rule, wherein the preset hierarchical display rule includes at least: continuously displaying the identity information and location information corresponding to the first level on the vehicle screen, and in response to the user performing a second level viewing operation, displaying the identity information and location information corresponding to the second level on the vehicle screen, the second level is initially in a hidden state, and the importance of the first level is greater than the importance of the second level.

[0015] The embodiment of the present invention can display the identity information and location information of the target passenger in a hierarchical structure, ensuring that the driver can quickly understand and take corresponding actions.

[0016] In an optional embodiment, displaying the identity information and location information of the target passenger on the vehicle screen also includes: using a direction indicator to prompt the driver of the direction of the target passenger relative to the vehicle in the interface displayed on the vehicle screen, and / or marking the target passenger with a preset marking style in the interface displayed on the vehicle screen.

[0017] The present invention uses graphics and symbols to convey information, and can intuitively and efficiently prompt the driver the location of the target passenger.

[0018] In an optional embodiment, the displaying of the target passenger's identity information and location information on the on-board screen further includes: performing 3D rendering processing on the target passenger in the interface displayed on the on-board screen, and floatingly displaying the target passenger's identity information and location information, wherein the 3D rendering processing on the target passenger includes: when the relative distance between the target passenger and the vehicle is greater than a preset distance threshold, displaying a transparent marking box for the target passenger on the on-board screen; when the relative distance between the target passenger and the vehicle is not greater than the preset distance threshold, displaying a 3D avatar of the target passenger on the on-board screen.

[0019] The present invention displays the target passenger in a 3D rendering manner, which enables the driver to obtain relevant information more clearly and intuitively, allowing the driver to quickly capture key information during driving and reducing the time for information search and identification.

[0020] In a second aspect, the present invention provides a target passenger identification and prompting device, which includes: an identity information acquisition module for acquiring the identity information of a target passenger related to a vehicle from a server; a feature extraction module for acquiring the external environment data collected by an environment collection device, and extracting pedestrian features from the external environment data, wherein the pedestrian features include at least facial features; a feature matching module for determining the target pedestrian as a target passenger and calculating the target passenger's location information when there is a target pedestrian whose facial features match the facial features of the target passenger among all the extracted pedestrian facial features; a passenger prompting module for prompting the driver of the target passenger's identity information and location information, so that the driver can identify the target passenger in the environment.

[0021] In a third aspect, the present invention provides a vehicle, comprising a controller, the controller comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the target passenger identification and prompting method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0022] The target passenger identification and prompting method provided by the present invention obtains the identity information of the target passenger related to the vehicle from a server, obtains the vehicle's external environment data collected by the environment collection device, and extracts the facial features of the pedestrian from the vehicle's external environment data. When there is a target pedestrian whose facial features match the facial features of the target passenger among all the extracted pedestrian facial features, the target pedestrian is determined as the target passenger, and the target passenger's position information is calculated. The driver is prompted with the target passenger's identity information and position information, which is used for the driver to identify the target passenger in the environment, realizes automatic identification of the target passenger in the vehicle's external environment, and prompts the user with the target passenger's information so that the user can directly identify the passenger in the environment based on the prompted information, thereby reducing the driver's workload, shortening the time it takes for the driver to reach the passenger's position, and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 is a flow chart of a target passenger identification and prompting method according to an embodiment of the present invention;

[0025] Figure 2 is a flowchart illustrating a target passenger identification and prompting method according to an embodiment of the present invention;

[0026] Figure 3 is a flow chart of another target passenger identification and prompting method according to an embodiment of the present invention;

[0027] Figure 4 is an example diagram of an in-vehicle screen display according to an embodiment of the present invention;

[0028] Figure 5 is a structural block diagram of a vehicle according to an embodiment of the present invention;

[0029] Figure 6 is a structural block diagram of a target passenger identification and prompting device according to an embodiment of the present invention;

[0030] Figure 7 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0032] According to an embodiment of the present invention, an embodiment of a target passenger identification and prompting method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0033] In this embodiment, a target passenger identification and prompting method is provided, which is applied to a controller in a vehicle. Figure 1 is a flow chart of a target passenger identification and prompting method according to an embodiment of the present invention, wherein all identity information of passengers or pedestrians is operated only after authorization by the corresponding passengers or pedestrians, such as Figure 1 As shown, the process includes the following steps:

[0034] Step S101: Acquire the identity information of the target passenger associated with the vehicle from the server.

[0035] The target passenger pre-enters the target passenger's identity information through the server (such as the online car-hailing platform). The identity information includes but is not limited to facial images (facial features) and identity verification information. Specifically, when the user registers on the server, he can upload a clear facial photo and fill in personal identity verification information (including but not limited to name, mobile phone number, account ID, email address, etc.). The online car-hailing platform will pre-process the uploaded facial features, such as denoising, standardization, and light correction, to improve the accuracy of subsequent recognition, and will verify and authorize the entered information (the user's identity information will only be used after authorization by the user) to ensure the accuracy and security of the information. Usually, when the facial image and identity verification information are entered, they are bound together. When storing, the online car-hailing platform can associate the facial image with the user's identity verification information one by one, and store it in a secure database to ensure that each user's identity is unique and verifiable, so that the vehicle controller can obtain the identity information for subsequent identification.

