CN112990548B - Position point determining method, device, electronic equipment and readable storage medium - Google Patents
Position point determining method, device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN112990548B CN112990548B CN202110172549.9A CN202110172549A CN112990548B CN 112990548 B CN112990548 B CN 112990548B CN 202110172549 A CN202110172549 A CN 202110172549A CN 112990548 B CN112990548 B CN 112990548B
- Authority
- CN
- China
- Prior art keywords
- probability
- road
- candidate
- determining
- position point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000011156 evaluation Methods 0.000 claims description 29
- 239000013598 vector Substances 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 18
- 230000006399 behavior Effects 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 31
- 230000008569 process Effects 0.000 description 16
- 230000006870 function Effects 0.000 description 12
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 5
- 238000013507 mapping Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012854 evaluation process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000004148 curcumin Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 230000003238 somatosensory effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/3438—Rendez-vous, i.e. searching a destination where several users can meet, and the routes to this destination for these users; Ride sharing, i.e. searching a route such that at least two users can share a vehicle for at least part of the route
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0645—Rental transactions; Leasing transactions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Finance (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Navigation (AREA)
Abstract
The embodiment of the application provides a position point determining method, a device, electronic equipment and a readable storage medium, which relate to the technical field of computers.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a location point determining method, a location point determining device, an electronic device, and a readable storage medium.
Background
Currently, with the development of internet technology, many offline services provide online and offline functions, for example, a user may order on an express platform through a terminal device (such as a smart phone) and then send the express to a designated place when sending the express. For another example, when the user takes a car, the user can place an order on the network about car platform through the terminal device, and then go to a designated car-on point to wait for the network about car.
In this process, after the user places an order, it is often necessary to go to a designated location point for the arrival of an offline service person, where the designated location point is generally recommended by the service platform.
However, if the recommended location point of the service platform is located on the opposite side of the road where the user is located, the user will be inconvenienced to a certain extent, and therefore, how to select the preferred recommended location point is a problem to be solved.
Disclosure of Invention
In view of this, embodiments of the present application provide a location point determining method, apparatus, electronic device, and readable storage medium, which can determine a more preferable target location point.
In a first aspect, a location point determining method is provided, where the method is applied to an electronic device, and the method includes:
And determining the current ordering positioning of the target terminal in response to receiving an ordering request sent by the target terminal.
At least one candidate location point is determined based on the current order location.
And determining the crossing probability and/or the non-crossing probability of each candidate position point, wherein the crossing probability is used for representing the probability that the target terminal crosses the road to the corresponding candidate position point after sending the ordering request, and the non-crossing probability is used for representing the probability that the target terminal does not cross the road to the corresponding candidate position point after sending the ordering request.
And determining the evaluation of each candidate position point based on the current order positioning, the at least one candidate position point and the cross-road probability and/or the non-cross-road probability of each candidate position point.
Based on the evaluation of each candidate position point, a target position point is determined among the candidate position points.
In a second aspect, there is provided a location point determining apparatus, the apparatus being applied to an electronic device, the apparatus comprising:
And the current ordering and positioning module is used for determining the current ordering and positioning of the target terminal in response to receiving an ordering request sent by the target terminal.
And the candidate position point module is used for determining at least one candidate position point based on the current ordering positioning.
The probability module is used for determining the cross-road probability and/or the non-cross-road probability of each candidate position point, wherein the cross-road probability is used for representing the probability that the target terminal crosses the road to the corresponding candidate position point after sending the ordering request, and the non-cross-road probability is used for representing the probability that the target terminal does not cross the road to the corresponding candidate position point after sending the ordering request.
And the evaluation module is used for determining the evaluation of each candidate position point based on the current order positioning, the at least one candidate position point and the cross-road probability and/or the non-cross-road probability of each candidate position point.
And a target location point module for determining a target location point among the candidate location points based on the evaluation of the candidate location points.
In a third aspect, an embodiment of the present application provides an electronic device, including a memory and a processor, the memory storing one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method as described in the first aspect.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement a method according to the first aspect.
In a fifth aspect, embodiments of the present application provide a computer program product comprising a computer program/instruction which, when executed by a processor, implements a method as described in the first aspect.
According to the embodiment of the application, the target position point can be determined based on the current order positioning, at least one candidate position point and the cross-road probability and/or the non-cross-road probability of each candidate position point, wherein the cross-road probability can represent the probability that the target terminal crosses the road to the corresponding candidate position point after sending the order request, the non-cross-road probability can represent the probability that the target terminal does not cross the road to the corresponding candidate position point after sending the order request, so the cross-road probability and/or the non-cross-road probability can represent the general cross-road willingness, and further, the more preferable target position point can be determined based on the general cross-road willingness.
Drawings
The above and other objects, features and advantages of embodiments of the present application will become more apparent from the following description of embodiments of the present application with reference to the accompanying drawings, in which:
FIG. 1 is a schematic diagram of a recommended get-on point according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a display interface including a recommended get-on point according to an embodiment of the present application;
fig. 3 is a schematic diagram of an application scenario of a location point determining method according to an embodiment of the present application;
FIG. 4 is a flowchart of a method for determining a location point according to an embodiment of the present application;
FIG. 5 is a flowchart of another method for determining a location point according to an embodiment of the present application;
FIG. 6 is a flowchart of another method for determining a location point according to an embodiment of the present application;
Fig. 7 is a schematic diagram of a service generating process according to an embodiment of the present application;
FIG. 8 is a schematic diagram of another business generation process according to an embodiment of the present application;
Fig. 9 is a schematic diagram of another service generating process according to an embodiment of the present application;
FIG. 10 is a schematic diagram of another business generation process according to an embodiment of the present application;
FIG. 11 is a schematic diagram of determining a second historical order location according to an embodiment of the present application;
FIG. 12 is a schematic diagram of an evaluation process for determining candidate location points according to an embodiment of the present application;
Fig. 13 is a schematic structural diagram of a location point determining device according to an embodiment of the present application;
fig. 14 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The present application is described below based on examples, but the present application is not limited to only these examples. In the following detailed description of the present application, certain specific details are set forth in detail. The present application will be fully understood by those skilled in the art without the details described herein. Well-known methods, procedures, flows, components and circuits have not been described in detail so as not to obscure the nature of the application.
Moreover, those of ordinary skill in the art will appreciate that the drawings are provided herein for illustrative purposes and that the drawings are not necessarily drawn to scale.
Unless the context clearly requires otherwise, the words "comprise," "comprising," and the like in the description are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, it is the meaning of "including but not limited to".
In the description of the present application, it should be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Furthermore, in the description of the present application, unless otherwise indicated, the meaning of "a plurality" is two or more.
Currently, with the development of internet technology, many offline services provide online and offline functions, for example, a user may order on an express platform through a terminal device (such as a smart phone) and then send the express to a designated place when sending the express. For another example, when the user takes a car, the user can place an order on the network about car platform through the terminal device, and then go to a designated car-on point to wait for the network about car.
