Route generation method, device, equipment, computer readable medium and program product

By filtering and matching the route feature information in the route database, and using the route matching information generation model, the driving route problem under the influence of real-time road restrictions is solved, efficient and accurate route recommendation is achieved, driving costs are reduced and efficiency is improved.

CN119022949APending Publication Date: 2024-11-26BEIJING JINGDONG QIANSHITECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411124732.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

At different times, the input driving routes are easily affected by real-time road restrictions, resulting in high driving costs and low efficiency.

Method used

By determining the starting and ending location information of the target route request, filtering candidate routes and feature information in the route library, using pre-trained route matching information to generate a model, generating route matching information, recommending the most suitable driving route, and considering route time characteristics and demand characteristics , optimize route selection.

Benefits of technology

Accurate and efficient driving route recommendations at different times are achieved, avoiding the problems of high driving costs and low efficiency, and ensuring the accuracy and adequacy of route recommendations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119022949A_ABST
    Figure CN119022949A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a route generation method, device and equipment, a computer readable medium and a program product. A specific embodiment of the method comprises the following steps: determining starting and ending place information corresponding to a target route request as first starting and ending place information; screening at least one first route corresponding to the first starting and ending place information and at least one piece of corresponding first route feature information from a pre-established route library; determining second route feature information corresponding to the target route request; inputting each piece of first route feature information and the second route feature information in the at least one piece of first route feature information into a pre-trained route matching information generation model to generate route matching information and obtain at least one piece of route matching information; and generating a recommended route corresponding to the target route request according to the at least one piece of route matching information. The embodiment is related to artificial intelligence, and the recommended route under the current request time can be accurately and efficiently generated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a route generation method, apparatus, device, computer-readable medium, and program product. Background Art

[0002] At present, in the field of road driving, a suitable driving route can not only ensure the safety of the driver, but also efficiently reach the destination, and reasonably control the driving cost and avoid unnecessary waste of resources. For the generation of a suitable driving route, the method usually adopted is: the driver inputs the driving route by himself.

[0003] However, the inventors have found that when the above method is used to generate a suitable driving route, the following technical problems often occur:

[0004] At different times, the driving routes input by the transporters are often affected by real-time road restrictions, resulting in high driving costs and low driving efficiency when using the input driving routes.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0006] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0007] Some embodiments of the present disclosure propose route generation methods, devices, equipment, computer-readable media, and program products to solve the technical problems mentioned in the above background technology section.

[0008] In a first aspect, some embodiments of the present disclosure provide a route generation method, comprising: determining the starting and ending location information corresponding to a target route request as the first starting and ending location information; screening out at least one first route corresponding to the above-mentioned first starting and ending location information and corresponding at least one first route feature information from a pre-established route library; determining the second route feature information corresponding to the above-mentioned target route request, wherein the above-mentioned second route feature information includes: route time feature information; inputting each first route feature information and the above-mentioned second route feature information in the above-mentioned at least one first route feature information into a pre-trained route matching information generation model to generate route matching information and obtain at least one route matching information; generating a recommended route corresponding to the above-mentioned target route request based on the above-mentioned at least one route matching information, wherein the above-mentioned recommended route is a route in the above-mentioned at least one first route.

[0009] Optionally, the route matching information in the above-mentioned at least one route matching information is information in the form of a score; and the above-mentioned generating a recommended route corresponding to the above-mentioned target route request based on the above-mentioned at least one route matching information includes: filtering out the route matching information whose corresponding score meets the preset score value condition from the above-mentioned at least one route matching information as the target route matching information; and determining the first route corresponding to the above-mentioned target route matching information as the above-mentioned recommended route.

[0010] Optionally, generating a recommended route corresponding to the target route request based on the at least one route matching information includes: obtaining route demand characteristic information corresponding to the target route request, wherein the route demand characteristic information includes: driving value consumption demand characteristic information and driving time consumption demand characteristic information; determining a route matching weight corresponding to each of the at least one first route according to the route demand characteristic information, and obtaining at least one route matching weight; generating the recommended route according to the at least one route matching information and the at least one route matching weight.

[0011] Optionally, the method further includes: adding the recommended route and the second route feature information to the route library.

[0012] Optionally, the route matching information generation model is trained through the following steps: for each historical driving task information in the acquired historical driving task information set, the following first generation step is performed: at least one second route corresponding to the second starting and ending location information and at least one corresponding third route feature information are screened out from a pre-established route library, wherein the second starting and ending location information corresponds to the historical driving task information, and the third route feature information includes: route driving time feature information; route feature information corresponding to the historical driving task information is generated as historical route feature information, wherein the historical route feature information includes: historical route driving time feature information; at least one route matching information for the at least one third route and the route corresponding to the historical driving task information is generated as at least one matching label; at least one training data is generated based on the at least one third route feature information, the historical route feature information and the at least one matching label; based on the obtained at least one training data set, the initial route matching information generation model is trained to generate a route matching information generation model.

