Method, device and computer program product for determining travel information

Abstract

The present disclosure provides a method, device, electronic device, storage medium, and computer program product for determining travel information, which relates to the field of artificial intelligence technology, specifically deep learning technology, and can be used in navigation scenarios. The specific implementation scheme is: determining the starting and ending points in the obtained route calculation request; determining the road network time series feature information of the road network data at multiple times within the time period to which the current moment belongs through a pre-trained feature extraction network; determining the coding information corresponding to the starting and ending points from the road network time series feature information; based on the coding information, determining the travel information including the connecting location and connecting travel mode between the starting and ending points through a pre-trained multi-task network. The present disclosure improves the accuracy of the obtained travel information and the flexibility of the travel mode.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, specifically to deep learning technology, and especially to a method and device for determining travel information, as well as a training method and device for a travel information determination model, an electronic device, a storage medium, and a computer program product, which can be used in navigation scenarios. Background Art

[0002] Combining multiple travel modes to determine a total travel route often achieves optimal travel efficiency in terms of time, cost, and energy consumption. Existing methods typically use a round-robin search approach, first brute-forcing different travel modes to generate different combinations, then sorting and filtering the resulting combinations to obtain a high-quality combined travel solution. Existing route calculation methods using round-robin search are computationally intensive and time-consuming. Summary of the Invention

[0003] The present disclosure provides a method and device for determining travel information, and a method and device for training a travel information determination model, an electronic device, a storage medium, and a computer program product.

[0004] According to a first aspect, a method for determining travel information is provided, comprising: determining the starting and ending points in an acquired route calculation request; determining, through a pre-trained feature extraction network, road network temporal feature information of road network data at multiple moments within a time period to which a current moment belongs; determining, from the road network temporal feature information, coding information corresponding to the starting and ending points; and determining, based on the coding information, travel information including connecting locations and connecting travel modes between the starting and ending points through a pre-trained multi-task network.

[0005] According to a second aspect, a method for training a travel information determination model is provided, comprising: obtaining a training sample set, wherein the training samples in the training sample set include trajectory data and connection location labels and connection travel mode labels containing different travel modes; determining, through a feature extraction network, road network temporal feature information of road network data at multiple moments within a target time period corresponding to the input trajectory data; determining, from the road network temporal feature information, encoding information corresponding to the start and end points of the input trajectory data; inputting the encoding information into a multi-task network, and using the connection location label and connection travel mode label corresponding to the input trajectory data as the expected outputs of the multi-task network, thereby training a travel information determination model including the feature extraction network and the multi-task network.

[0006] According to the third aspect, a travel information determination device is provided, comprising: a first determination unit, configured to determine the starting and ending points in an acquired route calculation request; an extraction unit, configured to determine, through a pre-trained feature extraction network, road network temporal feature information of road network data at multiple moments within a time period to which a current moment belongs; an encoding unit, configured to determine encoding information corresponding to the starting and ending points from the road network temporal feature information; and a second determination unit, configured to determine, based on the encoding information, travel information including connecting locations and connecting travel modes between the starting and ending points through a pre-trained multi-task network.

[0007] According to a fourth aspect, a training device for a travel information determination model is provided, comprising: an acquisition unit configured to acquire a training sample set, wherein the training samples in the training sample set include trajectory data and connection location labels and connection travel mode labels containing different travel modes; a training unit configured to determine, through a feature extraction network, road network temporal feature information of road network data at multiple moments within a target time period corresponding to the input trajectory data; determine, from the road network temporal feature information, encoding information corresponding to the start and end points of the input trajectory data; input the encoding information into a multi-task network, and use the connection location label and connection travel mode label corresponding to the input trajectory data as the expected output of the multi-task network, thereby training to obtain a travel information determination model comprising a feature extraction network and a multi-task network.

[0008] According to the fifth aspect, 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, and the instructions are executed by the at least one processor so as to enable the at least one processor to execute the method described in any implementation of the first aspect or the second aspect.

[0009] According to a sixth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method described in any one of the implementations of the first and second aspects.

[0010] According to a seventh aspect, a computer program product is provided, comprising: a computer program, which implements the method described in any implementation manner of the first aspect or the second aspect when executed by a processor.

[0011] According to the technology disclosed in the present invention, a method for determining travel information is provided, in which accurate coding information corresponding to the starting point is determined from the road network time series feature information of the road network data at multiple moments extracted by the feature extraction network in the travel information determination model, and then the connecting position and connecting travel mode between the starting and ending points are determined based on the determined coding information through a multi-task network, thereby improving the accuracy of the obtained travel information and the flexibility of the travel mode.