In this process, after the user places an order, it is often necessary to go to a designated location point for the arrival of an offline service person, where the designated location point is generally recommended by the service platform.
Taking a network taxi-taking scene as an example, as shown in fig. 1, fig. 1 is a schematic diagram of a recommended taxi-taking point according to an embodiment of the present application, where the schematic diagram includes: the user 11, the road 12, the candidate get-on points a, the candidate get-on points B and the candidate get-on points C respectively located on both sides of the road 12.
After the user 11 performs the network taxi-booking service ordering through the terminal device such as the smart phone, the network taxi-booking platform can determine one taxi-booking point from a plurality of candidate taxi-booking points as a recommended taxi-booking point according to the current position of the user 11, and as shown in fig. 1, the candidate taxi-booking point a, the candidate taxi-booking point B and the candidate taxi-booking point C are 3 candidate taxi-booking points determined by the network taxi-booking platform.
After the network taxi taking platform determines the recommended taxi taking point from the 3 candidate taxi taking points, the user 11 can walk to the recommended taxi taking point according to the recommended route displayed in the display interface of the terminal equipment, however, if the taxi taking point recommended by the network taxi taking platform is located on the opposite side of the road where the user is located, inconvenience is caused to the user to a certain extent.
For example, as shown in fig. 2, fig. 2 is a schematic diagram of a display interface including a recommended get-on point according to an embodiment of the present application, where the schematic diagram includes: a recommended route 21, a road 22, a recommended get-on point A and a net appointment-made car prompt box 23.
When the user uses the network taxi service, if the taxi-taking point recommended by the network taxi-taking platform is located on the opposite side of the road where the user is located (i.e. the location where the taxi-taking point recommended in fig. 2 is located), the user needs to travel to the taxi-taking point recommended in the way of crossing the road 22, as shown in fig. 2, and the user needs to travel to the taxi-taking point recommended in the way of crossing the road 22 according to the path 21 recommended by the recommended path 21, and waits for the network taxi-taking driver through the overpass, which causes inconvenience to the user to a certain extent, so how to select a more suitable taxi-taking point recommended is a problem to be solved.
In order to solve the above-mentioned problems, an embodiment of the present application provides a location point determining method to determine a more preferable target location point, where the method may be applied to an electronic device, and the electronic device may be a terminal or a server, and the terminal may be a smart phone, a tablet computer, a personal computer (Personal Computer, PC), or the like, and the server may be a single server, a server cluster configured in a distributed manner, or a cloud server.
For example, as shown in fig. 3, fig. 3 is a schematic diagram of an application scenario of a location point determining method according to an embodiment of the present application, where the schematic diagram includes: a terminal 31 and an electronic device 32 as a service terminal.
In the embodiment of the present application, the user may make an order through the terminal 31, and after the user makes an order, the terminal 31 may send an order request to the electronic device 32 through the network. The terminal 31 may be a smart phone installed with a specific application (e.g., a network bus service passenger application), or may be another terminal installed with a specific application, and the electronic device 32 is a device as a service, which is typically a server, but may also be a terminal in some cases.
When the electronic device 32 receives the order request sent by the terminal 31, the target location point may be determined according to the order request.
Specifically, as shown in fig. 4, fig. 4 is a flowchart of a location point determining method according to an embodiment of the present application.
As shown in fig. 4, after the electronic device receives the order request 41, it may determine the current order location 42 of the target terminal that sends the order request 41, in practical application, a part of specific application programs (for example, network bus service passenger end application programs) need to obtain location information of the target terminal (that is, the terminal running the specific application program) in the running process, so as to normally provide corresponding services, for example, in the embodiment of the present application, after the electronic device receives the order request sent by the target terminal, the electronic device may obtain the current order location of the target terminal, and further may provide services such as recommended boarding points, recommended paths, and so on for the user according to the order location.
After determining the current ordering position 42 of the target terminal, a plurality of candidate position points (i.e., candidate position points 1-n in fig. 4) may be determined according to the current ordering position 42, where the candidate position points may be all candidate position points near the current ordering position 42 or may be part of candidate position points near the current ordering position 42.
After determining each candidate location point, a cross-road probability and/or a non-cross-road probability (i.e., cross-road probabilities 431-43 n) corresponding to each candidate location point may be determined, where the cross-road probability is used to characterize a probability that the target terminal crosses the road to the corresponding candidate location point after sending the order request, and the non-cross-road probability is used to characterize a probability that the target terminal does not cross the road to the corresponding candidate location point after sending the order request.
After determining the cross-road probability and/or the non-cross-road probability for each candidate location point, the target location point 44 may be determined based on the current order location 42, the candidate location points, and the cross-road probability and/or the non-cross-road probability for each candidate location point.
According to the embodiment of the application, the target position point can be determined based on the current order positioning, at least one candidate position point and the cross-road probability and/or the non-cross-road probability of each candidate position point, wherein the cross-road probability can represent the probability that the target terminal crosses the road to the corresponding candidate position point after sending the order request, the non-cross-road probability can represent the probability that the target terminal does not cross the road to the corresponding candidate position point after sending the order request, so the cross-road probability and/or the non-cross-road probability can represent the general cross-road willingness, and further, the more preferable target position point can be determined based on the general cross-road willingness.
The following will describe a detailed description of a location point determining method according to an embodiment of the present application with reference to a specific embodiment, as shown in fig. 5, and the specific steps are as follows:
In step 51, in response to receiving the order request sent by the target terminal, the current order location of the target terminal is determined.
The order request may be used to request a service, for example, in a network about a car, the order request may be a request for requesting a calling service, and the electronic device may push a preferred target location point for the target terminal according to the current order location, so as to recommend the user to get on the target location point.
For another example, in a scenario of sending an express delivery, the order request may be a request for requesting an express delivery service, the user may order the express delivery platform through the target terminal, and the electronic device may push a preferred target location point for the target terminal according to the current order location, so as to recommend the user to wait for the express delivery member to pick up the express delivery member at the target location point.
At step 52, at least one candidate location point is determined based on the current order location.
The candidate location points may be all candidate location points near the current order location, or may be part of candidate location points near the current order location.
In an alternative embodiment, step 52 may be performed as: and determining a candidate position point list corresponding to the current ordering positioning, and determining a preset number of candidate position points in the candidate position point list.
The preset number may be a natural number set according to actual situations, or may be equal to the number of location points in the candidate location point list.
In the embodiment of the present application, the candidate location point list may include each candidate location point within a predetermined distance from the current position, where the predetermined distance may be a preset distance according to the actual situation, for example, 100 meters, 150 meters, and so on.
