WO2021143487A1 - Determination of poi coordinates - Google Patents

Abstract

Provided is a method for determining POI coordinates, comprising: obtaining a plurality of historical orders having the same target meal-delivery address (101); in the meal delivery path of each historical order, determining a meal delivery section path located within a first reference range of said target meal-delivery address (102); mapping said meal delivery section path of each historical order to a geographic hash block, and determining the target geographic hash block which maps the most meal delivery section paths (103); determining the coordinates of the center point of the target geographic hash block to be the POI coordinates of the target meal-delivery address (104).

Description

Determine POI coordinates

This application claims the priority of the Chinese patent application with the application number 202010060294.2 filed on January 19, 2020, and the application title is "Method, Apparatus, Storage Medium and Electronic Equipment for Determining POI Coordinates", the entire content of which is incorporated by reference In this application.

Technical field

The embodiments of the present disclosure relate to the field of computer technology, and in particular, to a method, device, storage medium, and electronic equipment for determining POI coordinates.

Background technique

In the delivery process, the last link is food delivery. The POI (Point of Interest) coordinates of the food delivery point are point data in the Internet electronic map, which can include four attributes: name, address, coordinates, and category.

Summary of the invention

The purpose of the embodiments of the present disclosure is to provide a method for determining POI coordinates.

On the one hand, an embodiment of the present disclosure provides a method for determining POI coordinates, and the method includes:

Obtain multiple historical orders with the same target delivery address;

In the food delivery trajectory of each historical order, determine the trajectory of the food delivery section within the first reference range of the target food delivery address;

Map the trajectory of the food delivery section of each historical order to a geographic hash block, and determine the target geographic hash block with the most trajectories of the food delivery section mapped;

The coordinates of the center point of the target geographic hash block are determined as the POI coordinates of the target meal delivery address.

Optionally, in the food delivery trajectory of each historical order, determining the trajectory of the food delivery section within the first reference range of the target food delivery address includes:

For the food delivery trajectory of each historical order, traverse the food delivery trajectory through a sliding window, the sliding window including a reference number of trajectory points;

If the characteristic information corresponding to the trajectory points in the sliding window meets the reference condition, it is determined that the trajectory composed of the trajectory points included in the sliding window is the trajectory of the food delivery section, and the characteristic information includes at least one of the following: Position information, speed information, and corner information.

Optionally, if the feature information corresponding to the trajectory points in the sliding window satisfies a reference condition, determining that the trajectory composed of the trajectory points included in the sliding window is the trajectory of the food delivery section includes:

Determine the hexagram limit number of the trajectory point according to the turning angle information of the trajectory point in the sliding window;

If the hexagram limit number of the trajectory point in the sliding window meets the reference hexagram limit number condition, the position information of the trajectory point meets the reference position condition, and the number of trajectory points that are stay points reaches the reference number, determine the trajectory included in the sliding window The trajectory composed of points is the trajectory of the food delivery section, and the stop point is a trajectory point whose speed is less than or equal to the first reference speed and the speed of the trajectory point in the second reference range is less than or equal to the first reference speed .

Optionally, if the feature information corresponding to the trajectory points in the sliding window satisfies a reference condition, determining that the trajectory composed of the trajectory points included in the sliding window is the trajectory of the food delivery section includes:

Determine the first target trajectory point in the food delivery trajectory whose speed is less than or equal to the second reference speed, and determine the time difference between the stay point and the target trajectory point to obtain the stay time of the stay point, the stay A point is a track point whose speed is less than or equal to the first reference speed and the speed of the track point in the second reference range is less than or equal to the first reference speed;

Determine the hexagram limit number of the trajectory point according to the turning angle information of the trajectory point in the sliding window;

If the hexagram limit number of the trajectory point in the sliding window satisfies the reference hexagram limit number condition, the position information of the trajectory point meets the reference position condition, the number of trajectory points that are the stay point reaches the reference number, and the stay time exceeds the reference time length, then It is determined that a trajectory composed of trajectory points included in the sliding window is the trajectory of the food delivery section.

Optionally, the position information of the track point satisfies a reference position condition, including:

On the reference map, the distance between the track point and the target meal delivery address is less than or equal to the first reference threshold; or

On the reference map, the distance between the track point and the meal pickup address is greater than or equal to a second reference threshold.

Optionally, the determining the target geographic hash block mapping the most trajectory of the food delivery segment includes:

If there are multiple target geographic hash blocks mapped to the trajectory of the most meal delivery section, determining whether the distance between the multiple geographic hash blocks is less than or equal to the first reference distance;

If the distance between the multiple geographic hash blocks is less than or equal to the first reference distance, determine the multiple geographic hash blocks as the target geographic hash block; accordingly,

The determining the coordinates of the center point of the target geographic hash block as the POI coordinates of the target meal delivery address includes:

The geometric center points of the multiple geographic hash blocks are determined, and the coordinates of the geometric center points are determined as the POI coordinates of the target meal delivery address.

Optionally, the acquiring multiple historical orders with the same target delivery address includes:

In historical orders with different food delivery addresses, respectively determine the address coordinates corresponding to the food delivery addresses in the reference map;

The multiple historical orders with the address coordinates are determined as multiple historical orders with the same target delivery address.

Optionally, the acquiring multiple historical orders with the same target delivery address includes:

In historical orders with different food delivery addresses, respectively determine the address coordinates corresponding to the food delivery addresses in the reference map;

The multiple historical orders within the third reference range of the address coordinates are determined as multiple historical orders with the same target food delivery address.

Optionally, in the food delivery trajectory of each historical order, determining the trajectory of the food delivery section within the first reference range of the target food delivery address includes:

For the delivery trajectory of each historical order, remove the noise trajectory points whose distance from other trajectory points exceeds the second reference distance;

In the food delivery trajectory from which the noise trajectory point is removed, the trajectory of the food delivery section located in the first reference range of the target food delivery address is determined.

On the one hand, an embodiment of the present disclosure also provides a method for determining POI coordinates, the method including:

Obtain multiple historical orders with the same target delivery address;

In the food delivery trajectory of each historical order, determine the trajectory of the food delivery section located in the first reference range of the target food delivery address;

Determine the target geographic area where the distribution density of the food delivery segment trajectory of each historical order is greatest;

The POI coordinates of the target meal delivery address are determined based on the coordinates of the target geographic area.

Optionally, the acquiring multiple historical orders with the same target food delivery address includes: in the historical orders with different food delivery addresses, respectively determining the address coordinates corresponding to the food delivery address in the reference map; for any One address coordinate, multiple historical orders with any one of the address coordinates are determined as multiple historical orders with the same target delivery address, the address coordinates of the target delivery address in the reference map Is any one of the address coordinates.

Optionally, the acquiring multiple historical orders with the same target food delivery address includes: in the historical orders with different food delivery addresses, respectively determining the address coordinates corresponding to the food delivery address in the reference map; for any An address coordinate determines multiple historical orders within the third reference range of any one of the address coordinates as multiple historical orders with the same target delivery address, and the target delivery address corresponds to the reference map The address coordinate is any one of the address coordinates.

