CN116844342B - Urban brain platform parking management system and method for realizing regional association dredging - Google Patents
Urban brain platform parking management system and method for realizing regional association dredging Download PDFInfo
- Publication number
- CN116844342B CN116844342B CN202311129868.7A CN202311129868A CN116844342B CN 116844342 B CN116844342 B CN 116844342B CN 202311129868 A CN202311129868 A CN 202311129868A CN 116844342 B CN116844342 B CN 116844342B
- Authority
- CN
- China
- Prior art keywords
- parking
- urban
- space
- regional
- region
- 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.)
- Active
Links
- 210000004556 brain Anatomy 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 17
- 238000002372 labelling Methods 0.000 claims abstract description 11
- 239000013598 vector Substances 0.000 claims description 50
- 238000004891 communication Methods 0.000 claims description 39
- 238000003062 neural network model Methods 0.000 claims description 30
- 238000007726 management method Methods 0.000 claims description 25
- 239000011159 matrix material Substances 0.000 claims description 14
- 230000003370 grooming effect Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 9
- 239000006185 dispersion Substances 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 241000764238 Isis Species 0.000 description 2
- 241000669618 Nothes Species 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096833—Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
- G08G1/148—Management of a network of parking areas
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Chemical & Material Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Analytical Chemistry (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a city brain platform parking management system and method for realizing regional association dredging. The system comprises: the parking space management system comprises a parking space data interface, a regional parking space real-time statistics module, a hot spot region labeling module, a regional relationship topology module, a regional prediction module and a parking region guiding module. The application can carry out real-time statistical monitoring on the parking space resources in a certain urban area range and accurately predict the parking demand of the vehicles in the area, thereby realizing the matching analysis of the parking space resources and the parking demand and executing real-time dredging under the condition that the parking space resources can not meet the parking demand.
Description
Technical Field
The application relates to the technical field of smart cities, in particular to a city brain platform parking management system and method for realizing regional association and mediation.
Background
The urban brain platform is a digital twin entity for establishing urban space based on computer software and hardware, so that the functions of information perception, simulation, resource scheduling, distributed control, dynamic visualization and the like are realized. The urban brain platform builds a base layer by various sensors and intelligent front-end facilities, and realizes the perception reporting of related events and data through wireless Internet of things covered by wide areas such as NB-IOT and the like; furthermore, data integration is realized on the support layer, and various support functions and algorithms oriented to subdivision fields and professional scenes are fused to perform data analysis; finally, supporting realization of various business processes related to city operation at an application layer, executing graphical display and chart statistics, and realizing early warning and auxiliary decision-making functions; the instructions of the application layer are also transmitted downstream to various intelligent front-end facilities of the base layer through the wireless internet of things so as to control the intelligent front-end facilities to execute necessary operations.
With the continuous expansion of the quantity of urban vehicles, parking management and dredging become a key problem of urban traffic operation, and are also an important subdivision application scene of urban brain platforms. In the prior art, functions related to parking of the urban brain platform are also limited to the relatively simple and fixed layers of parking space statistics, thermodynamic diagram drawing and the like. In the prior art, a solution is needed to enable the urban brain platform to effectively control traffic order, avoid the problems of illegal parking caused by unbalanced parking supply and demand contradiction, and efficiently utilize space resources of parking spaces.
Disclosure of Invention
In order to improve the parking management function of the urban brain platform, the application provides a parking management system and a parking management method for the urban brain platform for realizing regional association and dredging. The application can carry out real-time statistical monitoring on the parking space resources in a certain urban area range and accurately predict the parking demand of the vehicles in the area, thereby realizing the matching analysis of the parking space resources and the parking demand and executing real-time dredging under the condition that the parking space resources can not meet the parking demand.