For example, as shown in the following table one, a schematic diagram of a candidate location point list provided in an embodiment of the present application is specifically as follows:
List one
Location point | Distance (Rice) | Recommendation index |
A | 75 | 30 |
B | 80 | 40 |
C | 60 | 70 |
D | 50 | 100 |
E | 100 | 50 |
Wherein table one includes 5 location points (i.e., A, B, C, D and E), and each of the 5 location points corresponds to a recommendation index, where the recommendation index is used to represent a recommended level value of the corresponding location point, and the higher the recommendation index is, the higher the recommended level of the corresponding location point is, and conversely, the lower the recommendation index is, the lower the recommended level of the corresponding location point is.
In one case, after determining the candidate location point list corresponding to the current positioning, all the location points in the list may be used as candidate location points, for example, in table one, and after determining the candidate location point list corresponding to the current positioning, all the location points A, B, C, D and E shown in table one may be used as candidate location points.
In another case, after determining the list of candidate location points corresponding to the current order location, a part of the location points in the list may be used as the candidate location points.
For example, as shown in table one, after determining the candidate location point list corresponding to the current order location, a preset number of location points before the recommendation index ranking may be determined as candidate location points, and if the location point with the recommendation index ranking of 3 is selected as the candidate location point, the location points D, C and E in table one are selected as candidate location points.
At step 53, the probability of crossing and/or the probability of not crossing each candidate location point is determined.
The cross-road probability is used for representing the probability that the target terminal crosses the road to the corresponding candidate position point after sending the order request, and the non-cross-road probability is used for representing the probability that the target terminal does not cross the road to the corresponding candidate position point after sending the order request.
In the embodiment of the present application, the probability of crossing the road and/or the probability of not crossing the road of each candidate location point may be a predetermined probability, or may be a probability determined in real time after each candidate location point is determined.
In an alternative embodiment, as shown in fig. 6, the probability of a candidate location point crossing/probability of not crossing may be determined based on the following steps:
at step 61, at least one historical order with candidate location points as recommended locations is obtained.
Wherein, the historical order may be an order with the candidate location point as the recommended location in the past period of time, such as the past year, two years, three years, and so on. The historical order comprises a first historical order positioning, the candidate position point and a historical service occurrence position point when the historical order is placed, wherein the historical service occurrence position point is at least used for representing the actual service occurrence position of the target terminal.
In an embodiment of the present application, the historical order may include: the recommended location point (i.e., the candidate location point in step 61) is on the same side of the road as the place of placement of the historical order (i.e., the first historical place of placement location), and the user does not cross the road to arrive at the historical order of the actual business occurrence location (i.e., the historical business occurrence location point); the recommended position point is positioned on the same side of the road as the position of the historical order, and the user crosses the road to reach the historical order of the actual business occurrence position; the recommended position point and the next position of the historical order are positioned on different sides of the road, and the user does not cross the road to reach the historical order of the actual business occurrence position; the recommended location point is on a different side of the road than the place of placement of the historical order, and the user crosses the road to arrive at the historical order of the actual business occurrence location.
For example, as shown in fig. 7, fig. 7 is a schematic diagram of a service generating process according to an embodiment of the present application, where the schematic diagram includes: a user 71, a road 72, an actual business occurrence location 73, and a recommended location point a for the historical order.
In fig. 7, the position of the user 71, that is, the first history order location when the history order is placed, is shown in the user 71.
The actual service occurrence position 73 is a service occurrence position, that is, a historical service occurrence position point of the historical order, taking a network about car scene as an example, the actual service occurrence position 73 is a position of a user 71 getting on a car, taking an express scene as an example, and the actual service occurrence position 73 is a position of an express delivery person for collecting express delivery.
The recommended location point a is a location recommended by the electronic device according to the order placing request of the historical order after the corresponding historical order is placed, that is, the candidate location point in step 61.
As shown in fig. 7, after the user 71 places an order, the electronic device provides a recommended location point a for the user 71 according to the placing request, but the actual service occurrence location of the historical order is the actual service occurrence location 73, that is, the historical order shown in fig. 7 is a historical order in which the recommended location point is on a different side of the road from the place of the historical order, and the user does not reach the actual service occurrence location across the road.
As another example, as shown in fig. 8, fig. 8 is a schematic diagram of another service generating process according to an embodiment of the present application, where the schematic diagram includes: a user 81, a road 82, an actual business occurrence location 83, and a recommended location point B for the historical order.
In fig. 8, the location of the user 81, that is, the first history order location when the history order is placed, is shown in the user 81 who places the order through the terminal. The actual service occurrence location 83 is the location where the service occurs, i.e., the historical service occurrence location point of the historical order. The recommended location point B is a location recommended by the electronic device according to the order placing request of the historical order after the corresponding historical order is placed, that is, the candidate location point in step 61.
As shown in fig. 8, after the user 81 places an order, the electronic device provides a recommended location point B for the user 81 according to the request for placing an order, and the actual service occurrence location of the historical order is an actual service occurrence location 83, that is, the historical order shown in fig. 8 is a historical order in which the recommended location point is located on a different side of the road from the place of placing the historical order, and the user arrives at the actual service occurrence location across the road.
In addition, as shown in fig. 8, although the recommended location point B does not actually generate the business, the user 81 is moving across the road to the actual business generation location 83, and therefore, the historical order shown in fig. 8 is still a historical order in which the recommended location point is located on a different side of the road from the next location of the historical order, and the user arrives at the actual business generation location across the road.
As another example, as shown in fig. 9, fig. 9 is a schematic diagram of another service generating process according to an embodiment of the present application, where the schematic diagram includes: a user 91, a road 92, an actual business occurrence location 93, and a recommended location point C for the historical order.
In fig. 9, the position of the user 91, that is, the first history order location when the history order is placed, is shown in the user 91 who places the order through the terminal. The actual service occurrence location 93 is the location where the service occurs, i.e., the historical service occurrence location point of the historical order. The recommended location point C is a location recommended by the electronic device according to the order placing request of the historical order after the corresponding historical order is placed, that is, the candidate location point in step 61.
As shown in fig. 9, after the user 91 places an order, the electronic device provides a recommended location point C for the user 91 according to the placing request, and the actual service occurrence location of the historical order is an actual service occurrence location 93, that is, the historical order shown in fig. 9 is a historical order in which the recommended location point is on the same side of the road as the place where the historical order is placed, and the user does not reach the actual service occurrence location across the road.
In addition, it should be noted that, if the actual service occurrence position 93 is not located at the recommended position point C, but the actual service occurrence position 93 is still located at the same side of the road as the user 91, the historical order shown in fig. 9 is still a historical order in which the recommended position point is located at the same side of the road as the next position of the historical order, and the user does not cross the road to reach the actual service occurrence position.
As another example, as shown in fig. 10, fig. 10 is a schematic diagram of another service generating process according to an embodiment of the present application, where the schematic diagram includes: a user 101, a road 102, an actual business occurrence location 103, and a recommended location point D for the historical order.
In fig. 10, the location of the user 101, that is, the first history order location when the history order is placed, is shown as the position of the user 101. The actual service occurrence location 103 is the location where the service occurs, i.e. the historical service occurrence location point of the historical order. The recommended location point D is a location recommended by the electronic device according to the order placing request of the historical order after the corresponding historical order is placed, that is, the candidate location point in step 61.