On the one hand, an embodiment of the present disclosure also provides a device for determining POI coordinates, the device including:

The obtaining module is configured to obtain multiple historical orders with the same target delivery address;

The first determining module is configured to determine the trajectory of the food delivery section within the first reference range of the target food delivery address in the food delivery trajectory of each historical order;

The second determining module is configured to map the food delivery section trajectory of each historical order to a geographic hash block, and determine the target geographic hash block with the most food delivery section trajectory mapped;

The third determining module is configured to determine the coordinates of the center point of the target geographic hash block as the POI coordinates of the target meal delivery address.

On the one hand, an embodiment of the present disclosure also provides a device for determining POI coordinates, the device including:

The obtaining module is configured to obtain multiple historical orders with the same target delivery address;

The first determining module is configured to determine the trajectory of the food delivery section within the first reference range of the target food delivery address in the food delivery trajectory of each historical order;

The second determining module is configured to determine the target geographic area where the distribution density of the food delivery section trajectory of each historical order is the largest;

The third determining module is configured to determine the POI coordinates of the target meal delivery address based on the coordinates of the target geographic area.

Optionally, the acquisition module is configured to determine the address coordinates corresponding to the food delivery address in the reference map in historical orders with different food delivery addresses; for any address coordinate, there will be any Multiple historical orders with one address coordinate are determined as multiple historical orders with the same target meal delivery address, and the address coordinate corresponding to the target meal delivery address in the reference map is any one of the address coordinates.

Optionally, the acquisition module is configured to determine the address coordinates corresponding to the food delivery address in the reference map in historical orders with different food delivery addresses; for any address coordinates, the The multiple historical orders within the third reference range of address coordinates are determined to be multiple historical orders with the same target delivery address, and the address coordinates corresponding to the target delivery address in the reference map are any of the address coordinates .

On the one hand, embodiments of the present disclosure also provide a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

On the one hand, the embodiments of the present disclosure also provide an electronic device, including:

A memory on which a computer program is stored;

The processor is configured to execute the computer program in the memory to implement the steps of any one of the methods in the first aspect.

On the other hand, the embodiments of the present disclosure also provide a computer program or computer program product. The computer program or computer program product includes: computer instructions, when the computer instructions are executed by a computer, the computer realizes the first aspect. The steps of any one of the methods.

Through the above technical solution, the trajectory of the food delivery section of the historical order can be mapped to the geographic hash block, and the target geographic hash block with the most trajectory of the food delivery section can be determined, and then the center point of the target geographic hash block The POI coordinates are determined as the POI coordinates of the target food delivery address. Compared with the method of returning the coordinates through the map in the related technology, the dependence on the map service can be reduced, and the POI coordinates that are closer to the actual food delivery point can be obtained, which improves the determination of the POI coordinates. Accuracy.

Other features and advantages of the embodiments of the present disclosure will be described in detail in the following specific implementation section.

Description of the drawings

The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure, and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present disclosure, but do not constitute a limitation to the embodiments of the present disclosure. In the attached picture:

Fig. 1 is a flowchart showing a method for determining POI coordinates according to an exemplary embodiment of the present disclosure;

Fig. 2 is a schematic diagram showing the division of hexagrams in a method for determining POI coordinates according to an exemplary embodiment of the present disclosure;

3 is a schematic diagram of traversing a delivery track through a sliding window in a method for determining POI coordinates according to an exemplary embodiment of the present disclosure;

Fig. 4 is a schematic diagram showing the result of dividing the food delivery trajectory in Fig. 3 in a method for determining POI coordinates according to an exemplary embodiment of the present disclosure;

Fig. 5 is a schematic diagram showing the result of mapping a food delivery trajectory to a geographic hash block in a method for determining POI coordinates according to an exemplary embodiment of the present disclosure;

Fig. 6 is a flowchart showing a method for determining POI coordinates according to another exemplary embodiment of the present disclosure;

Figure 7 is a schematic diagram of the POI coordinates of the target meal delivery address determined according to related technologies;

FIG. 8 is a schematic diagram showing POI coordinates of the same target delivery address as in FIG. 7 determined by a method for determining POI coordinates according to another exemplary embodiment of the present disclosure;

Fig. 9 is a block diagram showing a device for determining POI coordinates according to an exemplary embodiment of the present disclosure;

Fig. 10 is a block diagram showing an electronic device according to an exemplary embodiment of the present disclosure.

Detailed ways

The specific implementation manners of the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific implementations described here are only used to illustrate and explain the embodiments of the present disclosure, and are not used to limit the embodiments of the present disclosure.

In the food delivery process, the final delivery link is a key link that directly affects the user experience. The correctness of the delivery point directly affects the delivery experience of the delivery staff. If the delivery point is incorrect, it may lead to The delivery staff cannot deliver the meal to the user on time.

POI (Point of Interest) is the point data in the Internet electronic map, which can contain four attributes: name, address, coordinates, and category. In related technologies, determining the POI coordinates of the food delivery point is mainly through the address filled in by the user, directly calling the map search service interface, and returning the coordinates given by the map service. However, the address filled in by the user does not necessarily represent the actual location of the food delivery, which causes a large number of positioning inaccuracies. In addition, this method relies too much on map services, but the accuracy of the map is relatively poor. The coordinates given by the map may be located on the top of the building or the center of the building, and these places are often places inaccessible to riders. If the building complex is large enough, The location returned by the map may be far from the location of the actual food delivery.

In addition, the related technology can also cluster the check-in points of takeaways within a certain space by using density clustering, and use the center of each cluster as the delivery point within the range, and pair the check-in points according to the names of existing POIs nearby. The delivery point is named. However, this method overly relies on the rider's check-in data, which is prone to deviation due to the rider's subjective reasons, such as early click delivery or delayed click delivery, which will cause the determined POI coordinates to be inconsistent with the actual delivery location.

Alternatively, the related technology can also denoise the sign-in coordinates of the rider in the same address using an isolated forest, and then calculate the geometric center of the de-noised sign-in coordinates as the POI coordinates of the food delivery point. However, this method may not be able to calculate the correct POI coordinates because the rider's sign-in coordinates are too discrete.

In view of this, the embodiments of the present disclosure provide a method, device, storage medium, and electronic device for determining POI coordinates, so as to solve technical problems existing in related technologies and improve the accuracy of determining POI coordinates.

First, the possible implementation scenarios of the embodiments of the present disclosure are explained. In a possible way, after the user fills in the delivery address on the client, the client can send the delivery address to the server, and the server can obtain multiple historical orders that are the same as the delivery address, and then execute the implementation of the present disclosure In the example, the steps of the method of determining the POI coordinates, so as to obtain the POI coordinates of the meal delivery address. In addition, the server can send the POI coordinates to the client held by the takeaway, so that the takeaway can accurately and timely deliver the meal to the user according to the received POI coordinates.