The application provides an urban brain platform parking management system for realizing regional association and mediation, which is characterized by comprising the following components:
the parking space data interface is used for receiving the state data of each parking space uploaded by the parking space sensor of the urban brain platform base layer;
the regional parking space real-time statistics module is used for determining available parking space quantity time sequence vectors of the urban space region by counting state data of each parking space in real time according to the selected urban space region;
the hot spot region labeling module is used for labeling the current parking resource saturation of the hot spot urban space region according to the time sequence vector of the number of available parking spaces of the urban space region;
the regional relation topology module is used for establishing regional relation topology of the urban space region according to the interrelationship of the urban space region, wherein the interrelationship of the urban space region comprises a space communication type and a space communication weight;
the regional prediction module is used for predicting the parking resource saturation of other urban space regions with interrelation with the hot spot urban space region based on a trained prediction neural network model according to the parking resource saturation of the hot spot urban space region and the regional relation topology of the urban space region;
and the parking area dredging module is used for determining a dredging strategy for the hot spot urban space area according to the parking resource saturation of other urban space areas.
Preferably, the parking space data interface receives status data indicating the "occupied status" or "available status" of the parking space, and the parking space ID number.
Preferably, the regional parking space real-time statistics module is used for inquiring and extracting the state data of all the parking spaces located in any selected urban space region from a parking space data interface; and further, taking the preset time length as a statistics window, carrying out real-time statistics on the state data of all the parking spaces in the urban space area one by one to obtain the number of available parking spaces in each statistics window, and further arranging according to the time sequence of the statistics window to form a time sequence of the number of available parking spaces in the urban space area.
Preferably, the region labeling module labels the statistical window with the number of available parking spaces lower than a specific threshold as a hot spot window according to a time sequence vector of the number of available parking spaces corresponding to each urban space region, and labels the parking resource saturation label vector for the urban space region according to different distribution modes of the hot spot window on the statistical window represented by the time sequence vector.
Preferably, the regional relation topology module represents the types of the spatial communication relations between the urban spatial regions through the regional relation topology, and the types of the spatial communication relations are distinguished by road grades between the urban spatial regions; and the regional relation topology represents the strength of the spatial communication relation between 2 urban spatial regions by the weight value of the spatial communication relation weight matrix, and the weight value is in direct proportion to the road traffic flow between the urban spatial regions.
Preferably, the neural network model of the regional prediction module is input into a city space region set applied to a city brain platform and a related available parking space quantity time sequence vector set, a parking resource saturation label set, a regional relation topology of the city space region, a related type set of space communication relation, a label vector type set and a space communication weight matrix, and parameter vectors of all parameter matrices of the neural network model are determined through training, so that a model for classifying parking resource saturation labels of the city region space is obtained.
Preferably, the neural network model is expressed asThe method comprises the steps of carrying out a first treatment on the surface of the Wherein the input setI.e.For urban brain platform applicationsTo the point ofSets of urban spatial regionsAnd its associated set of available parking space quantity time sequence vectorsParking resource saturation label setRegional relationship topology for urban spatial regionType set of related spatial communication relationsTag vector type setSpatial connected weight matrix；Is all parameter matrix of neural network modelA constructed parameter vector; and in the neural network model training process, initializingCalculating the neural network modelIs the first of (2)Layer characteristics represent:
here the number of the elements is the number,, is thatNeural network model NoThe output characteristics of the layer are such that,is the firstThe characteristic dimensions of the layer are such that,representing the maximum activation function from element to element,representation and representationHas a relation ofIs set of indices for urban area space,representing the normalization constant given in advance,is the firstThe matrix of unknown weight parameters of the layer, is the hidden layer number of the neural network model, and the output of the softmax classification layer of the neural network model:the method comprises the steps of carrying out a first treatment on the surface of the Wherein the vector isIs the first of (2)Individual elements. And, calculate the classification loss:；
wherein,is a parking resource saturation label index set,is a one-hot tagIs the first of (2)The elements.
Preferably, when the parking area guiding module performs parking guiding towards any urban space area, and when the number of available parking spaces in the area of the nearest statistical window is lower than a specific threshold, selecting the parking resource saturation label from parking resource saturation labels of other urban space areas with space communication relation with the area according to the area prediction module, wherein the parking resource saturation label and the urban space area belong to other urban space areas with different types as target areas for parking resource guiding, and further selecting actual guiding areas from the target areas according to factors such as distance, road grade, traffic flow and the like.