[0013] Optionally, the third route feature information also includes: route corner feature information; and the route corner feature information is generated by the following steps: performing node calibration on the second route to obtain a node sequence. For each node in the node sequence, executing the following second generation step: determining a candidate point in the second route that is located after the node at a preset value; generating a first vector between the candidate point and the node; determining a second vector between a next node and the corresponding candidate point, wherein the next node is a node in the node sequence that is located at the next position of the node; determining the angle between the first vector and the second vector; and generating the route corner feature information based on the obtained angle set.

[0014] Optionally, the route turning angle feature information includes: left turning angle feature information and right turning angle feature information; the route turning angle feature information is generated based on the angle set obtained above, including: removing angles whose corresponding angles are less than a preset angle from the angle set to obtain a removed angle set; screening out a first angle set representing an angle turning to the left and a second angle set representing an angle turning to the right from the removed angle set; determining the first angle set as the left turning angle feature information, and determining the second angle set as the right turning angle feature information.

[0015] In the second aspect, some embodiments of the present disclosure provide a route generation device, comprising: a first determination unit, configured to determine the starting and ending location information corresponding to the target route request as the first starting and ending location information; a screening unit, configured to screen out at least one first route corresponding to the above-mentioned first starting and ending location information and corresponding at least one first route feature information from a pre-established route library; a second determination unit, configured to determine the second route feature information corresponding to the above-mentioned target route request, wherein the above-mentioned second route feature information includes: route time feature information; an input unit, configured to input each first route feature information and the above-mentioned second route feature information in the above-mentioned at least one first route feature information into a pre-trained route matching information generation model to generate route matching information and obtain at least one route matching information; a generation unit, configured to generate a recommended route corresponding to the above-mentioned target route request based on the above-mentioned at least one route matching information, wherein the above-mentioned recommended route is a route in the above-mentioned at least one first route.

[0016] Optionally, the route matching information in the above-mentioned at least one route matching information is information in the form of scores; and the generation unit can be configured to: filter out the route matching information whose corresponding scores meet the preset score value conditions from the above-mentioned at least one route matching information as the target route matching information; and determine the first route corresponding to the above-mentioned target route matching information as the above-mentioned recommended route.

[0017] Optionally, the generation unit can be configured to: obtain route demand characteristic information corresponding to the above-mentioned target route request, wherein the above-mentioned route demand characteristic information includes: driving value consumption demand characteristic information and driving time consumption demand characteristic information; determine the route matching weight corresponding to each of the above-mentioned at least one first route according to the above-mentioned route demand characteristic information, and obtain at least one route matching weight; generate the above-mentioned recommended route according to the above-mentioned at least one route matching information and the above-mentioned at least one route matching weight.

[0018] Optionally, the device further includes: adding the recommended route and the second route feature information to the route library.

[0019] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

[0020] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.

[0021] In a fifth aspect, some embodiments of the present disclosure provide a computer program product, including a computer program, which implements the method described in any implementation manner in the above-mentioned first aspect when executed by a processor.

[0022] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: the route generation method of some embodiments of the present disclosure can accurately and efficiently generate the recommended route at the current request time. Specifically, the reason why the relevant recommended routes are not accurate and efficient is that at different times, the driving routes input by the transporter are often affected by real-time road restrictions, resulting in the use of the input driving routes for driving, which has the problem of high driving cost and low driving efficiency. Based on this, the route generation method of some embodiments of the present disclosure, first, determines the starting and ending location information corresponding to the target route request as the first starting and ending location information, so as to facilitate the subsequent matching of at least one first route that can be driven for the first starting and ending location information, and ensure that the starting point and end point of the subsequent recommended route are the same as the requirements of the target route request. Then, at least one first route corresponding to the above-mentioned first starting and ending location information and the corresponding at least one first route feature information are screened out from the pre-established route library. Here, the screened at least one first route is used as a candidate route set, and the obtained at least one first route feature information is convenient for matching with the demand characteristics corresponding to the target route request, so as to accurately generate the recommended route later. In addition, the pre-established route library can fully match the corresponding candidate routes for various starting and ending location information, ensuring the adequacy of route recommendation. Next, the second route feature information corresponding to the target route request is determined, wherein the second route feature information includes: route time feature information. Here, by determining the second route feature information, it is convenient to grasp the route demand feature corresponding to the target route request, so as to accurately screen out the appropriate route later. In addition, by extracting the route time feature information, the subsequent model can fully learn the time feature corresponding to the current target route request, so as to match a more suitable route under the time feature corresponding to the current time. That is, the influence of real-time road restrictions on the driving route at different times is fully considered, ensuring the accuracy of the subsequent recommended route. Furthermore, each first route feature information in the at least one first route feature information and the second route feature information are input into the pre-trained route matching information generation model to accurately generate route matching information and obtain at least one route matching information. Finally, according to the at least one route matching information, the recommended route corresponding to the target route request can be accurately generated, wherein the recommended route is a route in the at least one first route. In summary, the route library can ensure the adequacy of candidate routes. The time feature information of the route can fully consider the impact of real-time road restrictions on the driving route at the current time, ensuring the accuracy of the subsequent recommended routes. And through the route matching information generation model, the similarity between the route feature information corresponding to the candidate route and the route feature information corresponding to the route request can be fully compared, ensuring the subsequent accurate generation of the recommended route.On the basis of generating the recommended route, the problems of high driving cost and low driving efficiency can be avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0024] Figure 1 is a schematic diagram of an application scenario of a route generation method according to some embodiments of the present disclosure;

