Navigation path travel time processing method, apparatus, device, medium, and product

Abstract

This disclosure provides a method, apparatus, device, medium, and product for processing navigation route travel time, relating to the field of artificial intelligence, and particularly to the field of intelligent transportation. The specific implementation scheme is as follows: determining the positioning trajectory corresponding to at least one road in a road network; extracting the positioning features of the road based on the positioning trajectory; determining the travel time of the road using the positioning features and historical travel characteristics of the road, to obtain the travel time corresponding to at least one of the roads; determining the travel time corresponding to at least one target road in the navigation route based on the travel time corresponding to at least one of the roads; and adding the travel times corresponding to at least one target road to obtain the target travel time of the navigation route. The technical solution of this disclosure improves the accuracy of navigation route travel time.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent transportation in the field of artificial intelligence technology, and in particular to a method, apparatus, device, medium and product for processing navigation route travel time. Background Technology

[0002] In electronic map navigation, user devices can detect navigation requests entered into the electronic map, which may include the origin and destination. The corresponding electronic map server can then plan a navigation route based on these information, obtaining at least one navigation path. To provide accurate navigation path guidance, travel time can be predicted for each path, yielding the total travel time for the user to traverse the entire route. However, in practical applications, the accuracy of travel time prediction is not high, resulting in low accuracy of navigation prompts from electronic maps. Summary of the Invention

[0003] This disclosure provides a method, apparatus, device, medium, and product for processing navigation path travel time in map navigation scenarios.

[0004] According to a first aspect of this disclosure, a method for processing navigation path travel time is provided, comprising:

[0005] Determine the location trajectory corresponding to at least one road in the road network;

[0006] Based on the location trajectory of the road, extract the location features of the road;

[0007] By utilizing the location features of the road and combining them with the historical traffic features of the road, the travel time of the road is determined, so as to obtain the travel time corresponding to at least one of the roads respectively;

[0008] Based on the travel time corresponding to at least one of the roads, determine the travel time corresponding to at least one target road in the navigation path;

[0009] The target travel time of the navigation path is obtained by adding the travel times corresponding to at least one of the target roads.

[0010] According to a second aspect of this disclosure, a navigation time processing apparatus is provided, comprising:

[0011] A trajectory determination unit is used to determine the positioning trajectory corresponding to at least one road in the road network.

[0012] The feature extraction unit is used to extract the positioning features of the road based on the positioning trajectory of the road;

[0013] The feature calculation unit is used to determine the travel time of the road by utilizing the location features of the road and combining the historical traffic features of the road, so as to obtain the travel time corresponding to at least one of the roads respectively.

[0014] A time matching unit is used to determine the travel time of at least one target road in the navigation path based on the travel time of at least one of the roads respectively;

[0015] The time addition unit is used to add the travel times corresponding to at least one of the target roads to obtain the target travel time of the navigation path.

[0016] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] 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 described in the first aspect.

[0020] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect.

[0021] According to a fifth aspect of this disclosure, a computer program product is provided, the computer program product comprising: a computer program stored in a readable storage medium, wherein at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to cause the electronic device to perform the method described in the first aspect.

[0022] The technology disclosed herein solves the problem of low accuracy in travel time determination for navigation routes. It extracts the location features of a road by analyzing its positioning trajectory, and then accurately determines the travel time of the road using these extracted features and historical travel characteristics. By accurately determining the travel time, the target travel time of the obtained navigation route is more accurate.

[0023] 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

[0024] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0025] Figure 1 This is a system architecture diagram of an application navigation path travel time processing method provided according to the first embodiment of this disclosure;

[0026] Figure 2 This is a flowchart of a navigation path travel time processing method provided according to the second embodiment of this disclosure;

[0027] Figure 3 This is a flowchart of a navigation path travel time processing method provided according to the third embodiment of this disclosure;

[0028] Figure 4 This is a flowchart of a navigation path travel time processing method provided according to the fourth embodiment of this disclosure;

[0029] Figure 5 This is a flowchart of a navigation path travel time processing method provided according to the fifth embodiment of this disclosure;

[0030] Figure 6 This is a schematic diagram of a navigation path travel time processing device according to the sixth embodiment of the present disclosure;

[0031] Figure 7 This is a block diagram of an electronic device used to implement the navigation path travel time processing method of the embodiments of this disclosure. Detailed Implementation

[0032] 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.

[0033] The technical solution disclosed herein can be applied to scenarios involving time determination for navigation routes. By acquiring the positioning trajectory of a road, its positioning features can be accurately extracted, and these features can be used to accurately predict the travel time of the road. After obtaining the travel time of the road, accurate time acquisition can be performed on a navigation path consisting of at least one road, thereby improving the accuracy of travel time acquisition for navigation paths.

[0034] In related technologies, electronic map navigation can predict travel time for navigation routes, obtaining the time it takes for a user to travel along the navigation path. In practical applications, the travel time of a navigation route is generally estimated using historical travel times. However, the accuracy of the travel time obtained in this way is not high.

[0035] To address the aforementioned technical issues, this disclosure considers real-time extraction of the driving trajectories of each road to obtain the road's positioning trajectory, which can be collected in real time. Then, using the road's positioning trajectory, positioning features are extracted. Based on the extracted positioning features and the road's historical traffic characteristics, the travel time of the road is accurately determined. By accurately determining the road's travel time, the accuracy of the target travel time for the obtained navigation route is higher.

[0036] This disclosure provides a method, apparatus, device, medium, and product for processing navigation route travel time, which is applied to the field of intelligent transportation in the field of artificial intelligence, so as to accurately determine the travel time of navigation routes and improve the accuracy of navigation route travel time.

[0037] The technical solution of this disclosure will now be described in detail with reference to the accompanying drawings.

[0038] like Figure 1 The diagram shown is a system architecture diagram of an application navigation path travel time processing method provided in the first embodiment of this disclosure. The system may include an electronic device configured with an electronic map. The electronic device can be a computer, laptop, ordinary server, cloud server, etc., and this disclosure does not limit the specific type of electronic device. For example, the electronic device can be... Figure 1 The cloud server 1 shown is shown in the image.