Preferably, the parking area guiding module sends guiding information to a parking prompt display screen related to any urban space area based on the wireless internet of things, and based on the display of the guiding information, parking guiding to an actual guiding area is achieved.
The application further provides a city brain platform parking management method for realizing regional association and mediation, which comprises the following steps:
receiving state data of each parking space uploaded by a parking space sensor of a basic layer of the urban brain platform;
according to the selected urban space region, determining the number timing vectors of available parking spaces in the urban space region by counting the state data of each parking space in real time;
marking the current parking resource saturation of the urban space region according to the time sequence vector of the number of available parking spaces of the urban space region;
establishing a regional relationship topology of the urban space region according to the interrelation of the urban space region, wherein the interrelation of the urban space region comprises a space communication type and a space communication weight;
predicting the parking resource saturation of other urban space areas with interrelation with the urban space area based on a trained prediction neural network model according to the parking resource saturation of the urban space area and the area relation topology of the urban space area;
and determining a guiding strategy for the hot spot urban space region according to the parking resource saturation of other urban space regions.
Therefore, the urban brain platform realizes quantitative characterization by marking time sequence vectors and parking resource saturation label vectors on the basis of real-time acquisition and statistical monitoring of available information of parking spaces by taking the urban space area as a basic unit for parking management and dispersion, and further realizes parking resource saturation prediction and label classification representation of urban area space related to hot spot urban area space by using a deep trained neural network based on traffic, traffic flow and other relation topologies of the urban space area, thereby realizing targeted parking dispersion. The application is provided with a deep learning mechanism, improves the accuracy, predictability and high efficiency of parking and guiding, and improves the level of the urban brain platform in the aspects of parking management and guiding.
Drawings
The drawings that are needed in the embodiments or prior art description will be briefly described below, and it will be apparent that the drawings in the following description are some embodiments of the present application and that other drawings may be obtained from these drawings without inventive effort to those of ordinary skill in the art.
FIG. 1 is a block diagram of a parking management system for an urban brain platform for realizing regional association mediation;
fig. 2 is a flowchart of a method for managing parking of a regional association dredging urban brain platform provided by the application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application become more apparent, the technical solutions in the embodiments of the present application will be described in more detail below with reference to the accompanying drawings in the embodiments of the present application.
It should be noted that: in the drawings, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The described embodiments are some, but not all, embodiments of the application, and the embodiments and features of the embodiments of the application may be combined with each other without conflict. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, the following describes in detail an urban brain platform parking management system for implementing regional association mediation, which includes:
a parking space data interface 101, configured to receive status data of each parking space uploaded by a parking space sensor of a basic layer of the urban brain platform;
the regional parking space real-time statistics module 102 is configured to determine, according to a selected urban space region, a time sequence vector of the number of available parking spaces in the urban space region by real-time statistics of status data of each parking space;
the region labeling module 103 is configured to label the urban space region with the current parking resource saturation according to the time sequence vector of the number of available parking spaces in the urban space region;
the regional relationship topology module 104 is configured to establish a regional relationship topology of the urban spatial region according to a correlation of the urban spatial region, where the correlation of the urban spatial region includes a spatial communication type and a spatial communication weight;
the regional prediction module 105 is configured to predict, based on a trained prediction neural network model, the parking resource saturation of other urban spatial regions having a correlation with the urban spatial region according to the parking resource saturation of the urban spatial region and the regional relationship topology of the urban spatial region;
and the parking area grooming module 106 is configured to determine a grooming strategy for the hotspot urban space area according to the parking resource saturation of the other urban space areas.
The functions of each module of the system are specifically described below.
