Vehicle departure time determination method and device, electronic equipment and storage medium

Abstract

This disclosure provides a method, apparatus, electronic device, and storage medium for determining the departure time of a vehicle, relating to the field of artificial intelligence technology, particularly to the fields of the Internet of Things, intelligent transportation, and big data. The specific implementation scheme is as follows: for a target station, multiple candidate time sequences are determined based on the departure interval and predetermined fluctuation duration of the vehicle; for each candidate time sequence, an evaluation value is determined based on the difference between the candidate time sequence and historical time sequences; and based on the multiple evaluation values, a target time sequence is determined from the multiple candidate time sequences to obtain multiple departure times for the target station.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to the fields of the Internet of Things, intelligent transportation, and big data. More specifically, this disclosure provides a method, apparatus, electronic device, storage medium, and computer program product for determining the departure time of a means of transportation. Background Technology

[0002] Users sometimes need to plan their trips based on the departure schedules of public transportation such as buses and subways. Accurate public transportation timetables can improve users' travel efficiency and enhance the reputation of products such as maps and related LBS (Location Based Services). However, maps and related LBS services cannot provide timetable information. Summary of the Invention

[0003] This disclosure provides a method, apparatus, electronic device, storage medium, and computer program product for determining the departure time of a means of transport.

[0004] According to one aspect of this disclosure, a method for determining the departure time of a means of transportation is provided, comprising: determining multiple candidate time sequences for a target station based on the departure interval and predetermined fluctuation duration of the means of transportation; determining an evaluation value for each candidate time sequence in the multiple candidate time sequences based on the difference between the candidate time sequence and a historical time sequence; and determining a target time sequence from the multiple candidate time sequences based on the multiple evaluation values ​​to obtain multiple departure times for the target station.

[0005] According to another aspect of this disclosure, a means of transportation departure time determination apparatus is provided, comprising: a candidate sequence determination module, an evaluation module, and a target sequence determination module. The candidate sequence determination module determines multiple candidate time sequence sequences for a target station based on the departure interval and a predetermined fluctuation duration of the means of transportation. The evaluation module determines an evaluation value for each candidate time sequence based on the difference between the candidate time sequence and historical time sequences. The target sequence determination module determines a target time sequence from the multiple candidate time sequences based on the multiple evaluation values, thereby obtaining multiple departure times for the target station.

[0006] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the methods provided in this disclosure.

[0007] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods provided in this disclosure.

[0008] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the methods provided in this disclosure.

[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0011] Figure 1 This is a schematic diagram illustrating an application scenario of the method and apparatus for determining the departure time of a means of transport according to embodiments of this disclosure;

[0012] Figure 2 This is a schematic flowchart of a method for determining the departure time of a means of transport according to an embodiment of the present disclosure;

[0013] Figure 3 This is a schematic diagram of a method for determining the departure time of a means of transport according to an embodiment of the present disclosure;

[0014] Figure 4 This is a schematic flowchart illustrating the determination of the departure interval according to an embodiment of the present disclosure;

[0015] Figure 5 This is a schematic diagram illustrating the principle of determining the departure interval according to an embodiment of the present disclosure;

[0016] Figure 6 This is a schematic diagram illustrating the principle of generating candidate time sequences according to an embodiment of the present disclosure;

[0017] Figure 7 This is a schematic structural block diagram of a vehicle departure time determination device according to an embodiment of the present disclosure; and

[0018] Figure 8 This is a structural block diagram of an electronic device used to implement the method for determining the departure time of a vehicle according to embodiments of the present disclosure. Detailed Implementation

[0019] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0020] It should be noted that due to the decentralized operation, the cost of maintaining online timetable information in public transportation systems is high. Therefore, there is a bottleneck in the coverage of timetable information in maps and related LBS services, making it impossible to provide departure timetables for transportation.

[0021] In some embodiments, departure timetables for public transportation such as buses and subways can be generated through clustering statistics. However, this method requires significant manual intervention and has low accuracy. In other embodiments, departure intervals can be used to directly infer the departure times of stations. However, due to factors such as road conditions and driving differences, the inferred departure timetables deviate significantly from the actual times.