Fig. 1 is a flowchart showing a method for determining POI coordinates according to an exemplary embodiment of the present disclosure. This method can be applied to a server. Referring to Figure 1, the method includes:

Step 101: Obtain multiple historical orders with the same target delivery address.

Step 102: In the food delivery trajectory of each historical order, determine the trajectory of the food delivery section located in the first reference range of the target food delivery address.

Step 103: Map the food delivery segment trajectory of each historical order to a geographic hash block, and determine the target geographic hash block that has the most food delivery segment trajectory mapped.

Step 104: Determine the POI coordinates of the center point of the target geographic hash block as the POI coordinates of the target meal delivery address.

It should be understood that in the embodiments of the present disclosure, after the user fills in the meal delivery address on the client, the client can send the meal delivery address to the server, and the server can obtain multiple historical orders that are the same as the meal delivery address. Then perform the above steps to obtain the POI coordinates of the meal delivery address. In addition, the server can send the POI coordinates to the client held by the takeaway, so that the takeaway can accurately and timely deliver the meal to the user according to the received POI coordinates.

Through the above method, the trajectory of the historical order delivery section can be mapped to a geographic hash (geohash) block, and the target geographic hash block that maps the most trajectory of the food delivery section can be determined, and then the target geographic hash block center The POI coordinates of the points are determined as the POI coordinates of the target food delivery address, which reduces the dependence on map services and takeaway check-in data, and can obtain POI coordinates that are closer to the actual food delivery point, and improve the accuracy of determining the POI coordinates.

In order to enable those skilled in the art to better understand the method for determining POI coordinates provided in the embodiments of the present disclosure, the above steps are described in detail below with examples.

In step 101, obtaining multiple historical orders with the same target food delivery address may be: for historical orders with different food delivery addresses, through the NLP (Natural Language Processing) parsing algorithm, the historical order delivery The restaurant address (that is, the address filled in by the user) is parsed to obtain the stem words of different levels in the address, for example, the stem words of the three dimensions of "community", "building number", and "unit number" can be obtained. Then, the stem words of the address are compared in turn, and multiple historical orders with the same delivery address are obtained. For example, the results of address resolution can be as shown in Table 1, and then you can refer to the content of Table 1, and compare the stem words of the address in the order of "community", "building number", and "unit number" to get the same delivery address Of multiple historical orders.

Table 1

Delivery address Community Floor unit number No. 6 Yulin West Road (Unit 2, No. 2) No. 6 Yulin West Road 2 2 Building 1, No. 78, Chengbai Road 78 Chengbai Road 1 -

It should be understood that the result obtained by parsing the delivery address in the historical order through the NLP parsing algorithm can also be used as the name of the POI coordinate determined subsequently, so as to display the POI coordinate determined subsequently on the map.

Or, in a possible way, in order to avoid determining the delivery addresses with the same name but different actual address locations as the same delivery address, you can determine that the delivery addresses are on the reference map in historical orders with different delivery addresses. Then, multiple historical orders with the address coordinates are determined as multiple historical orders with the same target delivery address.

The reference map may be a map provided by various map services in related technologies, which is not limited in the embodiment of the present disclosure.

For example, the names of the first delivery address and the second delivery address are the same restaurant name, but the first delivery address is the branch of the restaurant in the west of the city, and the second delivery address is the branch of the restaurant in the east of the city. If only the name is used for comparison, the two food delivery addresses that are far apart may be determined to have the same food delivery address. In order to solve this technical problem, the historical orders after the name comparison can be compared by referring to the address coordinates on the map. That is to say, in the embodiment of the present disclosure, the same meal delivery address not only has the same address name, but also has the same address coordinates on the map.

Further, considering that the address coordinates on the map will flicker in a small range, it is also possible to obtain multiple historical orders with the same target delivery address: first, in historical orders with different delivery addresses, determine that the delivery addresses are located at Refer to the corresponding address coordinates in the map, and then determine the multiple historical orders within the third reference range of the address coordinates as multiple historical orders with the same target delivery address.

For example, the third reference range may be set according to actual conditions, and the embodiment of the present disclosure does not limit this. In a possible manner, the third reference range may be based on a certain address coordinate as the center and a radius of 100 meters. The range included in the circle.

Through the above method, the address coordinates in the third reference range of the original coordinates corresponding to the meal delivery address can be determined to be the same address coordinates as the original coordinates. For example, the coordinates within a 100-meter radius around the original coordinates can be determined to be the same as the original coordinates. Address coordinates, to avoid inaccurate results due to address coordinate jitter, and improve the accuracy of the final POI coordinates.

After obtaining multiple historical orders with the same target food delivery address, the trajectory of the food delivery section within the first reference range of the target food delivery address can be determined in the food delivery trajectory of each historical order. The first reference range may be set according to actual conditions, which is not limited in the embodiment of the present disclosure.

In a possible manner, for the food delivery trajectory of each historical order, the food delivery trajectory can be traversed through a sliding window, and the sliding window includes a reference number of trajectory points. If the characteristic information corresponding to the trajectory points in the sliding window meets the reference condition, it can be determined that the trajectory composed of the trajectory points included in the sliding window is the trajectory of the food delivery section, and the characteristic information includes at least one of the following: position information, speed information , Corner information.

For example, the reference number may be set according to actual conditions, which is not limited in the embodiment of the present disclosure. For example, the reference number can be set to 10, then the sliding window can include 10 track points, and the first reference range can be a range that includes 10 track points near the target meal delivery address.

For example, feature extraction and analysis can be performed on the track points in the sliding window. For example, you can extract the position information, turning angle information, and speed information of each track point, and then analyze whether the position information, turning angle information, and speed information of each track point meet the reference conditions.

For example, the turning angle information may be the turning angle information carried in the GPS coordinates of the track point, which is used to characterize the right deflection angle of the track point relative to the true north direction. Taking into account that the delivery staff will stay in place only when they encounter a red light or a traffic accident or a delivery or pick-up scene, and there will be no large corner characteristics in a red light or traffic accident scene. In addition, the delivery staff will have the same trajectory during the delivery section. It is impossible to maintain a high-speed driving state in the trajectory of the meal fetching section, so the trajectory of the delivery section and the meal fetching section can be determined by the corner information and speed information. Further, the trajectory of the food delivery and delivery section can be distinguished from the trajectory of the meal fetching section through the location information, thereby obtaining the trajectory of the food delivery and delivery section. For example, the address coordinates of the business and the address coordinates of the target food delivery address can be determined on the reference map, and then the track points that are farther from the business address or closer to the target food delivery address are determined as the track points included in the track of the food delivery section .

In a possible manner, the hexagram limit number of the track point can also be determined according to the corner information of the track point in the sliding window. If the hexagram limit number of the trajectory point in the sliding window meets the reference hexagram limit number condition, the position information of the trajectory point meets the reference position condition, and the number of trajectory points that are the stay points reaches the reference number, the trajectory points included in the sliding window can be determined The trajectory of is the trajectory of the delivery section. Wherein, the stay point is a track point whose speed is less than or equal to the first reference speed and the speed of the track point in the second reference range is less than or equal to the first reference speed.