The parking space data interface 101 is used as a base layer data interface of the urban brain platform, and can receive the state data of each parking space uploaded by the parking space sensor through wireless internet of things technologies such as NB-IOT, wherein the state data indicates that the parking space is in an occupied state or an available state. The parking space sensor can adopt any one or more of infrared, geomagnetic coils, video, automatic lock lifting position sensing and other means, so that whether a corresponding parking space is occupied by a vehicle or not is determined, and state data indicating an occupied state or an available state is generated. Furthermore, the parking space sensor can integrate a wireless internet of things module, support wireless internet of things communication under protocols such as NB-IOT and the like, and can wirelessly upload the state data together with the associated information such as the parking space ID number and the like to the urban brain platform; the parking space sensor can adopt a triggering mechanism, namely, when the state of the state data of the parking space is switched, the state data after being updated is triggered to be uploaded. The parking space data interface 101 receives the uploaded state data and associated information such as the parking space ID number in real time. According to the ID number of the parking space, the urban space region distributed by the parking space can be obtained through searching the background database.
Regional parking space real-time statistics module 102 is oriented to a selected urban spatial region and receives data from the parking spacesPort 101 receives status data for a parking space. The urban space area is a space area with different space scales, selected from a preset range of urban space (such as a whole city or a certain urban area of the city), a certain building, a certain district, a certain business complex, a certain street, a certain school and the like, and each urban space area is abstracted into a basic entity unit and expressed asWhereinThe numbering representing the urban spatial region, whereby the entire urban spatial region applied by the urban brain platform is represented as a setWherein, the method comprises the steps of, wherein,is the total number of urban space areas.
Further, the regional parking space real-time statistics module 102 queries and extracts the state data of all the parking spaces located within the urban space region from the parking space data interface 101 for any one selected urban space region. Furthermore, the regional parking space real-time statistics module 102 uses a preset time length as a statistics window (for example, uses every 10 minutes as a statistics window), performs real-time statistics on the state data of all the parking spaces in the urban space region one by one to obtain the number of available parking spaces in each statistics window, and further arranges the available parking spaces according to the time sequence of the statistics window to form a time sequence of the number of available parking spaces in the urban space region. The time sequence of the number of available parking spaces may be expressed as a time sequence vectorThe form of (2):
wherein the method comprises the steps ofA number representing the region of urban space,represent the firstUrban space regionA time-ordered sequence vector corresponding to the number of available parking spaces,to the point ofRepresenting chronologically arranged firstTo the point ofThe number of available parking spaces in the urban space region on the statistical window is used as the attribute value of the time sequence vector.
Further, the set of available parking space quantity time sequence vectors of all urban space areas applied by the urban brain platform is expressed as。
The region labeling module 103 is configured to label the urban space region with the current parking resource saturation according to the time sequence vector of the number of available parking spaces in the urban space region. Specifically, the region labeling module 103 is according to the firstMarking a statistical window of which the number of available parking spaces is lower than a specific threshold value as a hot spot window according to a time sequence vector of the number of available parking spaces corresponding to each urban space region, and further, according to the time sequence vectorTo the point ofDifferent distribution modes of hot spot windows on the statistical windows, for the firstLabeling parking resource saturation label vector for each urban space regionWherein the parking resource saturation label vectorIs a one-hot tag vector, namely: if the first isThe urban space region belongs toClass, thenOtherwise, the device can be used to determine whether the current,. And, in addition, the processing unit,, for a set of all tag vector types,the number of elements is counted as。
Further, the parking resource saturation label set of all urban space areas applied by the urban brain platform is expressed as。
The regional relationship topology module 104 is configured to establish a regional relationship topology of the urban spatial region according to a correlation of the urban spatial region, where the correlation of the urban spatial region includes a spatial communication type and a spatial communication weight. In particular, the region relationship topology is represented asWhereinTriplet(s)Representing urban spatial areasAndis provided with betweenIs provided with a spatial communication relationship of (a),representing a set of types for all spatial relationships,the number of elements is counted asThe method comprises the steps of carrying out a first treatment on the surface of the The spatial communication relationship between urban spatial regions can be distinguished by road grades between urban spatial regions and can be collectedA weight value representing the spatial communication relation between the ijth urban spatial regions of the spatial communication weight matrix is expressed asWhich measures urban space areasThe intensity of the spatial communication relationship, the weight value is proportional to the road traffic flow between urban spatial regions.