[0025] Figure 2 is a flow chart of some embodiments of the route generation method according to the present disclosure;

[0026] Figure 3 is a schematic diagram showing an angle between a first vector and a second vector in some embodiments of the route generation method according to the present disclosure;

[0027] Figure 4 are flow charts of other embodiments of the route generation method according to the present disclosure;

[0028] Figure 5 is a schematic diagram of the structure of some embodiments of the route generation device according to the present disclosure;

[0029] Figure 6 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0030] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0031] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0032] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0033] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0034] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0035] With regard to the collection, storage, and use of user personal information (such as starting and ending location information) involved in this disclosure, before performing the corresponding operations, the relevant organizations or individuals shall fulfill their obligations, including conducting personal information security impact assessments, fulfilling the obligation to inform the personal information subject, and obtaining the authorization and consent of the personal information subject in advance.

[0036] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0037] Figure 1 It is a schematic diagram of an application scenario of the route generation method according to some embodiments of the present disclosure.

[0038] exist Figure 1In the application scenario, first, the electronic device 101 can determine the starting and ending location information corresponding to the target route request 102 as the first starting and ending location information 103. In this application scenario, the first starting and ending location information 103 can be "starting location: location A, ending location: location B, vehicle type information: length is A, width is B, height is C, weight is D, baggage is E". Then, the electronic device 101 can filter out at least one first route 105 and corresponding at least one first route feature information 106 corresponding to the above-mentioned first starting and ending location information 103 from the pre-established route library 104. In this application scenario, the at least one first route 105 includes: route A, route B, route C and route D. The at least one first route feature information 106 includes: route feature information A corresponding to route A, route feature information B corresponding to route B, route feature information C corresponding to route C, and route feature information D corresponding to route D. Next, the electronic device 101 can determine the second route feature information 107 corresponding to the above-mentioned target route request 102. Among them, the above-mentioned second route feature information 107 includes: route time feature information. In this application scenario, the second route feature information 107 may be route feature information E. Furthermore, the electronic device 101 may input each first route feature information in the at least one first route feature information 106 and the second route feature information 107 into the pre-trained route matching information generation model 108 to generate route matching information and obtain at least one route matching information 109. In this application scenario, the at least one route matching information 109 includes: route matching information A corresponding to route A, route matching information B corresponding to route B, route matching information C corresponding to route C, and route matching information D corresponding to route D. Route matching information A may be "70". Route matching information B may be "65". Route matching information C may be "76". Route matching information D may be "89". Finally, the electronic device 101 may generate a recommended route corresponding to the target route request 102 according to the at least one route matching information 109, wherein the recommended route is a route in the at least one first route 105. In this application scenario, the recommended route may be route D.

[0039] It should be noted that the electronic device 101 can be hardware or software. When the electronic device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device. When the electronic device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here.

[0040] It should be understood that Figure 1The number of electronic devices in the embodiment is only for illustration. Any number of electronic devices may be provided according to implementation requirements.

[0041] Continue to refer Figure 2 , shows a process 200 of some embodiments of the route generation method according to the present disclosure. The route generation method comprises the following steps:

[0042] Step 201: Determine the starting and ending location information corresponding to the target route request as the first starting and ending location information.

[0043] In some embodiments, the execution body of the above route generation method (for example Figure 1 The electronic device 101 shown can determine the starting and ending location information corresponding to the target route request as the first starting and ending location information. Among them, the target route request can be the request information for requesting a recommended route at the current time. The target route request can include: route feature information (i.e., second route feature information) corresponding to the route to be requested, and starting and ending location information. The route feature information can be the feature content under each route feature related to the driving route. In practice, each route feature can include: route time feature, route cost feature, route highway feature, route intersection feature, route narrow road feature, and vehicle model feature. The route time feature can represent the start time of the route, and can also represent the end time of the route, and can also represent the time consumed by the route. The route cost feature can represent the value cost spent on the route. The route highway feature can represent the relevant information of the highway in the route. The route intersection feature can represent the information related to the intersection in the route. The route narrow road feature can represent the relevant information of the narrow road in the route. The vehicle model feature can be the vehicle model of the driving vehicle. The starting and ending location information can be the starting location of the route and the ending location of the route. For the logistics scenario, the target route request can be a request for a transportation route. The first starting and ending location information may be a transportation starting point and a transportation ending point.

[0044] Step 202: Filter out at least one first route corresponding to the first starting and ending location information and corresponding at least one first route feature information from a pre-established route library.

