CN114255596B - Parking lot parking space recommendation system and method based on big data - Google Patents
Parking lot parking space recommendation system and method based on big data Download PDFInfo
- Publication number
- CN114255596B CN114255596B CN202210192487.2A CN202210192487A CN114255596B CN 114255596 B CN114255596 B CN 114255596B CN 202210192487 A CN202210192487 A CN 202210192487A CN 114255596 B CN114255596 B CN 114255596B
- Authority
- CN
- China
- Prior art keywords
- parking
- recommendation
- parking space
- space
- data
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- 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
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a parking lot parking space recommendation system and method based on big data, and belongs to the technical field of parking space recommendation. The system comprises an instruction information acquisition module, a three-dimensional calibration module, a multi-source data analysis module, a parking space change prediction module and a recommendation module; the output end of the instruction information acquisition module is connected with the input end of the three-dimensional calibration module; the output end of the three-dimensional checking module is connected with the input end of the multi-source data analysis module; the output end of the multi-source data analysis module is connected with the input end of the parking space change prediction module; the output end of the parking space change prediction module is connected with the input end of the recommendation module. The invention further provides a parking lot parking space recommendation method based on the big data, which is used for specific analysis. The parking space recommendation method and device can realize accurate recommendation of the parking space, meet the current digital and refined development requirements, and further meet the requirements of car owners.
Description
Technical Field
The invention relates to the technical field of parking space recommendation, in particular to a parking space recommendation system and method based on big data for a parking lot.
Background
With the rapid development of economy, the number of private cars is rapidly increased, and most of people go out by the private cars for work, play and the like, so that the number of parking spaces in a parking lot in a city is more and more impressive. The imbalance of supply and demand leads to more and more car owners to cause great trouble because the parking stall is in short supply, often need to find out the parking stall for a long time around the destination, and the difficult phenomenon that becomes general of parkking.
In the parking spaces of the parking lot, due to the geographical position factor of the parking lot, some parking spaces close to the wall, parking spaces with bearing columns and the like are inevitably generated in the construction process, the parking spaces have higher requirements on driving of car owners, in patent cn201811208241.x personalized parking space recommendation method and system with application date 2018.10.17, the analysis of the parking difficulty is provided, however, the parking difficulty is only roughly substituted by setting a mode that parking difficulty indexes D of parking spaces with blocking side directions on two sides are 0.8, parking difficulty indexes D of parking spaces for backing and warehousing are 0.6, parking difficulty indexes D of parking spaces with blocking parking spaces on one side are 0.4, and parking difficulty indexes D of parking spaces with blocking parking spaces on two sides are not 0.2, the influence on the accuracy of the system is large, the current digital development cannot be met, the accurate parking space recommendation is greatly interfered, and the final recommendation result is not friendly to the vehicle owner.
Disclosure of Invention
The invention aims to provide a parking lot parking space recommendation system and method based on big data, and aims to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme:
a parking lot parking space recommendation system based on big data comprises an instruction information acquisition module, a three-dimensional check module, a multi-source data analysis module, a parking space change prediction module and a recommendation module;
the instruction information acquisition module is used for acquiring parking instruction information issued by a vehicle owner, acquiring a planned position of the vehicle owner, establishing a parking recommendation area and calculating a time difference value when the vehicle owner reaches the planned position; the three-dimensional checking module is used for acquiring basic information of the vehicle, constructing a three-dimensional model of the vehicle, comparing idle parking spaces, deleting the parking spaces which do not meet the requirements and reducing data redundancy; the multi-source data analysis module is used for acquiring multi-source data, constructing a driving proficiency model of a vehicle owner and a parking difficulty model of a parking space, and analyzing the driving proficiency of the vehicle owner and the parking difficulty of the parking space; the parking space change prediction module is used for establishing a parking space change prediction model and predicting parking preference and parking duration of a parking space; the recommendation module is used for sequencing the parking spaces from large to small according to the final recommendation scores of the parking spaces and sequentially recommending the parking spaces to the car owners;
the output end of the instruction information acquisition module is connected with the input end of the three-dimensional calibration module; the output end of the three-dimensional checking module is connected with the input end of the multi-source data analysis module; the output end of the multi-source data analysis module is connected with the input end of the parking space change prediction module; the output end of the parking space change prediction module is connected with the input end of the recommendation module.
According to the technical scheme, the instruction information acquisition module comprises an owner positioning unit and an owner reservation unit;
the vehicle owner positioning unit is used for positioning and recording the current position of a vehicle owner; the vehicle owner reservation unit is used for acquiring reserved parking time and reserved parking place provided by a vehicle owner;
the output end of the vehicle owner positioning unit is connected with the input end of the three-dimensional checking module; the output end of the vehicle owner reservation unit is connected with the input end of the three-dimensional checking module.