In spatial three-dimensional geometry, the space is divided into eight parts by the mutually perpendicular coordinate axes X, Y, and Z, and each part is called a hexagram limit. In the embodiment of the present disclosure, referring to FIG. 2, the plane 360 degrees can be divided into 8 hexagram limits, so that the hexagram limit number for the trajectory point can be determined through the rotation angle information of the trajectory point.

In the food delivery trajectory, usually ten consecutive trajectory points can cover more than 4 hexagram limits, that is, the turning angle of ten trajectory points will exceed 180 degrees, and it includes a U-turn action. Therefore, in the embodiment of the present disclosure, when the sliding window includes 10 trajectory points, the reference hexagram limit number condition can be set to exceed 4 hexagram limits.

It should be understood that the hexagram limit number determined by the corner information is used to determine the trajectory of the meal delivery section. Compared with the method of directly judging by the corner information, the actual trajectory of the trajectory point can be obtained more accurately, and the accuracy of the result can be further improved. . For example, in the process of going straight, the rotation angles of the front and back track points are 3 degrees and 356 degrees, respectively. If the rotation angle difference is directly calculated, the front and back rotation angle difference can be obtained as 353 degrees, and the rotation angle of the front and back track points is relatively large. It is impossible to determine which of the trajectory points are going straight, U-turn, or turning. By calculating the hexagram limit number in the embodiment of the present disclosure, it can be determined that the two trajectory points pass the one hexagram limit and the eight hexagram limit, and do not exceed 4 hexagram limits, so that it can be determined that the trajectory point belongs to a straight trajectory, not a meal delivery. Delivery segment trajectory.

For example, the location information of the track point that satisfies the reference location condition may include on the reference map, the distance between the track point and the target meal delivery address is less than or equal to the first reference threshold; or on the reference map, the track point and the meal pickup address The distance between is greater than or equal to the second reference threshold. The first reference threshold and the second reference threshold can be set according to actual conditions, which are not limited in the embodiment of the present disclosure. For example, the second reference threshold may be greater than the first reference threshold, and so on.

In other words, in the embodiment of the present disclosure, the reference location condition may be a condition that is farther from the business address on the reference map, or may be a condition that the target meal delivery address on the reference map is farther away. Not limited.

For example, the reference quantity, the first reference speed, and the second reference range may be set according to actual conditions, which are not limited in the embodiment of the present disclosure. For example, the first reference speed may be set to 1.5 m/s, and the second reference range may be the range included by a circle with a certain track point as the center and a radius of 100 meters. In this case, the stay point may be a trajectory point where the speed of the takeaway is less than or equal to 1.5 m/s, and the velocity of the track point within a range of 100 meters is also less than or equal to 1.5 m/s. In specific implementation, you can first determine the first target trajectory point with a speed less than or equal to 1.5m/s, and then set the speed to be less than or equal to 1.5m/s and within the second reference range of the target trajectory point (for example, within 100 meters) The trajectory point of) is determined as the stay point.

In other possible ways, in order to improve the accuracy of the results, it is also possible to determine the first target trajectory point in the food delivery trajectory whose speed is less than or equal to the second reference speed, and determine the time difference between the stay point and the target trajectory point, and obtain The length of stay at the stay point. Then, according to the turning angle information of the track point in the sliding window, the hexagram limit number of the track point is determined. If the hexagram limit number of the trajectory point in the sliding window meets the reference hexagram limit number condition, the position information of the trajectory point meets the reference position condition, the number of trajectory points that are the stay points reaches the reference number, and the stay time exceeds the reference time, then the sliding window is determined to include The trajectory composed of the trajectory points is the trajectory of the delivery section. The second reference speed can be set according to actual conditions, which is not limited in the embodiment of the present disclosure. For example, the second reference speed can be set to 1.5m/s, and so on.

That is to say, in the embodiment of the present disclosure, in order to improve the accuracy of the result, the stay time of the stay point can be further determined. For example, in the above example, when determining the first target trajectory with a speed less than or equal to 1.5m/s After the point, the time difference between any stay point and the target track point can be determined, and the stay time of the stay point can be obtained, so that the delivery can be determined according to the hexagram limit number, location information, the number of stay points, and the stay time of each stay point. The trajectory of the meal delivery segment.

Through the above method, the food delivery trajectory can be divided by combining the position information, the corner information and the stay information, so as to obtain the food delivery section trajectory in the food delivery trajectory more accurately.

For example, the food delivery trajectory is shown in Figure 3, and the food delivery trajectory is traversed through a sliding window including 10 trajectory points, and the food delivery trajectory can be divided to obtain a straight trajectory, a turning trajectory, and a stay delivery section trajectory ( That is, the trajectory of the delivery section and the trajectory of the stay and retrieval section. Specifically, please refer to Figure 4. It can be seen that the straight trajectory passes through two hexagram limits, the speed of the trajectory point is high, and there is no stopping point, the turning trajectory passes more than four hexagram limits, the speed of the trajectory point is high, and there is no stopping point. The trajectory of the stay delivery section passes more than four hexagram limits, the speed of the trajectory point is low, and there are more staying points, the trajectory of the staying meal fetching section passes more than four hexagram limits, the speed of the trajectory point is low, and there are more stay points. Then, according to the location information, the trajectory that is farther from the business address on the reference map or the trajectory that is further away from the target food delivery address on the reference map can be determined as the food delivery segment trajectory.

In actual situations, there may be missing track points in the food delivery trajectory, resulting in noise points that are far away from other track points in the food delivery trajectory. In the embodiments of the present disclosure, in order to further improve the accuracy of determining the POI coordinates, these noise points may be removed.

Specifically, for the food delivery trajectory of each historical order, noise trajectory points whose distances from other trajectory points exceed the second reference distance can be removed. Then, in the food delivery trajectory where the noise trajectory points are removed, the trajectory of the food delivery section located in the first reference range of the target delivery address is determined. The second reference distance may be set according to actual conditions, which is not limited in the embodiments of the present disclosure. For example, the second reference distance can be set to 30 meters, and when the distance between the track point and other track points exceeds 30 meters, the track point can be removed as a noise point. Then, the trajectory of the food delivery section can be determined by any of the above methods for the food delivery trajectory after the noise is removed.

After the trajectory of the food delivery section is determined, the trajectory of the food delivery section of each historical order can be mapped to a geographic hash block. Then, it is possible to determine the target geographic hash block that has the most trajectories of food delivery segments mapped.

For example, a geohash block is a sub-block obtained by understanding the earth as a two-dimensional plane and recursively decomposing the two-dimensional plane. Each sub-block has the same string code within a certain range of latitude and longitude. In other words, all points (ie, latitude and longitude coordinate points) in each sub-block share the same geohash string. In the embodiment of the present disclosure, the trajectory of the delivery section of each historical order may be mapped to an 8-bit coded geographic hash block or a 9-bit coded geographic hash block, etc., and the present disclosure does not do this. limited. It should be understood that the more coding digits of the geographic hash block, the higher the coding accuracy, so that more accurate POI coordinates can be obtained. In the specific implementation of the embodiments of the present disclosure, the coding of the geographic hash block can be selected according to the accuracy requirements. Number of digits.