[0045] In some embodiments, the execution entity may filter out at least one first route and corresponding at least one first route feature information corresponding to the first starting and ending location information from a pre-established route library. The route library includes: each route and route feature information corresponding to each route. There is a one-to-one correspondence between the first route in at least one first route and the first route feature information in at least one first route feature information. The relevant explanation of the first route feature information will not be repeated, refer to the explanation of the route feature information. The starting and ending location information corresponding to the first route is the first starting and ending location information.

[0046] It should be noted that the route library is established through the following steps:

[0047] The first step is to obtain an experience route set. The experience route can be a route taken by the driving object based on the experience of its own vehicles during driving. The experience route set can be each route generated by a clustering algorithm based on the routes of historical vehicle driving.

[0048] The second step is to obtain a route set input by the user. The route input by the user may be a custom route. The route input by the user may be a route that has not been traveled. For example, the route input by the user may be a route that avoids a target checkpoint.

[0049] The third step is to obtain a set of application recommended routes, wherein the application recommended routes may be routes recommended by the vehicle application.

[0050] The fourth step is to extract the experience route feature information corresponding to each experience route in the above experience route set to obtain the experience route feature information set.

[0051] The fifth step is to extract the input route feature information corresponding to each user-input route in the above user-input route set to obtain an input route feature information set.

[0052] The sixth step is to extract the application recommended route feature information corresponding to each application recommended route in the above application recommended route set to obtain the application recommended route feature information set.

[0053] The seventh step is to aggregate the above-mentioned experience route set, the above-mentioned route set input by the user, the above-mentioned application recommended route set, the above-mentioned experience route feature information set, the above-mentioned input route feature information set and the above-mentioned application recommended route feature information set to generate a route library.

[0054] Step 203: Determine the second route characteristic information corresponding to the target route request.

[0055] In some embodiments, the execution entity may determine the second route characteristic information corresponding to the target route request. The second route characteristic information includes: route time characteristic information. In practice, the route time characteristic information may be the request time corresponding to the target route request. For example, the route time characteristic information may be "the number of weeks when the request starts and the number of hours when the request starts". The rest of the specific explanations of the second route characteristic information will not be repeated, please refer to the explanation of the route characteristic information.

[0056] As an example, the execution entity may extract the second route feature information from the target route request.

[0057] Step 204: input each first route feature information in the at least one first route feature information and the second route feature information into a pre-trained route matching information generation model to generate route matching information, thereby obtaining at least one route matching information.

[0058] In some embodiments, the execution entity may input each of the at least one first route feature information and the second route feature information into a pre-trained route matching information generation model to generate route matching information and obtain at least one route matching information. The route matching information generation model may be a network model for generating route matching information. In practice, the route matching information generation model may be a machine learning model or a deep learning model. For example, the route matching information generation model may be an XGBoost (Extreme GradientBoosting) model. The route matching information generation model may also be a convolutional neural network model. The route matching information may characterize the degree of feature similarity between the first route feature information and the second route feature information. For example, the route matching information may include: high degree of similarity, average degree of similarity, and low degree of similarity.

[0059] Optionally, the first route characteristic information also includes: route time characteristic information.

[0060] In some optional implementations of some embodiments, the route matching information generation model is trained by the following steps:

[0061] In the first step, for each historical driving task information in the acquired historical driving task information set, the following first generation step is performed:

[0062] Sub-step 1, filtering out at least one second route corresponding to the second starting and ending location information and at least one corresponding third route characteristic information from a pre-established route library. The second starting and ending location information corresponds to the historical driving task information, and the third route characteristic information includes: route driving time characteristic information. The historical driving task information set may be task information of driving tasks in a historical time period. There is a corresponding driving route for the driving task.

[0063] Sub-step 2: Generate route characteristic information corresponding to the historical driving task information as historical route characteristic information. The historical route characteristic information includes: historical route driving time characteristic information. The route characteristic information corresponding to the historical driving task information may be route characteristic information corresponding to the driving route.

[0064] Sub-step 3: Generate at least one route matching information for the at least one third route and the route corresponding to the historical driving task information as at least one matching tag. The route matching information may indicate the matching degree between the third route and the route corresponding to the historical driving task information.

[0065] As an example, the inter-route spatial similarity between each third route and the route corresponding to the historical driving task information is determined as route matching information, and at least one route matching information is obtained. The inter-route spatial similarity can be the degree of spatial road similarity between different routes.

[0066] Sub-step 4: generating at least one training data according to the at least one third route characteristic information, the historical route characteristic information and the at least one matching tag, wherein the training data in the at least one training data has a one-to-one correspondence with the third route characteristic information in the at least one third route characteristic information.

[0067] As an example, for each third route feature information in the at least one third route feature information, the third route feature information, the above historical route feature information and the corresponding matching label are combined to generate training data.

[0068] The second step is to perform model training on the initial route matching information generation model according to the obtained at least one training data set to generate a route matching information generation model.

[0069] As an example, based on the obtained at least one training data set, the initial route matching information generation model is trained by back propagation to generate a route matching information generation model.

[0070] Optionally, the third route characteristic information further includes: route turning angle characteristic information, wherein the route turning angle characteristic information may represent the change of the turning angle of the corresponding route.