The regional prediction module 105 is configured to predict, based on a trained prediction neural network model, the parking resource saturation of the urban spatial region and the regional relationship topology of the urban spatial region, the parking resource saturation of other urban spatial regions having a correlation with the urban spatial region.
Specifically, the neural network model used by the region prediction module 105 to predict parking resource saturation of other urban spatial regions having an interrelation with the urban spatial region is represented asThe method comprises the steps of carrying out a first treatment on the surface of the Wherein the input setI.e.For urban brain platform applicationsTo the point ofSets of urban spatial regionsAnd its associated set of available parking space quantity time sequence vectorsParking resource saturation label setRegional relationship topology for urban spatial regionType set of related spatial communication relationsTag vector type setSpatial connected weight matrix；Is all parameter matrix of neural network modelAnd (5) constructing a parameter vector.
Initializing during the training process of the neural network modelCalculating the neural network modelIs the first of (2)Layer characteristics represent:
here the number of the elements is the number,, is thatNeural network model NoThe output characteristics of the layer are such that,is the firstThe characteristic dimensions of the layer are such that,representing the maximum activation function from element to element,representation and representationHas a relation ofIs set of indices for urban area space,representing a standardised constant, given in advance, e.g. taking , Representing a collectionThe number of elements is determined by the number of elements,is the firstThe matrix of unknown weight parameters of the layer, is the hidden layer number of the neural network model.
Output of softmax classification layer of the neural network model:
wherein the vector isIs the first of (2)Individual elements. And, calculate the classification loss:；
wherein,is a parking resource saturation label index set,is a one-hot tagIs the first of (2)The elements. Updating model parameters using gradient descent (Adam) algorithm(i.e. allAnd) Optimizing the classification loss, and finally obtaining the input-based setNeural network model for classifying parking resource saturation labels in urban area space。
Further, a region prediction module 105 is configured to predict based on training according to the parking resource saturation of the urban space region and the region relationship topology of the urban space regionNeural network modelAnd predicting the parking resource saturation of other urban space areas with correlations with the urban space areas, wherein the parking resource saturation is expressed as the parking resource saturation label classification of the other urban space areas.
And the parking area grooming module 106 is configured to determine a grooming strategy for the hotspot urban space area according to the label classification of the parking resource saturation of the other urban space areas. In particular, when facing the firstWhen the number of available parking spaces in the area of the nearest statistical window is lower than a specific threshold value while parking guiding is performed in the area of the urban space, selecting a parking resource saturation label and a first parking resource saturation label from parking resource saturation labels of other urban space areas with spatial communication relation with the area according to the area prediction module 105The individual urban space regions belong to other urban space regions of different types and serve as target regions for guiding parking resources, and further, actual guiding regions are selected from the target regions according to factors such as distance, road grade and traffic flow.
The parking area grooming module 106 may be based on wireless internet of things, and may route to the first partyAnd the equipment such as a parking prompt display screen and the like related to the urban space region sends a guiding message, and the parking guiding to the actual guiding region is realized based on the display of the guiding message.
Referring to fig. 2, the present application further provides a method for parking management on a regional association and mediation urban brain platform, comprising the following steps:
s101, receiving state data of each parking space uploaded by a parking space sensor of a basic layer of the urban brain platform;
s102, determining available parking space quantity time sequence vectors of the urban space region by counting state data of each parking space in real time according to the selected urban space region;
s103, marking the current parking resource saturation of the urban space area according to the time sequence vector of the number of available parking spaces of the urban space area;
s104, establishing a regional relationship topology of the urban space region according to the interrelation of the urban space region, wherein the interrelation of the urban space region comprises a space communication type and a space communication weight;
s105, predicting the parking resource saturation of other urban space areas with interrelation with the urban space area based on a trained prediction neural network model according to the parking resource saturation of the urban space area and the area relation topology of the urban space area;
s106, determining a dispersion strategy facing the hot spot urban space area according to the parking resource saturation of other urban space areas.
