CN111915877A - Method and device for processing traffic flow path distribution information and electronic equipment - Google Patents

Method and device for processing traffic flow path distribution information and electronic equipment Download PDF

Info

Publication number
CN111915877A
CN111915877A CN201910381137.9A CN201910381137A CN111915877A CN 111915877 A CN111915877 A CN 111915877A CN 201910381137 A CN201910381137 A CN 201910381137A CN 111915877 A CN111915877 A CN 111915877A
Authority
CN
China
Prior art keywords
traffic flow
flow path
distribution information
path distribution
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910381137.9A
Other languages
Chinese (zh)
Inventor
张欣
茅嘉磊
杨磊
肖楠
贺亚静
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba Group Holding Ltd
Original Assignee
Alibaba Group Holding Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Alibaba Group Holding Ltd filed Critical Alibaba Group Holding Ltd
Priority to CN201910381137.9A priority Critical patent/CN111915877A/en
Priority to PCT/CN2020/086574 priority patent/WO2020224445A1/en
Publication of CN111915877A publication Critical patent/CN111915877A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0133—Traffic data processing for classifying traffic situation

Abstract

The invention discloses a method and a device for processing traffic flow path distribution information and electronic equipment, wherein the processing method comprises the following steps: acquiring the distribution information of the predicted traffic flow path of the preset area in the next time period; acquiring a predicted traffic flow path distribution class corresponding to a preset area in the next time period; and correcting the predicted traffic flow path distribution information according to the predicted traffic flow path distribution class so that the corrected predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class.