[0071] Optionally, the above route corner feature information is generated by the following steps:

[0072] The first step is to calibrate the nodes of the second route to obtain a node sequence.

[0073] As an example, first, a route coordinate system is established for the second route. Then, each route point in the second route in the route coordinate system is marked according to a predetermined calibration method to generate a node and obtain a node sequence.

[0074] In the second step, for each node in the above node sequence, perform the following second generation step:

[0075] Sub-step 1: determining a candidate point in the second route that is located after the node by a preset value, for example, the preset value may be 1 kilometer.

[0076] Sub-step 2: Generate a first vector between the candidate point and the node, wherein the vector direction of the first vector is the direction of the node toward the corresponding candidate point.

[0077] As an example, the coordinate point corresponding to the candidate point and the coordinate point corresponding to the node may be connected in the route coordinate system to generate a first vector.

[0078] Sub-step 3, determining a second vector between the next node and the corresponding candidate point. The next node is a node in the node sequence that is located next to the node. The candidate point corresponding to the next node may be a candidate point in the second route that is located after the next node by a preset value. The vector direction of the second vector is the direction of the next node toward the corresponding candidate point.

[0079] As an example, the coordinate point corresponding to the next node may be connected with the coordinate point corresponding to the candidate point to generate a second vector.

[0080] Sub-step 4: determining the angle between the first vector and the second vector.

[0081] The third step is to generate the above-mentioned route corner feature information based on the obtained angle set.

[0082] As an example, the above execution entity may determine the angle set as the route corner feature information.

[0083] Optionally, the above-mentioned route corner feature information includes: left corner feature information and right corner feature information. The left corner feature information may be the angle change of the corner facing left in the route. The right corner feature information may be the angle change of the corner facing right in the route.

[0084] Optionally, the generating of the route corner feature information according to the obtained angle set may include the following steps:

[0085] In the first step, the angles whose corresponding angles are smaller than a preset angle are removed from the above angle set to obtain a removed angle set, wherein the preset angle may be 10 degrees.

[0086] In the second step, a first angle set representing an angle turning to the left and a second angle set representing an angle turning to the right are selected from the above-mentioned removed angle set.

[0087] The third step is to determine the first angle set as the left turn corner feature information, and to determine the second angle set as the right turn corner feature information.

[0088] See also Figure 3 , a schematic diagram showing the angle between the first vector and the second vector.

[0089] Figure 3 The current node in is node A. Node A corresponds to candidate node B. The distance between node A and candidate node B is a preset value. Node A corresponds to next node C. Next node C corresponds to candidate node D. The distance between next node C and candidate node D is a preset distance. The first vector is a vector from node A to candidate node B. The second vector is a vector from next node C to candidate node D. The angle between the first vector and the second vector is angle α.

[0090] Step 205: Generate a recommended route corresponding to the target route request based on the at least one route matching information.

[0091] In some embodiments, the execution subject may generate a recommended route corresponding to the target route request based on the at least one route matching information. The recommended route is a route in the at least one first route. The recommended route may be a route that responds to the target route request.

[0092] As an example, the execution entity may select any route with a corresponding label of “high similarity” from at least one route matching information as a recommended route.

[0093] In some optional implementations of some embodiments, the route matching information in the at least one route matching information is information in the form of a score, wherein a higher score corresponding to the route matching information indicates that the first route feature information is more similar to the second route feature information.

[0094] Optionally, generating a recommended route corresponding to the target route request according to the at least one route matching information may include the following steps:

[0095] In the first step, the execution subject may select route matching information whose corresponding score meets a preset score value condition from the at least one route matching information as the target route matching information. The preset score value condition may be that the route matching information has the highest corresponding score.

[0096] In a second step, the execution entity may determine the first route corresponding to the target route matching information as the recommended route.

[0097] In some optional implementations of some embodiments, after step 205, the steps further include:

[0098] The execution entity may add the recommended route and the second route characteristic information to the route library.

[0099] By adding the recommended route and the second route characteristic information to the route library, the integrity of each route in the route library can be guaranteed, so as to match a more accurate route later.