According to the technical scheme, the multi-source data analysis module comprises a multi-source data acquisition unit, an owner driving proficiency analysis unit and a parking space parking difficulty analysis unit;
the multi-source data acquisition unit is used for acquiring multi-source data of a vehicle owner and a parking space; the vehicle owner driving proficiency analyzing unit is used for constructing a vehicle owner driving proficiency model and analyzing the driving proficiency of a vehicle owner; the parking space parking difficulty analysis unit is used for constructing a parking space parking difficulty model and analyzing the parking difficulty of the parking space;
the output end of the multi-source data acquisition unit is respectively connected with the input ends of the vehicle owner driving proficiency analysis unit and the parking space parking difficulty analysis unit; the output ends of the car owner driving proficiency analysis unit and the parking space parking difficulty analysis unit are connected with the input end of the parking space change prediction module.
According to the technical scheme, the parking space change prediction module comprises a parking preference analysis unit and a parking duration analysis unit;
the parking preference analysis unit is used for analyzing the parking preference condition of each parking space in the parking lot and acquiring the parking preference probability; the parking duration analysis unit is used for analyzing the parking duration of the car owner in the parking lot and taking a mode as the predicted parking duration;
the output end of the parking preference analysis unit is connected with the input end of the recommendation module; the output end of the parking time length analysis unit is connected with the input end of the recommendation module.
According to the technical scheme, the recommendation module comprises a parking space recommendation score sorting unit and a recommendation unit;
the parking space recommendation score sorting unit is used for constructing an optimal parking space recommendation model, calculating parking space recommendation scores according to the optimal parking space recommendation model and sorting the calculated parking space recommendation scores from large to small; the recommendation unit is used for recommending the corresponding parking spaces to the vehicle owners according to the sequence;
the output end of the parking place recommendation score sorting unit is connected with the input end of the recommendation unit; and the output end of the recommendation unit is connected to the vehicle owner port.
A parking lot parking space recommendation method based on big data comprises the following steps:
s1, acquiring vehicle owner parking instruction information data, acquiring a planned position of a vehicle owner, establishing a parking recommendation area A by taking the planned position of the vehicle owner as a circle center and taking R as a radius, and acquiring a time difference value of the vehicle owner to the planned position;
s2, obtaining basic information of the vehicle, constructing a three-dimensional model of the vehicle, comparing all idle parking spaces in the parking recommendation area A, and deleting a recommendation system for the parking spaces which do not meet the size or height of the vehicle;
s3, acquiring vehicle owner information data, extracting vehicle owner characteristics, establishing a vehicle owner driving proficiency model, and calculating to obtain vehicle owner driving proficiency;
s4, obtaining the information of the free parking spaces, extracting the characteristics of the parking spaces, establishing a parking difficulty model of the parking spaces, and calculating the parking difficulty of each parking space;
s5, obtaining parking place historical data in the parking recommendation area A, establishing a parking place change prediction model, and analyzing parking preference and parking time of the parking place;
and S6, establishing an optimal parking space recommendation model, and recommending the corresponding parking space list to the vehicle owner according to the sequence of the parking space recommendation scores from large to small.
According to the above technical solution, in step S3, the vehicle owner driving proficiency model includes:
acquiring owner information data including driving age, accident rate, average vehicle speed and violation rate;
the weight ratio of construction is g1、g2、g3、g4;
Constructing a vehicle owner driving proficiency model:
wherein the content of the first and second substances,representing a driving age conversion value;representing the accident rate conversion value;represents the average vehicle speed conversion value;representing the violation rate conversion value.
Setting a functional relation in the system, and converting the driving age, the accident rate, the average vehicle speed and the violation rate to facilitate calculation; for example, driving age conversion can utilize a linear function because the conversion ratio is simple, and the proficiency is inevitably higher and higher as the driving age is increased; the average vehicle speed can be converted by utilizing a parabola, because the low vehicle speed represents that the tendency of low proficiency is large, and the influence degree of the normal vehicle speed on the proficiency is low, namely if the vehicle runs at a low vehicle speed all the time, the driving proficiency condition of the vehicle owner is more prone to be judged, and if the vehicle runs at the normal vehicle speed, the driving proficiency condition of the vehicle owner is more difficult to be judged.
According to the above technical scheme, in step S4, the parking difficulty model includes:
acquiring parking space information data;
constructing a model relation between parking space parking difficulty and parking space information data:
b is a parking space parking difficulty matrix; h is a parking space information data matrix;is a coefficient vector matrix;is a matrix of interference terms;
wherein, p represents the characteristic quantity of the parking space information; n represents n normalized data values for each feature;
wherein the content of the first and second substances,is the intercept;、、、is a coefficient vector;、、the parking space information characteristic value is obtained;is an interference value; the ratio of i =1, 2,,n;
and estimating by using a least square method to obtain an optimal coefficient vector and an interference value.
The information data of the parking spaces can comprise characteristic factors such as parking spaces close to walls, columns on the parking spaces and the like.
For the parking difficulty of the parking space, the measurement standard set by the invention is mean square error, and the mean square error refers to the mean square error between the predicted value and the actual value. The smaller the mean variance, the smaller the difference between the test value and the actual value, i.e. the better the model performance. Therefore, B and H are fixed by using training data, and then the optimal beta and epsilon are found by using a least square method, so that an optimal model is obtained.
According to the above technical solution, in step S5, the parking space change prediction model includes:
obtaining historical parking data of a parking lot, and respectively constructing a parking space preference model and a parking duration prediction model;
The parking space preference model is as follows:
wherein the content of the first and second substances,the parking initial probability is the parking space parking initial probability;the number of time series contained in the historical data time interval is shown;is as followsParking times of the parking places in a period of time;is as followsTotal number of parking times of the parking lot in a period of time;
obtaining a time difference value, and establishing a growth curve function:
wherein, the first and the second end of the pipe are connected with each other,parking for the parking space and growing probability;、、are all the values of the parameters,(ii) a In thatWhen the temperature of the water is higher than the set temperature,=;
obtaining the inflection point of the growth curve function, and recording as M: (,) The inflection point is the growth speed saturation point of the growth curve function;
in the growth curve function, the initial stage followsIn the growth of the plant, the growth rate of the plant,the increasing speed of the curve is gradually increased, and the curve shows a rapidly rising situation; after reaching an inflection point M, the saturation degree of the function reaches the end stage and begins to followIncrease inThe growth is slow, the growth speed approaches to 0,approaching 100%, the curve develops horizontally; the growth speed change point is denoted as an inflection point. This is because the parking lot is entered with the increase of time at the beginningThe vehicles are continuously increased, the probability of parking in the parking space is increased at a higher speed, the time is gradually increased, the probability of parking in the parking space reaches a certain height, the increase is gradually slow, the increase speed is close to 0, the parking probability is close to 100%, but the parking probability cannot reach 100%.
Obtaining the parking time of all vehicles in the parking lot, selecting a mode as the predicted parking time and recording the predicted parking time as the predicted parking time;
the time difference value of the set vehicle owner arriving at the planned position comprises the time sequence numberIs detected.
According to the above technical solution, in step S6, the best parking space recommendation model further includes:
respectively acquiring data sets of driving proficiency data, parking space parking difficulty data and parking space change data of a vehicle owner;
constructing an optimal parking space recommendation model:
wherein K is the parking space recommendation score;Scoring the normalized base parking space;、、respectively obtaining data mean values of driving proficiency data, parking space parking difficulty data and parking space change data of the car owner;、、respectively obtaining standard deviations of driving proficiency data, parking space parking difficulty data and parking space change data of the car owner; b is a parking difficulty value of the parking space;
and sorting the parking spaces from large to small according to the parking space recommendation score, and sequentially pushing the parking spaces to the car owner.
