CN117198040A - Intersection traffic information acquisition method and device, electronic equipment and readable storage medium - Google Patents
Intersection traffic information acquisition method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN117198040A CN117198040A CN202311013772.4A CN202311013772A CN117198040A CN 117198040 A CN117198040 A CN 117198040A CN 202311013772 A CN202311013772 A CN 202311013772A CN 117198040 A CN117198040 A CN 117198040A
- Authority
- CN
- China
- Prior art keywords
- target
- traffic
- duration
- intersection
- sample
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012549 training Methods 0.000 claims description 44
- 238000003062 neural network model Methods 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 12
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 14
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 206010021033 Hypomenorrhoea Diseases 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Abstract
The disclosure provides a method and a device for acquiring intersection traffic information, electronic equipment and a readable storage medium, and relates to the technical fields of artificial intelligence such as deep learning, automatic driving, big data and cloud service. The method for acquiring the intersection traffic information comprises the following steps: acquiring target track characteristics and target traffic characteristics according to the target moment and the target intersection; acquiring target estimated passage time length corresponding to the target intersection according to the current navigation information and the target track characteristics; and acquiring traffic information corresponding to the target intersection according to the target estimated traffic duration and the target traffic characteristics. The method and the device can simplify the acquisition steps of the intersection traffic information, improve the acquisition accuracy and the acquisition efficiency of the intersection traffic information, and further enhance the driving safety.
Description
Technical Field
The disclosure relates to the technical field of data processing, in particular to the technical field of artificial intelligence such as deep learning, automatic driving, big data, cloud service and the like. Provided are a method and a device for acquiring intersection traffic information, an electronic device and a readable storage medium.
Background
The driving navigation user has strong demands on whether the traffic light can pass through the intersection before the traffic light, for example, the normal running speed can normally pass through the traffic light, acceleration and deceleration actions are not needed, and if the green light time is not too much, the driving navigation user slightly accelerates to reduce the actions of waiting for the traffic light once. The average time length of the lamps of all users is reduced, so that the overall traffic efficiency of urban road traffic can be improved.
Disclosure of Invention
According to a first aspect of the present disclosure, there is provided a method for acquiring intersection traffic information, including: acquiring target track characteristics and target traffic characteristics according to the target moment and the target intersection; acquiring target estimated passage time length corresponding to the target intersection according to the current navigation information and the target track characteristics; and acquiring traffic information corresponding to the target intersection according to the target estimated traffic duration and the target traffic characteristics.
According to a second aspect of the present disclosure, there is provided an acquisition apparatus of intersection traffic information, including: the acquisition unit is used for acquiring target track characteristics and target traffic characteristics according to the target moment and the target intersection; the estimating unit is used for acquiring target estimated passage duration corresponding to the target intersection according to the current navigation information and the target track characteristics; and the processing unit is used for acquiring the traffic information corresponding to the target intersection according to the target estimated traffic duration and the target traffic characteristics.
According to a third aspect of the present disclosure, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described above.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method as described above.
According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method as described above.
According to the technical scheme, the method and the device for obtaining the traffic information of the target intersection can obtain the traffic information of the corresponding target intersection by combining the estimated traffic duration, the changing time of the traffic signal lamp of the target intersection is not required to be obtained, the step of obtaining the traffic information of the intersection can be simplified, the accuracy and the efficiency of obtaining the traffic information of the intersection are improved, and the driving safety is further improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram according to a first embodiment of the present disclosure;
FIG. 2 is a schematic diagram according to a second embodiment of the present disclosure;
FIG. 3 is a schematic diagram according to a third embodiment of the present disclosure;
FIG. 4 is a schematic diagram according to a fourth embodiment of the present disclosure;
FIG. 5 is a schematic diagram according to a fifth embodiment of the present disclosure;
fig. 6 is a block diagram of an electronic device for implementing a method of acquiring intersection traffic information according to an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram according to a first embodiment of the present disclosure. As shown in fig. 1, the method for acquiring intersection traffic information in this embodiment specifically includes the following steps:
s101, acquiring target track characteristics and target traffic characteristics according to target time and target intersections;
s102, acquiring target estimated traffic duration corresponding to the target intersection according to the current navigation information and the target track characteristics;
s103, acquiring traffic information corresponding to the target intersection according to the target estimated traffic duration and the target traffic characteristics.