[0036] Step S102 : acquiring the vehicle exterior environment data collected by the environment collection device, and extracting pedestrian features from the vehicle exterior environment data.

[0037] Wherein, the pedestrian features at least include facial features.

[0038] The embodiments of the present invention do not limit the environmental collection device, which can capture the surrounding environmental information outside the vehicle. For example, a high-resolution camera installed outside the vehicle can collect environmental information around the vehicle in real time through video streams, especially for visual data collection of pedestrians. It can also include devices such as lidar and infrared sensors to obtain more information about pedestrians, such as depth (describing the spatial position, posture and relationship of the pedestrian's surrounding environment, etc.), heat (describing the probability distribution of the appearance of pedestrians in images or video streams), etc. Among them, the pedestrian information is only used after authorization by the pedestrian to ensure the legitimacy and security of the information.

[0039] like Figure 2As shown, the embodiment of the present invention can pre-process the video captured by the camera, including denoising, image enhancement and other processing to optimize the subsequent analysis process, and can use image processing technology (such as Histogram of Oriented Gradients (HOG), target detection algorithm (You Only Look Once, YOLO), etc.) to extract and analyze the features of pedestrians (including the steps of pedestrian detection and positioning, feature extraction and feature analysis and recognition). Pedestrian features may include but are not limited to facial features (usually key points of the face (such as eyes, nose bridge, mouth, etc.) or generated facial feature vectors, which are digital representations of each person's facial features, are unique, and can effectively distinguish different individuals), body posture and walking patterns, etc., to ensure high-accuracy target passenger identification, wherein the extraction and analysis of pedestrian features is only performed after the pedestrian's authorization.

[0040] Step S103 : When there is a target pedestrian whose facial features match the facial features of the target passenger among all the extracted facial features of the pedestrians, the target pedestrian is determined as the target passenger, and the position information of the target passenger is calculated.

[0041] like Figure 2 As shown, the embodiment of the present invention can use a face recognition algorithm to match the facial features of all extracted pedestrians with the facial features of a target passenger. When there is a target pedestrian whose facial features match the facial features of a target passenger among all extracted facial features of pedestrians, the target pedestrian can be determined as the target passenger. The target detection algorithm can be used to detect the position of the target passenger in each frame of the video image, and then the same target passenger in different frames can be associated to obtain the real-time position information of the target passenger. The distance between the vehicle and the target passenger, i.e., the position information, can also be measured by infrared sensors, ultrasonic sensors and other devices, for example only.

[0042] In an optional embodiment, if the target passenger has not entered his or her identity information into the passenger management platform, the image captured by the camera can still be analyzed, and a pedestrian recognition algorithm can be used to identify pedestrian characteristics (including clothing, body shape, posture, behavior, and location, etc.). The target passenger can be confirmed based on the pedestrian characteristics, and potential passengers can also be inferred based on time, location, and other conditions within the target area. For example, when an order is received, the target passenger nearby can be inferred based on the passenger's location as a means of auxiliary judgment.

[0043] Step S104 , prompting the driver with the identity information and location information of the target passenger, so as to enable the driver to identify the target passenger in the environment.

[0044] After the embodiment of the present invention identifies the target passenger, the identity information and location information of the target passenger can be prompted to the driver in the form of voice, so that the driver can identify the target passenger in the environment based on the prompted information.

[0045] The target passenger identification and prompting method provided by the present invention obtains the identity information of the target passenger related to the vehicle from a server, obtains the vehicle's external environment data collected by the environment collection device, and extracts the facial features of the pedestrian from the vehicle's external environment data. When there is a target pedestrian whose facial features match the facial features of the target passenger among all the extracted pedestrian facial features, the target pedestrian is determined as the target passenger, and the target passenger's position information is calculated. The driver is prompted with the target passenger's identity information and position information, which is used for the driver to identify the target passenger in the environment, realizes automatic identification of the target passenger in the vehicle's external environment, and prompts the user with the target passenger's information so that the user can directly identify the passenger in the environment based on the prompted information, thereby reducing the driver's workload, shortening the time it takes for the driver to reach the passenger's position, and improving the user experience.

[0046] In this embodiment, a target passenger identification and prompting method is provided, which is applied to the controller of the vehicle. Figure 3 FIG. 1 is a flow chart of a target passenger identification and prompting method according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0047] Step S301: Obtain the identity information of the target passenger related to the vehicle from the server. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0048] Step S302: Obtain the vehicle exterior environment data collected by the environment collection device, and extract pedestrian features from the vehicle exterior environment data. Pedestrian features include at least facial features. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0049] Step S303 : When there is a target pedestrian whose facial features match the facial features of the target passenger among all the extracted facial features of the pedestrians, the target pedestrian is determined as the target passenger, and the position information of the target passenger is calculated.

[0050] Specifically, the above step S303 includes:

[0051] Step S3031 , calculating the similarity between the facial features of all pedestrians and the facial features of the target passenger.

[0052] Step S3032: A pedestrian whose facial features have a similarity with the facial features of the target passenger greater than a preset similarity threshold is determined as a target pedestrian.