[0039] refer to Figure 1 The cloud server 1 can be configured with an electronic map. The cloud server 1 can determine at least one road on the electronic map. To accurately distinguish each road, a road number can be assigned to each road. The cloud server 1 can receive location points uploaded by in-vehicle devices (located in vehicle 21, not shown in the figure), mobile phones 22, and other data collection devices to determine the location trajectory of each road in the road network. Then, using the technical solution of this disclosure, the travel time for each road is estimated. After obtaining the travel time for each road, the travel time for the navigation route is accurately estimated to obtain an accurate travel time. Typically, the navigation route can be generated based on a navigation request sent by a user device (located in vehicle 3, not shown in the figure). The navigation route in server 1 is obtained by navigation planning based on the starting point and destination in the navigation request.

[0040] like Figure 2The diagram shown is a flowchart of a navigation path travel time processing method according to a second embodiment of this disclosure. This method can be configured as a navigation path travel time processing device, which can be configured in an electronic device. The navigation path travel time processing method may include the following steps:

[0041] 201: Determine the location trajectory corresponding to at least one road in the road network.

[0042] The road network can be the traffic network of the target area on the electronic map. The road network can include at least one road. Location trajectories can be collected for any road, and multiple location trajectories can be collected for each road.

[0043] In one possible design, the electronic device can be configured with an input device and a display device. The electronic device can detect the region selection operation performed by the maintenance user on the electronic map, obtain the target region selected by the maintenance user on the electronic map, and obtain at least one road in the road network corresponding to the target region.

[0044] A positioning trajectory can be a path generated from the positioning points produced by the data acquisition device while it is traveling on a road. Of course, a positioning trajectory can also include a sequence of positioning points generated by the data acquisition device on the road.

[0045] 202: Extract the location features of the road based on its location trajectory.

[0046] Location features can be extracted from a location trajectory using feature extraction strategies. These strategies can involve extracting corresponding location features from the trajectory according to at least one defined road driving parameter. Location features can characterize the overall driving characteristics of a road and can be obtained by extracting at least one road feature parameter.

[0047] Road characteristic parameters may include, for example, the driving speed of each user, the average driving speed of all users, the number of trajectories, and the rate of change of trajectories.

[0048] 203: Utilize the location characteristics of the road and combine them with the road's historical traffic characteristics to determine the road's travel time, so as to obtain the travel time corresponding to at least one road.

[0049] The passage time can be determined based on the road's location characteristics and historical passage characteristics.

[0050] 204: Based on the travel time corresponding to at least one road, determine the travel time corresponding to at least one target road in the navigation path.

[0051] The navigation path includes at least one target road. Determining the travel time for each of the at least one target road in the navigation path may include querying the travel time of the road corresponding to the target road identifier from the road identifiers corresponding to the at least one target road, based on the target road identifiers for each of the at least one target road, to obtain the travel time of the target road corresponding to the target road identifier.

[0052] 205: Add up the travel times corresponding to at least one target road to obtain the target travel time of the navigation path.

[0053] The total travel time for the navigation path is the sum of the travel times for each of the at least one target road.

[0054] In this embodiment of the disclosure, when determining the positioning trajectory corresponding to at least one road in the road network, the positioning features of the road can be extracted based on the positioning trajectory. The road's travel time is determined by combining the positioning features with the road's historical trajectory features. The travel time is determined using both time-sensitive positioning features and historical trajectory features with certain reference value, comprehensively considering both the timeliness and inertia of the time determination, resulting in a relatively accurate travel time. By utilizing the travel times corresponding to at least one road, the travel time corresponding to at least one target road in the navigation path can be determined, achieving accurate acquisition of travel time and improving the accuracy of travel time acquisition.

[0055] As one example, the road's location features, combined with its historical traffic characteristics, are used to determine the road's travel time, including:

[0056] The road's location features and historical traffic features are fused to obtain the road's driving features.

[0057] By inputting road driving features into the trained time series model, the travel time of the road can be obtained.

[0058] Time series models are used to predict road travel times. The input data for a time series model can be road driving characteristics and historical traffic patterns, while the output data can be the road travel time. Time series models can be trained and can be deep learning models to accurately learn road travel times.

[0059] In this embodiment, the location features and historical traffic features of the road can be fused to obtain the road travel features. These travel features are then input into a trained time-series model to obtain the road travel time. The time-series model allows for accurate prediction of road travel time, improving the accuracy and efficiency of prediction.

[0060] like Figure 3 The diagram shown is a flowchart of a navigation path travel time processing method provided in the third embodiment of this disclosure. This method can be configured as a navigation path travel time processing device, which can be configured in an electronic device. The navigation path travel time processing method may include the following steps:

[0061] 301: Divide the overall time period into at least one candidate time period. The candidate time period includes a start time and an end time; the start time and end time of the overall time period are determined based on the data collection cycle.

[0062] Optionally, the overall time period can be determined by the start and end times of each data collection cycle. The data collection cycle can be determined based on the frequency of time updates to the electronic map. For example, in more complex road networks with significant real-time changes, a shorter data collection cycle can be set, such as one day, which represents the daily traffic time on the roads. In road networks with simpler road conditions and less real-time change, a longer data collection cycle can be used, such as one week or one month. The start time of a data collection cycle can be the time when the cycle begins, and the end time can be the time when the cycle ends. Taking a day as the cycle unit, 00:00-24:00 each day can be used as the start and end time of the cycle, which is also the start and end time of the overall time period.

[0063] The overall time period is divided into at least one time segment, the length of which is known. For example, a time segment can be divided at 5-minute intervals, with each segment lasting 5 minutes. In one possible design, the overall time period can be continuously divided into candidate time segments, achieving continuous division of time segments and enabling accurate time determination throughout the day.

[0064] 302: In response to a navigation request sent by a user equipment, determine the navigation path and navigation time corresponding to the navigation request.

[0065] 303: Determine the target time period corresponding to the navigation time from at least one candidate time period.

[0066] Optionally, the target time period corresponding to the navigation time may include: determining the candidate time period in which the navigation time falls, and using the candidate time period in which the navigation time falls as the target time period. The candidate time period in which the navigation time falls can be the time period with the highest real-time correlation to the navigation time.

[0067] Of course, in practical applications, the time period in which the navigation time is located may not be able to obtain a number of positioning trajectories that meet the requirements for accurate feature extraction. Therefore, the time period preceding the candidate time period in which the navigation time is located can be used as the target time period.

