CN115050210B - Parking lot intelligent induction method, system and device based on time sequence prediction - Google Patents
Parking lot intelligent induction method, system and device based on time sequence prediction Download PDFInfo
- Publication number
- CN115050210B CN115050210B CN202210634967.XA CN202210634967A CN115050210B CN 115050210 B CN115050210 B CN 115050210B CN 202210634967 A CN202210634967 A CN 202210634967A CN 115050210 B CN115050210 B CN 115050210B
- Authority
- CN
- China
- Prior art keywords
- parking lot
- parking
- destination
- initial
- berth
- 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
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000006698 induction Effects 0.000 title claims abstract description 50
- 238000012163 sequencing technique Methods 0.000 claims description 22
- 238000010606 normalization Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 230000005856 abnormality Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 4
- 238000007792 addition Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- 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
- G08G1/01—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
- G08G1/0141—Measuring and analyzing of parameters relative to traffic conditions for specific applications for traffic information dissemination
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 intelligent induction method, a system and a device based on time sequence prediction, wherein the method comprises the steps of acquiring an initial parking lot set of a parking destination within a preset threshold distance range based on the parking lot destination; predicting whether the parking lots in the initial parking lot set have vacant parking lots in the predicted arrival time point or not through a vacant parking lot time sequence prediction model, and obtaining an effective parking lot set; based on the selection frequency used for ranking elements in the historical parking guidance process of the parking lot destination as a scoring weight, weighting and scoring all the effective parking lots, and ranking based on ranking elements selected by a user; and carrying out parking lot induction according to the effective parking lot finally selected by the user. The invention improves the selectivity of the user to the parking lot by weighting and scoring the parking lot with the vacant berths.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a parking lot intelligent induction method, system and device based on time sequence prediction.
Background
Along with the continuous increase of the number of urban automobiles, the demand for parking spaces is larger, and most of the situations are that residents often spend a great deal of time searching for the parking spaces when traveling, and the parking positions are often far away from destinations, so that the traveling convenience of the residents is directly influenced.
At present, many parking guidance systems predict whether a destination parking lot has a vacant parking lot in an expected arrival time point, and push the parking lot with the vacant parking lot to a user, but the existing method cannot provide the general situation of the parking lot for the user, the user often randomly selects a certain parking lot, and the selected parking lot may have too high parking fee or too far distance, so that poor parking experience is caused to the user.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a parking lot intelligent induction method, a parking lot intelligent induction system and a parking lot intelligent induction device based on time sequence prediction.
In order to solve the technical problems, the invention is solved by the following technical scheme:
a parking lot intelligent induction method based on time sequence prediction comprises the following steps:
based on a parking lot destination, acquiring an initial parking lot set of the parking destination within a preset threshold distance range;
predicting whether the parking lots in the initial parking lot set have vacant parking lots in the predicted arrival time point or not through a vacant parking lot time sequence prediction model, and obtaining an effective parking lot set;
weighting and grading all effective parking lots based on the selection frequency of the sorting elements in the history parking induction process of the parking lots destination as a grading weight, and sorting all the effective parking lots according to the grading based on the sorting elements selected by the user, wherein the sorting elements at least comprise the walking distance from the parking lots destination to the parking lots, the parking fee corresponding to the parking lots at the expected arrival time point and the vacant parking space amount corresponding to the parking lots at the expected arrival time point;
and carrying out parking lot induction according to the effective parking lot finally selected by the user.
As an implementation manner, the step of weighting and scoring all the effective parking lots based on the selection frequency of the ranking elements as the scoring weight in the parking lot destination historical parking guidance process includes the following steps:
acquiring a sorting element selected by a user in the history parking induction process and a selection frequency corresponding to each sorting element;
normalizing all the sequencing elements to obtain a normalization result, and taking the selection frequency as a scoring weight, wherein the selection frequency is the ratio of the times of each sequencing element selected by a historical user during parking induction to the historical total parking induction times, when the user selects an effective parking lot in the intention sequencing elements to conduct parking lot induction, the times of the corresponding sequencing elements are increased by one, the times of the historical total parking lot induction are increased by one, and the corresponding selection frequency is changed immediately;
and obtaining the weighted score of the effective parking lot according to the normalization result and the selection frequency.