[0053] The embodiment of the present invention may adopt a similarity calculation method (such as cosine similarity, Euclidean distance, etc.) to evaluate the similarity between the facial features of all pedestrians and the facial features of the target passenger, and then the pedestrians corresponding to the similarity greater than the preset similarity threshold may be used as the target pedestrians, wherein the preset similarity threshold may be set according to the actual scenario, and the setting of the similarity threshold may be appropriately lowered. Multiple pedestrians with similarities greater than the preset similarity threshold may be determined as target pedestrians. The driver may accurately identify the target passenger based on other non-facial features to prevent the automatic facial feature recognition from being incorrectly affected by other factors, thereby affecting the efficiency of the driver in picking up passengers.

[0054] Furthermore, the identity information also includes identity verification information. The server stores a database of identity information corresponding to all passengers whose information has been entered. The identity verification information corresponds one-to-one to facial features. Based on the facial features of the target pedestrian, the corresponding first identity verification information is filtered out from the database stored in the server; the first identity verification information is compared with the identity verification information of the target passenger; if the first identity verification information is successfully compared with the identity verification information of the target passenger, the target pedestrian is determined as the target passenger.

[0055] The server of an embodiment of the present invention stores a database of identity information corresponding to all passengers whose information has been entered, wherein the identity information corresponding to all passengers whose information has been entered will only be subsequently operated after the passenger authorizes it. After successfully matching the target pedestrian based on facial features, the first identity authentication information (including name, mobile phone number, etc.) bound to the facial features of the target pedestrian can also be called from the database stored in the server, and then the first identity authentication information is compared with the identity authentication information of the target passenger to determine whether the identity authentication information is consistent. If the identity authentication information is consistent, the target pedestrian is determined as the target passenger. If it is inconsistent, the driver can be provided with an entrance for communicating and interacting with the target passenger, so that the driver can confirm the identity authentication information of the target passenger or confirm the specific location and passenger characteristics (such as clothing color, etc.), and re-identify the target passenger in the image.

[0056] After identifying the target pedestrian based on facial features, the present invention also needs to compare the identity verification information bound to the facial features in the database with the identity verification information of the target passenger. Only after the comparison is successful, the target pedestrian is determined as the target passenger to ensure that the target passenger is identified accurately.

[0057] Step S304: prompt the driver with the target passenger's identity information and location information, so that the driver can identify the target passenger in the environment. Detailed descriptions can be found in the above embodiment, which will not be repeated here.

[0058] In an optional embodiment, if the facial features of all extracted pedestrians do not contain a target pedestrian whose facial features match the facial features of the target passenger, or the comparison between the first identity authentication information and the identity authentication information of the target passenger fails, information indicating that there is currently no target passenger is output to the driver, or, if the calculated relative distance between the current location of the target passenger and the target pick-up point is greater than a preset distance threshold, information indicating that the target passenger has deviated from the target pick-up point is output to the driver, and a communication interaction portal for contacting the target passenger is provided on the vehicle screen.

[0059] The identity information also includes the target pick-up point.

[0060] In an embodiment of the present invention, after comparing the facial features of all pedestrians with the facial features of the target passenger, if the target pedestrian cannot be identified from all pedestrians (the reason may be that the camera fails to clearly capture the facial image of the pedestrian (for example, due to poor lighting, obstruction, the pedestrian is far away, etc.), a corresponding prompt may be given indicating that the pedestrian's face cannot be recognized, or multiple pedestrians are in the same location, or direct facial feature comparison fails), or the target passenger cannot be confirmed for a long time or the identity verification information of the target passenger cannot be accurately confirmed for a long time, a corresponding prompt may be given indicating that "the identity of the target passenger cannot be confirmed, please operate manually", or the first identity verification information fails to be compared with the identity verification information of the target passenger, then information indicating that there is no target passenger at present may be output to the driver, such as a voice prompt to the driver indicating that "no matching passenger was found, please check whether you are in the correct location". , and visual reminders can also be given, such as displaying a red or flashing warning icon in the vehicle interface, or popping up a manual matching option on the interface, allowing the driver to enter passenger characteristics (such as clothing color) for assisted exploration; if the target passenger is identified, but the calculated relative distance between the target passenger's current location and the pre-entered target pick-up point is greater than the preset distance threshold, a sound alarm "target passenger position deviation, no pick-up point found" can be given, or the distance between the passenger location and the target pick-up point location can be displayed on the map of the vehicle interface and marked with a red error icon, and a communication interaction entrance for contacting the target passenger can be provided on the vehicle interface, such as a convenient button, communication link, and other methods that can directly establish communication with the target passenger to ensure the safety and accuracy of the driver's pick-up process, just as an example.