[0068] 304: During the target time period, determine the location trajectory corresponding to at least one road in the road network.

[0069] 305: Extract the location features of the road based on its location trajectory.

[0070] 306: By utilizing the location characteristics of roads and combining them with the historical traffic characteristics of roads, determine the travel time of roads to obtain the travel time corresponding to at least one road.

[0071] 307: Based on the travel time corresponding to at least one road, determine the travel time corresponding to at least one target road in the navigation path.

[0072] 308: Add up the travel times corresponding to at least one target road to obtain the target travel time of the navigation path.

[0073] It should be noted that some steps in this embodiment are the same as some steps in other embodiments, and for the sake of brevity, they will not be repeated here.

[0074] In this embodiment, an overall time is determined based on a data acquisition period. The overall time can be divided into at least one candidate time period. Each candidate time period includes a start time and an end time. Upon receiving a navigation request from a user device, a navigation path and navigation time can be determined in response to the request. A target time period corresponding to the navigation time is determined from the at least one candidate time period. Within the target time period, the positioning trajectory corresponding to at least one road in the road network is determined. By correlating the navigation time with time periods, a positioning trajectory corresponding to the navigation time of the navigation request can be obtained, achieving high real-time and corresponding positioning trajectory acquisition, thus improving the timeliness and accuracy of the positioning trajectory.

[0075] As one embodiment, the navigation path corresponding to the navigation request includes at least one; the method further includes:

[0076] Determine the target travel time for at least one navigation path;

[0077] Based on the target travel time corresponding to at least one navigation path, generate navigation prompt information;

[0078] Send navigation prompts to the user's device.

[0079] Each navigation route can have its corresponding travel time determined using at least one road. Navigation prompts may include the travel times for at least one navigation route.

[0080] Navigation prompts are displayed on the user's device. The user can view at least one navigation path in the navigation prompts and can also select a target navigation path from the displayed at least one navigation path that matches their time and needs, and drive according to at least one road indicated by the target navigation path.

[0081] Optionally, generating navigation prompts based on the target travel times corresponding to at least one navigation path may include: determining the navigation path with the shortest target travel time from the target travel times corresponding to at least one navigation path as the target navigation path, and generating corresponding navigation prompts using the target navigation path.

[0082] In this embodiment of the disclosure, determining the target travel time corresponding to at least one navigation path can generate navigation prompt information. After the navigation prompt information is sent to the user device, the user device can output it, thereby providing accurate prompts for the travel time corresponding to at least one navigation path.

[0083] In one possible design, before determining the travel time of a road by utilizing its location characteristics and historical traffic patterns, and to obtain the travel time corresponding to at least one road, the following steps are also included:

[0084] Determine the target start time and target end time for the target time period;

[0085] Determine the preceding data collection period of the target time period;

[0086] Obtain the historical time period corresponding to the target start time and target end time of the previous collection cycle;

[0087] Determine the historical traffic characteristics of the road in the corresponding historical time period.

[0088] The target time period is the latest collection period, which determines the collection period of the navigation time. For example, using a daily collection period, if the navigation request is initiated at 9:00 AM on March 2nd, the collection period for the navigation time is the collection period of March 2nd, and the target time period can be the time period preceding 9:00 AM within that collection period. The historical time period can be the previous collection period, specifically the historical time period corresponding to the same start and end times as the target time within the collection period of March 1st. For example, if the target time period is 8:55-9:00 AM on March 2nd, the historical time period is 8:55-9:00 AM on March 1st. When the target time period is less than a certain time period threshold, the timeliness of the road features collected for that target time period is higher, ensuring the timeliness of the obtained road features.

[0089] In this embodiment of the disclosure, the target start time and target end time of the target time period are determined. The previous collection period of the target time period can be obtained, and the historical time periods corresponding to the target start time and target end time of the previous collection period can be obtained. Historical time periods that are in the same time phase as the target time period are obtained, and these historical time periods are used as time constraints to obtain the corresponding historical traffic characteristics. This enables the identification of traffic characteristics of roads in the same historical period, improving the temporal correlation between characteristics.

[0090] In some embodiments, determining the historical traffic characteristics of the road network for a historical time period includes:

[0091] Determine at least one historical driving trajectory for the road network within a historical time period;

[0092] Determine at least one historical passage parameter;

[0093] Based on at least one historical driving trajectory, extract historical passage data corresponding to at least one historical passage parameter;

[0094] Historical passage characteristics are determined based on historical passage data corresponding to at least one historical passage parameter.

[0095] The historical driving trajectory and the location trajectory are obtained in the same way, both of which are extracted from the location points collected within the time period, and will not be described in detail here.

[0096] At least one historical traffic parameter can be a parameter that accurately characterizes historical traffic characteristics. At least one historical traffic parameter can be partially identical to at least one road driving parameter. For example, both can include individual driving parameters and overall driving parameters. Furthermore, historical traffic parameters can also include parameters such as road congestion status, congestion time, and number of vehicles passing through, to extract historical driving characteristics more comprehensively and ensure the accuracy of the features.

[0097] In this embodiment of the disclosure, at least one historical driving trajectory corresponding to a road network in a historical time period is determined. The historical traffic data corresponding to the at least one historical driving trajectory in the at least one historical traffic parameter can be extracted using the determined at least one historical traffic parameter, thereby achieving accurate extraction of historical traffic data.

[0098] like Figure 4 The diagram shown is a flowchart of a navigation path travel time processing method provided in the fourth embodiment of this disclosure. This method can be configured as a navigation path travel time processing device, which can be configured in an electronic device. Wherein, with Figure 1 The difference in the illustrated embodiment is that the step of determining the positioning trajectory corresponding to at least one road in the road network may include:

[0099] 401: Determine at least one valid location point corresponding to the road network.

[0100] At least one valid location point can be obtained from at least one data acquisition device in the road network. The data acquisition device can be configured with a location point acquisition program or a software development kit (SDK), which sends the acquired location points to electronic devices.

[0101] 402: Extract at least one driving trajectory from at least one valid location point based on the user identification information corresponding to at least one valid location point.

[0102] 403: Determine the target road that matches the driving trajectory from at least one road, and obtain the target road corresponding to at least one positioning trajectory respectively.