As an implementation manner, the calculation formula of the weighted score is:
wherein Score b Represents a weighted score, b represents an effective parking lot, num represents the number of ranking elements, per num Indicating the frequency of selection of the ranking elements,is a normalization result;
the normalization result is expressed as:
wherein ,to normalize the result, x num For the original value, x, of each sort element of an effective parking lot min For the original minimum value, x, of each sort element in the active parking set max For the original maximum value of each sort element in the active parking set, num represents the number of sort elements.
As an embodiment, the method for constructing the vacant berth timing prediction model comprises the following steps:
obtaining an initial free berth quantity data set based on the acquired historical free berth quantity of the previous period;
performing data preprocessing operation on elements in the initial free berth amount data set to obtain the free berth amount data set, wherein the data preprocessing operation comprises abnormal data processing operation;
constructing an initial vacant berth time sequence prediction model by adopting an autoregressive moving average model, and training to obtain the initial vacant berth time sequence prediction model;
obtaining a hysteresis order by using an information criterion method, determining the order of the initial vacant berth time sequence prediction model, and obtaining parameters of the initial vacant berth time sequence prediction model by using a maximum likelihood estimation method;
and checking the initial vacant berth time sequence prediction model, and obtaining the vacant berth time sequence prediction model when the residual sequence of the initial vacant berth time sequence prediction model is a white noise sequence.
As an implementation manner, the checking the initial free berth timing prediction model includes the following steps:
verifying a prediction result based on an average absolute percentage error detection model, and if the error result is within a preset error range, enabling an initial vacant berth time sequence prediction model to meet requirements, wherein the average absolute percentage error detection model is as follows:
wherein r is the total number of samples, real k For the true value of the kth sample, pre k Is the predicted value of the kth sample.
As an embodiment, the abnormal data processing operation includes the steps of:
identifying whether a numerical value abnormality exists in the initial vacant berth amount data set, wherein the numerical value abnormality is that the initial vacant berth amount is larger than the total berth amount of a parking lot or a missing value exists in the initial vacant berth amount set;
when the initial vacant berth quantity is larger than the total berth quantity of the parking lot, performing a first deleting operation to obtain a first vacant berth quantity set;
adopting a dynamic threshold-based algorithm to establish a data queue for values in the same time period in the first free berth quantity set, and identifying and deleting abnormal values of the data queue to obtain an effective free berth quantity set;
and when the missing value exists in the initial unoccupied berth quantity set, filling the missing value in the initial unoccupied berth quantity set by using a quadratic spline interpolation method.
As an implementation manner, the obtaining, based on the parking lot destination, an initial parking lot set of the parking destination within a preset threshold distance range includes the following steps:
screening an initial parking lot set in a destination parking lot network based on the destination parking lot network and a preset threshold distance range, wherein the construction of the destination parking lot network comprises the following steps:
carrying out batch analysis on the obtained information of the all-market parking lot to obtain longitude and latitude coordinate information of a destination and the parking lot;
based on longitude and latitude coordinates of venues and parking lots in the city, a relation is established between a destination and a parking lot set by using Cartesian products, and a destination parking lot network is obtained.
A parking lot intelligent guidance system based on time sequence prediction comprises a destination parking lot collection module, a parking lot vacant berth prediction module, an effective parking lot scoring module and a parking lot guidance module;
the destination parking lot set module is used for acquiring an initial parking lot set of the parking destination within a preset threshold distance range based on a parking lot destination;
the parking lot vacant berth prediction module predicts whether vacant berths exist in the parking lots in the initial parking lot set in the predicted arrival time point through a vacant berth time sequence prediction model, and obtains an effective parking lot set;
the effective parking lot scoring module is used for weighting and scoring all effective parking lots based on the selection frequency of the ranking elements in the historical parking induction process of the parking lots destination as a scoring weight, and ranking all the effective parking lots according to the scoring based on the ranking elements selected by a user, wherein the ranking elements at least comprise the walking distance from the parking lots destination to the parking lots, the parking fees corresponding to the parking lots at the expected arrival time point and the vacant parking space quantity corresponding to the parking lots at the expected arrival time point;
and the parking lot induction module is used for conducting parking lot induction according to the effective parking lot finally selected by the user.