[0061] Furthermore, the scenarios in which the alarm system is triggered in the embodiments of the present invention also include the target passenger being a pedestrian or in an abnormal state, which may affect the safety of the vehicle. The motion trajectory and real-time dynamic location information of the target passenger can be calculated based on the video stream captured by the camera. When it is detected that the target passenger disappears at the target pick-up point or the surrounding area, it may cause the pick-up task to fail or the route needs to be replanned, or the target passenger is detected to enter a road with heavy traffic or a dangerous area, and the driver needs to be alerted. A sound warning can be given (for example, "The target pedestrian has left the pick-up area, please reconfirm the target pick-up point"). If necessary, emergency processing prompts can be provided, such as contacting emergency services, seeking help, etc., and visual prompts can also be given, as an example only; if a problem is detected in the camera, sensor or computing module, resulting in the inability to collect images or data, or an error occurs during the platform operation and the face recognition algorithm or location monitoring function cannot be started, an alarm operation can also be performed, such as a sound warning ("System abnormality, please check the sensor or restart the system") or a visual prompt, as an example only.

[0062] The present invention is designed with a warning system. Aiming at emergency situations, a sound and display warning system is designed to arouse the driver's high alertness and ensure that the driver takes action quickly and safely.

[0063] In an optional embodiment, the environment collection device includes an external camera, and the external environment video collected by the external camera is displayed on the vehicle screen to prompt the driver of the target passenger's identity information and location information, including: displaying the target passenger's identity information and location information on the vehicle screen, and / or broadcasting voice prompt information, and the voice prompt information is used to prompt the driver of the target passenger's location information.

[0064] An embodiment of the present invention can design a clear and intuitive display screen in the vehicle cockpit to display the identity information and location information of the target passenger, which may include a map interface, pedestrian photos or images, distance indications, and navigation indicator light information. Different information can be displayed using corresponding icons or visual elements, such as using a phone icon to indicate contacting the passenger, and using a location identification icon to display the location of the target passenger. Real-time changing information (such as the location of the target passenger) can be dynamically presented through gradient animation, progress bar or jumping effect, so that it does not appear static and rigid visually. A voice prompt system can also be integrated to provide real-time voice information, such as "Target passenger found, please pay attention to the left", etc., to prompt the driver of the target passenger's location information, so as to improve the usability of the platform, especially in situations where the driver needs to concentrate.

[0065] The present invention realizes clear and definite information display and voice prompts, so that the driver can quickly locate the target passenger, reduce the time of searching for the passenger, and improve the recording efficiency of the vehicle.

[0066] In an optional embodiment, the identity information and location information of the target passenger are displayed on the vehicle screen, including: classifying the identity information and location information of the target passenger according to a preset hierarchical display rule; displaying the classified identity information and location information of the target passenger on the vehicle screen according to the preset hierarchical display rule, wherein the preset hierarchical display rule includes at least: continuously displaying the identity information and location information corresponding to the first level on the vehicle screen, and in response to the user performing a second level viewing operation, displaying the identity information and location information corresponding to the second level on the vehicle screen, the second level is initially in a hidden state, and the importance of the first level is greater than the importance of the second level.

[0067] The embodiment of the present invention does not limit the setting of hierarchical display rules, and multiple levels can be set. Different levels have different importance. The display form corresponding to information at different levels is not limited and can be set according to actual needs. Specifically, three levels can be set. The first level is the most important level, which is used to display the core identity information and location information of the target passenger. For example, the target passenger's portrait can be displayed frequently, and it can be marked whether the feature has been matched, the location information of the target passenger (such as 5 meters ahead), and the order status (waiting to get on the bus / on the bus / matching failed). The information displayed at the first level can be displayed in the center of the interface or in a prominent position. The second level is the secondary information level, which can display auxiliary information related to the target passenger, including but not limited to the target passenger's name, contact information, pick-up location, etc. Among them, the second level The first level of information can be displayed by folding or expanding. It is initially hidden. When the user wants to view the second level of information, he can click to expand it; the third level is auxiliary information, which is only viewed when necessary to avoid excessive interference with the driver's attention. It can display secondary information or operations related to the target passenger, such as the passenger's historical orders (which can be used to determine whether he is a frequent passenger), the target passenger's preferences (whether special care is required, the temperature in the car or the preference for music), buttons and functions related to the target passenger (such as confirming identity, viewing order details), etc., just as an example; then, the target passenger's identity information and location information can be classified into corresponding levels according to the preset hierarchical display rules, and the classified target passenger's identity information and location information can be displayed on the in-vehicle screen in the corresponding display format.

[0068] Furthermore, different levels can be distinguished by size, font, color, etc. For example, the first level can be highlighted using larger font size, bold, etc. to ensure that the driver can get the most critical information at first glance. The display fonts of subsequent levels can be relatively small, or gray fonts can be used to avoid interfering with the visual focus of the main information; high-contrast colors can be used to display the information of the first level, and low-saturation colors can be used to display the subsequent levels to reduce the visual burden.

[0069] Furthermore, information displayed at different levels should avoid overlap, with appropriate white space between them to avoid visual crowding. A card-like design can also be used to separate information from operational buttons. For example, passenger information could be displayed in one card area, while operational buttons could be placed in another, visually distinguishing them. Users can also expand or collapse information on demand through clicks or swipe gestures, ensuring that the most important information is always visible while avoiding the interface complexity caused by displaying too much information at once. Important information at the first level can be further reinforced through voice prompts and dynamic visual feedback. By designing the information hierarchy, the hierarchical display ensures that drivers can efficiently and quickly access critical and relevant information through reasonable classification, information prioritization, visual hierarchy design (such as fonts, colors, and layout), and interactive design (such as folding and dynamic feedback). This hierarchical design not only improves the user experience but also enhances the convenience and safety of system operation, avoids information overload, and ensures that drivers can make quick decisions in stressful driving environments.