[0100] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: the route generation method of some embodiments of the present disclosure can accurately and efficiently generate the recommended route at the current request time. Specifically, the reason why the relevant recommended routes are not accurate and efficient is that at different times, the driving routes input by the transporter are often affected by real-time road restrictions, resulting in the use of the input driving routes for driving, which has the problem of high driving cost and low driving efficiency. Based on this, the route generation method of some embodiments of the present disclosure, first, determines the starting and ending location information corresponding to the target route request as the first starting and ending location information, so as to facilitate the subsequent matching of at least one first route that can be driven for the first starting and ending location information, and ensure that the starting point and end point of the subsequent recommended route are the same as the requirements of the target route request. Then, at least one first route corresponding to the above-mentioned first starting and ending location information and the corresponding at least one first route feature information are screened out from the pre-established route library. Here, the screened at least one first route is used as a candidate route set, and the obtained at least one first route feature information is convenient for matching with the demand characteristics corresponding to the target route request, so as to accurately generate the recommended route later. In addition, the pre-established route library can fully match the corresponding candidate routes for various starting and ending location information, ensuring the adequacy of route recommendation. Next, the second route feature information corresponding to the target route request is determined, wherein the second route feature information includes: route time feature information. Here, by determining the second route feature information, it is convenient to grasp the route demand feature corresponding to the target route request, so as to accurately screen out the appropriate route later. In addition, by extracting the route time feature information, the subsequent model can fully learn the time feature corresponding to the current target route request, so as to match a more suitable route under the time feature corresponding to the current time. That is, the influence of real-time road restrictions on the driving route at different times is fully considered, ensuring the accuracy of the subsequent recommended route. Furthermore, each first route feature information in the at least one first route feature information and the second route feature information are input into the pre-trained route matching information generation model to accurately generate route matching information and obtain at least one route matching information. Finally, according to the at least one route matching information, the recommended route corresponding to the target route request can be accurately generated, wherein the recommended route is a route in the at least one first route. In summary, the route library can ensure the adequacy of candidate routes. The time feature information of the route can fully consider the impact of real-time road restrictions on the driving route at the current time, ensuring the accuracy of the subsequent recommended routes. And through the route matching information generation model, the similarity between the route feature information corresponding to the candidate route and the route feature information corresponding to the route request can be fully compared, ensuring the subsequent accurate generation of the recommended route.On the basis of generating the recommended route, the problems of high driving cost and low driving efficiency can be avoided.

[0101] Further references Figure 4 , shows a process 400 of another embodiment of the route generation method according to the present disclosure. The route generation method comprises the following steps:

[0102] Step 401, determining the starting and ending location information corresponding to the target route request as the first starting and ending location information.

[0103] Step 402: Filter out at least one first route corresponding to the first starting and ending location information and corresponding at least one first route feature information from a pre-established route library.

[0104] Step 403: Determine the second route characteristic information corresponding to the target route request.

[0105] Step 404: Input each first route feature information in the at least one first route feature information and the second route feature information into a pre-trained route matching information generation model to generate route matching information, thereby obtaining at least one route matching information.

[0106] In some embodiments, the specific implementation of steps 401-404 and the technical effects thereof can be referred to in Figure 2 The steps 201-204 in the corresponding embodiment are not described in detail here.

[0107] Step 405: Obtain route requirement characteristic information corresponding to the target route request.

[0108] In some embodiments, an execution entity (e.g. Figure 1The electronic device 101 shown) can obtain the route demand characteristic information corresponding to the above-mentioned target route request. Among them, the above-mentioned route demand characteristic information includes: driving value consumption demand characteristic information and driving time consumption demand characteristic information. Among them, the route demand characteristic information may be the characteristic information required for route driving (i.e., the characteristic information of the constraint characteristics corresponding to route driving). The driving value consumption demand characteristic information may be the characteristic information for value consumption constraints on route driving. Value consumption may be cost consumption. For example, value consumption may be the vehicle driving fee spent. Driving time consumption demand characteristic information may be the characteristic information for time consumption constraints on route driving. Time consumption may be driving time consumption. The above-mentioned target route request may include: route demand characteristic information. The driving value consumption demand characteristic information and the driving time consumption demand characteristic information may both be numerical information. For example, the driving time consumption demand characteristic information may be a requirement that the time consumption is less than 1 hour. The driving value consumption demand characteristic information may be a requirement that the vehicle driving fee spent is less than 10,000 yuan.

[0109] Step 406: Determine a route matching weight corresponding to each of the at least one first route according to the route demand characteristic information to obtain at least one route matching weight.

[0110] In some embodiments, the execution subject may determine the route matching weight corresponding to each of the at least one first route according to the route demand characteristic information to obtain at least one route matching weight. The route matching weight may represent the importance of the corresponding first route. The route matching weight may be a value between 0 and 1. The larger the value, the more important the first route is.

[0111] As an example, the above-mentioned execution entity can determine the degree of matching between each first route and the driving value consumption demand characteristic information and the driving time consumption demand characteristic information included in the above-mentioned route demand characteristic information, and obtain the corresponding route matching coefficient as the route matching weight.

[0112] Step 407: Generate the recommended route based on the at least one route matching information and the at least one route matching weight.

[0113] In some embodiments, the execution entity may generate the recommended route based on the at least one route matching information and the at least one route matching weight.

[0114] As an example, first, the execution subject may multiply the route matching information in the at least one route matching information and the route matching weight in the at least one route matching weight correspondingly to obtain at least one multiplication result. Then, the first route with the largest corresponding multiplication result is extracted from the at least one first route as the recommended route.

[0115] from Figure 4 It can be seen that Figure 2 Compared with the description of some corresponding embodiments, Figure 4 In some corresponding embodiments, the process 400 of the route generation method can effectively measure the cost of at least one route in terms of time cost and driving cost based on the driver's route demand through route demand characteristic information, thereby ensuring that the subsequently generated recommended route better meets the driver's requirements.