Description

Method and device for processing traffic flow path distribution information and electronic equipment
Technical Field
The present invention relates to the field of traffic control technologies, and in particular, to a method and an apparatus for processing traffic flow path distribution information, an electronic device, and a computer-readable medium.
Background
The traffic demand of the traffic region in the future may be obtained from the predicted traffic flow path distribution information. The traffic flow path distribution information includes the paths in the traffic area and the traffic flow values passing through each path. Wherein a path may be a sequence of road segments on a traffic network.
The traffic route distribution in the target time zone may be related to the current traffic route distribution information in the traffic area, the traffic route distribution information around the traffic area, time, date, weather, and other factors.
In the prior art, a regression model is generally established for each route in a traffic area to obtain a predicted traffic flow value of each route, and the predicted traffic flow values of each route are combined and superposed to form prediction of traffic flow route distribution information of the traffic area in a target time period. However, this prediction method does not consider the overall factors of the preset area, and thus, errors are likely to accumulate, so that the traffic flow path distribution information obtained by combination may greatly deviate from the actual traffic flow path distribution information.
Disclosure of Invention
The invention aims to provide a new technical scheme for predicting traffic flow path distribution information of a preset area in the future.
According to a first aspect of the present invention, there is provided a method for processing traffic route distribution information, including:
acquiring the distribution information of a predicted traffic flow path of a preset area in a target time period; the traffic flow path distribution information comprises paths in the preset area and traffic flow values passing through each path in a corresponding time period;
acquiring a predicted traffic flow path distribution class corresponding to the preset area in the target time period; the traffic flow path distribution class comprises a clustering result obtained by clustering traffic flow path distribution information of at least one historical time period;
and correcting the predicted traffic flow path distribution information according to the predicted traffic flow path distribution class so that the corrected predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class.
Optionally, the step of obtaining the predicted traffic flow path distribution information of the preset area in the target time period includes:
acquiring a path in the preset area;
respectively acquiring a predicted traffic flow value passing through each path in a target time period;
and acquiring the distribution information of the predicted traffic flow paths of the preset area in the target time period according to the predicted traffic flow value passing through each path in the target time period.
Optionally, taking each path in turn as a target path,
the step of obtaining a predicted traffic flow value through the target route at a target time period includes:
obtaining a selected first feature vector, wherein the first feature vector comprises a plurality of first features influencing the traffic flow value of the target path in a target time period; the plurality of first features includes a first traffic feature and a first environmental feature;
acquiring a first mapping function between the first characteristic vector and a traffic flow value passing through the target path;
and obtaining a predicted traffic flow value passing through the target path in a target time period according to the first mapping function and the vector value of the first characteristic vector in the current time period.
Optionally, the first traffic characteristic includes at least one of traffic flow path distribution information of the preset area and traffic flow path distribution information around the preset area; and/or, the first environmental characteristic comprises at least one of time, date, weather.
Optionally, the step of obtaining a first mapping function between the first feature vector and the traffic flow value passing through the target path includes:
acquiring first training samples according to historical traffic flow tracks, wherein each first training sample comprises the historical traffic flow track matched with the target path;
and training to obtain the first mapping function according to the vector value of the first feature vector of the first training sample and the actual vehicle flow value which corresponds to the first training sample and passes through the target path.
Optionally, the processing method further includes:
acquiring an actual traffic flow track matched with the target path in the target time period, and taking the actual traffic flow track as a new first training sample;
and correcting the first mapping function according to the vector value of the first feature vector of the new first training sample and the actual vehicle flow value which passes through the target path in the target time interval and corresponds to the new first training sample.
Optionally, the obtaining of the predicted traffic flow path distribution class corresponding to the target time period in the preset area further includes:
acquiring traffic flow path distribution information of the preset area in a plurality of historical time periods as historical traffic flow path distribution information;
clustering the historical traffic flow path distribution information to obtain at least one traffic flow path distribution class;
the obtaining of the predicted traffic flow path distribution class corresponding to the preset area in the target time period includes: and acquiring the traffic flow path distribution class corresponding to the preset area in the target time period from the at least one traffic flow path distribution class as the predicted traffic flow path distribution class.
Optionally, the step of clustering the plurality of historical traffic flow path distribution information to obtain at least one traffic flow path distribution class includes:
determining the number of road segments contained in each path;
determining a traffic flow value passing through each path in a corresponding historical time period according to the distribution information of each historical traffic flow path;
determining the distance between every two pieces of historical traffic flow path distribution information according to the number of the road segments contained in each path and the traffic flow value passing through the corresponding path in each historical time period;
and clustering the plurality of historical traffic flow path distribution information according to the distance between every two pieces of historical traffic flow path distribution information to obtain at least one traffic flow path distribution class.
Optionally, the step of determining the distance between every two pieces of historical traffic flow path distribution information according to the number of segments included in each path and the traffic flow value passing through the corresponding path in each historical time period includes:
determining the road section flow sum corresponding to the distribution information of each historical traffic flow path according to the number of the road sections contained in each path and the traffic flow value passing through the corresponding path in each historical time period; wherein the sum of the road section flow rates is the sum of traffic flow values passing through each road section in the corresponding time period;
determining a road section flow difference corresponding to each two pieces of historical traffic flow path distribution information according to the number of road sections contained in each path and the traffic flow value passing through the corresponding path in each historical time period; the road section flow difference is the sum of the differences of the traffic flow values passing through each road section in the corresponding two time periods;
and determining the distance between every two pieces of historical traffic flow path distribution information according to the sum of the road section flow corresponding to each piece of historical traffic flow path distribution information and the difference of the road section flow corresponding to every two pieces of historical traffic flow path distribution information.
Optionally, the step of clustering the plurality of pieces of historical traffic flow path distribution information according to the distance between every two pieces of historical traffic flow path distribution information to obtain at least one traffic flow path distribution class includes:
taking the distribution information of each traffic flow path as a node, and constructing a relational graph according to the distance between every two nodes;
splitting the relationship graph into at least one sub-graph according to the distance between every two nodes;
and obtaining traffic flow path distribution classes corresponding to the sub-images one by one, and dividing traffic flow path distribution information corresponding to the nodes contained in each sub-image into the corresponding traffic flow path distribution classes.
Optionally, the step of constructing a relationship graph according to the distance between each two nodes by using the distribution information of each traffic flow path as a node includes:
and taking the distribution information of each traffic flow path as a node, and respectively connecting each node and a set number of nodes with the shortest distance to the node to obtain the relational graph.
Optionally, the step of splitting the relationship graph into at least one sub-graph according to the distance between each two nodes includes:
truncating the connection between two nodes with a distance exceeding a preset distance threshold value so as to split the relational graph into at least one sub-graph.
Optionally, the step of obtaining the predicted traffic flow path distribution class corresponding to the preset area in the target time period includes:
obtaining a selected second feature vector, wherein the second feature vector comprises a plurality of second features which influence the traffic flow path distribution class corresponding to the preset area in a target time period; the plurality of second features includes a second traffic feature and a second environmental feature;
acquiring a second mapping function between the second feature vector and the traffic flow path distribution class;
and obtaining a traffic flow path distribution class corresponding to the preset area in a target time interval according to the second mapping function and the vector value of the second characteristic vector in the current time interval, and using the traffic flow path distribution class as the predicted traffic flow path distribution class.
Optionally, the second traffic characteristic includes at least one of traffic flow path distribution information of the preset area and traffic flow path distribution information around the preset area; and/or the second environmental characteristic comprises at least one of time, date, weather.
Optionally, the step of obtaining a second mapping function between the second eigenvector and the traffic flow path distribution class includes:
taking the historical traffic flow track as a second training sample;
and training to obtain the second mapping function according to the vector value of the second feature vector of the second training sample and the traffic flow path distribution class actually corresponding to the second training sample.
Optionally, the processing method further includes:
acquiring an actual traffic flow track in the target time period as a new second training sample;
and correcting the second mapping function according to the vector value of the second eigenvector of the new second training sample and the traffic flow path distribution class actually corresponding to the new second training sample.
Optionally, the step of correcting the predicted traffic flow path distribution information according to the predicted traffic flow path distribution class so that the corrected predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class includes:
determining target traffic flow path distribution information of a clustering center representing the predicted traffic flow path distribution class;
determining a distance between the predicted traffic flow path distribution information and the target traffic flow path distribution information;
and correcting the predicted traffic flow path distribution information according to the distance between the predicted traffic flow path distribution information and the target traffic flow path distribution information, so that the corrected predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class.
Optionally, the step of correcting the predicted traffic flow path distribution information according to the distance between the predicted traffic flow path distribution information and the target traffic flow path distribution information, so that the corrected predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class includes:
respectively determining the distance between each traffic flow path distribution information contained in the predicted traffic flow path distribution class and the target traffic flow path distribution information;
determining the maximum value of the distance between each traffic flow path distribution information and the target traffic flow path distribution information;
and correcting the predicted traffic flow path distribution information so that the distance between the corrected predicted traffic flow path distribution information and the target traffic flow path distribution information is smaller than or equal to the maximum value.
Optionally, the step of determining target traffic flow path distribution information representing a cluster center of the predicted traffic flow path distribution class includes:
determining an optimization function between a target traffic flow value passing through each path and an index measuring a clustering center according to the traffic flow value passing through each path in the traffic flow path distribution information contained in the predicted traffic flow path distribution class;
determining a target traffic flow value passing through each path under the condition that the index for measuring the clustering center is minimum according to the optimization function corresponding to each path;
and obtaining the target traffic flow path distribution information according to the target traffic flow value passing through each path.
Optionally, the processing method further includes:
and carrying out traffic control on the preset area according to the corrected predicted traffic flow path distribution information.
According to a second aspect of the present invention, there is provided a traffic route distribution information processing apparatus including:
the distribution information prediction module is used for acquiring the predicted traffic flow path distribution information of a preset area in a target time interval; the traffic flow path distribution information comprises paths in the preset area and traffic flow values passing through each path in a corresponding time period;
the distribution type prediction module is used for acquiring a predicted traffic flow path distribution type corresponding to the preset area in a target time period; the traffic flow path distribution class comprises traffic flow path distribution information of at least one historical time period;
and the distribution information correction module is used for correcting the predicted traffic flow path distribution information according to the predicted traffic flow path distribution class so as to enable the corrected predicted traffic flow path distribution information to belong to the predicted traffic flow path distribution class.
According to a third aspect of the invention, there is provided an electronic device comprising the processing apparatus according to the second aspect of the invention; or a processor and a memory for storing executable instructions for controlling the processor to perform the processing method according to the first aspect of the invention.
According to a fourth aspect of the present invention, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the processing method according to the first aspect of the present invention.
In the embodiment of the invention, the finally obtained corrected predicted traffic flow path distribution information can be more accurate by acquiring the predicted traffic flow path distribution information of the preset area in the target time interval in advance, acquiring the predicted traffic flow path distribution class corresponding to the target time interval, and correcting the predicted traffic flow path distribution information according to the predicted traffic flow path distribution class.
Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a block diagram of one example of a hardware configuration of an electronic device that can be used to implement an embodiment of the present invention.
FIG. 2 is a block diagram of another example of a hardware configuration of an electronic device that may be used to implement an embodiment of the invention;
fig. 3 is a flowchart of a processing method of traffic flow path distribution information according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an example of a preset area according to an embodiment of the present invention;
fig. 5 is a diagram illustrating an example of traffic flow path distribution information of a first history period according to an embodiment of the present invention;
fig. 6 is a diagram showing an example of traffic flow path distribution information of a second history period according to the embodiment of the present invention;
fig. 7 is a diagram showing an example of traffic flow path distribution information of a third history period according to the embodiment of the present invention;
fig. 8 is a flowchart illustrating an example of a processing method of traffic route distribution information according to an embodiment of the present invention;
fig. 9 is a schematic diagram of a processing device of traffic path distribution information according to an embodiment of the present invention;
FIG. 10 is a functional block diagram of an electronic device provided in accordance with a first embodiment of the invention;
fig. 11 is a schematic diagram of a hardware structure of an electronic device according to a second embodiment of the present invention.