[0070] The embodiment of the present invention can display the identity information and location information of the target passenger in a hierarchical structure, ensuring that the driver can quickly understand and take corresponding actions.

[0071] In an optional embodiment, displaying the identity information and location information of the target passenger on the vehicle screen also includes: using a direction indicator to prompt the driver of the direction of the target passenger relative to the vehicle in the interface displayed on the vehicle screen, and / or marking the target passenger with a preset marking style in the interface displayed on the vehicle screen.

[0072] The present invention can use graphics and symbols to convey information, such as Figure 4 As shown, a direction indicator (such as an arrow) can be used to prompt the driver of the direction of the target passenger relative to the vehicle, or the target passenger can be marked using a preset marking style, such as marking the target passenger's position on a map, as an example only.

[0073] The present invention uses graphics and symbols to convey information, and can intuitively and efficiently prompt the driver the location of the target passenger.

[0074] In an optional embodiment, displaying the identity information and location information of the target passenger on the on-board screen also includes: performing 3D rendering processing on the target passenger in the interface displayed on the on-board screen, and floatingly displaying the identity information and location information of the target passenger, wherein the 3D rendering processing of the target passenger includes: when the relative distance between the target passenger and the vehicle is greater than a preset distance threshold, displaying a transparent marking box for the target passenger on the on-board screen; when the relative distance between the target passenger and the vehicle is not greater than the preset distance threshold, displaying a 3D avatar of the target passenger on the on-board screen.

[0075] In embodiments of the present invention, after extracting the target passenger's position and posture information from a two-dimensional image, the information is converted into a three-dimensional coordinate system around the vehicle based on the calibration of the vehicle's sensors and the acquisition of depth information. Three-dimensional reconstruction techniques in computer graphics (such as stereo matching and triangulation) are then used to reconstruct the target passenger's actual position around the vehicle based on the three-dimensional information surrounding the vehicle, including the camera's field of view and environmental depth information. After the target passenger is determined in three dimensions, 3D rendering can be performed on the target passenger. The 3D rendering process can include selecting a specific color (such as red) to highlight the target passenger, making them more conspicuous in the vehicle's surroundings, and displaying the target passenger's key identity and location information above their head. As the environmental acquisition device acquires and processes information, the rendered position and status of the target passenger can be continuously updated and adjusted to reflect their real-time position and dynamic changes. For example, when the target passenger's distance from the vehicle exceeds a preset distance threshold, a transparent red frame can be displayed on the vehicle's screen to indicate their approximate location. As the target passenger approaches the vehicle, the rendering mode can be switched to a high-definition 3D avatar to enhance recognition, allowing the driver to more intuitively observe the target passenger's position, posture, and movement.

[0076] Specifically, embodiments of the present invention can use multiple sensors such as vehicle-mounted cameras, lidar, and millimeter-wave radar, combined with computer vision and deep learning technologies, to reconstruct pedestrians in three-dimensional space. This includes: using cameras to capture two-dimensional image information of the external environment and the depth information of pedestrians; using lidar to generate high-precision three-dimensional point cloud data to obtain the spatial position of the pedestrian's surrounding environment; using millimeter-wave radar to assist in detecting the pedestrian's movement direction and speed to improve tracking accuracy; and then using a multi-sensor fusion algorithm to fuse the above-obtained data to form a complete three-dimensional environmental model. For pedestrians, a convolutional neural network can be used to identify pedestrians and select their bounding boxes. Key point detection algorithms such as the High-Resolution Network (HRNet) and the Open-source Real-time Multi-person Key point and Pose Detection Program (OpenPose) are then used to obtain the pedestrian's key point information to improve the 3D reconstruction accuracy. The pedestrian's depth can then be calculated using a binocular stereo vision algorithm (i.e., camera baseline distance, camera focal length, and parallax between left and right cameras). Light Detection and Ranging (LDR) can also be used to calculate the pedestrian's depth. The three-dimensional coordinates of pedestrians can be directly obtained from the point cloud data of LiDAR (LiDAR), or the ranging information can be converted into a rectangular coordinate system through millimeter-wave radar. Kalman filtering and fusion flow tracking algorithm are then used to optimize the three-dimensional coordinates of pedestrians, eliminate noise, and improve accuracy.

[0077] Specifically, after the pedestrian's three-dimensional coordinates are determined, the pedestrian's key point information can be used to construct a simple skeleton model. A 3D network is generated based on the skeleton structure to fit the pedestrian's outline. The pedestrian is rendered in red with highlights to enhance the visualization effect. Finally, the optical flow tracking and target tracking algorithms are combined to ensure that the rendering position is updated as the pedestrian moves. Ultimately, the reconstructed 3D pedestrian information will be displayed on the vehicle's screen (such as the in-car display or head-up display). Non-target passengers can be displayed with a transparent white outline, and target passengers are marked with red 3D rendering, and additional identity information and location information such as name and avatar are displayed in a floating manner.

