Method, device, equipment and readable storage medium for obtaining a planned path

By calculating the pass risk of candidate paths and selecting a path with a pass risk less than the preset threshold, the accuracy of road planning methods in the prior art under special road conditions is solved, and the efficiency of door-to-door service is improved.

CN113358130BInactive Publication Date: 2024-11-19BANK OF CHINA
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110600232.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-05-31
Publication Date
2024-11-19
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing road planning methods only refer to the passage time, resulting in low accuracy of planning paths under short-term special road conditions, affecting the efficiency of door-to-door services.

Method used

By obtaining the road blocking probability of the candidate path and predicting the pass time, calculating the pass risk, selecting a path with a pass risk less than the preset threshold as the planned path, considering road state and time factors to improve the accuracy of the path.

Benefits of technology

It improves the accuracy of the planning path, promotes the efficiency of completing appointment tasks, and ensures the efficiency of on-site services.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113358130B_ABST
    Figure CN113358130B_ABST
Patent Text Reader

Abstract

The embodiments of the present application provide a method, device, equipment and readable storage medium for obtaining a planned path, obtaining a set of candidate paths, obtaining the road congestion probability of each candidate path based on historical traffic flow data, the road congestion probability of the candidate path indicating the probability that the candidate path is in a congested state at a preset time, obtaining the travel risk of each candidate path based on the predicted travel time of each candidate path and the road congestion probability of each candidate path, and if the candidate path meets the preset conditions, using the candidate path as the planned path for the scheduled task. The greater the travel risk, the longer the travel time from the departure point to the destination of the scheduled task according to the candidate path or the greater the probability that the candidate path is in a congested state, selecting the candidate path with a risk less than a preset threshold as the planned path, considering the travel time of the candidate path and the probability of being in a congested state at the preset time, thereby improving the accuracy of the planned path.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment and readable storage medium for acquiring a planned path. Background Art

[0002] Currently, most banks have added door-to-door services to enhance customer experience. Door-to-door services, on the one hand, need to meet customer appointment times, and on the other hand, need to improve the efficiency of door-to-door services. Currently, in addition to assigning salespersons with higher efficiency in handling appointment business, an effective way to improve the efficiency of door-to-door services is to choose a reasonable door-to-door route.

[0003] The current road planning method is to select the path with the shortest travel time as the planned path. However, in reality, there are often short-term special road conditions (such as road construction or road closures for other reasons) that seriously affect the efficiency of door-to-door service. It can be seen that the planning path based only on travel time is less accurate, which often leads to low efficiency of door-to-door service for appointment tasks. Summary of the invention

[0004] The present application provides a method, device, equipment and readable storage medium for obtaining a planned path, which are used to improve the accuracy of the planned path, as follows:

[0005] A method for obtaining a planned path, comprising:

[0006] Acquire a candidate path set, the candidate path set including at least two candidate paths, the candidate paths being paths from a departure point of the scheduled task to a destination of the scheduled task;

[0007] According to the historical traffic flow data, a road blocking probability of each candidate path is obtained, wherein the road blocking probability indicates the probability that the candidate path is in a blocked state at a preset time, and the preset time is the scheduled time of the scheduled task;

[0008] At a preset time, the travel risk of each candidate path is obtained according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, wherein the longer the predicted travel time and / or the greater the road blocking probability, the greater the travel risk;

[0009] If the candidate path meets a preset condition, the candidate path is used as the planned path for the scheduled task, and the preset condition includes that the travel risk of the candidate path is less than a preset threshold.

[0010] Optionally, before obtaining the road blocking probability of each candidate path according to the historical traffic flow data, the method further includes:

[0011] Generate a traffic flow curve for each candidate path according to the traffic flow of each preset time period of each candidate path on a preset date, wherein the preset time period is before the preset time, and the preset date is the scheduled date of the scheduled task;

[0012] Generate a traffic flow curve for each preset sample route according to the traffic flow of each preset sample route in each preset time period on a preset sample date;

[0013] The traffic flow curve of each candidate path, the traffic flow curve of each preset sample path, and the road status of each preset sample path are used as the historical traffic flow data, and the road status of the preset sample path indicates whether the preset sample path is in the blocked state or the non-blocked state.

[0014] Optionally, the process of obtaining the road blocking probability of the target candidate path according to the historical traffic flow data includes:

[0015] If the similarity between the traffic flow curve of the preset sample path and the traffic flow curve of the target candidate path exceeds the preset similarity, the preset sample path is used as the first sample path, and the target candidate path is any candidate path in the candidate path set;

[0016] If the road state of the first sample path indicates that the preset sample path is in the blocked state, using the first sample path as the second sample path;

[0017] The ratio of the number of the second sample paths to the number of the first sample paths is used as the road blocking probability of the target candidate path.

[0018] Optionally, before obtaining the travel risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, the method further includes:

[0019] Acquire attribute information, the attribute information including: preset attributes of each of the preset sample dates and preset attributes of the preset date, the preset attributes indicating holidays and / or weather;

[0020] According to the attribute information and the preset corresponding relationship, the matching degree between the preset attribute of each of the preset sample dates and the preset attribute of the preset date is obtained, wherein the preset corresponding relationship includes: the matching degree between different preset attributes;

[0021] If the preset attribute of the preset sample date matches the preset attribute of the preset date, the preset sample date is used as the target date;

[0022] The travel time of the candidate path at a preset time on the target date is obtained as the predicted travel time of the candidate path.

[0023] Optionally, obtaining the travel risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path includes:

[0024] The product of the predicted travel time of each candidate path and the road blocking probability of each candidate path is obtained as the travel risk of each candidate path.