For example, to map the food delivery trajectory of each historical order to the geographic hash block, it can be that the trajectory of the food delivery segment of each historical order and the divided geographic hash block are displayed on the same map, and then you can Determine the total number of trajectories that each geographic hash block passes, and obtain the target geographic hash block mapped with the most trajectories of the food delivery section. For example, referring to Figure 5, the rectangular block in the figure is a geographic hash block, where the deeper the gray scale, the more trajectories of the food delivery section have passed, and then the geographic hash block with the deepest gray scale can be determined as the target The geographic hash block, that is, the geographic hash block A in FIG. 5 can be determined as the target geographic hash block.

After determining the target geographic hash block to which the most food delivery segment trajectory is mapped, the coordinates of the center point of the target geographic hash block may be determined as the POI coordinates of the target food delivery address. For example, the coordinates of the center point of the geographic hash block can be determined by the self-contained attributes of the geographic hash block, for example, can be obtained by a specific geohash function. The process is similar to that in the related technology, and will not be repeated here.

In a possible manner, if there are multiple target geographic hash blocks mapped to the trajectory of the most meal delivery section, it can be determined whether the distance between the multiple geographic hash blocks is less than or equal to the first reference distance. If the distance between the multiple geographic hash blocks is less than or equal to the first reference distance, the multiple geographic hash blocks may be determined as the target geographic hash block. Correspondingly, determining the coordinates of the center point of the target geographic hash block as the POI coordinates of the target food delivery address may be: determining the geometric center points of multiple geographic hash blocks, and determining the coordinates of the geometric center point as the target food delivery address POI coordinates of the address.

For example, the first reference distance may be set according to actual conditions, which is not limited in the embodiment of the present disclosure. For example, the first reference distance can be set to 50 meters. In this case, if there are multiple target geographic hash blocks that map the trajectory of the most food delivery segment, then one of the multiple geographic hash blocks can be determined. Is the distance between them less than or equal to 50 meters. If the distance between the multiple geographic hash blocks is less than or equal to 50 meters, the multiple geographic hash blocks may be determined as the target geographic hash block. Then, the coordinates of the geometric center points of the multiple geographic hash blocks are determined as the POI coordinates of the target meal delivery address. In other possible cases, if the distance between a certain geographic hash block and other geographic hash blocks is greater than 50 meters, the geographic hash block can be discarded, and then the coordinates of the geometric center point of the remaining geographic hash blocks are determined as POI coordinates of the target delivery address.

Exemplarily, if the distance between the multiple geographic hash blocks is less than or equal to 50 meters, the multiple geographic hash blocks may be determined as the target geographic hash block, including: if any of the multiple geographic hash blocks If the distance between the two geographic hash blocks is less than or equal to 50 meters, the multiple geographic hash blocks can be determined as the target geographic hash block. Taking three geographic hash blocks X, Y, and Z as an example, if the distance between X and Y is less than or equal to 50 meters, and the distance between X and Z is less than or equal to 50 meters, and the distance between Y and Z If the distance is less than or equal to 50 meters, this embodiment can determine X, Y, and Z as the target geographic hash block.

The method for determining POI coordinates in the embodiments of the present disclosure will be described below through another exemplary embodiment. Referring to Figure 6, the method includes:

Step 601: In historical orders with different food delivery addresses, respectively determine the address coordinates corresponding to the food delivery addresses in the reference map.

Step 602: Determine multiple historical orders within the third reference range of address coordinates as multiple historical orders with the same target delivery address.

Step 603: For the food delivery trajectory of each historical order, remove noise trajectory points whose distances from other trajectory points exceed the second reference distance.

Step 604: For each historical order's food delivery trajectory after removing noise, traverse the food delivery trajectory through a sliding window. Among them, the sliding window includes a reference number of track points.

Step 605: Determine the hexagram limit number of the track point according to the corner information of the track point in the sliding window.

Step 606: If the hexagram limit number of the trajectory point in the sliding window meets the reference hexagram limit number condition, the position information of the trajectory point meets the reference position condition, and the number of trajectory points that are stay points reaches the reference number, determine the trajectory points included in the sliding window The composed trajectory is the trajectory of the delivery section.

Step 607: Map the trajectory of the food delivery section of each historical order to a geographic hash block, and determine the target geographic hash block that has the most trajectories of the food delivery section mapped.

Step 608: Determine the coordinates of the center point of the target geographic hash block as the POI coordinates of the target meal delivery address.

The specific implementation manners of the above steps have been described in detail with examples above, and will not be repeated here. In addition, it should be understood that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the embodiments of the present disclosure are not subject to the sequence of actions described above. limits. Secondly, those skilled in the art should also know that the embodiments described above are exemplary embodiments, and the steps involved are not necessarily required by the embodiments of the present disclosure.

Through the above method, the trajectory of the delivery section of the historical order can be mapped to the geographic hash block, and the target geographic hash block with the most trajectory of the delivery section can be determined, and then the POI of the center point of the target geographic hash block The coordinates are determined as the POI coordinates of the target food delivery address, which reduces the dependence on map services and takeaway check-in data, and can obtain POI coordinates that are closer to the actual food delivery point, and improve the accuracy of determining the POI coordinates.

For example, for the same target meal delivery address, the POI coordinates are determined by the method of returning the coordinates of the map in the related technology, the method of determining the geometric center of the sign-in coordinate, and the method of the embodiment of the present disclosure to determine the POI coordinates, and the results shown in Figures 7 and 8 can be obtained. . Among them, point O in Figure 7 is the target food delivery address, point B is the POI coordinate determined by the way the map returns the coordinates in the related technology, and point C in Figure 7 is determined by the method of determining the sign-in coordinate geometric center in the related technology The POI coordinates. Point D in FIG. 8 is the POI coordinate determined by the method of the embodiment of the disclosure. With reference to Figures 7 and 8, it can be seen that the method in the related art determines that the POI coordinates and the actual location of the target delivery address have a large deviation, and the method in the embodiment of the present disclosure can obtain a POI that is more in line with the actual location of the target delivery address. Coordinates, improve the accuracy of determining POI coordinates.

The method for determining POI coordinates in the embodiments of the present disclosure is described below through another exemplary embodiment, and the method includes:

Step 701: Obtain multiple historical orders with the same target delivery address.

In an exemplary embodiment, acquiring multiple historical orders with the same target food delivery address includes: in the historical orders with different food delivery addresses, respectively determining the address coordinates corresponding to the food delivery address in the reference map. For any address coordinate, multiple historical orders with any address coordinate are determined as multiple historical orders with the same target meal delivery address, and the address coordinate corresponding to the target meal delivery address in the reference map is any address coordinate.