[0078] Furthermore, an embodiment of the present invention designs interactive buttons on the vehicle screen to provide a convenient user experience through simple touch or button operation. For some of the most commonly used and frequently operated buttons (such as viewing target passenger information, confirming identity, contacting passengers, etc.), they can always appear on the interface in a permanent display manner and can be located at the bottom or sidebar of the interface to ensure that the driver can quickly click without affecting driving operations; for functions with less frequent operation (such as viewing history, settings, feedback, etc.), the corresponding buttons can be hidden through a side menu, drop-down menu or setting button. For example, the driver can click the "More" or "Settings" button in the lower right corner of the screen to pop up relevant operation options. For example, in an optional embodiment, the function of the button can be set according to the driver's operating needs. Specifically, on the main screen (the initial interface after target passenger identification), (The screen appears to be unrelated and should be omitted as it may be an error.) Includes: Target pedestrian information button (always displayed), function: click to display the target pedestrian's basic identity information, such as name, avatar, destination, distance, pick-up point, etc., location: usually located in the center or right side of the bottom of the screen, and the icon is designed as a "human icon" or "avatar" icon, which makes it convenient for the driver to quickly view passenger information; Confirm identity button (always displayed), function: click to confirm whether the identity of the target pedestrian matches. After the system confirms the pedestrian's identity through facial recognition or other verification information, the system will automatically display an "identity confirmation successful" prompt, or trigger subsequent operations (such as navigating to the pick-up point), location: this button should be close to the target pedestrian information button, designed as an obvious "confirm" button, using a green check icon or the text "confirm identity"; Contact passenger button (always displayed), function: click to directly call the passenger or initiate a text message / voice message (if the passenger information has been entered). This function can reduce the time the driver spends manually entering the phone number, location: usually located in the operation bar in the lower right corner or at the bottom of the interface, and the icon is a phone icon or a message icon.

[0079] In an optional embodiment, in the detailed information expansion interface, when the driver clicks the target pedestrian information button, the platform will enter the detailed information interface. In addition to displaying the target pedestrian's detailed information, this interface may also include the following function buttons: View Trip and Order button (visible), Function: Click to view the passenger's detailed trip information, such as past orders, scheduled times, and starting and ending locations. This function allows the driver to confirm whether they are the correct passenger. Location: This button can be located at the top of the screen or displayed as a card below the target pedestrian information, with the icon designed as a "File" or "Order" icon; Chat with Passenger button (hide / expand), Function: This button allows the driver to communicate with the passenger in real-time (for example, the passenger can communicate with the driver about the pick-up location). To ensure that it does not affect driving safety, this function should be hidden by default and expanded by clicking the "More" or "Chat" button. Location: In the information expansion interface, located in the lower middle part of the screen, designed as a chat bubble icon; View Passenger Rating button (visible), Function: Click to display the passenger's rating and comments. This function can help the driver understand the passenger's credibility and decide whether to continue driving. Position: Generally set as part of the information bar, or displayed in the form of a star rating below the target pedestrian information.

[0080] In the dynamic status interface after the information is confirmed, when the identity of the target pedestrian is confirmed, the system enters the dynamic status interface and displays the real-time location and pick-up information: Real-time location update button (always displayed), function: after clicking, the driver can view the real-time location of the target pedestrian or passenger, helping the driver to make accurate decisions and avoid picking up or missing passengers, location: always displayed in the center of the interface, the icon can be a "positioning" icon or a real-time updated progress bar; Guide passengers to the pick-up point button (always displayed), function: after clicking, the vehicle's navigation system will automatically plan the route to help guide the driver to the pick-up point of the target pedestrian, providing real-time navigation and road conditions information, location: usually located at the bottom of the screen, the icon is a "navigation" or "path" icon.

[0081] During the driver's operation, the platform may also need to provide feedback or warnings corresponding to the operation feedback and abnormal prompt functions: Abnormal warning button (constant display / flashing), function: when the system detects an abnormality in the target pedestrian recognition (such as face mismatch, unclear passenger position, etc.), the button will flash or change color to remind the driver to confirm or take action. After clicking, the system will display detailed error information or recommended solutions. Location: usually located at the top or upper right corner of the screen, the icon is designed as "warning" or "exclamation mark"; Cancel task button (hidden), function: when a problem occurs or the passenger cannot be recognized, the driver can click this Button to cancel the current order task and re-acquire other tasks. Location: Hide the button and place it in the sidebar or "More" menu; Considering the safety of interactive design, voice assistance and automation: In order to avoid distracting the driver when operating buttons, the driver can be assisted by voice assistant or voice feedback to reduce manual operation, for example, "The system has identified the target passenger Zhang San, the distance is X kilometers, do you confirm the passenger's identity?"; Anti-accidental touch design: All important buttons (such as confirm identity, contact passengers, etc.) should be avoided from accidental touch to ensure that the driver can obtain visual confirmation and feedback during operation and avoid accidental operation.

[0082] When designing interactive buttons, the present invention first considers the functionality and priority of the buttons, and always displays frequently used buttons to ensure that the driver can complete tasks quickly. Secondly, different functions are set according to different interactive nodes to adapt to the driver's operational needs. From displaying target pedestrian information, identity confirmation to contacting passengers, the layout of buttons should take safety into consideration to avoid information overload. At the same time, clear visual design and voice prompts are used to help drivers make more accurate decisions.