[0012] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0014] Figure 1 is an exemplary system architecture diagram in which an embodiment of the present disclosure may be applied;

[0015] Figure 2 is a flow chart of an embodiment of a method for determining travel information according to the present disclosure;

[0016] Figure 3 is a schematic diagram of an application scenario of the method for determining travel information according to this embodiment;

[0017] Figure 4 is a schematic diagram of the structure of a travel information determination model according to the present disclosure;

[0018] Figure 5 is a flow chart of another embodiment of a method for determining travel information according to the present disclosure;

[0019] Figure 6 is a flowchart of an embodiment of a method for training a travel information determination model according to the present disclosure;

[0020] Figure 7 is a structural diagram of an embodiment of a device for determining travel information according to the present disclosure;

[0021] Figure 8 is a structural diagram of an embodiment of a training device for determining a travel information model according to the present disclosure;

[0022] Figure 9 It is a schematic diagram of the structure of a computer system suitable for implementing the embodiments of the present disclosure. DETAILED DESCRIPTION

[0023] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0024] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0025] Figure 1 An exemplary architecture 100 is shown to which the method and apparatus for determining travel information and the method and apparatus for training a travel information determination model of the present disclosure can be applied.

[0026] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. The communication connections between terminal devices 101, 102, and 103 constitute a topological network, and network 104 is used to provide a medium for communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0027] Terminal devices 101, 102, and 103 can be hardware devices or software that support network connection for data interaction and data processing. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices that support network connection, information acquisition, interaction, display, processing, and other functions, including but not limited to smartphones, tablet computers, e-book readers, laptop computers, and desktop computers. When terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software or software modules, for example, to provide distributed services, or they can be implemented as a single software or software module. No specific limitations are given here.

[0028] Server 105 can be a server that provides various services. For example, in response to route calculation requests issued by terminal devices 101, 102, and 103, it can determine the accurate coding information corresponding to the starting point from the road network time series feature information of the road network data at multiple times extracted by the feature extraction network in the travel information determination model, and then determine the connection location and connecting travel mode between the starting and ending points based on the determined coding information through the multi-task network. For another example, a backend processing server that trains a travel information determination model including a feature extraction network and a multi-task network using training samples provided by terminal devices 101, 102, and 103. As an example, server 105 can be a cloud server.

[0029] It should be noted that the server can be either hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software or software modules (e.g., software or software modules for providing distributed services), or as a single software or software module. No specific limitations are given here.

[0030] It should also be noted that the travel information determination method and travel information determination model training method provided in the embodiments of the present disclosure can be executed by a server, a terminal device, or a server and a terminal device in coordination with each other. Accordingly, the various components (e.g., various units) included in the travel information determination device and the travel information determination model training device can be entirely located in the server, entirely located in the terminal device, or separately located in the server and the terminal device.

[0031] It should be understood that Figure 1 The number of terminal devices, networks, and servers in the system is merely illustrative. Any number of terminal devices, networks, and servers may be provided as needed. When the electronic device on which the method for determining travel information or the method for training a travel information determination model runs does not need to transmit data with other electronic devices, the system architecture may only include the electronic device (e.g., a server or terminal device) on which the method for determining travel information or the method for training a travel information determination model runs.

[0032] Please refer to Figure 2 , Figure 2 This is a flow chart of a method for determining travel information provided in an embodiment of the present disclosure, wherein process 200 includes the following steps:

[0033] Step 201: Determine the starting and ending points in the acquired path calculation request.

[0034] In this embodiment, the execution subject of the method for determining travel information (for example, Figure 1 The terminal device or server in the network may obtain the path calculation request remotely or locally based on a wired network connection mode or a wireless network connection mode, and determine the starting and ending points in the obtained path calculation request.

[0035] A route calculation request is used to request the calculation of a navigation route between a starting point and an ending point. For example, the map navigation application in the aforementioned execution entity provides an application interface for users to enter starting and ending points. The application interface includes input boxes for the starting and ending points. Users can enter the corresponding starting and ending point information in the input boxes to initiate a route calculation request.

[0036] After receiving the path calculation request, the execution entity may parse the path calculation request to determine the start and end points included therein.

[0037] Step 202: Determine the road network temporal feature information of the road network data at multiple moments within the time period to which the current moment belongs through a pre-trained feature extraction network.

[0038] In this embodiment, the execution subject may determine the road network temporal feature information of the road network data at multiple moments within the time period to which the current moment belongs through a pre-trained feature extraction network.

[0039] Road network data includes road data for various modes of travel, including but not limited to subway network data, bus network data, driving network data, walking network data, and cycling network data. It is understood that, in general, the same road data may include multiple attributes. For example, the same road may include both bus road attributes and driving road attributes.