According to the method for acquiring the traffic information of the intersection, firstly, the target track characteristic and the target traffic characteristic are acquired according to the target moment and the target intersection, then the target estimated traffic duration passing through the target intersection is acquired according to the current navigation information and the target track characteristic, and finally the traffic information of the corresponding target intersection is acquired according to the target estimated traffic duration and the target traffic characteristic.
The execution main body of the intersection traffic information acquiring method of the embodiment may be a terminal device with a navigation function, for example, a smart phone, a vehicle-mounted device, or a server that communicates with the terminal device with a navigation function.
If the execution subject is a terminal device that is performing navigation, in the embodiment, when executing S101, the current time may be taken as the target time when it is determined that the distance between the current position and the target intersection is less than or equal to the preset distance threshold, and then the target track feature and the target traffic feature are acquired according to the target intersection and the target time.
If the execution subject is a server, in the embodiment, when S101 is executed, it may be determined that, when the distance between the current position and the target intersection is less than or equal to the preset distance threshold, the current time is taken as the target time, and then a traffic information acquisition request is sent to the server, so that the server acquires the target track feature and the target traffic feature according to the current time and the target intersection.
Different trajectory characteristics or different traffic characteristics correspond to different times and different intersections, for example, intersection 1 at time 1 corresponds to trajectory characteristic a and intersection 2 at time 1 corresponds to trajectory characteristic B.
Therefore, in the embodiment, when executing S101, the track feature corresponding to the target time and the target intersection may be obtained as the target track feature according to the preset time and the corresponding relationship between the intersection and the feature (the track feature and the traffic feature), and the traffic feature corresponding to the target time and the target intersection may be obtained as the target traffic feature.
In this embodiment, the track features and the traffic features are extracted from the historical navigation track and the real-time navigation track passing through the corresponding intersections; therefore, the track features and the traffic features extracted from the historical navigation track and the real-time navigation track can be stored in the server, and the track features and the traffic features can be obtained from the server according to the target moment and the target intersection when needed.
According to the embodiment, corresponding historical navigation tracks and real-time navigation tracks can be obtained according to the target moment and the target intersection (for example, when the target moment is 8 am on the Wednesday, the navigation tracks in the period of 7:30-8:00 am on the Wednesday can be obtained to serve as the real-time navigation tracks, and the navigation tracks in the period of 7:30-8:00 am on each day of the Wednesday week are obtained to serve as the historical navigation tracks), so that target track features and target traffic features are extracted from the navigation tracks.
Specifically, the embodiment executes the target track feature acquired in S101, including road network information of the road where the track is located (for example, road width, road length, road speed limit, etc., which may be extracted from the historical navigation track or the real-time navigation track), road condition information of the road where the track is located (congestion, jogging or smoothness, which may be extracted from the real-time navigation track), a green light passing period of the track when the track passes through the intersection (which may be extracted from the historical navigation track or the real-time navigation track), a red light period of the track when the track lights at the intersection, etc. (which may be extracted from the historical navigation track or the real-time navigation track), etc.
The present embodiment executes the target traffic characteristics acquired in S101, including the parking probability of the track before the intersection (extracted from the history navigation track), the travel speed when the track passes through the intersection (extracted from the history navigation track), and the like.
It can be understood that the number of the target intersections in this embodiment may be one or more, that is, the next N intersections in the current navigation process may be taken as the target intersections in this embodiment, where N is a positive integer greater than or equal to 1.
After the step S101 of acquiring the target track characteristics and the target traffic characteristics is executed, the step S102 of acquiring the target estimated traffic duration of the corresponding target intersection according to the current navigation information and the target track characteristics is executed; the estimated passage duration is the duration required by a user to pass through a target intersection according to the current navigation track when the user starts at the target moment.
Specifically, in the embodiment, when S102 is executed to obtain the target estimated passage duration of the corresponding target intersection according to the current navigation information and the target track feature, the following optional implementation manners may be adopted: acquiring initial estimated traffic duration of a corresponding target intersection; according to the current navigation information, the target track characteristics and the initial estimated traffic duration, the target estimated traffic duration of the corresponding target intersection is obtained, and the current navigation information in the embodiment is steering information (left turn, straight run or right turn) of the current navigation track.
When the step S102 is executed to obtain the initial estimated passage duration of the corresponding target intersection, the embodiment may use the preset estimated passage duration corresponding to the target intersection as the initial estimated passage duration; the existing method for estimating the traffic duration can also be used for acquiring initial estimated traffic duration according to the navigation track; the embodiment may acquire the initial estimated passage duration according to the passage law extracted from the navigation tracks (e.g., the real-time navigation track and the historical navigation track) when executing S102.
That is, in this embodiment, the initial estimated traffic duration is first obtained, then the target estimated traffic duration is obtained according to the three types of information including the initial estimated traffic duration, the current navigation information and the target track feature, and the accuracy of the obtained target estimated traffic duration can be improved by using richer data.
It can be understood that if the execution body is a server, in the embodiment, when executing S102, the server may further acquire current navigation information sent by the terminal device, where the current navigation information may further include driving speed information, route information, and other information besides the steering information of the current navigation track.
In the embodiment, when executing S102 to obtain the target estimated traffic duration of the corresponding target intersection according to the current navigation information, the target track feature and the initial estimated traffic duration, the following optional implementation manners may be adopted: inputting current navigation information, target track characteristics and initial estimated traffic duration into a duration estimation model, and taking an output result of the duration estimation model as a target estimated traffic duration; the duration estimation model in this embodiment is obtained by training in advance.
In this embodiment, after executing S102 to obtain the target estimated passage duration of the corresponding target intersection, executing S103 to obtain the passage information of the corresponding target intersection according to the target estimated passage duration and the target passage feature.
The traffic information of the corresponding target intersection obtained in S103 may include information about whether the traffic light can pass through the target intersection, and may further include a driving speed interval when the traffic light cannot pass through the target intersection.
In the embodiment, when executing S103 to obtain the traffic information of the corresponding target intersection according to the target estimated traffic duration and the target traffic characteristics, the following optional implementation manners may be adopted: and inputting the target estimated traffic duration and the target traffic characteristics into an intersection traffic model, and taking the output result of the intersection traffic model as traffic information of the corresponding target intersection.
It can be understood that if there are multiple target intersections in the present embodiment, when executing S103, the target estimated traffic duration and the target traffic characteristics corresponding to different target intersections are respectively input into the intersection traffic model, so as to obtain traffic information output by the intersection traffic model for each target intersection.
In this embodiment, after S103 is executed to obtain the traffic information of the corresponding target intersection, the obtained traffic information may be displayed, so that the user may more intuitively obtain the information whether the user can pass through one or more intersections by using a green light.
It can be understood that, if the execution subject is a server, in this embodiment, after S103 is executed to obtain the traffic information of the corresponding target intersection, the obtained traffic information is sent to the terminal device, so that the terminal device displays the traffic information corresponding to the target intersection in the navigation interface; if the execution subject is a terminal device, the embodiment may directly display the traffic information of the corresponding target intersection in the navigation interface after executing S103.
Fig. 2 is a schematic diagram according to a second embodiment of the present disclosure. As shown in fig. 2, the method for obtaining intersection traffic information in this embodiment may further include the following:
s201, acquiring a first training set, wherein the first training set comprises a plurality of sample navigation tracks and actual passing time lengths of the plurality of sample navigation tracks;
s202, acquiring sample track characteristics and first estimated passage duration of the plurality of sample navigation tracks according to the plurality of sample navigation tracks;
and S203, training a first neural network model by using the sample track characteristics, the first estimated passage duration, the navigation information and the actual passage duration of the plurality of sample navigation tracks to obtain a duration estimated model.
In the present embodiment, when S202 is executed, the track feature extracted from each sample navigation track may be used as a sample track feature corresponding to the sample navigation track; in addition, the sample navigation tracks in the present embodiment correspond to different moments and different road openings.
In the embodiment, when executing S202, the existing method for estimating the traffic duration may be used to obtain the first estimated traffic duration according to the sample navigation track.
In the embodiment, when executing S203, training the first neural network model by using the sample track features of the plurality of sample navigation tracks, the first estimated passage duration, the navigation information and the actual passage duration to obtain the duration estimated model, the optional implementation manners may be: respectively inputting sample track characteristics, first estimated passing time length and navigation information (steering information of the navigation tracks) of a plurality of sample navigation tracks into a first neural network model to obtain second estimated passing time length output by the first neural network model for each sample navigation track; obtaining a first loss function value according to the second estimated passage duration and the actual passage duration of the plurality of sample navigation tracks; and adjusting parameters of the first neural network model according to the first loss function value to obtain a duration estimation model.
In addition, before executing S203 to train the first neural network model, the embodiment may further compare the first estimated traffic duration with the actual traffic duration, and reject the sample navigation track corresponding to the current first estimated traffic duration when determining that the difference between the first estimated traffic duration and the actual traffic duration is greater than or equal to the preset threshold, that is, training the neural network model without using data corresponding to the sample navigation track; the weight of the loss function value obtained by calculating the sample navigation track can be adjusted, for example, the weight is adjusted to a preset weight value (for example, 0.1), so that the effect of the sample navigation track in the training process is reduced.
Fig. 3 is a schematic diagram according to a third embodiment of the present disclosure. As shown in fig. 3, the method for obtaining intersection traffic information in this embodiment may further include the following:
s301, acquiring a second training set, wherein the second training set comprises a plurality of sample navigation tracks and actual traffic information of the plurality of sample navigation tracks;
s302, acquiring sample traffic characteristics and sample estimated traffic duration of the plurality of sample navigation tracks according to the plurality of sample navigation tracks;
S303, training a second neural network model by using the sample traffic characteristics, the sample estimated traffic duration and the actual traffic information of the plurality of sample navigation tracks to obtain an intersection traffic model.
In the embodiment, when executing the step S302, firstly, sample track features and first estimated passage duration can be obtained according to a sample navigation track, then the sample track features, the first estimated passage duration and navigation information are input into a duration estimation model, and an output result of the duration estimation model is used as a sample estimated passage duration; in addition, in the embodiment, when executing S302, the preset estimated traffic duration may be used as the sample estimated traffic duration.
In the embodiment, when executing S303, training the second neural network model by using the sample traffic characteristics, the sample estimated traffic duration and the actual traffic information of the plurality of sample navigation tracks to obtain the intersection traffic model, optional implementation manners may be: respectively inputting sample traffic characteristics and sample estimated traffic duration of a plurality of sample navigation tracks into a second neural network model to obtain predicted traffic information output by the second neural network model for each sample navigation track; obtaining a second loss function value according to the predicted traffic information and the actual traffic information of the plurality of sample navigation tracks; and adjusting parameters of the second neural network model according to the second loss function value to obtain an intersection passing model.
It can be understood that the duration estimation model and the intersection traffic model in this embodiment may be two models that are independent of each other, or may be two calculation modules that are located under the same model architecture.
Fig. 4 is a schematic diagram according to a fourth embodiment of the present disclosure. Fig. 4 is a block diagram showing an acquisition method of intersection traffic information according to the present embodiment: s401, acquiring historical navigation behaviors and real-time navigation behaviors in a user navigation process; s402, acquiring a historical navigation track and a real-time navigation track; s403, extracting a history passing rule from the history navigation track, and extracting a real-time passing rule from the real-time navigation data; s404, acquiring initial estimated traffic duration according to a historical traffic rule and a real-time traffic rule; meanwhile, track characteristics (road network information, road condition information, green light passing time period, red light and other light time periods and the like) and passing characteristics (parking probability, running speed and the like) are extracted from the historical navigation track and the real-time navigation track; s405, inputting the track characteristics and the steering information into a duration estimation model to obtain a target estimated passage duration output by the duration estimation model; s406, inputting the target estimated traffic duration and the traffic characteristics into an intersection traffic model, and obtaining traffic information output by the intersection traffic model, such as whether a green light can pass through a target intersection, a driving speed interval under the condition that the green light cannot pass through the target intersection, and the like.
Fig. 5 is a schematic diagram according to a fifth embodiment of the present disclosure. As shown in fig. 5, the intersection traffic information acquiring apparatus 500 of the present embodiment includes:
the acquiring unit 501 is configured to acquire a target track feature and a target traffic feature according to a target moment and a target intersection;
the estimating unit 502 is configured to obtain a target estimated passage duration corresponding to the target intersection according to the current navigation information and the target track feature;
the processing unit 503 is configured to obtain traffic information corresponding to the target intersection according to the target estimated traffic duration and the target traffic feature.
Different trajectory characteristics or different traffic characteristics correspond to different times and different intersections, for example, intersection 1 at time 1 corresponds to trajectory characteristic a and intersection 2 at time 1 corresponds to trajectory characteristic B.
The acquiring unit 501 may acquire the trajectory feature corresponding to the target time and the target intersection as the target trajectory feature, and acquire the traffic feature corresponding to the target time and the target intersection as the target traffic feature according to the preset time and the intersection, and the correspondence relationship between the feature (the trajectory feature and the traffic feature).
In this embodiment, the track features and the traffic features are extracted from the historical navigation track and the real-time navigation track passing through the corresponding intersections; therefore, the acquisition unit 501 may store the trajectory features and the traffic features extracted from the history navigation trajectory and the real-time navigation trajectory in the server, and acquire them from the server according to the target time and the target intersection when necessary.
The obtaining unit 501 may also obtain a corresponding historical navigation track and a real-time navigation track according to the target moment and the target intersection (further extract the target track feature and the target traffic feature from the navigation track).
Specifically, the target track features acquired by the acquiring unit 501 include road network information of a road where the track is located (for example, road width, road length, road speed limit, etc. may be extracted from a historical navigation track or a real-time navigation track), road condition information of a road where the track is located (congestion, creep or smoothness, extracted from a real-time navigation track), a green light passing period of the track when the track passes through an intersection (may be extracted from a historical navigation track or a real-time navigation track), a red light period of the track when the track passes through a light such as an intersection (may be extracted from a historical navigation track or a real-time navigation track), and the like.
The target traffic characteristics acquired by the acquisition unit 501 include a parking probability of the trajectory before the intersection (extracted from the history navigation trajectory), a traveling speed when the trajectory passes through the intersection (extracted from the history navigation trajectory), and the like.
It can be understood that the number of the target intersections in this embodiment may be one or more, that is, the next N intersections in the current navigation process may be taken as the target intersections in this embodiment, where N is a positive integer greater than or equal to 1.
In this embodiment, after the obtaining unit 501 obtains the target track feature and the target traffic feature, the estimating unit 502 obtains the target estimated traffic duration of the corresponding target intersection according to the current navigation information and the target track feature; the estimated passage duration is the duration required by a user to pass through a target intersection according to the current navigation track when the user starts at the target moment.
Specifically, when the estimating unit 502 obtains the target estimated traffic duration of the corresponding target intersection according to the current navigation information and the target track feature, the following optional implementation manners may be adopted: acquiring initial estimated traffic duration of a corresponding target intersection; according to the current navigation information, the target track characteristics and the initial estimated traffic duration, the target estimated traffic duration of the corresponding target intersection is obtained, and the current navigation information in the embodiment is steering information (left turn, straight run or right turn) of the current navigation track.
When the estimating unit 502 obtains an initial estimated traffic duration corresponding to the target intersection, the estimated traffic duration corresponding to the target intersection may be used as the initial estimated traffic duration; the existing method for estimating the traffic duration can also be used for acquiring initial estimated traffic duration according to the navigation track; the estimating unit 502 may obtain the initial estimated passage duration according to the passage law extracted from the navigation tracks (for example, the real-time navigation track and the historical navigation track).
That is, the estimating unit 502 obtains the initial estimated traffic duration first, then obtains the target estimated traffic duration according to the three types of information including the initial estimated traffic duration, the current navigation information and the target track feature, and can improve the accuracy of the obtained target estimated traffic duration by using richer data.
It may be understood that if the execution subject is a server, the estimating unit 502 may further obtain current navigation information sent by the terminal device, where the current navigation information may further include driving speed information, route information, and the like, in addition to the steering information of the current navigation track.
When the estimating unit 502 obtains the target estimated traffic duration of the corresponding target intersection according to the current navigation information, the target track characteristics and the initial estimated traffic duration, the following optional implementation manners may be adopted: inputting current navigation information, target track characteristics and initial estimated traffic duration into a duration estimation model, and taking an output result of the duration estimation model as a target estimated traffic duration; the duration estimation model in this embodiment is obtained by training in advance.
In this embodiment, after the estimated passage duration of the target corresponding to the target intersection is obtained by the estimating unit 502, the processing unit 503 obtains the passage information of the corresponding target intersection according to the estimated passage duration of the target and the passage characteristics of the target.
The traffic information of the corresponding target intersection acquired by the processing unit 503 may include information about whether the traffic light can pass through the target intersection, and may further include a driving speed section when the traffic light cannot pass through the target intersection.
When the processing unit 503 obtains the traffic information of the corresponding target intersection according to the estimated traffic duration and the target traffic characteristics, the following alternative implementation manners may be adopted: and inputting the target estimated traffic duration and the target traffic characteristics into an intersection traffic model, and taking the output result of the intersection traffic model as traffic information of the corresponding target intersection.
It can be understood that, if there are multiple target intersections in the present embodiment, the processing unit 503 will input the target estimated traffic duration and the target traffic characteristics corresponding to different target intersections into the intersection traffic model respectively, so as to obtain the traffic information output by the intersection traffic model for each target intersection.
After acquiring the traffic information of the corresponding target intersection, the processing unit 503 may further display the acquired traffic information, so that the user can acquire information about whether to pass through one or more intersections by green light more intuitively.
It may be understood that, if the execution subject is a server, after the processing unit 503 obtains the traffic information corresponding to the target intersection, the processing unit sends the obtained traffic information to the terminal device, so that the terminal device displays the traffic information corresponding to the target intersection in the navigation interface; if the execution subject is a terminal device, the processing unit 503 may directly display the traffic information of the corresponding target intersection in the navigation interface after obtaining the traffic information.
The intersection traffic information acquiring apparatus 500 of the present embodiment may further include a first training unit 504 configured to perform: acquiring a first training set, wherein the first training set comprises a plurality of sample navigation tracks and the actual passing duration of the plurality of sample navigation tracks; according to the plurality of sample navigation tracks, sample track characteristics and first estimated passage time length of the plurality of sample navigation tracks are obtained; training a first neural network model by using sample track characteristics of a plurality of sample navigation tracks, a first estimated passage duration, navigation information and actual passage duration to obtain a duration estimated model.
The first training unit 504 may use the track feature extracted from each sample navigation track as a sample track feature corresponding to the sample navigation track; in addition, the sample navigation tracks in the present embodiment correspond to different moments and different road openings.
The first training unit 504 may use an existing traffic duration estimation method to obtain a first estimated traffic duration according to the sample navigation track.
The first training unit 504 trains the first neural network model by using the sample track features of the plurality of sample navigation tracks, the first estimated passage duration, the navigation information and the actual passage duration, and when obtaining the duration estimated model, optional implementation manners may be: respectively inputting sample track characteristics, first estimated passing time length and navigation information (steering information of the navigation tracks) of a plurality of sample navigation tracks into a first neural network model to obtain second estimated passing time length output by the first neural network model for each sample navigation track; obtaining a first loss function value according to the second estimated passage duration and the actual passage duration of the plurality of sample navigation tracks; and adjusting parameters of the first neural network model according to the first loss function value to obtain a duration estimation model.
In addition, before training the first neural network model, the first training unit 504 may further compare the first estimated traffic duration with the actual traffic duration, and if it is determined that the difference between the first estimated traffic duration and the actual traffic duration is greater than or equal to the preset threshold, the sample navigation track corresponding to the current first estimated traffic duration may be removed, that is, the training of the neural network model is performed without using data corresponding to the sample navigation track; the weight of the loss function value obtained by calculating the sample navigation track can be adjusted, for example, the weight is adjusted to a preset weight value (for example, 0.1), so that the effect of the sample navigation track in the training process is reduced.
The intersection traffic information acquiring apparatus 500 of the present embodiment may further include a second training unit 505, configured to perform: acquiring a second training set, wherein the second training set comprises actual traffic information of a plurality of sample navigation tracks; according to the plurality of sample navigation tracks, sample traffic characteristics and sample estimated traffic duration of the plurality of sample navigation tracks are obtained; and training a second neural network model by using sample traffic characteristics, sample estimated traffic duration and actual traffic information of a plurality of sample navigation tracks to obtain an intersection traffic model.
The second training unit 505 may first obtain a sample track feature and a first estimated traffic duration according to a sample navigation track, then input the sample track feature, the first estimated traffic duration and navigation information into a duration estimation model, and take an output result of the duration estimation model as a sample estimated traffic duration; in addition, the second training unit 505 may further use the preset estimated traffic duration as the sample estimated traffic duration.
The second training unit 505 trains the second neural network model by using the sample traffic characteristics, the sample estimated traffic duration and the actual traffic information of the plurality of sample navigation tracks, and obtains the intersection traffic model, and may adopt the following alternative implementation modes: respectively inputting sample traffic characteristics and sample estimated traffic duration of a plurality of sample navigation tracks into a second neural network model to obtain predicted traffic information output by the second neural network model for each sample navigation track; obtaining a second loss function value according to the predicted traffic information and the actual traffic information of the plurality of sample navigation tracks; and adjusting parameters of the second neural network model according to the second loss function value to obtain an intersection passing model.
It can be understood that the duration estimation model and the intersection traffic model in this embodiment may be two models that are independent of each other, or may be two calculation modules that are located under the same model architecture.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related user personal information all conform to the regulations of related laws and regulations, and the public sequence is not violated.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
As shown in fig. 6, a block diagram of an electronic device of a method for acquiring intersection traffic information according to an embodiment of the present disclosure is shown. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the apparatus 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data required for the operation of the device 600 may also be stored. The computing unit 601, ROM602, and RAM603 are connected to each other by a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Various components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, mouse, etc.; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The calculation unit 601 performs the respective methods and processes described above, for example, the acquisition method of the intersection traffic information. For example, in some embodiments, the method of acquiring intersection traffic information may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 608.
In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM602 and/or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the above-described intersection traffic information acquisition method may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the method of acquiring intersection traffic information in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here can be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable crossing traffic information acquisition device such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, 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), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a presentation device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for presenting information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service ("Virtual Private Server" or simply "VPS") are overcome. The server may also be a server of a distributed system or a server that incorporates a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (17)
1. A method for acquiring intersection traffic information comprises the following steps:
acquiring target track characteristics and target traffic characteristics according to the target moment and the target intersection;
acquiring target estimated passage time length corresponding to the target intersection according to the current navigation information and the target track characteristics;
and acquiring traffic information corresponding to the target intersection according to the target estimated traffic duration and the target traffic characteristics.
2. The method of claim 1, wherein the acquiring the target trajectory feature and the target traffic feature according to the target moment and the target intersection comprises:
under the condition that the distance between the current position and the target intersection is smaller than or equal to a preset distance threshold value, taking the current moment as the target moment;
and acquiring the target track characteristic and the target traffic characteristic according to the target moment and the target intersection.
3. The method of claim 1, wherein the obtaining the target estimated passage duration corresponding to the target intersection according to the current navigation information and the target trajectory feature comprises:
acquiring an initial estimated passage time length corresponding to the target intersection;
and obtaining the target estimated traffic duration corresponding to the target intersection according to the current navigation information, the target track characteristics and the initial estimated traffic duration.
4. The method of claim 3, wherein the obtaining the target estimated passage duration corresponding to the target intersection based on the current navigation information, the target trajectory feature, and the initial estimated passage duration comprises:
and inputting the current navigation information, the target track characteristics and the initial estimated passage duration into a duration estimation model, and taking an output result of the duration estimation model as the target estimated passage duration.
5. The method of claim 1, wherein the obtaining traffic information corresponding to the target intersection according to the target estimated traffic duration and the target traffic characteristic comprises:
and inputting the target estimated passage duration and the target passage characteristics into an intersection passage model, and taking an output result of the intersection passage model as the passage information.
6. The method of claim 4, further comprising,
acquiring a first training set, wherein the first training set comprises a plurality of sample navigation tracks and actual passing time lengths of the plurality of sample navigation tracks;
according to the plurality of sample navigation tracks, sample track features and first estimated traffic duration of the plurality of sample navigation tracks are obtained;
And training a first neural network model by using sample track characteristics, first estimated passing time length, navigation information and actual passing time length of the plurality of sample navigation tracks to obtain a time length estimated model.
7. The method of claim 5, further comprising,
acquiring a second training set, wherein the second training set comprises a plurality of sample navigation tracks and actual traffic information of the plurality of sample navigation tracks;
according to the plurality of sample navigation tracks, sample traffic characteristics and sample estimated traffic duration of the plurality of sample navigation tracks are obtained;
and training a second neural network model by using the sample traffic characteristics, the sample estimated traffic duration and the actual traffic information of the plurality of sample navigation tracks to obtain the intersection traffic model.
8. An acquisition device of intersection traffic information, comprising:
the acquisition unit is used for acquiring target track characteristics and target traffic characteristics according to the target moment and the target intersection;
the estimating unit is used for acquiring target estimated passage duration corresponding to the target intersection according to the current navigation information and the target track characteristics;
and the processing unit is used for acquiring the traffic information corresponding to the target intersection according to the target estimated traffic duration and the target traffic characteristics.
9. The apparatus of claim 8, wherein the acquiring unit, when acquiring the target trajectory feature and the target traffic feature according to the target time and the target intersection, specifically performs:
under the condition that the distance between the current position and the target intersection is smaller than or equal to a preset distance threshold value, taking the current moment as the target moment;
and acquiring the target track characteristic and the target traffic characteristic according to the target moment and the target intersection.
10. The apparatus of claim 8, wherein the estimating unit, when obtaining the target estimated passage duration corresponding to the target intersection according to the current navigation information and the target track feature, specifically performs:
acquiring an initial estimated passage time length corresponding to the target intersection;
and obtaining the target estimated traffic duration corresponding to the target intersection according to the current navigation information, the target track characteristics and the initial estimated traffic duration.
11. The apparatus of claim 10, wherein the estimating unit, when obtaining the target estimated passage duration corresponding to the target intersection according to the current navigation information, the target trajectory feature and the initial estimated passage duration, specifically performs:
And inputting the current navigation information, the target track characteristics and the initial estimated passage duration into a duration estimation model, and taking an output result of the duration estimation model as the target estimated passage duration.
12. The apparatus of claim 8, wherein the processing unit, when acquiring traffic information corresponding to the target intersection according to the target estimated traffic duration and the target traffic characteristic, specifically performs:
and inputting the target estimated passage duration and the target passage characteristics into an intersection passage model, and taking an output result of the intersection passage model as the passage information.
13. The apparatus of claim 11, further comprising a first training unit to perform:
acquiring a first training set, wherein the first training set comprises a plurality of sample navigation tracks and actual passing time lengths of the plurality of sample navigation tracks;
according to the plurality of sample navigation tracks, sample track features and first estimated traffic duration of the plurality of sample navigation tracks are obtained;
and training a first neural network model by using sample track characteristics, first estimated passing time length, navigation information and actual passing time length of the plurality of sample navigation tracks to obtain a time length estimated model.
14. The apparatus of claim 12, further comprising a second training unit to perform:
acquiring a second training set, wherein the second training set comprises a plurality of sample navigation tracks and actual traffic information of the plurality of sample navigation tracks;
according to the plurality of sample navigation tracks, sample traffic characteristics and sample estimated traffic duration of the plurality of sample navigation tracks are obtained;
and training a second neural network model by using the sample traffic characteristics, the sample estimated traffic duration and the actual traffic information of the plurality of sample navigation tracks to obtain the intersection traffic model.
15. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
16. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-7.
17. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311013772.4A CN117198040A (en) | 2023-08-11 | 2023-08-11 | Intersection traffic information acquisition method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311013772.4A CN117198040A (en) | 2023-08-11 | 2023-08-11 | Intersection traffic information acquisition method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117198040A true CN117198040A (en) | 2023-12-08 |
Family
ID=88995171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311013772.4A Pending CN117198040A (en) | 2023-08-11 | 2023-08-11 | Intersection traffic information acquisition method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117198040A (en) |
-
2023
- 2023-08-11 CN CN202311013772.4A patent/CN117198040A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220084400A1 (en) | Green wave speed determination method, electronic device and storage medium | |
| CN113129596B (en) | Travel data processing method, travel data processing device, travel data processing apparatus, storage medium, and program product | |
| CN113899381B (en) | Method, apparatus, device, medium, and product for generating route information | |
| CN114543829A (en) | Model training method, navigation track recommendation method and device and vehicle | |
| CN113119999B (en) | Method, device, equipment, medium and program product for determining automatic driving characteristics | |
| CN113722342A (en) | High-precision map element change detection method, device and equipment and automatic driving vehicle | |
| CN114582125B (en) | Method, device, equipment and storage medium for identifying road traffic direction | |
| CN113837455B (en) | Taxi taking method, taxi taking device, electronic equipment and readable storage medium | |
| CN115771526A (en) | Method and device for controlling left turn of vehicle in automatic driving and automatic driving vehicle | |
| CN117198040A (en) | Intersection traffic information acquisition method and device, electronic equipment and readable storage medium | |
| CN113450569A (en) | Method, device, electronic equipment and storage medium for determining intersection state | |
| CN113847923A (en) | Calculation method and device of estimated arrival time, electronic equipment and readable storage medium | |
| CN113886413A (en) | Map updating method and device | |
| CN116264038A (en) | Signal lamp control method and device, electronic equipment and storage medium | |
| CN114689061A (en) | Navigation route processing method and device of automatic driving equipment and electronic equipment | |
| CN114689069A (en) | Navigation route processing method and device of automatic driving equipment and electronic equipment | |
| CN113344277A (en) | Prediction model training method, state updating method, device, equipment and medium | |
| CN115507866B (en) | Map data processing method and device, electronic equipment and medium | |
| CN114970949B (en) | Method and device for predicting running speed, electronic device, and storage medium | |
| CN114333326B (en) | Intersection congestion detection method and device and electronic equipment | |
| CN111882860B (en) | Lane adjusting method and device | |
| CN114565905A (en) | Lane line extraction method and device and electronic equipment | |
| CN117746661A (en) | Vehicle running control method and device, electronic equipment and readable storage medium | |
| CN116129393A (en) | Signal lamp switching identification method, device, equipment and storage medium | |
| CN116434166A (en) | Target area identification method, device, equipment and storage medium |
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 |