[0025] Optionally, after obtaining the travel risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, the method further includes:

[0026] Sort the candidate paths in ascending order according to the predicted travel time to obtain a time series;

[0027] The predicted travel time of the first candidate path is used as the first value of the first candidate path, and the product of the road blocking probability of the first candidate path and the predicted travel time of the second candidate path is used as the second value of the first candidate path, the second candidate path is the candidate path that is located after the first candidate path in the time series, and the first candidate path is any candidate path except the candidate path that is the last in the time series;

[0028] acquiring a sum of a first value of the first candidate path and a second value of the first candidate path as a risk cost value of the first candidate path;

[0029] It is determined whether the risk cost value of the first candidate path is less than the predicted travel time of the second candidate path. If so, it is determined that the first candidate path is a low-risk path.

[0030] If the candidate path meets the preset condition, taking the candidate path as the planned path for the scheduled task includes:

[0031] If the candidate path meets a preset condition, the candidate path is used as the planned path for the scheduled task, and the preset condition further includes: the candidate path belongs to the low-risk path.

[0032] A device for acquiring a planned path, comprising:

[0033] A path set acquisition unit, used to acquire a candidate path set, wherein the candidate path set includes at least two candidate paths, and the candidate paths are paths from a departure point of a scheduled task to a destination of the scheduled task;

[0034] A probability acquisition unit, configured to acquire a road blocking probability of each candidate path according to historical traffic flow data, wherein the road blocking probability indicates a probability that the candidate path is in a blocked state at a preset time, and the preset time is a scheduled time of the scheduled task;

[0035] A traffic risk acquisition unit, configured to acquire the traffic risk of each candidate path according to the predicted traffic time of each candidate path and the road blocking probability of each candidate path, wherein the longer the predicted traffic time and / or the greater the road blocking probability, the greater the traffic risk;

[0036] The planning result acquisition unit is used to use the candidate path as the planned path for the scheduled task if the candidate path meets a preset condition, wherein the preset condition includes that the travel risk of the candidate path is less than a preset threshold.

[0037] Optionally, the traffic risk acquisition unit is used to acquire the traffic risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, including:

[0038] The travel risk acquisition unit is specifically used to: acquire the product of the predicted travel time of each candidate path and the road blocking probability of each candidate path as the travel risk of each candidate path.

[0039] A device for acquiring a planned path, comprising: a memory and a processor;

[0040] The memory is used to store programs;

[0041] The processor is used to execute the program to implement each step of the method for acquiring the planned path.

[0042] A readable storage medium stores a computer program, which, when executed by a processor, implements each step of a method for acquiring a planned path.

[0043] It can be seen from the above technical scheme that the method, device, equipment and readable storage medium for obtaining the planned path provided in the embodiments of the present application obtain a set of candidate paths, where the candidate path set includes at least two candidate paths, and the candidate path is a path from the departure point of the scheduled task to the destination of the scheduled task. Based on historical traffic data, the road congestion probability of each candidate path is obtained, and the road congestion probability of the candidate path indicates the probability that the candidate path is in a blocked state at a preset time. Based on the predicted travel time of each candidate path and the road congestion probability of each candidate path, the travel risk of each candidate path is obtained. If the candidate path meets the preset conditions, the candidate path is used as the planned path for the scheduled task. The preset conditions include that the travel risk of the candidate path is less than a preset threshold. Since the longer the predicted travel time and / or the greater the probability of road congestion, the greater the travel risk, and the road congestion probability is obtained based on historical traffic flow data, which is objective data, the greater the travel risk, the longer the travel time from the departure point to the destination of the appointment task according to the candidate path or the greater the probability that the candidate path is in a blocked state, the candidate path with a risk less than a preset threshold is selected as the planned path. On the one hand, the travel time of the candidate path is considered, and on the other hand, the road state of the candidate path is considered, that is, the probability of being in a blocked state at the preset time, thereby improving the accuracy of the planned path and further promoting the improvement of the efficiency of completing the appointment task. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A flowchart of a specific implementation method of a method for obtaining a planned path provided in an embodiment of the present application;

[0046] Figure 2 A schematic diagram of a process for obtaining a planned path provided in an embodiment of the present application;

[0047] Figure 3 A schematic diagram of the structure of a device for acquiring a planned path provided in an embodiment of the present application;

[0048] Figure 4 A schematic diagram of the structure of a planned path acquisition device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] The method for obtaining the planned path provided in the embodiment of the present application is applied to, but not limited to, the method for scheduling appointment tasks, and can be specifically applied to a task scheduling system. The task scheduling system is pre-configured in a server, and includes a task list generation module, a path planning module, and a task delivery module, wherein the task list generation module is used to obtain appointment tasks in real time and generate itinerary information for appointment tasks, and the itinerary information includes the correspondence between the departure point and the destination of each appointment task. The path planning module is used to execute the method for obtaining the planned path and obtain the planned path for the appointment task. The task delivery module is used to deliver the appointment task and the planned path of the appointment task to the client bound to the account of the business personnel who meet the preset requirements. It should be noted that, specifically, Figure 1 A specific implementation of a method for obtaining a planned path provided in an embodiment of the present application may include S101 to S112:

[0051] S101: Obtain a set of candidate paths.

[0052] In this embodiment, the candidate path set includes at least two candidate paths, the candidate paths are paths from the departure point of the scheduled task to the destination of the scheduled task, and each candidate path includes at least one road segment. The scheduled task is a task for which a path is to be planned.