[0040] Road network data may change at different times due to factors such as road construction, road regulations, and tidal lanes. To determine the impact of network data changes on travel information, the execution entity can use a pre-trained feature extraction network to extract feature information from road network data at multiple times close to the current time, and then extract the time series variation information of the feature information of the road network data at each time to obtain road network time series feature information.

[0041] In this embodiment, the pre-trained feature extraction network can be an encoding network with feature extraction function, including but not limited to a convolutional neural network model, a residual network model, an AlexNet model, and a VGG (Visual Geometry Group Network) model.

[0042] Specifically, the execution entity can divide a day into multiple moments (for example, a day can be divided into 96 moments on average) based on a daily cycle. A time window is used to determine multiple moments adjacent to the current moment, using the length of a preset time period as the time window. The length of the time period can be flexibly set. As an example, the length of a time period is 120 minutes.

[0043] Step 203: Determine the coding information corresponding to the start and end points from the road network time sequence characteristic information.

[0044] In this embodiment, the execution entity may determine the coding information corresponding to the start and end points from the road network temporal feature information.

[0045] The road network temporal characteristic information includes the coding information of each position in the road network. In this embodiment, the execution entity can determine the coding information of the starting position and the coding information of the end position from the road network temporal characteristic information based on the matching of the position information.

[0046] Step 204 : Based on the encoded information, the pre-trained multi-task network is used to determine travel information including the connecting location between the starting and ending points and the connecting travel mode.

[0047] In this embodiment, the execution entity may determine travel information including the connecting location between the starting and ending points and the connecting travel mode through a pre-trained multi-task network based on the encoding information.

[0048] Specifically, the above-mentioned execution entity can input the coding information of the starting and ending points into the multi-task network, output the connecting location through the sub-network responsible for outputting the connecting location in the multi-task network, and output the connecting travel mode through the sub-network responsible for outputting the connecting travel mode.

[0049] In this embodiment, the number of connecting locations between the starting and ending points and the types of connecting travel modes are not limited during the process of processing route calculation requests. Generally speaking, when the distance between the starting and ending points is short, the number of connecting locations determined between the starting and ending points is small, and the types of connecting travel modes are small; when the distance between the starting and ending points is long, the number of connecting locations determined between the starting and ending points is large, and the types of connecting travel modes are large.

[0050] For example, for a route calculation request corresponding to start point A and end point B, the connecting locations between the start and end points are determined to include C and D. The travel mode between locations A and C is the subway; between locations C and D, the travel mode is the bus; and between locations D and B, the travel mode is cycling.

[0051] Continue to see Figure 3 , Figure 3 FIG3 is a schematic diagram 300 of an application scenario of the method for determining travel information according to this embodiment. Figure 3 In the application scenario, user 301 sends a route calculation request to server 303 through terminal device 302. The route calculation request includes a starting point 304 and an end point 305. After determining the starting and ending points in the obtained route calculation request, the server first determines the road network time series feature information of the road network data 307, 308, and 309 at multiple times within the time period to which the current moment belongs through the pre-trained feature extraction network 306; then, the coding information corresponding to the starting and ending points is determined from the road network time series feature information; finally, based on the coding information, the pre-trained multi-task network 310 is used to determine the travel information including the connecting locations 311 and 312 between the starting and ending points and the connecting travel mode. Specifically, between locations 304 and 311, the travel mode is subway; between 311 and 312, the travel mode is bus; between 312 and 305, the travel mode is cycling.

[0052] In this embodiment, a method for determining travel information is provided. For the road network time series feature information of the road network data at multiple times extracted by the feature extraction network in the travel information determination model, accurate coding information corresponding to the starting point is determined, and then the connecting position and connecting travel mode between the starting and ending points are determined based on the determined coding information through a multi-task network, thereby improving the accuracy of the obtained travel information and the flexibility of the travel mode.

[0053] In some optional implementations of this embodiment, the feature extraction network includes multiple graph convolutional networks and a temporal feature extraction network. In this implementation, the execution entity may perform step 202 as follows:

[0054] First, multiple graph convolutional networks are used to extract the road network feature information of road network data at multiple times within a time period.

[0055] As an example, multiple graph convolutional networks correspond one-to-one to multiple moments. For each graph convolutional network in the multiple graph convolutional networks, the road network data of the graph convolutional network at the corresponding moment is input into the graph convolutional network to obtain the road network data and road network feature information of the corresponding moment.

[0056] Second, the time series feature extraction network is used to extract the time series change information between the road network feature information corresponding to multiple moments within a time period to obtain the road network time series feature information.

[0057] In this implementation, after obtaining the road network feature information of the road network data at multiple time points, the time series change information between the multiple road network feature information is extracted through the time series feature extraction network to obtain the road network time series feature information.

[0058] The temporal feature extraction network may be any network model having a temporal feature extraction function. As an example, the temporal feature extraction network is an LSTM (long-short term memory) model having a GRU (Gated Recurrent Unit) structure.

