CN111813881B

CN111813881B - Method, apparatus, device and storage medium for journey information processing

Info

Publication number: CN111813881B
Application number: CN202010524350.3A
Authority: CN
Inventors: 傅昆; 王征
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2020-06-10
Filing date: 2020-06-10
Publication date: 2024-09-27
Anticipated expiration: 2040-06-10
Also published as: CN111813881A

Abstract

According to embodiments of the present disclosure, a method, apparatus, device, and storage medium for travel information processing are provided. The method proposed herein comprises: determining a plurality of road segments associated with the trip; determining a position code for a plurality of road segments, one position code indicating an order in which a respective one of the plurality of road segments is traversed in a journey; and determining an estimated time consumption of the journey based on traffic attributes and position codes for the plurality of road segments, the traffic attributes being indicative of at least a current traffic state for the plurality of road segments. According to the facts of the present disclosure, the estimated time consumption of the trip can be determined more accurately.

Description

Method, apparatus, device and storage medium for journey information processing

Technical Field

Implementations of the present disclosure relate to the field of intelligent transportation, and more particularly, to a method, apparatus, and computer storage medium for travel information processing.

Background

In the field of electronic maps and navigation, the time taken for a moving body (vehicle or pedestrian, etc.) from a start point to an end point is a very important technical indicator describing the relevant time penalty for travel. In the field of intelligent transportation, this is also referred to as determination of the Estimated Time of Arrival (ETA), ESTIMATED TIME of Arrival.

In the smart travel scenario, each particular trip will correspond to a particular path from the start point to the end point. The route may be a route for the driver to get on the passenger, or a route for the driver to get to the passenger destination after receiving the passenger. The estimated time consumption of a trip can be used for various aspects of intelligent transportation. For example, the estimated time consumption may be used to estimate the travel remaining time, to estimate the time to end, to estimate the cost of travel, or to schedule a vehicle, etc. Thus, how to more accurately determine the estimated time consumption of a trip is known as the current focus of attention.

Disclosure of Invention

Embodiments of the present disclosure provide a solution for journey information processing.

In a first aspect of the present disclosure, a method for trip information processing is provided. The method comprises the following steps: determining a plurality of road segments associated with the trip; determining a position code for a plurality of road segments, one position code indicating an order in which a respective one of the plurality of road segments is traversed in a journey; and determining an estimated time consumption of the journey based on traffic attributes and position codes for the plurality of road segments, the traffic attributes being indicative of at least a current traffic state for the plurality of road segments.

In a second aspect of the present disclosure, an apparatus for trip information processing is provided. The device comprises: a link determination module configured to determine a plurality of links associated with the journey; a position code determination module configured to determine a position code for a plurality of road segments, one position code indicating an order in which a respective one of the plurality of road segments is passed in a journey; and a time-consuming determination module configured to determine an estimated time consumption of the journey based on traffic attributes and position codes for the plurality of road segments, the traffic attributes being indicative of at least a current traffic state for the plurality of road segments.

In a third aspect of the present disclosure, there is provided an electronic device comprising: a memory and a processor; wherein the memory is for storing one or more computer instructions, wherein the one or more computer instructions are executable by the processor to implement a method according to the first aspect of the present disclosure.

In a fourth aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon one or more computer instructions, wherein the one or more computer instructions are executed by a processor to implement a method according to the first aspect of the present disclosure.

According to various embodiments of the present disclosure, the estimated time consumption of a trip may be more accurately determined, thereby providing a more accurate reference for participants (e.g., drivers or passengers) of the trip.

Drawings

The above and other features, advantages and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, wherein like or similar reference numerals designate like or similar elements, and wherein:

FIG. 1 illustrates a schematic diagram of an example environment in which various embodiments of the present disclosure may be implemented;

FIG. 2 illustrates a schematic diagram of determining the expected time consumption of different strokes according to some embodiments of the present disclosure;

FIG. 3 illustrates a flowchart of an example trip information processing method, according to some embodiments of the present disclosure;

FIG. 4 illustrates a flowchart of an example method of determining feature vectors with position-coding information, according to some embodiments of the present disclosure;

FIG. 5 illustrates a schematic diagram of determining estimated time consumption using a model in accordance with some embodiments of the present disclosure;

FIG. 6 illustrates a schematic block diagram of an apparatus for information processing according to some embodiments of the present disclosure; and

FIG. 7 illustrates a block diagram of a computing device capable of implementing various embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

In describing embodiments of the present disclosure, the term "comprising" and its like should be taken to be open-ended, i.e., including, but not limited to. The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first," "second," and the like, may refer to different or the same object. Other explicit and implicit definitions are also possible below.

Referring first to FIG. 1, a schematic diagram of an environment 100 in which an application according to an exemplary implementation of the present disclosure may be used is schematically shown.

Applications that enable a user to call a vehicle service online are known and may be referred to as "call software" or "call applications". As shown in fig. 1, environment 100 includes a terminal device 160 configured to present user interface 110 as shown in fig. 1. At the user interface 110, a user (e.g., a driver or passenger) may be presented with a start point 120, an end point 130, and a path 140 from the start point 120 to the end point 130 of the trip.

The terminal device 160 may, for example, obtain the estimated time consumption of the trip. It should be appreciated that end device 160 may determine the estimated time consumption based on start point 120, end point 130, and travel route 140 of the start trip. Alternatively, the terminal device 160 may provide information about the formation to the server 170, and the estimated time consumption is determined by the server 170 and sent from the server 170 to the terminal device 160.

After the estimated time of the trip is obtained, the terminal 160 may provide additional information to the user to allow the user to better understand the status of the trip. For example, the terminal device 160 may present the alert information 150-1 regarding the predicted arrival time ETA so that the user can intuitively understand the predicted end time of the trip. In one specific example scenario, a passenger has reserved a vehicle for a particular trip, for example. At this point, prompt 150-1 may be used to prompt the passenger that the estimated time of arrival for the trip is 15:00.

In another example, the terminal device 160 may also present, for example, a reminder 150-2 regarding the projected time consumption of the trip so that the user can intuitively learn the time that the trip is projected to require. In one specific example scenario, a user (e.g., driver) may specify a start point (e.g., start point 120) and an end point (e.g., end point 130) of a trip through terminal device 160. At this point, the reminder message 150-2 can be used to remind the passenger that the estimated time taken for the journey from the start 120 to the end 130 is 30 minutes.

In yet another example, the terminal device 160 may also present a prompt 150-3 regarding the estimated price of the trip, for example, so that the user can intuitively learn what is expected to be the cost of the trip. It should be appreciated that the spending information may be calculated by the terminal device 160 or the server 170 based on the estimated time consumption of the trip. In one particular example scenario, a user (e.g., a passenger) may reserve a trip from a specified origin 120 to a specified destination 130 using a terminal device 160. At this point, prompt 150-3 may be used to prompt the passenger that the projected cost of the journey is XX.

In yet another example, the terminal device 160 may also present a prompt 150-4 for the remaining time of the trip, for example, so that the user can intuitively learn the projected remaining time of the trip in progress. In one specific example scenario, a user (e.g., driver) has already begun a particular trip to the endpoint 130. At this time, the terminal device 160 or the server 170 may, for example, acquire a real-time position of the user and update the estimated time consumption of the trip according to the real-time position as a new starting point (e.g., the starting point 120). The reminder 150-4 may be updated in real-time or periodically to present the user with the projected remaining time of the trip.

In one known class of schemes, machine learning models (e.g., GBDT (Gradient Based Decision Tree), FM (Factorization Machine), RNN (Recurrent Neural Network), etc.) may be utilized to estimate the estimated time consumption of a trip. For example, after a path 140 from a start point 120 to an end point 130 is acquired using a path planning service, known schemes may divide the path 140 into a plurality of end-to-end segments (also referred to as links). A road segment may refer to a path having a relatively short length and having a direction. According to some known schemes, the path planning service may directly generate a plurality of road segments from a start point and an end point to indicate a path from the start point to the end point.

The input of the machine learning model may include, for example, a path 140 and other personalized information (driver ID, weather, day of week, month, etc.), where the path may include a plurality of road segments, each of which may include corresponding traffic attributes such as congestion status, speed limit, number of lanes, whether to charge, etc. According to known approaches, the machine learning model may utilize traffic attributes of road segments and other personalized information (e.g., driver information, passenger information, weather information, etc., that is not related to the road segments) to determine the projected time consumption of the journey.

However, in such a machine learning model, traffic attributes of the road segments input into the machine learning model include both static attributes (e.g., number of lanes) of the road segments and dynamic attributes (e.g., congestion conditions) of the road segments. In some known solutions, the dynamic properties of the road segments will not change in a very short time (e.g. in 2 minutes). In other words, during the processing of the machine learning model, the dynamic properties of such road segments will always be converted into the same feature vectors for estimating the estimated time consumption. However, such a manner of processing is not reasonable.

FIG. 2 illustrates a schematic diagram 200 of determining predicted time consumption for different strokes according to some embodiments of the present disclosure. As shown in fig. 2, the machine learning model needs to estimate the estimated time consumption of two strokes at the same time, one of which (hereinafter, referred to as a first stroke for convenience of description) has a start point 120 and an end point 130, and the other of which (hereinafter, referred to as a second stroke for convenience of description) has a start point 210 and an end point 220. As shown in fig. 2, both the first trip and the second trip need to travel through the road segment 220 from the location 230 to the location 130 (i.e., the end 130 of the first trip).

According to known schemes, the traffic attributes of the road segments 220 will be converted into the same feature vector for determining the estimated time consumption of two different trips. However, the role played by the road segment 220 on two different trips is actually different. For the first trip, the road segment 220 is at the rear of the trip, and the traffic condition of the road segment 220 may vary greatly when the user actually travels through the road segment 220. In contrast, for the second journey, the road segment 220 is the middle-front segment of the journey, and the user may, for example, quickly pass the road segment 220, at which time the traffic conditions of the road segment 220, for example, will not change significantly. Thus, the same road segment 220 should have different impact on the estimated time of different trips. However, known solutions do not effectively distinguish between the above situations, which results in some situations where the estimated time consumption of the journey will be inaccurate.

According to various embodiments of the present disclosure, a solution for journey information processing is provided. In embodiments of the present disclosure, a plurality of road segments associated with a journey may be determined by a path planning service. The system may then determine a position code for the plurality of road segments, wherein the position code indicates an order in which a respective one of the plurality of road segments was traversed during the journey. For example, when a link is the first link to be traversed in a journey, its position code may be determined to be 1, for example. The system may then determine the estimated time consumption of the journey based on the traffic attributes and location codes for the plurality of road segments. Based on this approach, by introducing position coding, embodiments of the present disclosure can distinguish the effect of the same road segment on different trips, thereby more accurately determining the estimated time consumption of a trip.

Fig. 3 illustrates a flowchart of an example method 300 of travel information processing according to some embodiments of the present disclosure. The method 300 may be implemented, for example, at the terminal device 160 and/or the server 170 of fig. 1. For ease of description, the method 300 is described below with the server 170 as an example.

At block 302, the server 170 determines a plurality of road segments associated with the journey. In some embodiments, server 170 may determine a plurality of road segments associated with the journey based on, for example, the journey information received from terminal device 160.

In some embodiments, the user may reserve a trip with the terminal device 160. Specifically, the user can designate the start point 120, the end point 130, the start time of the trip, and the like of the reserved trip through the terminal device 160. The terminal device 160 may, for example, transmit trip information including the start 120, intermediate stops, and/or end 130 points specified by the user (e.g., passenger) to the server 170. In some embodiments, the trip information may also include, for example, time information for the trip, e.g., with a specified trip start time, etc. Further, the server 170 may process the journey information using the route generation service to determine a plurality of road segments corresponding to the journey.

In other embodiments, for an ongoing trip (e.g., after the driver receives the passenger and begins the trip), the terminal device 160 may, for example, periodically send a current location including the user (e.g., the passenger) to the server 170. The server 170 may determine a plurality of road segments associated with the journey in progress based on the current location (to be a new starting point) and previous journey information (e.g., end point of journey and travel route), for example.

In some embodiments, server 170 may determine a corresponding plurality of road segments from route 140 from start point 120 to end point 130. For example, route 140 (TR) may be represented as m positions:

TR＝[W₁,W₂,…,W_i…,W_m],(1≤i≤m) (1)

Where TR denotes a route, m denotes the number of positions included in the route TR, W _i denotes geographical information of position i in the route TR, the arrangement order of the m positions corresponds to the direction of the route TR, and the geographical information of position i may include longitude-latitude coordinates of position i.

Based on the locations included in the route 140, the server 170 may determine a plurality of road segments by, for example, looking up a pre-stored road segment table. In this way, route 140 may be represented, for example, as a sequence of multiple road segments:

At block 304, the server 170 determines a position code for the plurality of road segments, wherein the position code indicates an order in which a respective one of the plurality of road segments was traversed during the journey. It should be appreciated that the position code may characterize the position of a road segment in a sequence of road segments. Taking the formula (2) as an example, The position code of (c) may be determined to be 1,May be determined as i. It should be understood that the above specific position-coded values are illustrative only, and that other values capable of indicating an order may be employed as position codes.

For the first journey from the start point 120 to the end point 130 shown in fig. 2, it comprises, for example, 6 road segments. The start and end points (except for start point 120 and end point 130) of each road segment are shown in fig. 2 by open dots. In this trip, the server 170 may determine, for example, that the position code of the road segment 220 is 6, which indicates that the road segment 220 is the 6 th passed road segment in the first trip. For the second journey from the start point 210 to the end point 220 in fig. 2, it comprises, for example, 4 road segments. The position of the road segment 220 in the second trip is encoded with 3, indicating that the road segment 220 is the 3 rd passed road segment in the second trip.

At block 306, the server 170 determines an estimated time consumption of the journey based on traffic attributes and location codes for the plurality of road segments, the weighted traffic attributes indicating at least the current traffic status for the plurality of road segments. In some embodiments, the server 170 may determine the estimated time consumption by comprehensively considering both traffic attributes and location codes of the road segments. For example, the server 170 may use a combination of both the location codes and the traffic attributes as inputs to a machine learning model to determine the estimated time consumption of the journey.

In some embodiments, the server 170 may adjust feature vectors corresponding to traffic attributes based on the position codes to generate feature vectors with position code information as input to the machine learning model. Specifically, the server 170 may generate feature vectors with location-encoded information based on traffic attributes and location codes for a plurality of road segments.

A specific procedure of generating the feature vector with the position-coding information will be described below with reference to fig. 4 and 5. Fig. 4 illustrates a flowchart of an example method 400 of determining a position-encoded feature vector, according to some embodiments of the present disclosure.

As shown in fig. 4, at block 402, the server 170 may generate an initial feature vector based on traffic attributes. In some embodiments, the server 170 may obtain traffic attributes corresponding to road segments, for example, by querying a pre-stored road segment table. In some embodiments, traffic attributes may include static attributes and dynamic attributes. Static properties may refer to factors that are less time-dependent, with less impact on ETA. Static features may include, but are not limited to, length of road segments, number of lanes, speed limits, road level, road tolls, etc., or any combination thereof. Dynamic properties may refer to factors that change over time, with greater impact on ETA. The dynamic attributes may include, but are not limited to, current time, congestion level, traffic light latency of intersections included in the road segments, and the like, or any combination thereof.

In some embodiments, server 170 may utilize a time-consuming predictive model, for example, to generate an initial feature vector. FIG. 5 illustrates a schematic diagram 500 of determining predicted time consumption using a model in accordance with an embodiment of the present disclosure. As shown in FIG. 5, the time-consuming predictive model 520 may receive the traffic attributes 510 and process the traffic attributes 510 with the input layer 530 to generate an initial feature vector 535 having N dimensions, where each dimension feature may be represented as a feature 535-1, 535-2, …, 535-N.

With continued reference to fig. 4, at block 404, the server 170 may determine weight coefficients associated with different dimensions of the initial feature vector based on the position encoding. As shown in fig. 5, the time-consuming prediction model 520 may include a weighting layer 540 configured to encode 515 based on the received position and determine a weight coefficient for each dimension in the initial feature vector 535.

In some embodiments, the server 170 may represent the weight coefficients as a function of position encoding and dimensions. In particular, the server 170 may determine a plurality of periodic functions corresponding to different dimensions, and the plurality of periodic functions have different periods with respect to the variables (position codes). Illustratively, the periodic function may be a trigonometric function, including a sine function, a cosine function, and the like. As a specific example, the periodic function may be expressed, for example, as:

where pos represents the position code of the road segment, D represents the dimension in the initial feature vector, and D represents the total number of dimensions in the initial feature vector.

For example, in the example of fig. 5, if the total number of dimensions n=2 of the initial feature vector 535, the periodic function corresponding to the first dimension feature 535-1 may be expressed, for example, as:

the periodic function corresponding to the second dimension feature 535-2 may be expressed, for example, as:

It can be seen that the two periodic functions determined based on this approach have different periods of the relative variable pos. The period of the periodic function (4) is relatively small, which means that the weight of the first dimension feature 535-1 varies to a large extent with position-encoded pos. In contrast, the period of the periodic function (5) is relatively large, which means that the weight of the first dimension feature 535-1 varies less with position-encoded pos.

The server 170 may then determine the weight coefficients based on the position encoding and the periodic function. In connection with the example of fig. 2, in the case where the traffic information of the road segment 220 is utilized to determine the estimated time consumption of the first journey, the position code of the road segment 220 will be determined to be 6. At this time, the weight coefficient corresponding to the first dimension feature 535-1 may be determined as cos (6/100), and the weight coefficient corresponding to the second dimension feature 535-2 may be determined as cos (6/1000).

At block 406, the server 170 may apply the weight coefficients to the initial feature vector to obtain a feature vector with position-coding information. As shown in fig. 5, the time-consuming prediction model 520 may weight the corresponding dimensions in the initial feature vector 535 with the determined weight coefficients by weighting 540.

For example, the first dimension feature 535-1 of the initial feature vector would be multiplied by a corresponding weight coefficient (e.g., cos (6/100)) to obtain a corresponding weighted feature 545-1. Accordingly, the second dimension feature 535-2 of the initial feature vector will be multiplied by the corresponding weight coefficient (e.g., cos (6/100)) to obtain the corresponding weighted feature 545-2. That is, the initial feature vector 535 is converted to a feature vector 545 with position-coding information, each of which is represented as a feature 545-1, 545-2, …, 545-N, respectively. It should be understood that the above specific periodic functional forms, parameter values, are illustrative only and are not intended to be limiting of the present disclosure.

It should be appreciated that the above weighted procedure can also be expressed as equation (6):

Where x represents the initial feature vector 535, PE represents a mask vector (e.g., [ cos (6/100), cos (6/100) ]) consisting of weights corresponding to different dimensions, Representing feature vectors 545 with position-coding information.

By setting different periodic functions for position coding for features of different dimensions, feature vectors 545 with position coding information can be obtained. In this way, the time-consuming prediction model 520 may further divide the initial feature vector 535 into an intermediate feature representation that is more affected by position-encoded pos and an intermediate feature representation that is less affected by pos.

Compared with the direct input of taking the position code as the model, the scheme further considers the relevance of the position code and the specific characteristics in the traffic attribute, and the attribute of the input is divided into an intermediate characteristic representation with larger influence of the received position code and an intermediate characteristic representation with smaller influence of the position code in the characteristic processing stage. For example, position coding may have more impact on the dynamic properties of the road segment, while having no or only a minor impact on the static properties. In this way, embodiments of the present disclosure may construct more accurate feature vectors, thereby improving the accuracy of the time-consuming predictive model.

Further, server 170 may process the feature vectors with the position-coding information using a time-consuming prediction model to determine the predicted time consumption. With continued reference to the example of fig. 5, the feature vector 545 with the position-coding information may be provided, for example, to an intermediate processing layer 550 of the time-consuming prediction model 520 and output the predicted time-consuming 570 via an output layer 560.

The time-consuming predictive model 520 is shown in fig. 5 as a deep neural network. Deep neural networks have a hierarchical architecture, with each processing layer (also referred to as a network layer) having one or more processing units (also referred to as processing nodes, neurons, or filters) that process inputs based on corresponding parameters. In deep neural networks, the output of the previous layer after processing is the input of the next layer, where the first layer in the architecture receives the network input for processing and the output of the last layer is provided as the network output. The parameters used by all processing unit processes of the time-consuming predictive model 520 constitute a set of parameters of the time-consuming predictive model 520. The specific values of such parameter sets need to be determined by a training process.

It should be understood that the architecture of the time-consuming predictive model 520 shown in FIG. 5 and the number of processing layers and processing units therein are illustrative and not limiting. The time consuming predictive model 520 may be designed with other suitable architecture and/or suitable number of processing layers, each of which may have a suitable number of processing units, as desired.

In some embodiments, the time-consuming predictive model 520 may be trained based on historical travel, for example. Specifically, the time-consuming prediction model 520 may obtain traffic attributes of a plurality of road segments corresponding to a set of historical trips, and position-coding information corresponding to the plurality of road segments. During the training process, the parameter values of the time-consuming predictive model 520 may be adjusted to achieve a convergence condition. The convergence condition may be, for example, such that the predicted time consumption of the historical trip by the time-consuming predictive model 520 is close to the corresponding actual time consumption.

Based on the determination of estimated time consumption discussed above, embodiments of the present disclosure are able to consider not only the traffic properties of the road segment itself, but also the location of the road segment in the journey (which is represented, for example, as a location code). Based on the mode, the embodiment of the disclosure can effectively distinguish the feature vectors corresponding to the same road section in different strokes, so that the accuracy of time consumption prediction is improved.

In some embodiments, server 170 may also determine an estimated time of arrival for the trip based on the estimated time consumption and send the estimated time of arrival to terminal device 160 associated with the trip. For example, in some scenarios discussed with reference to fig. 1, the user may be more interested in the estimated time of arrival ETA, at which time the server 170 may determine the estimated time of arrival based on the current time and the estimated time consumption and send that time to the terminal device 160 for presentation.

In some embodiments, the estimated time of arrival determined by the server 170 may be used, for example, for scheduling of vehicles in a transit trip platform, in addition to the scenarios discussed with reference to fig. 1. In scheduling vehicles for multiple users within an area, the user is typically not simply scheduled for their nearest vehicle, but rather, for example, is selected in a manner that minimizes the total projected time required for the multiple vehicles to the corresponding passengers. It should be appreciated that the estimated time of day or the estimated time of arrival ETA of a trip is an important indicator in intelligent transportation travel, which may also be used in any other suitable aspect. By increasing the accuracy of the estimated time of consumption, embodiments of the present disclosure may, for example, increase the scheduling efficiency of the vehicle, help the user (passenger or driver) schedule more reasonably, and so forth.

It should be appreciated that while the expected time-consuming determination method implemented in accordance with the present disclosure is discussed above with reference to server 170, the above method may also be performed by terminal device 160 utilizing local resources and/or remote resources (e.g., a road segment table maintained by the server). The description is not repeated here.

Embodiments of the present disclosure also provide corresponding apparatus for implementing the above-described methods or processes. Fig. 6 illustrates a schematic block diagram of an apparatus 600 for trip management in accordance with some embodiments of the present disclosure.

As shown in fig. 6, the apparatus 600 may include a segment determination module 610 configured to determine a plurality of segments associated with a trip. The apparatus 600 further comprises a position code determination module 620 configured to determine a position code of a plurality of road segments, one position code indicating an order in which a respective one of the plurality of road segments is traversed in the journey. The apparatus 600 further comprises a time-consuming determination module 630 configured to determine an estimated time-consuming of the journey based on traffic attributes and position codes for the plurality of road segments, the traffic attributes being indicative of at least a current traffic status of the plurality of road segments.

In some embodiments, the time consuming determination module 630 comprises: a feature vector generation module configured to generate a feature vector with position coding information based on traffic attributes and position codes of a plurality of road segments; and a time-consuming prediction module configured to determine an estimated time consumption based on the feature vector with the position-coding information.

In some embodiments, the feature vector generation module comprises: an initial feature vector determination module configured to generate an initial feature vector based on the traffic attribute; a weight coefficient determination module configured to determine weight coefficients associated with different dimensions of the initial feature vector based on the position encoding; and a weighting module configured to apply the weighting coefficients to the initial feature vector to obtain a feature vector with position-coding information.

In some embodiments, the weight coefficient determination module comprises: a periodic function determination module configured to determine periodic functions having different periods corresponding to different dimensions; and a weight coefficient calculation module configured to determine a weight coefficient based on the position code and the periodic function.

In some embodiments, the time-consuming prediction module comprises: a model processing module configured to process the feature vector with the position-coding information using a time-consuming prediction model to determine an estimated time consumption, wherein the time-consuming prediction model is trained based on road segment information corresponding to a set of historical trips and actual time-consuming information.

In some embodiments, the apparatus 600 further comprises: a predicted arrival time determination module configured to determine a predicted arrival time of the trip based on the predicted time consumption; and a transmission module configured to transmit the estimated time of arrival to a terminal device associated with the trip.

Fig. 7 illustrates a block diagram of a computing device/server 700 in which one or more embodiments of the disclosure may be implemented. It should be understood that the computing device/server 700 illustrated in fig. 7 is merely exemplary and should not be taken as limiting the functionality and scope of the embodiments described herein.

As shown in fig. 7, computing device/server 700 is in the form of a general purpose computing device. Components of computing device/server 700 may include, but are not limited to, one or more processors or processing units 710, memory 720, storage 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. The processing unit 710 may be an actual or virtual processor and is capable of performing various processes according to programs stored in the memory 720. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to increase the parallel processing capabilities of computing device/server 700.

Computing device/server 700 typically includes a number of computer storage media. Such media may be any available media that is accessible by computing device/server 700 and includes, but is not limited to, volatile and non-volatile media, removable and non-removable media. The memory 720 may be volatile memory (e.g., registers, cache, random Access Memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 730 may be a removable or non-removable media and may include machine-readable media such as flash drives, magnetic disks, or any other media that may be capable of storing information and/or data (e.g., training data for training) and may be accessed within computing device/server 700.

Computing device/server 700 may further include additional removable/non-removable, volatile/nonvolatile storage media. Although not shown in fig. 7, a magnetic disk drive for reading from or writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data medium interfaces. Memory 720 may include a computer program product 725 having one or more program modules configured to perform the various methods or acts of the various embodiments of the disclosure.

Communication unit 740 enables communication with other computing devices via a communication medium. Additionally, the functionality of the components of computing device/server 700 may be implemented in a single computing cluster or in multiple computing machines capable of communicating over a communication connection. Accordingly, computing device/server 700 may operate in a networked environment using logical connections to one or more other servers, a network Personal Computer (PC), or another network node.

The input device 750 may be one or more input devices such as a mouse, keyboard, trackball, etc. The output device 760 may be one or more output devices such as a display, speakers, printer, etc. Computing device/server 700 may also communicate with one or more external devices (not shown), such as storage devices, display devices, etc., as needed through communication unit 740, with one or more devices that enable users to interact with computing device/server 700, or with any device (e.g., network card, modem, etc.) that enables computing device/server 700 to communicate with one or more other computing devices. Such communication may be performed via an input/output (I/O) interface (not shown).

According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which one or more computer instructions are stored, wherein the one or more computer instructions are executed by a processor to implement the method described above.

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer readable program instructions may be provided to a processing unit of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various implementations of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The foregoing description of implementations of the present disclosure has been provided for illustrative purposes, is not exhaustive, and is not limited to the implementations disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various implementations described. The terminology used herein was chosen in order to best explain the principles of each implementation, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand each implementation disclosed herein.

Claims

1. A method of travel information processing, comprising:

Determining a plurality of road segments associated with the trip; the plurality of road segments have different effects on the estimated time consumption of different of the trips;

Determining a position code for the plurality of road segments, one position code indicating an order in which a respective one of the plurality of road segments was traversed in the trip;

generating an initial feature vector based on traffic attributes of the plurality of road segments;

determining periodic functions with different periods corresponding to different dimensions through a weighting layer of the time-consuming prediction model; and determining weight coefficients associated with the different dimensions of the initial feature vector based on the position encoding and the periodic function;

Applying the weight coefficients to the initial feature vector to obtain a feature vector with position coding information; based on the feature vector with position-coding information, the estimated time consumption of the journey is determined, the traffic attribute being indicative of at least current traffic conditions for the plurality of road segments.

2. The method of claim 1, wherein determining the estimated time consumption comprises:

processing the feature vector with position-coding information using the time-consuming predictive model to determine the predicted time consumption,

Wherein the time-consuming predictive model is trained based on road segment information corresponding to a set of historical trips and actual time-consuming information.

3. The method of claim 1, further comprising:

determining an estimated time of arrival for the trip based on the estimated time consumption; and

The estimated time of arrival is sent to a terminal device associated with the trip.

4. An apparatus for travel information processing, comprising:

A link determination module configured to determine a plurality of links associated with the journey; the plurality of road segments have different effects on the estimated time consumption of different of the trips;

a position code determination module configured to determine a position code of the plurality of road segments, one position code indicating an order in which a respective one of the plurality of road segments is passed in the trip;

an initial feature vector determination module configured to generate an initial feature vector based on traffic attributes of the plurality of road segments;

A weight coefficient determination module including a periodic function determination module and a weight coefficient calculation module configured to determine periodic functions having different periods corresponding to different dimensions by the periodic function determination module, and determine the weight coefficient based on the position code and the periodic functions by the weight coefficient calculation module, using a weighting layer of a time-consuming prediction model;

A weighting module configured to apply the weight coefficients to the initial feature vector to obtain a feature vector with position-coding information; and

A time-consuming prediction module configured to determine the estimated time consumption of the journey based on the feature vector with position-coding information, the traffic attribute being indicative of at least a current traffic state of the plurality of road segments.

5. The apparatus of claim 4, wherein the time-consuming prediction module comprises:

a model processing module configured to process the feature vector with position-coding information using the time-consuming prediction model to determine the predicted time consumption,

6. The apparatus of claim 4, further comprising:

An estimated time of arrival determination module configured to determine an estimated time of arrival of the trip based on the estimated time consumption; and

And a transmitting module configured to transmit the estimated time of arrival to a terminal device associated with the trip.

7. An electronic device, comprising:

a memory and a processor;

wherein the memory is for storing one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method of any of claims 1-3.

8. A computer readable storage medium having stored thereon one or more computer instructions, wherein the one or more computer instructions are executed by a processor to implement the method of any of claims 1 to 3.