[0053] It should be noted that the method for obtaining candidate paths can refer to the prior art.

[0054] S102: Obtain historical vehicle flow data.

[0055] In this embodiment, the historical traffic flow data includes the traffic flow curve of each candidate path, the traffic flow curve of each preset sample path, and the road status of each preset sample path. Among them, the preset sample path includes the path whose similarity with the candidate path is greater than the first similarity threshold, and the similarity between each path and the candidate path is obtained based on the path information of the path and the path information of the candidate path, wherein the path information includes at least one of the number of road sections, the number of intersections, the number of traffic lights, and the road type. The road status of the preset sample path indicates whether the preset sample path is in a blocked state or a non-blocked state at the preset time on the preset sample date. The specific similarity calculation method can refer to the prior art, which will not be described in detail in this embodiment.

[0056] In this embodiment, the specific process of obtaining historical traffic flow data includes: 1. Generate a traffic flow curve for each candidate path based on the traffic flow of each candidate path in each preset time period on a preset date. The preset date is the appointment date of the appointment service, and the preset time period is the time period before the appointment time point. The duration of each preset time period is half an hour. For example, if the appointment time point is 16:00, every half hour before 16:00 is regarded as a reservation time period.

[0057] 2. Generate a traffic flow curve for each preset sample route based on the traffic flow of each preset sample route in each preset time period on the preset sample date.

[0058] The number of preset sample paths is multiple, and the preset sample date is a date before the preset date. In order to improve the accuracy of probability prediction, the data volume of the preset sample paths and the preset sample dates is as large as possible in practical applications.

[0059] It should be noted that the method for calculating the traffic flow in the reservation time period and the method for generating the traffic flow curve can refer to the existing technology.

[0060] 3. Obtain the road status of each preset sample path. The road status of the preset sample path indicates whether the preset sample path is in a blocked state on the preset sample date. For a specific acquisition method, refer to the prior art.

[0061] S103: If the curve similarity between the traffic flow curve of the candidate path and the traffic flow curve of the preset sample path exceeds a preset similarity, the preset sample path is used as the first sample path.

[0062] In this embodiment, there are multiple methods for obtaining the curve similarity between the traffic flow curve of the candidate path and the traffic flow curve of the preset sample path, for example, a point-based curve similarity calculation method and a shape-based curve similarity calculation method. For details, please refer to the prior art and this embodiment will not be described in detail.

[0063] It can be understood that if the traffic flow curve of the preset sample is highly similar to the traffic flow curve of the candidate path, then the traffic flow of the preset sample path in each preset time period on the preset sample date and the traffic flow of the candidate path in each preset time period on the preset date are highly similar, that is, the road conditions are highly similar.

[0064] S104: If the road state of the first sample path indicates that the preset sample path is in a blocked state, use the preset sample path as the second sample path.

[0065] It should be noted that, since there are multiple preset sample paths, this embodiment executes S103 to S104 for each preset sample path to obtain all the first sample paths and the second sample paths.

[0066] S105: Taking the ratio of the number of the second sample paths to the number of the first sample paths as the road blocking probability of the candidate paths.

[0067] In this embodiment, the second sample path satisfies that the curve similarity between the traffic flow curve and the candidate path is greater than a preset threshold and is in a blocked state at a preset time on a preset sample date, and the first sample path at least satisfies that the curve similarity between the traffic flow curve and the candidate path is greater than a preset threshold. That is, the second sample path is a path in a blocked state at a preset time on a preset sample date among multiple first sample paths.

[0068] Therefore, the ratio of the number of second sample paths to the number of first sample paths is the proportion of blocked paths among paths with similar road conditions to the candidate paths. Since the preset sample paths are similar paths to the candidate paths and the historical traffic data are objective data, the proportion of blocked paths can be used as the road blocking probability of the candidate paths.

[0069] It should be noted that the candidate path set includes multiple candidate paths, and the road blocking probability of each candidate path is obtained according to the above steps.

[0070] S106: Obtain the predicted travel time of each candidate path.

[0071] In this embodiment, there are multiple methods for obtaining the predicted travel time of each candidate path. The following is an optional predicted travel time of a candidate path, specifically including A1 to A4, as follows:

[0072] A1. Acquire attribute information, the attribute information including: preset attributes of each preset sample date and preset attributes of a preset date, the preset attributes indicating date, holiday, and weather.

[0073] For example, if the preset date is April 15, 2021, and the preset sample date is April 13, 2021, the attribute information of the preset date includes April 15, 2021 (date), non-holiday (holiday), light rain (weather). The attribute information of the preset sample date includes April 13, 2021 (date), holiday (holiday), cloudy (weather)

[0074] A2. According to the attribute information and the preset corresponding relationship, the matching degree between the attribute information of each preset sample date and the attribute information of the preset date is obtained.

[0075] In this embodiment, the preset corresponding relationship includes: the matching degree between different preset attributes. For example, the matching degree between holidays and non-holidays is 0.2, the matching degree between holidays and holidays is 0.6, the matching degree between cloudy and light rain is 0.4, and the matching degree between sunny and cloudy is 0.8. It should be noted that the matching degree between different preset attributes is pre-configured. Specifically, the matching degree between preset attributes is determined based on the similarity of the degree of influence of each preset attribute on the traffic flow. For example, cloudy and sunny days have very little influence on the traffic flow, but light rain and thunderstorms have a relatively large influence on the traffic flow, so the matching degree between cloudy and sunny days is greater than the matching degree between light rain and sunny days. The specific matching degree preset method can refer to the prior art.