Therefore, the urban brain platform realizes quantitative characterization by marking time sequence vectors and parking resource saturation label vectors on the basis of real-time acquisition and statistical monitoring of available information of parking spaces by taking the urban space area as a basic unit for parking management and dispersion, and further realizes parking resource saturation prediction and label classification representation of urban area space related to hot spot urban area space by using a deep trained neural network based on traffic, traffic flow and other relation topologies of the urban space area, thereby realizing targeted parking dispersion. The application is provided with a deep learning mechanism, improves the accuracy, predictability and high efficiency of parking and guiding, and improves the level of the urban brain platform in the aspects of parking management and guiding.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the scope of the present application should be included in the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An urban brain platform parking management system for implementing regional association grooming, comprising:
a parking space data interface for receiving the state data of each parking space uploaded by the parking space sensor of the basic layer of the urban brain platform,
the regional parking space real-time statistics module is used for determining available parking space quantity time sequence vectors of the urban space region by counting state data of each parking space in real time according to the selected urban space region;
the hot spot region labeling module is used for labeling the current parking resource saturation of the hot spot urban space region according to the time sequence vector of the number of available parking spaces of the urban space region;
the regional relation topology module is used for establishing regional relation topology of the urban space region according to the interrelationship of the urban space region, wherein the interrelationship of the urban space region comprises a space communication type and a space communication weight;
the regional prediction module is used for predicting the parking resource saturation of other urban space regions with interrelation with the hot spot urban space region based on a trained prediction neural network model according to the parking resource saturation of the hot spot urban space region and the regional relation topology of the urban space region;
and the parking area dredging module is used for determining a dredging strategy for the hot spot urban space area according to the parking resource saturation of other urban space areas.
2. The urban brain platform parking management system implementing regional association grooming of claim 1, wherein the parking space data interface receives status data indicating a parking space "occupied status" or "available status" and a parking space ID number.
3. The urban brain platform parking management system for realizing regional association mediation according to claim 2, wherein the regional parking space real-time statistics module is configured to query and extract the status data of all parking spaces located within any selected urban space region from a parking space data interface; and further, taking the preset time length as a statistics window, carrying out real-time statistics on the state data of all the parking spaces in the urban space area one by one to obtain the number of available parking spaces in each statistics window, and further arranging according to the time sequence of the statistics window to form a time sequence of the number of available parking spaces in the urban space area.
4. The urban brain platform parking management system for realizing regional association and mediation according to claim 3, wherein the regional labeling module labels the statistical window with the number of available parking spaces lower than a specific threshold as a hot spot window according to a time sequence vector of the number of available parking spaces corresponding to each urban space region, and further labels the urban space region with a parking resource saturation label vector according to different distribution modes of the hot spot window on the statistical window represented by the time sequence vector.
5. The urban brain platform parking management system for realizing regional association and mediation according to claim 4, wherein the regional relation topology module represents types of spatial communication relations among urban spatial regions through the regional relation topology, and the types of the spatial communication relations are distinguished by road grades among the urban spatial regions; and the regional relation topology represents the strength of the spatial communication relation between 2 urban spatial regions by the weight value of the spatial communication relation weight matrix, and the weight value is in direct proportion to the road traffic flow between the urban spatial regions.
6. The urban brain platform parking management system for realizing regional association mediation according to claim 5, wherein the neural network model of the regional prediction module is input into a urban space regional set and an associated available parking space quantity time sequence vector set applied to the urban brain platform, a parking resource saturation label set, a regional relationship topology of the urban space region, a type set of related space communication relationships, a label vector type set and a space communication weight matrix, and parameter vectors of all parameter matrices of the neural network model are determined through training, so as to obtain a model for classifying parking resource saturation labels of the urban space.
7. The urban brain platform parking management system implementing regional association grooming of claim 6, wherein the neural network model is represented asThe method comprises the steps of carrying out a first treatment on the surface of the Wherein the input set->I.e.Application of +.>To->Set of urban spatial regions->And its related set of available parking space number time sequence vectors +.>Parking resource saturation tag set->Regional relation topology of urban spatial region>And the type set of the related spatial communication relations +.>Tag vector type set->Spatial communication weight matrix +.>；/>Is a matrix of all parameters of the neural network model>A constructed parameter vector; and initializing +.>Calculating +.>Is>Layer characteristics represent:
here, a->, Is->Neural network model->Output characteristics of layer->Is->The characteristic dimensions of the layer are such that,representing the maximum activation function element by element, +.>Representation and->There is a relationship of->Index set of urban area space, +.>Represents a normalization constant given in advance, +.>Is->Unknown weight parameter matrix of layer, +.> Is the hidden layer number of the neural network model, and the output of the softmax classification layer of the neural network model: />The method comprises the steps of carrying out a first treatment on the surface of the Wherein the vector->Is>Individual elementsAnd, calculating a classification loss:
,
wherein,is a label index set with parking resource saturation degree, < >>Is a one-hot tag->Is>The elements.
8. The urban brain platform parking management system for realizing regional association and mediation according to claim 7, wherein when the parking regional mediation module performs parking and mediation for any urban space region, when the number of available parking spaces in the region is lower than a specific threshold value in a nearest statistical window, selecting a parking resource saturation label for other urban space regions having a spatial communication relationship with the region according to the regional prediction module, wherein the parking resource saturation label and the urban space region belong to other urban space regions of different types, as target regions of parking resource mediation, and further selecting an actual mediation region from the target regions according to factors such as distance, road grade, traffic flow and the like.
9. The urban brain platform parking management system for realizing regional association mediation according to claim 8, wherein the parking region mediation module sends a mediation message to a parking prompt display screen related to any urban space region based on the wireless internet of things, and realizes parking mediation to an actual mediation region based on the display of the mediation message.
10. A city brain platform parking management method for realizing regional association and mediation is characterized by comprising the following steps:
receiving state data of each parking space uploaded by a parking space sensor of a basic layer of the urban brain platform;
according to the selected urban space region, determining the number timing vectors of available parking spaces in the urban space region by counting the state data of each parking space in real time;
marking the current parking resource saturation of the urban space region according to the time sequence vector of the number of available parking spaces of the urban space region;
establishing a regional relationship topology of the urban space region according to the interrelation of the urban space region, wherein the interrelation of the urban space region comprises a space communication type and a space communication weight;
predicting the parking resource saturation of other urban space areas with interrelation with the urban space area based on a trained prediction neural network model according to the parking resource saturation of the urban space area and the area relation topology of the urban space area;
and determining a guiding strategy for the hot spot urban space region according to the parking resource saturation of other urban space regions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311129868.7A CN116844342B (en) | 2023-09-04 | 2023-09-04 | Urban brain platform parking management system and method for realizing regional association dredging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311129868.7A CN116844342B (en) | 2023-09-04 | 2023-09-04 | Urban brain platform parking management system and method for realizing regional association dredging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116844342A CN116844342A (en) | 2023-10-03 |
| CN116844342B true CN116844342B (en) | 2023-12-01 |
Family
ID=88165629