[0022] This disclosure provides a method for determining the departure time of public transportation. After obtaining the departure interval, the method uses the departure interval of the target station as a floating benchmark and a predetermined fluctuation duration as the floating amplitude for floating processing. This expands a time sequence corresponding to the departure interval into multiple candidate time sequences. Next, based on historical time sequences, the method calculates the evaluation value of each of the multiple candidate time sequences and selects the most accurate sequence from among the multiple candidate time sequences as the target time sequence. The times in this target time sequence are the departure times of the target station. This technical solution can improve the accuracy of public transportation departure timetables and enhance the user's travel experience.

[0023] The technical solutions provided in this disclosure will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0024] Figure 1 This is a schematic diagram illustrating an application scenario of the method and apparatus for determining the departure time of a vehicle according to embodiments of this disclosure.

[0025] It is important to note that Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, in order to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments or scenarios.

[0026] like Figure 1As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, and 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the terminal devices 101, 102, and 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0027] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Terminal devices 101, 102, and 103 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0028] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using terminal devices 101, 102, and 103 (for example only). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as departure timetables of target sites obtained or generated according to user requests) to the terminal devices.

[0029] For example, server 105 can collect large-scale trajectory information (such as crowdsourced trajectory, bus and subway driving trajectory, user trajectory, etc.), then determine the departure interval of the vehicle at the target station based on the trajectory information, then determine multiple candidate time sequences based on the departure interval and the predetermined fluctuation duration, then determine the evaluation value of each of the multiple candidate time sequences based on the historical time sequence, and finally select the target time sequence from the multiple candidate time sequences based on the evaluation value.

[0030] It should be noted that the method for determining the departure time of a vehicle provided in this embodiment can generally be executed by server 105. Correspondingly, the device for determining the departure time of a vehicle provided in this embodiment can generally be located in server 105. The method for determining the departure time of a vehicle provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105. Correspondingly, the device for determining the departure time of a vehicle provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105.

[0031] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0032] Figure 2 This is a schematic flowchart of a method for determining the departure time of a vehicle according to an embodiment of the present disclosure.

[0033] like Figure 2 As shown, the method 200 for determining the departure time of the vehicle may include operations S210 to S230.

[0034] In operation S210, for the target station, multiple candidate time sequences are determined based on the departure interval of the vehicles and the predetermined fluctuation duration.

[0035] For example, transportation can include subways, buses, etc. A station can refer to a station of public transportation such as a subway or bus, and a target station can refer to any station whose departure timetable needs to be determined, such as a starting station, intermediate station, or terminal station.

[0036] For example, departure interval indicates the time interval between two consecutive trains leaving the target station.

[0037] It is understandable that, due to factors such as scheduling arrangements, driver's personal reasons, and road conditions, vehicles may sometimes fail to depart on time according to the pre-planned departure intervals, and there may be some differences between the actual departure time and the pre-planned departure time. Taking this difference into account, this embodiment pre-configures a predetermined fluctuation duration, which may include, for example, -2, -1, 1, 2, or 3 minutes.

[0038] Taking a vehicle departure time of 9:00 AM with a 10-minute interval and a planned fluctuation range of ±1 minute as an example, it can be seen that one bus is expected to depart between 9:09 AM and 9:11 AM (hereinafter referred to as time slot 1), while another bus is expected to depart between 9:19 AM and 9:21 AM (hereinafter referred to as time slot 2). Either time slot 1 or time slot 2 can be selected to form a candidate time slot sequence.

[0039] In operation S220, for each candidate time sequence among multiple candidate time sequences, the evaluation value of the candidate time sequence is determined based on the difference between the candidate time sequence and the historical time sequence.

[0040] For example, a historical time series includes one or more historical departure times. A historical departure time can represent a specific actual departure time of the target station in the past, or it can represent a departure time obtained by averaging, fitting, or other processing of actual departure times over multiple historical days. For example, if a vehicle departed from the target station at 9:00, 9:09, and 9:20 yesterday, the historical time series could include 9:00, 9:09, and 9:20.

[0041] For example, the similarity between candidate time series and historical time series can be calculated, and the similarity can be used as an evaluation value.