Compared with the prior art, the invention has the following beneficial effects:
the method comprises the steps of firstly obtaining basic information of a vehicle, constructing a three-dimensional model of the vehicle, comparing all idle parking spaces in a parking recommendation area, deleting a recommendation system for the parking spaces which do not meet the size or height of the vehicle, reducing data redundancy and operation complexity; calculating the driving proficiency of the vehicle owner by establishing a vehicle owner driving proficiency model; establishing a parking space parking difficulty model, and calculating the parking difficulty of each parking space; establishing a parking space change prediction model, and analyzing parking preference and parking time of a parking space; by combining the factors, an optimal parking place recommendation model is established, and corresponding parking place lists are recommended to car owners according to the sequence of the parking place recommendation scores from large to small.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart diagram of a big data-based parking lot space recommendation system and method according to the present invention;
FIG. 2 is a schematic diagram of a growth curve function of a big data-based parking lot stall recommendation method of the present invention;
FIG. 3 is a schematic diagram of a judgment function of the method for recommending parking spaces in a parking lot based on big data.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-3, the present invention provides a technical solution:
a parking lot parking space recommendation system based on big data comprises an instruction information acquisition module, a three-dimensional check module, a multi-source data analysis module, a parking space change prediction module and a recommendation module;
the instruction information acquisition module is used for acquiring parking instruction information issued by a vehicle owner, acquiring a planned position of the vehicle owner, establishing a parking recommendation area and calculating a time difference value when the vehicle owner reaches the planned position; the three-dimensional checking module is used for acquiring basic information of the vehicle, constructing a three-dimensional model of the vehicle, comparing idle parking spaces, deleting the parking spaces which do not meet the requirements and reducing the data redundancy; the multi-source data analysis module is used for acquiring multi-source data, constructing a driving proficiency model of a vehicle owner and a parking difficulty model of a parking space, and analyzing the driving proficiency of the vehicle owner and the parking difficulty of the parking space; the parking space change prediction module is used for establishing a parking space change prediction model and predicting parking preference and parking duration of a parking space; the recommendation module is used for sequencing the parking spaces from large to small according to the final recommendation scores of the parking spaces and sequentially recommending the parking spaces to the car owners;
the output end of the instruction information acquisition module is connected with the input end of the three-dimensional calibration module; the output end of the three-dimensional checking module is connected with the input end of the multi-source data analysis module; the output end of the multi-source data analysis module is connected with the input end of the parking space change prediction module; the output end of the parking space change prediction module is connected with the input end of the recommendation module.
The instruction information acquisition module comprises an owner positioning unit and an owner reservation unit;
the vehicle owner positioning unit is used for positioning and recording the current position of a vehicle owner; the vehicle owner reservation unit is used for acquiring reserved parking time and reserved parking place provided by a vehicle owner;
the output end of the vehicle owner positioning unit is connected with the input end of the three-dimensional checking module; the output end of the vehicle owner reservation unit is connected with the input end of the three-dimensional checking module.
The multi-source data analysis module comprises a multi-source data acquisition unit, an owner driving proficiency analysis unit and a parking space parking difficulty analysis unit;
the multi-source data acquisition unit is used for acquiring multi-source data of a vehicle owner and a parking space; the vehicle owner driving proficiency analyzing unit is used for constructing a vehicle owner driving proficiency model and analyzing the driving proficiency of a vehicle owner; the parking space parking difficulty analysis unit is used for constructing a parking space parking difficulty model and analyzing the parking difficulty of the parking space;
the output end of the multi-source data acquisition unit is respectively connected with the input ends of the vehicle owner driving proficiency analysis unit and the parking space parking difficulty analysis unit; the output ends of the car owner driving proficiency analysis unit and the parking space parking difficulty analysis unit are connected with the input end of the parking space change prediction module.
The parking space change prediction module comprises a parking preference analysis unit and a parking duration analysis unit;
the parking preference analysis unit is used for analyzing the parking preference condition of each parking space in the parking lot and acquiring the parking preference probability; the parking duration analysis unit is used for analyzing the parking duration of the car owner in the parking lot and taking a mode as the predicted parking duration;
the output end of the parking preference analysis unit is connected with the input end of the recommendation module; and the output end of the parking time length analysis unit is connected with the input end of the recommendation module.
The recommendation module comprises a parking space recommendation score sorting unit and a recommendation unit;
the parking space recommendation score sorting unit is used for constructing an optimal parking space recommendation model, calculating parking space recommendation scores according to the optimal parking space recommendation model and sorting the calculated parking space recommendation scores from large to small; the recommendation unit is used for recommending the corresponding parking spaces to the vehicle owners according to the sequence;
the output end of the parking place recommendation score sorting unit is connected with the input end of the recommendation unit; and the output end of the recommendation unit is connected to the vehicle owner port.
A parking lot parking space recommendation method based on big data comprises the following steps:
s1, acquiring vehicle owner parking instruction information data, acquiring a planned position of a vehicle owner, establishing a parking recommendation area A by taking the planned position of the vehicle owner as a circle center and taking R as a radius, and acquiring a time difference value of the vehicle owner to the planned position;
s2, obtaining basic information of the vehicle, constructing a three-dimensional model of the vehicle, comparing all idle parking spaces in the parking recommendation area A, and deleting a recommendation system for the parking spaces which do not meet the size or height of the vehicle;
s3, acquiring vehicle owner information data, extracting vehicle owner characteristics, establishing a vehicle owner driving proficiency model, and calculating to obtain vehicle owner driving proficiency;
s4, obtaining the information of the free parking spaces, extracting the characteristics of the parking spaces, establishing a parking difficulty model of the parking spaces, and calculating the parking difficulty of each parking space;
s5, obtaining parking place historical data in the parking recommendation area A, establishing a parking place change prediction model, and analyzing parking preference and parking time of the parking place;
and S6, establishing an optimal parking space recommendation model, and recommending the corresponding parking space list to the vehicle owner according to the sequence of the parking space recommendation scores from large to small.
In step S3, the vehicle owner driving proficiency model includes:
acquiring owner information data including driving age, accident rate, average vehicle speed and violation rate;
the weight ratio of construction is g1、g2、g3、g4;
Constructing a vehicle owner driving proficiency model:
wherein the content of the first and second substances,representing a driving age conversion value;representing the accident rate conversion value;means for expressingAverage vehicle speed conversion value;representing the violation rate conversion value.
In step S4, the parking difficulty model includes:
acquiring parking space information data;
constructing a model relation between the parking space parking difficulty and the parking space information data:
b is a parking space parking difficulty matrix; h is a parking space information data matrix;is a coefficient vector matrix;is a matrix of interference terms;
wherein, p represents the characteristic quantity of the parking space information; n represents n normalized data values for each feature;
wherein the content of the first and second substances,is the intercept;、、、is a coefficient vector;、、the parking space information characteristic value is obtained;is an interference value; the ratio of i =1, 2,,n;
and estimating by using a least square method to obtain an optimal coefficient vector and an interference value.
In step S5, the space change prediction model includes:
obtaining historical parking data of a parking lot, and respectively constructing a parking space preference model and a parking duration prediction model;
The parking space preference model is as follows:
wherein, the first and the second end of the pipe are connected with each other,the parking initial probability is the parking space parking initial probability;the number of time series contained in the historical data time interval is shown;is as followsParking times of the parking places in a period of time;is as followsTotal number of parking times of the parking lot in a period of time;
obtaining a time difference value, and establishing a growth curve function:
wherein the content of the first and second substances,parking for the parking space and growing probability;、、are all made ofThe value of the parameter(s) is,(ii) a In thatWhen the temperature of the water is higher than the set temperature,=;
obtaining the inflection point of the growth curve function, and recording as M: (,) The inflection point is the growth curve function growth speed saturation point;
obtaining the parking time of all vehicles in the parking lot, selecting a mode as the predicted parking time and recording the predicted parking time as the predicted parking time;
the time difference value of the set vehicle owner arriving at the planned position comprises the time sequence numberIs detected.
In step S6, the best space recommendation model further includes:
respectively acquiring data sets of driving proficiency data, parking space parking difficulty data and parking space change data of a vehicle owner;
constructing an optimal parking space recommendation model:
wherein K is the parking space recommendation score;scoring the normalized base parking space;、、respectively obtaining data mean values of driving proficiency data, parking space parking difficulty data and parking space change data of the car owner;、、respectively obtaining standard deviations of driving proficiency data, parking space parking difficulty data and parking space change data of the car owner; b is a parking difficulty value of the parking space;
and sorting the parking spaces from large to small according to the parking space recommendation score, and sequentially pushing the parking spaces to the car owner.
In this embodiment:
a vehicle owner issues instruction information data, and the vehicle is parked at a Y point, so that a parking recommendation area is established around the Y point;
acquiring vehicle information data of the vehicle owner, establishing a three-dimensional model, acquiring information of idle parking spaces in a recommended parking area, and deleting the unsatisfactory parking spaces;
acquiring owner information data, including the driving age of 3 years, the accident rate of 0%, the average vehicle speed of 65km/h and the violation rate of 25%;
the weight ratio of construction is g1=0.6、g2=0.1、g3=0.2、g4=0.1;
The conversion model is respectively set as a linear function, a parabola and a linear function;
constructing a vehicle owner driving proficiency model:
wherein the content of the first and second substances,representing a driving age conversion value;representing the accident rate conversion value;represents the average vehicle speed conversion value;representing the violation rate conversion value.
Calculating to obtain the driving proficiency of the vehicle ownerDegree of a1;
Acquiring parking space information data;
wherein the content of the first and second substances,is the intercept;、、、is a coefficient vector;、、the parking space information characteristic value is obtained;is an interference value; the ratio of i =1, 2,,n;
acquiring a parking space parking difficulty value of each parking space;
Constructing a parking space preference model:
wherein the content of the first and second substances,the parking initial probability is the parking space parking initial probability;the number of time series contained in the historical data time interval;is a firstParking times of the parking places in a period of time;is as followsTotal number of parking times of the parking lot in a period of time;
obtaining a time difference value, and establishing a growth curve function:
wherein the content of the first and second substances,parking for the parking space and growing probability;、、are all the values of the parameters,(ii) a In thatWhen the temperature of the water is higher than the set temperature,=;
obtaining the inflection point of the growth curve function, and recording as M: (,) The inflection point is the growth curve function growth speed saturation point;
obtaining the parking time of all vehicles in the parking lot, selecting a mode as the predicted parking time and recording the predicted parking time as the predicted parking time;
the time difference value of the set vehicle owner arriving at the planned position comprises the time sequence numberIs detected.
Constructing an optimal parking space recommendation model:
wherein K is the parking space recommendation score;scoring the normalized base parking space;、、respectively obtaining data mean values of driving proficiency data, parking space parking difficulty data and parking space change data of the car owner;、、respectively obtaining standard deviations of driving proficiency data, parking space parking difficulty data and parking space change data of the car owner; b is a parking difficulty value of the parking space;
obtaining the parking place recommendation scores of all the free parking places;
and sorting the parking spaces from large to small according to the parking space recommendation score, and sequentially pushing the parking spaces to the car owner.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. The utility model provides a parking area parking stall recommendation method based on big data which characterized in that: the method comprises the following steps:
s1, acquiring vehicle owner parking instruction information data, acquiring a planned position of a vehicle owner, establishing a parking recommendation area A by taking the planned position of the vehicle owner as a circle center and taking R as a radius, and acquiring a time difference value of the vehicle owner to the planned position;
s2, obtaining basic information of the vehicle, constructing a three-dimensional model of the vehicle, comparing all idle parking spaces in the parking recommendation area A, and deleting a recommendation system for the parking spaces which do not meet the size or height of the vehicle;
s3, acquiring vehicle owner information data, extracting vehicle owner characteristics, establishing a vehicle owner driving proficiency model, and calculating to obtain vehicle owner driving proficiency;
s4, obtaining the information of the free parking spaces, extracting the characteristics of the parking spaces, establishing a parking difficulty model of the parking spaces, and calculating the parking difficulty of each parking space;
s5, obtaining parking place historical data in the parking recommendation area A, establishing a parking place change prediction model, and analyzing parking preference and parking time of the parking place;
s6, establishing an optimal parking place recommendation model, and recommending the corresponding parking place list to the vehicle owner according to the sequence of the parking place recommendation scores from large to small;
in step S3, the vehicle owner driving proficiency model includes:
acquiring owner information data including driving age, accident rate, average vehicle speed and violation rate;
the weight ratio of construction is g1、g2、g3、g4;
Constructing a vehicle owner driving proficiency model:
wherein the content of the first and second substances,representing a driving age conversion value;representing the accident rate conversion value;represents the average vehicle speed conversion value;a representative violation rate conversion value;
in step S4, the parking difficulty model includes:
acquiring parking space information data;
constructing a model relation between the parking space parking difficulty and the parking space information data:
b is a parking space parking difficulty matrix; h is a parking space information data matrix;is a coefficient vector matrix;is a matrix of interference terms;
wherein, p represents the characteristic quantity of the parking space information; n represents n normalized data values for each feature;
wherein the content of the first and second substances,is the intercept;、、、is a coefficient vector;、、the parking space information characteristic value is obtained;is an interference value; the ratio of i =1, 2,,n;
estimating by using a least square method to obtain an optimal coefficient vector and an interference value;
in step S5, the space change prediction model includes:
obtaining historical parking data of a parking lot, and respectively constructing a parking space preference model and a parking duration prediction model;
The parking space preference model is as follows:
wherein the content of the first and second substances,the parking initial probability is the parking space parking initial probability;the number of time series contained in the historical data time interval is shown;is as followsParking times of the parking places in a period of time;is as followsTotal number of parking times of the parking lot in a period of time;
obtaining a time difference value, and establishing a growth curve function:
wherein, the first and the second end of the pipe are connected with each other,parking for the parking space and growing probability;、、are all the values of the parameters,(ii) a s is greater than 1; in thatWhen the temperature of the water is higher than the set temperature,=;
obtaining the inflection point of the growth curve function, and recording as M: (,) The inflection point is the growth curve function growth speed saturation point;
obtaining the parking time of all vehicles in the parking lot, selecting a mode as the predicted parking time and recording the predicted parking time as the predicted parking time;
the time difference value of the set vehicle owner arriving at the planned position comprises the time sequence numberA threshold number of;
in step S6, the best space recommendation model further includes:
respectively acquiring data sets of driving proficiency data, parking space parking difficulty data and parking space change data of an automobile owner;
constructing an optimal parking space recommendation model:
wherein K is the parking space recommendation score;scoring the normalized base parking space;、、respectively obtaining data mean values of driving proficiency data, parking space parking difficulty data and parking space change data of the car owner;、、respectively obtaining standard deviations of driving proficiency data, parking space parking difficulty data and parking space change data of the car owner; b is a parking difficulty value of the parking space;
and sorting the parking spaces from large to small according to the parking space recommendation score, and sequentially pushing the parking spaces to the car owner.
2. The big data-based parking lot space recommendation system applied to the big data-based parking lot space recommendation method according to claim 1 is characterized in that: the system comprises an instruction information acquisition module, a three-dimensional calibration module, a multi-source data analysis module, a parking space change prediction module and a recommendation module;
the instruction information acquisition module is used for acquiring parking instruction information issued by a vehicle owner, acquiring a planned position of the vehicle owner, establishing a parking recommendation area and calculating a time difference value of the vehicle owner reaching the planned position; the three-dimensional checking module is used for acquiring basic information of the vehicle, constructing a three-dimensional model of the vehicle, comparing idle parking spaces, deleting the parking spaces which do not meet the requirements and reducing data redundancy; the multi-source data analysis module is used for acquiring multi-source data, constructing a driving proficiency model of a vehicle owner and a parking difficulty model of a parking space, and analyzing the driving proficiency of the vehicle owner and the parking difficulty of the parking space; the parking space change prediction module is used for establishing a parking space change prediction model and predicting parking preference and parking duration of a parking space; the recommendation module is used for sequencing the parking spaces from large to small according to the final recommendation scores of the parking spaces and sequentially recommending the parking spaces to the car owners;
the output end of the instruction information acquisition module is connected with the input end of the three-dimensional calibration module; the output end of the three-dimensional checking module is connected with the input end of the multi-source data analysis module; the output end of the multi-source data analysis module is connected with the input end of the parking space change prediction module; the output end of the parking space change prediction module is connected with the input end of the recommendation module.
3. The big data-based parking lot space recommendation system of the big data-based parking lot space recommendation method according to claim 2, characterized in that: the instruction information acquisition module comprises an owner positioning unit and an owner reservation unit;
the vehicle owner positioning unit is used for positioning and recording the current position of a vehicle owner; the vehicle owner reservation unit is used for acquiring reserved parking time and reserved parking place provided by a vehicle owner;
the output end of the vehicle owner positioning unit is connected with the input end of the three-dimensional checking module; the output end of the vehicle owner reservation unit is connected with the input end of the three-dimensional checking module.
4. The big data-based parking lot space recommendation system of the big data-based parking lot space recommendation method according to claim 2, characterized in that: the multi-source data analysis module comprises a multi-source data acquisition unit, an owner driving proficiency analysis unit and a parking space parking difficulty analysis unit;
the multi-source data acquisition unit is used for acquiring multi-source data of a vehicle owner and a parking space; the vehicle owner driving proficiency analyzing unit is used for constructing a vehicle owner driving proficiency model and analyzing the driving proficiency of a vehicle owner; the parking space parking difficulty analysis unit is used for constructing a parking space parking difficulty model and analyzing the parking difficulty of the parking space;
the output end of the multi-source data acquisition unit is respectively connected with the input ends of the vehicle owner driving proficiency analysis unit and the parking space parking difficulty analysis unit; the output ends of the car owner driving proficiency analysis unit and the parking space parking difficulty analysis unit are connected with the input end of the parking space change prediction module.
5. The big data-based parking lot space recommendation system of the big data-based parking lot space recommendation method according to claim 2, characterized in that: the parking space change prediction module comprises a parking preference analysis unit and a parking duration analysis unit;
the parking preference analysis unit is used for analyzing the parking preference condition of each parking space in the parking lot and acquiring the parking preference probability; the parking duration analysis unit is used for analyzing the parking duration of the car owner in the parking lot and taking a mode as the predicted parking duration;
the output end of the parking preference analysis unit is connected with the input end of the recommendation module; the output end of the parking time length analysis unit is connected with the input end of the recommendation module.
6. The big data-based parking lot space recommendation system of the big data-based parking lot space recommendation method according to claim 2, characterized in that: the recommendation module comprises a parking space recommendation score sorting unit and a recommendation unit;
the parking space recommendation score sorting unit is used for constructing an optimal parking space recommendation model, calculating parking space recommendation scores according to the optimal parking space recommendation model and sorting the calculated parking space recommendation scores from large to small; the recommendation unit is used for recommending the corresponding parking spaces to the vehicle owners according to the sequence;
the output end of the parking place recommendation score sorting unit is connected with the input end of the recommendation unit; and the output end of the recommendation unit is connected to the vehicle owner port.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210192487.2A CN114255596B (en) | 2022-03-01 | 2022-03-01 | Parking lot parking space recommendation system and method based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210192487.2A CN114255596B (en) | 2022-03-01 | 2022-03-01 | Parking lot parking space recommendation system and method based on big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114255596A CN114255596A (en) | 2022-03-29 |
CN114255596B true CN114255596B (en) | 2022-05-17 |
Family
ID=80800114
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210192487.2A Active CN114255596B (en) | 2022-03-01 | 2022-03-01 | Parking lot parking space recommendation system and method based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114255596B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116189470B (en) * | 2022-12-20 | 2023-10-10 | 北京阳光海天停车管理有限公司 | Computer data intelligent recognition system and method based on artificial intelligence |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103871270A (en) * | 2014-02-28 | 2014-06-18 | 张剑锋 | Cloud computing and big data-based parking method and system |
CN105427660A (en) * | 2015-11-24 | 2016-03-23 | 上海汽车集团股份有限公司 | Intelligent parking information providing method and apparatus |
CN108122426A (en) * | 2016-11-28 | 2018-06-05 | 东莞职业技术学院 | City parking inducible system and method based on Internet of Things |
CN108140313A (en) * | 2015-10-30 | 2018-06-08 | 三菱电机株式会社 | Parking aid and parking assistance method |
CN108986527A (en) * | 2018-07-17 | 2018-12-11 | 新华三云计算技术有限公司 | A kind of parking position guiding method, device, system and electronic equipment |
-
2022
- 2022-03-01 CN CN202210192487.2A patent/CN114255596B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103871270A (en) * | 2014-02-28 | 2014-06-18 | 张剑锋 | Cloud computing and big data-based parking method and system |
CN108140313A (en) * | 2015-10-30 | 2018-06-08 | 三菱电机株式会社 | Parking aid and parking assistance method |
CN105427660A (en) * | 2015-11-24 | 2016-03-23 | 上海汽车集团股份有限公司 | Intelligent parking information providing method and apparatus |
CN108122426A (en) * | 2016-11-28 | 2018-06-05 | 东莞职业技术学院 | City parking inducible system and method based on Internet of Things |
CN108986527A (en) * | 2018-07-17 | 2018-12-11 | 新华三云计算技术有限公司 | A kind of parking position guiding method, device, system and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN114255596A (en) | 2022-03-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110415516B (en) | Urban traffic flow prediction method and medium based on graph convolution neural network | |
CN106127329A (en) | Order forecast method and device | |
CN107919014B (en) | Taxi running route optimization method for multiple passenger mileage | |
CN102324128A (en) | Method for predicting OD (Origin-Destination) passenger flow among bus stations on basis of IC (Integrated Circuit)-card record and device | |
CN104200267A (en) | Vehicle driving economy evaluation system and vehicle driving economy evaluation method | |
CN111415752B (en) | Hand-foot-and-mouth disease prediction method integrating meteorological factors and search indexes | |
CN106767875A (en) | A kind of paths planning method based on weather and driver driving experience | |
CN112863182B (en) | Cross-modal data prediction method based on transfer learning | |
CN113177657B (en) | Rail transit passenger flow prediction method and device | |
CN114255596B (en) | Parking lot parking space recommendation system and method based on big data | |
CN107564290A (en) | A kind of urban road intersection saturation volume rate computational methods | |
CN107292417A (en) | Region heavily contaminated based on heavily contaminated sequence case library differentiates forecasting procedure and device | |
CN115063978B (en) | Bus arrival time prediction method based on digital twins | |
CN114819305B (en) | Path planning method based on carbon emission measurement scale | |
CN106777169A (en) | A kind of user's trip hobby analysis method based on car networking data | |
CN113380043B (en) | Bus arrival time prediction method based on deep neural network calculation | |
CN114328675A (en) | Bus travel time prediction method based on double-attention machine system and bidirectional double-layer LSTM | |
CN115457764B (en) | Road section traffic density estimation method, device and medium based on vehicle track data | |
CN110867075B (en) | Method for evaluating influence of road speed meter on reaction behavior of driver under rainy condition | |
CN114418606B (en) | Network vehicle order demand prediction method based on space-time convolution network | |
CN116933946A (en) | Rail transit OD passenger flow prediction method and system based on passenger flow destination structure | |
CN116384635A (en) | Green ecological city informatization management system based on big data | |
CN107331164A (en) | A kind of Forecasting Methodology of freeway toll station entrance vehicle number | |
CN111292535B (en) | Road network traffic state evaluation method for passenger travel in vehicle and road cooperation environment | |
CN116629425A (en) | Method and device for calculating vehicle energy consumption, computer readable medium and electronic equipment |
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 |