In an exemplary embodiment, acquiring multiple historical orders with the same target food delivery address includes: in the historical orders with different food delivery addresses, respectively determining the address coordinates corresponding to the food delivery address in the reference map. For any address coordinate, multiple historical orders within the third reference range of any address coordinate are determined as multiple historical orders with the same target delivery address, and the address coordinates corresponding to the target delivery address in the reference map are arbitrary An address coordinate.

For the specific implementation of step 701, please refer to the detailed example above, which will not be repeated here.

In step 702, in the food delivery trajectory of each historical order, determine the trajectory of the food delivery section located in the first reference range of the target food delivery address.

For the specific implementation of step 702, please refer to the detailed example above, which will not be repeated here.

Step 703: Determine the target geographic area where the distribution density of the trajectory of the food delivery section of each historical order is the largest.

Exemplarily, in this embodiment, the trajectory of the delivery section of each historical order may be displayed on the map in the form of a line. After that, the area with the highest line density is determined as the target geographic area, and this embodiment does not limit the area or shape of the target geographic area. Alternatively, the target geographic area where the distribution density of the trajectory of the food delivery section is the largest may be: the target geographic hash block exemplified above, and the specific implementation manner for determining the target geographic hash block can be referred to the above description.

Step 704: Determine the POI coordinates of the target meal delivery address based on the coordinates of the target geographic area.

Among them, in this embodiment, the coordinates of any point in the target geographic area may be determined as the POI coordinates of the target meal delivery address. For example, in this embodiment, the center point of the target geographic area may be determined as the POI coordinates of the target meal delivery address. Alternatively, in this embodiment, the coordinates of any point that is offset from the center point of the target geographic area may also be determined as the POI coordinates of the target meal delivery address.

Based on the same inventive concept, embodiments of the present disclosure also provide a device for determining POI coordinates. The device can become part or all of an electronic device (such as a server) through software, hardware, or a combination of the two. Referring to FIG. 9, the device 900 for determining POI coordinates may include:

The obtaining module 901 is configured to obtain multiple historical orders with the same target delivery address;

The first determining module 902 is configured to determine the trajectory of the food delivery section within the first reference range of the target food delivery address in the food delivery trajectory of each historical order;

The second determining module 903 is configured to map the food delivery section trajectory of each historical order to a geographic hash block, and determine the target geographic hash block with the most food delivery section trajectory mapped;

The third determining module 904 is configured to determine the coordinates of the center point of the target geographic hash block as the POI coordinates of the target meal delivery address.

Optionally, the first determining module 902 is configured to:

For the food delivery trajectory of each historical order, traverse the food delivery trajectory through a sliding window, the sliding window including a reference number of trajectory points;

When the characteristic information corresponding to the trajectory points in the sliding window meets a reference condition, it is determined that the trajectory composed of the trajectory points included in the sliding window is the trajectory of the food delivery section, and the characteristic information includes at least one of the following: Position information, speed information and corner information.

Optionally, the first determining module 902 is configured to:

Determine the hexagram limit number of the trajectory point according to the turning angle information of the trajectory point in the sliding window;

When the hexagram limit number of the trajectory point in the sliding window meets the reference hexagram limit number condition, the position information of the trajectory point meets the reference position condition, and the number of trajectory points that are stay points reaches the reference number, determine the trajectory included in the sliding window The trajectory composed of points is the trajectory of the food delivery section, and the stop point is a trajectory point whose speed is less than or equal to a reference speed and the speed of a trajectory point in the second reference range is less than or equal to the reference speed.

Optionally, the first determining module 902 is configured to:

Determine the first target trajectory point in the food delivery trajectory whose speed is less than or equal to the second reference speed, and determine the time difference between the stay point and the target trajectory point to obtain the stay time of the stay point, the stay A point is a track point whose speed is less than or equal to the first reference speed and the speed of the track point in the second reference range is less than or equal to the first reference speed;

Determine the hexagram limit number of the trajectory point according to the turning angle information of the trajectory point in the sliding window;

When the hexagram limit number of the trajectory point in the sliding window meets the reference hexagram limit number condition, the position information of the trajectory point meets the reference position condition, the number of trajectory points that are the stay points reaches the reference number, and the stay duration exceeds the reference duration, It is determined that a trajectory composed of trajectory points included in the sliding window is the trajectory of the food delivery section.

Optionally, the position information of the track point satisfies a reference position condition, including:

On the reference map, the distance between the track point and the target meal delivery address is less than or equal to the first reference threshold; or on the reference map, the distance between the track point and the meal pickup address is greater than or Equal to the second reference threshold.

Optionally, the second determining module 903 is configured to:

When there are multiple target geographic hash blocks mapped with the most food delivery segment trajectory, it is determined whether the distance between the multiple geographic hash blocks is less than or equal to the first reference distance;

When the distance between the multiple geographic hash blocks is less than or equal to the first reference distance, determine the multiple geographic hash blocks as the target geographic hash block; accordingly,

The third determining module 904 is configured to:

The geometric center points of the multiple geographic hash blocks are determined, and the coordinates of the geometric center points are determined as the POI coordinates of the target meal delivery address.

Optionally, the acquiring module 901 is configured to:

In historical orders with different food delivery addresses, respectively determine the address coordinates corresponding to the food delivery addresses in the reference map;

The multiple historical orders with the address coordinates are determined as multiple historical orders with the same target delivery address.

Optionally, the acquiring module 901 is configured to:

In historical orders with different food delivery addresses, respectively determine the address coordinates corresponding to the food delivery addresses in the reference map;

The multiple historical orders within the third reference range of the address coordinates are determined as multiple historical orders with the same target food delivery address.

Optionally, the first determining module 902 is configured to:

For the delivery trajectory of each historical order, remove the noise trajectory points whose distance from other trajectory points exceeds the second reference distance;

In the food delivery trajectory from which the noise trajectory point is removed, the trajectory of the food delivery section located in the first reference range of the target food delivery address is determined.

The embodiment of the present disclosure also provides a device for determining POI coordinates, which includes:

The obtaining module is configured to obtain multiple historical orders with the same target delivery address;

The first determining module is configured to determine the trajectory of the food delivery section within the first reference range of the target food delivery address in the food delivery trajectory of each historical order;

The second determining module is configured to determine the target geographic area where the distribution density of the trajectory of the food delivery section of each historical order is the largest;

The third determining module is configured to determine the POI coordinates of the target meal delivery address based on the coordinates of the target geographic area.

In an exemplary embodiment, the acquiring module is configured to respectively determine the address coordinates corresponding to the food delivery address in the reference map in historical orders with different delivery addresses; for any address coordinate, any address coordinate will be provided The multiple historical orders of are determined as multiple historical orders with the same target delivery address, and the address coordinates corresponding to the target delivery address in the reference map are any address coordinates.

In an exemplary embodiment, the acquiring module is configured to respectively determine the address coordinates corresponding to the food delivery address in the reference map in historical orders with different delivery addresses; for any address coordinates, the first 3. Multiple historical orders within the reference range are determined to be multiple historical orders with the same target delivery address, and the address coordinates corresponding to the target delivery address in the reference map are any address coordinates.

Regarding the device in the foregoing embodiment, the specific manner in which each module performs operation has been described in detail in the embodiment of the method, and detailed description will not be given here.

Based on the same inventive concept, embodiments of the present disclosure also provide an electronic device, including:

A memory on which a computer program is stored;

The processor is configured to execute the computer program in the memory to implement the steps of any of the foregoing methods for determining POI coordinates.

In a possible manner, the block diagram of the electronic device may be as shown in FIG. 10. 10, the electronic device 1000 may be provided as a server, may include a processor 1022, the number of which may be one or more, and a memory 1032 for storing computer programs executable by the processor 1022. The computer program stored in the memory 1032 may include one or more modules each corresponding to a set of instructions. In addition, the processor 1022 may be configured to execute the computer program to execute the aforementioned method for determining POI coordinates.

In addition, the electronic device 1000 may further include a power supply component 1026 and a communication component 1050, the power supply component 1026 may be configured to perform power management of the electronic device 1000, and the communication component 1050 may be configured to implement communication of the electronic device 1000, for example, wired Or wireless communication. In addition, the electronic device 1000 may further include an input/output (I/O) interface 1058. The electronic device 1000 can operate based on an operating system stored in the memory 1032, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM and so on.

In another exemplary embodiment, there is also provided a computer-readable storage medium including program instructions, which, when executed by a processor, implement the steps of the aforementioned method for determining POI coordinates. For example, the computer-readable storage medium may be the foregoing memory 1032 including program instructions, and the foregoing program instructions may be executed by the processor 1022 of the electronic device 1000 to complete the foregoing method for determining POI coordinates.

In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program that can be executed by a programmable device, and the computer program has a function for executing the foregoing when executed by the programmable device. The code part of the method to determine the POI coordinates.

The embodiments of the present disclosure are described in detail above with reference to the accompanying drawings. However, the embodiments of the present disclosure are not limited to the specific details in the above-mentioned embodiments. Within the scope of the technical concept of the embodiments of the present disclosure, the technology of the embodiments of the present disclosure can be compared. Various simple modifications are made to the solution, and these simple modifications all fall within the protection scope of the embodiments of the present disclosure.

In addition, it should be noted that the various specific technical features described in the above-mentioned specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the embodiments of the present disclosure have various The possible combinations are not explained separately.

In addition, various different implementations of the embodiments of the present disclosure can also be combined arbitrarily, as long as they do not violate the idea of the embodiments of the present disclosure, they should also be regarded as the content disclosed in the embodiments of the present disclosure.

Claims (26)