As shown in fig. 10, after the user 101 places an order, the electronic device provides a recommended location point D for the user 101 according to the placing request, and the actual service occurrence location of the historical order is the actual service occurrence location 103, that is, the historical order shown in fig. 10 is a historical order in which the recommended location point is on the same side of the road as the place of the historical order, and the user arrives at the actual service occurrence location across the road.
At step 62, the probability of crossing/not crossing of the candidate location point is determined based on the first historical order location, the candidate location point, and the historical traffic occurrence location point statistics.
As can be seen from the foregoing descriptions of fig. 7 to 10, the positioning of the arrival history service occurrence point from the first history order by the user can be specifically divided into 4 cases: in the first case, the recommended location point (i.e. the candidate location point in step 61) is located on the same side of the road as the first historical order location, and the user does not cross the road to reach the actual business occurrence location; in the second case, the recommended position point and the first historical order are positioned on the same side of the road, and the user crosses the road to reach the actual business occurrence position; in the third case, the recommended position point and the first historical order positioning are positioned at different sides of the road, and the user does not cross the road to reach the actual business occurrence position; in the fourth case, the recommended location point is located on a different side of the road than the first historical order location, and the user crosses the road to reach the actual business occurrence location.
Further, in an alternative embodiment, a cross-road event corresponding to each historical order using the candidate location point in step 61 as the recommended location may be generated based on the 4 cases, and then the cross-road probability or the non-cross-road probability of the candidate location point may be determined based on each cross-road event.
Specifically, step 62 may be performed as: generating a crossing event corresponding to the historical order according to the first historical order positioning, the candidate position points and the historical service occurrence position points, and determining the crossing probability/non-crossing probability of the candidate position points based on the Bayesian formula and the crossing event corresponding to each historical order.
Wherein, when the cross-road event is used for representing the service occurrence of the historical order, the occurrence/non-occurrence of the cross-road behavior is generated, that is, each cross-road event can be used for representing one of the 4 conditions.
The bayesian formula, which is a tool in statistics and can describe the relationship between two conditional probabilities based on the frequency of occurrence of an event, can be also called Bayes Rule (Bayes Rule), and can be specifically as follows:
Wherein A and B are used for representing the event, P (A) is used for representing the prior probability of the event A (i.e. the probability of occurrence of the event A without considering the event B), P (B) is used for representing the prior probability of the event B (i.e. the probability of occurrence of the event B without considering the event A), P (A|B) is used for representing the conditional probability of the event A after the occurrence of the known event B (i.e. the probability of occurrence of the event A on the premise of occurrence of the event B), and P (B|A) is used for representing the conditional probability of the event B after the occurrence of the known event A (i.e. the probability of occurrence of the event B on the premise of occurrence of the event A).
Furthermore, the bayesian formula and the statistical data for the 4 cases can be combined to determine the probability of crossing the road or the probability of not crossing the road of the candidate position point.
For example, as shown in the following table two, the table two is a statistical table of occurrence frequency of a cross-road event provided by the embodiment of the present application, which is specifically as follows:
Watch II
Furthermore, the above 4 cases (i.e., case one to case four) may be calculated based on the events shown in table two, the frequency corresponding to each event, and the bayesian formula.
For the first case (the recommended location point is located on the same side of the road as the first historical order location, and the user does not cross the road to reach the actual service occurrence location), the probability of the first case can be determined according to the table two and the bayesian formula, which is specifically as follows:
For the second case (the recommended location point is located on the same side of the road as the first historical order location, and the user crosses the road to reach the actual service occurrence location), the probability of the second case can be determined according to the table two and the bayesian formula, specifically as follows:
For the third case (the recommended location point is located on a different side of the road from the first historical order location, and the user does not cross the road to reach the actual service occurrence location), the probability of occurrence of the third case can be determined according to the table two and the bayesian formula, specifically as follows:
for the fourth case (the recommended location point is located at a different side of the road from the first historical order location, and the user crosses the road to reach the actual service occurrence location), the probability of occurrence of the fourth case can be determined according to the table two and the bayesian formula, specifically as follows:
In another alternative embodiment, the probabilities of occurrence of the 4 cases may also be calculated directly based on statistical data, for example, as shown in table two, on the premise that the number of historical orders is 100, the first case occurs 50 times, and the second case occurs 10 times, because the first case and the second case are both events occurring under the condition that the recommended location point is located on the same side of the road as the first historical order, and thus the probability of occurrence of the first case is: 50 ≡ (50+10) =83.3%. Similarly, the probabilities of occurrence of the second to fourth cases can be sequentially calculated through statistical data.
As can be seen from the above steps, each candidate location point may correspond to a plurality of road crossing probabilities or a plurality of non-road crossing probabilities, for example, for any candidate location point X, the embodiment of the present application may determine the road crossing probability (corresponding to the second case) or the non-road crossing probability (corresponding to the first case) when the candidate location point X and the current order location are on the same side of the road, and may determine the road crossing probability (corresponding to the fourth case) or the non-road crossing probability (corresponding to the third case) when the candidate location point X and the current order location are on different sides of the road. That is, candidate location point X may correspond to 4 probabilities (including 2-way probabilities and 2-way-non-probability).
Furthermore, in determining the cross-road probability and/or the non-cross-road probability of each candidate position point, the embodiment of the application can determine the position relation between each candidate position point and the current ordering positioning first, and then determine the cross-road probability and/or the non-cross-road probability of each candidate position point according to the position relation. Specifically, the step 53 may be performed as follows: determining the position relation between the current ordering location and each candidate position point, and determining the cross-road probability and/or the non-cross-road probability of each candidate position point based on the position relation.
The position relation is used for representing that the current order positioning and the candidate position point are positioned on the same side of the road, or the current order positioning and the candidate position point are positioned on different sides of the road. In particular, reference may be made to fig. 7-10 described above.
According to the embodiment of the application, the cross-road probability or the non-cross-road probability of the candidate position point can be determined based on the cross-road event corresponding to each historical order, wherein the event corresponding to the historical order is a real occurrence order, so that the cross-road probability or the non-cross-road probability of the candidate position point can be determined more accurately based on the real occurrence event.
In an alternative embodiment, if the first historical order positioning has a drift or other problem due to objective reasons, the first historical order positioning may be corrected by translation or other manners, so as to obtain more accurate positioning data.
Specifically, the step 62 may be performed as follows: and translating the first historical order positioning to one side of the road according to the road position information to determine a second historical order positioning, and determining the road crossing probability/non-road crossing probability of the candidate position point according to the second historical order positioning, the candidate position point and the statistics of the historical service occurrence position point.
For example, as shown in fig. 11, fig. 11 is a schematic diagram of determining a second historical order location according to an embodiment of the present application, where the schematic diagram includes: user 111, road 112, location point A1, and location point A2.
The location of the user 111 is the first historical order location in the historical order, and as can be seen from fig. 11, the first historical order location is not located on any side of the road, that is, the cross-road event cannot be generated according to the first historical order location. Therefore, in the embodiment of the present application, the first historical order positioning may be translated to one side of the road to determine the second historical order positioning, and as can be seen from fig. 11, the second historical order positioning may be the location point A1 or the location point A2.
In the embodiment of the application, when the first historical order positioning is not positioned on any side of the road, the embodiment of the application can translate the first historical order positioning to one side of the road and determine the second historical order positioning, thereby ensuring that a road crossing event can be generated in the process of determining the road crossing probability or the non-road crossing probability.
And after determining the second historical order positioning, determining the crossing probability/non-crossing probability of the candidate position point according to the second historical order positioning, the candidate position point and the statistics of the historical service occurrence position point.
Specifically, the process may be performed as: generating a crossing event corresponding to the historical order according to the second historical order positioning, the candidate position points and the historical service occurrence position points, and determining the crossing probability/non-crossing probability of the candidate position points based on the Bayesian formula and the crossing event corresponding to each historical order.
The process is similar to the cross-road probability or the non-cross-road probability of the candidate location point determined by the first historical order positioning, and the embodiments of the present application are not described herein.
At step 54, an evaluation of each candidate location point is determined based on the current order location, at least one candidate location point, and the probability of crossing and/or the probability of not crossing each candidate location point.
In an alternative embodiment, the evaluation of each candidate location point may be determined based on the size of the probability of crossing or the probability of not crossing, e.g., the smaller the probability of crossing a certain candidate location point, the higher the evaluation of the candidate location point, and further, the larger the probability of not crossing a certain candidate location point, the higher the evaluation of the candidate location point.
In another alternative embodiment, step 54 may be performed as: determining the distance between the current ordering location and each candidate position point, determining a plurality of target distances, determining a first feature vector corresponding to each target distance, determining a crossing probability of each candidate position point and/or a second feature vector corresponding to a non-crossing probability, inputting each first feature vector and each second feature vector into a pre-trained deep neural network (Deep Neural Networks, DNN) model, and determining the evaluation of each candidate position point.
The DNN model is a model in the machine learning field, and in the embodiment of the present application, the DNN model may be a Deep & Cross Network (DCN) with multiple head optimization.
The DCN model comprises a deep network and a cross network, can effectively capture the interaction of the features, learn the interaction of the highly nonlinear features, does not need manual feature engineering or traversal search, and has lower calculation cost.
Specifically, as shown in fig. 12, fig. 12 is a schematic diagram of an evaluation process for determining each candidate location point according to an embodiment of the present application, where the schematic diagram includes: current order location 121, candidate location points 122, cross-road and/or non-cross-road probabilities 123, target distance 124, first feature vector 125, second feature vector 126, DCN model 127, and evaluation 128 of each candidate location point.
In this process, after the electronic device determines each candidate location point 122 corresponding to the current position 121, a distance between the current position 121 and each candidate location point 122, that is, the target distance 124, may be determined.
In addition, the electronic device may also determine a cross-road probability and/or a non-cross-road probability 123 corresponding to each candidate location point 122.
Specifically, after determining the current position 121 and each candidate position point 122, the position relationship between each candidate position point 122 and the current position 121 is determined, in general, some candidate position points 122 are located on different sides of the road where the current position 121 is located, and some candidate position points 122 are located on the same side of the road where the current position 121 is located. Of course, in some cases, there are cases where the candidate location points 122 are all located on different sides of the road on which the current order location 121 is located, and there are cases where the candidate location points 122 are all located on the same side of the road on which the current order location 121 is located.
After determining the positional relationship between each candidate location point 122 and the current ordering location 121, the cross-road probability and/or the non-cross-road probability 123 corresponding to each candidate location point 122 may be determined based on the cross-road probabilities or the non-cross-road probabilities determined for the 4 cases in step 62. For example, if a certain candidate location point 122 is located on a different side of the road on which the current position 121 is located, the third case and the fourth case are corresponding at this time, and then the probability of crossing the road (i.e., the probability corresponding to the fourth case) or the probability of not crossing the road (i.e., the probability corresponding to the third case) corresponding to the candidate location point 122 can be determined.
After the electronic device determines the target distances 124 and the cross probabilities and/or non-cross probabilities 123, the target distances 124 and the cross probabilities and/or non-cross probabilities 123 may be embedded embedding to determine the first feature vectors 125 and the second feature vectors 126.
Wherein embedding is a feature extraction method commonly used in deep learning, specifically, feature extraction is to map high-dimensional original data (images, characters, etc.) to a low-dimensional Manifold (Manifold), so that the high-dimensional original data becomes separable after being mapped to the low-dimensional Manifold, and the mapping process can be called embedding.
In the embodiment of the present application, each target distance 124 and each cross-road probability and/or non-cross-road probability 123 are data of a numerical class, and through embedding processing, each target distance 124 and each cross-road probability and/or non-cross-road probability 123 may be mapped as a feature vector, so as to determine each first feature vector 125 and each second feature vector 126.
After determining each first feature vector 125 and each second feature vector 126, each first feature vector 125 and each second feature vector 126 may be input into a pre-trained DCN model to determine an evaluation 128 of each candidate location point.
The evaluation 128 of each candidate location point may be represented by a numerical value, a percentage, or other forms.
In addition, the DCN model can adjust model parameters during training by a cross entropy function, wherein the cross entropy function is mainly used for measuring the difference information between two probability distributions and calculating the loss according to the difference information.
Specifically, the cross entropy function may be as follows:
Where H is used to characterize the loss, p is used to characterize the true probability distribution, and q is used to characterize the non-true probability distribution.
In the embodiment of the present application, after calculating the loss through the cross entropy function, the model parameters may be adjusted by a multi-head optimization mode, for example, the DNN model in the embodiment of the present application includes 3 parameters, and the losses of the 3 parameters are L 1、l2 and L 3, respectively, and then the loss l=a 1l1+a2l2+a3l3 of the DNN model, where a 1、a2 and a 3 are weights of L 1、l2 and L 3, and the weights may be dynamically adjusted according to the importance degrees of L 1、l2 and L 3.
After determining the loss L of the DNN model, model parameters of the DNN model may be adjusted based on a back propagation algorithm (Backpropagation algorithm, BP), which is a learning algorithm suitable for multi-layer neuronal networks, which is based on a gradient descent method. The input-output relationship of the back propagation algorithm is essentially a mapping relationship, that is, the back propagation algorithm of one input n and one output m performs the following functions: a continuous mapping from n-dimensional euclidean space to a finite field in m-dimensional euclidean space, which mapping has a high degree of nonlinearity. The information processing capability of the back propagation algorithm is derived from the multiple complex of simple nonlinear functions, so that the back propagation algorithm has strong function reproduction capability.
In step 55, a target location point is determined among the candidate location points based on the evaluation of the candidate location points.
In the embodiment of the application, after the target position point is determined, the target position point can be displayed so that the user can go to the target position point.
According to the embodiment of the application, the target position point can be determined based on the current order positioning, at least one candidate position point and the cross-road probability and/or the non-cross-road probability of each candidate position point, wherein the cross-road probability can represent the probability that the target terminal crosses the road to the corresponding candidate position point after sending the order request, the non-cross-road probability can represent the probability that the target terminal does not cross the road to the corresponding candidate position point after sending the order request, so the cross-road probability and/or the non-cross-road probability can represent the general cross-road willingness, and further, the more preferable target position point can be determined based on the general cross-road willingness.
Based on the same technical concept, the embodiment of the application further provides a location point determining device, as shown in fig. 13, which includes: a current order location module 131, a candidate location point module 132, a probability module 133, an evaluation module 134, and a target location point module 135.
The current ordering and positioning module 131 is configured to determine a current ordering and positioning of a target terminal in response to receiving an ordering request sent by the target terminal;
A candidate location point module 132 for determining at least one candidate location point based on the current order location;
The probability module 133 is configured to determine a cross probability and/or a non-cross probability of each candidate location point, where the cross probability is used to characterize a probability that the target terminal crosses a road to a corresponding candidate location point after sending a request for ordering, and the non-cross probability is used to characterize a probability that the target terminal does not cross the road to the corresponding candidate location point after sending the request for ordering;
An evaluation module 134, configured to determine an evaluation of each candidate location point based on the current order location, the at least one candidate location point, and a cross probability and/or a non-cross probability of each candidate location point; and
The target location point module 135 is configured to determine a target location point among the candidate location points based on the evaluation of the candidate location points.
Optionally, the probability of crossing/not crossing of the candidate location point is determined based on the following module:
The acquisition module is used for acquiring at least one historical order taking the candidate position point as a recommended position, wherein the historical order comprises a first historical order placing position, the candidate position point and a historical service occurrence position point when the historical order is placed, and the historical service occurrence position point is at least used for representing the actual service occurrence position of the target terminal; and
And the determining module is used for determining the crossing probability/non-crossing probability of the candidate position point according to the first historical order positioning, the candidate position point and the historical service occurrence position point statistics.
Optionally, the determining module is specifically configured to:
Generating a road crossing event corresponding to the historical order according to the first historical order positioning, the candidate position point and the historical service occurrence position point, wherein the road crossing event is used for representing the behavior of crossing a road when the service of the historical order occurs; and
And determining the cross-road probability/non-cross-road probability of the candidate position point based on the Bayesian formula and the cross-road event corresponding to each historical order.
Optionally, the determining module is specifically configured to:
Translating the first historical order positioning to one side of the road according to the road position information to determine a second historical order positioning; and
And determining the crossing probability/non-crossing probability of the candidate position point according to the second historical order positioning, the candidate position point and the historical service occurrence position point statistics.
Optionally, the determining module is specifically configured to:
Generating a road crossing event corresponding to the historical order according to the second historical order positioning, the candidate position point and the historical service occurrence position point, wherein the road crossing event is used for representing the behavior of crossing a road when the service of the historical order occurs; and
And determining the cross-road probability/non-cross-road probability of the candidate position point based on the Bayesian formula and the cross-road event corresponding to each historical order.
Optionally, the probability module 133 is specifically configured to:
Determining the position relation between the current order positioning and each candidate position point, wherein the position relation is used for representing that the current order positioning and the candidate position point are positioned on the same side of a road or the current order positioning and the candidate position point are positioned on different sides of the road; and determining the cross-road probability and/or the non-cross-road probability of each candidate position point based on the position relation.
Optionally, the evaluation module 134 is specifically configured to:
Determining the distance between the current order positioning and each candidate position point, and determining a plurality of target distances;
Determining a first feature vector corresponding to each target distance;
determining the crossing probability and/or the second feature vector corresponding to the non-crossing probability of each candidate position point; and
And inputting each first characteristic vector and each second characteristic vector into a pre-trained deep neural network model, and determining the evaluation of each candidate position point.
Optionally, the candidate location point module 132 is specifically configured to:
Determining a candidate position point list corresponding to the current order positioning; and
And determining a preset number of candidate position points in the candidate position point list.
Optionally, the deep neural network model is a multi-head optimized deep crossover network.
According to the embodiment of the application, the target position point can be determined based on the current order positioning, at least one candidate position point and the cross-road probability and/or the non-cross-road probability of each candidate position point, wherein the cross-road probability can represent the probability that the target terminal crosses the road to the corresponding candidate position point after sending the order request, the non-cross-road probability can represent the probability that the target terminal does not cross the road to the corresponding candidate position point after sending the order request, so the cross-road probability and/or the non-cross-road probability can represent the general cross-road willingness, and further, the more preferable target position point can be determined based on the general cross-road willingness.
Fig. 14 is a schematic diagram of an electronic device according to an embodiment of the application. As shown in fig. 14, the electronic device shown in fig. 14 is a general address query device, which includes a general computer hardware structure including at least a processor 141 and a memory 142. Processor 141 and memory 142 are connected by bus 143. The memory 142 is adapted to store instructions or programs executable by the processor 141. Processor 141 may be a stand-alone microprocessor or may be a collection of one or more microprocessors. Thus, processor 141, by executing instructions stored in memory 142, performs the method flows of embodiments of the application described above to effect processing of data and control of other devices. Bus 143 connects the above components together, as well as to display controller 144 and display devices and input/output (I/O) devices 145. Input/output (I/O) devices 145 may be a mouse, keyboard, modem, network interface, touch input device, somatosensory input device, printer, and other devices known in the art. Typically, the input/output devices 145 are connected to the system through input/output (I/O) controllers 146.
It will be apparent to those skilled in the art that embodiments of the present application may be provided as a method, apparatus (device) or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may employ a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations of methods, apparatus (devices) and computer program products according to embodiments of the application. It will be understood that each of the flows in the flowchart may be implemented by computer program instructions.
These computer program instructions may be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows.
These computer program instructions may also be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows.
Another embodiment of the present application is directed to a non-volatile storage medium storing a computer readable program for causing a computer to perform some or all of the method embodiments described above.
That is, it will be understood by those skilled in the art that all or part of the steps in implementing the methods of the embodiments described above may be implemented by specifying relevant hardware by a program, where the program is stored in a storage medium, and includes several instructions for causing a device (which may be a single-chip microcomputer, a chip or the like) or a processor (processor) to perform all or part of the steps in the methods of the embodiments of the application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a read-only memory (ROM), a random access memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Another embodiment of the application relates to a computer program product comprising a computer program/instruction which, when executed by a processor, can implement some or all of the above-described method embodiments.