[0116] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a route generation device. These device embodiments are similar to Figure 2 Corresponding to the method embodiments shown, the route generating device can be specifically applied to various electronic devices.

[0117] like Figure 5 As shown, a route generation device 500 includes: a first determination unit 501, a screening unit 502, a second determination unit 503, an input unit 504 and a generation unit 505. The first determination unit 501 is configured to determine the starting and ending location information corresponding to the target route request as the first starting and ending location information; the screening unit 502 is configured to screen out at least one first route corresponding to the first starting and ending location information and at least one corresponding first route feature information from a pre-established route library; the second determination unit 503 is configured to determine the second route feature information corresponding to the target route request, wherein the second route feature information includes: route time feature information; the input unit 504 is configured to input each first route feature information and the second route feature information in the at least one first route feature information into a pre-trained route matching information generation model to generate route matching information and obtain at least one route matching information; the generation unit 505 is configured to generate a recommended route corresponding to the target route request according to the at least one route matching information, wherein the recommended route is a route in the at least one first route.

[0118] In some optional implementations of some embodiments, the route matching information in the above-mentioned at least one route matching information is information in the form of scores; and the generation unit 505 can be further configured to: filter out the route matching information whose corresponding scores meet the preset score value conditions from the above-mentioned at least one route matching information as the target route matching information; determine the first route corresponding to the above-mentioned target route matching information as the above-mentioned recommended route.

[0119] In some optional implementations of some embodiments, the generation unit 505 can be further configured to: obtain route demand characteristic information corresponding to the above-mentioned target route request, wherein the above-mentioned route demand characteristic information includes: driving value consumption demand characteristic information and driving time consumption demand characteristic information; determine the route matching weight corresponding to each first route in the above-mentioned at least one first route according to the above-mentioned route demand characteristic information, and obtain at least one route matching weight; generate the above-mentioned recommended route according to the above-mentioned at least one route matching information and the above-mentioned at least one route matching weight.

[0120] In some optional implementations of some embodiments, the apparatus 500 further includes: an adding unit (not shown in the figure). The adding unit may be configured to: add the recommended route and the second route feature information to the route library.

[0121] In some optional implementations of some embodiments, the route matching information generation model is trained through the following steps: for each historical driving task information in the acquired historical driving task information set, the following first generation step is performed: at least one second route corresponding to the second starting and ending location information and at least one corresponding third route feature information are screened out from a pre-established route library, wherein the second starting and ending location information corresponds to the historical driving task information, and the third route feature information includes: route driving time feature information; route feature information corresponding to the historical driving task information is generated as historical route feature information, wherein the historical route feature information includes: historical route driving time feature information; at least one route matching information is generated for the at least one third route and the route corresponding to the historical driving task information as at least one matching label; at least one training data is generated based on the at least one third route feature information, the historical route feature information and the at least one matching label; based on the obtained at least one training data set, the initial route matching information generation model is trained to generate a route matching information generation model.

[0122] In some optional implementations of some embodiments, the third route feature information also includes: route corner feature information; and the above-mentioned route corner feature information is generated by the following steps: performing node calibration on the second route to obtain a node sequence; for each node in the above-mentioned node sequence, executing the following second generation step: determining a candidate point in the above-mentioned second route that is located after the above-mentioned node at a preset value; generating a first vector between the above-mentioned candidate point and the above-mentioned node; determining a second vector between the next node and the corresponding candidate point, wherein the above-mentioned next node is a node in the above-mentioned node sequence that is located at the next position of the above-mentioned node; determining the angle between the above-mentioned first vector and the above-mentioned second vector; and generating the above-mentioned route corner feature information based on the obtained angle set.

[0123] In some optional implementations of some embodiments, the route corner feature information includes: left turn feature information and right turn feature information; and the route corner feature information is generated based on the obtained angle set, including: removing angles whose corresponding angles are less than a preset angle from the angle set to obtain a removed angle set; screening out a first angle set representing an angle turning to the left and a second angle set representing an angle turning to the right from the removed angle set; determining the first angle set as the left turn feature information, and determining the second angle set as the right turn feature information.

[0124] It is understandable that the units described in the route generation device 500 are similar to those described in the reference Figure 2 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the route generation device 500 and the units included therein, and will not be described in detail here.

[0125] Reference below Figure 6 , which shows an electronic device (eg, Figure 1 Schematic diagram of the structure of the electronic device 101)600. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0126] like Figure 6 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory 602 or a program loaded from a storage device 608 into a random access memory 603. Various programs and data required for the operation of the electronic device 600 are also stored in the random access memory 603. The processing device 601, the read-only memory 602, and the random access memory 603 are connected to each other via a bus 604. An input / output interface 605 is also connected to the bus 604.