A computer readable storage medium storing a computer program which, when executed by a processor, performs the method steps of:
based on a parking lot destination, acquiring an initial parking lot set of the parking destination within a preset threshold distance range;
predicting whether the parking lots in the initial parking lot set have vacant parking lots in the predicted arrival time point or not through a vacant parking lot time sequence prediction model, and obtaining an effective parking lot set;
weighting and grading all effective parking lots based on the selection frequency of the sorting elements in the history parking induction process of the parking lots destination as a grading weight, and sorting all the effective parking lots according to the grading based on the sorting elements selected by the user, wherein the sorting elements at least comprise the walking distance from the parking lots destination to the parking lots, the parking fee corresponding to the parking lots at the expected arrival time point and the vacant parking space amount corresponding to the parking lots at the expected arrival time point;
and carrying out parking lot induction according to the effective parking lot finally selected by the user.
A parking lot intelligent induction device based on time sequence prediction, comprising a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor realizes the following method steps when executing the computer program:
based on a parking lot destination, acquiring an initial parking lot set of the parking destination within a preset threshold distance range;
predicting whether the parking lots in the initial parking lot set have vacant parking lots in the predicted arrival time point or not through a vacant parking lot time sequence prediction model, and obtaining an effective parking lot set;
weighting and grading all effective parking lots based on the selection frequency of the sorting elements in the history parking induction process of the parking lots destination as a grading weight, and sorting all the effective parking lots according to the grading based on the sorting elements selected by the user, wherein the sorting elements at least comprise the walking distance from the parking lots destination to the parking lots, the parking fee corresponding to the parking lots at the expected arrival time point and the vacant parking space amount corresponding to the parking lots at the expected arrival time point;
and carrying out parking lot induction according to the effective parking lot finally selected by the user.
The invention has the remarkable technical effects due to the adoption of the technical scheme:
according to the method, the selection frequency of the ordering elements is used as the scoring weight in the historical parking guidance process of the destination of the parking lot, the parking lot is weighted and scored, the current comprehensive scoring of the parking lot is presented to the user, parking guidance is carried out according to the selection of the user, and the parking experience of the user is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a schematic overall flow diagram of an exemplary method of the present invention;
FIG. 2 is a schematic diagram of the overall structure of the system of the present invention;
FIG. 3 is a diagram of a parking guidance service database E-R;
fig. 4 is a data access flow.
Detailed Description
The present invention will be described in further detail with reference to the following examples, which are illustrative of the present invention and are not intended to limit the present invention thereto.
Example 1:
a parking lot intelligent induction method based on time sequence prediction, as shown in figure 1, comprises the following steps:
s100, acquiring an initial parking lot set of a parking destination within a preset threshold distance range based on the parking lot destination;
s200, predicting whether a parking lot in the initial parking lot set has a vacant parking lot in an expected arrival time point through a vacant parking lot time sequence prediction model, and obtaining an effective parking lot set;
s300, weighting and grading all the effective parking lots based on the selection frequency of the sorting elements in the historical parking induction process of the parking lots destination, and sorting all the effective parking lots according to the grading based on the sorting elements selected by the user, wherein the sorting elements at least comprise the walking distance from the parking lots destination to the parking lots, the parking fee corresponding to the expected arrival time point of the parking lots and the vacant parking space corresponding to the expected arrival time point of the parking lots;
s400, carrying out parking lot induction according to the effective parking lot finally selected by the user.
In step S100, based on a parking lot destination, an initial parking lot set of the parking destination within a preset threshold distance range is acquired, including the steps of:
screening an initial parking lot set in a destination parking lot network based on the destination parking lot network and a preset threshold distance range, wherein the construction of the destination parking lot network comprises the following steps:
carrying out batch analysis on the obtained information of the all-market parking lot to obtain longitude and latitude coordinate information of a destination and the parking lot;
based on longitude and latitude coordinates of venues and parking lots in the city, a relation is established between a destination and a parking lot set by using Cartesian products, and a destination parking lot network is obtained.
In actual operation, the following steps are included:
as shown in fig. 4, through a unified data interface of the urban parking management platform, a request tool and a timer are utilized to initiate an application at regular time, callback data in a Json format is obtained, data access of basic construction information and real-time running conditions of a parking lot is completed, a relation between a destination set a and a parking lot set B is established in a Cartesian product form, destination coordinates and parking lot coordinates are obtained through batch analysis by using a third party map API, a destination parking lot network is obtained, and the weight value of each side in the network is the distance between a venue a and an associated parking lot B.
