Passenger positioning method and system

Abstract

The application discloses a passenger positioning method, which comprises the following steps: obtaining a rough position of a user; obtaining possible boarding positions within a preset range according to the rough position; obtaining a scene picture corresponding to each possible boarding position; selecting a scene picture according to a scene currently seen by the user; and obtaining an optimal boarding position of the user according to the selected scene picture. The passenger positioning method can enable a driver to obtain a more accurate position of the passenger, thereby avoiding a detour caused by positioning error and saving waiting time of the passenger and the driver.

Description

Technical Field

[0001] This invention relates to the field of urban transportation, and in particular to a passenger positioning method and system. Background Technology

[0002] Ride-hailing apps have revolutionized the traditional way of hailing a taxi, establishing and cultivating a modern travel mode led by the mobile internet era. Compared to traditional phone calls and street hailing, the emergence of ride-hailing apps has further transformed the traditional taxi market, overturning the concept of hailing a taxi on the street. By leveraging the characteristics of the mobile internet, it integrates online and offline services, allowing drivers to pay fares online from the initial stage of hailing a taxi to the point of disembarking. This changes the traditional way taxi drivers wait for passengers, allowing drivers to "accept orders" based on passengers' destinations, saving communication costs for both drivers and passengers, reducing empty mileage, and maximizing the saving of resources and time for both parties.

[0003] However, quickly picking up passengers after they place an order presents a significant challenge. Currently, intelligent navigation systems can quickly pinpoint a passenger's approximate location, but this location isn't precise enough. For example, when a passenger hails a taxi in an unfamiliar place, they may not know how to describe their exact location. Even if they are on the left side of a street, the error margin of satellite positioning is generally within 10 meters, meaning the passenger's location on the map might actually be on the right side of the street. In such cases, the driver often needs to take a longer route. Therefore, it's difficult for a driver to find a passenger based solely on a simple address. In some situations, the driver and passenger may be very close but unable to find each other. Even after confirming by phone, the driver may not be able to pinpoint the passenger's location accurately, potentially leading to a long detour around the destination before finally finding them. Therefore, improving efficiency and ensuring quick and accurate passenger pickup remains a pressing issue. Summary of the Invention

[0004] Based on the above, this invention proposes a passenger positioning method. The server pre-stores multiple sets of scene images formed by pictures taken from different angles. The user compares the scene they currently see with the pre-stored multiple sets of scene images. When the user selects a scene image that is close to the scene they currently see, the user's more accurate coordinates can be obtained, thereby obtaining the user's optimal boarding position.

[0005] This invention proposes a passenger positioning method, comprising the steps of: obtaining a user's approximate location; obtaining possible boarding locations within a preset range based on the approximate location, and obtaining scene images corresponding to each possible boarding location; the user selecting one of the scene images based on the currently viewed scene; and obtaining the user's optimal boarding location based on the selected scene image.

[0006] The scene image consists of two or more images taken from different shooting angles at possible boarding locations; the different shooting angles include at least a first shooting angle and a second shooting angle.

[0007] The method for obtaining the user's optimal boarding position from the scene image includes: obtaining a first direction line from a first shooting angle image, and then obtaining a second direction line from a second shooting angle image; determining the user's optimal boarding position based on the intersection of the first direction line and the second direction line.

[0008] The user uploads an image taken from a third shooting angle and obtains the third direction; it is determined whether the first direction, the second direction, and the third direction intersect at a point. If so, this point is used as the user's current coordinates; if not, the pairwise intersection points of the first direction, the second direction, and the third direction can form a triangle, and the centroid of this triangle is used as the user's current coordinates.

[0009] Obtain merchant information within a second preset range of the user's destination location; embed relevant advertisements of the merchant information into the scene image.

[0010] This invention also provides a passenger positioning system, comprising: a user location acquisition module, a scene image information acquisition module, a scene image information display module, and an optimal boarding location recommendation module, wherein each module is network-connected; the user location acquisition module is used to acquire the user's approximate location; the scene image information acquisition module is used to acquire possible boarding locations within a preset range based on the approximate location, and acquire scene images corresponding to each possible boarding location; the scene image information processing module is used to display the scene images corresponding to each possible boarding location; and the optimal boarding location recommendation module is used to recommend the optimal boarding location to the user based on the scene image corresponding to the boarding location selected by the user.

[0011] Compared to existing technologies, this invention is simple to operate. It obtains the user's approximate location and displays scene images corresponding to various possible pick-up locations. The user then selects from these scene images based on their current view, ultimately determining the optimal pick-up location. This allows drivers to obtain a more precise passenger location, avoiding detours caused by positioning errors and saving waiting time for both passengers and drivers. Attached Figure Description

[0012] Figure 1 This is a flowchart illustrating an embodiment of the passenger positioning method of the present invention;

[0013] Figure 2 This is a schematic diagram of an embodiment of the method for obtaining the optimal boarding position according to the present invention;

[0014] Figure 3This is a comparison image of the scene picture and the shooting angle picture of the present invention;

[0015] Figure 4 This is a schematic diagram of a passenger positioning system embodiment of the present invention. Detailed Implementation

[0016] The present invention will now be described in detail with reference to the preferred embodiments thereof.

[0017] like Figure 1 As shown, the method in this embodiment includes the following steps:

[0018] S101: Obtain the approximate location of the user.

[0019] When a user opens a ride-hailing app, the app uses a location system (GPS, BeiDou) to obtain the user's approximate location and automatically generates a corresponding address. Since the area indicated by an address can be very large (e.g., the name of a bus stop often doesn't specify which side of the stop it refers to), drivers may take a long detour when picking up or dropping off passengers. After obtaining the user's approximate location, the system retrieves possible pick-up locations within a preset range. These possible pick-up locations are generally based on experience derived from multiple passenger rides. In most cases, passengers are unlikely to be very familiar with the names of their pick-up and drop-off locations and the images of the surrounding scenery. This means that even if a user knows the name of the best pick-up location, they may still not be able to accurately reach their destination. It's also possible that the user sees the relevant scenery but cannot obtain the corresponding location name.

[0020] Based on the rough location, obtain possible boarding locations within a first preset range, and obtain scene images corresponding to each possible boarding location.

[0021] After the system obtains possible pick-up locations within a first preset range, the user can see the corresponding location name on the map. Generally, after GPS positioning, the system provides several locations around the user's location as possible pick-up locations (or recommended pick-up locations). Corresponding scene images can be preset for each possible pick-up location on the system. Thus, when possible pick-up locations are obtained, the system can retrieve scene images corresponding to each location and display them to the user for selection. These scene images consist of two or more images taken from different angles at the possible pick-up locations. These different angles include at least a first angle and a second angle. Of course, in simpler traffic environments, a single image from a single angle can be used as the scene image.

[0022] S103: The user selects a scene image based on the current real-world scene; the optimal boarding location for the user is obtained based on the selected scene image.

[0023] Scene images are pre-stored on the server. Based on the user's current approximate location information, several sets of pre-stored scene images within a preset range (e.g., within 100 meters) of the user's approximate location are retrieved. After these sets of pre-stored scene images are displayed to the user, the user can compare them with the scenery they can see from their current location (i.e., the actual scene). By simply looking around, it is not difficult to find images that are the same as or similar to the current scene image. The user can then select a scene image that closely resembles their current view. Through system comparison, the current location of the user can be roughly generated. In areas with simple traffic conditions, a single scene image can accurately locate the user. In more complex traffic environments, the positioning effect of a single image is greatly reduced.

[0024] As a better implementation example, the pre-stored scene images here are scene images taken from different angles. Due to the inherent errors in satellite positioning accuracy, most mobile phone positioning systems can only pinpoint a street, making it difficult to accurately determine which side of the street the user is on. This increases the difficulty for taxi drivers in picking up and dropping off passengers. Using scene images taken from different angles and comparing them with system images allows for a more accurate determination of the user's location, solving the inconvenience of traditional satellite positioning. Generally, the shooting direction of the image can be obtained by comparing the pre-stored image with the image taken at different angles; the direction of the line connecting the camera and a reference object is the shooting direction (from a planar perspective, it's the direction line from the camera to the reference object). The method for obtaining the user's optimal boarding position using scene images includes: obtaining the first direction of the first shooting angle image, and then obtaining the second direction of the second shooting angle image; determining the user's optimal boarding position based on the intersection of the first and second directions. Here, the first and second shooting angle images are pre-stored scene images (i.e., a combination of multiple pre-stored images), which can be pre-stored by the system and displayed to the user for selection. To achieve better technical results, since the lighting conditions may vary due to weather and time factors when the user pre-stores scene images, this method is suitable for different scenarios. Therefore, when selecting scene images, different images should be selected based on the upload time and the weather at that time, so that users will not select the wrong image because different scene images appear at different times.

[0025] like Figure 2As shown, User A is below the street, and User B is on the other side of the street. User A sees reference objects A, B, and C from their current position. They then select images of reference objects A and B that are closest to their current position on a mobile terminal or other electronic device (obviously, the images of the same reference object seen from A and B's positions will be different). This allows us to obtain the first direction when viewing reference object A (the direction A points towards reference object A; in this embodiment, the direction is represented by a straight line, and so on), and the second direction when photographing reference object B. The current position of User A can be determined by the intersection of these directions (i.e., the intersection of the backward extensions of the photographing direction). Similarly, User B's current position can be obtained in the same way. Theoretically, User A's current position can be determined using only two directions. The third direction obtained when photographing reference object C can be used for calibration. This third direction can be obtained by the user photographing reference object C from their current position and uploading it to the server. The server pre-stores panoramic or landmark images, and the third direction can be calculated by comparing these images with the image of reference object C. The calibration method using a third-direction calibration is as follows: Determine whether the first, second, and third directions intersect at a single point. If so, use this point as the precise coordinates of the current user (or user B). If not, the pairwise intersections of the first, second, and third directions form a triangle. The centroid of this triangle (which, depending on the situation, can be replaced by the circumcenter, incenter, orthocenter, or excenter) is used as the coordinates of the current user (or user B). The presence of a triangle indicates a deviation between the user's current location and the previously stored image location on the server. After the user selects a pre-stored scene image, it proves that their location is relatively close to the precise coordinates in the pre-stored system. By taking the centroid of the triangle, the user's actual coordinates can be combined with the precise coordinates in the pre-stored system, resulting in calibrated coordinates that are closer to the true coordinates. This more precise positioning allows taxi drivers to quickly determine the passenger's exact location on the street after receiving a rough location information, thus saving time searching for the passenger.

[0026] like Figure 3As shown, Person A, at their current location, uses the first scene image (the same first scene image can be used anywhere near the selected location). Person A takes two images, one from a first shooting angle and the other from a second shooting angle, and uploads them to the server. The system compares the similarity between the first scene image and the first shooting angle image to determine the location of the shot within the first scene image, thus calculating the first direction. Similarly, the system compares the similarity between the first scene image and the second shooting angle image to calculate the second direction. When displayed on a monitor or mobile phone, the panoramic image corresponding to the first scene image is a rectangular image. Dividing the length of the rectangle by 360 gives the portion of the image corresponding to each angle. The user's shooting device also has a corresponding lens angle of 150°. The first shooting angle image is also rectangular, and dividing the length of the rectangle by 150 gives the portion of the image corresponding to each angle. Thus, by extracting 1° from the first shooting angle image and comparing it with 1° from the first scene image, the similarity can be quickly determined. As a verification, multiple images of the first shooting angle image are compared with the first scene image, and finally, the intermediate value of 75° from the first shooting angle image is taken as the corresponding direction of the first shooting angle direction, using only 1° of data. Because the entire captured image is a parallel plane, the directions of all points within it are parallel, and the intersecting points are shown as a plane, but from a 3D perspective, it appears as two planes intersecting.

[0027] To achieve better economic benefits for users, ride-hailing platforms, and merchants, users can choose between two modes when obtaining location information using the above method: an advertising mode and a no-ad mode. In the advertising mode, merchant information within a second preset range of the user's destination is obtained; relevant advertisements for these merchants are then embedded in pre-stored scene images. Obtaining merchant information within a second preset range of the user's destination (or approximate location, i.e., current location) and then displaying corresponding merchant advertisements to the user allows them to gain a better understanding of businesses around their destination, achieving the goal of targeted advertising. The user's destination location is the information entered when the user hails a ride. Users typically shop or conduct business at their destination; advertisements for relevant merchants help users better understand their destination. In this mode, users can reduce some ride costs, advertisers can place appropriate ads, and ride-hailing platforms can increase advertising revenue, offering users greater discounts and thus increasing user stickiness to the software.

[0028] Figure 4 The diagram shows a structural schematic of an embodiment of the passenger positioning system of the present invention.

[0029] A passenger positioning system includes: a user location acquisition module, a scene image information acquisition module, a scene image information display module, and an optimal boarding location recommendation module, all connected to a network. The user location acquisition module acquires the user's approximate location; the scene image information acquisition module acquires possible boarding locations within a preset range based on the approximate location and acquires scene images corresponding to each possible boarding location; the scene image information processing module displays the scene images corresponding to each possible boarding location; and the optimal boarding location recommendation module recommends the optimal boarding location to the user based on the scene image corresponding to the boarding location selected by the user.

[0030] The method of recommending the best boarding position to the user based on scene images includes: obtaining the first direction of the first shooting angle image, and then obtaining the second direction of the second shooting angle image; determining the best boarding position for the user based on the intersection of the first and second directions.

[0031] As a better embodiment, the system also includes a positioning calibration module, which obtains a third direction based on a third-angle image uploaded by the user at the current location, and then determines whether the first direction, the second direction, and the third direction intersect at a point. If so, this point is used as the precise coordinates of the current A (or B). If not, the pairwise intersections of the first direction, the second direction, and the third direction can form a triangle, and the centroid of this triangle (which, depending on the actual situation, can also be replaced by the circumcenter, incenter, orthocenter, or excenter of the triangle) is used as the coordinates of the current A (or B).

[0032] To enhance the economic benefits for users, ride-hailing platforms, and merchants, this system also includes an advertising module. This module retrieves merchant information within a second preset range around the user's destination (or current location) and embeds advertisements for these merchants into pre-stored scene images. Retrieving merchant information within this second preset range and then displaying corresponding merchant advertisements to the user allows for a better understanding of businesses around their destination, achieving targeted advertising. The user's destination is the starting and ending point information entered when hailing a ride. Users typically shop or conduct business at their destination; therefore, displaying advertisements for relevant merchants helps users better understand their destination. This model allows users to reduce ride costs, advertisers to place appropriate ads, and ride-hailing platforms to increase advertising revenue, offering greater discounts and increasing user engagement with the software.

[0033] The embodiments described above are merely illustrative of implementation methods of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A passenger positioning method, characterized in that, The steps include: obtaining the user's approximate location; obtaining possible boarding locations within a preset range based on the approximate location, obtaining scene images corresponding to each possible boarding location and displaying them to the user; the user selecting one of the displayed scene images based on the current actual scene; obtaining the user's optimal boarding location based on the selected scene image; the scene image consists of two or more images taken from different shooting angles at the possible boarding locations; the different shooting angles include at least a first shooting angle and a second shooting angle; The method for obtaining the user's optimal boarding position from the scene image includes: obtaining the first direction of the first shooting angle image, and then obtaining the second direction of the second shooting angle image; The optimal boarding location for the user is determined based on the intersection of the first and second directions.

2. The passenger positioning method according to claim 1, characterized in that, The user uploads an image taken from a third shooting angle and obtains the third direction; it is determined whether the first direction, the second direction, and the third direction intersect at a point. If so, this point is used as the user's current coordinates; if not, the pairwise intersection points of the first direction, the second direction, and the third direction can form a triangle, and the centroid of this triangle is used as the user's current coordinates.

3. The passenger positioning method according to any one of claims 1-2, characterized in that, Obtain merchant information within a second preset range of the user's destination location; embed relevant advertisements of the merchant information into the scene image.

4. A passenger positioning system, characterized in that, The system includes a user location acquisition module, a scene image information acquisition module, a scene image information display module, and an optimal boarding location recommendation module, all connected via a network. The user location acquisition module acquires the user's approximate location. The scene image information acquisition module acquires possible boarding locations within a preset range based on the approximate location and obtains scene images corresponding to each possible boarding location. The scene image information processing module displays the scene images corresponding to each possible boarding location. The optimal boarding location recommendation module recommends the best boarding location to the user based on the scene image corresponding to the selected boarding location. Each scene image consists of two or more images taken from different shooting angles at a possible boarding location; the different shooting angles include at least a first shooting angle and a second shooting angle. The method of recommending the best boarding position to users based on scene images includes: obtaining the first direction of the first shooting angle image, and then obtaining the second direction of the second shooting angle image; determining the best boarding position for the user based on the intersection of the first and second directions.

5. The passenger positioning system according to claim 4, characterized in that, It also includes a positioning calibration module, which obtains the third direction based on the third-angle image uploaded by the user standing at the current position, and then determines whether the first direction, the second direction and the third direction intersect at a point. If so, the point is used as the user's current coordinates; if not, the pairwise intersection points of the first direction, the second direction and the third direction can form a triangle, and the centroid of the triangle is used as the user's current coordinates.

6. The passenger positioning system according to any one of claims 4-5, characterized in that, It also includes an advertising module for obtaining merchant information within a second preset range of the user's destination location; and embedding relevant advertisements of the merchant information into the scene image.

Images