Detailed Description
Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
< hardware configuration >
Fig. 1 and 2 are block diagrams of the hardware configuration of an electronic device 1000 that can be used to implement the method of processing traffic path distribution information according to any embodiment of the present invention.
In one embodiment, as shown in FIG. 1, the electronic device 1000 may be a server 1100.
The server 1100 provides a service point for processes, databases, and communications facilities. The server 1100 can be a unitary server or a distributed server across multiple computers or computer data centers. The server may be of various types, such as, but not limited to, a web server, a news server, a mail server, a message server, an advertisement server, a file server, an application server, an interaction server, a database server, or a proxy server. In some embodiments, each server may include hardware, software, or embedded logic components or a combination of two or more such components for performing the appropriate functions supported or implemented by the server. For example, a server, such as a blade server, a cloud server, etc., or may be a server group consisting of a plurality of servers, which may include one or more of the above types of servers, etc.
In this embodiment, the server 1100 may include a processor 1110, a memory 1120, an interface device 1130, a communication device 1140, a display device 1150, and an input device 1160, as shown in fig. 1.
In this embodiment, the server 1100 may also include a speaker, a microphone, and the like, which are not limited herein.
The processor 1110 may be a dedicated server processor, or may be a desktop processor, a mobile version processor, or the like that meets performance requirements, and is not limited herein. The memory 1120 includes, for example, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, and the like. The interface device 1130 includes various bus interfaces such as a serial bus interface (including a USB interface), a parallel bus interface, and the like. The communication device 1140 is capable of wired or wireless communication, for example. The display device 1150 is, for example, a liquid crystal display panel, an LED display panel touch display panel, or the like. Input devices 1160 may include, for example, a touch screen, a keyboard, and the like.
In this embodiment, the memory 1120 of the server 1100 is configured to store instructions for controlling the processor 1110 to operate so as to perform at least a processing method of traffic path distribution information according to any of the embodiments of the present invention. The skilled person can design the instructions according to the disclosed solution. How the instructions control the operation of the processor is well known in the art and will not be described in detail herein.
Although shown as multiple devices in fig. 1, the present invention may relate to only some of the devices, e.g., server 1100 may relate to only memory 1120 and processor 1110.
In one embodiment, the electronic device 1000 may be a terminal device 1200 such as a PC, a notebook computer, or the like used by an operator, which is not limited herein.
In this embodiment, referring to fig. 2, the terminal apparatus 1200 may include a processor 1210, a memory 1220, an interface device 1230, a communication device 1240, a display device 1250, an input device 1260, a speaker 1270, a microphone 1280, and the like.
The processor 1210 may be a mobile version processor. The memory 1220 includes, for example, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, and the like. The interface device 1230 includes, for example, a USB interface, a headphone interface, and the like. The communication device 1240 may be capable of wired or wireless communication, for example, the communication device 1240 may include a short-range communication device, such as any device that performs short-range wireless communication based on short-range wireless communication protocols, such as the Hilink protocol, WiFi (IEEE 802.11 protocol), Mesh, bluetooth, ZigBee, Thread, Z-Wave, NFC, UWB, LiFi, and the like, and the communication device 1240 may also include a long-range communication device, such as any device that performs WLAN, GPRS, 2G/3G/4G/5G long-range communication. The display device 1250 is, for example, a liquid crystal display, a touch display, or the like. The input device 1260 may include, for example, a touch screen, a keyboard, and the like. A user can input/output voice information through the speaker 1270 and the microphone 1280.
In this embodiment, the memory 1220 of the terminal device 1200 is configured to store instructions for controlling the processor 1210 to operate at least to perform a method of processing traffic path distribution information according to any of the embodiments of the present invention. The skilled person can design the instructions according to the disclosed solution. How the instructions control the operation of the processor is well known in the art and will not be described in detail herein.
Although a plurality of devices of the terminal apparatus 1200 are shown in fig. 2, the present invention may relate only to some of the devices, for example, the terminal apparatus 1200 relates only to the memory 1220 and the processor 1210 and the display device 1250.
< method examples >
In the present embodiment, a method for processing traffic route distribution information is provided. The processing method may be implemented by an electronic device. The electronic device may be the server 1100 as shown in fig. 1 or the terminal device 1200 as shown in fig. 2.
As shown in fig. 3, the method for processing traffic route distribution information according to the present embodiment may include the following steps S1000 to S3000:
step S1000, acquiring the distribution information of the predicted traffic flow path of the preset area in the target time interval.
The target time period may be a future time period or a past time period.
The preset area in this embodiment may be a traffic area selected in a city according to an application scenario or a specific requirement. For example, the preset region may be as shown in fig. 4, or may be as shown in fig. 5 to 7.
Specifically, the predicted traffic flow path distribution information may include paths in a preset area and a predicted traffic flow value passing through each path in a target time period.
The path in this embodiment may be a sequence of road segments on a road network, and a road segment may refer to a traffic line in a driving direction between two adjacent intersections on a traffic network. Specifically, in the embodiments as shown in fig. 4 to 7, the path in the preset area acquired through step S1000 may include: path a, path B, path C, path D, path E, and path F.
In one embodiment, the step of acquiring the predicted traffic route distribution information of the preset area in the target time period may include steps S1100 to S1300 as follows:
step S1100, a path in a preset area is acquired.
Step S1200, respectively obtaining the predicted traffic flow values passing through each route in the target time period.
The specific steps of respectively obtaining the predicted traffic flow values passing through each path in the target time period may be: taking each path as a target path in turn, and acquiring a predicted traffic flow value passing through the target path in a target time period.
Specifically, the time periods may be set according to an application scenario or specific requirements, and the duration of each time period (including the target time period, the current time period, and the historical time period described in this embodiment) is equal. For example, the time interval between every two adjacent integer points may be regarded as one time interval. Then, 8-9 points of the current date may be the current period and 9-10 points may be the target period.
The step of acquiring the predicted traffic flow value passing through the target route in the target period may include steps S1210 to S1230 as follows:
in step S1210, the selected first vector feature is obtained.
The first feature vector may include a plurality of first features that affect a traffic flow value of the target path over the target time period. The plurality of first features includes a first traffic feature and a first environmental feature.
The first traffic characteristic may include at least one of traffic flow path distribution information of a preset area and traffic flow path distribution information around the preset area. The first environmental characteristic may include at least one of time, date, weather.
In this example, xjMay be a first traffic characteristic, a first environmental characteristic, etc. that may affect the traffic flow value of the target route over the target time period. For example, the first traffic feature may be traffic route distribution information of a preset area and traffic route distribution information around the preset area, the first environment feature may be time, date and weather, and the feature vector X may have 5 features, that is, n is 5, and in this case, the feature vector X may be represented as X (X is 5)1,x2,x3,x4,x5). Of course, other features related to the vehicle flow value may also be included in the feature vector X.
In step S1220, a first mapping function between the first feature vector and the traffic flow value passing through the target path is obtained.
The independent variable of the first mapping function F1(X) is the eigenvector X, and the dependent variable F1(X) is the predicted vehicle flow value determined by the eigenvector X.
In this embodiment, the step S1220 of obtaining the first mapping function between the first feature vector and the traffic flow value passing through the target path may further include the following steps S1221 to S1222:
step S1221, a first training sample is obtained according to the historical traffic flow track.
And each first training sample comprises a traffic track matched with the target path.
In step S1222, a first mapping function is obtained by training according to the vector value of the first feature vector of the first training sample and the actual vehicle flow value passing through the target path corresponding to the first training sample.
In one embodiment, the steps S1221 to S1222 of training the first mapping function may be performed according to a preset training period. The training period may be set according to a specific application scenario or application requirements, and may be set to 1 day, for example.
In this embodiment, the first mapping function f (x) may be obtained by various fitting means based on vector values of the first feature vector of the training sample and actual vehicle flow values through the target path corresponding to the training sample. For example, the first mapping function F1(x) may be obtained by using any multiple linear regression model, which is not limited herein.
In one example, the multiple linear regression model may be a simple polynomial function reflecting the first mapping function F1(x), wherein the coefficients of each order of the polynomial function are unknown, and the coefficients of each order of the polynomial function may be determined by substituting vector values of the first feature vector of the first training sample and the actual traffic flow value through the target path corresponding to the first training sample into the polynomial function, thereby obtaining the first mapping function F1 (x).
In another example, various regression models, such as an additive model, may be used to perform multiple rounds of training with the first vector value of the first feature vector of the first training sample and the actual traffic flow value through the target path corresponding to the first training sample as accurate samples, each round learns the residual after the last round of fitting, and the residual is controlled to a very low value by iterating T rounds, so that the resulting first mapping function F1(x) has very high accuracy. The addition model is, for example, LightGBM, GBDT, XGBoost, etc., and is not limited herein.
In step S1230, a predicted traffic flow value passing through the target route in the target time period is obtained according to the first mapping function and the vector value of the first feature vector in the current time period.
In this embodiment, according to the first mapping function between the first eigenvector obtained in step S1220 and the traffic flow value passing through the target path, the vector value can be substituted into the first mapping function f (x) according to the vector value of the first eigenvector in the current time period, so as to obtain the predicted traffic flow value passing through the target path in the target time period.
According to the embodiment of the invention, the predicted traffic flow value passing through the target path in the target time period can be obtained according to the first feature vector and the first mapping function, and the first mapping function is obtained by training according to a large number of training samples, so that when the predicted traffic flow value is determined by utilizing the first mapping function, the accuracy of the obtained predicted traffic flow value can be improved.
Step 1300, obtaining the predicted traffic flow path distribution information of the preset area in the next time period according to the predicted traffic flow value passing through each path in the next time period.
Specifically, the predicted traffic flow values passing through each route in the next time period may be integrated, so as to obtain the predicted traffic flow route distribution information of the preset area in the next time period.
Step S2000, obtaining a predicted traffic flow path distribution class corresponding to the preset area in the target time period.
The traffic flow path distribution type comprises a clustering result obtained by clustering traffic flow path distribution information of a preset area in at least one historical time period.
Specifically, the traffic flow path distribution information of the preset area in at least one historical time period may be clustered to obtain at least one traffic flow path distribution class, and each traffic flow path distribution class may be a set of the traffic flow path distribution information of all the historical time periods belonging to the cluster, or may be a unique identifier of a corresponding cluster. And through the unique identification of the cluster, the traffic flow path distribution information of all historical periods belonging to the corresponding cluster can be uniquely determined. Wherein the identifier may be composed of at least one character.
Then, the predicted traffic flow path distribution class corresponding to the target time interval may be one of at least one traffic flow path distribution class obtained by clustering.
The traffic flow path distribution information may include paths in a preset area and a traffic flow value passing through each path in a corresponding period. For example, fig. 5 to 7 are schematic diagrams of traffic flow path distribution information of the preset area in fig. 4 in different historical periods.
In one embodiment, step S1000 and step S2000 may be performed simultaneously, step S1000 may be performed first and step S2000 may be performed second, and step S2000 may be performed first and step S1000 may be performed second. The present invention does not specifically limit the execution sequence of step S1000 and step S2000.
In an embodiment, before performing step S2000, the processing method may further include a step of acquiring at least one traffic flow path distribution class corresponding to the preset area, so that the traffic flow path distribution class corresponding to the preset area in the target time period is acquired in step S2000 as the predicted traffic flow path distribution class. The predicted traffic flow path distribution class in this embodiment is one of the at least one acquired traffic flow path distribution class corresponding to the preset area.
The step of obtaining at least one traffic flow distribution class may further include steps S6100 to S6200 as follows:
in step S6100, traffic flow path distribution information of the preset area in a plurality of historical time periods is obtained as historical traffic flow path distribution information.
For example, fig. 5 may be a schematic diagram of traffic flow path distribution information in a first historical period, fig. 6 may be a schematic diagram of traffic flow path distribution information in a second historical period, and fig. 7 may be a schematic diagram of traffic flow path distribution information in a third historical period.
In the traffic flow path distribution information in the first history period as shown in fig. 5, it can be found that the traffic flow values passing through the path a, the path B, the path C, the path D, the path E, and the path F in the first history period are 300, 168, 270, 156, 0, respectively. In the traffic flow path distribution information in the second history period as shown in fig. 6, it can be found that the traffic flow values passing through the path a, the path B, the path C, the path D, the path E, and the path F in the second history period are 340, 168, 270, 0, 227, 0, respectively. In the traffic flow path distribution information in the third history period as shown in fig. 7, it is found that the traffic flow values passing through the path a, the path B, the path C, the path D, the path E, and the path F in the third history period are 0, 168, 270, 0, 227, 100, respectively.
And S6200, clustering the plurality of historical traffic flow path distribution information to obtain at least one traffic flow path distribution class.
In one example, clustering the plurality of historical traffic flow path distribution information to obtain at least one traffic flow path distribution class may further include steps S6210 to S6240 shown below:
in step S6210, the number of links included in each route is determined.
The road segments in this embodiment are traffic lines between two adjacent intersections in the corresponding path, and the number of the road segments is the number of the road segments included in the corresponding path.
For example, in the preset area shown in fig. 4 to 7, the number of links included in each of the route a, the route B, and the route F is 5, and the number of links included in each of the route C, the route D, and the route E is 3.
Step 6220, according to the distribution information of each historical traffic flow path, determining the traffic flow value passing through each path in the corresponding historical time period.
Step 6230, determining a distance between every two pieces of historical traffic flow path distribution information according to the number of the segments included in each path and the traffic flow value passing through the corresponding path in each historical time period.
The distance between every two pieces of historical traffic flow path distribution information can be used for representing the difference degree between the corresponding two pieces of historical traffic flow path distribution information.
In one example, determining the distance between every two pieces of historical traffic flow path distribution information according to the number of segments included in each path and the traffic flow value passing through the corresponding path in each historical time period may include the following steps S6231 to S6233:
step 6231, determining a road section traffic sum corresponding to each historical traffic flow path distribution information according to the number of road sections included in each path and the traffic flow value passing through the corresponding path in each historical time period.
Wherein the link traffic sum is a sum of traffic flow values passing through each link during the corresponding time period.
In the traffic flow path distribution information in the first history period as shown in fig. 5, the sum of the road section flow rate corresponding to the traffic flow path distribution information in the first history period may be obtained as f according to the number of the road sections included in each path and the traffic flow rate value of the corresponding path passing through the first history period1Wherein f is1＝300*5+168*5+270*3+156*3+0*5+0*5＝3618。
In the traffic flow path distribution information in the second history period as shown in fig. 6, the sum of the road section flow rate corresponding to the traffic flow path distribution information in the second history period may be obtained as f according to the number of the road sections included in each route and the traffic flow rate value of the corresponding route passing through the second history period2Wherein f is2＝340*5+168*5+270*3+0*3+227*5+0*5＝4031。
In the traffic flow path distribution information in the third history period shown in fig. 7, the sum of the road flow rate f corresponding to the traffic flow path distribution information in the third history period can be obtained according to the number of the road segments included in each route and the traffic flow rate value of the corresponding route passing through the third history period3Wherein f is3＝0*5+168*5+270*3+0*3+227*5+100*5＝3285。
Step 6232, determining a road section traffic flow difference corresponding to each two pieces of historical traffic flow path distribution information according to the number of road sections included in each path and the traffic flow value passing through the corresponding path in each historical time period.
The road section flow difference is the sum of the difference values of the traffic flow values passing through each road section in the corresponding two time periods.
Specifically, the sum of the differences of the traffic flow values of all road sections passing through each path in the two corresponding time periods may be determined, and then the sum of the differences of the traffic flow values of each path may be obtained according to the sum of the differences of the traffic flow values of each path, so as to obtain the sum of the differences of the traffic flow values of each road section passing through each path in the two corresponding time periods. The sum of the differences between the traffic flow values of all the road segments passing through one of the routes in the two corresponding time periods may be obtained by determining the difference between the traffic flow values of the routes in the two corresponding time periods, and then multiplying the difference by the number of the road segments included in the route.
For the traffic flow path distribution information in the first history period shown in fig. 5 and the traffic flow path distribution information in the second history period shown in fig. 6, the link traffic flow difference corresponding to the traffic flow path distribution information in the first history period and the traffic flow distribution information in the second history period can be determined according to the number of links included in each link, the traffic flow value of the corresponding link passing through the first history period, and the traffic flow value of the corresponding link passing through the second history period.
Specifically, the sum of the difference values of the historical traffic flow passing through each road segment in the route a in the first historical period and the second historical period is determined to be (340- 5. Then, the first historyThe difference between the traffic flow path distribution information in the time period and the road section flow rate corresponding to the traffic flow path distribution information in the second historical time period may be Δ f12，Δf12＝(340-300)*5+(168-168)*5+(270-270)*3+(156-0)*3+(227-0)*3+(0-0)*5＝1349。
For the traffic flow path distribution information in the first history period shown in fig. 5 and the traffic flow path distribution information in the third history period shown in fig. 7, the link traffic flow difference corresponding to the traffic flow path distribution information in the first history period and the traffic flow distribution information in the third history period can be determined according to the number of links included in each link, the traffic flow value passing through the corresponding link in the first history period, and the traffic flow value passing through the corresponding link in the third history period.
Specifically, the sum of the difference values of the historical traffic flow of each road segment passing through the route a in the first historical period and the third historical period is determined to be (340-0) × 5, the sum of the difference values of the historical traffic flow of each road segment passing through the route B in the first historical period and the third historical period is determined to be (168) × 5, the sum of the difference values of the historical traffic flow of each road segment passing through the route C in the first historical period and the third historical period is determined to be (270) × 3, the sum of the difference values of the historical traffic flow of each road segment passing through the route D in the first historical period and the third historical period is determined to be (156-0) × 3, the sum of the difference values of the historical traffic flow of each road segment passing through the route E in the first historical period and the third historical period is determined to be (227-0) × 5, the sum of the historical traffic flow of each road segment passing through the route F in the first historical period and the third historical period is determined to be (100) × 3 5. Then, a difference between the road section flow rates corresponding to the traffic flow path distribution information in the first history period and the traffic flow path distribution information in the third history period may be Δ f13，Δf13＝(340-0)*5+(168-168)*5+(270-270)*3+(156-0)*3+(227-0)*3+(100-0)*5＝3349。
For the traffic flow path distribution information in the second history period shown in fig. 6 and the traffic flow path distribution information in the third history period shown in fig. 7, the link traffic flow difference between the traffic flow path distribution information in the second history period and the traffic flow path distribution information in the third history period can be determined according to the number of links included in each link, the traffic flow value of the corresponding link in the second history period, and the traffic flow value of the corresponding link in the third history period.
Specifically, the sum of the difference values of the historical traffic flow of each road segment in the passing route a in the second historical period and the third historical period is determined to be (340-0) × 5, the sum of the difference values of the historical traffic flow of each road segment in the passing route B in the second historical period and the third historical period is (168) - 5. Then, a difference between the road section flow rate corresponding to the traffic flow path distribution information in the second history period and the traffic flow path distribution information in the third history period may be Δ f23，Δf23＝(340-0)*5+(168-168)*5+(270-270)*3+(0-0)*3+(227-227)*3+(100-0)*5＝2200。
Step S6233, determining a distance between every two pieces of historical traffic flow path distribution information according to the sum of the traffic flow corresponding to each piece of historical traffic flow path distribution information and the difference between the traffic flow corresponding to every two pieces of historical traffic flow path distribution information.
In one example, the distance between every two pieces of historical traffic path distribution information may be determined by: and determining a geometric mean value of the road section flow sum corresponding to the two pieces of historical traffic flow path distribution information, and calculating a ratio of the road section flow difference corresponding to the two pieces of historical traffic flow path distribution information to the geometric mean value to be used as a distance between the two pieces of historical traffic flow path distribution information.
For the traffic flow path distribution information in the first history period as shown in fig. 5, and the traffic flow path distribution information in the second history period as shown in fig. 6For the traffic flow path distribution information, the geometric average value of the sum of the road section flow rates corresponding to the traffic flow path distribution information in the first historical period and the traffic flow path distribution information in the second historical period may be determined as
Figure BDA0002053403750000181
Then, calculating the road section flow difference delta f corresponding to the traffic flow path distribution information in the first historical time period and the traffic flow path distribution information in the second historical time period12And the geometric mean value
Figure BDA0002053403750000182
The distance d between the traffic flow path distribution information in the first historical period and the traffic flow path distribution information in the second historical period is obtained12，
Figure BDA0002053403750000183
For the traffic flow path distribution information in the first historical period shown in fig. 5 and the traffic flow path distribution information in the third historical period shown in fig. 7, the geometric average of the sum of the road section flow rates corresponding to the traffic flow path distribution information in the first historical period and the traffic flow path distribution information in the third historical period may be determined as
Figure BDA0002053403750000184
Then, calculating the road section flow difference delta f corresponding to the traffic flow path distribution information in the first historical period and the traffic flow path distribution information in the third historical period13And the geometric mean value
Figure BDA0002053403750000185
The distance d between the traffic flow path distribution information in the first historical period and the traffic flow path distribution information in the third historical period is obtained13，
Figure BDA0002053403750000186
For the second history as shown in FIG. 6For the traffic flow path distribution information in the segment and the traffic flow path distribution information in the third history period as shown in fig. 7, the geometric average of the sum of the road section flow rates corresponding to the traffic flow path distribution information in the second history period and the traffic flow path distribution information in the third history period may be determined as
Figure BDA0002053403750000187
Then, the traffic flow path distribution information in the second historical period and the road section flow difference delta f corresponding to the traffic flow path distribution information in the third historical period are calculated23And the geometric mean value
Figure BDA0002053403750000188
The distance d between the traffic flow path distribution information in the second historical period and the traffic flow path distribution information in the third historical period is obtained23，
Figure BDA0002053403750000191
And step S6240, clustering the plurality of historical traffic flow path distribution information according to the distance between every two pieces of historical traffic flow path distribution information to obtain at least one traffic flow path distribution class.
The clustering method adopted in this embodiment may be any one or more of a systematic clustering method, an ordered sample clustering method, a dynamic clustering method, a fuzzy clustering method, and a graph theory clustering method, and the specific clustering method is not limited herein.
By clustering a plurality of historical traffic flow path distribution information, the distance between the historical traffic flow path distribution information belonging to the same traffic flow path distribution class is smaller, and the distance between the historical traffic flow path distribution information belonging to different traffic flow path distribution classes is longer.
In an example, the step of clustering the plurality of pieces of historical traffic flow path distribution information according to the distance between every two pieces of historical traffic flow path distribution information to obtain at least one traffic flow path distribution class may include steps S6241 to S6243 shown below:
step 6241, each traffic flow path distribution information is used as a node, and a relational graph is constructed according to the distance between every two nodes.
In one example, the relationship graph may be obtained by connecting every two nodes with each traffic route distribution information as one node.
In another example, the relationship graph may be obtained by connecting each node and a set number of nodes closest to the node, with each traffic route distribution information as one node.
In this example, the set number may be set in advance according to an application scenario or a specific requirement, for example, the set number may be set to 5, and then each node and 5 nodes closest to itself may be connected to obtain the relationship graph.
Step S6242, according to the distance between each two nodes, the relationship graph is split into at least one sub-graph.
In one example, it may be that a connection between two nodes whose distance exceeds a preset distance threshold is truncated to split the relationship graph into at least one subgraph.
In another example, a graph partitioning method is applied to split the graph into at least one subgraph such that the sum of distances between every two nodes located within the same subgraph is minimum and the sum of distances between every two nodes located within different subgraphs is maximum.
The graph division method used in this example may be a minimum division method or a Normalized Cut method, and is not limited herein.
Step 6243, obtaining traffic flow path distribution classes corresponding to each sub-graph one by one, and dividing the traffic flow path distribution information corresponding to the nodes included in each sub-graph into corresponding traffic flow path distribution classes.
For example, when node 1 and node 2 are located in sub-graph 1 and node 3 and node 4 are located in sub-graph 2, traffic flow path distribution class 1 corresponding to sub-graph 1 and traffic flow path distribution class 2 corresponding to sub-graph 2 may be obtained, traffic flow path distribution information corresponding to node 1 and node 2 may be divided into traffic flow path distribution class 1, and traffic flow path distribution information corresponding to node 3 and node 4 may be divided into traffic flow path distribution class 2.
After the at least one traffic flow path distribution class is obtained, the traffic flow path distribution information of the preset area in the target time period is obtained and belongs to one of the obtained at least one traffic flow path distribution class, and the obtained at least one traffic flow path distribution class is used as a predicted traffic flow path distribution class.
The step of acquiring the traffic flow distribution class corresponding to the preset area in the target time period as the predicted traffic flow distribution class may further include steps S2100 to S2300 shown below:
in step S2100, the selected second feature vector is acquired.
The second feature vector may include a plurality of second features that affect the traffic flow path distribution class corresponding to the preset region in the target time period. The plurality of second features includes a second traffic feature and a second environmental feature.
The second traffic characteristic may include at least one of traffic flow path distribution information of a preset area and traffic flow path distribution information around the preset area. The second environmental characteristic may include at least one of time, date, weather.
In this example, yjThe second traffic characteristic, the second environmental characteristic, and the like may affect the traffic flow path distribution class corresponding to the preset area in the target time period. For example, the second traffic characteristic may be traffic route distribution information of a preset area and traffic route distribution information around the preset area, the second environment characteristic may be time, date and weather, here, the characteristic vector Y may have 5 characteristics, that is, n is 5, and in this case, the characteristic vector Y may be represented as Y (Y is 5)1,y2,y3,y4,y5). Of course, other features related to the corresponding traffic route distribution class may also be included in the feature vector Y.
Step S2200 is performed to obtain a second mapping function between the second eigenvector and the traffic flow path distribution class.
The argument of the second mapping function F2(Y) is the feature vector Y, and the dependent variable F2(Y) is the predicted traffic flow path distribution class determined by the feature vector Y.
In this embodiment, the step S2200 of obtaining the second mapping function between the second eigenvector and the traffic flow path distribution class may further include the following steps S2210 to S2220:
step S2210, taking the historical traffic flow track as a second training sample.
Step S2220, a second mapping function is obtained through training according to the vector value of the second feature vector of the second training sample and the traffic flow path distribution class actually corresponding to the second training sample.
In one embodiment, the steps S2210 to S2220 of training the second mapping function may be performed according to a preset training period. The training period may be set according to a specific application scenario or application requirements, and may be set to 1 day, for example.
In this embodiment, the second mapping function F2(y) may be obtained by various fitting means based on the vector value of the second feature vector of the training sample and the traffic flow path distribution class actually corresponding to the training sample. For example, the second mapping function F2(y) may be obtained by using any multiple linear regression model, which is not limited herein.
In one example, the multiple linear regression model may be a simple polynomial function reflecting the second mapping function F2(y), wherein each order coefficient of the polynomial function is unknown, and each order coefficient of the polynomial function may be determined by substituting a vector value of the second feature vector of the second training sample and a traffic flow path distribution class actually corresponding to the second training sample into the polynomial function, thereby obtaining the second mapping function F2 (y).
In another example, various regression models, such as an addition model, may be used to perform multiple rounds of training with the second vector value of the second feature vector of the second training sample and the traffic flow path distribution class actually corresponding to the second training sample as accurate samples, each round learns the residual after the last round of fitting, and the residual is controlled to a very low value by iterating T rounds, so that the resulting second mapping function F2(y) has very high accuracy. The addition model is, for example, LightGBM, GBDT, XGBoost, etc., and is not limited herein.
Step S2300, according to the second mapping function and the vector value of the second feature vector at the current time interval, obtaining a traffic flow distribution class corresponding to the preset area at the target time interval as a predicted traffic flow distribution class.
In this embodiment, according to the second mapping function between the second eigenvector and the traffic flow path distribution class obtained in step S2200, the vector value can be substituted into the second mapping function f (x) according to the vector value of the second eigenvector in the current time period, so as to obtain the predicted traffic flow path distribution class actually corresponding to the preset region in the target time period.
According to the embodiment of the invention, the predicted traffic flow path distribution class corresponding to the preset area in the target time period can be obtained according to the second eigenvector and the second mapping function. The second mapping function is obtained by training according to a large number of training samples, so that when the second mapping function is used for determining the distribution class of the predicted traffic flow path, the accuracy of the obtained distribution class of the predicted traffic flow path can be improved.
After step S1000 and step S2000 are executed, the following step S3000 is continuously executed.
And step S3000, correcting the predicted traffic flow path distribution information according to the predicted traffic flow path distribution class so that the corrected predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class.
In the case where the predicted traffic flow path distribution class is the set of the traffic flow path distribution information in all the historical periods belonging to the corresponding cluster, the predicted traffic flow path distribution information may be corrected according to the traffic flow path distribution information in all the historical periods belonging to the predicted traffic flow path distribution class. When the predicted traffic flow path distribution class is the unique identifier of the corresponding cluster, the traffic flow path distribution information of all historical time periods belonging to the predicted traffic flow path distribution class is determined through the unique identifier, and then the predicted traffic flow path distribution information is corrected according to the traffic flow path distribution information of all historical time periods belonging to the predicted traffic flow path distribution class.
In one example, modifying the predicted traffic path distribution information according to the predicted traffic path distribution class may include steps S3100 to S3300:
in step S3100, target traffic flow distribution information representing a cluster center of the predicted traffic flow distribution class is determined.
The target traffic flow path distribution information may be traffic flow path distribution information that is obtained according to the traffic flow path distribution information of all the historical time periods included in the predicted traffic flow path distribution class and that can represent the cluster center of the predicted traffic flow path distribution class, instead of the traffic flow path distribution information of any historical time period included in the predicted traffic flow path distribution class.
In one example, the step of determining the target traffic route distribution information may include steps S3110 to S3130:
step S3110, determining an optimization function between the target traffic flow value of each route and an index for measuring a cluster center according to the traffic flow value of each route in the traffic flow route distribution information included in the predicted traffic flow route distribution class.
Specifically, the index for measuring the cluster center of each path may be a sum of squares of differences between the target traffic flow value passing through the corresponding path and each traffic flow value passing through the corresponding path.
And S3120, determining a target traffic flow value passing through each path under the condition that the index for measuring the clustering center is minimum according to the optimization function corresponding to each path.
In one embodiment, a heuristic solver Louvain algorithm may be used to solve the optimization function corresponding to each path to obtain a target traffic flow value passing through each path.
Step S3130, obtaining target traffic flow path distribution information according to the target traffic flow value passing through each path.
Specifically, the target traffic flow value passing through each path may be integrated to obtain the target traffic flow path distribution information.
In step S3200, the distance between the predicted traffic flow path distribution information and the target traffic flow path distribution information is determined.
The manner of determining the distance between the predicted traffic route distribution information and the target traffic route distribution information may specifically refer to the manner of determining the distance between every two pieces of historical traffic route distribution information in the foregoing steps S6231 to S6233, which is not described herein again.
And step S3300, according to the distance between the predicted traffic flow path distribution information and the target traffic flow path distribution information, correcting the predicted traffic flow path distribution information so that the corrected predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class.
The predicted traffic flow path distribution information may be corrected in such a manner that the distance between the corrected predicted traffic flow path distribution information and the target traffic flow path distribution information is smaller, according to the distance between the predicted traffic flow path distribution information and the target traffic flow path distribution information.
In one example, the step of modifying the predicted traffic flow path distribution information based on the distance between the predicted traffic flow path distribution information and the target traffic flow path distribution information so that the modified predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class may include steps S3310 to S3330:
step S3310, the distance between each piece of traffic flow path distribution information included in the predicted traffic flow path distribution class and the target traffic flow path distribution information is determined, respectively.
The manner of determining the distance between each piece of traffic route distribution information included in the predicted traffic route distribution class and the target traffic route distribution information may specifically refer to the manner of determining the distance between each two pieces of historical traffic route distribution information in steps S6231 to S6233, which is not described herein again.
Step S3320, a maximum value of the distance between each piece of traffic flow path distribution information and the target traffic flow path distribution information is determined.
In step S3330, the predicted traffic flow path distribution information is corrected so that the distance between the corrected predicted traffic flow path distribution information and the target traffic flow path distribution information is less than or equal to the maximum value.
If the distance between the corrected predicted traffic flow path distribution information and the target traffic flow path distribution information is smaller than or equal to the maximum value, it can be indicated that the corrected predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class.
In one example, the processing method may further include, before performing step S3000: determining whether the predicted traffic flow path distribution information belongs to a predicted traffic flow path distribution class, if so, correcting the predicted traffic flow path distribution information according to the predicted traffic flow path distribution class; if not, step S3000 is executed to modify the predicted traffic flow path distribution information according to the predicted traffic flow path distribution class, so that the modified predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class.
In this way, the traffic flow path distribution information of the preset area target time period is predicted by the processing method of the embodiment, so that the finally obtained corrected predicted traffic flow path distribution information can be more accurate.
In one example, after the predicted traffic route distribution information is corrected in step S3000, traffic control may be performed on the preset area based on the corrected predicted traffic route distribution information. Specifically, the traffic manager can be helped to decide the signal lamp optimization regulation and control scheme in advance according to the corrected predicted traffic flow path distribution information. Therefore, the traffic manager can be helped to more actively specify or adjust the traffic management scheme, and the quality and decision efficiency of traffic management are improved.
Specifically, the specific manner of performing traffic control on the preset area may include: and correspondingly controlling at least one of the signal period duration of the signal lamps in the preset area, the green signal ratio of at least one phase and the phase difference of at least one phase of the intersections.
The phase in this embodiment is known in the art. For example, it may include that within a signal cycle, a sequence of signal states of one or several traffic flows with the same signal light color is called a phase. The phases are divided according to the time sequence of the signal display obtained by the traffic flow, and there are several phases according to different time sequence arrangements. Each control state corresponds to a different set of lamp color combinations, called a phase. In short, one phase is also referred to as one control state. For another example, the signal display states corresponding to a group of traffic flows which do not conflict with each other and simultaneously obtain the right of way may be referred to as phases. It can be seen that the phases are divided according to the alternation of the right of way in the crossing in one signal period.
The signal period duration comprises the time required for the signal to run for one cycle, including the change of the signal lamp, and is equal to the sum of the green, yellow and red lamp times; and also equal to the sum of the green and yellow lamp times (which are typically fixed) required for all phases.
The split ratio is the proportional time available for the vehicle to pass through during one period of the signal light. I.e. the ratio of the green time of a certain phase to the period duration. The green time may be an actual green time or an effective green time.
The actual green light time may be the time taken for the green light to turn on until the green light is turned off. Effective green time: including the actual vehicle transit time that is effectively utilized, which is equal to the sum of the green light time and the yellow light time minus the loss time. The lost time comprises two parts, namely the time when the green light signal is turned on and the vehicle is started; when the green light is turned off and the yellow light is turned on, only the vehicle passing the stop line can pass continuously, so that a part of the lost time is the delay time of the acceleration ending of the actual green light time minus the starting time. The end lag time is the fraction of the yellow lamp time that is effectively utilized. The loss time for each phase is the difference between the start delay time and the end delay time.
Phase difference: the two signal intersections refer to the difference between the start times of green (or red) lights in the same phase of two adjacent intersections.
The above definitions are only for exemplifying the description of the specific embodiments of the present invention and are not to be construed as limiting the scope of the invention.
For example, in the corrected predicted traffic route distribution information obtained from the preset area as shown in fig. 4, if the traffic flow values of the passing route C and the route D are smaller than the traffic flow values of the passing route a and the route F, for the intersection of the route C and the route a, the manner of traffic control over the preset area in the target time period may include: the green signal ratio of the intersection in the phase corresponding to the path A and the path F is set to be larger than that in the phase corresponding to the path C and the path D.
For another example, in the corrected predicted traffic flow path distribution information obtained according to the preset area shown in fig. 4, if the traffic flow values passing through the path a and the path F are much larger than the traffic flow values passing through other paths, the manner of performing traffic control on the preset area in the target time period may include: the intersections are provided with phase differences in phase corresponding to the route A and the route F, so that the vehicles can enjoy the green wave effect of passing through the intersections without stopping when traveling along the route A or the route F.
In one example, after the target period of time has elapsed, the processing method may further include steps S7110 to S7120:
and step S7110, acquiring the traffic flow track matched with each path in a future time period as a new first training sample of the corresponding path.
Step S7120, a first mapping function of each path is modified according to the vector value of the first feature vector of the new first training sample of each path and the actual vehicle flow value of each path passing through the corresponding path in the target time period corresponding to the new first training sample of each path.
According to the embodiment of the invention, after the target time interval passes, the actual traffic flow track of the preset area matched with each path in the target time interval can be obtained and used as a new training sample of the corresponding path to respectively correct the first mapping function of the corresponding path, that is, the new training samples are added, and the first mapping function of each path is respectively retrained, so that the prediction of the traffic flow value passing through each path is more and more accurate.
In one example, after the target period of time has elapsed, the processing method may further include steps S7210 to S7220:
step S7210, acquiring an actual traffic flow track in a target time period as a new second training sample.
Step S7220, the second mapping function is modified according to the vector value of the second feature vector of the new second training sample and the traffic flow path distribution class actually corresponding to the new second training sample.
According to the embodiment of the invention, after the target time interval passes, the actual traffic flow trajectory of the preset area in the target time interval can be obtained, the actual traffic flow trajectory is used as a new training sample to modify the second mapping function, that is, the new training samples are added, and the second mapping function is retrained, so that the prediction of the corresponding traffic flow path distribution class is more and more accurate.
< example >
Fig. 8 is a method for processing traffic route distribution information, and the example describes a method for processing traffic route distribution information, taking the preset area shown in fig. 4 to 7 as an example. The processing method may include steps S8001 to S8011:
step S8001, a path in the preset area is acquired.
In step S8002, the selected first vector feature is acquired.
Step S8003, a first mapping function between the first feature vector and the traffic flow value passing through each path is obtained.
Step S8004, according to the first mapping function corresponding to each path and the vector value of the first feature vector in the current time period, respectively determining the predicted traffic flow values passing through the corresponding paths in the target time period.
In this example, the target period may be a future period.
And step S8005, obtaining the distribution information of the predicted traffic flow paths of the preset area in the target time period according to the predicted traffic flow value passing through each path in the target time period.
Step S8006, traffic flow path distribution information of the preset area in a plurality of historical time periods is acquired as historical traffic flow path distribution information.
And step S8007, clustering the plurality of historical traffic flow path distribution information to obtain at least one traffic flow path distribution class.
Step S8008, the selected second feature vector is acquired.
Step S8009, a second mapping function between the second feature vector and the traffic flow path distribution class is obtained.
Step S8010, according to the second mapping function and the vector value of the second feature vector in the current time period, obtains a traffic flow path distribution class corresponding to the preset area in the target time period, as a predicted traffic flow path distribution class.
In step S8011, target traffic flow distribution information representing a cluster center of the predicted traffic flow distribution class is determined.
In step S8012, the maximum value of the distance between each piece of traffic flow path distribution information and the target traffic flow path distribution information is determined.
Step S8013 determines the distance between the predicted traffic flow path distribution information and the target traffic flow path distribution information.
Step S8014, the distance between each piece of traffic flow path distribution information included in the predicted traffic flow path distribution class and the target traffic flow path distribution information is determined, respectively.
In step S8015, the predicted traffic flow path distribution information is corrected such that the distance between the corrected predicted traffic flow path distribution information and the target traffic flow path distribution information is smaller than or equal to the maximum value.
The maximum value in this step is the maximum value obtained in step S8012.
< apparatus embodiment >
In the present embodiment, a processing apparatus 9000 of traffic route distribution information includes a distribution information prediction module 9100, a distribution class prediction module 9200, and a distribution information correction module 9300, as shown in fig. 9. The distribution information acquiring module 9100 is used for acquiring the predicted traffic flow path distribution information of a preset area in a target time period; the traffic flow path distribution information comprises paths in a preset area and traffic flow values passing through each path in a corresponding time period; the distribution type prediction module 9200 is configured to obtain a predicted traffic flow path distribution type corresponding to a preset area in a target time period; the traffic flow path distribution class comprises traffic flow path distribution information of at least one historical time period; the distribution information modification module 9300 is configured to modify the predicted traffic flow path distribution information according to the predicted traffic flow path distribution class, so that the modified predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class.
In one example, the distribution information prediction module 9100 can be further configured to:
the method comprises the steps of obtaining a path in a preset area;
respectively acquiring a predicted traffic flow value passing through each path in a target time period;
and acquiring the distribution information of the predicted traffic flow paths of the preset area in the target time period according to the predicted traffic flow value passing through each path in the target time period.
In one example, the respectively obtaining the predicted traffic flow values through each of the routes during the target time period includes:
taking each path as a target path in turn;
obtaining a selected first feature vector, wherein the first feature vector comprises a plurality of first features influencing the traffic flow value of the target path in the target time period; the plurality of first features includes a first traffic feature and a first environmental feature;
acquiring a first mapping function between the first characteristic vector and a traffic flow value passing through a target path;
and obtaining a predicted traffic flow value passing through the target path in the target time period according to the first mapping function and the vector value of the first characteristic vector in the current time period.
In one example, the first traffic characteristic includes at least one of traffic flow path distribution information of a preset area and traffic flow path distribution information around the preset area; and/or the first environmental characteristic comprises at least one of time, date, weather.
In one example, obtaining a first mapping function between the first eigenvector and a value of traffic flow through the target path comprises:
acquiring first training samples according to historical traffic flow tracks, wherein each first training sample comprises the historical traffic flow track matched with the target path;
and training to obtain a first mapping function according to the vector value of the first feature vector of the first training sample and the actual vehicle flow value which corresponds to the first training sample and passes through the target path.
In one example, the processing device 9000 may further comprise:
the module is used for acquiring an actual traffic flow track matched with a target path in a target time period and taking the actual traffic flow track as a new first training sample;
and the module is used for correcting the first mapping function according to the vector value of the first feature vector of the new first training sample and the actual vehicle flow value which corresponds to the new first training sample and passes through the target path in the target time interval.
In one example, the processing device 9000 may further comprise:
the module is used for acquiring traffic flow path distribution information of a preset area in a plurality of historical time periods as historical traffic flow path distribution information;
and the module is used for clustering the distribution information of the plurality of historical traffic flow paths to obtain at least one traffic flow path distribution class.
In one example, clustering the plurality of historical traffic flow path distribution information to obtain at least one traffic flow path distribution class includes:
determining the number of road segments contained in each path;
determining a traffic flow value passing through each path in a corresponding historical time period according to the distribution information of each historical traffic flow path;
determining the distance between every two pieces of historical traffic flow path distribution information according to the number of the road segments contained in each path and the traffic flow value passing through the corresponding path in each historical time period;
and clustering the plurality of historical traffic flow path distribution information according to the distance between every two pieces of historical traffic flow path distribution information to obtain at least one traffic flow path distribution class.
In one example, determining the distance between every two pieces of historical traffic flow path distribution information according to the number of segments included in each path and the traffic flow value passing through the corresponding path in each historical time period includes:
determining the road section flow sum corresponding to the distribution information of each historical traffic flow path according to the number of the road sections contained in each path and the traffic flow value passing through the corresponding path in each historical time period; the sum of the road section flow is the sum of traffic flow values passing through each road section in the corresponding time period;
determining a road section flow difference corresponding to each two pieces of historical traffic flow path distribution information according to the number of road sections contained in each path and the traffic flow value passing through the corresponding path in each historical time period; the road section flow difference is the sum of the difference of the traffic flow values passing through each road section in the corresponding two time periods;
and determining the distance between every two pieces of historical traffic flow path distribution information according to the sum of the road section flow corresponding to each piece of historical traffic flow path distribution information and the difference of the road section flow corresponding to every two pieces of historical traffic flow path distribution information.
In one example, clustering the plurality of pieces of historical traffic flow path distribution information according to a distance between every two pieces of historical traffic flow path distribution information to obtain at least one traffic flow path distribution class includes:
taking the distribution information of each traffic flow path as a node, and constructing a relational graph according to the distance between every two nodes;
splitting the relationship graph into at least one subgraph according to the distance between every two nodes;
and obtaining traffic flow path distribution classes corresponding to the sub-images one by one, and dividing traffic flow path distribution information corresponding to the nodes contained in each sub-image into the corresponding traffic flow path distribution classes.
In one example, taking each traffic flow path distribution information as a node, and constructing a relationship graph according to the distance between every two nodes includes:
and taking the distribution information of each traffic flow path as a node, and respectively connecting each node and a set number of nodes closest to the node to obtain a relational graph.
In one example, splitting the relationship graph into at least one subgraph according to the distance between every two nodes comprises:
truncating the connection between two nodes whose distance exceeds a preset distance threshold to split the relational graph into at least one sub-graph.
In one example, the distribution class prediction module 9200 can also be configured to:
obtaining a selected second feature vector, wherein the second feature vector comprises a plurality of second features which affect the traffic flow path distribution class corresponding to the preset area in the target time period; the plurality of second features includes a second traffic feature and a second environmental feature;
acquiring a second mapping function between the second feature vector and the traffic flow path distribution class;
and obtaining a traffic flow path distribution class corresponding to the preset area in the target time interval according to the second mapping function and the vector value of the second characteristic vector in the current time interval, and using the traffic flow path distribution class as a predicted traffic flow path distribution class.
In one example, the second traffic characteristic includes at least one of traffic flow path distribution information of a preset area and traffic flow path distribution information around the preset area; and/or the second environmental characteristic comprises at least one of time, date, weather.
In one example, obtaining the second mapping function between the second eigenvector and the traffic flow path distribution class includes:
taking the historical traffic flow track as a second training sample;
and training to obtain a second mapping function according to the vector value of the second feature vector of the second training sample and the traffic flow path distribution class actually corresponding to the second training sample.
In one example, the processing device may further include:
a module for obtaining an actual traffic flow track in a target time period as a new second training sample;
and the module is used for correcting the second mapping function according to the vector value of the second feature vector of the new second training sample and the traffic flow path distribution class actually corresponding to the new second training sample.
In one example, the distribution information modification module 9300 can be further configured to:
determining target traffic flow path distribution information of a clustering center representing a predicted traffic flow path distribution class;
determining the distance between the predicted traffic flow path distribution information and the target traffic flow path distribution information;
and correcting the predicted traffic flow path distribution information according to the distance between the predicted traffic flow path distribution information and the target traffic flow path distribution information, so that the corrected predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class.
In one example, modifying the predicted traffic flow path distribution information so that the modified predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class according to the distance between the predicted traffic flow path distribution information and the target traffic flow path distribution information includes:
respectively determining the distance between each traffic flow path distribution information contained in the predicted traffic flow path distribution class and the target traffic flow path distribution information;
determining the maximum value of the distance between each traffic flow path distribution information and the target traffic flow path distribution information;
and correcting the predicted traffic flow path distribution information so that the distance between the corrected predicted traffic flow path distribution information and the target traffic flow path distribution information is less than or equal to the maximum value.
In one example, determining target traffic path distribution information representative of a cluster center of the predicted traffic path distribution class includes:
determining an optimization function between a target traffic flow value passing through each path and an index measuring a clustering center according to the traffic flow value passing through each path in traffic flow path distribution information contained in the predicted traffic flow path distribution class;
determining a target traffic flow value passing through each path under the condition that the index for measuring the clustering center is minimum according to the optimization function corresponding to each path;
and obtaining target traffic flow path distribution information according to the target traffic flow value passing through each path.
In one example, the processing device 9000 may further comprise:
and the module is used for carrying out traffic control on the preset area according to the corrected predicted traffic flow path distribution information.
It will be appreciated by those skilled in the art that the processing device 9000 of traffic path distribution information may be implemented in various ways. For example, the processing device 9000 of the traffic path distribution information may be realized by an instruction configuration processor. For example, the processing device 9000 that can store instructions in the ROM and read instructions from the ROM into the programmable device when starting the apparatus realizes the traffic path distribution information. For example, the processing device 9000 of the traffic path distribution information may be solidified into a dedicated device (e.g., ASIC). The processing device 9000 of the traffic distribution path information may be divided into units independent of each other, or may be implemented by combining them together. The processing device 9000 of the traffic route distribution information may be implemented by one of the various implementations described above, or may be implemented by a combination of two or more of the various implementations described above.
In this embodiment, the traffic route distribution information processing device 9000 may have various implementation forms, for example, the traffic route distribution information processing device 9000 may be any functional module running in a software product or an application program providing the traffic route distribution information processing service, or a peripheral insert, a plug-in, a patch, or the like of the software product or the application program, or may be the software product or the application program itself.
< electronic apparatus >
In this embodiment, an electronic device 7000 is also provided. The electronic device 7000 may be the server 1100 shown in fig. 1, or may be the terminal device 1200 shown in fig. 2.
In one aspect, as shown in fig. 10, the electronic device 7000 may include the aforementioned processing device 9000 of traffic route distribution information, configured to implement the method for processing traffic route distribution information according to any embodiment of the present invention.
In another aspect, as shown in FIG. 11, electronic device 7000 may also include processor 7100 and memory 7200, the memory 7200 for storing executable instructions; the processor 7100 is configured to control the electronic device 7000 to operate according to the instruction to perform the method of processing the traffic route distribution information according to any of the embodiments of the present invention.
< computer-readable storage Medium >
In the present embodiment, there is also provided a computer-readable storage medium on which a computer program is stored, the computer program, when being executed by a processor, implementing a method of processing traffic path distribution information according to any embodiment of the present invention.
The present invention may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therewith for causing a processor to implement various aspects of the present invention.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations of the present invention may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), with state information of computer-readable program instructions, which can execute the computer-readable program instructions.
Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. 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 processor 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 processor 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 storing the instructions comprises 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 flowchart 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 embodiments of the present invention. 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. It is well known to those skilled in the art that implementation by hardware, by software, and by a combination of software and hardware are equivalent.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments 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 described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.

Claims (23)

1. A method for processing traffic flow path distribution information comprises the following steps:
acquiring the distribution information of a predicted traffic flow path of a preset area in a target time period; the traffic flow path distribution information comprises paths in the preset area and traffic flow values passing through each path in a corresponding time period;
acquiring a predicted traffic flow path distribution class corresponding to the preset area in the target time period; the traffic flow path distribution class comprises a clustering result obtained by clustering traffic flow path distribution information of at least one historical time period;
and correcting the predicted traffic flow path distribution information according to the predicted traffic flow path distribution class so that the corrected predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class.
2. The processing method according to claim 1, wherein the step of obtaining the predicted traffic flow path distribution information of the preset area in the target time period comprises:
acquiring a path in the preset area;
respectively acquiring a predicted traffic flow value passing through each path in a target time period;
and acquiring the distribution information of the predicted traffic flow paths of the preset area in the target time period according to the predicted traffic flow value passing through each path in the target time period.
3. The processing method according to claim 2, wherein each path within the preset area is taken as a target path in turn,
the step of obtaining a predicted traffic flow value through the target route at a target time period includes:
obtaining a selected first feature vector, wherein the first feature vector comprises a plurality of first features influencing the traffic flow value of the target path in a target time period; the plurality of first features includes a first traffic feature and a first environmental feature;
acquiring a first mapping function between the first characteristic vector and a traffic flow value passing through the target path;
and obtaining a predicted traffic flow value passing through the target path in a target time period according to the first mapping function and the vector value of the first characteristic vector in the current time period.
4. The processing method according to claim 3, wherein the first traffic characteristic includes at least one of traffic flow path distribution information of the preset area and traffic flow path distribution information of the periphery of the preset area; and/or, the first environmental characteristic comprises at least one of time, date, weather.
5. A processing method according to claim 3, wherein the step of obtaining a first mapping function between the first eigenvector and a value of the traffic flow passing through the target path comprises:
acquiring first training samples according to historical traffic flow tracks, wherein each first training sample comprises the historical traffic flow track matched with the target path;
and training to obtain the first mapping function according to the vector value of the first feature vector of the first training sample and the actual vehicle flow value which corresponds to the first training sample and passes through the target path.
6. The processing method of claim 5, wherein the processing method further comprises:
acquiring an actual traffic flow track matched with the target path in the target time period, and taking the actual traffic flow track as a new first training sample;
and correcting the first mapping function according to the vector value of the first feature vector of the new first training sample and the actual vehicle flow value which passes through the target path in the target time interval and corresponds to the new first training sample.
7. The processing method according to claim 1, wherein the obtaining of the predicted traffic flow path distribution class corresponding to the preset area in the target time period further comprises:
acquiring traffic flow path distribution information of the preset area in a plurality of historical time periods as historical traffic flow path distribution information;
clustering the historical traffic flow path distribution information to obtain at least one traffic flow path distribution class;
the obtaining of the predicted traffic flow path distribution class corresponding to the preset area in the target time period includes: and acquiring the traffic flow path distribution class corresponding to the preset area in the target time period from the at least one traffic flow path distribution class as the predicted traffic flow path distribution class.
8. The processing method of claim 7, wherein the step of clustering the plurality of historical traffic path distribution information to obtain at least one traffic path distribution class comprises:
determining the number of road segments contained in each path;
determining a traffic flow value passing through each path in a corresponding historical time period according to the distribution information of each historical traffic flow path;
determining the distance between every two pieces of historical traffic flow path distribution information according to the number of the road segments contained in each path and the traffic flow value passing through the corresponding path in each historical time period;
and clustering the plurality of historical traffic flow path distribution information according to the distance between every two pieces of historical traffic flow path distribution information to obtain at least one traffic flow path distribution class.
9. The processing method according to claim 8, wherein the step of determining the distance between every two pieces of historical traffic flow path distribution information according to the number of segments included in each path and the traffic flow value passing through the corresponding path in each historical period comprises:
determining the road section flow sum corresponding to the distribution information of each historical traffic flow path according to the number of the road sections contained in each path and the traffic flow value passing through the corresponding path in each historical time period; wherein the sum of the road section flow rates is the sum of traffic flow values passing through each road section in the corresponding time period;
determining a road section flow difference corresponding to each two pieces of historical traffic flow path distribution information according to the number of road sections contained in each path and the traffic flow value passing through the corresponding path in each historical time period; the road section flow difference is the sum of the differences of the traffic flow values passing through each road section in the corresponding two time periods;
and determining the distance between every two pieces of historical traffic flow path distribution information according to the sum of the road section flow corresponding to each piece of historical traffic flow path distribution information and the difference of the road section flow corresponding to every two pieces of historical traffic flow path distribution information.
10. The processing method according to claim 8, wherein the step of clustering the plurality of pieces of historical traffic flow path distribution information according to the distance between every two pieces of historical traffic flow path distribution information to obtain at least one traffic flow path distribution class comprises:
taking the distribution information of each traffic flow path as a node, and constructing a relational graph according to the distance between every two nodes;
splitting the relationship graph into at least one sub-graph according to the distance between every two nodes;
and obtaining traffic flow path distribution classes corresponding to the sub-images one by one, and dividing traffic flow path distribution information corresponding to the nodes contained in each sub-image into the corresponding traffic flow path distribution classes.
11. The processing method according to claim 10, wherein the step of constructing a relationship graph according to the distance between each two nodes with each traffic flow path distribution information as one node comprises:
and taking the distribution information of each traffic flow path as a node, and respectively connecting each node and a set number of nodes with the shortest distance to the node to obtain the relational graph.
12. The processing method according to claim 11, wherein the step of splitting the relationship graph into at least one subgraph according to the distance between each two nodes comprises:
truncating the connection between two nodes with a distance exceeding a preset distance threshold value so as to split the relational graph into at least one sub-graph.
13. The processing method according to claim 1, wherein the step of obtaining the predicted traffic flow path distribution class corresponding to the preset area in the target time period includes:
obtaining a selected second feature vector, wherein the second feature vector comprises a plurality of second features which influence the traffic flow path distribution class corresponding to the preset area in a target time period; the plurality of second features includes a second traffic feature and a second environmental feature;
acquiring a second mapping function between the second feature vector and the traffic flow path distribution class;
and obtaining a traffic flow path distribution class corresponding to the preset area in the target time interval according to the second mapping function and the vector value of the second feature vector in the current time interval, and using the traffic flow path distribution class as the predicted traffic flow path distribution class.
14. The processing method according to claim 13, wherein the second traffic characteristic includes at least one of traffic flow path distribution information of the preset area and traffic flow path distribution information of a periphery of the preset area; and/or the second environmental characteristic comprises at least one of time, date, weather.
15. The process of claim 13, wherein said step of obtaining a second mapping function between said second eigenvector and said traffic path distribution class comprises:
taking the historical traffic flow track as a second training sample;
and training to obtain the second mapping function according to the vector value of the second feature vector of the second training sample and the traffic flow path distribution class actually corresponding to the second training sample.
16. The processing method of claim 15, wherein the processing method further comprises:
acquiring an actual traffic flow track in the target time period as a new second training sample;
and correcting the second mapping function according to the vector value of the second eigenvector of the new second training sample and the traffic flow path distribution class actually corresponding to the new second training sample.
17. The processing method according to claim 1, wherein the step of modifying the predicted traffic flow path distribution information according to the predicted traffic flow path distribution class so that the modified predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class comprises:
determining target traffic flow path distribution information of a clustering center representing the predicted traffic flow path distribution class;
determining a distance between the predicted traffic flow path distribution information and the target traffic flow path distribution information;
and correcting the predicted traffic flow path distribution information according to the distance between the predicted traffic flow path distribution information and the target traffic flow path distribution information, so that the corrected predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class.
18. The processing method according to claim 17, wherein the step of modifying the predicted traffic flow path distribution information so that the modified predicted traffic flow path distribution information belongs to the predicted traffic flow path distribution class according to the distance between the predicted traffic flow path distribution information and the target traffic flow path distribution information comprises:
respectively determining the distance between each traffic flow path distribution information contained in the predicted traffic flow path distribution class and the target traffic flow path distribution information;
determining the maximum value of the distance between each traffic flow path distribution information and the target traffic flow path distribution information;
and correcting the predicted traffic flow path distribution information so that the distance between the corrected predicted traffic flow path distribution information and the target traffic flow path distribution information is smaller than or equal to the maximum value.
19. The process of claim 17, wherein the step of determining target traffic path distribution information representative of a cluster center of the predicted traffic path distribution class comprises:
determining an optimization function between a target traffic flow value passing through each path and an index measuring a clustering center according to the traffic flow value passing through each path in the traffic flow path distribution information contained in the predicted traffic flow path distribution class;
determining a target traffic flow value passing through each path under the condition that the index for measuring the clustering center is minimum according to the optimization function corresponding to each path;
and obtaining the target traffic flow path distribution information according to the target traffic flow value passing through each path.
20. The processing method according to any one of claims 1 to 19, wherein the processing method further comprises:
and carrying out traffic control on the preset area according to the corrected predicted traffic flow path distribution information.
21. A processing device for traffic route distribution information, comprising:
the distribution information prediction module is used for acquiring the predicted traffic flow path distribution information of a preset area in a target time interval; the traffic flow path distribution information comprises paths in the preset area and traffic flow values passing through each path in a corresponding time period;
the distribution type prediction module is used for acquiring a predicted traffic flow path distribution type corresponding to the preset area in the target time period; the traffic flow path distribution class comprises a clustering result obtained by clustering traffic flow path distribution information of at least one historical time period;
and the distribution information correction module is used for correcting the predicted traffic flow path distribution information according to the predicted traffic flow path distribution class so as to enable the corrected predicted traffic flow path distribution information to belong to the predicted traffic flow path distribution class.
22. An electronic device comprising the processing apparatus of claim 21; or, comprising a processor and a memory for storing executable instructions for controlling the processor to perform a processing method according to any one of claims 1 to 20.
23. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the processing method of any one of claims 1 to 20.
CN201910381137.9A 2019-05-08 2019-05-08 Method and device for processing traffic flow path distribution information and electronic equipment Pending CN111915877A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201910381137.9A CN111915877A (en) 2019-05-08 2019-05-08 Method and device for processing traffic flow path distribution information and electronic equipment
PCT/CN2020/086574 WO2020224445A1 (en) 2019-05-08 2020-04-24 Method and apparatus for processing traffic flow path distribution information, and electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910381137.9A CN111915877A (en) 2019-05-08 2019-05-08 Method and device for processing traffic flow path distribution information and electronic equipment

Publications (1)

Publication Number Publication Date
CN111915877A true CN111915877A (en) 2020-11-10

Family

ID=73050578

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910381137.9A Pending CN111915877A (en) 2019-05-08 2019-05-08 Method and device for processing traffic flow path distribution information and electronic equipment

Country Status (2)

Country Link
CN (1) CN111915877A (en)
WO (1) WO2020224445A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117612379A (en) * 2024-01-24 2024-02-27 山东华夏高科信息股份有限公司 Intelligent traffic flow prediction method and system

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2022157321A (en) * 2021-03-31 2022-10-14 トヨタ自動車株式会社 Traffic control system, traffic control method, and program
CN114463969B (en) * 2021-12-22 2023-05-16 高德软件有限公司 Mining method for traffic light cycle duration, electronic equipment and computer program product
CN114973659A (en) * 2022-05-12 2022-08-30 山东高速集团有限公司创新研究院 Method, device and system for detecting indirect event of expressway
CN115206092B (en) * 2022-06-10 2023-09-19 南京工程学院 Traffic prediction method of BiLSTM and LightGBM models based on attention mechanism
CN116453333B (en) * 2023-03-24 2024-04-16 阿波罗智联(北京)科技有限公司 Method for predicting main traffic flow path and model training method
CN116311941B (en) * 2023-03-24 2023-12-26 阿波罗智联(北京)科技有限公司 Main traffic flow path extraction method, device, equipment and medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103632542A (en) * 2012-08-27 2014-03-12 国际商业机器公司 Traffic information processing method, device and corresponding equipment
WO2015122729A1 (en) * 2014-02-17 2015-08-20 Samsung Electronics Co., Ltd. Method and apparatus for forecasting flow of traffic
CN106530762A (en) * 2016-12-26 2017-03-22 东软集团股份有限公司 Traffic signal control method and device
CN108492568A (en) * 2018-04-25 2018-09-04 南京邮电大学 A kind of Short-time Traffic Flow Forecasting Methods based on space-time characterisation analysis
WO2018214361A1 (en) * 2017-05-25 2018-11-29 Beijing Didi Infinity Technology And Development Co., Ltd. Systems and methods for improvement of index prediction and model building
CN109598936A (en) * 2018-12-18 2019-04-09 中国科学院地理科学与资源研究所 A kind of prediction of short-term traffic volume method based on dynamic STKNN model

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4743523B2 (en) * 2006-03-22 2011-08-10 住友電気工業株式会社 Prediction system for vehicle behavior at intersections
CN101789176B (en) * 2010-01-22 2013-09-04 天津市市政工程设计研究院 Forecasting method for port area short-time traffic flow under model of reservation cargo concentration in port
CN102693633B (en) * 2012-06-07 2014-03-12 浙江大学 Short-term traffic flow weighted combination prediction method
CN103839409B (en) * 2014-02-27 2015-09-09 南京大学 Based on the traffic flow modes method of discrimination of multibreak facial vision sensing cluster analysis
CN105788249B (en) * 2014-12-16 2018-09-28 高德软件有限公司 A kind of traffic flow forecasting method, prediction model generation method and device
CN105185115B (en) * 2015-09-07 2018-04-06 华迪计算机集团有限公司 A kind of traffic forecast method and forecasting system
CN107862864B (en) * 2017-10-18 2021-06-15 南京航空航天大学 Driving condition intelligent prediction estimation method based on driving habits and traffic road conditions
CN108629973A (en) * 2018-05-11 2018-10-09 四川九洲视讯科技有限责任公司 Road section traffic volume congestion index computational methods based on fixed test equipment

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103632542A (en) * 2012-08-27 2014-03-12 国际商业机器公司 Traffic information processing method, device and corresponding equipment
WO2015122729A1 (en) * 2014-02-17 2015-08-20 Samsung Electronics Co., Ltd. Method and apparatus for forecasting flow of traffic
CN106530762A (en) * 2016-12-26 2017-03-22 东软集团股份有限公司 Traffic signal control method and device
WO2018214361A1 (en) * 2017-05-25 2018-11-29 Beijing Didi Infinity Technology And Development Co., Ltd. Systems and methods for improvement of index prediction and model building
CN108492568A (en) * 2018-04-25 2018-09-04 南京邮电大学 A kind of Short-time Traffic Flow Forecasting Methods based on space-time characterisation analysis
CN109598936A (en) * 2018-12-18 2019-04-09 中国科学院地理科学与资源研究所 A kind of prediction of short-term traffic volume method based on dynamic STKNN model

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117612379A (en) * 2024-01-24 2024-02-27 山东华夏高科信息股份有限公司 Intelligent traffic flow prediction method and system
CN117612379B (en) * 2024-01-24 2024-03-29 山东华夏高科信息股份有限公司 Intelligent traffic flow prediction method and system

Also Published As

Publication number Publication date
WO2020224445A1 (en) 2020-11-12

Similar Documents

Publication Publication Date Title
CN111915877A (en) Method and device for processing traffic flow path distribution information and electronic equipment
CN111721317B (en) Method and device for generating navigation information
CN110020913A (en) Products Show method, equipment and storage medium
CN111210625B (en) Traffic control method and device and electronic equipment
CN104052811A (en) Service scheduling method and device and system
CN112683287A (en) Path generation method and device, electronic equipment and storage medium
JP6613475B2 (en) Route inquiry method, apparatus, device, and non-volatile computer storage medium
CN113808400B (en) Method, device, equipment and medium for displaying traffic flow migration situation
US20210342749A1 (en) Adaptive asynchronous federated learning
Liu et al. Popular route planning with travel cost estimation
US20170030723A1 (en) Simplification of trajectory representation
US10607481B2 (en) Dynamic road width division for adaptive road-space utilization
CN113760971A (en) Method, computing device and storage medium for retrieving data of a graph database
CN111768615A (en) Intelligent traffic optimization technology with high-definition map
Cabannes et al. Measuring regret in routing: assessing the impact of increased app usage
US9826039B2 (en) Configurable communication systems and methods for communication
Chen et al. Traffic flow guidance algorithm in intelligent transportation systems considering the effect of non-floating vehicle
US20140297243A1 (en) Traffic simulation method, program, and system
CN113129614B (en) Traffic control method and device and electronic equipment
CN111915875A (en) Method and device for processing traffic flow path distribution information and electronic equipment
CN113705827B (en) Model evaluation method and device and electronic equipment
CN112652161B (en) Method and device for processing traffic flow path distribution information and electronic equipment
CN111564047A (en) Signal control area segmentation method and device and electronic equipment
Golasowski et al. Alternative paths reordering using probabilistic time-dependent routing
WO2020147600A1 (en) Traffic control method, apparatus, and electronic device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination