A navigation route recommendation method and device, electronic equipment and medium

Abstract

This application relates to the field of navigation planning technology, and provides a method, device, electronic device, and medium for recommending navigation routes. The method includes: determining the route start point, route end point, and target time information based on user instructions; determining multiple initial routes from the route start point to the route end point and their distances based on map information; determining all travel options based on historical driving datasets; determining the traffic efficiency corresponding to each travel option based on the historical driving datasets; calculating the expected function value of each travel option according to a driving expectation function scheme based on the corresponding traffic efficiency and route distance; and selecting the travel option with the smallest of a preset number of expected function values ​​as the recommendation result. This application provides more accurate and thorough calculations, allowing users to directly obtain effective and user-relevant recommendation results, thus improving the user experience.

Description

Technical Field

[0001] This application relates to the field of navigation planning technology, and in particular to a method, apparatus, electronic device and medium for recommending navigation routes. Background Technology

[0002] In recent years, navigation software has been widely used in various mobile terminals and in-vehicle systems, providing users with map-based route planning and real-time navigation functions. With the increasing sophistication of user needs and the development of big data analytics, navigation software has incorporated route congestion factors into its route planning time calculations, enabling users to more accurately understand route conditions and plan their travel more effectively.

[0003] Currently, route planning time calculations are rather simplistic, typically relying on historical congestion data from big data to directly estimate the time required for a planned route. However, the current estimation methods lack detailed descriptions of congestion, are not thorough enough in their calculations, and produce inaccurate results. Furthermore, the application software does not provide users with information on all routes during each planning session. Users must issue multiple commands to the application to obtain specific information on different planned routes and manually compare all the planned routes to determine the one that best suits their needs, resulting in a poor user experience.

[0004] Therefore, how to provide a solution to the above-mentioned technical problems is a problem that needs to be solved by those skilled in the art. Summary of the Invention

[0005] In view of this, embodiments of this application provide a method, apparatus, electronic device, and medium for recommending navigation routes to solve the problem that path planning in the prior art does not meet user needs.

[0006] A first aspect of this application provides a method for recommending navigation routes, comprising:

[0007] Obtain user instructions, and determine the route start point, route end point, and target time information based on the user instructions. The target time information includes at least one of the target departure time interval and the target arrival time interval.

[0008] Based on map information, multiple initial routes from the starting point to the ending point of the route and the route distance of each initial route are determined;

[0009] Based on the historical driving dataset corresponding to the map information, all travel plans are determined. Each travel plan includes an initial route and a set of driving action times that completely match the target time information. Each set of driving action times includes at least one of a departure time corresponding to the target departure time interval and an arrival time corresponding to the target arrival time interval.

[0010] Based on historical driving datasets, the traffic efficiency corresponding to each travel option is determined; traffic efficiency is used to indicate the degree of road congestion.

[0011] For each travel plan, based on the corresponding traffic efficiency and route distance, the expected function value for each departure time is calculated according to the travel expectation function scheme. In the travel expectation function scheme, the expected function value is negatively correlated with traffic efficiency and positively correlated with route distance.

[0012] The travel plan with the smallest expected function value among a preset number of options is sent as the recommended result of the user's command to the display terminal.

[0013] A second aspect of this application provides a navigation route recommendation device, comprising:

[0014] The preprocessing module is used to obtain user instructions and determine the route start point, route end point and target time information based on the user instructions. The target time information includes at least one of the target departure time interval and the target arrival time interval.

[0015] The initial route module is used to determine multiple initial routes from the starting point to the ending point of the route and the route distance of each initial route based on map information;

[0016] The travel plan module is used to determine all travel plans based on the historical driving dataset corresponding to the map information. Each travel plan includes an initial route and a set of driving action times that completely match the target time information. Each set of driving action times includes at least one of a departure time corresponding to the target departure time interval and an arrival time corresponding to the target arrival time interval.

[0017] The traffic efficiency module is used to determine the traffic efficiency of each travel option based on historical driving datasets; traffic efficiency is used to indicate the degree of road congestion.

[0018] The expected calculation module is used to calculate the expected function value for each departure time based on the corresponding traffic efficiency and route distance for each travel plan, according to the travel expected function scheme. In the travel expected function scheme, the expected function value is negatively correlated with traffic efficiency and positively correlated with route distance.

[0019] The recommendation module is used to send the travel plan with the smallest expected function value from a preset number of options as the recommendation result of the user's command to the display terminal.

[0020] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method.

[0021] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0022] The beneficial effects of this application embodiment compared with the prior art include at least the following: This application embodiment determines travel plans that conform to user instructions, calculates the traffic efficiency of each travel plan based on historical driving datasets, and calculates the expected function value based on traffic efficiency and route distance as the basis for determining the final recommendation result. The calculation of traffic efficiency and driving expected function schemes based on historical driving datasets with nonlinear road segment delays is more accurate and thorough. Users do not need to perform multiple operations and manual analysis to directly obtain effective and user-relevant recommendation results, thus improving the user experience. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram illustrating one application scenario of this application.

[0025] Figure 2 This is a flowchart illustrating a navigation route recommendation method provided in an embodiment of this application;

[0026] Figure 3 This is a schematic diagram of the structure of a navigation route recommendation device provided in an embodiment of this application;

[0027] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0028] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0029] The following will describe in detail, with reference to the accompanying drawings, a method, apparatus, electronic device, and medium for recommending navigation routes according to embodiments of this application.

[0030] Figure 1 This is a schematic diagram illustrating an application scenario according to an embodiment of this application. The application scenario may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a server 104, and a network 105.

[0031] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be hardware or software. When the first terminal device 101, the second terminal device 102, and the third terminal device 103 are hardware, they can be various electronic devices with displays and supporting communication with the server 104, including but not limited to vehicle systems, smartphones, tablets, laptops, and desktop computers. When the first terminal device 101, the second terminal device 102, and the third terminal device 103 are software, they can be installed in the aforementioned electronic devices. The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be implemented as multiple software programs or software modules, or as a single software program or software module; this application embodiment does not impose any limitations on this. Furthermore, various applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as data processing applications, instant messaging tools, social platform software, search applications, shopping applications, etc.

[0032] Server 104 can be a server that provides various services, such as a backend server that receives requests sent by terminal devices with which it has established communication connections. This backend server can receive and analyze the requests sent by the terminal devices and generate processing results. Server 104 can be a single server, a server cluster consisting of several servers, or a cloud computing service center. This application embodiment does not limit this.

[0033] It should be noted that the server 104 can be either hardware or software. When the server 104 is hardware, it can be various electronic devices that provide various services to the first terminal device 101, the second terminal device 102, and the third terminal device 103. When the server 104 is software, it can be multiple software programs or software modules that provide various services to the first terminal device 101, the second terminal device 102, and the third terminal device 103, or it can be a single software program or software module that provides various services to the first terminal device 101, the second terminal device 102, and the third terminal device 103. This application embodiment does not impose any limitations on this.

[0034] Network 105 can be a wired network using coaxial cable, twisted pair, and fiber optic connection, or it can be a wireless network that enables interconnection of various communication devices without wiring, such as Bluetooth, Near Field Communication (NFC), and Infrared. This application embodiment does not limit this.

[0035] It should be noted that the specific types, quantities and combinations of the first terminal device 101, the second terminal device 102, the third terminal device 103, the server 104 and the network 105 can be adjusted according to the actual needs of the application scenario, and this application embodiment does not impose any restrictions on this.

[0036] Figure 2 This is a flowchart illustrating a navigation route recommendation method provided in an embodiment of this application. Figure 2 The method for recommending navigation routes is executed by the controller, which can be... Figure 1 This is implemented through a first terminal device, a second terminal device, a third terminal device, or a server. For example... Figure 2 As shown, the recommended method includes:

[0037] S201: Obtain user instructions, and determine the route start point, route end point and target time information based on the user instructions. The target time information includes at least one of the target departure time interval and the target arrival time interval.

[0038] S202: Based on map information, determine multiple initial routes from the starting point to the ending point of the route and the route distance of each initial route;

[0039] S203: Based on the historical driving dataset corresponding to the map information, determine all travel plans. Each travel plan includes an initial route and a set of driving action times that completely match the target time information. Each set of driving action times includes at least one of a departure time corresponding to the target departure time interval and an arrival time corresponding to the target arrival time interval.

[0040] S204: Based on historical driving datasets, determine the traffic efficiency corresponding to each travel option; traffic efficiency is used to indicate the degree of road congestion.

[0041] S205: For each travel plan, based on the corresponding traffic efficiency and route distance, the expected function value for each departure time is calculated according to the travel expectation function scheme; in the travel expectation function scheme, the expected function value is negatively correlated with traffic efficiency and positively correlated with route distance;

[0042] S206: Send the travel plan with the smallest expected function value out of a preset number of options as the recommended result of the user's command to the display terminal.

[0043] Understandably, after receiving user instructions, the method in this embodiment determines the route start and end points based on the user instructions to plan multiple initial routes. It also determines the target time information based on the user instructions and iterates through all travel options using historical driving datasets. Each travel option includes an initial route and a set of driving action times that perfectly match the target time information. Then, for each travel option, the traffic efficiency is determined based on the historical driving dataset. Based on the traffic efficiency and route distance, a comprehensive calculation is performed using a driving expectation function scheme. The obtained expectation function value is used to measure the driving effect of the travel option; the smaller the preset function value, the better the driving experience. Multiple travel options with the smallest preset function values ​​are selected as recommended options and sent to the display terminal. The user obtains the recommended results through the display terminal without needing multiple operations or manual analysis. The recommended results directly show the user the most accurate, comprehensive, and best-performing travel options, thus improving the user experience of route planning.

[0044] It is understood that users issue user commands to the execution controller of this embodiment through the human-computer interaction interface. The user commands may be in the form of text, voice, etc. Parsing the user commands can yield information such as the route start point, route end point, and target time.

[0045] The starting and ending points of the route are the most fundamental basis for route planning. The final planned route must start from the starting point and end at the ending point. When executing step S202 based on the starting and ending points, map information serves as a prerequisite for determining the route distance. The map information includes the geographic information of all roads in the current city or region. Based on the map information, conventional path planning strategies such as Dijkstra's algorithm, A*, RRT (Rapidly-Exploring Random Trees), and RRT* are used to determine multiple initial routes. The number of initial routes is determined by a pre-set number of initial routes, which can be set to 3 or 4, depending on the actual hardware and computing resources and user needs.

[0046] It is understandable that the starting point of each initial route determined in step S202 is the same as the route starting point mentioned above, and the ending point is the same as the route ending point mentioned above. For each initial route, the route distance will not change with the departure time or arrival time, and will not change after being determined in step S202. However, the smoothness and travel time of each initial route are not fixed quantities. The smoothness may vary at different departure times or arrival times, which will lead to different travel times.

[0047] It is understandable that the specific information on traffic flow and travel time is implied in the specific numerical changes of vehicle speed and acceleration. Therefore, by collecting historical data on vehicle speed and acceleration from all roads and merging them, a historical travel dataset is obtained. Based on the nonlinear characteristics of the historical travel dataset, a nonlinear road segment delay model is applied to calculate the traffic flow of each road at a specific time and further estimate the travel time of each road. Therefore, steps S203 and S204 are executed based on the historical travel dataset to determine the travel plan that meets the target time information and the corresponding traffic efficiency for each initial route.

[0048] The target time information is also determined based on user instructions. Compared to the relatively fixed and unique route start and end points, target time information is more flexible, and can be at least one of the target departure time interval and the target arrival time interval.

[0049] Specifically, if the user instruction includes a definite departure time interval with two endpoints, then that departure time interval is directly used as the target departure time interval. Similarly, if the user instruction includes a definite arrival time interval with two endpoints, then that arrival time interval is directly used as the target arrival time interval.

[0050] If the user command specifies a departure time with a time point and a time relationship (e.g., not earlier than, later than, not later than, or earlier than the departure time), the corresponding target departure time interval can be determined based on this time point and time relationship. In this case, a suggested time length can be returned based on the user command, allowing the user to add a time interval length command based on that time point. The time length could be, for example, 2 hours or 30 minutes, which the user can choose according to their specific needs. Finally, the time point in the user command is determined as one endpoint of the target departure time interval. The time relationship in the user command determines whether this endpoint is the left or right endpoint. The time length in the user command is then used as the target departure time interval length, ultimately determining an accurate target departure time interval. For example, if the time point is 7:00 AM, the time relationship is "not earlier than" and the time length is 30 minutes, then the target departure time interval is from 7:00 AM to 7:30 AM. The target arrival time interval is set similarly, also based on the time point, time relationship, and time length.

[0051] If the user instruction specifies only one departure time without setting any time relationship, the target departure time interval will only include this one time point, and step S203 can be skipped to determine that this time point is the only departure time. Similarly, if the user instruction specifies only one arrival time without setting any time relationship, the target arrival time interval will only include this one time point.

[0052] Specifically, in step S203, the target time information is used as the basis for calculating route time. Calculations are made based on historical driving datasets, and the target time information serves as a constraint. For example, if the target time information is a target departure time interval, the departure time is initially determined from this interval according to a preset unit duration. For instance, if the target departure time interval is from 7:00 AM to 7:30 AM, and the preset unit duration can be set to 5 minutes or 10 minutes, the initially determined departure times include 7:00 AM, 7:05 AM, 7:10 AM, 7:15 AM, 7:20 AM, 7:25 AM, and 7:30 AM. Then, for each departure time, the total time spent traveling each initial route is calculated based on the historical driving dataset, thus obtaining the corresponding arrival time for each departure time. It is known that the traffic efficiency of each road changes over time; for example, during morning and evening rush hours, road traffic efficiency decreases, and the time spent traveling through roads increases. Therefore, for different departure times, it is necessary to calculate the total time spent traveling from that departure time. The target arrival time interval serves as a constraint on the arrival time. After obtaining all arrival times, we then analyze whether the arrival times satisfy the target arrival time interval in the target time information. Of course, if there is no target arrival time interval in the target time information, that is, there is no constraint on the arrival time, it is not necessary to analyze whether the arrival times satisfy the target time information.

[0053] Correspondingly, if the target time information does not contain a target departure time interval but only a target arrival time interval, one or more arrival times are initially determined from the target arrival time interval according to a preset unit duration. Then, based on the historical driving dataset, the total time and departure time of each initial route are reversed for each arrival time.

[0054] Understandably, in step S203, when determining the travel plan based on the historical driving dataset, the travel action times for each initial route that match the target time information are calculated. If the target time information only contains the target departure time interval, one or more departure times can be directly determined from the target departure time interval according to a preset unit duration. If the target time information only contains the target arrival time interval, one or more arrival times can be directly determined from the target arrival time interval according to a preset unit duration. If the target time information includes both the target departure time interval and the target arrival time interval, the interval with the shorter interval length can be selected from the target departure time interval and the times within that interval can be initially determined according to a preset unit duration. Based on these times, another time can be calculated, and then the times that match the corresponding interval can be selected from the calculated times. For example, initially... Once the departure time is determined, the corresponding arrival time is calculated, and arrival times that match the target arrival time interval are selected. Similarly, once the arrival time is initially determined, the corresponding departure time is calculated, and departure times that match the target departure time interval are selected. Furthermore, if the target time information includes both the target departure time interval and the target arrival time interval, the interval lengths can be disregarded. Instead, a pre-set calculation order can be used: first, determine the time within one interval, calculate the corresponding time within the other interval, and then select the calculated times based on the other interval. This calculation order can be either first determining the departure time from the target departure time interval, calculating the corresponding arrival time, and selecting arrival times that match the target arrival time interval, or first determining the arrival time from the target arrival time interval, calculating the corresponding departure time, and selecting departure times that match the target departure time interval.

[0055] Understandably, when the target time information includes both the target departure time range and the target arrival time range, there may be situations where there is no departure time that matches the target time information. One situation is that the journey takes a short time and the arrival time will be earlier. For example, the target departure time range is 7:00 to 7:30, and the target arrival time range is 11:30 to 12:30. The longest journey time for each initial route is 3 hours. Assuming that the target departure time range is met, even if the latest departure time is 7:30, the calculated arrival time based on the longest journey time of 3 hours will be earlier than the earliest time of the target arrival time range, 11:30. Another situation is that the journey takes a long time and the arrival time is unlikely to be timely. For example, the target departure time range is 7:00 to 7:30, and the target arrival time range is 11:30 to 12:30. The shortest journey time for each initial route is 6 hours. Even if the earliest departure time is 7:00, the arrival time based on the shortest journey time of 6 hours will be later than the latest time of the target arrival time range, 12:30.

[0056] If no travel option matches the target time information, the system can either return an empty planning result or relax the constraints to determine alternative travel options. These alternative options will then be used for subsequent steps. When outputting the recommendation result, a prompt will be added regarding the constraints met by the current route. Specifically, the most stringent constraint (departure time simultaneously meeting both the target departure and arrival time intervals) will be temporarily removed. Alternative travel options whose departure times match the target departure time interval will be determined solely based on historical driving datasets, without considering whether the arrival time matches the target arrival time interval. Similarly, alternative travel options whose arrival times match the target arrival time interval will be determined solely based on historical driving datasets, without considering whether the derived departure time matches the target departure time interval. This provides users with more possible alternative options.

[0057] Understandably, after removing the constraint that requires both the departure time and the arrival time to conform to the target departure time interval within the same set of travel actions, there are two scenarios for alternative travel plans: the departure time conforms to the target departure time interval, but the arrival time corresponding to the departure time does not conform to the target arrival time interval; the arrival time conforms to the target arrival time interval, but the departure time corresponding to the arrival time does not conform to the target departure time interval.

[0058] At this point, several alternative departure times are available. These alternative travel plans can be directly used to execute steps S204-S205, or one or more alternative travel plans can be selected from the alternative travel plans based on the filtering criteria determined by the user's needs before executing subsequent steps S204-S205. For example, if the user's need is to be as close as possible to the target time information, i.e., allowing late departure or late arrival but with a short time difference, or allowing early departure or early arrival but with a short time difference, then the filtering criterion is that the difference between the departure time or arrival time and the target time information is the shortest possible time difference. Another example is that the user's need is to not be late, i.e. allowing early arrival or early departure, but not lateness, then the filtering criterion is that the arrival time is not later than the right end of the target arrival time interval. Yet another example is that the user's need is to not depart early, i.e. allowing late arrival or late departure, but not early departure, then the filtering criterion is that the departure time is not later than the left end of the target departure time interval.

[0059] Furthermore, after determining the departure time in step S203, step S204 is executed to calculate the traffic efficiency based on the historical driving dataset corresponding to the travel plan. It is important to note that each travel plan in steps S204-S206 includes a unique initial route and a unique set of driving action times. For example, initial routes may have r1 and r2, with departure times t11, t12, and t13 for initial route r1, and t21, t22, and t23 for initial route r2. Even if there are identical time values ​​between t11-t13 and t21-t23 (e.g., both t11 and t23 are 7:15), since these two departure times correspond to different initial routes, they are not considered the same departure time. There is no correlation between two departure times belonging to different initial routes; each is treated as an independent parameter for subsequent steps.

[0060] The traffic efficiency at a certain point on the initial route is used to characterize whether the traffic flow is smooth when vehicles pass through that point. If the traffic efficiency is high, there is no congestion at that point, and vehicles can travel at a relatively high and uniform speed when passing through that point. If the traffic efficiency is low, there is some congestion at that point, and vehicles usually travel at a low speed or frequently experience braking and acceleration when passing through that point.

[0061] Therefore, the traffic efficiency at a given location is typically determined by the vehicle's driving performance, which includes speed and acceleration. Further, the maximum traffic efficiency at a location corresponds to the vehicle's expected driving performance, which refers to the vehicle's performance on a clear road. This clear road can be other roads on the initial route or the current location being calculated, which is typically in a clear state. Under normal conditions, the vehicle can maintain its maximum speed and expected acceleration, i.e., a relatively high and constant speed. It is understandable that by comparing the actual and expected driving performance at that location in the historical driving dataset, it can be analyzed whether the traffic efficiency at that location has reached its maximum.

[0062] Understandably, according to steps S201-S204, all feasible travel plans have been determined. Each travel plan includes a specific travel time and initial route. When a vehicle executes a travel plan, it will travel according to the travel time and initial route. The problem to be solved in step S205 is how to determine the travel plan that best meets the user's needs from all the currently obtained travel plans and return it as a recommendation result. To this end, step S205 uses a travel expectation function to calculate the traffic efficiency and route distance for each travel plan. The independent variables of this travel expectation function include the traffic efficiency and route distance of the travel plan, and the function result is the expectation function value. User needs generally tend towards shorter route distances and higher traffic efficiency. In this method, the relationship between the function result and each independent variable in the travel expectation function is as follows: the expectation function value is negatively correlated with traffic efficiency and positively correlated with route distance. Therefore, the larger the route distance, the larger the expectation function value; the higher the traffic efficiency, the smaller the expectation function value. In other words, a smaller expectation function value indicates a shorter route distance or higher traffic efficiency, thus user needs tend towards a smaller expectation function value.

[0063] Understandably, after obtaining the expected function value for each travel option in step S205, all expected function values ​​are compared, and the travel options with the smallest expected function values ​​(a preset number of options) are selected as recommended options. For example, if the preset number is 3, the travel options corresponding to the 3 smallest expected function values ​​are output as the recommendation results. This recommendation result takes into account both route distance and travel efficiency, and can comprehensively meet the user needs in driving navigation scenarios.

[0064] The method in this application embodiment determines travel plans that conform to user instructions, calculates the traffic efficiency of each travel plan based on historical driving datasets, and calculates the expected function value based on traffic efficiency and route distance as the basis for determining the final recommendation result. The calculation of traffic efficiency and the expected function based on historical driving datasets characterized by nonlinear road segment delays is more accurate and thorough. Users do not need multiple operations and manual analysis to directly obtain effective and user-relevant recommendation results, thus improving the user experience. In some embodiments, since the traffic efficiency of consecutive location points is usually similar, the initial route can be segmented based on historical driving datasets to obtain multiple travel segments. The traffic efficiency within each travel segment should have a uniform performance. Furthermore, traffic efficiency is used to represent the congestion level of the travel segment and can be measured by a nonlinear road segment delay model. In this case, step S204, which determines the traffic efficiency corresponding to each travel plan based on historical driving datasets, may include:

[0065] For each travel plan, based on historical driving datasets, the corresponding initial route is divided into multiple travel segments;

[0066] Based on historical driving datasets, the traffic rate ratio within the time period of driving through each road segment is integrated to obtain the traffic efficiency of the corresponding road segment.

[0067] The throughput ratio is the ratio of the real-time throughput of the travel plan corresponding to the same location point to the preset throughput ratio. The real-time throughput ratio is the ratio of the speed to the acceleration of the corresponding travel plan in the historical driving data set.

[0068] Accordingly, the traffic efficiency of each road segment was calculated using a nonlinear road segment delay model, and the calculation process is as follows:

[0069]

[0070] Among them, L ij Let c be the traffic efficiency of the i-th road segment corresponding to the j-th travel plan. ij Let c be the real-time traffic rate at a certain location on the i-th road segment corresponding to the j-th travel plan. ref-i Let $\frac{i}{i}$ be the preset throughput for the corresponding location point in the $i$-th traffic segment. The traffic efficiency L is obtained by integrating the traffic efficiency ratios of all traffic rate ratios on the traffic segment over location point x, or over time t. ij The reason we can integrate over time t is that there is an implicit correspondence between the location points the vehicle passes through and the time. Therefore, the integral of the throughput rate of all location points x on the passage can also be integrated over time t.

[0071] Real-time traffic flow rate is determined based on real-time driving performance. The specific values ​​for real-time driving performance are selected from the historical driving dataset corresponding to the historical data. The real-time traffic flow rate is as follows:

[0072]

[0073] Where v ij and a ij These represent the speed and acceleration at a specific location in the historical driving dataset, corresponding to the j-th travel plan and the i-th travel segment, respectively.

[0074] The preset traffic rate can be a predetermined value or a value calculated based on predetermined expected traffic performance. The calculation process includes:

[0075]

[0076] Where v ref-i and a ref-i These represent the speed and acceleration, respectively, in the expected driving performance for the i-th road segment.

[0077] It is understandable that, regardless of whether it is the expected driving performance or the real-time driving performance, there is a corresponding formula between speed and acceleration: v(x) = u × e a(x)×Δt , where v(x) and a(x) are the velocity and acceleration of position x, respectively, u is the historical velocity at the previous moment, and Δt is the time difference between u and the current v(x).

[0078] Furthermore, after the initial route is divided into multiple travel segments, the calculation of the initial route based on the travel expectation function scheme is equivalent to the sum of the calculations for the multiple travel segments. Specifically, based on the specific calculation of traffic efficiency mentioned above, an example of a travel expectation function scheme can be the ratio of distance to speed, where speed is the product of expected travel speed and traffic efficiency. In this case, the travel expectation function scheme corresponding to any travel plan is as follows:

[0079] The sum of the expected travel time for all road segments corresponding to the travel plan;

[0080] The expected travel time for each road segment is specifically the ratio of the road segment distance to the expected travel speed;

[0081] The expected traffic speed is the product of the preset speed and the corresponding traffic efficiency.

[0082] Specifically, the driving expectation function scheme can be expressed as:

[0083] Among them, T j Let d be the expected function value corresponding to the j-th travel option. i and V i V represents the traffic efficiency and preset speed of the i-th road segment corresponding to the j-th travel plan. i ×L ij To achieve the expected traffic speed, This represents the expected travel time for the i-th road segment. The preset speed is the same as the preset driving performance speed mentioned above.

[0084] Furthermore, if a certain road segment corresponding to a travel plan is not congested, it is called a non-congested road segment, with very high traffic efficiency, which can be directly recorded as 100% to save computational resources related to traffic efficiency. Based on this, the complete initial route corresponding to the travel plan can be analyzed in advance to determine if there are congested road segments. The traffic efficiency of non-congested road segments is directly recorded as 100%, skipping the calculation of traffic efficiency. Congested road segments have lower traffic efficiency and varying degrees of congestion, and specific throughput ratios and traffic efficiencies are calculated for congested road segments. Therefore, for each travel plan, the process of dividing the corresponding initial route into multiple road segments based on historical driving datasets can include:

[0085] For each departure time, based on historical driving datasets, determine whether there are congested road sections;

[0086] If so, for each travel plan, based on the historical driving dataset, the corresponding initial route is divided into multiple traffic segments; each traffic segment is either a congested segment or a non-congested segment.

[0087] If not, the initial route is determined to include only non-congested road sections;

[0088] The traffic efficiency of non-congested road sections is preset to 1.

[0089] It is understandable that the driving expectation function scheme is essentially a functional relationship between traffic efficiency and route distance, corresponding to the expected function value, which can be described as: Expected function value = f(traffic efficiency, route distance). Both traffic efficiency and route distance will affect the expected function value. Considering the different degrees of preference for traffic efficiency and route distance in user needs, the weights of traffic efficiency and route distance can be flexibly adjusted to meet user needs. In this case, the weight of traffic efficiency is denoted as the first weight, and the weight of route distance is denoted as the second weight. The first weight and the second weight are also included as influencing variables in the driving expectation function scheme, so:

[0090] Expected function value = f(traffic efficiency, first weight, route distance, second weight).

[0091] Therefore, in some embodiments, the degree of negative correlation between the expected function value and traffic efficiency is determined by a first weight.

[0092] The degree of positive correlation between the expected function value and the route distance is determined by the second weight.

[0093] It is understandable that the correlation between the independent variable and the expected function value is positively correlated with the magnitude of the weight: when the first weight increases, the correlation between the expected function value and the traffic efficiency increases; when the first weight decreases, the correlation between the expected function value and the traffic efficiency decreases; the same applies to the second weight.

[0094] When users prioritize distance over travel efficiency, the second weight can be set to be larger and the first weight to be smaller.

[0095] Furthermore, the above travel expectation function scheme does not consider the impact of travel time. In reality, travel time is also significant for users choosing travel options. For example, users may want the total travel time to be earlier, or they may want to depart later, or they may want to arrive earlier, etc. Therefore, travel time information can be added as an independent variable to the travel expectation function scheme. In this case, the travel expectation function scheme is:

[0096] Expected function value = f(traffic efficiency, route distance, travel time information).

[0097] Accordingly, for each travel plan, based on the corresponding traffic efficiency and route distance, the process of calculating the expected function value at each departure time according to the travel expectation function scheme includes:

[0098] For each travel plan, based on the corresponding travel time information, corresponding travel efficiency and route distance, the expected function value for each departure time is calculated according to the travel expectation function scheme.

[0099] Travel time information includes at least one of the following: departure time, arrival time, and travel time corresponding to the travel plan.

[0100] Understandably, when the specific expected content of user needs differs, the correlation between travel time information and the expected function value will also change, including whether the correlation is negative or positive, and the degree of correlation. Typically, travel time information can be set to include travel time by default, and the expected function value can be set to be positively correlated with travel time, with the degree of positive correlation determined by a weight. Users can manually submit settings corresponding to their needs via user commands: travel time information, correlation, and degree of correlation. Therefore, for each travel plan, before calculating the expected function value for each travel plan based on the corresponding travel time information, corresponding travel efficiency, and route distance, the following steps are also included:

[0101] Based on user instructions, determine one or more passage time information, and determine the correlation between the expected function value and each passage time information and the degree of correlation.

[0102] The correlation is either negative or positive.

[0103] Understandably, if, based on user instructions, the travel time information is determined to be the arrival time and the correlation between the expected function value and the arrival time is positive, then travel options with earlier arrival times have smaller expected function values ​​and are more likely to be included in the recommendation results, meaning that the user's demand is for the vehicle to arrive earlier. Similarly, if, based on user instructions, the travel time information is determined to be the departure time and the correlation between the expected function value and the departure time is negative, then travel options with later departure times have smaller expected function values ​​and are more likely to be included in the recommendation results, meaning that the user's demand is for the vehicle to depart later.

[0104] It is understandable that the weights of the above independent variables are a quantitative representation of the importance of different independent variables in the driving expectation function scheme of this method. The larger the weight value, the higher the importance of the corresponding independent variable in determining the overall expectation function value. Assuming that the independent variables of the driving expectation function scheme in one embodiment include departure time, distance, and traffic efficiency, if the user instruction does not make any decision and does not set any priority, it will run according to the default priority. The default priority may include distance being better than traffic efficiency being better than departure time, and the weights of the independent variables will be determined according to this priority. If the user instruction adjusts the priority or weight, the driving expectation function scheme will be calculated according to the adjusted weight. In addition, the subsequent execution of the recommendation results can further reflect the user's preference for each independent variable. Therefore, the weight of each independent variable can be adjusted according to the travel scheme selected for execution in the recommendation results.

[0105] In addition, the priority setting can also be used to specify the step-by-step filtering of each travel option by the travel expectation function scheme. That is, the execution process of the function scheme includes: performing the filtering operation step by step according to the priority from high to low, and finally obtaining the remaining recommendation results. The filtering operation includes: for each priority, taking the sort number as the expectation function value, sorting the travel options according to the correlation between the expectation function value and the independent variable corresponding to each priority, and selecting the corresponding number of travel options with the smallest expectation function value.

[0106] For example, the priority order from highest to lowest is distance, then efficiency, then time. First, a selection process is performed based on distance. Since the expected function value is positively correlated with distance, and the ultimate goal is to minimize the expected function value, the five travel options with the shortest distances are selected from all options. Next, a selection process is performed based on efficiency. Since the expected function value is negatively correlated with efficiency, and the ultimate goal is to minimize the expected function value, the three travel options with the highest efficiency are selected from the previous five. Finally, a selection process is performed based on time. Assuming the expected function value is positively correlated with time, and the ultimate goal is to minimize the expected function value, the two travel options with the shortest time are selected from the remaining three options. These two departure times and corresponding initial routes are then used as the recommended results for the user's command and sent to the display terminal. The specific figures for the travel options above are for illustrative purposes only and can be adjusted according to actual conditions and user needs. No restrictions are imposed here.

[0107] It is understandable that, in addition to the function relationship expression and step-by-step filtering operation mentioned above, the specific implementation of the expected driving function scheme can be set to other forms according to the actual situation and user needs, and no restrictions are imposed here.

[0108] All the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here. It should be understood that the sequence number of each step in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The description of "when..." in the above embodiments is only used to describe the corresponding information, environment, and state, and does not constitute a limitation on the timing.

[0109] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0110] Figure 3 This is a schematic diagram of a navigation route recommendation device provided in an embodiment of this application. Figure 3 As shown, the recommended device includes:

[0111] Preprocessing module 301 is used to acquire user instructions and determine the route start point, route end point and target time information based on the user instructions. The target time information includes at least one of the target departure time interval and the target arrival time interval.

[0112] The initial route module 302 is used to determine multiple initial routes from the starting point to the ending point of the route and the route distance of each initial route based on map information;

[0113] The departure time module 303 is used to determine all departure times that meet the target time information when traveling on each initial route, based on the historical driving dataset.

[0114] The traffic efficiency module 304 is used to determine the traffic efficiency corresponding to each departure time when traveling on the corresponding initial route based on historical driving datasets; traffic efficiency is used to indicate the degree of road congestion.

[0115] The expected calculation module 305 is used to calculate the expected function value for each departure time based on the corresponding traffic efficiency and route distance, according to the driving expected function scheme. In the driving expected function scheme, the expected function value is negatively correlated with traffic efficiency and positively correlated with route distance.

[0116] The recommendation module 306 is used to send the preset number of departure times and corresponding initial routes with the minimum expected function value as the recommendation results of the user command to the display terminal.

[0117] The device in this application embodiment determines travel plans that conform to user instructions, calculates the traffic efficiency of each travel plan based on historical driving datasets, and calculates the expected function value based on traffic efficiency and route distance as the basis for determining the final recommendation result. The calculation of traffic efficiency and expected function plan based on historical driving datasets with nonlinear road segment delays is more accurate and thorough. Users do not need to perform multiple operations and manual analysis to directly obtain effective and user-relevant recommendation results, thus improving the user experience.

[0118] In an exemplary embodiment, the traffic efficiency module is specifically used for:

[0119] For each travel plan, based on historical driving datasets, the corresponding initial route is divided into multiple travel segments;

[0120] Based on historical driving datasets, the traffic rate ratio within the time period of driving through each road segment is integrated to obtain the traffic efficiency of the corresponding road segment.

[0121] The throughput ratio is the ratio of the real-time throughput of the travel plan corresponding to the same location point to the preset throughput ratio. The real-time throughput ratio is the ratio of the speed and acceleration of the corresponding travel plan and location point in the historical driving data.

[0122] In an exemplary embodiment, the specific driving expectation function scheme corresponding to any travel plan is as follows:

[0123] The sum of the expected travel time for all road segments corresponding to the travel plan;

[0124] The expected travel time for each road segment is specifically the ratio of the road segment distance to the expected travel speed;

[0125] The expected traffic speed is the product of the preset speed and the traffic efficiency.

[0126] In an exemplary embodiment, the traffic efficiency module is specifically used for:

[0127] For each travel plan, based on historical driving datasets, determine whether there are congested road sections;

[0128] If so, for each travel plan, based on the historical driving dataset, the corresponding initial route is divided into multiple traffic segments; each traffic segment is either a congested segment or a non-congested segment.

[0129] If not, the initial route is determined to include only non-congested road sections;

[0130] The traffic efficiency of non-congested road sections is preset to 1.

[0131] In one exemplary embodiment, the degree of negative correlation between the expected function value and traffic efficiency is determined by a first weight, and the degree of positive correlation between the expected function value and route distance is determined by a second weight.

[0132] In one exemplary embodiment, the computation module is intended to specifically be used for:

[0133] For each travel plan, based on the corresponding travel time information, corresponding travel efficiency and route distance, the expected function value of each travel plan is calculated according to the travel expectation function scheme.

[0134] Travel time information includes at least one of the following: departure time, arrival time, and travel time corresponding to the travel plan.

[0135] In one exemplary embodiment, the preprocessing module is further configured to:

[0136] Based on user instructions, determine one or more passage time information, and determine the correlation between the expected function value and each passage time information and the degree of correlation.

[0137] The correlation is either negative or positive.

[0138] Figure 4 This is a schematic diagram of the electronic device 4 provided in an embodiment of this application. Figure 4 As shown, the electronic device 4 of this embodiment includes: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, it implements the steps in the various method embodiments described above. Alternatively, when the processor 401 executes the computer program 403, it implements the functions of each module / unit in the various device embodiments described above.

[0139] Electronic device 4 can be a desktop computer, laptop, handheld computer, cloud server, or other electronic device. Electronic device 4 may include, but is not limited to, processor 401 and memory 402. Those skilled in the art will understand that... Figure 4 This is merely an example of electronic device 4 and does not constitute a limitation on electronic device 4. It may include more or fewer components than shown, or different components.

[0140] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0141] The memory 402 can be an internal storage unit of the electronic device 4, such as a hard disk or RAM of the electronic device 4. The memory 402 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., equipped on the electronic device 4. The memory 402 can also include both internal and external storage units of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device.

[0142] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0143] If an integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program may include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0144] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method of recommending a navigation route, characterized by, The method comprises the following steps: acquiring a user instruction, determining a route starting point, a route ending point and target time information based on the user instruction, the target time information including at least one of a target departure time interval and a target arrival time interval; determining a plurality of initial routes from the route starting point to the route ending point and route distances of the initial routes based on map information; determining all travel schemes based on a historical travel data set corresponding to the map information, each travel scheme including an initial route and a set of travel action time points corresponding to the initial route and fully meeting the target time information, each set of travel action time points including at least one of a departure time point corresponding to the target departure time interval and an arrival time point corresponding to the target arrival time interval; determining a traffic efficiency corresponding to each travel scheme based on the historical travel data set; the traffic efficiency is used to indicate the degree of road traffic; wherein for each travel scheme, the initial route corresponding to the travel scheme is divided into a plurality of traffic segments based on the historical travel data set; the traffic efficiency of each traffic segment is obtained by integrating a traffic rate ratio within a time period of traveling through the traffic segment based on the historical travel data set; the traffic rate ratio is a ratio of a real-time traffic rate of a same position point corresponding to the travel scheme to a preset traffic rate, and the real-time traffic rate is a ratio of speed to acceleration corresponding to the position point and the travel scheme in the historical travel data set; for each travel scheme, an expected function value of each departure time point is calculated based on the traffic efficiency corresponding to the travel scheme and the route distance according to a travel expected function scheme; in the travel expected function scheme, the expected function value is negatively correlated with the traffic efficiency, and the expected function value is positively correlated with the route distance; a travel scheme with a preset number of expected function values is selected as a recommended result of the user instruction, and is sent to a display terminal.

2. The method of claim 1, wherein, The travel expected function scheme corresponding to any travel scheme is specifically a sum value of expected traffic time consumptions of all traffic segments corresponding to the travel scheme; the expected traffic time consumption of each traffic segment is specifically a ratio of a traffic segment distance of the traffic segment to an expected traffic speed; the expected traffic speed is a product of a preset speed and the traffic efficiency corresponding to the traffic segment.

3. The method of claim 1, wherein, For each travel scheme, the process of dividing the initial route corresponding to the travel scheme into a plurality of traffic segments based on the historical travel data set comprises the following steps: for each travel scheme, it is determined whether there is a congestion segment based on the historical travel data set; if yes, the action of dividing the initial route corresponding to the travel scheme into a plurality of traffic segments based on the historical travel data set is performed; each traffic segment is the congestion segment or a non-congestion segment; if no, it is determined that the initial route only includes the non-congestion segment; wherein the traffic efficiency of the non-congestion segment is preset as 1.

4. The method according to claim 1, wherein A negative correlation degree between the expected function value and the traffic efficiency is determined by a first weight; A positive correlation degree between the expected function value and the route distance is determined by a second weight.

5. The method according to any one of claims 1 to 4, characterized in that, For each of the travel plans, an expected function value of each of the departure time points is obtained by calculating, based on the corresponding traffic efficiency and the route distance, according to a driving expected function plan, including: For each of the travel plans, an expected function value of each of the travel plans is obtained by calculating, based on the corresponding traffic time information, the corresponding traffic efficiency and the route distance, according to a driving expected function plan; The traffic time information is at least one of the departure time, the arrival time and the route time consumption corresponding to the travel plan.

6. The method of claim 5, wherein, Before the expected function value of each of the travel plans is obtained by calculating, based on the corresponding traffic time information, the corresponding traffic efficiency and the route distance, according to a driving expected function plan, it further includes: Based on the user instruction, one or more of the traffic time information is determined, and a correlation between the expected function value and each of the traffic time information and a correlation degree of the correlation are determined; The correlation is negative correlation or positive correlation.

7. A route guidance recommendation device characterized by comprising: It includes: A preprocessing module is configured to obtain a user instruction, determine a route starting point, a route ending point and target time information based on the user instruction, and the target time information includes at least one of a target departure time interval and a target arrival time interval; An initial route module is configured to determine a plurality of initial routes from the route starting point to the route ending point and route distances of the initial routes based on map information; A travel plan module is configured to determine all travel plans based on a historical driving data set corresponding to the map information, each of the travel plans including an initial route and a set of travel action time points corresponding to the initial route and fully meeting the target time information, and each of the set of travel action time points including at least one of a departure time point corresponding to the target departure time interval and an arrival time point corresponding to the target arrival time interval; A traffic efficiency module is configured to determine a traffic efficiency corresponding to each of the travel plans based on the historical driving data set; The traffic efficiency is used to indicate the degree of road smoothness; It includes: for each of the travel plans, the corresponding initial route is divided into a plurality of traffic road segments based on the historical driving data set; and the traffic efficiency of each of the traffic road segments is obtained by integrating a traffic rate ratio within a time period of driving through each of the traffic road segments based on the historical driving data set; the traffic rate ratio is a ratio of a real-time traffic rate of a same position point corresponding to the travel plan to a preset traffic rate, and the real-time traffic rate is a ratio of a speed to an acceleration corresponding to the travel plan and the position point in the historical driving data set. An expectation calculating module is configured to calculate, for each of the travel plans, an expectation function value of each of the departure time points according to a travel expectation function scheme based on the corresponding traffic efficiency and the route distance; in the travel expectation function scheme, the expectation function value is negatively correlated with the traffic efficiency, and the expectation function value is positively correlated with the route distance; A recommendation module is configured to send, to a display terminal, the travel plan with the minimum expectation function value as a recommended result of the user instruction.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. The computer program is executed by the processor to implement the steps of the method according to any one of claims 1 to 6.

Images