[0042] For example, the value of at least one evaluation indicator for each candidate time series can be calculated, and the value of a single evaluation indicator or the weighted sum of multiple evaluation indicators can be used as the evaluation value. Evaluation indicators may include error, coverage, etc. The process of determining error and coverage is described in detail below.

[0043] In operation S230, based on multiple evaluation values ​​of multiple candidate time sequences, the target time sequence is determined from the multiple candidate time sequences to obtain multiple departure times for the target station.

[0044] For example, a candidate time sequence with the largest or smallest evaluation value can be selected as the target time sequence.

[0045] According to the technical solution provided in this disclosure, the departure interval of the target station is used as the floating benchmark, and a predetermined fluctuation duration is used as the floating amplitude for floating processing. This expands a time series corresponding to the departure interval into multiple candidate time series. Next, based on historical time series, the evaluation values ​​of each of the multiple candidate time series are calculated, and based on the evaluation values, the most accurate sequence is selected from the multiple candidate time series as the target time series. The times in the target time series are the departure times of the target station. The above technical solution can improve the accuracy of public transportation departure timetables and enhance the user's travel experience.

[0046] Figure 3 This is a schematic diagram of a method for determining the departure time of a vehicle according to an embodiment of the present disclosure.

[0047] like Figure 3 As shown, in this embodiment, the method 300 for determining the departure time of a vehicle may include the following process: determining the departure interval S340 through operation S340, generating a candidate time sequence through operation S310, evaluating the candidate time sequence through operation S320, and selecting the target time sequence through operation S330. Operations S310 to S330 can refer to operations S210 to S230 above, and operation S340 is described below.

[0048] Figure 4 This is a schematic flowchart illustrating the determination of the departure interval according to an embodiment of the present disclosure.

[0049] The following combination Figure 4 The process of determining the departure interval is explained in detail.

[0050] In one example, departure intervals can be obtained directly from the public transport operator.

[0051] In another example, the departure interval can be determined based on large-scale object trajectories. This example is illustrated below through operations S441 to S443.

[0052] In operation S441, multiple object trajectories are acquired. Each object trajectory includes multiple trajectory points, and the information of each trajectory point includes location information and time information.

[0053] For example, object trajectories can include crowdsourced trajectories, public transportation trajectories, user trajectories, etc. Taking user trajectories as an example, after obtaining user authorization, user trajectory information can be collected.

[0054] In operation S442, for each object trajectory, the estimated departure time representing the target station is determined based on the position and time information of multiple trajectory points in the object trajectory.

[0055] For example, a reservation process can be performed based on a large number of object trajectories to obtain the estimated departure time of the target station. The reservation process is described in detail below.

[0056] In operation S443, the departure interval of the target station is determined based on multiple estimated times for the target station determined from multiple object trajectories.

[0057] For example, based on a single object trajectory, an estimated departure time for a train at a target station can be determined. Thus, multiple estimated times can be obtained from multiple object trajectories. The distribution information of these estimated times can be statistically analyzed, for example, by plotting time on the x-axis and frequency on the y-axis to generate a distribution map of the estimated times. Then, departure intervals can be determined based on this distribution information. For instance, the distribution map can be divided into multiple time intervals based on time, and the time difference between two peaks in each time interval can be used as the departure interval for that time interval.

[0058] This embodiment determines the estimated departure times of multiple departures from the target station based on large-scale object trajectories, and then determines the departure interval through the distribution information of these estimated times. Therefore, the departure interval of the target station can be estimated based on a large amount of historical real departure data, thus improving the accuracy of the departure interval.

[0059] Figure 5 This is a schematic diagram illustrating the determination of the departure interval according to an embodiment of the present disclosure.

[0060] like Figure 5As shown, in this embodiment, multiple object trajectories 501 can be obtained first, and then operation S542 can be performed, that is, pre-processing can be performed on each object trajectory 501 to obtain the estimated departure time of the target station. Then, the distribution information 502 of multiple estimated times can be statistically analyzed. The distribution information 502 can include a distribution map with time as the horizontal axis and frequency as the vertical axis. Then, based on the distribution information 502, the departure interval 503 of the target station in each time zone can be obtained.

[0061] In one example, the aforementioned pre-processing operation S542 may include the following procedures: trajectory denoising, route matching, station identification, target route determination, and calculation of the estimated departure time from the target station.

[0062] In the process of trajectory denoising, for example, stationary trajectory points that remain stationary for a period of time can be removed, or two adjacent trajectory points that are far apart can be removed.

[0063] During route matching, for example, at least one candidate route can be determined from multiple travel routes of a vehicle based on the object trajectory 501. For example, the similarity between the shape of the object trajectory 501 and the shape of the vehicle's travel route can be calculated, and travel routes with a similarity greater than or equal to a similarity threshold can be identified as candidate routes.

[0064] During the site identification process, for example, multiple matching sites can be determined based on the location information of multiple trajectory points in object trajectory 501 and the location information of multiple sites in at least one candidate route. A trajectory point matching a site indicates that the trajectory point is located in the area indicated by the site. Through site identification, it is possible to determine which site in the candidate route the user is at.

[0065] In the process of determining the target route, for example, the target route can be determined from at least one candidate route based on multiple matching stations. It is understood that two candidate routes for a vehicle may overlap in some areas (e.g., two subway lines both have XX subway stations), and since the overlapping area is limited, a target route and its direction can be uniquely determined based on two, three, or more matching stations. In other embodiments, whether to filter out a candidate trajectory can also be determined by whether the speed of the object trajectory 501 is consistent with the speed of the vehicle traveling on the candidate route.

[0066] The above process selects the target route from multiple candidate routes through route matching, station identification, and target route determination. Compared with directly determining the candidate route as the target route, this embodiment can accurately determine the target route from multiple candidate routes with local route overlap based on the multiple stations where the user is located, thereby improving the accuracy of the target route.

[0067] In calculating the estimated departure time from the target station, for example, reference trajectory points can be determined from multiple trajectory points in the object trajectory 501, and reference stations can be determined from multiple stations on the target route. The location information of the reference trajectory points is consistent with the location information of the reference stations, meaning they indicate the same or similar geographical locations. Then, based on the time information of the reference trajectory points and the travel interval between the reference stations and the target station, the estimated departure time from the target station is determined. For example, if the object is at reference station XX at 9:00 AM, and it takes half an hour for the vehicle to travel from the target station to reference station XX, the estimated departure time from the target station can be determined to be 8:30 AM. This method can accurately determine the estimated departure time from the target station.

[0068] Figure 6 This is a schematic diagram illustrating the principle of generating candidate time sequences according to an embodiment of the present disclosure.

[0069] The following combination Figure 6 The process of generating candidate time sequences is explained in detail.

[0070] In this embodiment, for the current shift out of N shifts at the target station, multiple departure times for subsequent shifts can be determined based on at least one departure time, departure interval, and predetermined fluctuation duration of the current shift, where N is an integer greater than or equal to 2. Then, a tree structure is determined based on the order of the N shifts and the departure time of each of the N shifts. Next, multiple candidate time sequences are determined based on the path of the tree structure, wherein nodes in the tree structure represent departure times, and the node representing the departure time of the current shift has a parent-child relationship with at least a portion of the nodes representing the departure times of subsequent shifts.

[0071] For example, different time intervals can correspond to different departure intervals. One time interval is from 8:00 to 9:00, with a departure interval of 5 minutes. Another time interval is from 9:00 to 10:00, with a departure interval of 9 minutes. Candidate time sequences can be generated for each interval, and multiple intervals can be computed in parallel.

[0072] The process of generating candidate departure times is explained below. Figure 6 In this context, minute T represents the departure time of the first train departing from the target station within a certain time interval, K represents the departure interval, and the predetermined fluctuation duration is ±1 minute.

[0073] like Figure 6As shown, with the departure time T of the first bus as the root node 601, and a fluctuation range of ±1 minute, three child nodes 6021, 6022, and 6023 are generated for the root node 601. These three child nodes 6021, 6022, and 6023 represent three candidate departure times for the second bus. Next, for child node 6021, three child nodes 6031, 6032, and 6033 are generated with a fluctuation range of ±1 minute. Similar processing is performed for child nodes 6022 and 6023. This allows us to obtain nine candidate departure times 6031 to 6039 for the third bus based on the three candidate departure times 6021, 6022, and 6023 for the second bus. This process continues until multiple candidate departure times for the Nth bus are obtained, such as candidate departure time 6041, etc. The above process yields a tree structure, in which each path from the root node to a leaf node represents a candidate time sequence for the target station within that time interval. For example, nodes 601, 6021, 6031, ..., 6041 constitute a candidate time sequence.

[0074] In some embodiments, if the departure time A of a later shift is determined based on a departure time B of a previous shift, rather than on another departure time C of a previous shift, then the node representing departure time A and the node representing departure time B may have a parent-child relationship, while the node representing departure time A and the node representing departure time C may not have a parent-child relationship. For example, node 6031 and node 6021 have a parent-child relationship, while node 6031 and node 6022 may not have a parent-child relationship.

[0075] Understandable Figure 6 Taking a predetermined fluctuation duration of ±1 minute as an example, the predetermined fluctuation duration can also be other values. For example, when the predetermined fluctuation duration is ±2 minutes, the second bus has 5 candidate departure times, and the second bus has 25 candidate departure times.

[0076] In this embodiment, a depth-first search approach is used to generate the candidate departure time sequence, enumerating all possible departure times to ensure the comprehensiveness of the candidate departure time sequence. Furthermore, a tree structure is generated during processing, so no traversal operations are required when determining the candidate departure time sequence; the candidate time sequence can be determined directly based on the hierarchical relationship of the tree structure, thereby improving the efficiency of determining the candidate time sequence.

[0077] It is understood that in other embodiments, candidate departure times for each bus can be determined, and then the candidate departure times of multiple buses can be arranged and combined to obtain a candidate time sequence. In a candidate time sequence, each bus has only one candidate departure time.

[0078] In some embodiments, after obtaining the candidate departure time sequence, it can be filtered using predetermined rules to remove candidate departure time sequences that are clearly inconsistent with the actual situation. For example, constraints can be set for each time interval. One constraint is that the departure interval between two consecutive trips in the interval must be greater than a certain duration threshold th. If the departure interval in a candidate departure time sequence is less than the duration threshold th, the candidate departure time sequence is filtered out, and its evaluation value is not calculated again.

[0079] The process of evaluating candidate time series is explained below.

[0080] In this embodiment, the value of at least one evaluation index for each candidate time sequence can be calculated, and then the evaluation value can be determined based on the evaluation index.

[0081] In one example, the evaluation metric may include error. Taking historical time series T0 and candidate time series T1 as examples, the process of determining the error is explained. The process of determining the error of other candidate time series can refer to candidate time series T1.

[0082] In this embodiment, for each historical departure time in the historical time sequence T0, the minimum interval duration between multiple candidate times in the candidate time sequence T1 and the historical departure time can be determined to obtain the minimum interval duration corresponding to the historical departure time. Then, based on the multiple minimum interval durations corresponding to the multiple historical departure times in the historical time sequence, the error between the candidate time sequence T1 and the historical time sequence T0 is determined.

[0083] For example, if the historical time sequence T0 includes 9:05, 9:10, and 9:15, and the candidate time sequence T1 includes 9:06 and 9:12, then the minimum interval corresponding to 9:05 in sequence T0 is 1 minute, the minimum interval corresponding to 9:10 in sequence T0 is 2 minutes, and the minimum interval corresponding to 9:15 in sequence T0 is 3 minutes. Next, for example, the sum of multiple minimum intervals can be used as the error, then the error in the above sequence T0 can be 6 minutes. Alternatively, the ratio of the sum of multiple minimum intervals to the number of elements in sequence T0 can be used as the error, then the error in the above sequence T0 can be 2 minutes.

[0084] This embodiment determines the time offset of the candidate time sequence relative to the historical time sequence by the minimum interval between the candidate time sequence and the historical time sequence, and therefore can be used to evaluate whether the candidate time sequence is accurate.

[0085] In another example, the evaluation metric can also include coverage. The following uses the historical time series T0 and the candidate time series T1 mentioned above as examples to illustrate coverage.

[0086] For each historical departure time in the historical time sequence T0, it can be determined whether the candidate time sequence T1 includes a time with an interval less than or equal to a predetermined threshold, such as 2 minutes. If it does, the historical departure time is determined to be covered; otherwise, it is determined that the historical departure time is not covered. For example, 9:05 and 9:10 in the above sequence T0 are covered, but 9:15 in the sequence T0 is not covered.

[0087] Next, the coverage rate is calculated based on whether each historical departure time in the historical time sequence T0 is covered. The coverage rate can be determined as the ratio between the number of covered historical departure times and the total number of times in the historical departure time sequence. For example, the coverage rate of the above sequence T0 is two-thirds.

[0088] This embodiment determines the coverage of the candidate time sequence with the historical departure time by detecting whether there are candidate departure times near the actual historical departure time, and evaluates the accuracy of the candidate time sequence based on the coverage.

[0089] After obtaining the error and coverage, the evaluation value can be determined based on at least one of the error and coverage.

[0090] In one example, the weights for error and coverage can be pre-configured, and then a weighted sum of the two can be calculated as the evaluation value. For another example, if the coverage reaches a predetermined threshold (e.g., 80%), a smaller error results in a higher evaluation value. In other examples, either the error or the coverage can be determined as the evaluation value.

[0091] Figure 7 This is a schematic structural block diagram of a vehicle departure time determination device according to an embodiment of the present disclosure.

[0092] like Figure 7 As shown, the vehicle departure time determination device 700 may include a candidate sequence determination module 710, an evaluation module 720, and a target sequence determination module 730.

[0093] The candidate sequence determination module 710 is used to determine multiple candidate time sequences for a target station based on the departure interval of the vehicles and the predetermined fluctuation duration.

[0094] The evaluation module 720 is used to determine the evaluation value of each candidate time sequence among multiple candidate time sequences based on the difference between the candidate time sequence and the historical time sequence.

[0095] The target sequence determination module 730 is used to determine the target time sequence from multiple candidate time sequences based on multiple evaluation values, so as to obtain multiple departure times for the target station.

[0096] In this embodiment, the historical time sequence includes multiple historical departure times. The evaluation module includes: an interval duration determination submodule, an error determination submodule, and a first evaluation value determination submodule. The interval duration determination submodule is used to determine, for each historical departure time in the candidate time sequence, the minimum interval duration between multiple candidate times in the candidate time sequence and the historical departure time, thereby obtaining the minimum interval duration corresponding to the historical departure time. The error determination submodule is used to determine the error between the candidate time sequence and the historical time sequence based on the multiple minimum interval durations corresponding to the multiple historical departure times. The first evaluation value determination submodule is used to determine the evaluation value based on the error.

[0097] In this embodiment, the evaluation module includes a coverage determination submodule and a second evaluation value determination submodule. The coverage determination submodule is used to determine whether each historical departure time in the historical time sequence is covered, thereby obtaining the coverage rate. The second evaluation value determination submodule is used to determine the evaluation value based on the coverage rate. Coverage of historical departure times is characterized by the following: the candidate time sequence includes times whose interval with a historical departure time is less than or equal to a predetermined threshold.

[0098] In this embodiment, the candidate sequence determination module includes: a time determination submodule, a tree structure determination submodule, and a candidate sequence determination submodule. The time determination submodule is used to determine multiple departure times for subsequent shifts based on at least one departure time, departure interval, and predetermined fluctuation duration for the current shift among N shifts at the target station. N is an integer greater than or equal to 2. The tree structure determination submodule is used to determine a tree structure based on the order of the N shifts and the departure time of each of the N shifts. The candidate sequence determination submodule is used to determine multiple candidate time sequences based on the path of the tree structure. Nodes in the tree structure represent departure times, and the node representing the departure time of the current shift has a parent-child relationship with at least a portion of the nodes representing the departure times of subsequent shifts.

[0099] In this embodiment, the above-mentioned apparatus further includes: an acquisition module, an estimated time determination module, and a departure interval determination module. The acquisition module acquires multiple object trajectories, each object trajectory including multiple trajectory points, and each trajectory point including location information and time information. The estimated time determination module, for each object trajectory, determines an estimated time representing the departure from the target station based on the location information and time information of the multiple trajectory points in the object trajectory. The departure interval determination module determines the departure interval of the target station based on the multiple estimated times determined for the target station based on the multiple object trajectories.