[0127] Typically, the following devices may be connected to the input / output interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 6 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0128] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from a network through a communication device 609, or installed from a storage device 608, or installed from a read-only memory 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0129] It should be noted that the computer-readable medium in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0130] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0131] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: determines the starting and ending location information corresponding to the target route request as the first starting and ending location information; selects at least one first route corresponding to the first starting and ending location information and at least one corresponding first route feature information from a pre-established route library; determines the second route feature information corresponding to the target route request, wherein the second route feature information includes: route time feature information; inputs each first route feature information and the second route feature information in the at least one first route feature information into a pre-trained route matching information generation model to generate route matching information and obtain at least one route matching information; generates a recommended route corresponding to the target route request according to the at least one route matching information, wherein the recommended route is a route in the at least one first route.

[0132] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0133] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0134] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor comprising a first determination unit, a screening unit, a second determination unit, an input unit, and a generation unit. Among them, the names of these units do not constitute a limitation on the units themselves in certain circumstances, for example, the first determination unit may also be described as "a unit for determining the starting and ending location information corresponding to the target route request as the first starting and ending location information".

[0135] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0136] Some embodiments of the present disclosure further provide a computer program product, including a computer program, which implements any of the above-mentioned route generation methods when executed by a processor.

[0137] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A route generation method, comprising: Determine the starting and ending location information corresponding to the target route request as the first starting and ending location information; Filtering at least one first route corresponding to the first starting and ending location information and corresponding at least one first route feature information from a pre-established route library; Determine second route characteristic information corresponding to the target route request, wherein the second route characteristic information includes: route time characteristic information; Inputting each first route feature information of the at least one first route feature information and the second route feature information into a pre-trained route matching information generation model to generate route matching information, thereby obtaining at least one route matching information; A recommended route corresponding to the target route request is generated according to the at least one route matching information, wherein the recommended route is a route in the at least one first route.

2. The method according to claim 1, wherein: The route matching information in the at least one route matching information is information in the form of a score; as well as The step of generating a recommended route corresponding to the target route request according to the at least one route matching information includes: Filtering out route matching information whose corresponding score meets a preset score value condition from the at least one route matching information as target route matching information; A first route corresponding to the target route matching information is determined as the recommended route.

3. The method according to claim 1, wherein: The step of generating a recommended route corresponding to the target route request according to the at least one route matching information includes: Acquire route demand characteristic information corresponding to the target route request, wherein the route demand characteristic information includes: driving value consumption demand characteristic information and driving time consumption demand characteristic information; Determine, according to the route demand characteristic information, a route matching weight corresponding to each first route in the at least one first route to obtain at least one route matching weight; The recommended route is generated according to the at least one route matching information and the at least one route matching weight.

4. The method according to claim 1, wherein: The method further comprises: The recommended route and the second route characteristic information are added to the route library.

5. The method according to claim 1, wherein: The route matching information generation model is trained through the following steps: For each piece of historical driving task information in the acquired historical driving task information set, the following first generation step is performed: Filtering out at least one second route corresponding to the second starting and ending location information and at least one corresponding third route feature information from a pre-established route library, wherein the second starting and ending location information corresponds to the historical driving task information, and the third route feature information includes: route driving time feature information; Generate route characteristic information corresponding to the historical driving task information as historical route characteristic information, wherein the historical route characteristic information includes: historical route driving time characteristic information; generating at least one route matching information for the at least one third route and the route corresponding to the historical driving task information as at least one matching tag; generating at least one training data according to the at least one third route feature information, the historical route feature information and the at least one matching tag; According to the obtained at least one training data set, model training is performed on the initial route matching information generation model to generate a route matching information generation model.

6. The method according to claim 5, wherein: The third route characteristic information also includes: route corner characteristic information; and The route corner feature information is generated by the following steps: Node calibration is performed on the second route to obtain a node sequence; For each node of the node sequence, the following second generation step is performed: Determine a candidate point in the second route that is located after the node by a preset value; generating a first vector between the candidate point and the node; Determine a second vector between a next node and a corresponding candidate point, wherein the next node is a node in the node sequence that is at a next position of the node; determining an angle between the first vector and the second vector; The route corner feature information is generated according to the obtained angle set.

7. The method according to claim 6, wherein: The route corner feature information includes: left turn feature information and right turn feature information; and The step of generating the route corner feature information according to the obtained angle set includes: Remove the angles whose corresponding angles are smaller than the preset angle from the angle set to obtain a removed angle set; Filter out a first angle set representing an angle turning to the left and a second angle set representing an angle turning to the right from the removed angle set; The first angle set is determined as the left turn angle feature information, and the second angle set is determined as the right turn angle feature information.

8. A route generating device, comprising: A first determining unit is configured to determine the starting and ending location information corresponding to the target route request as the first starting and ending location information; a screening unit, configured to screen out at least one first route corresponding to the first starting and ending location information and corresponding at least one first route feature information from a pre-established route library; The second determining unit is configured to determine second route characteristic information corresponding to the target route request, wherein the second route characteristic information includes: route time characteristic information; an input unit configured to input each of the first route feature information and the second route feature information in the at least one first route feature information into a pre-trained route matching information generation model to generate route matching information, thereby obtaining at least one route matching information; The generating unit is configured to generate a recommended route corresponding to the target route request according to the at least one route matching information, wherein the recommended route is a route in the at least one first route.

9. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.