That is, those skilled in the art will appreciate that embodiments of the application may be implemented by a processor executing a computer program product (computer program/instructions) to specify associated hardware, including the processor itself, to carry out all or part of the steps of the methods of the embodiments described above.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, and various modifications and variations may be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (18)
1. A method of location point determination, the method comprising:
determining the current ordering positioning of a target terminal in response to receiving an ordering request sent by the target terminal;
determining at least one candidate location point based on the current order location;
Determining the crossing probability and/or the non-crossing probability of each candidate position point, wherein the crossing probability is used for representing the probability that the target terminal crosses a road to the corresponding candidate position point after sending a ordering request, and the non-crossing probability is used for representing the probability that the target terminal does not cross the road to the corresponding candidate position point after sending the ordering request;
Determining the evaluation of each candidate position point based on the current order positioning, the at least one candidate position point and the cross-road probability and/or the non-cross-road probability of each candidate position point; and
Determining a target location point among the candidate location points based on the evaluation of the candidate location points;
The candidate position points are all or part of position points to be recommended within a preset distance from the current order positioning;
The probability of crossing/probability of not crossing the candidate position point is determined based on the following steps:
Acquiring at least one historical order taking the candidate position point as a recommended position, wherein the historical order comprises a first historical order placing position, the candidate position point and a historical service occurrence position point when the historical order is placed, and the historical service occurrence position point is at least used for representing the actual service occurrence position of the target terminal; and
And determining the crossing probability/non-crossing probability of the candidate position point according to the first historical order positioning, the candidate position point and the historical service occurrence position point statistics.
2. The method of claim 1, wherein said determining the probability of crossing/not crossing of the candidate location point based on the first historical order location, the candidate location point, and the historical traffic occurrence location point statistics comprises:
Generating a road crossing event corresponding to the historical order according to the first historical order positioning, the candidate position point and the historical service occurrence position point, wherein the road crossing event is used for representing the behavior of crossing a road when the service of the historical order occurs; and
And determining the cross-road probability/non-cross-road probability of the candidate position point based on the Bayesian formula and the cross-road event corresponding to each historical order.
3. The method of claim 1, wherein said determining the probability of crossing/not crossing of the candidate location point based on the first historical order location, the candidate location point, and the historical traffic occurrence location point statistics comprises:
Translating the first historical order positioning to one side of the road according to the road position information to determine a second historical order positioning; and
And determining the crossing probability/non-crossing probability of the candidate position point according to the second historical order positioning, the candidate position point and the historical service occurrence position point statistics.
4. The method of claim 3, wherein said determining the probability of crossing/not crossing of the candidate location point based on the second historical order location, the candidate location point, and the historical traffic occurrence location point statistics comprises:
Generating a road crossing event corresponding to the historical order according to the second historical order positioning, the candidate position point and the historical service occurrence position point, wherein the road crossing event is used for representing the behavior of crossing a road when the service of the historical order occurs; and
And determining the cross-road probability/non-cross-road probability of the candidate position point based on the Bayesian formula and the cross-road event corresponding to each historical order.
5. The method according to claim 1, wherein determining the probability of crossing and/or the probability of not crossing each candidate location point comprises:
Determining the position relation between the current order positioning and each candidate position point, wherein the position relation is used for representing that the current order positioning and the candidate position point are positioned on the same side of a road or the current order positioning and the candidate position point are positioned on different sides of the road; and
And determining the crossing probability and/or the non-crossing probability of each candidate position point based on the position relation.
6. The method of claim 1, wherein the determining an evaluation of each candidate location point based on the current order location, the at least one candidate location point, and a cross-road probability for each candidate location point comprises:
Determining the distance between the current order positioning and each candidate position point, and determining a plurality of target distances;
Determining a first feature vector corresponding to each target distance;
determining the crossing probability and/or the second feature vector corresponding to the non-crossing probability of each candidate position point; and
And inputting each first characteristic vector and each second characteristic vector into a pre-trained deep neural network model, and determining the evaluation of each candidate position point.
7. The method of claim 1, wherein the determining at least one candidate location point based on the current ordering fix comprises:
Determining a candidate position point list corresponding to the current order positioning; and
And determining a preset number of candidate position points in the candidate position point list.
8. The method of claim 6, wherein the deep neural network model is a multi-headed optimized deep crossover network.
9. A location point determining device, the device comprising:
The current ordering and positioning module is used for determining the current ordering and positioning of the target terminal in response to receiving an ordering request sent by the target terminal;
A candidate location point module for determining at least one candidate location point based on the current order location;
The probability module is used for determining the cross-road probability and/or the non-cross-road probability of each candidate position point, wherein the cross-road probability is used for representing the probability that the target terminal crosses a road to the corresponding candidate position point after sending the ordering request, and the non-cross-road probability is used for representing the probability that the target terminal does not cross the road to the corresponding candidate position point after sending the ordering request;
The evaluation module is used for determining the evaluation of each candidate position point based on the current order positioning, the at least one candidate position point and the cross-road probability and/or the non-cross-road probability of each candidate position point; and
A target location point module for determining a target location point among the candidate location points based on the evaluation of the candidate location points;
The candidate position points are all or part of position points to be recommended within a preset distance from the current order positioning;
the probability of crossing/probability of not crossing the candidate position point is determined based on the following modules:
The acquisition module is used for acquiring at least one historical order taking the candidate position point as a recommended position, wherein the historical order comprises a first historical order placing position, the candidate position point and a historical service occurrence position point when the historical order is placed, and the historical service occurrence position point is at least used for representing the actual service occurrence position of the target terminal; and
And the determining module is used for determining the crossing probability/non-crossing probability of the candidate position point according to the first historical order positioning, the candidate position point and the historical service occurrence position point statistics.
10. The apparatus according to claim 9, wherein the determining module is specifically configured to:
Generating a road crossing event corresponding to the historical order according to the first historical order positioning, the candidate position point and the historical service occurrence position point, wherein the road crossing event is used for representing the behavior of crossing a road when the service of the historical order occurs; and
And determining the cross-road probability/non-cross-road probability of the candidate position point based on the Bayesian formula and the cross-road event corresponding to each historical order.
11. The apparatus according to claim 9, wherein the determining module is specifically configured to:
Translating the first historical order positioning to one side of the road according to the road position information to determine a second historical order positioning; and
And determining the crossing probability/non-crossing probability of the candidate position point according to the second historical order positioning, the candidate position point and the historical service occurrence position point statistics.
12. The apparatus according to claim 11, wherein the determining module is specifically configured to:
Generating a road crossing event corresponding to the historical order according to the second historical order positioning, the candidate position point and the historical service occurrence position point, wherein the road crossing event is used for representing the behavior of crossing a road when the service of the historical order occurs; and
And determining the cross-road probability/non-cross-road probability of the candidate position point based on the Bayesian formula and the cross-road event corresponding to each historical order.