[0100] In this embodiment, the estimated time determination module includes a target route determination submodule and a reference information determination submodule. The target route determination submodule determines a target route that matches the object trajectory from multiple travel routes of the vehicle. The reference information determination submodule determines reference trajectory points and reference stations from multiple trajectory points in the object trajectory and multiple stations in the target route, respectively, where the location information of the reference trajectory points is consistent with the location information of the reference stations. The estimated time determination submodule determines the estimated departure time from the target station based on the time information of the reference trajectory points and the travel interval between the reference stations and the target station.

[0101] In this embodiment, the target route determination submodule includes: a candidate route determination unit, a matching station determination unit, and a target route determination unit. The candidate route determination unit determines at least one candidate route from multiple driving routes based on the object trajectory. The matching station determination unit determines multiple matching stations based on the location information of multiple trajectory points in the object trajectory and the location information of multiple stations in the at least one candidate route. The target route determination unit determines the target route from at least one candidate route based on the multiple matching stations.

[0102] According to embodiments of this disclosure, this disclosure also provides an electronic device, including at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the above-described method for determining the departure time of a means of transport.

[0103] According to embodiments of this disclosure, this disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the above-described method for determining the departure time of a means of transport.

[0104] According to embodiments of this disclosure, this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method for determining the departure time of a means of transport.

[0105] Figure 8This is a structural block diagram of an electronic device used to implement the vehicle departure time determination method according to embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0106] like Figure 8 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0107] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0108] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the transportation departure time determination method. For example, in some embodiments, the transportation departure time determination method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the transportation departure time determination method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the transportation departure time determination method by any other suitable means (e.g., by means of firmware).

[0109] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0110] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0111] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0112] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0113] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0114] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0115] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0116] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0117] In the technical solution disclosed herein, the user's authorization or consent is obtained before acquiring or collecting the user's personal information.

[0118] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for determining the departure time of a means of transportation, comprising: For a target station, multiple candidate time sequences are determined based on the departure interval and predetermined fluctuation duration of the transportation vehicles, including: for the current bus among N buses at the target station, multiple departure times of subsequent buses are determined based on at least one departure time of the current bus, the departure interval, and the predetermined fluctuation duration, so as to determine the multiple candidate time sequences, where N is an integer greater than or equal to 2. For each of the plurality of candidate time sequences, an evaluation value for the candidate time sequence is determined based on at least one of the error between the candidate time sequence and the historical time sequence and the coverage; and Based on multiple evaluation values, a target time sequence is determined from the multiple candidate time sequences to obtain multiple departure times for the target station; The error is determined as follows: the historical time sequence includes multiple historical departure times; for each of the multiple historical departure times, the minimum interval between multiple candidate times in the candidate time sequence and the historical departure time is determined to obtain the minimum interval corresponding to the historical departure time; the error between the candidate time sequence and the historical time sequence is determined based on the multiple minimum intervals corresponding to the multiple historical departure times. The coverage rate is determined based on whether each historical departure time in the historical time sequence is covered; the coverage of the historical departure time indicates that the candidate time sequence includes times with an interval of less than or equal to a predetermined threshold between them.

2. The method of claim 1, wherein, The process of determining multiple candidate time sequences for a target station based on the departure intervals and predetermined fluctuation durations of transportation vehicles also includes: Based on the order of the N trips and the departure time of each of the N trips, a tree structure is determined; and Based on the path of the tree structure, the multiple candidate time sequences are determined; In the tree structure, the nodes represent departure times, and the node representing the departure time of the current shift has a parent-child relationship with at least some of the nodes representing the departure times of subsequent shifts.

3. The method according to any one of claims 1 to 2, further comprising: Acquire multiple object trajectories, each object trajectory includes multiple trajectory points, and the information of each trajectory point includes location information and time information; For each object trajectory, based on the position and time information of multiple trajectory points in the object trajectory, an estimated time representing the departure from the target station is determined; as well as The departure interval of the target station is determined based on multiple estimated times for the target station determined from the trajectories of the multiple objects.