[0083] In this embodiment, a vehicle is also provided. Figure 5 As shown, the vehicle includes an environment acquisition device and a controller. The controller includes a memory and a processor. The memory and the processor are communicatively connected to each other. The memory stores computer instructions. The processor executes the target passenger identification and prompting method described in the above embodiment by executing the computer instructions, which will not be repeated here.

[0084] This embodiment also provides a target passenger identification and notification device for implementing the aforementioned embodiments and preferred implementations. Details already described will not be repeated. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. While the devices described in the following embodiments are preferably implemented using software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0085] This embodiment provides a target passenger identification and prompting device, such as Figure 6As shown, it includes: an identity information acquisition module 601, which is used to obtain the identity information of the target passenger related to the vehicle from the server; a feature extraction module 602, which is used to obtain the external environment data collected by the environment collection device, and extract pedestrian features from the external environment data, and the pedestrian features at least include facial features; a feature matching module 603, which is used to determine the target pedestrian as the target passenger when there is a target pedestrian whose facial features match the facial features of the target passenger among all the extracted pedestrian facial features, and calculate the location information of the target passenger; a passenger prompting module 604, which is used to prompt the driver with the identity information and location information of the target passenger, so that the driver can identify the target passenger in the environment.

[0086] In some optional embodiments, the following steps determine whether there is a target pedestrian among all pedestrians whose facial features match the facial features of the target passenger: calculate the similarity between the facial features of all pedestrians and the facial features of the target passenger; and determine as the target pedestrian a pedestrian whose facial features have a similarity with the facial features of the target passenger that is greater than a preset similarity threshold.

[0087] In some optional embodiments, the identity information also includes identity authentication information. The server stores a database of identity information corresponding to all passengers whose information has been entered. The identity authentication information corresponds one-to-one to facial features. The feature matching module 603 includes: an information screening unit, which is used to screen out the corresponding first identity authentication information from the database stored in the server based on the facial features of the target pedestrian; an information comparison unit, which is used to compare the first identity authentication information with the identity authentication information of the target passenger; and a target passenger determination unit, which is used to determine the target pedestrian as the target passenger if the first identity authentication information is successfully compared with the identity authentication information of the target passenger.

[0088] In some optional embodiments, the identity information also includes a target pick-up point, and the device also includes: a first information prompt module for outputting information indicating that there is no target passenger to the driver if no target pedestrian whose facial features match the facial features of the target passenger among all the extracted facial features of the pedestrians, or if the comparison between the first identity verification information and the identity verification information of the target passenger fails; or a second information prompt module for outputting information indicating that the target passenger has deviated from the target pick-up point to the driver if the calculated relative distance between the current location of the target passenger and the target pick-up point is greater than a preset distance threshold, and providing a communication interaction portal on the vehicle screen for contacting the target passenger.

[0089] In some optional embodiments, the environment collection device includes an external camera, and the vehicle-mounted screen displays the external environment video collected by the external camera. The passenger prompt module 604 includes: a display prompt unit for displaying the identity information and location information of the target passenger on the vehicle-mounted screen, and / or a voice prompt unit for broadcasting voice prompt information, and the voice prompt information is used to prompt the driver of the location information of the target passenger.

[0090] In some optional embodiments, the display prompt unit includes: a hierarchical classification subunit, used to classify the identity information and location information of the target passenger according to a preset hierarchical display rule; a hierarchical display subunit, used to display the classified identity information and location information of the target passenger on the vehicle screen according to the preset hierarchical display rule, wherein the preset hierarchical display rule includes at least: continuously displaying the identity information and location information corresponding to the first level on the vehicle screen, and in response to the user performing a second-level viewing operation, displaying the identity information and location information corresponding to the second level on the vehicle screen, the second level is initially in a hidden state, and the importance of the first level is greater than the importance of the second level.

[0091] In some optional embodiments, the display prompt unit also includes: a marking prompt subunit, which is used to use a direction indicator to prompt the driver of the direction of the target passenger relative to the vehicle in the interface displayed on the vehicle screen, and / or a passenger marking subunit, which is used to mark the target passenger with a preset marking style in the interface displayed on the vehicle screen.

[0092] In some optional embodiments, the display prompt unit also includes: a 3D rendering subunit, which is used to perform 3D rendering processing on the target passenger in the interface displayed on the vehicle screen, and to suspend and display the identity information and location information of the target passenger, wherein the 3D rendering processing of the target passenger includes: when the relative distance between the target passenger and the vehicle is greater than a preset distance threshold, a transparent marking box for the target passenger is displayed on the vehicle screen; when the relative distance between the target passenger and the vehicle is not greater than the preset distance threshold, a 3D avatar of the target passenger is displayed on the vehicle screen.

[0093] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0094] The target passenger identification and prompting device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0095] The embodiment of the present invention also provides a computer device having the above Figure 6 The target passenger identification and prompting device shown.

[0096] See also Figure 7 , Figure 7 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0097] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0098] The memory 20 stores instructions that can be executed by at least one processor 10, so as to enable at least one processor 10 to execute the method shown in the above embodiment.

[0099] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0100] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0101] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 7 The bus connection is taken as an example.

[0102] The input device 30 can receive input digital or character information and generate key signal input related to user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a trackpad, a touch pad, an indicator stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 can include a display device, an auxiliary lighting device (e.g., an LED), and a tactile feedback device (e.g., a vibration motor). The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display, and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0103] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0104] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0105] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A target passenger identification and prompting method, characterized in that: The method comprises: Obtain identity information of a target passenger associated with the vehicle from a server; Acquire external environment data collected by an environment collection device, and extract pedestrian features from the external environment data, wherein the pedestrian features include at least facial features; When there is a target pedestrian whose facial features match the facial features of the target passenger among all the extracted facial features of the pedestrians, determining the target pedestrian as the target passenger and calculating the position information of the target passenger; The driver is prompted with the identity and location information of the target passenger, so as to be used by the driver to identify the target passenger in the environment.

2. The method according to claim 1, characterized in that The following steps are used to determine whether there is a target pedestrian whose facial features match the facial features of the target passenger among all pedestrians: Calculate the similarity between the facial features of all pedestrians and the facial features of the target passenger; A pedestrian whose facial features have a similarity with the facial features of the target passenger greater than a preset similarity threshold is determined as a target pedestrian.

3. The method according to claim 1 or 2, characterized in that The identity information also includes authentication information. The server stores a database of identity information corresponding to all passengers whose information has been entered. The authentication information corresponds to facial features one-to-one. Determining the target pedestrian as a target passenger includes: Based on the facial features of the target pedestrian, filtering out corresponding first identity verification information from a database stored in the server; comparing the first identity verification information with the identity verification information of the target passenger; If the first identity verification information is successfully compared with the identity verification information of the target passenger, the target pedestrian is determined as the target passenger.

4. The method according to claim 3, characterized in that The identity information also includes a target pick-up point, and the method further includes: If there is no target pedestrian whose facial features match the facial features of the target passenger among all the extracted facial features of the pedestrians, or if the first identity verification information fails to be compared with the identity verification information of the target passenger, then a message indicating that there is no target passenger at present is output to the driver, or, If the calculated relative distance between the target passenger's current location and the target pick-up point is greater than a preset distance threshold, information indicating that the target passenger has deviated from the target pick-up point is output to the driver, and a communication interaction portal for contacting the target passenger is provided on the in-vehicle screen.

5. The method according to claim 1, wherein The environment collection device includes an external camera, and the vehicle screen displays the external environment video collected by the external camera. The identification information and location information of the target passenger to the driver include: Display the target passenger's identity and location information on the vehicle screen, and / or The voice prompt information is broadcast, and the voice prompt information is used to prompt the driver of the location information of the target passenger.

6. The method according to claim 5, characterized in that Displaying the target passenger's identity information and location information on the vehicle screen includes: Classify the target passenger's identity information and location information according to the preset hierarchical display rules; The identity information and location information of the classified target passengers are displayed on the vehicle screen according to the preset hierarchical display rules, wherein the preset hierarchical display rules at least include: continuously displaying the identity information and location information corresponding to the first level on the vehicle screen, and in response to the user performing a second-level viewing operation, displaying the identity information and location information corresponding to the second level on the vehicle screen, the second level is initially in a hidden state, and the importance of the first level is greater than the importance of the second level.

7. The method according to claim 5, characterized in that The displaying of the target passenger's identity information and location information on the vehicle screen further includes: In the interface displayed on the vehicle screen, a direction indicator is used to prompt the driver of the direction of the target passenger relative to the vehicle, and / or, In the interface displayed on the in-vehicle screen, the target passenger is marked with a preset marking style.

8. The method according to claim 5, characterized in that The displaying of the identity information and location information of the target passenger on the vehicle screen further includes: In the interface displayed on the vehicle screen, the target passenger is 3D rendered, and the identity information and location information of the target passenger are displayed in a floating manner. The 3D rendering of the target passenger includes: when the relative distance between the target passenger and the vehicle is greater than a preset distance threshold, a transparent marking box for the target passenger is displayed on the vehicle screen; when the relative distance between the target passenger and the vehicle is not greater than the preset distance threshold, a 3D avatar of the target passenger is displayed on the vehicle screen.

9. A target passenger identification and prompting device, characterized in that: The device comprises: An identity information acquisition module is used to obtain the identity information of the target passenger associated with the vehicle from the server; a feature extraction module, configured to obtain the vehicle exterior environment data collected by the environment collection device, and extract pedestrian features from the vehicle exterior environment data, wherein the pedestrian features include at least facial features; a feature matching module, configured to, when a target pedestrian whose facial features match the facial features of the target passenger exists among all the extracted facial features of the pedestrians, determine the target pedestrian as the target passenger, and calculate the position information of the target passenger; The passenger prompt module is used to prompt the driver with the identity information and location information of the target passenger, so that the driver can identify the target passenger in the environment.

10. A vehicle, characterized in that: The vehicle includes an environment collection device and a controller, the controller includes a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the target passenger identification and prompting method according to any one of claims 1 to 8 by executing the computer instructions.

Images