In step S200, whether the parking lot in the initial parking lot set has a vacant parking place in the expected arrival time point is predicted by a vacant parking place timing prediction model, and an effective parking lot set is obtained.
In actual operation, regarding to constructing the vacant berth timing prediction model, there are the following steps:
the method comprises the steps of obtaining historical vacant berth quantity of a previous period of a parking lot as an initial vacant berth quantity data set, preprocessing data in the data set, constructing an initial vacant berth time sequence prediction model by adopting an autoregressive moving average model, determining hysteresis orders p and q of the autoregressive moving average model by using information criteria and the like, obtaining parameters of the initial vacant berth time sequence prediction model by using a maximum likelihood estimation method, predicting future values by using existing time sequence data of the autoregressive moving average model, and adopting the following formula:
C t+1 ＝β 0 +β 1 C t +…+β p C t+1-p +ε t+1 +α 1 ε t +…+α q ε t+1-q
wherein ,{εt The sequence of the white noise is represented by the sequence of the white noise, p represents the hysteresis order of the autoregressive part, q represents the hysteresis order of the moving average part, beta is the coefficient of AR, alpha is the coefficient of MA, AR and MA are special cases of the autoregressive moving average model, and t is the model parameterIs a statistic of (a).
Preprocessing operation is carried out on data in the data set, specifically:
identifying whether a numerical value abnormality exists in the initial vacant berth amount data set, wherein the numerical value abnormality is that the initial vacant berth amount is larger than the total berth amount of a parking lot or a missing value exists in the initial vacant berth amount set;
when the initial vacant berth quantity is larger than the total berth quantity of the parking lot, performing a first deleting operation to obtain a first vacant berth quantity set;
adopting a dynamic threshold-based algorithm to establish a data queue for values in the same time period in the first free berth quantity set, and identifying and deleting abnormal values of the data queue to obtain an effective free berth quantity set;
and when the missing value exists in the initial unoccupied berth quantity set, filling the missing value in the initial unoccupied berth quantity set by using a quadratic spline interpolation method.
In addition, after an initial vacant berth time sequence prediction model is built, the model is checked, an average absolute percentage error check model is used for checking a prediction result, if the error result is within a preset error range, the initial vacant berth time sequence prediction model meets the requirement, wherein the average absolute percentage error check model is as follows:
wherein r is the total number of samples, real k For the true value of the kth sample, pre k Is the predicted value of the kth sample.
In the specific implementation step S300, the ordering elements selected by the user in the history parking guidance process and the corresponding selection frequency of each ordering element are obtained; normalizing all the sequencing elements to obtain a normalization result, and taking the selection frequency as a scoring weight, wherein the selection frequency is the ratio of the times of each sequencing element selected by a historical user during parking induction to the historical total parking induction times, when the user selects an effective parking lot in the intention sequencing elements to conduct parking lot induction, the times of the corresponding sequencing elements are increased by one, the times of the historical total parking lot induction are increased by one, and the corresponding selection frequency is changed immediately; and obtaining the weighted score of the effective parking lot according to the normalization result and the selection frequency. The method can be realized by the following algorithm:
the method comprises the steps of obtaining sequencing elements selected by a user in a historical parking guidance process and selection frequencies corresponding to the sequencing elements, taking the selection frequencies as scoring weights, normalizing the sequencing elements at least comprising a driving distance, parking fees and free berth amounts, and compressing the sequencing elements to a [0,1] interval, wherein a normalization calculation formula is used as follows:
wherein Score b Represents a weighted score, b represents an effective parking lot, num represents the number of ranking elements, per num Indicating the frequency of selection of the ranking elements,is a normalization result;
according to the normalization result and the selection frequency, obtaining a weighted score of the effective parking lot, wherein the calculation formula of the weighted score is as follows:
wherein Score b Represents a weighted score, b represents an effective parking lot, num represents the number of ranking elements, per num Indicating the frequency of selection of the ranking elements,is normalized result.