4. The method of claim 3, wherein, Based on the position and time information of multiple trajectory points in the object trajectory, determining the estimated departure time representing the target station includes: From multiple driving routes of the vehicle, determine the target route that matches the trajectory of the object; Reference trajectory points and reference stations are determined from multiple trajectory points in the object trajectory and multiple stations in the target route, respectively, wherein the location information of the reference trajectory points is consistent with the location information of the reference stations; and Based on the time information of the reference trajectory points and the travel interval between the reference station and the target station, the estimated departure time of the train from the target station is determined.

5. The method according to claim 4, wherein, Determining the target route that matches the trajectory of the object from multiple driving routes of the vehicle includes: Based on the object trajectory, at least one candidate route is determined from the plurality of driving routes; Based on the location information of multiple trajectory points in the object trajectory and the location information of multiple stations in the at least one candidate route, multiple matching stations are determined; and The target route is determined from the at least one candidate route based on the plurality of matching stations.

6. A device for determining the departure time of a means of transportation, comprising: The candidate sequence determination module is used to determine multiple candidate time sequences for a target station based on the departure interval of the vehicles and the predetermined fluctuation duration. The candidate sequence determination module includes a time determination submodule, which is used to determine multiple departure times of subsequent shifts for the current shift among N shifts of the target station, based on at least one departure time of the current shift, the departure interval, and the predetermined fluctuation duration, so as to determine the multiple candidate time sequences, where N is an integer greater than or equal to 2. An evaluation module is used to determine an evaluation value for each of the plurality of candidate time sequences based on at least one of the error between the candidate time sequence and the historical time sequence and the coverage. as well as The target sequence determination module is used to determine a target time sequence from the multiple candidate time sequences based on multiple evaluation values, so as to obtain multiple departure times for the target station; The error is determined by an interval duration determination submodule and an error determination submodule. The historical time sequence includes multiple historical departure times. The interval duration determination submodule is used to determine, for each of the multiple historical departure times, the minimum interval duration between multiple candidate times in the candidate time sequence and the historical departure time, thereby obtaining the minimum interval duration corresponding to the historical departure time. The error determination submodule is used to determine the error between the candidate time sequence and the historical time sequence based on the multiple minimum interval durations corresponding to the multiple historical departure times. The coverage rate is determined based on whether each historical departure time in the historical time sequence is covered; the coverage of the historical departure time indicates that the candidate time sequence includes times with an interval of less than or equal to a predetermined threshold between them.

7. The apparatus according to claim 6, wherein, The candidate sequence determination module further includes: A tree structure determination submodule is used to determine the tree structure based on the order of the N shifts and the departure time of each of the N shifts; and The candidate sequence determination submodule is used to determine the multiple candidate time sequences based on the path of the tree structure; In the tree structure, the nodes represent departure times, and the node representing the departure time of the current shift has a parent-child relationship with at least some of the nodes representing the departure times of subsequent shifts.

8. The apparatus according to any one of claims 6 to 7, further comprising: The acquisition module is used to acquire the trajectories of multiple objects. Each object trajectory includes multiple trajectory points, and the information of each trajectory point includes location information and time information. The estimated time determination module is used to determine, for each object trajectory, the estimated time representing the departure time from the target station based on the position and time information of multiple trajectory points in the object trajectory; as well as The departure interval determination module is used to determine the departure interval of the target station based on multiple estimated times determined for the target station based on the trajectories of the multiple objects.

9. The apparatus according to claim 8, wherein, The estimated time determination module includes: The target route determination submodule is used to determine a target route that matches the trajectory of the object from multiple driving routes of the vehicle; A reference information determination submodule is used to determine reference trajectory points and reference stations from multiple trajectory points in the object trajectory and multiple stations in the target route, respectively, wherein the location information of the reference trajectory points is consistent with the location information of the reference stations; and The estimated time determination submodule is used to determine the estimated departure time of the target station based on the time information of the reference trajectory points and the travel interval between the reference station and the target station.

10. The apparatus according to claim 9, wherein, The target route determination submodule includes: A candidate route determination unit is configured to determine at least one candidate route from the plurality of driving routes based on the object trajectory; A matching station determination unit is configured to determine multiple matching stations based on the location information of multiple trajectory points in the object trajectory and the location information of multiple stations in the at least one candidate route; and A target route determination unit is configured to determine the target route from at least one candidate route based on the plurality of matching stations.

11. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 5.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images