[0103] Optionally, after extracting at least one driving trajectory from at least one valid positioning point, a trajectory identifier can be set for each driving trajectory. In practical applications, a corresponding road identifier can be set for each road. Once a target road matching the driving trajectory is obtained, an identifier association can be established between the trajectory identifier of the driving trajectory and the target road identifier of its corresponding target road. The road identifier of the target road corresponding to the driving trajectory is then added to the trajectory identifier of the driving trajectory.

[0104] 404: Based on the target roads corresponding to at least one positioning trajectory, determine at least one positioning trajectory corresponding to at least one road.

[0105] At least one location trajectory can correspond to a target road. Once the target road for each location trajectory is determined, the location trajectory for that road can be determined by querying the location trajectory that has an association relationship with the road identifier, based on the road identifier of each road, until all location trajectories corresponding to the road are obtained.

[0106] In some embodiments, after obtaining at least one positioning trajectory corresponding to a road, trajectory filtering can be performed on the at least one positioning trajectory corresponding to the road to obtain valid trajectories. Trajectory filtering may include filtering by trajectory length and / or trajectory shape. Trajectory lengths below a first length threshold or above a second length threshold are considered invalid trajectories, while those between the first and second length thresholds are considered valid trajectories. If the trajectory shape does not meet the shape usage conditions, such as having too many curved curves or an arc greater than an arc threshold, then the shape usage conditions are not met; otherwise, if there are few curved curves or the arc is less than or equal to an arc threshold, then the shape usage conditions are met.

[0107] In this embodiment of the disclosure, after determining at least one valid location point in the road network, at least one driving trajectory can be extracted from the at least one valid location point using the user identification information corresponding to each of the at least one valid location points. Using the user identification information as the basis for extracting the driving trajectory, the trajectory of each user on the road can be accurately extracted. After obtaining at least one driving trajectory, a target road matching the driving trajectory can be determined from at least one road, that is, the driving trajectory is located on the target road, obtaining the target road corresponding to each of the at least one location trajectory. Based on the target roads corresponding to each of the at least one location trajectory, the driving trajectories located on each target road are unified to obtain at least one location trajectory corresponding to each road. Through road matching, the matching of roads and location trajectories is achieved, improving the matching efficiency and accuracy of location trajectories.

[0108] In some embodiments, determining at least one valid location point corresponding to the road network may include:

[0109] Acquire at least one location point of the road network collected during the target time period;

[0110] Based on the location point selection criteria, at least one valid location point is selected from at least one location point.

[0111] The acquisition of at least one location point in the road network may include receiving location points transmitted by acquisition devices. Multiple acquisition devices may be used, each capable of acquiring location points at a specific acquisition frequency. These devices may be configured with positioning systems such as the Global Positioning System (GPS) or the BeiDou Navigation Satellite System (BDS) to acquire location points and transmit them to electronic devices.

[0112] Optionally, the data acquisition steps for at least one location point within any given time period may include:

[0113] The overall time period is divided into at least one candidate time period; the candidate time period includes a start time and an end time; the start time and end time of the overall time period are determined based on the collection cycle; the start time corresponding to each of the at least one candidate time period is monitored, and if the current time is detected as the start time of any candidate time period, the candidate time period is determined as the collection time period; during the collection time period, at least one location point in the road network is collected.

[0114] In this embodiment of the disclosure, at least one location point in the road network can be collected during the target time period. At least one valid location point can be selected from the at least one location point based on location point selection criteria. By collecting location points and filtering them using the location point selection criteria, valid location points can be obtained, achieving accurate acquisition of location points.

[0115] In one possible design, based on the location point selection criteria, at least one valid location point is selected from at least one location point, including:

[0116] Determine multiple location point categories;

[0117] Based on multiple location point categories, the location points are classified to obtain at least one location point category corresponding to each location point.

[0118] Determine the target positioning point category that meets the positioning point selection criteria from multiple positioning point categories;

[0119] At least one location point corresponding to the target location point category is identified as at least one valid location point.

[0120] At least one location point category can be determined based on attributes such as the location point's data acquisition device, the distance between the location point and the road, and the association between the location point and the road. At least one location point category can include: drift category, hotspot category, location device category, wireless network category, normal location category, low-speed trajectory type, etc. The location device category can be a target location point category. The normal location category can also be a target location point category. Multiple target location point categories can be included, for example, simultaneously including device location category and normal location category. The location point corresponding to a target location point category must satisfy all target location point categories. In actual classification, a location point can correspond to multiple categories; for example, a location point can have a drift list and a hotspot category. Low-speed trajectories are obtained based on location points of the same user device; for example, location points uploaded by the same user device at a previous time and a subsequent time have not shifted or have shifted less than a distance threshold.

[0121] The wireless network category can include Wireless Fidelity (WIFI) networks, Bluetooth networks, etc. The positioning devices category can include GPS devices, BeiDou positioning devices, etc.

[0122] In this embodiment, the selection of valid positioning points can be achieved by identifying positioning point types and obtaining positioning point categories corresponding to multiple positioning point types. From these categories, a target positioning point category that meets the selection criteria is determined, and at least one positioning point corresponding to the target positioning point category is identified as at least one valid positioning point. By classifying positioning points, the target positioning point category that meets the selection criteria can be confirmed, enabling rapid and accurate selection of valid positioning points.

[0123] As one example, determining a target road from at least one road that matches the driving trajectory includes:

[0124] The driving trajectory is input into the Hidden Markov Model corresponding to the road network, and the Hidden Markov Model is used to determine the target road with the highest matching degree from at least one road.

[0125] Hidden Markov Models can perform matching calculations on road trajectories and obtain the matching degree of the driving trajectory on at least one road. Based on the trajectory degree of the driving trajectory on at least one road, the road with the highest matching degree can be selected as the target road.

[0126] In this embodiment of the disclosure, when determining the target road corresponding to the driving trajectory from at least one road, a hidden Markov model is used to determine the target road with the highest matching degree to the driving trajectory from at least one road. This can obtain the target road that best matches the driving trajectory, thereby improving the accuracy and efficiency of obtaining the target road corresponding to the driving trajectory.