[0076] In this embodiment, the matching degree between the attribute information of the preset sample date and the attribute information of the preset date is obtained by adding the matching degrees between the preset attributes corresponding to the preset sample date and the preset date.

[0077] A3. If the preset attribute of the preset sample date and the preset attribute of the preset date are greater than the preset matching threshold, the preset sample date is used as the target date.

[0078] A4. Obtain the travel time of the candidate path at a preset time on the target date as the predicted travel time of the candidate path.

[0079] It should be noted that the method for obtaining the travel time of the candidate paths at the preset time on the target date can be referred to the prior art.

[0080] In this embodiment, the target date is obtained based on the similarity with the attribute information of the candidate date. The road conditions of the candidate paths on the target date are highly similar to those on the preset date, and the predicted travel time of each candidate path is obtained with high accuracy.

[0081] S107: Obtain the product of the predicted travel time of the candidate path and the road blocking probability of the candidate path as the travel risk of the candidate path.

[0082] It is understandable that the longer the predicted travel time and / or the greater the probability of road congestion, the greater the travel risk.

[0083] S108. Sort the candidate paths from small to large according to their predicted travel time to obtain a time series.

[0084] S109: Taking the predicted travel time of the first candidate path as the first value of the first candidate path, and taking the product of the road congestion probability of the first candidate path and the predicted travel time of the second candidate path as the second value of the first candidate path.

[0085] In this embodiment, the first candidate path is any candidate path except the candidate path ranked last in the time sequence, and the second candidate path is the candidate path ranked after the first candidate path in the time sequence.

[0086] For example, the candidate path set includes three candidate paths, namely the first path L1, the second path L2 and the third path L3. The predicted travel time of the first path is T1, the predicted travel time of the second path is T2, the predicted travel time of the third path is T3, the probability of the road blocking probability of the first path is P1, the probability of the road blocking probability of the second path is P2, and the probability of the road blocking probability of the third path is P3. T1<T2<T3, the time series is {L1, L2, L3}.

[0087] For example, the first candidate path is L1, the second candidate path is L2, the first value of the first candidate path is T1, and the second value is P1*T2.

[0088] S110 . Obtain a sum of a first value of the first candidate path and a second value of the first candidate path as a risk cost value of the first candidate path.

[0089] That is, the risk cost value of the candidate path L1 is equal to T1+P1*T2. The risk cost value of the candidate path L2 is equal to T2+P2*T3.

[0090] S111. Determine whether the risk cost value of the first candidate path is less than the predicted travel time of the second candidate path. If so, determine that the first candidate path is a low-risk path.

[0091] Specifically, the candidate path L1 is taken as the first candidate path, and it is determined whether the risk cost value of the candidate path L1 is less than that of the second candidate path, that is, the candidate path L2. If so, the candidate path L1 is taken as a low-risk path.

[0092] S112: If the candidate path meets the preset conditions, the candidate path is used as the planned path for the scheduled task.

[0093] In this embodiment, the preset conditions include: the travel risk of the candidate path is less than a preset threshold, and the candidate path is a low-risk path.

[0094] It should be noted that if there are multiple candidate paths that meet the preset conditions, the candidate path with the shortest preset travel time can be selected.

[0095] It can be seen from the above technical solution that the travel risk of each candidate path is determined based on the predicted travel time of the candidate path and the road congestion probability of the candidate path. The longer the predicted travel time and / or the greater the road congestion probability, the greater the travel risk, and the road congestion probability is obtained based on historical traffic flow data, which is objective data. Therefore, the greater the travel risk, the longer the travel time from the departure point to the destination of the appointment task according to the candidate path or the greater the probability that the candidate path is in a blocked state. The candidate path with a risk less than a preset threshold is selected as the planned path. On the one hand, the travel time of the candidate path is considered, and on the other hand, the road state of the candidate path is considered, that is, the probability of being in a blocked state at the preset time, which improves the accuracy of the planned path and further promotes the improvement of the completion efficiency of the appointment task.

[0096] Furthermore, based on the attribute information of the preset date and the sample preset date, the sample preset date that has a high degree of match with the attribute information of the preset date is determined as the target date. It can be understood that the road condition on the target date is highly similar to the road condition on the preset date. The travel time of the candidate path at the preset time of the target date is used as the predicted travel time of the candidate path, which has high objectivity and accuracy, and further improves the accuracy of the planned path.

[0097] Furthermore, the risk cost value of the first candidate path is determined based on the predicted travel time of the first candidate path, the road congestion probability, and the predicted travel time of the candidate path (the second candidate path) that is shorter than the predicted travel time of the first candidate path. When the risk cost value of the first candidate path is less than the predicted travel time of the second candidate path, it means that the opportunity cost of selecting the second candidate path after the first candidate path is blocked is less than directly selecting the second candidate path. Since the predicted travel time and road congestion probability of the candidate path are predicted based on objective data, the risk cost value of the first candidate path is objective.

[0098] It should be noted that Figure 1 The described process is only a specific implementation of an optional method for obtaining a planned path provided in an embodiment of the present application, and the present application also includes other specific implementations. For example, S102 is an optional step and is only an optional method for obtaining historical traffic flow data. For another example, S103 to S105 are only an optional method for obtaining the road blocking probability of each candidate path. The present application also includes other optional methods for obtaining the road blocking probability of each candidate path based on historical traffic flow data.

[0099] In summary, the method for obtaining a planned path provided in the embodiment of the present application is summarized as follows: Figure 2 The process shown is as follows Figure 2 As shown, this method specifically includes:

[0100] S201: Obtain a set of candidate paths.

[0101] In this embodiment, the candidate path set includes at least two candidate paths, the candidate path is a path from the departure point of the scheduled task to the destination of the scheduled task, and the candidate path includes at least one road segment.

[0102] S202: Obtain the road congestion probability of each candidate path based on historical traffic flow data.

[0103] In this embodiment, the road blocking probability of the candidate path indicates the probability that the candidate path is in a blocked state at a preset time.

[0104] In this embodiment, there are multiple methods for obtaining historical traffic flow data, one of which can be selected in S102. There are multiple methods for obtaining the road blocking probability of each candidate path, one of which can be selected in S103 to S104.

[0105] S203 . Obtain the travel risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path.

[0106] In this embodiment, the longer the predicted travel time is and / or the greater the probability of road congestion is, the greater the travel risk is.

[0107] S204: If the candidate path meets the preset conditions, the candidate path is used as the planned path for the scheduled task.

[0108] In this embodiment, the preset condition includes that the travel risk of the candidate path is less than a preset threshold.

[0109] It can be seen from the above technical scheme that an embodiment of the present application provides a method for obtaining a planned path, in which the travel risk of each candidate path is determined based on the predicted travel time of the candidate path and the road congestion probability of the candidate path. The longer the predicted travel time and / or the greater the road congestion probability, the greater the travel risk, and the road congestion probability is obtained based on historical traffic flow data, which is objective data. Therefore, the greater the travel risk, the longer the travel time from the departure point to the destination of the appointment task according to the candidate path or the greater the probability that the candidate path is in a blocked state. The candidate path with a risk less than a preset threshold is selected as the planned path. On the one hand, the travel time of the candidate path is considered, and on the other hand, the road state of the candidate path is considered, that is, the probability of being in a blocked state at a preset time, thereby improving the accuracy of the planned path and further promoting the improvement of the completion efficiency of the appointment task.

[0110] Figure 3 A schematic diagram of the structure of a device for acquiring a planned path provided in an embodiment of the present application is shown. Figure 3As shown, the device may include:

[0111] A path set acquisition unit 301 is used to acquire a candidate path set, wherein the candidate path set includes at least two candidate paths, and the candidate paths are paths from a departure point of a scheduled task to a destination of the scheduled task;

[0112] The probability acquisition unit 302 is used to acquire the road blocking probability of each candidate path according to the historical traffic flow data, wherein the road blocking probability indicates the probability that the candidate path is in a blocked state at a preset time, and the preset time is the scheduled time of the scheduled task;

[0113] A traffic risk acquisition unit 303 is used to acquire the traffic risk of each candidate path according to the predicted traffic time of each candidate path and the road blocking probability of each candidate path. The longer the predicted traffic time and / or the greater the road blocking probability, the greater the traffic risk;

[0114] The planning result acquisition unit 304 is used to use the candidate path as the planned path for the scheduled task if the candidate path meets a preset condition, wherein the preset condition includes that the travel risk of the candidate path is less than a preset threshold.

[0115] Optionally, the device further comprises: a historical data acquisition unit, which is used to generate a traffic flow curve for each candidate path according to the traffic flow of each candidate path in each preset time period on a preset date before acquiring the road blocking probability of each candidate path according to the historical traffic flow data, wherein the preset time period is before the preset time, and the preset date is the appointment date of the appointment task;

[0116] Generate a traffic flow curve for each preset sample route according to the traffic flow of each preset sample route in each preset time period on a preset sample date;

[0117] The traffic flow curve of each candidate path, the traffic flow curve of each preset sample path, and the road status of each preset sample path are used as the historical traffic flow data, and the road status of the preset sample path indicates whether the preset sample path is in the blocked state or the non-blocked state.

[0118] Optionally, when the probability acquisition unit is used to acquire the road congestion probability of each candidate path according to the historical traffic flow data, it is specifically used to: acquire the road congestion probability of the target candidate path according to the historical traffic flow data.

[0119] The process of obtaining the road blocking probability of the target candidate path according to the historical traffic flow data includes: if the similarity between the traffic flow curve of the preset sample path and the traffic flow curve of the target candidate path exceeds a preset similarity, taking the preset sample path as the first sample path, and the target candidate path is any candidate path of the candidate path set;

[0120] If the road state of the first sample path indicates that the preset sample path is in the blocked state, using the first sample path as the second sample path;

[0121] The ratio of the number of the second sample paths to the number of the first sample paths is used as the road blocking probability of the target candidate path.

[0122] Optionally, the device further comprises: a predicted travel time acquisition unit, configured to acquire attribute information before acquiring the travel risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, wherein the attribute information comprises: preset attributes of each preset sample date and preset attributes of the preset date, wherein the preset attributes indicate holidays and / or weather;

[0123] According to the attribute information and the preset corresponding relationship, the matching degree between the preset attribute of each of the preset sample dates and the preset attribute of the preset date is obtained, wherein the preset corresponding relationship includes: the matching degree between different preset attributes;

[0124] If the preset attribute of the preset sample date matches the preset attribute of the preset date, the preset sample date is used as the target date;

[0125] The travel time of the candidate path at a preset time on the target date is obtained as the predicted travel time of the candidate path.

[0126] Optionally, a traffic risk acquisition unit is used to acquire the traffic risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, including: the traffic risk acquisition unit is specifically used to:

[0127] The product of the predicted travel time of each candidate path and the road blocking probability of each candidate path is obtained as the travel risk of each candidate path.

[0128] Optionally, the device further comprises: a risk comparison unit, configured to, after obtaining the travel risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path:

[0129] Sort the candidate paths in ascending order according to the predicted travel time to obtain a time series;

[0130] The predicted travel time of the first candidate path is used as the first value of the first candidate path, and the product of the road blocking probability of the first candidate path and the predicted travel time of the second candidate path is used as the second value of the first candidate path, the second candidate path is the candidate path that is located after the first candidate path in the time series, and the first candidate path is any candidate path except the candidate path that is the last in the time series;

[0131] acquiring a sum of a first value of the first candidate path and a second value of the first candidate path as a risk cost value of the first candidate path;

[0132] It is determined whether the risk cost value of the first candidate path is less than the predicted travel time of the second candidate path. If so, it is determined that the first candidate path is a low-risk path.

[0133] The planning result acquisition unit is used to use the candidate path as the planned planning path of the scheduled task if the candidate path meets the preset conditions, including: the planning result acquisition unit is specifically used to:

[0134] If the candidate path meets a preset condition, the candidate path is used as the planned path for the scheduled task, and the preset condition further includes: the candidate path belongs to the low-risk path.

[0135] Figure 4 A schematic diagram of the structure of the acquisition device of the planned path is shown, and the device may include: at least one processor 401, at least one communication interface 402, at least one memory 403 and at least one communication bus 404;

[0136] In the embodiment of the present application, the number of the processor 401, the communication interface 402, the memory 403, and the communication bus 404 is at least one, and the processor 401, the communication interface 402, and the memory 403 communicate with each other through the communication bus 404;

[0137] The processor 401 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention;

[0138] The memory 403 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory;

[0139] The memory stores a program, and the processor can execute the program stored in the memory to implement the steps of a method for obtaining a planned path provided in an embodiment of the present application, as follows:

[0140] A method for obtaining a planned path, comprising:

[0141] Acquire a candidate path set, the candidate path set including at least two candidate paths, the candidate paths being paths from a departure point of the scheduled task to a destination of the scheduled task;

[0142] According to the historical traffic flow data, a road blocking probability of each candidate path is obtained, wherein the road blocking probability indicates the probability that the candidate path is in a blocked state at a preset time, and the preset time is the scheduled time of the scheduled task;

[0143] At a preset time, the travel risk of each candidate path is obtained according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, wherein the longer the predicted travel time and / or the greater the road blocking probability, the greater the travel risk;

[0144] If the candidate path meets a preset condition, the candidate path is used as the planned path for the scheduled task, and the preset condition includes that the travel risk of the candidate path is less than a preset threshold.

[0145] Optionally, before obtaining the road blocking probability of each candidate path according to the historical traffic flow data, the method further includes:

[0146] Generate a traffic flow curve for each candidate path according to the traffic flow of each preset time period of each candidate path on a preset date, wherein the preset time period is before the preset time, and the preset date is the scheduled date of the scheduled task;

[0147] Generate a traffic flow curve for each preset sample route according to the traffic flow of each preset sample route in each preset time period on a preset sample date;

[0148] The traffic flow curve of each candidate path, the traffic flow curve of each preset sample path, and the road status of each preset sample path are used as the historical traffic flow data, and the road status of the preset sample path indicates whether the preset sample path is in the blocked state or the non-blocked state.

[0149] Optionally, the process of obtaining the road blocking probability of the target candidate path according to the historical traffic flow data includes:

[0150] If the similarity between the traffic flow curve of the preset sample path and the traffic flow curve of the target candidate path exceeds the preset similarity, the preset sample path is used as the first sample path, and the target candidate path is any candidate path in the candidate path set;

[0151] If the road state of the first sample path indicates that the preset sample path is in the blocked state, using the first sample path as the second sample path;

[0152] The ratio of the number of the second sample paths to the number of the first sample paths is used as the road blocking probability of the target candidate path.

[0153] Optionally, before obtaining the travel risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, the method further includes:

[0154] Acquire attribute information, the attribute information including: preset attributes of each of the preset sample dates and preset attributes of the preset date, the preset attributes indicating holidays and / or weather;

[0155] According to the attribute information and the preset corresponding relationship, the matching degree between the preset attribute of each of the preset sample dates and the preset attribute of the preset date is obtained, wherein the preset corresponding relationship includes: the matching degree between different preset attributes;

[0156] If the preset attribute of the preset sample date matches the preset attribute of the preset date, the preset sample date is used as the target date;

[0157] The travel time of the candidate path at a preset time on the target date is obtained as the predicted travel time of the candidate path.

[0158] Optionally, obtaining the travel risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path includes:

[0159] The product of the predicted travel time of each candidate path and the road blocking probability of each candidate path is obtained as the travel risk of each candidate path.

[0160] Optionally, after obtaining the travel risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, the method further includes:

[0161] Sort the candidate paths in ascending order according to the predicted travel time to obtain a time series;

[0162] The predicted travel time of the first candidate path is used as the first value of the first candidate path, and the product of the road blocking probability of the first candidate path and the predicted travel time of the second candidate path is used as the second value of the first candidate path, the second candidate path is the candidate path that is located after the first candidate path in the time series, and the first candidate path is any candidate path except the candidate path that is the last in the time series;

[0163] acquiring a sum of a first value of the first candidate path and a second value of the first candidate path as a risk cost value of the first candidate path;

[0164] It is determined whether the risk cost value of the first candidate path is less than the predicted travel time of the second candidate path. If so, it is determined that the first candidate path is a low-risk path.

[0165] If the candidate path meets the preset condition, taking the candidate path as the planned path for the scheduled task includes:

[0166] If the candidate path meets a preset condition, the candidate path is used as the planned path for the scheduled task, and the preset condition further includes: the candidate path belongs to the low-risk path.

[0167] The embodiment of the present application further provides a readable storage medium, which may store a computer program suitable for execution by a processor. When the computer program is executed by the processor, the steps of a method for obtaining a planned path provided in the embodiment of the present application are implemented as follows:

[0168] A method for obtaining a planned path, comprising:

[0169] Acquire a candidate path set, the candidate path set including at least two candidate paths, the candidate paths being paths from a departure point of the scheduled task to a destination of the scheduled task;

[0170] According to the historical traffic flow data, a road blocking probability of each candidate path is obtained, wherein the road blocking probability indicates the probability that the candidate path is in a blocked state at a preset time, and the preset time is the scheduled time of the scheduled task;

[0171] At a preset time, the travel risk of each candidate path is obtained according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, wherein the longer the predicted travel time and / or the greater the road blocking probability, the greater the travel risk;

[0172] If the candidate path meets a preset condition, the candidate path is used as the planned path for the scheduled task, and the preset condition includes that the travel risk of the candidate path is less than a preset threshold.

[0173] Optionally, before obtaining the road blocking probability of each candidate path according to the historical traffic flow data, the method further includes:

[0174] Generate a traffic flow curve for each candidate path according to the traffic flow of each preset time period of each candidate path on a preset date, wherein the preset time period is before the preset time, and the preset date is the scheduled date of the scheduled task;

[0175] Generate a traffic flow curve for each preset sample route according to the traffic flow of each preset sample route in each preset time period on a preset sample date;

[0176] The traffic flow curve of each candidate path, the traffic flow curve of each preset sample path, and the road status of each preset sample path are used as the historical traffic flow data, and the road status of the preset sample path indicates whether the preset sample path is in the blocked state or the non-blocked state.

[0177] Optionally, the process of obtaining the road blocking probability of the target candidate path according to the historical traffic flow data includes:

[0178] If the similarity between the traffic flow curve of the preset sample path and the traffic flow curve of the target candidate path exceeds the preset similarity, the preset sample path is used as the first sample path, and the target candidate path is any candidate path in the candidate path set;

[0179] If the road state of the first sample path indicates that the preset sample path is in the blocked state, using the first sample path as the second sample path;

[0180] The ratio of the number of the second sample paths to the number of the first sample paths is used as the road blocking probability of the target candidate path.

[0181] Optionally, before obtaining the travel risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, the method further includes:

[0182] Acquire attribute information, the attribute information including: preset attributes of each of the preset sample dates and preset attributes of the preset date, the preset attributes indicating holidays and / or weather;

[0183] According to the attribute information and the preset corresponding relationship, the matching degree between the preset attribute of each of the preset sample dates and the preset attribute of the preset date is obtained, wherein the preset corresponding relationship includes: the matching degree between different preset attributes;

[0184] If the preset attribute of the preset sample date matches the preset attribute of the preset date, the preset sample date is used as the target date;

[0185] The travel time of the candidate path at a preset time on the target date is obtained as the predicted travel time of the candidate path.

[0186] Optionally, obtaining the travel risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path includes:

[0187] The product of the predicted travel time of each candidate path and the road blocking probability of each candidate path is obtained as the travel risk of each candidate path.

[0188] Optionally, after obtaining the travel risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, the method further includes:

[0189] Sort the candidate paths in ascending order according to the predicted travel time to obtain a time series;

[0190] The predicted travel time of the first candidate path is used as the first value of the first candidate path, and the product of the road blocking probability of the first candidate path and the predicted travel time of the second candidate path is used as the second value of the first candidate path, the second candidate path is the candidate path that is located after the first candidate path in the time series, and the first candidate path is any candidate path except the candidate path that is the last in the time series;

[0191] acquiring a sum of a first value of the first candidate path and a second value of the first candidate path as a risk cost value of the first candidate path;

[0192] It is determined whether the risk cost value of the first candidate path is less than the predicted travel time of the second candidate path. If so, it is determined that the first candidate path is a low-risk path.

[0193] If the candidate path meets the preset condition, taking the candidate path as the planned path for the scheduled task includes:

[0194] If the candidate path meets a preset condition, the candidate path is used as the planned path for the scheduled task, and the preset condition further includes: the candidate path belongs to the low-risk path.

[0195] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0196] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0197] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for obtaining a planned path, characterized in that: include: Acquire a candidate path set, the candidate path set including at least two candidate paths, the candidate paths being paths from a departure point of the scheduled task to a destination of the scheduled task; According to the historical traffic flow data, a road blocking probability of each candidate path is obtained, wherein the road blocking probability indicates the probability that the candidate path is in a blocked state at a preset time, and the preset time is the scheduled time of the scheduled task; At a preset time, the travel risk of each candidate path is obtained according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, wherein the longer the predicted travel time and / or the greater the road blocking probability, the greater the travel risk; If the candidate path meets a preset condition, the candidate path is used as the planned path for the scheduled task, and the preset condition includes that the travel risk of the candidate path is less than a preset threshold; Before obtaining the road blocking probability of each candidate path according to the historical traffic flow data, the method further includes: Generate a traffic flow curve for each candidate path according to the traffic flow of each preset time period of each candidate path on a preset date, wherein the preset time period is before the preset time, and the preset date is the scheduled date of the scheduled task; Generate a traffic flow curve for each preset sample path according to the traffic flow of each preset time period on the preset sample date, wherein the preset sample path includes paths whose similarity with the candidate path is greater than a first similarity threshold, and the similarity between each path and the candidate path is obtained according to the path information of the path and the path information of the candidate path, wherein the path information includes at least one of the number of road sections, the number of intersections, the number of traffic lights, and the type of road; The traffic flow curve of each candidate path, the traffic flow curve of each preset sample path, and the road state of each preset sample path are used as the historical traffic flow data, and the road state of the preset sample path indicates whether the preset sample path is in the blocked state or the non-blocked state; The process of obtaining the road blocking probability of each candidate path according to the historical traffic flow data includes: If the similarity between the traffic flow curve of the preset sample path and the traffic flow curve of the candidate path exceeds a preset similarity, the preset sample path is used as the first sample path, and the candidate path is any candidate path in the candidate path set; If the road state of the first sample path indicates that the preset sample path is in the blocked state, using the first sample path as the second sample path; The ratio of the number of the second sample paths to the number of the first sample paths is used as the road blocking probability of the candidate path.

2. The method according to claim 1, characterized in that Before obtaining the travel risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, the method further includes: Acquire attribute information, the attribute information including: preset attributes of each of the preset sample dates and preset attributes of the preset date, the preset attributes indicating holidays and / or weather; According to the attribute information and the preset corresponding relationship, the matching degree between the preset attribute of each of the preset sample dates and the preset attribute of the preset date is obtained, wherein the preset corresponding relationship includes: the matching degree between different preset attributes; If the preset attribute of the preset sample date matches the preset attribute of the preset date, the preset sample date is used as the target date; The travel time of the candidate path at a preset time on the target date is obtained as the predicted travel time of the candidate path.

3. The method according to claim 1, characterized in that: The obtaining of the travel risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path includes: The product of the predicted travel time of each candidate path and the road blocking probability of each candidate path is obtained as the travel risk of each candidate path.

4. The method according to claim 1, characterized in that After obtaining the travel risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, the method further includes: Sort the candidate paths in ascending order according to the predicted travel time to obtain a time series; The predicted travel time of the first candidate path is used as the first value of the first candidate path, and the product of the road blocking probability of the first candidate path and the predicted travel time of the second candidate path is used as the second value of the first candidate path, the second candidate path is the candidate path that is located after the first candidate path in the time series, and the first candidate path is any candidate path except the candidate path that is the last in the time series; acquiring a sum of a first value of the first candidate path and a second value of the first candidate path as a risk cost value of the first candidate path; Determine whether the risk cost value of the first candidate path is less than the predicted travel time of the second candidate path, and if so, determine that the first candidate path is a low-risk path; If the candidate path meets the preset condition, taking the candidate path as the planned path for the scheduled task includes: If the candidate path meets a preset condition, the candidate path is used as the planned path for the scheduled task, and the preset condition further includes: the candidate path belongs to the low-risk path.

5. A device for acquiring a planned path, characterized in that: include: A path set acquisition unit, used to acquire a candidate path set, wherein the candidate path set includes at least two candidate paths, and the candidate paths are paths from a departure point of a scheduled task to a destination of the scheduled task; A probability acquisition unit, configured to acquire a road blocking probability of each candidate path according to historical traffic flow data, wherein the road blocking probability indicates a probability that the candidate path is in a blocked state at a preset time, and the preset time is a scheduled time of the scheduled task; A traffic risk acquisition unit, configured to acquire the traffic risk of each candidate path according to the predicted traffic time of each candidate path and the road blocking probability of each candidate path, wherein the longer the predicted traffic time and / or the greater the road blocking probability, the greater the traffic risk; A planning result acquisition unit, configured to use the candidate path as the planned path for the scheduled task if the candidate path meets a preset condition, wherein the preset condition includes that the travel risk of the candidate path is less than a preset threshold; The acquisition device of the planned path is also used for: Generate a traffic flow curve for each candidate path according to the traffic flow of each preset time period of each candidate path on a preset date, wherein the preset time period is before the preset time, and the preset date is the scheduled date of the scheduled task; Generate a traffic flow curve for each preset sample path according to the traffic flow of each preset time period on the preset sample date, wherein the preset sample path includes paths whose similarity with the candidate path is greater than a first similarity threshold, and the similarity between each path and the candidate path is obtained according to the path information of the path and the path information of the candidate path, wherein the path information includes at least one of the number of road sections, the number of intersections, the number of traffic lights, and the type of road; The traffic flow curve of each candidate path, the traffic flow curve of each preset sample path, and the road state of each preset sample path are used as the historical traffic flow data, and the road state of the preset sample path indicates whether the preset sample path is in the blocked state or the non-blocked state; The probability acquisition unit is specifically used for: If the similarity between the traffic flow curve of the preset sample path and the traffic flow curve of the candidate path exceeds a preset similarity, the preset sample path is used as the first sample path, and the candidate path is any candidate path in the candidate path set; If the road state of the first sample path indicates that the preset sample path is in the blocked state, using the first sample path as the second sample path; The ratio of the number of the second sample paths to the number of the first sample paths is used as the road blocking probability of the candidate path.

6. The device according to claim 5, characterized in that The traffic risk acquisition unit is used to acquire the traffic risk of each candidate path according to the predicted travel time of each candidate path and the road blocking probability of each candidate path, including: The travel risk acquisition unit is specifically used to: acquire the product of the predicted travel time of each candidate path and the road blocking probability of each candidate path as the travel risk of each candidate path.

7. A device for acquiring a planned path, characterized in that: include: Memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the method for acquiring a planned path as described in any one of claims 1 to 4.

8. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the method for acquiring a planned path as claimed in any one of claims 1 to 4 is implemented.