A method for determining POI coordinates, wherein the method includes: Obtain multiple historical orders with the same target delivery address; In the food delivery trajectory of each historical order, determine the trajectory of the food delivery section within the first reference range of the target food delivery address; Map the food delivery section trajectory of each historical order to a geographic hash block, and determine the target geographic hash block that has the most food delivery section trajectory mapped; The coordinates of the center point of the target geographic hash block are determined as the POI coordinates of the target meal delivery address. The method according to claim 1, wherein, in the food delivery trajectory of each historical order, determining the trajectory of the food delivery segment located within the first reference range of the target food delivery address comprises: For the food delivery trajectory of each historical order, traverse the food delivery trajectory through a sliding window, the sliding window including a reference number of trajectory points; If the characteristic information corresponding to the trajectory points in the sliding window meets the reference condition, it is determined that the trajectory composed of the trajectory points included in the sliding window is the trajectory of the food delivery section, and the characteristic information includes at least one of the following: Position information, speed information, and corner information. The method according to claim 2, wherein if the feature information corresponding to the track points in the sliding window meets a reference condition, it is determined that the track composed of the track points included in the sliding window is the delivery delivery Segment trajectory, including: Determine the hexagram limit number of the trajectory point according to the turning angle information of the trajectory point in the sliding window; If the hexagram limit number of the trajectory point in the sliding window meets the reference hexagram limit number condition, the position information of the trajectory point meets the reference position condition, and the number of trajectory points that are stay points reaches the reference number, determine the trajectory included in the sliding window The trajectory composed of points is the trajectory of the food delivery section, and the stop point is the trajectory point whose speed is less than or equal to the first reference speed and the speed of the trajectory point in the second reference range is less than or equal to the first reference speed . The method according to claim 2, wherein if the feature information corresponding to the track points in the sliding window meets a reference condition, it is determined that the track composed of the track points included in the sliding window is the delivery delivery Segment trajectory, including: Determine the first target trajectory point in the food delivery trajectory whose speed is less than or equal to the second reference speed, and determine the time difference between the stay point and the target trajectory point to obtain the stay time of the stay point, the stay A point is a track point whose speed is less than or equal to the first reference speed and the speed of the track point in the second reference range is less than or equal to the first reference speed; Determine the hexagram limit number of the trajectory point according to the turning angle information of the trajectory point in the sliding window; If the hexagram limit number of the trajectory point in the sliding window satisfies the reference hexagram limit number condition, the position information of the trajectory point meets the reference position condition, the number of trajectory points that are the stay point reaches the reference number, and the stay time exceeds the reference time length, then It is determined that a trajectory composed of trajectory points included in the sliding window is the trajectory of the food delivery section. The method according to claim 3 or 4, wherein the position information of the track point satisfies a reference position condition, comprising: On the reference map, the distance between the track point and the target meal delivery address is less than or equal to the first reference threshold; or On the reference map, the distance between the track point and the meal pickup address is greater than or equal to a second reference threshold. The method according to any one of claims 1 to 4, wherein the determining the target geographic hash block mapped with the most trajectory of the food delivery segment comprises: If there are multiple target geographic hash blocks mapped to the trajectory of the most meal delivery section, determining whether the distance between the multiple geographic hash blocks is less than or equal to the first reference distance; If the distance between the multiple geographic hash blocks is less than or equal to the first reference distance, determine the multiple geographic hash blocks as the target geographic hash block; accordingly, The determining the coordinates of the center point of the target geographic hash block as the POI coordinates of the target meal delivery address includes: The geometric center points of the multiple geographic hash blocks are determined, and the coordinates of the geometric center points are determined as the POI coordinates of the target meal delivery address. The method according to any one of claims 1 to 4, wherein said obtaining multiple historical orders with the same target food delivery address comprises: In historical orders with different food delivery addresses, respectively determine the address coordinates corresponding to the food delivery addresses in the reference map; The multiple historical orders with the address coordinates are determined as multiple historical orders with the same target delivery address. The method according to any one of claims 1 to 4, wherein said obtaining multiple historical orders with the same target food delivery address comprises: In historical orders with different food delivery addresses, respectively determine the address coordinates corresponding to the food delivery addresses in the reference map; The multiple historical orders within the third reference range of the address coordinates are determined as multiple historical orders with the same target food delivery address. The method according to any one of claims 1 to 4, wherein, in the food delivery trajectory of each historical order, determining the trajectory of the food delivery segment located within the first reference range of the target food delivery address comprises: For the delivery trajectory of each historical order, remove the noise trajectory points whose distance from other trajectory points exceeds the second reference distance; In the food delivery trajectory from which the noise trajectory point is removed, the trajectory of the food delivery section located in the first reference range of the target food delivery address is determined. A method for determining POI coordinates, wherein the method includes: Obtain multiple historical orders with the same target delivery address; In the food delivery trajectory of each historical order, determine the trajectory of the food delivery section located in the first reference range of the target food delivery address; Determine the target geographic area where the distribution density of the food delivery segment trajectory of each historical order is greatest; The POI coordinates of the target meal delivery address are determined based on the coordinates of the target geographic area. The method according to claim 10, wherein said acquiring multiple historical orders with the same target delivery address comprises: In historical orders with different food delivery addresses, respectively determine the address coordinates corresponding to the food delivery addresses in the reference map; For any address coordinate, multiple historical orders with any one of the address coordinates are determined as multiple historical orders with the same target delivery address, and the target delivery address corresponds to the reference map The address coordinate is any one of the address coordinates. The method according to claim 10, wherein said obtaining multiple historical orders with the same target delivery address comprises: In historical orders with different food delivery addresses, respectively determine the address coordinates corresponding to the food delivery addresses in the reference map; For any address coordinate, multiple historical orders within the third reference range of any one address coordinate are determined as multiple historical orders with the same target delivery address, and the target delivery address is in the reference map The corresponding address coordinate is any one of the address coordinates. A device for determining POI coordinates, wherein the device includes: The obtaining module is configured to obtain multiple historical orders with the same target delivery address; The first determining module is configured to determine the trajectory of the food delivery section within the first reference range of the target food delivery address in the food delivery trajectory of each historical order; The second determining module is configured to map the food delivery section trajectory of each historical order to a geographic hash block, and determine the target geographic hash block with the most food delivery section trajectory mapped; The third determining module is configured to determine the coordinates of the center point of the target geographic hash block as the POI coordinates of the target meal delivery address. The device according to claim 13, wherein the first determining module is configured to traverse the food delivery trajectory through a sliding window for the food delivery trajectory of each historical order, and the sliding window includes a reference number of trajectories Points; when the characteristic information corresponding to the track points in the sliding window meets the reference condition, it is determined that the track composed of the track points included in the sliding window is the trajectory of the food delivery section, and the characteristic information includes at least one of the following People: position information, speed information and corner information. The device according to claim 14, wherein the first determining module is configured to determine the hexagram limit number of the track point according to the turning angle information of the track point in the sliding window; when the track point in the sliding window When the hexagram limit number meets the reference hexagram limit number condition, the position information of the track point meets the reference position condition, and the number of trajectory points that are stay points reaches the reference number, it is determined that the trajectory composed of trajectory points included in the sliding window For the trajectory of the food delivery section, the stop point is a trajectory point whose speed is less than or equal to the reference speed and the speed of the trajectory point in the second reference range is less than or equal to the reference speed. The device according to claim 14, wherein the first determining module is configured to determine a first target trajectory point in the food delivery trajectory whose speed is less than or equal to a second reference speed, and to determine the stay point and the The time difference between the target trajectory points to obtain the stay time of the stay point, the stay point is that the speed is less than or equal to the first reference speed, and the speed of the trajectory point in the second reference range is less than or equal to the first reference speed According to the corner information of the track point in the sliding window, determine the hexagram limit number of the track point; when the hexagram limit number of the track point in the sliding window meets the reference hexagram limit number condition, the position information of the track point When the reference position condition is met, the number of trajectory points for the stay point reaches the reference number, and the stay duration exceeds the reference duration, it is determined that the trajectory composed of trajectory points included in the sliding window is the trajectory of the food delivery section. The device according to claim 15 or 16, wherein the location information of the track point satisfies a reference location condition, comprising: on a reference map, the distance between the track point and the target meal delivery address is less than or equal to A first reference threshold; or on the reference map, the distance between the track point and the meal pickup address is greater than or equal to the second reference threshold. The apparatus according to any one of claims 13-16, wherein the second determining module is configured to determine the plurality of geographic hash blocks when there are multiple target geographic hash blocks mapped with the most trajectory of the food delivery section. Whether the distance between the hash blocks is less than or equal to the first reference distance; when the distance between the multiple geographic hash blocks is less than or equal to the first reference distance, determine the multiple geographic hash blocks Is the target geographic hash block; accordingly, The third determining module is configured to determine the geometric center points of the multiple geographic hash blocks, and determine the coordinates of the geometric center points as the POI coordinates of the target meal delivery address. The device according to any one of claims 13-16, wherein the acquisition module is configured to determine the address coordinates corresponding to the meal delivery address in a reference map in historical orders with different meal delivery addresses; The multiple historical orders with the address coordinates are determined to be multiple historical orders with the same target delivery address. The device according to any one of claims 13-16, wherein the acquisition module is configured to determine the address coordinates corresponding to the meal delivery address in a reference map in historical orders with different meal delivery addresses; The multiple historical orders within the third reference range of the address coordinates are determined to be multiple historical orders with the same target food delivery address. The device according to any one of claims 13-16, wherein the first determining module is configured to remove the noise trajectory points whose distance from other trajectory points exceeds a second reference distance for the food delivery trajectory of each historical order In the food delivery trajectory where the noise trajectory point is removed, the trajectory of the delivery section of the food delivery within the first reference range of the target food delivery address is determined. A device for determining POI coordinates, wherein the device includes: The obtaining module is configured to obtain multiple historical orders with the same target delivery address; The first determining module is configured to determine the trajectory of the food delivery section within the first reference range of the target food delivery address in the food delivery trajectory of each historical order; The second determining module is configured to determine the target geographic area where the distribution density of the food delivery section trajectory of each historical order is the largest; The third determining module is configured to determine the POI coordinates of the target meal delivery address based on the coordinates of the target geographic area. The device according to claim 22, wherein the acquisition module is configured to determine the address coordinates corresponding to the meal delivery address in the reference map in historical orders with different meal delivery addresses; for any address Coordinates, multiple historical orders with any one of the address coordinates are determined as multiple historical orders with the same target food delivery address, and the address coordinates corresponding to the target food delivery address in the reference map are all Describe any address coordinate. The device according to claim 22, wherein the acquisition module is configured to determine the address coordinates corresponding to the meal delivery address in the reference map in historical orders with different meal delivery addresses; for any address Coordinates, the multiple historical orders within the third reference range of any one of the address coordinates are determined as multiple historical orders with the same target delivery address, and the address coordinates of the target delivery address in the reference map Is any one of the address coordinates. A computer-readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to realize the steps of the method according to any one of claims 1-12. An electronic device, including: A memory on which a computer program is stored; The processor is configured to execute the computer program in the memory to implement the steps of the method in any one of claims 1-12.

Images