[0127] like Figure 5 The diagram shown is a flowchart of a navigation path travel time processing method provided in the fifth embodiment of this disclosure. This method can be configured as a navigation path travel time processing device, which can be configured in an electronic device. The positioning trajectory corresponding to the road may include at least one... Figure 1 The difference in the illustrated embodiment is that the step of extracting location features using the road's location trajectory may include:

[0128] 501: Determine at least one road driving parameter;

[0129] 502: Based on at least one positioning trajectory corresponding to the road, extract parameter data corresponding to at least one road driving parameter;

[0130] 503: Determine the location features of a road based on the parameter data corresponding to at least one road driving parameter.

[0131] At least one road driving parameter can be used to extract feature parameters. Road driving parameters may include trajectory speed parameters, average speed parameters, trajectory quantity parameters, trajectory change parameters, trajectory shape parameters, etc. Any parameter that can characterize road driving conditions can be used as a road driving parameter in this disclosure.

[0132] In this embodiment, the location features of the road can be extracted using at least one road driving parameter, enabling accurate extraction of road driving characteristics. This parameter extraction method, with its low computational complexity, allows for rapid and accurate extraction of the road's location features.

[0133] As one embodiment, after determining at least one road driving parameter, the method further includes:

[0134] Determine at least one individual driving parameter and the overall driving parameter in road driving parameters;

[0135] Based on at least one positioning trajectory corresponding to the road, extract parameter data corresponding to at least one road driving parameter, including:

[0136] Individual data of individual driving parameters are extracted based on the road positioning trajectory, and individual data corresponding to individual driving parameters in at least one positioning trajectory are obtained.

[0137] Overall data of overall driving parameters are extracted based on at least one positioning trajectory of the road.

[0138] Individual driving parameters can include multiple parameters, and overall driving parameters can also include multiple parameters.

[0139] Individual driving parameters can be parameters that characterize the features of a single trajectory. Overall driving parameters can be parameters that characterize at least one driving trajectory on a road as a whole. For example, trajectory speed parameters and trajectory shape parameters can be individual driving parameters, while average speed parameters and trajectory quantity parameters can be overall driving parameters.

[0140] In this embodiment of the disclosure, at least one road driving parameter can be divided into individual driving parameters and overall driving parameters. Individual driving parameters can extract the characteristics of each driving trajectory, while overall driving parameters can extract the characteristics of all driving trajectories. By setting individual and overall driving parameters, the road's positioning features include both local and overall road characteristics, resulting in a more comprehensive and accurate representation of the road.

[0141] In one possible design, the location features of the road are determined based on parameter data corresponding to at least one road driving parameter, including:

[0142] Based on the individual data corresponding to the individual driving parameters in at least one positioning trajectory, determine the individual sub-features corresponding to the individual driving parameters;

[0143] Based on the overall data corresponding to the overall driving parameters, determine the overall sub-features corresponding to the overall driving parameters;

[0144] By fusing individual sub-features with overall sub-features, the location features of the road are obtained.

[0145] Individual sub-features can be generated by stitching together individual data corresponding to individual driving parameters on at least one positioning trajectory to obtain stitched individual data, and then converting the stitched individual data into individual sub-features. Individual sub-features can include individual features from all trajectories.

[0146] The parameter data corresponding to the overall driving parameters can be extracted from at least one positioning trajectory.

[0147] In this embodiment of the disclosure, the positioning features of the road are accurately extracted based on individual driving parameters and overall driving parameters. Individual driving parameters can be used to extract individual data for each positioning trajectory, thereby realizing feature extraction for each positioning trajectory. Overall driving parameters can be used to extract overall features for at least one driving trajectory, ensuring the accuracy of the extracted positioning features.

[0148] In some embodiments, it also includes:

[0149] Identify the associated roads that are connected to the road and the location features corresponding to the associated roads;

[0150] By utilizing the road's location characteristics and combining them with its historical traffic patterns, the road's permitted travel time is determined, including:

[0151] The travel time of a road is determined by using the location features of the road, the location features of associated roads, and the historical traffic characteristics of the road.

[0152] Optionally, determining the travel time of a road by utilizing the road's location features, the location features of associated roads, and the road's historical traffic features may include: inputting the road's location features, the location features of associated roads, and the road's historical traffic features into a trained time series model to obtain the road's travel time.

[0153] By associating roads, time series models can take into account the contextual information of roads, enabling more accurate road predictions. Time series models can be deep learning models, which can be trained. Input data can include the location features of roads, the location features of associated roads, and the historical traffic characteristics of roads. Output data can be the travel time of roads. The specific training steps for time series models, given that the specific content of the input data is determined, can be found in the descriptions of relevant technologies and will not be elaborated upon here.

[0154] In this embodiment of the disclosure, associated roads that are connected to the existing roads, as well as the location features corresponding to the associated roads, can be identified. The associated roads can be used as input data for travel time, and together with the road's location features and historical travel characteristics, they are used to determine the travel time. This allows the determination of travel time to comprehensively consider both the road itself and the road environment characteristics, resulting in accurate acquisition of road travel time.

[0155] In practical applications, the technical solution of this disclosure can be applied to the automatic navigation scenario of autonomous vehicles. Autonomous vehicles can be equipped with data collection devices that can send the collected location points to electronic devices during vehicle operation. When a user drives an autonomous vehicle, they can initiate a navigation request. Using the technical solution of this disclosure, the travel time corresponding to at least one navigation path can be obtained. The travel time corresponding to at least one navigation path is sent to the driving system of the autonomous vehicle, and can be displayed by an output device in the driving system, such as a display screen. Furthermore, the driving system can also provide a route selection function. For example, the display screen can be a touchscreen, allowing the user to directly select a target navigation path from at least one navigation path output on the touchscreen, such as selecting the navigation path with the shortest travel time. When the driving system detects the user-triggered selection operation, it can execute autonomous driving control according to the user-selected target navigation path.

[0156] Of course, in practical applications, in addition to autonomous vehicles, the technical solutions disclosed herein can also be applied to mobile phone navigation, assisted navigation and other application scenarios. The application process is similar to that of autonomous vehicles, and will not be described in detail here.

[0157] like Figure 6 The diagram shown is a structural schematic of a navigation path travel time processing device according to the sixth embodiment of this disclosure. This device can be configured with a navigation path travel time processing method and can be configured in an electronic device. The navigation time processing device 600 may include:

[0158] Trajectory determination unit 601: used to determine the positioning trajectory corresponding to at least one road in the road network.

[0159] Feature extraction unit 602: used to extract the location features of the road based on the road's location trajectory.

[0160] Feature calculation unit 603: Used to determine the travel time of a road by utilizing the road's location features and combining them with the road's historical traffic features, so as to obtain the travel time corresponding to at least one road.

[0161] Time matching unit 604: used to determine the travel time of at least one target road in the navigation path based on the travel time of at least one road.

[0162] Time addition unit 605: used to add the travel times corresponding to at least one target road to obtain the target travel time of the navigation path.

[0163] As one embodiment, the feature calculation unit includes:

[0164] The first extraction module is used to fuse the location features and historical traffic features of the road to obtain the road driving features.

[0165] The time calculation module is used to input road driving features into the time series model obtained through training to obtain the road travel time.

[0166] As yet another embodiment, the device further includes:

[0167] A time division unit is used to divide the overall time period into at least one candidate time period; the candidate time period includes a start time and an end time; the start time and end time of the overall time period are determined based on the collection cycle.

[0168] The request and response unit is used to respond to a navigation request sent by the user equipment and determine the navigation path and navigation time corresponding to the navigation request.

[0169] The target determination unit is used to determine the target time period corresponding to the navigation time from at least one candidate time period.

[0170] The trajectory determination unit includes:

[0171] The trajectory determination module is used to determine the positioning trajectory of at least one road in the road network during the target time period.

[0172] In some embodiments, the navigation path corresponding to the navigation request includes at least one; the apparatus further includes:

[0173] A time determination unit is used to determine the target travel time corresponding to at least one navigation path;

[0174] The navigation generation unit is used to generate navigation prompt information based on the target travel time corresponding to at least one navigation path;

[0175] The information prompting unit is used to send navigation prompts to the user's device.

[0176] Navigation prompts can be displayed on the user's device.

[0177] One possible design also includes:

[0178] The first determining unit is used to determine the target start time and target end time of the target time period;

[0179] The second determining unit is used to determine the previous acquisition cycle of the acquisition cycle in which the target time period is located.

[0180] Historical time unit, used to obtain the historical time period corresponding to the target start time and target end time of the previous collection cycle;

[0181] Historical feature units are used to determine the historical traffic characteristics of the road network in a historical time period.

[0182] In some embodiments, the historical time unit includes:

[0183] The first determining module is used to determine at least one historical driving trajectory of the road network in a historical time period;

[0184] The second determining module is used to determine at least one historical passage parameter;

[0185] The parameter determination module is used to extract historical passage data corresponding to at least one historical passage parameter based on at least one historical driving trajectory.

[0186] The second extraction module is used to determine historical passage features based on historical passage data corresponding to at least one historical passage parameter.

[0187] In one possible design, the trajectory determination unit includes:

[0188] The effective determination module is used to determine at least one valid location point corresponding to the road network;

[0189] The identification and positioning module is used to extract at least one driving trajectory from at least one valid positioning point based on the user identification information corresponding to at least one valid positioning point.

[0190] The road matching module is used to determine the target road that matches the driving trajectory from at least one road, and obtain the target road corresponding to at least one positioning trajectory respectively;

[0191] The trajectory positioning module is used to determine at least one positioning trajectory corresponding to at least one target road based on at least one positioning trajectory.

[0192] In some embodiments, the effective determination module includes:

[0193] The location acquisition submodule is used to acquire at least one location point of the road network during the target time period;

[0194] The positioning selection word module is used to select at least one valid positioning point from at least one positioning point based on positioning point selection conditions.

[0195] In some embodiments, the positioning selection word module is specifically used for:

[0196] The category determination submodule is used to determine the category of multiple positioning points;

[0197] The location classification submodule is used to classify location points based on multiple location point categories, and obtain at least one location point category corresponding to each location point.

[0198] The category selection submodule is used to determine the target positioning point category that meets the positioning point selection criteria from multiple positioning point categories;

[0199] The location acquisition submodule is used to determine at least one location point corresponding to the target location point category as at least one valid location point.

[0200] Further, optionally, the road matching module includes:

[0201] The road matching submodule is used to input the driving trajectory into the hidden Markov model corresponding to the road network, and use the hidden Markov model to determine the target road with the highest matching degree from at least one road.

[0202] As another embodiment, the positioning trajectory corresponding to the road includes at least one feature extraction unit, including:

[0203] The driving determination module is used to determine at least one road driving parameter;

[0204] The data acquisition module is used to extract parameter data corresponding to at least one road driving parameter based on at least one positioning trajectory corresponding to the road.

[0205] The data conversion module is used to determine the location features of a road based on parameter data corresponding to at least one road driving parameter.

[0206] In some embodiments, the driving determination module includes:

[0207] The individual determination module is used to determine the individual driving parameters and the overall driving parameters in at least one road driving parameter;

[0208] The data acquisition module includes:

[0209] The first acquisition submodule is used to extract individual data of individual driving parameters based on the positioning trajectory of the road, and to obtain individual data corresponding to the individual driving parameters in at least one positioning trajectory.

[0210] The second acquisition submodule is used to extract overall data of overall driving parameters based on at least one positioning trajectory of the road.

[0211] In some embodiments, the data conversion module includes:

[0212] The first extraction submodule is used to determine the individual sub-features corresponding to the individual driving parameters based on the individual data corresponding to at least one positioning trajectory for the individual driving parameters.

[0213] The second extraction submodule is used to determine the overall sub-features corresponding to the overall driving parameters based on the overall data corresponding to the overall driving parameters.

[0214] The feature fusion submodule is used to fuse individual sub-features with overall sub-features to obtain the location features of the road.

[0215] As yet another embodiment, it also includes:

[0216] The association determination unit is used to determine the associated roads that have road connection relationships with the roads and the location features corresponding to the associated roads;

[0217] Feature calculation unit, including:

[0218] The time calculation module is used to determine the travel time of a road by utilizing the road's location features, the location features of associated roads, and the road's historical traffic characteristics.

[0219] The apparatus in this disclosure corresponds to the method in the foregoing embodiments. The various steps performed by the apparatus can be referred to the description in the method, and will not be repeated here.

[0220] It should be noted that the location trajectory in this embodiment is not a trajectory specific to any particular user and does not reflect the personal information of any particular user. It should also be noted that the driving trajectory and location points in this embodiment are from publicly available datasets.

[0221] 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.

[0222] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0223] According to embodiments of this disclosure, this disclosure also provides a computer program product comprising: a computer program stored in a readable storage medium, at least one processor of an electronic device being able to read the computer program from the readable storage medium, and the at least one processor executing the computer program causing the electronic device to perform the scheme provided in any of the above embodiments.

[0224] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. 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.

[0225] like Figure 7 As shown, device 700 includes a computing unit 701, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 702 or a computer program loaded from storage unit 708 into random access memory (RAM) 703. RAM 703 may also store various programs and data required for the operation of device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via bus 704. Input / output (I / O) interface 705 is also connected to bus 704.

[0226] Multiple components in device 700 are connected to I / O interface 705, including: input unit 706, such as keyboard, mouse, etc.; output unit 707, such as various types of monitors, speakers, etc.; storage unit 708, such as disk, optical disk, etc.; and communication unit 709, such as network card, modem, wireless transceiver, etc. Communication unit 709 allows device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0227] The computing unit 701 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 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 701 performs the various methods and processes described above, such as the navigation path travel time processing method X. For example, in some embodiments, the navigation path travel time processing method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the navigation path travel time processing method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform a navigation path travel time processing method by any other suitable means (e.g., by means of firmware).

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0234] It should be understood that the various forms of processes shown above can be used to reorder, 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.

[0235] 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 processing navigation path travel time, comprising: During the target time period, acquire at least one location point of the road network obtained during the target time period; Determine multiple location point categories; Based on multiple positioning point categories, the positioning points are classified to obtain at least one positioning point category corresponding to each positioning point. Determine the target positioning point category that meets the positioning point selection criteria from among the multiple positioning point categories; At least one positioning point corresponding to the target positioning point category is determined as at least one valid positioning point; Based on the user identification information corresponding to at least one of the effective positioning points, extract at least one driving trajectory from at least one of the effective positioning points; Determine the target road that matches the driving trajectory from at least one road, and obtain the target road corresponding to at least one positioning trajectory respectively; Based on the target roads corresponding to at least one of the positioning trajectories, determine at least one positioning trajectory corresponding to at least one of the roads; Based on the location trajectory of the road, the location features of the road are extracted; the location features are obtained by extracting at least one road feature parameter; the road feature parameter includes: the driving speed of each user, the average driving speed of all users, the number of trajectories, and the trajectory change rate; By utilizing the location features of the road and combining them with the historical traffic features of the road, the travel time of the road is determined, so as to obtain the travel time corresponding to at least one of the roads respectively; Based on the travel time corresponding to at least one of the roads, determine the travel time corresponding to at least one target road in the navigation path; The target travel time of the navigation path is obtained by adding the travel times corresponding to at least one of the target roads.

2. The method according to claim 1, wherein, The method of determining the travel time of a road by utilizing its location features and historical traffic characteristics includes: The road driving characteristics are obtained by fusing the location features and historical traffic features of the road. The road driving characteristics are input into the trained time series model to obtain the road travel time.

3. The method according to claim 1 or 2, further comprising: The overall time period is divided into at least one candidate time period; the candidate time period includes a start time and an end time. The start and end times of the overall time period are determined based on the collection cycle; In response to a navigation request sent by a user equipment, determine the navigation path and navigation time corresponding to the navigation request; The target time period corresponding to the navigation time is determined from at least one of the candidate time periods.

4. The method according to claim 3, wherein, The navigation path corresponding to the navigation request includes at least one; the method further includes: Determine the target travel time for at least one of the navigation paths; Based on the target travel time corresponding to at least one of the navigation paths, generate navigation prompt information; The navigation prompt information is sent to the user device.

5. The method according to claim 3, further comprising, before determining the travel time of the road by utilizing the road's location features and combining the road's historical traffic features to obtain the travel time corresponding to at least one of the roads: Determine the target start time and target end time for the target time period; Determine the preceding acquisition cycle of the acquisition cycle in which the target time period falls; Obtain the historical time period corresponding to the target start time and the target end time of the previous collection cycle; Determine the historical traffic characteristics of the road network corresponding to the historical time period.

6. The method according to claim 5, wherein, Determining the historical traffic characteristics of the road network corresponding to the historical time period includes: Determine at least one historical driving trajectory of the road network corresponding to the historical time period; Determine at least one historical passage parameter; Based on at least one of the historical driving trajectories, extract historical passage data corresponding to at least one of the historical passage parameters respectively; The historical passage features are determined based on the historical passage data corresponding to at least one of the historical passage parameters.

7. The method according to claim 1, wherein, Determining a target road from at least one of the roads that matches the driving trajectory includes: The driving trajectory is input into the hidden Markov model corresponding to the road network, and the hidden Markov model is used to determine the target road with the highest matching degree from at least one of the roads.

8. The method according to any one of claims 1-2 and 4-7, wherein, The location trajectory corresponding to the road includes at least one, and the step of extracting the location features of the road based on the location trajectory includes: Determine at least one road driving parameter; Based on at least one of the positioning trajectories corresponding to the road, extract parameter data corresponding to at least one of the road driving parameters respectively; The positioning features of the road are determined based on the parameter data corresponding to at least one of the road driving parameters.

9. The method according to claim 8, wherein, After determining at least one road driving parameter, the method further includes: Determine at least one individual driving parameter and the overall driving parameter among the road driving parameters; The step of extracting parameter data corresponding to at least one of the road driving parameters based on at least one positioning trajectory corresponding to the road includes: Individual data of the individual driving parameters are extracted based on the positioning trajectory of the road, and individual data corresponding to the individual driving parameters in at least one of the positioning trajectories are obtained. The overall data of the overall driving parameters are extracted based on at least one positioning trajectory of the road.

10. The method according to claim 9, wherein, The step of determining the location features of the road based on parameter data corresponding to at least one of the road driving parameters includes: Based on the individual data corresponding to the individual driving parameters in at least one of the positioning trajectories, determine the individual sub-features corresponding to the individual driving parameters; Based on the overall data corresponding to the overall driving parameters, determine the overall sub-features corresponding to the overall driving parameters; The individual sub-features and the overall sub-features are fused to obtain the location features of the road.

11. The method according to any one of claims 1-2, 4-7, and 9-10, further comprising: Identify the associated roads that have road connections with the road and the location features corresponding to the associated roads; The method of determining the travel time of a road by utilizing its location features and historical traffic characteristics includes: The travel time of the road is determined by using the location features of the road, the location features of the associated roads, and the historical traffic features of the road.

12. A navigation time processing device, comprising: A trajectory determination unit is used to determine the positioning trajectory corresponding to at least one road in the road network. The feature extraction unit is used to extract the positioning features of the road based on the positioning trajectory of the road; the positioning features are obtained by extracting at least one road feature parameter; the road feature parameter includes: the driving speed of each user, the average driving speed of all users, the number of trajectories, and the trajectory change rate; The feature calculation unit is used to determine the travel time of the road by utilizing the location features of the road and combining the historical traffic features of the road, so as to obtain the travel time corresponding to at least one of the roads respectively. A time matching unit is used to determine the travel time of at least one target road in the navigation path based on the travel time of at least one of the roads respectively; A time addition unit is used to add the travel times corresponding to at least one of the target roads to obtain the target travel time of the navigation path; The trajectory determination unit includes: The trajectory determination module is used to determine the positioning trajectory corresponding to at least one of the roads in the road network during a target time period. The trajectory determination unit includes: A valid determination module is used to determine at least one valid location point corresponding to the road network; The identification and positioning module is used to extract at least one driving trajectory from at least one of the at least one effective positioning points based on the user identification information corresponding to at least one of the at least one effective positioning points. The road matching module is used to determine a target road that matches the driving trajectory from at least one of the roads, and to obtain the target road corresponding to at least one of the positioning trajectories respectively; A trajectory positioning module is used to determine at least one positioning trajectory corresponding to at least one of the target roads based on at least one positioning trajectory; The effective determination module includes: The positioning and acquisition submodule is used to acquire at least one positioning point of the road network during the target time period; The positioning selection submodule is used to select at least one valid positioning point from at least one of the positioning points based on the positioning point selection conditions. The positioning selection submodule is specifically used for: The category determination submodule is used to determine the category of multiple positioning points; The positioning and classification submodule is used to classify the positioning points based on multiple positioning point categories to obtain at least one positioning point category corresponding to each positioning point. The category selection submodule is used to determine the target positioning point category that meets the positioning point selection conditions among the multiple positioning point categories; The positioning acquisition submodule is used to determine at least one positioning point corresponding to the target positioning point category as at least one of the valid positioning points.

13. The apparatus according to claim 12, wherein, The feature calculation unit includes: The first extraction module is used to fuse the location features of the road and the historical traffic features of the road to obtain the road driving features of the road. The time calculation module is used to input the road driving features into the trained time series model to obtain the road travel time.

14. The apparatus according to claim 12 or 13, further comprising: A time division unit is used to divide an overall time period into at least one candidate time period; the candidate time period includes a start time and an end time. The start and end times of the overall time period are determined based on the collection cycle; The request response unit is used to respond to a navigation request sent by a user equipment and determine the navigation path and navigation time corresponding to the navigation request. A target determination unit is configured to determine the target time period corresponding to the navigation time from at least one of the candidate time periods.

15. The apparatus according to claim 14, wherein, The navigation path corresponding to the navigation request includes at least one; the device further includes: A time determination unit is used to determine the target travel time corresponding to at least one of the navigation paths; A navigation generation unit is used to generate navigation prompt information based on the target travel time corresponding to at least one of the navigation paths; An information prompting unit is used to send the navigation prompt information to the user equipment.

16. The apparatus of claim 14, further comprising: The first determining unit is used to determine the target start time and the target end time of the target time period; The second determining unit is used to determine the previous acquisition cycle of the acquisition cycle in which the target time period is located; Historical time unit, used to obtain the historical time period corresponding to the target start time and the target end time of the previous collection cycle; A historical feature unit is used to determine the historical traffic features of the road network corresponding to the historical time period.

17. The apparatus according to claim 16, wherein, The historical time unit includes: The first determining module is used to determine at least one historical driving trajectory of the road network corresponding to the historical time period. The second determining module is used to determine at least one historical passage parameter; The parameter determination module is used to extract historical passage data corresponding to at least one of the historical passage parameters based on at least one of the historical driving trajectories. The second extraction module is used to determine the historical passage features based on the historical passage data corresponding to at least one of the historical passage parameters.

18. The apparatus according to claim 12, wherein, The road matching module includes: The road matching submodule is used to input the driving trajectory into the hidden Markov model corresponding to the road network, and use the hidden Markov model to determine the target road with the highest matching degree with the driving trajectory from at least one of the roads.

19. The apparatus according to any one of claims 12-13, 15-18, wherein, The location trajectory corresponding to the road includes at least one feature extraction unit, which includes: The driving determination module is used to determine at least one road driving parameter; The data acquisition module is used to extract parameter data corresponding to at least one of the road driving parameters based on at least one of the positioning trajectories corresponding to the road. A data conversion module is used to determine the positioning features of the road based on parameter data corresponding to at least one of the road driving parameters.

20. The apparatus according to claim 19, wherein, The driving determination module includes: An individual determination module is used to determine at least one individual driving parameter and the overall driving parameter among the road driving parameters; The data acquisition module includes: The first obtaining submodule is used to extract individual data of the individual driving parameters based on the positioning trajectory of the road, and to obtain individual data corresponding to the individual driving parameters in at least one of the positioning trajectories. The second acquisition submodule is used to extract overall data of the overall driving parameters based on at least one positioning trajectory of the road.

21. The apparatus according to claim 20, wherein, The data conversion module includes: The first extraction submodule is used to determine the individual sub-features corresponding to the individual driving parameters based on the individual data corresponding to at least one of the positioning trajectories. The second extraction submodule is used to determine the overall sub-features corresponding to the overall driving parameters based on the overall data corresponding to the overall driving parameters; The feature fusion submodule is used to fuse the individual sub-features with the overall sub-features to obtain the location features of the road.

22. The apparatus according to any one of claims 12-13, 15-18, and 20-21, further comprising: The association determination unit is used to determine the associated roads that have a road connection relationship with the road and the location features corresponding to the associated roads; The feature calculation unit includes: The time calculation module is used to determine the travel time of the road by utilizing the location features of the road, the location features of the associated roads, and the historical traffic features of the road.

23. 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 executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method according to any one of claims 1-11.

24. 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 1-11.

25. A computer program product comprising a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-11.

Images