13. The apparatus according to claim 9, wherein the probability module is specifically configured to:
Determining the position relation between the current order positioning and each candidate position point, wherein the position relation is used for representing that the current order positioning and the candidate position point are positioned on the same side of a road or the current order positioning and the candidate position point are positioned on different sides of the road; and
And determining the crossing probability and/or the non-crossing probability of each candidate position point based on the position relation.
14. The apparatus of claim 9, wherein the evaluation module is configured to:
Determining the distance between the current order positioning and each candidate position point, and determining a plurality of target distances;
Determining a first feature vector corresponding to each target distance;
determining the crossing probability and/or the second feature vector corresponding to the non-crossing probability of each candidate position point; and
And inputting each first characteristic vector and each second characteristic vector into a pre-trained deep neural network model, and determining the evaluation of each candidate position point.
15. The apparatus of claim 9, wherein the candidate location point module is specifically configured to:
Determining a candidate position point list corresponding to the current order positioning; and
And determining a preset number of candidate position points in the candidate position point list.
16. The apparatus of claim 14, wherein the deep neural network model is a multi-headed optimized deep crossover network.
17. An electronic device comprising a memory and a processor, wherein the memory is configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method of any of claims 1-8.
18. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when executed by a processor, implements the method of any of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110172549.9A CN112990548B (en) | 2021-02-08 | 2021-02-08 | Position point determining method, device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110172549.9A CN112990548B (en) | 2021-02-08 | 2021-02-08 | Position point determining method, device, electronic equipment and readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112990548A CN112990548A (en) | 2021-06-18 |
CN112990548B true CN112990548B (en) | 2024-04-19 |
Family
ID=76347649
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110172549.9A Active CN112990548B (en) | 2021-02-08 | 2021-02-08 | Position point determining method, device, electronic equipment and readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112990548B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017137822A1 (en) * | 2016-02-08 | 2017-08-17 | Uber Technologies, Inc. | Selecting a route to a destination based on zones |
CN107492063A (en) * | 2016-06-13 | 2017-12-19 | 滴滴(中国)科技有限公司 | One kind is got on the bus a recommendation process method and system |
CN110175713A (en) * | 2019-05-22 | 2019-08-27 | 北京交通大学 | Timesharing rent-a-car user's trip purpose prediction technique |
CN110672107A (en) * | 2018-07-02 | 2020-01-10 | 北京嘀嘀无限科技发展有限公司 | Convergence position recommendation method, system and computer readable storage medium |
CN111210297A (en) * | 2019-12-23 | 2020-05-29 | 南京领行科技股份有限公司 | Method and device for dividing boarding points |
CN111814069A (en) * | 2019-09-17 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Information processing method, information processing apparatus, storage medium, and electronic device |
CN111814070A (en) * | 2019-12-16 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Method and system for recommending boarding points, storage medium and electronic equipment |
CN111861622A (en) * | 2019-12-28 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Method and system for determining boarding point recommendation model |
CN111931079A (en) * | 2020-07-21 | 2020-11-13 | 欧拉信息服务有限公司 | Method and system for recommending online booking getting-on points |
CN112270427A (en) * | 2020-11-10 | 2021-01-26 | 北京嘀嘀无限科技发展有限公司 | Method and system for recommending boarding points |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11158017B2 (en) * | 2016-12-28 | 2021-10-26 | Sap Se | Warehouse management system |
-
2021
- 2021-02-08 CN CN202110172549.9A patent/CN112990548B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017137822A1 (en) * | 2016-02-08 | 2017-08-17 | Uber Technologies, Inc. | Selecting a route to a destination based on zones |
CN107492063A (en) * | 2016-06-13 | 2017-12-19 | 滴滴(中国)科技有限公司 | One kind is got on the bus a recommendation process method and system |
CN110672107A (en) * | 2018-07-02 | 2020-01-10 | 北京嘀嘀无限科技发展有限公司 | Convergence position recommendation method, system and computer readable storage medium |
CN110175713A (en) * | 2019-05-22 | 2019-08-27 | 北京交通大学 | Timesharing rent-a-car user's trip purpose prediction technique |
CN111814069A (en) * | 2019-09-17 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Information processing method, information processing apparatus, storage medium, and electronic device |
CN111814070A (en) * | 2019-12-16 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Method and system for recommending boarding points, storage medium and electronic equipment |
CN111210297A (en) * | 2019-12-23 | 2020-05-29 | 南京领行科技股份有限公司 | Method and device for dividing boarding points |
CN111861622A (en) * | 2019-12-28 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Method and system for determining boarding point recommendation model |
CN111931079A (en) * | 2020-07-21 | 2020-11-13 | 欧拉信息服务有限公司 | Method and system for recommending online booking getting-on points |
CN112270427A (en) * | 2020-11-10 | 2021-01-26 | 北京嘀嘀无限科技发展有限公司 | Method and system for recommending boarding points |
Also Published As
Publication number | Publication date |
---|---|
CN112990548A (en) | 2021-06-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20230394203A1 (en) | Generating integrated circuit floorplans using neural networks | |
EP3542319B1 (en) | Training neural networks using a clustering loss | |
US11068285B2 (en) | Machine-learning models applied to interaction data for determining interaction goals and facilitating experience-based modifications to interface elements in online environments | |
CN111723292B (en) | Recommendation method, system, electronic equipment and storage medium based on graph neural network | |
CN112541122A (en) | Recommendation model training method and device, electronic equipment and storage medium | |
CN111652378B (en) | Learning to select vocabulary for category features | |
CN110222220A (en) | Image processing method, device, computer-readable medium and electronic equipment | |
WO2021034932A1 (en) | Automated path-based recommendation for risk mitigation | |
CN111091196A (en) | Passenger flow data determination method and device, computer equipment and storage medium | |
CN110400184A (en) | Method and apparatus for generating information | |
CN113706251A (en) | Commodity recommendation method and device based on model, computer equipment and storage medium | |
CN115204971B (en) | Product recommendation method, device, electronic equipment and computer readable storage medium | |
CN113656686A (en) | Task report generation method based on birth teaching fusion and service system | |
CN112818262A (en) | Map POI searching method, system, device and medium based on user data | |
JP6714268B1 (en) | Question sentence output method, computer program, and information processing apparatus | |
CN116701734B (en) | Address text processing method and device and computer readable storage medium | |
CN114090898A (en) | Information recommendation method and device, terminal equipment and medium | |
CN106776757A (en) | User completes the indicating means and device of Net silver operation | |
CN113761375A (en) | Message recommendation method, device, equipment and storage medium based on neural network | |
CN116843483A (en) | Vehicle insurance claim settlement method, device, computer equipment and storage medium | |
CN112990548B (en) | Position point determining method, device, electronic equipment and readable storage medium | |
JP2023533723A (en) | Evaluate interpretation of search queries | |
CN110083674B (en) | Intellectual property information processing method and device | |
CN116910373A (en) | House source recommendation method and device, electronic equipment and storage medium | |
CN109242927B (en) | Advertisement template generation method and device and computer equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |