Traffic subarea division method and device based on cross-modal feature association, and medium

Abstract

The invention discloses a traffic subarea division method and device based on cross-modal feature association, and a medium, and the method specifically comprises the steps: obtaining the number of first vehicles passing through every two adjacent initial checkpoint devices in a historical time period, obtaining a plurality of key checkpoint device clusters according to the number of the first vehicles and a preset number of vehicles, and obtaining a plurality of key checkpoint device clusters; when the number of the key checkpoint devices in the cluster is larger than a preset key checkpoint number threshold value, the second vehicle number of every two adjacent key checkpoint devices in the cluster is obtained, and according to the second vehicle number and the number of vehicles passing through the multiple key checkpoint devices connected in sequence, an initial traffic sub-area is divided; and finally, dividing a target traffic sub-area. According to the invention, the rationality of traffic subarea division can be improved, and effective traffic subarea division reference can be provided for traffic management personnel.

Description

Technical Field

[0001] The present invention belongs to the field of traffic technology, and in particular relates to a traffic sub-area division method, a device and a medium based on cross-modal feature association. Background Art

[0002] Traffic signals are one of the main means to achieve road traffic status control. The control methods for single intersections and main roads have become increasingly mature, but there is still a lack of effective methods for coordinated control of traffic sub-regions on a larger scale. Different areas and historical periods of the city present different traffic flow change characteristics, among which the historical time periods include: morning peak historical period, evening peak historical period, and flat peak historical period; the direction of traffic flow during the morning peak period mainly flows from residential areas to work areas, and the direction of traffic flow during the evening peak period mainly flows from work areas to residential areas; therefore, the direction of vehicles during the morning and evening peaks shows an obvious tidal effect.

[0003] In order to reduce the complexity of traffic survey and traffic analysis, the study area is usually divided into several sub-areas when conducting traffic planning. How to reasonably divide the traffic sub-areas is an urgent problem to be solved. Summary of the invention

[0004] In view of this, the present invention provides a method, device and medium for dividing traffic sub-areas based on cross-modal feature association.

[0005] In the first aspect, an embodiment of the present invention provides a method for dividing traffic sub-areas based on cross-modal feature association; wherein the modal features include: vehicle characteristics in the time dimension, vehicle proximity characteristics in the plane dimension, and topological dimension characteristics of key points of intersections where cameras are installed. By associating the above three modal features, the target traffic sub-areas are divided.

[0006] Specifically, the method comprises:

[0007] Get the initial card port device list A={A1,A2,…, A m}, m is the number of initial bayonet devices;

[0008] Get the first vehicle quantity list B={B1,B2,…,B m-1};

[0009] According to the first vehicle quantity list B and the vehicle quantity threshold θ, the initial checkpoint devices in the initial checkpoint device list A are clustered to obtain a key checkpoint device cluster list C={C1,C2,…,C j ,…,C n}, C j ={C j1 ,Cj2 ,…,C jf}; where n is the number of key bayonet device clusters, and f is the number of key bayonet devices in the jth key bayonet device cluster;

[0010] Set the threshold of the number of key checkpoint devices. When the jth key checkpoint device cluster C j When the number of key checkpoint devices f in the vehicle is greater than the preset threshold value η of the number of key checkpoint devices, the vehicle number list B is used to obtain the vehicle number of the first vehicle through the jth key checkpoint device cluster C. j The second vehicle quantity list D of two adjacent key checkpoint devices j ={D j1 ,D j2 ,…, D j(f-1)};

[0011] Dividing an initial traffic sub-area according to the second vehicle quantity list and the number of vehicles passing through a plurality of key checkpoint devices connected in sequence during a historical time period;

[0012] The target traffic sub-area is divided according to the initial traffic sub-area and a number of vehicle inflows and a number of vehicle outflows corresponding to each key checkpoint device in the initial traffic sub-area.

[0013] In a second aspect, an embodiment of the present invention provides a method for dividing traffic sub-areas based on cross-modal feature association, the method comprising:

[0014] Get the initial card port device list A={A1,A2,…, A m}, m is the number of initial bayonet devices;

[0015] Get the first vehicle quantity list B={B1,B2,…,B m-1};

[0016] For the first vehicle quantity list B={B1,B2,…,B m-1}, and obtain the first bayonet device combinations corresponding to the first w first vehicle quantities, thereby obtaining the first bayonet device combination list Z={Z1,Z2,…,Z v ,…,Z w}, v∈[1,w], w is the initial screening number;

[0017] Get the key vehicle quantity list T={T1,T2,…,T m-λ+1};

[0018] Set the minimum number of vehicles to be screened λ, select from the key vehicle quantity list T a number of vehicles not less than the minimum screening vehicle quantity threshold ζ λ The number of key vehicles is selected, and the second checkpoint device combinations corresponding to the selected number of key vehicles are merged into a second checkpoint device combination list Y={Y1,Y2,…,Y α ,…,Y β}, α∈[1,β], β is the number of second bayonet device combinations;

[0019] Update the first bayonet device combination list Z according to the second bayonet device combination list Y, and divide the road sections between each bayonet device combination in the updated first bayonet device combination list Z into initial traffic sub-areas;

[0020] The target traffic sub-area is divided according to the initial traffic sub-area and a number of vehicle inflows and a number of vehicle outflows corresponding to each checkpoint device in the initial traffic sub-area.

[0021] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the above-mentioned traffic sub-area division method based on cross-modal feature association.

[0022] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for dividing traffic sub-areas based on cross-modal feature association.

[0023] In a fifth aspect, an embodiment of the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the above-mentioned traffic sub-area division method based on cross-modal feature association.

[0024] The beneficial effects of the present invention are:

[0025] By acquiring the vehicle flow between every two adjacent key checkpoint devices and the vehicle flow between two key checkpoint devices running through the interval, the present invention can learn that when the vehicle flow between two key checkpoint devices running through the interval is large, only a small number of vehicles leave from other intersections between the two interval key checkpoint devices, indicating that the vehicle driving continuity of the two interval key checkpoint devices is high. The traffic area between the two interval key checkpoint devices can be divided into initial traffic sub-areas, and according to a number of vehicle entry and exit corresponding to each key checkpoint device, a target traffic sub-area is divided, thereby improving the rationality of traffic sub-area division, which is beneficial to provide effective traffic sub-area division reference for traffic management personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 A first flow chart of a method for dividing traffic sub-areas based on cross-modal feature association provided by an embodiment of the present invention;

[0028] Figure 2 A second flow chart of a method for dividing traffic sub-areas based on cross-modal feature association provided by an embodiment of the present invention;

[0029] Figure 3 A schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0032] Example 1

[0033] like Figure 1 As shown, when the number of initial checkpoint devices is greater than a preset first checkpoint number threshold (i.e., m>ε1), an embodiment of the present invention provides a traffic sub-area division method based on cross-modal feature association, the method comprising the following steps:

[0034] Step S1, obtain the initial card slot device list A = {A1, A2, ..., Ai ,…,A m}, i=1,2,…,m, m is the number of initial bayonet devices, A i is the i-th initial mount device.

[0035] Specifically, the initial checkpoint device refers to any one of several checkpoint devices collected sequentially on a driving trajectory; it can be understood that: a driving trajectory includes several connected road sections, and the vehicle can travel sequentially on several road sections according to the order of the road sections.

[0036] Step S2, obtaining a first list of vehicle numbers B={B1, B2, ..., B g ,…,B m-1}, g = 1, 2, ..., m-1, B g is the number of initial checkpoint devices A that have passed through the gth time period in the history g To the g+1th initial mount device A g+1 The number of vehicles.

[0037] Specifically, the historical time periods include: morning rush hour historical period, evening rush hour historical period, and off-peak historical period; among them, the direction of traffic flow during the morning rush hour mainly flows from residential areas to work areas, and the direction of traffic flow during the evening rush hour mainly flows from work areas to residential areas. The direction of vehicles during the morning and evening rush hours shows an obvious tidal effect.

[0038] Preferably, m>ε1, where ε1 is the preset first checkpoint quantity threshold; when performing subsequent steps in this embodiment, the initial checkpoint devices are first screened according to the first vehicle quantity and the vehicle quantity threshold, and then only data collection, calculation and area expansion are performed on the screened initial checkpoint devices to reduce complexity. This embodiment is suitable for situations where there are many checkpoint devices.

[0039] It should be noted that by obtaining the number of vehicles between each two adjacent initial checkpoints, the traffic flow and traffic flow changes between each two adjacent initial checkpoints can be known, so that the staff can screen out the initial checkpoints that meet the requirements according to the traffic flow, providing a basis for the subsequent traffic sub-area division.

[0040] Step S3: cluster the initial checkpoint devices in the initial checkpoint device list A according to the first vehicle quantity list B and the preset vehicle quantity threshold θ, and obtain a key checkpoint device cluster list C = {C1, C2, ..., C j ,…,C n}, C j ={C j1 ,C j2 ,…,C je ,…,Cjf}, where C je is the e-th key checkpoint device in the j-th key checkpoint device cluster, j=1,2,…,n, n is the number of key checkpoint device clusters, e=1,2,…,f, f is the number of key checkpoint devices in the j-th key checkpoint device cluster.

[0041] In a specific embodiment, step S3 includes the following sub-steps:

[0042] Step S301, set a vehicle quantity threshold θ, and obtain an intermediate vehicle quantity list from the first vehicle quantity list B according to the preset vehicle quantity θ ,in, is the pth intermediate vehicle number, p=1,2,…,q, q is the number of intermediate vehicles, and the intermediate vehicle number refers to any first vehicle number that is not less than a preset vehicle number threshold θ.

[0043] Step S302: According to the intermediate vehicle quantity list B 0 , get the intermediate vehicle quantity list B 0 Corresponding first-mount device list ,in, , is the number of the pth intermediate vehicles B 0 p The first initial mount device of the corresponding two initial mount devices, is the number of the pth intermediate vehicles B 0 p The latter of the two corresponding initial bayonet devices.

[0044] Step S303: 0 The first bayonet devices in the list are deduplicated to obtain a second bayonet device list; wherein the second bayonet device list includes a plurality of second bayonet devices, and the second bayonet device is any first bayonet device after the deduplication process.

[0045] For easier understanding, the following example is used to illustrate: , , Indicates the latter of the two initial checkpoint devices corresponding to the first intermediate vehicle number, represents the first initial checkpoint device among the two initial checkpoint devices corresponding to the second intermediate vehicle number, so and For the same first mount device, and Deduplication processing is performed, that is, the same card mount device in the second card mount device list is recorded only once.

[0046] Step S304: according to the arrangement order of the initial bayonet devices in the initial bayonet device list A, the bayonet devices that are sequentially connected in the second bayonet device list are grouped into a cluster, and a key bayonet device cluster list C is obtained.

[0047] For example, when the second bayonet device list only includes the initial bayonet devices A1, A2, A4, A5, A6, A8, and A9, A1 and A2 are clustered into a cluster C1, A4, A5, and A6 are clustered into a cluster C2, and A8 and A9 are clustered into a cluster C3. The first key bayonet device cluster C1, the second key bayonet device cluster C2, and the third key bayonet device cluster C3 constitute the key bayonet device cluster list C.

[0048] It should be noted that the sections with heavy traffic volume are first screened out, and then the initial checkpoint devices corresponding to these sections are clustered. Through clustering, multiple sections with heavy traffic volume can be preliminarily divided out, providing a preliminary basis for the subsequent division of traffic sub-areas.

[0049] Step S4, setting a critical checkpoint device quantity threshold η, when the jth critical checkpoint device cluster C j When the number of key checkpoint devices f in the vehicle is greater than the preset threshold value of the number of key checkpoint devices η (ie, f>η), the first vehicle number list B is used to obtain the vehicle number that passes through the jth key checkpoint device cluster C. j The second vehicle quantity list D of two adjacent key checkpoint devices j ={D j1 ,D j2 ,…,D jh ,…, D j(f-1)},h=1,2,…,f-1,D jh is the equipment cluster C that passed the jth key checkpoint in the historical time period j The hth key card port device C jh To the h+1th key card port device C j(h+1) The number of vehicles on the road segment between two adjacent key checkpoint devices.

[0050] Preferably, the critical checkpoint device quantity threshold η=2.

[0051] Specifically, when f=2, since the number of key checkpoint devices in the corresponding key checkpoint device cluster is small, whether a traffic sub-area can be formed is not considered; it can be understood that: when f=2, two key checkpoint devices cannot form a traffic sub-area.

[0052] Step S5: divide the initial traffic sub-area according to the second vehicle quantity list D and the number of vehicles passing through a plurality of key checkpoints connected in sequence in a historical time period.

[0053] Furthermore, the initial traffic sub-area can only be divided when the number of vehicles passing through several key checkpoints connected in sequence during the historical time period meets the preset requirements.

[0054] In a specific embodiment, step S5 also includes the following sub-steps:

[0055] Step S501: Obtain the device cluster C that has passed through the jth key checkpoint in the historical time period. j The kth key card port device C in jk To the k+rth key card port device C j(k+r) The number of vehicles L k(k+r) ; Initialize k=1, r=2.

[0056] Step S502 specifically includes:

[0057] when When r is updated to r+1, the process returns to S501 to obtain the number of times C has passed in the historical time period. jk To C j(k+r+1) The number of vehicles L k(k+r+1) Iterate the calculation until k+r>f, and then the jth key card port equipment cluster C j The kth key card port device C in jk To the jth key card port equipment cluster C j The fth key card port device C in jf The key checkpoint devices in are merged and divided into initial traffic sub-areas, where ω is the preset deviation threshold; it can be understood that: merging the key checkpoint devices into initial traffic sub-areas means merging the road sections between several key checkpoint devices into initial traffic sub-areas.

[0058] when When r≥ε2, C jk To C j(k+r-1) The key checkpoints in the system are merged into initial traffic sub-areas and the C jk C j(k+r-1) , update C j(k+r) C j(k+r+1) , return to execute S501 until it is updated to C j(k+r) C j(f+1) ; can be understood as: update C jk C j(k+r-1) C jk The corresponding key card port equipment is updated to C j(k+r-1) The corresponding key bayonet device, the updated result is used as the new C jk ; The other updating principles in step S400 are the same as this and will not be repeated here.

[0059] Specifically, the r meets the preset requirement, which means that r≥ε2 at this time, wherein ε2 is a preset second bayonet quantity threshold, for example, ε2 is 3; and the r at this time refers to the value obtained after the latest update.

[0060] when When r<ε2, update C jk C j(k+r-1) , and update C j(k+r) C j(k+r+1) , return to execute S501 until it is updated to C j(k+r) C j(f+1) .

[0061] For ease of understanding, in this example, the jth key card port device cluster C is set. j The number of key card-point devices in f = 7, the jth key card-point device cluster C j The key bayonet devices in the system are: C j1 , C j2 , C j3 , C j4 , C j5 , C j6 , C j7 ;include:

[0062] Step S501: Obtain the device cluster C that has passed through the jth key checkpoint in the historical time period. j The first key card device C j1 To the jth key card port equipment cluster C j The third key card device C j3 The number of vehicles L 13 , initially set k=1, r=2.

[0063] Step S502 specifically includes:

[0064] when When C is obtained during the historical time period j1 To C j4 The number of vehicles L 14 ,when When C is obtained during the historical time period j1 To C j5 The number of vehicles L 15 , and the cycle continues until the latest update r is r+1, k+r>f, the cycle ends, and C j1 To C j7 The seven key checkpoints in the figure are combined into an initial traffic sub-area, and ω can be taken as 0.3.

[0065] when When the second bayonet quantity threshold ε2=3 is set, r=2, r<ε2, C j1 , C j2 , C j3 Cannot be merged into the initial traffic sub-area, then update C j1 C j2 , update C j3 C j4 , at this time k=2, r=2, get the number of times C j2 To C j4 The number of vehicles L 24 ;when When r<ε2, then C j2 , C j3 , C j4 Cannot be merged and divided into initial traffic sub-areas, repeat the above steps for C jk and C j(k+r) The update step of When C j(f-2) C j(f-1) , update C jf C j(f+1) , since there is no C j(f+1) , then the loop ends.

[0066] when and When C is obtained during the historical time period j2 To C j5 The number of vehicles L 25 ,when When , the cycle continues according to the above cycle principle, which will not be repeated here; when When r=3, r≥ε2, C j2 , C j3 , C j4 Merge and divide into initial traffic sub-areas, and update C j2 C j4 , update C j5 C j6 , and then return to execute S401 to perform subsequent execution steps.

[0067] It should be noted that when dividing the initial traffic sub-areas, that is, when dividing the traffic area according to the distribution of traffic flow, if it is determined that two non-adjacent key checkpoint devices can be divided into an initial traffic sub-area, first obtain the difference between the average traffic flow between the two key checkpoint devices and the traffic flow of the section between the two key checkpoint devices, and calculate the ratio of the difference to the average traffic flow. When the ratio is small, it means that the traffic flow of the section between the two key checkpoint devices is large, then the possibility of dividing the area between the two key checkpoint devices into the initial traffic sub-area is high, thereby improving the accuracy of the initial traffic sub-area division, which is beneficial to provide traffic management personnel with an effective traffic sub-area division reference, so that traffic management personnel can implement corresponding management measures according to different areas.

[0068] Step S6: dividing the target traffic sub-area according to the initial traffic sub-area and the vehicle entry and exit volume corresponding to each key checkpoint device in the initial traffic sub-area.

[0069] Specifically, the vehicle entry volume corresponding to the key checkpoint device refers to the number of vehicles entering the key checkpoint device from any preceding road section corresponding to the key checkpoint device. For example, if the intersection where a key checkpoint device is located is a crossroads, then its corresponding preceding road section refers to any one of the three sections except the section where the key checkpoint device is located.

[0070] Specifically, the vehicle outflow volume corresponding to the key checkpoint device refers to the number of vehicles that drive out from the road section where the key checkpoint device is located to any subsequent road section corresponding to it; it can be understood that: the subsequent road section corresponding to the key checkpoint device refers to any road section that is subsequently entered after leaving the road section where the key checkpoint device is located.

[0071] In a specific embodiment, step S6 also includes the following sub-steps:

[0072] Step S601: according to the e-th key card port device C in the j-th key card port device cluster, je The corresponding number of vehicle entry volumes is obtained to obtain the road section corresponding to any vehicle entry volume and the e-th key checkpoint device C in the j-th key checkpoint device cluster. je The first correlation ρ1 of the road segment.

[0073] Specifically, ρ1 meets the following conditions:

[0074]

[0075] Where γ is the e-th key card device C in the j-th key card device cluster. je The corresponding number of vehicles entering, φ σis the e-th key card device C in the j-th key card device cluster je The corresponding σth vehicle entry volume can be understood as: φ σ It refers to the e-th key card device C in the j-th key card device cluster. je The corresponding σth preceding road segment enters C je The number of vehicles on the road segment.

[0076] S602, set the first correlation threshold ψ1, when ρ1≥ψ1, set φ σ The corresponding road segments are added to the initial traffic sub-area to update the initial traffic sub-area to form the target traffic sub-area.

[0077] S603: according to the e-th key card port device C in the j-th key card port device cluster, je The corresponding number of vehicle outflows is obtained to obtain the road section corresponding to any vehicle outflow and C je The second correlation ρ2 of the road segment.

[0078] Specifically, ρ2 meets the following conditions:

[0079]

[0080] in, is the e-th key card device C in the j-th key card device cluster je The corresponding ξ-th vehicle outflow can be understood as: It refers to the e-th key card device C in the j-th key card device cluster. je The number of vehicles that leave the current section and enter the ξth subsequent section.

[0081] S604, set the second correlation threshold ψ2, when ρ2≥ψ2, The corresponding road segments are added to the initial traffic sub-area to update the initial traffic sub-area to form the target traffic sub-area.

[0082] It should be noted that, by using the vehicle entry and exit volumes of each key checkpoint device, other road sections at the fork intersection with a high correlation with each key checkpoint device can be reasonably determined. In practical applications, the correlation of the extended road sections can be calculated again for further extension. Since the extension method is the same, the calculation process will not be repeated here, and the extension from line to surface is realized, thereby dividing the final traffic sub-area, which improves the rationality of the traffic sub-area division.

[0083] Example 2

[0084] In another specific embodiment, Figure 2As shown, when the number of initial checkpoint devices is less than or equal to a preset first checkpoint number threshold (i.e., m≤ε1), an embodiment of the present invention provides a traffic sub-area division method based on cross-modal feature association, the method comprising the following steps:

[0085] Step S1, obtain the initial card slot device list A = {A1, A2, ..., A i ,…,A m}, i=1,2,…,m, m is the number of initial bayonet devices, A i is the i-th initial mount device.

[0086] Step S2, obtaining a first list of vehicle numbers B={B1, B2, ..., B g ,…,B m-1}, g = 1, 2, ..., m-1, B g is the number of initial checkpoint devices A that have passed through the gth time period in the history g To the g+1th initial mount device A g+1 The number of vehicles.

[0087] Step S3: for the first vehicle quantity list B={B1, B2,…, B g ,…,B m-1}, and obtain the first bayonet device combinations corresponding to the first w first vehicle quantities, thereby obtaining the first bayonet device combination list Z={Z1,Z2,…,Z v ,…,Z w}, v∈[1,w], w is the initial screening number.

[0088] Among them, Z v ={Z v1 , Z v2}, Z v1 is the previous initial checkpoint device corresponding to the vth first vehicle number after screening, Z v2 is the next initial checkpoint device corresponding to the vth first vehicle number after screening, v=1,2,…,w; for example: A g For B g The corresponding previous initial mount device, A g+1 For B g The corresponding latter initial bayonet device.

[0089] In a specific embodiment, step S3 also includes the following steps:

[0090] S301, based on the sorting result of the first number of vehicles and the preset initial screening number w, a third vehicle number list U={U1,U2,…,U v ,…,Uw}, where U v is the vth first vehicle number among the w first vehicle numbers screened out; it can be understood as: the initial screening number is the number of screened first vehicle numbers, and after sorting the first vehicle numbers from large to small, the first w first vehicle numbers are screened out.

[0091] Preferably, the target vehicle number is the smallest third vehicle number among w third vehicle numbers.

[0092] S302, according to U v The corresponding first vehicle number is obtained v Corresponding first bayonet device combination Z v ; can be understood as: U v The corresponding first bayonet device combination is U v A combination of two corresponding initial bayonet devices.

[0093] S303: According to the first checkpoint device combinations corresponding to each third number of vehicles, a first checkpoint device combination list Z={Z1, Z2, …, Z v ,…,Z w}; It can be understood as: merging the obtained w first bayonet device combinations into a list.

[0094] It should be noted that after sorting the first vehicle quantities, several first vehicle quantities that meet the requirements can be screened out, and then several sections with large traffic flow and initial checkpoint equipment corresponding to the sections with large traffic flow can be obtained, so as to achieve preliminary screening of the initial checkpoint equipment and preliminary determination of the sections, so as to grasp the changes in traffic flow in multiple sections on this basis, and provide a basis for the subsequent expansion of related sections and the division of traffic sub-areas.

[0095] S4, obtain the key vehicle quantity list T={T1,T2,…,T x ,…,T m-λ+1}, where T x A is the number of times A has passed in the historical period x To A x+λ-1 The number of vehicles, x=1,2,…,m-λ+1, at this time λ=3; for example: when λ=3, T1 is the number of vehicles passing through the section between the three initial checkpoints A1 to A3 in the historical time period.

[0096] S5, set the minimum screening vehicle quantity threshold ζ λ , select from the key vehicle quantity list T a number of vehicles not less than the minimum screening vehicle quantity threshold ζ λThe number of key vehicles is selected, and the second checkpoint device combinations corresponding to the selected number of key vehicles are merged into a second checkpoint device combination list Y={Y1,Y2,…,Y α ,…,Y β}, α∈[1,β], β is the number of second bayonet device combinations.

[0097] Among them, Y α ={Y α1 ,Y α2 ,…,Y αλ},Y α1 is the first initial checkpoint device corresponding to the αth number of critical vehicles after screening, Y α2 is the second initial bayonet device corresponding to the αth critical vehicle number after screening, Y αλ is the λth initial checkpoint device corresponding to the αth number of key vehicles after screening; it can also be understood as: Y αλ It is the last initial bayonet device corresponding to the αth critical number of vehicles after screening.

[0098] In a specific embodiment, S5 includes the following steps:

[0099] S501, according to the preset minimum number of vehicles to be screened λ , select from T a number of values ​​not less than ζ λ The number of key vehicles.

[0100] S502 , respectively obtain the second checkpoint device combinations corresponding to each of the selected key vehicle quantities, and combine the second checkpoint device combinations corresponding to several selected key vehicle quantities into Y.

[0101] Specifically, λ Meet the following conditions:

[0102] ζ λ =ζ λ-1 / λ×(λ-1), where ζ2 is the number of target vehicles; it can also be understood as: since there are at least 2 bayonet devices in the bayonet device combination, the minimum value of λ is 2, and the number of target vehicles is taken as ζ λ The initial value of .

[0103] It should be noted that as the road section lengthens, some vehicles that pass through a certain checkpoint will leave at subsequent intersections. When driving to more and more checkpoints, the original vehicles will become fewer and fewer. Therefore, it is necessary to adjust the minimum number of screened vehicles to obtain a more reasonable second checkpoint device combination and improve the rationality of the traffic sub-area division.

[0104] S6, updating the first checkpoint device combination list Z according to the second checkpoint device combination list Y, and dividing the road sections between each checkpoint device combination in the updated first checkpoint device combination list Z into initial traffic sub-areas.

[0105] When there is an αth second bayonet device combination Y α Contains the vth first bayonet device combination Z v When the first bayonet device combination Z v Delete from the first bayonet device combination list Z, and add the αth second bayonet device combination Y α Add it to the first checkpoint device combination list Z to obtain an updated first checkpoint device combination list Z, and update λ to λ+1, return to execute step S3 to obtain the first checkpoint device combination list Z for iteration, until λ is updated to m+1, and divide the road sections between each checkpoint device combination in the current first checkpoint device combination list Z into initial traffic sub-areas.

[0106] When there is no αth second bayonet device combination Y α Contains the vth first bayonet device combination Z v , merge the second checkpoint device combination list Y with the first checkpoint device combination list Z to obtain an updated first checkpoint device combination list Z, update λ to λ+1, and step S3 obtains the first checkpoint device combination list Z for iteration until λ is updated to m+1, and each target checkpoint device combination in Z at this time is divided into initial traffic sub-areas; it can be understood as: merging the road sections corresponding to each target checkpoint device combination in Z into initial traffic sub-areas.

[0107] It should be noted that when there is a second checkpoint device combination that includes the first checkpoint device combination, the second checkpoint device combination is added to the first checkpoint device combination list, and the duplicate first checkpoint device combination is deleted; when all second checkpoint device combinations do not include any first checkpoint device combination, the first checkpoint device combination list and the second checkpoint device combination list are merged as a new first checkpoint device combination list, and the iterations are performed in sequence; each target checkpoint device combination in the target checkpoint device combination list finally obtained is a combination with a high degree of vehicle correlation; by dividing the checkpoint devices in each combination into initial traffic sub-areas, the rationality of the traffic sub-area division is improved, which is beneficial to provide traffic management personnel with an effective traffic sub-area division reference.

[0108] S7, dividing the target traffic sub-area according to the initial traffic sub-area and the number of vehicles entering and exiting corresponding to each checkpoint device in the initial traffic sub-area; the division method is the same as the division method in step S6 in Example 1, which will not be repeated here.

[0109] It should be noted that, by using the vehicle entry and exit volumes of each target checkpoint device, other road sections at the fork intersection with a high correlation with each target checkpoint device can be reasonably determined. In practical applications, the correlation of the extended road sections can be calculated again for further extension. Since the extension method is the same, the calculation process will not be repeated here, and the extension from line to surface is realized, thereby dividing the final traffic sub-area, which improves the rationality of the traffic sub-area division.

[0110] According to an embodiment of the present invention, the present invention also provides an electronic device and a readable storage medium.

[0111] Figure 3 A schematic block diagram of an electronic device that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0112] The electronic device includes a computing unit 101, which can perform various appropriate actions and processes according to a computer program stored in a ROM 102 or a computer program loaded from a storage unit 108 into a RAM 103. In the RAM 103, various programs and data required for the operation of the electronic device can also be stored. The computing unit 101, the ROM 102, and the RAM 103 are connected to each other via a bus 104. An I / O interface 105 is also connected to the bus 104.

[0113] A number of components in the electronic device are connected to the I / O interface 105, including: an input unit 106, such as a keyboard, a mouse, etc.; an output unit 107, such as various types of displays, speakers, etc.; a storage unit 108, such as a disk, an optical disk, etc.; and a communication unit 109, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 109 allows the electronic device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0114] The computing unit 101 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 101 performs the various methods and processes described above. For example, in some embodiments, the method in the multidimensional early warning system for pressure injuries may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 108. In some embodiments, part or all of the computer program may be loaded and / or installed on an electronic device via ROM 102 and / or a communication unit 109. When the computer program is loaded into RAM 103 and executed by the computing unit 101, one or more steps of the method in the multidimensional early warning system for pressure injuries described above may be executed. Alternatively, in other embodiments, the computing unit 101 may be configured to execute the method in the multidimensional early warning system for pressure injuries in any other appropriate manner (e.g., by means of firmware).

[0115] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0116] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0117] In the context of the present invention, a readable storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. A readable storage medium may be a machine-readable signal medium or a machine-readable storage medium. A readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of readable storage media may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0118] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0119] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0120] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0121] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A traffic sub-area division method based on cross-modal feature association, characterized in that: The method comprises: Get the initial card port device list A={A1,A2,…, A m }, m is the number of initial bayonet devices; Get the first vehicle quantity list B={B1,B2,…,B m-1 }; According to the first vehicle quantity list B and the vehicle quantity threshold θ, the initial checkpoint devices in the initial checkpoint device list A are clustered to obtain a key checkpoint device cluster list C={C1,C2,…,C j ,…,C n }, C j ={C j1 ,C j2 ,…,C jf }; where n is the number of key bayonet device clusters, and f is the number of key bayonet devices in the jth key bayonet device cluster; Set the threshold of the number of key checkpoint devices. When the jth key checkpoint device cluster C j When the number of key checkpoint devices f in the vehicle is greater than the preset threshold value η of the number of key checkpoint devices, the vehicle number list B is used to obtain the vehicle number of the first vehicle through the jth key checkpoint device cluster C. j The second vehicle quantity list D of two adjacent key checkpoint devices j ={D j1 ,D j2 ,…, D j(f-1) }; Dividing an initial traffic sub-area according to the second vehicle quantity list and the number of vehicles passing through a plurality of key checkpoint devices connected in sequence during a historical time period; The target traffic sub-area is divided according to the initial traffic sub-area and a number of vehicle inflows and a number of vehicle outflows corresponding to each key checkpoint device in the initial traffic sub-area.

2. The method for dividing traffic sub-areas based on cross-modal feature association according to claim 1, characterized in that: The historical time periods include the morning peak historical period, the evening peak historical period, and the off-peak historical period.

3. The method for dividing traffic sub-areas based on cross-modal feature association according to claim 1, characterized in that: The process of clustering the initial checkpoint devices in the initial checkpoint device list A according to the first vehicle quantity list B and the vehicle quantity threshold θ to obtain the key checkpoint device cluster list C includes: Set a vehicle quantity threshold θ, and obtain the intermediate vehicle quantity list from the first vehicle quantity list B according to the preset vehicle quantity θ ,in, is the pth intermediate vehicle number, p=1, 2, ..., q, q is the number of intermediate vehicles, and the intermediate vehicle number refers to any first vehicle number that is not less than a preset vehicle number threshold θ; List B according to the number of intermediate vehicles 0 , get the intermediate vehicle quantity list B 0 Corresponding first-mount device list ,in, , is the number of the pth intermediate vehicles B 0 p The first initial mount device of the corresponding two initial mount devices, is the number of the pth intermediate vehicles B 0 p The latter of the two corresponding initial bayonet devices; List B for the number of intermediate vehicles 0 Corresponding first mount device list A 0 Deduplication is performed on the first card port device in the list to obtain a second card port device list; According to the arrangement order of the initial bayonet devices in the initial bayonet device list A, the bayonet devices that are sequentially connected in the second bayonet device list are clustered to obtain a key bayonet device cluster list C.

4. The method for dividing traffic sub-areas based on cross-modal feature association according to claim 1, characterized in that: The process of dividing the initial traffic sub-area according to the second vehicle quantity list D and the number of vehicles passing through a plurality of key checkpoints connected in sequence in a historical time period includes: Get the number of times C has passed in the historical time period jk To C j(k+r) The number of vehicles L k(k+r) ; when ω is the deviation threshold, r is updated to r+1, and the number of times C is passed in the historical time period is obtained. jk To C j(k+r+1) The number of vehicles L k(k+r+1) Perform iterative calculation until k+r>f, and C jk To C jf The road sections between them are merged and divided into initial traffic sub-areas; Set the second bayonet quantity threshold ε2 when When r≥ε2, C jk To C j(k+r-1) The road sections between them are merged and divided into initial traffic sub-areas.

5. The method for dividing traffic sub-areas based on cross-modal feature association according to claim 1, characterized in that: The process of dividing the target traffic sub-area according to the initial traffic sub-area and the vehicle inflow and outflow corresponding to each key checkpoint device in the initial traffic sub-area includes: According to the e-th key card device C in the j-th key card device cluster je The corresponding number of vehicles entering the road can obtain the road section and backup C corresponding to any vehicle entering the road je The first correlation ρ1 of the road segment is expressed as follows: ； In the formula, γ is C je The corresponding number of vehicles entering, φ σ C je The corresponding σth vehicle entry volume; Set the first correlation threshold ψ1, when ρ1≥ψ1, σ The corresponding road segments are added to the initial traffic sub-area; According to the e-th key card device C in the j-th key card device cluster je The corresponding number of vehicle outflows is obtained to obtain the road section and C corresponding to any vehicle outflow je The second correlation ρ2 of the road segment is expressed as follows: ； in, C je The corresponding ξ-th vehicle outflow; Set the second correlation threshold ψ2, when ρ2≥ψ2, The corresponding road segments are added to the initial traffic sub-area.

6. A traffic sub-area division method based on cross-modal feature association, characterized in that: The method comprises: Get the initial card port device list A={A1,A2,…, A m }, m is the number of initial bayonet devices; Get the first vehicle quantity list B={B1,B2,…,B m-1 }; For the first vehicle quantity list B={B1,B2,…,B m-1 }, and obtain the first checkpoint device combinations corresponding to the first w first vehicle quantities, thereby obtaining the first checkpoint device combination list Z={Z1,Z2,…,Z v ,…,Z w }, v∈[1,w], w is the initial screening number; Get the key vehicle quantity list T={T1,T2,…,T m-λ+1 }; Set the minimum number of vehicles to be screened λ , select from the key vehicle quantity list T a number of vehicles not less than the minimum screening vehicle quantity threshold ζ λ The number of key vehicles is selected, and the second checkpoint device combinations corresponding to the selected number of key vehicles are merged into a second checkpoint device combination list Y={Y1,Y2,…,Y α ,…,Y β }, α∈[1,β], β is the number of second bayonet device combinations; Update the first bayonet device combination list Z according to the second bayonet device combination list Y, and divide the road sections between each bayonet device combination in the updated first bayonet device combination list Z into initial traffic sub-areas; The target traffic sub-area is divided according to the initial traffic sub-area and a number of vehicle inflows and a number of vehicle outflows corresponding to each checkpoint device in the initial traffic sub-area.

7. The method for dividing traffic sub-areas based on cross-modal feature association according to claim 6, characterized in that: The process of updating the first bayonet device combination list Z according to the second bayonet device combination list Y and dividing the road sections between each bayonet device combination in the updated first bayonet device combination list Z into initial traffic sub-areas includes: When there is an αth second bayonet device combination Y α Contains the vth first bayonet device combination Z v When the first bayonet device combination Z v Delete from the first bayonet device combination list Z, and add the αth second bayonet device combination Y α Add to the first bayonet device combination list Z; When there is no αth second bayonet device combination Y α Contains the vth first bayonet device combination Z v , merging the second bayonet device combination list Y with the first bayonet device combination list Z to obtain an updated first bayonet device combination list Z; Update λ to λ+1, re-acquire the first checkpoint device combination list Z for iteration, until λ is updated to m+1, and divide the road sections between each checkpoint device combination in the current first checkpoint device combination list Z into initial traffic sub-areas.

8. An electronic device, comprising a memory and a processor, characterized in that: The memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the traffic sub-area division method based on cross-modal feature association as described in any one of claims 1-7 above.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for dividing traffic sub-areas based on cross-modal feature association as described in any one of claims 1 to 7 is implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the method for dividing traffic sub-areas based on cross-modal feature association described in any one of claims 1-7 is implemented.

Images