[0059] In this implementation method, the road network feature information of the road network data at each time is first extracted through multiple graph convolutional networks, and then the road network temporal feature information between the road network feature information corresponding to multiple time periods is extracted through a temporal feature extraction network, thereby improving the accuracy of the obtained road network temporal feature information, and then improving the accuracy of the coding information of the start and end points, thereby improving the accuracy of travel information.

[0060] In some optional implementations of this embodiment, the above-mentioned execution entity can perform the above-mentioned step 204 in the following manner: based on the coding information and the environmental information corresponding to the current moment, determine the travel information including the connecting location between the starting and ending points and the connecting travel mode through a multi-task network.

[0061] The environmental information may be any environmental information that may affect the mode of travel, including but not limited to at least one of the following: weather, holidays, city size, preset activities, and seasons.

[0062] In this implementation method, on the basis of considering the starting and ending points, the above-mentioned execution entity also considers the environmental information corresponding to the starting and ending points at the current moment, so as to generate travel information suitable for the current environment under the influence of the environmental information, including the connecting position and connecting travel mode between the starting and ending points.

[0063] For example, on rainy days, walking, cycling and other travel modes should be minimized; on holidays, traffic congestion generally occurs, so travel modes corresponding to congested sections should be minimized.

[0064] In this implementation, the coding information of the starting and ending points and the corresponding environmental information are combined to determine the travel information including the connecting location and connecting travel mode between the starting and ending points, so that the determined travel information is compatible with the environmental information, further improving the accuracy of the determined travel information.

[0065] Continue to refer Figure 4 , showing a schematic diagram of the structure of the travel information determination model. The travel information determination model 400 includes a feature extraction network 401 and a multi-task network 402. The feature extraction network 401 includes multiple graph convolutional networks 4011 and a temporal feature extraction network 4012. The multiple graph convolutional networks 4011 respectively extract the road network feature information of the road network data at the corresponding time, and input the obtained road network feature information corresponding to the multiple time periods into the temporal feature extraction network 4012 to obtain road network temporal feature information. The encoding information of the start and end points in the route calculation request is determined from the road network temporal feature information, and the encoding information and environmental information are then input into the multi-task network 402 to obtain travel information including the connection locations and connecting travel modes between the start and end points.

[0066] In some optional implementations of this embodiment, the execution entity may further perform the following operations:

[0067] First, a graph search engine that corresponds to the determined multiple connecting travel modes one by one is used to determine travel routes corresponding to various connecting travel modes based on the starting and ending points and the connecting locations.

[0068] In this implementation, the graph search engine is used to determine the travel route based on the road network data of the corresponding travel mode, including but not limited to a subway network data search engine, a bus network data search engine, a driving network data search engine, a walking network data search engine, and a cycling network data search engine.

[0069] After determining the connection location, the endpoint information of multiple road segments between the starting and ending points in the route calculation request can be determined by combining the starting and ending points. Then, for each road segment, the travel route of the road segment is determined by combining the endpoint and travel mode of the road segment through the corresponding graph search engine.

[0070] In some optional implementations, the above-mentioned execution entity can determine the travel routes corresponding to various connecting travel modes based on the starting and ending points, connecting locations and preset indicators through a graph search engine that corresponds one to one with the determined multiple connecting travel modes.

[0071] Among them, the preset indicators include but are not limited to travel time, cost, distance and other indicators.

[0072] For each road segment under each metric, the execution entity can determine at least one travel route using the travel mode corresponding to that road segment. For example, under the metric of travel time, for the road segment between the starting point and the connecting point, where the travel mode is public transportation, the execution entity can determine the two bus travel routes that take the least time.

[0073] Second, based on the travel routes corresponding to the various connecting travel modes determined, a total travel route is obtained.

[0074] As an example, the above-mentioned execution entity can splice the travel routes corresponding to various connecting travel modes according to the travel order between the starting and ending points to obtain the total travel route.

[0075] When the above-mentioned execution entity determines the travel routes corresponding to various connecting travel modes based on the starting and ending points, connecting locations and preset indicators, the travel routes corresponding to the various connecting travel modes under each preset indicator can be spliced ​​together to obtain the total travel route corresponding to the preset indicator.

[0076] After obtaining the total travel route, the execution entity may display at least one of the obtained total travel routes to the user for selection, and provide navigation to the user based on the selected total travel route.

[0077] In this implementation, after obtaining the connecting location and connecting travel mode, the above-mentioned execution entity determines the travel route of the corresponding road section through the graph search engine corresponding to the connecting travel mode to obtain the total travel route, thereby improving the accuracy of the travel route.

[0078] Continue to refer Figure 5 , shows a schematic process 500 of another embodiment of a method for determining travel information according to the present disclosure, comprising the following steps:

[0079] Step 501: Determine the starting and ending points in the acquired path calculation request.

[0080] Step 502: extract road network feature information of road network data at multiple moments within a time period through multiple graph convolutional networks.

[0081] Step 503: extracting the time series variation information between the road network feature information corresponding to multiple moments within a time period through a time series feature extraction network to obtain the road network time series feature information.

[0082] Step 504: Determine the coding information corresponding to the start and end points from the road network time sequence characteristic information.

[0083] Step 505 : Based on the coding information and the environmental information corresponding to the current moment, the travel information including the connecting location and the connecting travel mode between the starting and ending points is determined through the multi-task network.

[0084] Step 506 : using a graph search engine that corresponds to the determined multiple connecting travel modes, determine travel routes corresponding to the various connecting travel modes based on the starting and ending points and the connecting locations.

[0085] Step 507 : Obtain a total travel route based on the determined travel routes corresponding to the various connecting travel modes.

[0086] It can be seen from this embodiment that Figure 2 Compared with the corresponding embodiments, the process 500 of the method for determining travel information in this embodiment specifically illustrates the process of determining the road network temporal characteristic information, the process of determining travel information, and the process of determining the travel route, thereby improving the accuracy of the determined travel route.

[0087] Continue to refer Figure 6 , shows a schematic process 600 of an embodiment of a method for training a travel information determination model according to the present disclosure, comprising the following steps:

[0088] Step 601: Obtain a training sample set.

[0089] In this embodiment, the execution subject of the training method of the travel information determination model (for example, Figure 1 The terminal device or server in the network can obtain the training sample set remotely or locally based on a wired network connection or a wireless network connection.

[0090] Among them, the training samples in the training sample set include trajectory data containing different travel modes, connection location labels, and connection travel mode labels.

[0091] As an example, the above-mentioned execution entity can collect the user's trajectory data based on the user's mobile device, extract trajectory data that mixes different travel modes, and determine the connection location and connecting travel mode from the trajectory data that mixes different travel modes as labels.

[0092] In step 602, the feature extraction network is used to determine the road network temporal feature information of the road network data at multiple times within the target time period corresponding to the input trajectory data; the coding information corresponding to the start and end points of the input trajectory data is determined from the road network temporal feature information; the coding information is input into the multi-task network, and the connection location label and connection travel mode label corresponding to the input trajectory data are used as the expected output of the multi-task network. The travel information determination model including the feature extraction network and the multi-task network is trained to obtain.

[0093] In this embodiment, the above-mentioned execution entity can determine the road network time series feature information of the road network data at multiple times within the target time period corresponding to the input trajectory data through the feature extraction network; determine the coding information corresponding to the start and end points of the input trajectory data from the road network time series feature information; input the coding information into the multi-task network, and use the connection location label and the connection travel mode label corresponding to the input trajectory data as the expected output of the multi-task network, and train to obtain a travel information determination model including the feature extraction network and the multi-task network.

[0094] Road network data refers to road data for various modes of travel, including but not limited to subway network data, bus network data, driving network data, walking network data, and cycling network data. Due to factors such as road construction, road regulations, and tidal lanes, road network data may change at different times. To determine the impact of changes in network data on travel information, the aforementioned execution entity may extract feature information of road network data at multiple times adjacent to the current time through a feature extraction network, and then extract time-series variation information of the feature information of the road network data at each time, thereby obtaining road network time-series feature information.

[0095] In this embodiment, the feature extraction network can be an encoding network with feature extraction function, including but not limited to a convolutional neural network model, a residual network model, an AlexNet model, and a VGG (Visual Geometry Group Network) model.

[0096] The target time period corresponding to the input trajectory data is the time period to which the trajectory data was generated. The execution entity can divide a day into multiple moments based on a daily cycle (for example, dividing a day into 96 equal moments). The time length corresponding to the preset time period is used as a time window to determine multiple moments adjacent to the current moment. The time length of the time period can be flexibly set. As an example, the time length of the time period is 120 minutes.

[0097] The road network temporal characteristic information includes the coding information of each position in the road network. In this embodiment, the execution entity can determine the coding information of the starting position and the coding information of the end position from the road network temporal characteristic information based on the matching of the position information.

[0098] The encoded information of the start and end points is input into the multi-task network, and the actual connecting location is output through the sub-network responsible for outputting the connecting location in the multi-task network, and the actual connecting travel mode is output through the sub-network responsible for outputting the connecting travel mode; then, a first loss between the actual connecting location and the connecting location label, and a second loss between the actual connecting travel mode and the connecting travel mode label are determined; the total loss is determined based on the first loss and the second loss by adding or weighted summing, and the gradient is determined according to the total loss to update the parameters of the feature extraction network and the multi-task network.

[0099] The above training operation is repeated until a preset termination condition is met, thereby obtaining a trained travel information determination model. The preset termination condition may include, for example, the number of training cycles exceeding a preset number, the training time exceeding a preset time threshold, or the training loss tending to converge. The trained travel information determination model can be used to execute the method of embodiment 200 above.

[0100] In this embodiment, a training method for a travel information determination model is provided. For the road network time series feature information of the road network data at multiple times extracted by the feature extraction network in the travel information determination model, accurate coding information corresponding to the starting point is determined, and then the determined coding information is used as the input of the multi-task network, and the connection position label and connection travel mode label corresponding to the input trajectory data are used as the expected output of the multi-task network to determine the connection position and connection travel mode between the starting and ending points, thereby improving the accuracy of the trained travel information determination model.

[0101] In some optional implementations of this embodiment, the feature extraction network includes multiple graph convolutional networks and a temporal feature extraction network. In this implementation, the execution entity may perform the following method to determine the road network temporal feature information of the road network data at multiple moments within the target time period corresponding to the input trajectory data through the feature extraction network:

[0102] First, multiple graph convolutional networks are used to extract the road network feature information of road network data at multiple times within a time period.

[0103] As an example, multiple graph convolutional networks correspond one-to-one to multiple moments. For each graph convolutional network in the multiple graph convolutional networks, the road network data of the graph convolutional network at the corresponding moment is input into the graph convolutional network to obtain the road network data and road network feature information of the corresponding moment.

[0104] Second, the temporal change information between the road network feature information corresponding to multiple moments is extracted through the temporal feature extraction network to obtain the road network temporal feature information.

[0105] In this implementation, after obtaining the road network feature information of the road network data at multiple time points, the time series change information between the multiple road network feature information is extracted through the time series feature extraction network to obtain the road network time series feature information.

[0106] The temporal feature extraction network may be any network model having a temporal feature extraction function. As an example, the temporal feature extraction network is an LSTM (long-short term memory) model having a GRU (Gated Recurrent Unit) structure.

[0107] In this implementation method, the road network feature information of the road network data at each time is first extracted through multiple graph convolutional networks, and then the road network temporal feature information between the road network feature information corresponding to multiple time periods is extracted through a temporal feature extraction network, thereby improving the accuracy of the obtained road network temporal feature information, and then improving the accuracy of the coding information of the start and end points, thereby improving the accuracy of travel information.

[0108] In some optional implementations of this embodiment, the execution entity may perform the following steps to input the encoded information into the multi-task network, and use the connection location label and the connection travel mode label corresponding to the input trajectory data as the expected output of the multi-task network:

[0109] The encoded information and the environmental information corresponding to the generation time of the input trajectory data are input into the multi-task network, and the connection location label and the connection travel mode label corresponding to the input trajectory data are used as the expected output of the multi-task network.

[0110] The environmental information includes but is not limited to at least one of the following: weather, holidays, city size, preset activities, and seasons.

[0111] In this implementation method, on the basis of considering the starting and ending points, the above-mentioned execution entity also considers the environmental information corresponding to the starting and ending points at the current moment, so as to generate travel information suitable for the current environment under the influence of the environmental information, including the connecting position and connecting travel mode between the starting and ending points.

[0112] In this implementation, the coding information of the starting and ending points and the corresponding environmental information are combined to determine the travel information including the connecting location and connecting travel mode between the starting and ending points, so that the determined travel information is compatible with the environmental information, further improving the accuracy of the determined travel information.

[0113] Continue to refer Figure 7 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a device for determining travel information. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0114] like Figure 7 As shown, the travel information determination device includes: a first determination unit 701, configured to determine the starting and ending points in the obtained route calculation request; an extraction unit 702, configured to determine the road network time series feature information of the road network data at multiple moments within the time period to which the current moment belongs through a pre-trained feature extraction network; an encoding unit 703, configured to determine the encoding information corresponding to the starting and ending points from the road network time series feature information; a second determination unit 704, configured to determine the travel information including the connecting position and connecting travel mode between the starting and ending points through a pre-trained multi-task network based on the encoding information.

[0115] In some optional implementations of this embodiment, the feature extraction network includes multiple graph convolution networks and a temporal feature extraction network, and the extraction unit 702, which is further configured to: extract the road network feature information of the road network data at multiple moments within a time period through multiple graph convolution networks; extract the temporal change information between the road network feature information corresponding to multiple moments within the time period through the temporal feature extraction network to obtain the road network temporal feature information.

[0116] In some optional implementations of this embodiment, the second determination unit 704 is further configured to: determine travel information including the connecting location and connecting travel mode between the starting and ending points through a multi-task network based on the coding information and the environmental information corresponding to the current moment.

[0117] In some optional implementations of this embodiment, the above-mentioned device also includes: a third determination unit (not shown in the figure), which is configured to determine the travel routes corresponding to various connecting travel modes based on the starting and ending points and connecting locations through a graph search engine that corresponds one to one to the multiple connecting travel modes determined; an obtaining unit (not shown in the figure), which is configured to obtain the total travel route based on the travel routes corresponding to the various connecting travel modes determined.

[0118] In this embodiment, a travel information determination device is provided, which determines the accurate coding information corresponding to the starting point from the road network time series feature information of the road network data at multiple times extracted by the feature extraction network in the travel information determination model, and then determines the connection position and connection travel mode between the starting and ending points based on the determined coding information through a multi-task network, thereby improving the accuracy of the obtained travel information and the flexibility of the travel mode.

[0119] Continue to refer Figure 8 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a training device for a travel information determination model. Figure 6 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0120] like Figure 8 As shown, the travel information determination device includes: an acquisition unit 801, which is configured to acquire a training sample set, wherein the training samples in the training sample set include trajectory data and connecting position labels and connecting travel mode labels containing different travel modes; a training unit 802, which is configured to determine the road network time series feature information of the road network data at multiple moments within the target time period corresponding to the input trajectory data through a feature extraction network; determine the coding information corresponding to the start and end points of the input trajectory data from the road network time series feature information; input the coding information into the multi-task network, and use the connecting position label and connecting travel mode label corresponding to the input trajectory data as the expected output of the multi-task network, and train to obtain a travel information determination model including the feature extraction network and the multi-task network.

[0121] In some optional implementations of this embodiment, the feature extraction network includes multiple graph convolution networks and a temporal feature extraction network; and the training unit 802 is further configured to: extract road network feature information of road network data at multiple moments within a time period through multiple graph convolution networks; extract temporal change information between the road network feature information corresponding to multiple moments through the temporal feature extraction network to obtain road network temporal feature information.

[0122] In some optional implementations of this embodiment, the training unit 802 is further configured to: input the encoded information and the environmental information corresponding to the generation time of the input trajectory data into the multi-task network, and use the connection location label and the connection travel mode label corresponding to the input trajectory data as the expected output of the multi-task network.

[0123] In this embodiment, a training device for a travel information determination model is provided. For the road network time series feature information of the road network data at multiple times extracted by the feature extraction network in the travel information determination model, accurate coding information corresponding to the starting point is determined, and then the determined coding information is used as the input of the multi-task network. The connection position label and the connection travel mode label corresponding to the input trajectory data are used as the expected output of the multi-task network to determine the connection position and the connection travel mode between the starting and ending points, thereby improving the accuracy of the trained travel information determination model.

[0124] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, which includes: at least one processor; and 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, and the instructions are executed by the at least one processor so that when the at least one processor executes, it can implement the travel information determination method and the travel information determination model training method described in any of the above embodiments.

[0125] According to an embodiment of the present disclosure, the present disclosure also provides a readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to implement the travel information determination method and travel information determination model training method described in any of the above embodiments when executed.

[0126] The embodiments of the present disclosure provide a computer program product, which, when executed by a processor, can implement the method for determining travel information and the method for training a travel information determination model described in any of the above embodiments.

[0127] Figure 9 A schematic block diagram of an example electronic device 900 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 can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0128] like Figure 9 As shown, the device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. Various programs and data required for the operation of the device 900 can also be stored in the RAM 903. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0129] Various components in the device 900 are connected to the I / O interface 905, including an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a magnetic disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0130] The computing unit 901 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 901 performs the various methods and processes described above, such as the method for determining travel information. For example, in some embodiments, the method for determining travel information can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the method for determining travel information described above can be performed. Alternatively, in other embodiments, the computing unit 901 can be configured to perform the method for determining travel information by any other appropriate means (e.g., via firmware).

[0131] Various embodiments of the systems and techniques described 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), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0132] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0133] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0134] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the 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 acoustic input, voice input, or tactile input).

[0135] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0136] A computer system may include a client and a server. The client and server are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, establishing a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within a cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosts and virtual private servers (VPS). It may also be a server in a distributed system or a server integrated with blockchain.

[0137] According to the technical solution of the embodiment of the present disclosure, a method for determining travel information is provided, in which the road network time series feature information of the road network data at multiple moments extracted by the feature extraction network in the travel information determination model is used to determine the accurate coding information corresponding to the starting point, and then the connecting position and connecting travel mode between the starting and ending points are determined based on the determined coding information through a multi-task network, thereby improving the accuracy of the obtained travel information and the flexibility of the travel mode.

[0138] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions provided by this disclosure can be achieved. This is not a limitation herein.

[0139] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for determining travel information, comprising: Determine the starting and ending points in the obtained path calculation request; Extracting road network feature information of road network data at multiple moments within a time period to which the current moment belongs, using multiple graph convolutional networks in a pre-trained feature extraction network, wherein the road network data includes at least one of the following: subway network data, bus network data, driving network data, walking network data, and cycling network data; extracting time series change information between the road network feature information corresponding to the multiple moments within the time period, using a time series feature extraction network in the feature extraction network, to obtain road network time series feature information; Determining coding information corresponding to the starting and ending points from the road network time sequence characteristic information; Based on the encoded information and the environmental information corresponding to the current moment, travel information including the connecting location and connecting travel mode between the starting and ending points that is adapted to the environmental information is determined through a pre-trained multi-task network, where the environmental information includes at least one of the following: weather, holidays, city size, preset activities, and season.

2. The method according to claim 1, wherein Also includes: Determining travel routes corresponding to the various connecting travel modes based on the starting and ending points and the connecting locations through a graph search engine corresponding to the multiple connecting travel modes; Based on the travel routes corresponding to the various determined connecting travel modes, a total travel route is obtained.

3. A method for training a travel information determination model, comprising: Obtaining a training sample set, wherein the training samples in the training sample set include trajectory data of different travel modes and connection location labels and connection travel mode labels; Road network feature information of road network data at multiple moments within a time period to which the current moment belongs is extracted through multiple graph convolutional networks in the feature extraction network, wherein the road network data includes at least one of the following: subway network data, bus network data, driving network data, walking network data, and cycling network data; time series change information between road network feature information corresponding to multiple moments within the time period is extracted through a time series feature extraction network in the feature extraction network to obtain road network time series feature information; coding information corresponding to the start and end points of the input trajectory data is determined from the road network time series feature information; the coding information and environmental information corresponding to the generation moment of the input trajectory data are input into a multi-task network, and the connection location label and the connection travel mode label corresponding to the input trajectory data and adapted to the environmental information are used as the expected output of the multi-task network, and a travel information determination model including the feature extraction network and the multi-task network is trained, wherein the environmental information includes at least one of the following: weather, holidays, city size, preset activities, and season.

4. A device for determining travel information, comprising: A first determining unit is configured to determine the start and end points in the acquired path calculation request; The extraction unit is configured to respectively extract road network feature information of road network data at multiple moments within a time period to which a current moment belongs through multiple graph convolutional networks in a pre-trained feature extraction network, wherein the road network data includes at least one of the following: subway network data, bus network data, driving network data, walking network data, and cycling network data; and extract time series change information between the road network feature information corresponding to the multiple moments within the time period through a time series feature extraction network in the feature extraction network to obtain road network time series feature information; an encoding unit configured to determine encoding information corresponding to the start and end points from the road network temporal characteristic information; The second determination unit is configured to determine, based on the encoded information and the environmental information corresponding to the current moment, travel information including the connecting location and connecting travel mode between the starting and ending points that is adapted to the environmental information through a pre-trained multi-task network, wherein the environmental information includes at least one of the following: weather, holidays, city size, preset activities, and season.

5. The device according to claim 4, wherein Also includes: a third determining unit configured to determine travel routes corresponding to the various connecting travel modes based on the starting and ending points and the connecting locations through a graph search engine that corresponds to the determined multiple connecting travel modes one by one; The obtaining unit is configured to obtain a total travel route based on the determined travel routes corresponding to the various connecting travel modes.

6. A training device for a travel information determination model, comprising: An acquisition unit is configured to acquire a training sample set, wherein the training samples in the training sample set include trajectory data of different travel modes and connection location labels and connection travel mode labels; The training unit is configured to extract road network feature information of road network data at multiple moments within the time period to which the current moment belongs through multiple graph convolutional networks in the feature extraction network, wherein the road network data includes at least one of the following: subway network data, bus network data, driving network data, walking network data, and cycling network data; extract the time series change information between the road network feature information corresponding to multiple moments within the time period through the time series feature extraction network in the feature extraction network to obtain road network time series feature information; determine the coding information corresponding to the start and end points of the input trajectory data from the road network time series feature information; input the coding information and the environmental information corresponding to the generation time of the input trajectory data into the multi-task network, and use the connection location label and the connection travel mode label corresponding to the input trajectory data and adapted to the environmental information as the expected output of the multi-task network, and train to obtain a travel information determination model including the feature extraction network and the multi-task network, wherein the environmental information includes at least one of the following: weather, holidays, city size, preset activities, and season.

7. An electronic device, characterized in that: include: 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, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 3.

8. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 3.

9. A computer program product comprising: A computer program which, when executed by a processor, implements the method according to any one of claims 1 to 3.

Images