In step S400, the parking lot guidance is performed according to the effective parking lot finally selected by the user, and in actual operation, the parking lot guidance service receives the destination coordinates, the running time, the surrounding parking lot distance threshold value, and the sorting mode in the background, calculates and returns the parking lot name, the parking lot coordinates, the charging price, the walking distance and time between the parking lot and the destination, and the free berth number at the arrival time, and performs the parking guidance on the user.
In addition, fig. 3 is an E-R diagram of a parking guidance service database, where the parking guidance service background database includes two parts, namely a space database and a running condition database, and the parking guidance service background database acquires basic information, parking coordinate information and destination coordinate information of a parking lot through a unified data interface of a city level parking management platform, stores the basic information, the parking coordinate information and the destination coordinate information in the space database, and constructs a destination parking lot network; in addition, the parking lot induction service constructs a vacant berth time sequence prediction model by regularly acquiring the parking lot data, predicts the vacant berth at the arrival time, acquires the historical parking fee of the parking lot and the selection mode of the sequencing elements by a user in the historical parking induction process, calculates the selection frequency of each sequencing element and stores the selection frequency in the running condition database.
Example 2:
the intelligent guidance system for the parking lot based on time sequence prediction comprises a destination parking lot collection module 100, a parking lot vacant berth prediction module 200, an effective parking lot scoring module 300 and a parking lot guidance module 400 as shown in fig. 2;
the destination parking lot set module 100 obtains an initial parking lot set of the parking destination within a preset threshold distance range based on a parking lot destination;
the parking lot vacant berth predicting module 200 predicts whether the parking lot in the initial parking lot set has vacant berths in the expected arrival time point through a vacant berth time sequence predicting model, and obtains an effective parking lot set;
the effective parking lot scoring module 300 performs weighted scoring on all effective parking lots based on the selection frequency of the ranking elements used in the historical parking guidance process of the parking lot destination as a scoring weight, and ranks all the effective parking lots according to the scoring based on the ranking elements selected by the user, wherein the ranking elements at least comprise the walking distance from the parking lot destination to the parking lot, the parking fee corresponding to the parking lot at the expected arrival time point and the vacant parking space corresponding to the parking lot at the expected arrival time point;
the parking lot guidance module 400 performs parking lot guidance according to the effective parking lot finally selected by the user.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In addition, the specific embodiments described in the present specification may differ in terms of parts, shapes of components, names, and the like. All equivalent or simple changes of the structure, characteristics and principle according to the inventive concept are included in the protection scope of the present invention. Those skilled in the art may make various modifications or additions to the described embodiments or substitutions in a similar manner without departing from the scope of the invention as defined in the accompanying claims.
Claims (7)
1. The intelligent induction method for the parking lot based on the time sequence prediction is characterized by comprising the following steps of:
based on a destination, acquiring an initial parking lot set of the destination within a preset threshold distance range, wherein the initial parking lot set comprises the following specific steps: screening an initial parking lot set in a destination parking lot network based on the destination parking lot network and a preset threshold distance range, wherein the construction of the destination parking lot network comprises the following steps: carrying out batch analysis on the obtained information of the all-market parking lot to obtain longitude and latitude coordinate information of a destination and the parking lot; based on longitude and latitude coordinates of venues and parking lots in the city, establishing a relation between a destination and a parking lot set by using Cartesian products to obtain a destination parking lot network;
predicting whether the parking lots in the initial parking lot set have vacant parking lots in the predicted arrival time point or not through a vacant parking lot time sequence prediction model, and obtaining an effective parking lot set;
weighting and grading all the effective parking lots based on the selection frequency of the sorting elements in the history parking induction process of the destination as a grading weight, and sorting all the effective parking lots according to the grading based on the sorting elements selected by the user, wherein the sorting elements at least comprise the walking distance from the destination to the parking lots, the parking fee corresponding to the expected arrival time point of the parking lots and the vacant berth amount corresponding to the expected arrival time point of the parking lots, and specifically, the sorting elements selected by the user in the history parking induction process and the selection frequency corresponding to each sorting element are obtained; normalizing all the sequencing elements to obtain a normalization result, and taking the selection frequency as a scoring weight, wherein the selection frequency is the ratio of the times of each sequencing element selected by a historical user during parking induction to the historical total parking induction times, when the user selects an effective parking lot in the intention sequencing elements to conduct parking lot induction, the times of the corresponding sequencing elements are increased by one, the times of the historical total parking lot induction are increased by one, and the corresponding selection frequency is changed immediately; and obtaining a weighted score of the effective parking lot according to the normalization result and the selection frequency, wherein the calculation formula of the weighted score is as follows:
wherein ,representing weighted scores, b representing valid parking lotsNum represents the number of ranking elements, +.>Representing the selection frequency of the ranking elements +.>Is a normalization result;
the normalization result is expressed as:
wherein ,for normalization result->For the original value of each sort element of the effective parking lot,/->For the original minimum value of each sort element in the active parking set,/for each sort element in the active parking set>For the original maximum value of each sort element in the effective parking lot set, num represents the number of sort elements;
and carrying out parking lot induction according to the effective parking lot finally selected by the user.
2. The intelligent induction method for the parking lot based on time sequence prediction according to claim 1, wherein the construction of the vacant berth time sequence prediction model comprises the following steps:
obtaining an initial free berth quantity data set based on the acquired historical free berth quantity of the previous period;
performing data preprocessing operation on elements in the initial free berth amount data set to obtain the free berth amount data set, wherein the data preprocessing operation comprises abnormal data processing operation;
constructing an initial vacant berth time sequence prediction model by adopting an autoregressive moving average model, and training to obtain the initial vacant berth time sequence prediction model;
obtaining a hysteresis order by using an information criterion method, determining the order of the initial vacant berth time sequence prediction model, and obtaining parameters of the initial vacant berth time sequence prediction model by using a maximum likelihood estimation method;
and checking the initial vacant berth time sequence prediction model, and obtaining the vacant berth time sequence prediction model when the residual sequence of the initial vacant berth time sequence prediction model is a white noise sequence.
3. The intelligent guidance method for the parking lot based on time sequence prediction according to claim 2, wherein the checking of the initial vacant berth time sequence prediction model comprises the following steps:
verifying a prediction result based on an average absolute percentage error detection model, and if the error result is within a preset error range, enabling an initial vacant berth time sequence prediction model to meet requirements, wherein the average absolute percentage error detection model is as follows:
where r is the total number of samples,is the true value of the kth sample, < >>Is the predicted value of the kth sample.
4. The intelligent guidance method for a parking lot based on time series prediction according to claim 2, wherein the abnormal data processing operation comprises the steps of:
identifying whether a numerical value abnormality exists in the initial vacant berth amount data set, wherein the numerical value abnormality is that the initial vacant berth amount is larger than the total berth amount of a parking lot or a missing value exists in the initial vacant berth amount data set;
when the initial vacant berth quantity is larger than the total berth quantity of the parking lot, performing a first deleting operation to obtain a first vacant berth quantity set;
adopting a dynamic threshold-based algorithm to establish a data queue for values in the same time period in the first free berth quantity set, and identifying and deleting abnormal values of the data queue to obtain an effective free berth quantity set;
and when the missing value exists in the initial empty berth quantity data set, filling the missing value in the initial empty berth quantity data set by using a quadratic spline interpolation method.
5. The intelligent guidance system for the parking lot based on the time sequence prediction is characterized by comprising a destination parking lot collection module, a parking lot vacant berth prediction module, an effective parking lot scoring module and a parking lot guidance module;
the destination parking lot set module obtains an initial parking lot set of the destination within a preset threshold distance range based on the destination, specifically: screening an initial parking lot set in a destination parking lot network based on the destination parking lot network and a preset threshold distance range, wherein the construction of the destination parking lot network comprises the following steps: carrying out batch analysis on the obtained information of the all-market parking lot to obtain longitude and latitude coordinate information of a destination and the parking lot; based on longitude and latitude coordinates of venues and parking lots in the city, establishing a relation between a destination and a parking lot set by using Cartesian products to obtain a destination parking lot network;
the parking lot vacant berth prediction module predicts whether vacant berths exist in the parking lots in the initial parking lot set in the predicted arrival time point through a vacant berth time sequence prediction model, and obtains an effective parking lot set;
the effective parking lot scoring module is used for weighting and scoring all effective parking lots based on the selection frequency of the ranking elements in the destination historical parking induction process as a scoring weight, and ranking all the effective parking lots according to the scoring based on the ranking elements selected by the user, wherein the ranking elements at least comprise the walking distance from the destination to the parking lots, the parking fee corresponding to the expected arrival time point of the parking lots and the vacant parking space corresponding to the expected arrival time point of the parking lots, and particularly, the ranking elements selected by the user in the historical parking induction process and the selection frequency corresponding to each ranking element are obtained; normalizing all the sequencing elements to obtain a normalization result, and taking the selection frequency as a scoring weight, wherein the selection frequency is the ratio of the times of each sequencing element selected by a historical user during parking induction to the historical total parking induction times, when the user selects an effective parking lot in the intention sequencing elements to conduct parking lot induction, the times of the corresponding sequencing elements are increased by one, the times of the historical total parking lot induction are increased by one, and the corresponding selection frequency is changed immediately; and obtaining a weighted score of the effective parking lot according to the normalization result and the selection frequency, wherein the calculation formula of the weighted score is as follows:
wherein ,represents a weighted score, b represents an effective parking lot, num represents the number of ranking elements, +.>Representing the selection frequency of the ranking elements +.>Is a normalization result;
the normalization result is expressed as:
wherein ,for normalization result->For the original value of each sort element of the effective parking lot,/->For the original minimum value of each sort element in the active parking set,/for each sort element in the active parking set>For the original maximum value of each sort element in the effective parking lot set, num represents the number of sort elements;
and the parking lot induction module is used for conducting parking lot induction according to the effective parking lot finally selected by the user.
6. A computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the time-series prediction-based parking lot intelligent guidance method of any one of claims 1 to 4.
7. A time-series prediction-based intelligent guidance device for a parking lot, comprising a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor implements the time-series prediction-based intelligent guidance method for a parking lot according to any one of claims 1 to 4 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210634967.XA CN115050210B (en) | 2022-06-07 | 2022-06-07 | Parking lot intelligent induction method, system and device based on time sequence prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210634967.XA CN115050210B (en) | 2022-06-07 | 2022-06-07 | Parking lot intelligent induction method, system and device based on time sequence prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115050210A CN115050210A (en) | 2022-09-13 |
| CN115050210B true CN115050210B (en) | 2023-10-20 |
Family
ID=83159290
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210634967.XA Active CN115050210B (en) | 2022-06-07 | 2022-06-07 | Parking lot intelligent induction method, system and device based on time sequence prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115050210B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116582134B (en) * | 2023-07-11 | 2023-10-13 | 江苏盖亚环境科技股份有限公司 | Drilling and testing integrated equipment data processing method |
| CN116913123B (en) * | 2023-08-14 | 2024-04-02 | 合肥工业大学智能制造技术研究院 | Space-time integrated intelligent parking guidance method |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107038488A (en) * | 2017-02-25 | 2017-08-11 | 浙江大学 | A kind of real-time berth reserving method in parking lot based on berth prediction and selection of stopping |
| CN107134170A (en) * | 2017-07-04 | 2017-09-05 | 北京悦畅科技有限公司 | A kind for the treatment of method and apparatus of parking position information of park |
| CN107146462A (en) * | 2017-06-23 | 2017-09-08 | 武汉大学 | A kind of idle parking stall number long-term prediction method in parking lot |
| CN107547269A (en) * | 2017-08-14 | 2018-01-05 | 浙江大学 | The construction method of intelligent substation communication flow threshold model based on FARIMA |
| CN108984870A (en) * | 2018-06-29 | 2018-12-11 | 中国科学院深圳先进技术研究院 | Freezer data of the Temperature and Humidity module prediction technique and Related product based on ARIMA |
| CN109492808A (en) * | 2018-11-07 | 2019-03-19 | 浙江科技学院 | A kind of parking garage residue parking stall prediction technique |
| CN110415546A (en) * | 2018-04-26 | 2019-11-05 | 中移(苏州)软件技术有限公司 | It parks abductive approach, device and medium |
| CN111788617A (en) * | 2018-03-06 | 2020-10-16 | 斯堪尼亚商用车有限公司 | Method and control device for identifying parking areas |
| CN113728212A (en) * | 2020-03-26 | 2021-11-30 | 百度时代网络技术（北京）有限公司 | Navigation route planning method for autonomous vehicle |
| CN114218483A (en) * | 2021-12-16 | 2022-03-22 | 城云科技（中国）有限公司 | Parking recommendation method and application thereof |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110675651B (en) * | 2019-09-29 | 2021-08-17 | 百度在线网络技术（北京）有限公司 | Parking lot recommendation method and device |
-
2022
- 2022-06-07 CN CN202210634967.XA patent/CN115050210B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107038488A (en) * | 2017-02-25 | 2017-08-11 | 浙江大学 | A kind of real-time berth reserving method in parking lot based on berth prediction and selection of stopping |
| CN107146462A (en) * | 2017-06-23 | 2017-09-08 | 武汉大学 | A kind of idle parking stall number long-term prediction method in parking lot |
| CN107134170A (en) * | 2017-07-04 | 2017-09-05 | 北京悦畅科技有限公司 | A kind for the treatment of method and apparatus of parking position information of park |
| CN107547269A (en) * | 2017-08-14 | 2018-01-05 | 浙江大学 | The construction method of intelligent substation communication flow threshold model based on FARIMA |
| CN111788617A (en) * | 2018-03-06 | 2020-10-16 | 斯堪尼亚商用车有限公司 | Method and control device for identifying parking areas |
| CN110415546A (en) * | 2018-04-26 | 2019-11-05 | 中移(苏州)软件技术有限公司 | It parks abductive approach, device and medium |
| CN108984870A (en) * | 2018-06-29 | 2018-12-11 | 中国科学院深圳先进技术研究院 | Freezer data of the Temperature and Humidity module prediction technique and Related product based on ARIMA |
| CN109492808A (en) * | 2018-11-07 | 2019-03-19 | 浙江科技学院 | A kind of parking garage residue parking stall prediction technique |
| CN113728212A (en) * | 2020-03-26 | 2021-11-30 | 百度时代网络技术（北京）有限公司 | Navigation route planning method for autonomous vehicle |
| CN114218483A (en) * | 2021-12-16 | 2022-03-22 | 城云科技（中国）有限公司 | Parking recommendation method and application thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115050210A (en) | 2022-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115050210B (en) | Parking lot intelligent induction method, system and device based on time sequence prediction | |
| US11305780B2 (en) | Road condition status prediction method, device, and server, and storage medium | |
| CN110766269A (en) | Task allocation method and device, readable storage medium and terminal equipment | |
| CN108133619B (en) | Parking lot parking prediction method and device, storage medium and terminal equipment | |
| CN111428137B (en) | Recommendation method and recommendation device for electric vehicle charging facilities | |
| US20200210905A1 (en) | Systems and Methods for Managing Networked Vehicle Resources | |
| EP3514738A1 (en) | Demand prediction apparatus, redistribution plan generation apparatus, user model generation apparatus | |
| CN115330357B (en) | Intelligent stereo garage data management method, device, equipment and storage medium | |
| CN111626648B (en) | Survey task scheduling method and device, computer equipment and storage medium | |
| GB2576312A (en) | Method and system of recommending a place to park | |
| CN116007647A (en) | Routing inspection path planning method and device, electronic equipment and storage medium | |
| CN113256405B (en) | Method, device, equipment and storage medium for predicting cheating user concentrated area | |
| CN112257936B (en) | Recommendation method and device for order receiving area, electronic equipment and storage medium | |
| CN115330281B (en) | Smart city new energy automobile charging service method, system, device and medium | |
| CN111798283A (en) | Order distribution method and device, electronic equipment and computer readable storage medium | |
| CN110837903A (en) | Rail transit short-term passenger flow prediction method and system and electronic equipment | |
| CN115375237A (en) | Cold-chain logistics intelligent management method, system, equipment and storage medium | |
| US20220327650A1 (en) | Transportation bubbling at a ride-hailing platform and machine learning | |
| CN111833595B (en) | Shared automobile auxiliary vehicle configuration method, electronic device and storage medium | |
| CN113469475B (en) | Data processing method, device, storage medium and electronic equipment | |
| JP7260463B2 (en) | Information processing device, information processing method, and information processing program | |
| CN112116170A (en) | Method and device for automatically planning work route | |
| CN112434877A (en) | Smart city data processing method and device based on cloud computing | |
| CN117807283B (en) | Big data-based parking order analysis method and system | |
| CN116523231A (en) | Method, equipment, device and storage medium for matching driving orders |
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 |