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311129868.7A Active CN116844342B (en) | 2023-09-04 | 2023-09-04 | Urban brain platform parking management system and method for realizing regional association dredging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116844342B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2447927A1 (en) * | 2010-10-26 | 2012-05-02 | Bmob Sagl | System and process for estimating the availability and/or occupied status of car parks located in a given urban area at a given time |
| CN202534162U (en) * | 2012-03-22 | 2012-11-14 | 武汉爱迪科技发展有限公司 | Public service system for intelligent parking lot |
| KR101976110B1 (en) * | 2018-07-27 | 2019-08-28 | 주식회사 에이디테크 | IoT standard-based parking guidance optimization system for smart city |
| CN112634110A (en) * | 2020-12-08 | 2021-04-09 | 浙江安防职业技术学院 | Digital twin space-time big data platform based on CIM technology |
| CN116416792A (en) * | 2023-03-13 | 2023-07-11 | 上海淼泊科技有限公司 | Urban parking management system |
-
2023
- 2023-09-04 CN CN202311129868.7A patent/CN116844342B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2447927A1 (en) * | 2010-10-26 | 2012-05-02 | Bmob Sagl | System and process for estimating the availability and/or occupied status of car parks located in a given urban area at a given time |
| CN202534162U (en) * | 2012-03-22 | 2012-11-14 | 武汉爱迪科技发展有限公司 | Public service system for intelligent parking lot |
| KR101976110B1 (en) * | 2018-07-27 | 2019-08-28 | 주식회사 에이디테크 | IoT standard-based parking guidance optimization system for smart city |
| CN112634110A (en) * | 2020-12-08 | 2021-04-09 | 浙江安防职业技术学院 | Digital twin space-time big data platform based on CIM technology |
| CN116416792A (en) * | 2023-03-13 | 2023-07-11 | 上海淼泊科技有限公司 | Urban parking management system |
Non-Patent Citations (4)
| Title |
|---|
| CBD区域的停车多级分层诱导模式研究;刘斯 等;长春师范大学学报(第04期);全文 * |
| 城市停车诱导管理信息系统的设计与实现;陈书雨 等;成都大学学报(自然科学版)(第01期);全文 * |
| 城市停车选择行为研究综述;郑楠 等;交通运输研究(第01期);全文 * |
| 基于熵权与模糊聚类算法的城市停车分区研究;缪千千 等;综合运输(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116844342A (en) | 2023-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lathia et al. | Measuring the impact of opening the London shared bicycle scheme to casual users | |
| Yu et al. | Analysing the spatial-temporal characteristics of bus travel demand using the heat map | |
| Desyllas et al. | Pedestrian demand modelling of large cities: an applied example from London | |
| Torrisi et al. | Innovative transport systems to promote sustainable mobility: Developing the model architecture of a traffic control and supervisor system | |
| US20120220274A1 (en) | Position information analysis device and position information analysis method | |
| JP2011138487A (en) | Method and system for traffic prediction based on space-time relation | |
| CN109618140B (en) | Vehicle monitoring method, device and system based on video monitoring and server | |
| CN104484993A (en) | Processing method of cell phone signaling information for dividing traffic zones | |
| JPWO2012105516A1 (en) | Terminal number estimation device and terminal number estimation method | |
| Alfeo et al. | A stigmergy-based analysis of city hotspots to discover trends and anomalies in urban transportation usage | |
| CN106951828B (en) | Urban area function attribute identification method based on satellite images and network | |
| CN112749825A (en) | Method and device for predicting destination of vehicle | |
| Jensen et al. | Location intelligence application in digital data activity dimensioning in smart cities | |
| CN113222442A (en) | Real-time traffic atmospheric pollution emission list calculation method and decision auxiliary method | |
| CN105323024A (en) | Network signal intensity detecting and fusing method | |
| Vidović et al. | Estimation of urban mobility using public mobile network | |
| WO2019104952A1 (en) | Scene intelligent analysis system and method based on metropolitan area level internet of things perceptual data | |
| Batista et al. | Identification of central points in road networks using betweenness centrality combined with traffic demand | |
| CN116844342B (en) | Urban brain platform parking management system and method for realizing regional association dredging | |
| CN104700616B (en) | Urban traffic pressure Forecasting Methodology and system | |
| CN110399537A (en) | A kind of alert spatio-temporal prediction method based on artificial intelligence technology | |
| CN116233759B (en) | Resident travel track investigation method and system | |
| CN118262516A (en) | Vehicle traffic prediction method and system based on multiple attention neural networks | |
| KR102054985B1 (en) | Monitoring method of path-based traffic, monitoring system, operating method for monitoring service of path-based traffic and operating system | |
| CN117315558A (en) | Park management system and method constructed by intelligent street lamps |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |