A data control system and method based on building intelligence

Abstract

The present invention discloses a data control system and method based on building intelligence, which relates to the field of data analysis technology, including: constructing a user parking preference portrait based on the background database of a parking lot; quantifying the dynamic convenience index of each divided parking area; generating a parking planning area for users to be parked according to the correlation matching between the user parking preference portrait and the dynamic convenience index of each divided parking area; marking all accessible routes between the position of the user to be parked and the position of the planned parking area to be parked, generating a parking planning area guidance route for the user to be parked; uploading the parking planning area guidance route for the user to be parked to the intelligent guidance lights in the parking lot to complete the guidance control task. The advantages of the present invention are: improving the intelligent parking efficiency of the parking lot and reducing the operating cost.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a data control system and method based on building intelligence. Background Art

[0002] Intelligent building data control refers to the use of advanced information technology and data analysis methods to intelligently manage and optimize various systems within the building (such as lighting, security, temperature control, parking management, etc.) to improve operational efficiency and reduce operating costs.

[0003] However, although the existing intelligent parking lots have car-finding assistance maps, they do not have a linked guidance function, resulting in chaotic parking management. In addition, the traffic volume at the entrances and exits is large during holidays, which easily leads to congestion at the entrances and exits and internal roads, further reducing the service efficiency of the parking lot. Summary of the invention

[0004] In order to solve the above technical problems, a data control system and method based on building intelligence is provided. This technical solution solves the above technical problems. However, although the existing intelligent parking lot has a car-finding auxiliary map, it does not have a linkage guidance function, which leads to chaotic parking management. In addition, the traffic volume at the entrances and exits is large during holidays, which easily leads to congestion of the entrances and exits and internal roads, further reducing the service efficiency of the parking lot.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A data control method based on building intelligence, comprising:

[0007] Based on the parking lot's backend database, obtain the user's historical parking data in the parking lot, analyze the user's parking preferences based on the historical parking data, and build a user parking preference profile;

[0008] Based on the divided parking areas of the parking lot, analyze the parking attributes of each divided parking area and quantify the dynamic convenience index of each divided parking area;

[0009] According to the user's parking preference profile and the dynamic convenience index of each divided parking area, a parking planning area for the user to park is generated;

[0010] Based on the parking planning area of ​​the user to be parked, mark all accessible routes between the position of the user to be parked and the position of the parking planning area to be parked, and record them as accessible routes in the parking planning area of ​​the user to be parked;

[0011] Estimate the accessible routes in the parking planning area for users waiting to park, build a parking route guidance planning model, and generate a parking planning area guidance route for users waiting to park;

[0012] The guidance route of the parking planning area for the user to park is uploaded to the intelligent guidance lights in the parking lot to complete the guidance control task.

[0013] Preferably, based on the backend database of the parking lot, historical parking data of users in the parking lot is obtained, parking preferences of users in the historical parking data are analyzed, and a user parking preference profile is constructed as follows:

[0014] Based on the backend database of the parking lot, the historical parking data of users in the parking lot corresponding to the marking time is obtained to obtain the historical parking time series data of users in the parking lot;

[0015] Based on the user historical parking time series data of the parking lot, the vehicle license plate information is used as the unique index, and the data is filtered according to the time attribute to obtain the user historical parking time series data set of the parking lot;

[0016] Performing normalization processing on a user's historical parking time series data set based on the parking lot, and extracting the user's historical parking feature data; the user's historical parking feature data includes: parking time feature, parking duration feature, and parking frequency feature;

[0017] Through the clustering algorithm, the vehicle license plate information per unit time is used as the centroid of the corresponding data point, and cluster analysis is performed on the user's historical parking feature data to obtain the user's parking preference portrait;

[0018] The clustering algorithm is specifically:

[0019]

[0020] In the formula, For the A user parking preference profile, is the sum of the squares of the distances from all samples in the cluster to the centroid of each cluster, for k Clusters of user historical parking feature data, for k The central value of the user's historical parking feature data of each cluster, For the User's Historical parking feature data, for The central value of the user's historical parking feature data of each cluster, is the total number of clusters.

[0021] Preferably, based on the divided parking areas of the parking lot, the parking attributes of each divided parking area are analyzed, and the dynamic convenience index of each divided parking area is quantified, specifically including:

[0022] Based on the divided parking areas of the parking lot, the distance between each divided parking area and the entrance and exit and the elevator platform is taken as the convenience influencing factor of the area, which is recorded as the convenient distance characteristic parameter of each divided parking area;

[0023] Normalizing the convenience distance characteristic parameter of each divided parking area to obtain a normalized score of the convenience distance characteristic parameter of each divided parking area;

[0024] Based on the normalized score of the convenience distance characteristic parameter of each divided parking area, a weight is assigned to the convenience distance characteristic parameter of each divided parking area;

[0025] Based on the normalized score of the convenience distance feature parameter of each divided parking area and the weight of the convenience distance feature parameter of each divided parking area, the initial convenience index of each divided parking area is quantified;

[0026] Based on the parking lot's divided parking areas, analyze the changing trend of historical user parking data in the divided parking areas, and obtain the convenience index influence coefficient of each divided parking area:

[0027] Based on the convenience index influence coefficient of each divided parking area, the initial convenience index of each divided parking area is corrected to obtain a dynamic convenience index of each divided parking area;

[0028] The initialization convenience index for quantifying each divided parking area is specifically:

[0029]

[0030] In the formula, For the Initial convenience index for dividing parking areas, For the The first parking area Normalized score of convenience distance feature parameter, For the The first parking area Convenience distance feature parameter weight, The total number of parking areas to be divided;

[0031] The method of obtaining the dynamic convenience index of each divided parking area is as follows:

[0032]

[0033] In the formula, For the A dynamic convenience index that divides parking areas. For the The convenience index influence coefficient of the divided parking area;

[0034] The parking area division based on the parking lot, analyzing the change trend of the historical parking data of users in the divided parking area, and obtaining the convenience index influence coefficient of each divided parking area are specifically:

[0035] Based on the historical parking data of users in the divided parking areas, a binary time series scatter plot of the historical parking data of users in the divided parking areas is constructed according to unit time;

[0036] Based on the binary time series scatter plot of historical parking data of users divided into parking areas, the parking quantity corresponding to each scatter point in the binary time series scatter plot of historical parking data of users is screened to obtain the traffic flow characteristic data of the divided parking areas;

[0037] According to the traffic flow characteristic data of the divided parking area, the external influencing factors of each corresponding time node are screened out as restriction conditions; the external influencing factors include: weather factors and holiday factors;

[0038] Based on time series autoregression, a convenience trend assessment model for dividing parking areas is constructed;

[0039] Based on the convenience trend evaluation model of divided parking areas, under the constraints, the traffic flow characteristic data of the divided parking areas are used as input, and the convenience index influence coefficient of each divided parking area is used as output;

[0040] The convenience trend evaluation model for dividing parking areas is specifically as follows:

[0041]

[0042] In the formula, For the The convenience index influence coefficient of dividing parking areas is: For the The parking areas are divided into Traffic flow characteristic data under unit time learning order, is a constant term, is the autoregression coefficient, is the error term under t unit time.

[0043] Preferably, the generation of a parking planning area for a user to park includes associating and matching the user's parking preference profile with the dynamic convenience index of each divided parking area:

[0044] Based on the dynamic convenience index of each divided parking area in the parking lot, a dynamic convenience index matrix for divided parking areas is constructed;

[0045] Based on the user's parking preference profile and the dynamic convenience index matrix of the divided parking areas, the matching value of each divided parking area is obtained;

[0046] Filter out the maximum value of the matching value of each divided parking area and record it as the parking planning area for the user to park;

[0047] The specific matching value of each divided parking area is obtained as follows:

[0048]

[0049] In the formula, For the The matching values ​​for dividing the parking area, For the A user parking preference profile, For the A dynamic convenience indicator that divides parking areas.

[0050] Preferably, estimating the accessible routes of the parking planning area for the user to be parked, building a parking route guidance planning model, and generating the parking planning area guidance route for the user to be parked specifically include:

[0051] Obtaining the location of the parking user in the parking planning area of ​​the user to be parked and the location information of the parking planning area;

[0052] Filter out all accessible routes between the parking user's location and the parking planning area location information, and construct a road network diagram in the parking lot;

[0053] According to the road network diagram in the parking lot, the historical traffic flow data of each entrance and exit in the road network diagram in the parking lot is screened out to form the historical traffic flow time series data of the road network in the parking lot;

[0054] Based on the historical traffic flow time series data of the road network in the parking lot, the congestion index of the passable roads in the historical traffic flow time series data of the road network is analyzed;

[0055] Taking the congestion index of the drivable road in the historical traffic flow time series data of the road network between the location of the parking user and the location of the parking planning area as the constraint condition to minimize the drivable route;

[0056] The objective function is to minimize the travel time between the traversable routes and the nodes connecting the routes;

[0057] Construct a parking route guidance planning model;

[0058] Based on the parking route guidance planning model, according to the constraint conditions and the objective function, the historical traffic flow time series data of the road network in the parking lot is substituted under the constraint conditions to generate the parking planning area guidance route for the user to be parked;

[0059] Among them, the parking route guidance planning model is specifically as follows:

[0060]

[0061] In the formula, Provide guidance routes for parking area planning for users waiting to park. is the travel time of the e-th pass road in the road network, is the congestion index of the e-th access road in the road network, is the travel time weight, is the congestion index weight.

[0062] Furthermore, a data control system based on building intelligence is proposed, which is used to implement the data control method based on building intelligence as described above, including:

[0063] A user portrait building module is used to obtain historical parking data of users in the parking lot based on the backend database of the parking lot, analyze the parking preferences of users in the historical parking data, and build a parking preference portrait of the users;

[0064] A dynamic convenience index module is used to divide parking areas based on the parking lot, analyze the parking attributes of each divided parking area, and quantify the dynamic convenience index of each divided parking area;

[0065] A parking area matching module, the parking area matching module is electrically connected to the dynamic convenience index module and the user portrait building module, and the parking area matching module is used to associate and match the user's parking preference portrait with the dynamic convenience index of each divided parking area to generate a parking planning area for the user to be parked;

[0066] A route marking module, the route marking module is electrically connected to the parking area matching module, and the route marking module is used to mark all passable routes between the position of the user to be parked and the position of the parking area to be parked based on the parking area to be parked, and record them as passable routes in the parking area to be parked by the user to be parked;

[0067] A guidance route generation module, the guidance route generation module is electrically connected to the route marking module, and the guidance route generation module is used to estimate the accessible route of the parking planning area for the user to be parked, build a parking route guidance planning model, and generate a guidance route for the parking planning area for the user to be parked;

[0068] The guidance control module is electrically connected to the guidance route generation module. The guidance control module is used to upload the parking planning area guidance route of the user to be parked to the intelligent guidance lights in the parking lot to complete the guidance control task.

[0069] Optionally, the user portrait building module includes:

[0070] The data collection unit obtains the historical parking time series data of users in the parking lot based on the backend database of the parking lot by marking the historical parking data of users in the parking lot corresponding to the time.

[0071] The time series data unit is based on the user historical parking time series data of the parking lot, uses the vehicle license plate information as the unique index, and filters according to the time attribute to obtain the user historical parking time series data set of the parking lot;

[0072] A feature extraction unit, which performs normalization processing on a user's historical parking time series data set in the parking lot and extracts the user's historical parking feature data;

[0073] The preference portrait unit uses a clustering algorithm to take the vehicle license plate information per unit time as the centroid of the corresponding data point, and performs cluster analysis on the user's historical parking feature data to obtain the user's parking preference portrait.

[0074] Optionally, the dynamic convenience indicator module includes:

[0075] The distance factor unit, based on the divided parking areas of the parking lot, takes the distance between each divided parking area and the entrance and exit and the elevator platform as the convenience influencing factor of the area, and records it as the convenience distance characteristic parameter of each divided parking area;

[0076] A scoring unit performs normalization processing on the convenience distance characteristic parameter of each divided parking area to obtain a normalized score of the convenience distance characteristic parameter of each divided parking area;

[0077] A weighting unit assigns a weight to the convenience distance characteristic parameter of each divided parking area based on a normalized score of the convenience distance characteristic parameter of each divided parking area;

[0078] An initialization index unit, which quantifies an initialization convenience index of each divided parking area based on a normalized score of a convenience distance feature parameter of each divided parking area and a weight of a convenience distance feature parameter of each divided parking area;

[0079] The influence coefficient unit analyzes the changing trend of historical parking data of users in the divided parking areas based on the divided parking areas of the parking lot, and obtains the influence coefficient of the convenience index of each divided parking area:

[0080] The index correction unit corrects the initialization convenience index of each divided parking area based on the convenience index influence coefficient of each divided parking area to obtain a dynamic convenience index of each divided parking area.

[0081] Optionally, the parking area matching module includes:

[0082] A matrix unit, based on the dynamic convenience index of each divided parking area in the parking lot, constructs a dynamic convenience index matrix for dividing parking areas;

[0083] A matching unit, which performs correlation matching based on the user's parking preference profile and the dynamic convenience index matrix of the divided parking areas, and obtains a matching value for each divided parking area;

[0084] The screening unit screens out the maximum value of the matching value of each divided parking area and records it as the parking planning area for the user to park.

[0085] Optionally, the guidance route generation module includes:

[0086] The road network unit screens out all accessible routes between the parking user's location and the parking planning area location information, and constructs a road network diagram in the parking lot;

[0087] The vehicle flow data unit, based on the road network diagram in the parking lot, screens out the historical vehicle flow data of each entrance and exit in the road network diagram in the parking lot, and forms the historical vehicle flow time series data of the road network in the parking lot;

[0088] A congestion status unit, based on the historical traffic flow time series data of the road network in the parking lot, analyzes the congestion index of the passable roads in the historical traffic flow time series data of the road network;

[0089] A restriction condition unit, which takes a drivable route that minimizes a congestion index of a drivable road in the historical traffic flow time series data of a road network between a parking user's location and a parking planning area location as a restriction condition;

[0090] The objective function unit takes minimizing the travel time between the traversable routes and the route connection nodes as the objective function;

[0091] A model building unit, building a parking route guidance planning model;

[0092] The guidance route unit, based on the parking route guidance planning model, substitutes the historical traffic flow time series data of the road network in the parking lot under the constraints and according to the objective function, to generate a parking planning area guidance route for the user to be parked.

[0093] Compared with the prior art, the present invention has the following beneficial effects:

[0094] The present invention proposes a data control solution based on building intelligence, which builds a parking preference profile by analyzing the historical parking data of users in the parking lot, and quantifies the dynamic convenience index of each parking area, and then associates and matches the two to generate the planned parking area for users to park, further plans the optimal route and realizes parking guidance through intelligent guide lights. Its beneficial effects are: improving the intelligent parking efficiency of the parking lot and reducing operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] Figure 1 The present invention is a flow chart of a data control method based on building intelligence.

[0096] Figure 2 Flowchart of the method for constructing a user parking preference profile.

[0097] Figure 3 Flowchart of the method for quantifying the dynamic convenience index for each zoned parking area.

[0098] Figure 4 A flow chart of a method for generating a parking planning area for users waiting to park.

[0099] Figure 5 A flow chart of a method for generating a parking planning area guidance route for a user waiting to park.

[0100] Figure 6 This is a framework diagram of a data control system based on building intelligence. DETAILED DESCRIPTION

[0101] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0102] Reference Figure 1 As shown, a data control method based on building intelligence includes:

[0103] Based on the parking lot's backend database, obtain the user's historical parking data in the parking lot, analyze the user's parking preferences based on the historical parking data, and build a user parking preference profile;

[0104] Based on the divided parking areas of the parking lot, analyze the parking attributes of each divided parking area and quantify the dynamic convenience index of each divided parking area;

[0105] According to the user's parking preference profile and the dynamic convenience index of each divided parking area, a parking planning area for the user to park is generated;

[0106] Based on the parking planning area of ​​the user to be parked, mark all accessible routes between the position of the user to be parked and the position of the parking planning area to be parked, and record them as accessible routes in the parking planning area of ​​the user to be parked;

[0107] Estimate the accessible routes in the parking planning area for users waiting to park, build a parking route guidance planning model, and generate a parking planning area guidance route for users waiting to park;

[0108] The guidance route of the parking planning area for the user to park is uploaded to the intelligent guidance lights in the parking lot to complete the guidance control task.

[0109] This solution builds a parking preference profile by analyzing the historical parking data of users in the parking lot, and quantifies the dynamic convenience index of each parking area, then associates and matches the two to generate the planned parking area for users to park, further plans the optimal route and implements parking guidance through intelligent guide lights. Its beneficial effects are: improving the intelligent parking efficiency of the parking lot and reducing operating costs.

[0110] Reference Figure 2 As shown in the figure, based on the backend database of the parking lot, the historical parking data of users in the parking lot is obtained, the parking preferences of users in the historical parking data are analyzed, and the parking preference profile of users is constructed as follows:

[0111] Based on the backend database of the parking lot, the historical parking data of users in the parking lot corresponding to the marking time is obtained to obtain the historical parking time series data of users in the parking lot;

[0112] Based on the user historical parking time series data of the parking lot, the vehicle license plate information is used as the unique index, and the data is filtered according to the time attribute to obtain the user historical parking time series data set of the parking lot;

[0113] Performing normalization processing on a user's historical parking time series data set based on the parking lot, and extracting the user's historical parking feature data; the user's historical parking feature data includes: parking time feature, parking duration feature, and parking frequency feature;

[0114] Through the clustering algorithm, the vehicle license plate information per unit time is used as the centroid of the corresponding data point, and cluster analysis is performed on the user's historical parking feature data to obtain the user's parking preference portrait;

[0115] The clustering algorithm is specifically:

[0116]

[0117] In the formula, For the A user parking preference profile, is the sum of the squares of the distances from all samples in the cluster to the centroid of each cluster, for k Clusters of user historical parking feature data, for k The central value of the user's historical parking feature data of each cluster, For the User's Historical parking feature data, for The central value of the user's historical parking feature data of each cluster, is the total number of clusters.

[0118] It can be understood that by constructing a user parking preference profile, key data can be provided for the convenience trend of the number of parking spaces in the subsequent parking lot and the division of areas. By analyzing the behavioral trends of user parking preferences, targeted preventive planning can be carried out in advance to avoid parking shortages and congestion on parking roads.

[0119] Reference Figure 3 As shown, based on the parking area division of the parking lot, the parking attributes of each divided parking area are analyzed, and the dynamic convenience index of each divided parking area is quantified, including:

[0120] Based on the divided parking areas of the parking lot, the distance between each divided parking area and the entrance and exit and the elevator platform is taken as the convenience influencing factor of the area, which is recorded as the convenient distance characteristic parameter of each divided parking area;

[0121] Normalizing the convenience distance characteristic parameter of each divided parking area to obtain a normalized score of the convenience distance characteristic parameter of each divided parking area;

[0122] Based on the normalized score of the convenience distance characteristic parameter of each divided parking area, a weight is assigned to the convenience distance characteristic parameter of each divided parking area;

[0123] Based on the normalized score of the convenience distance feature parameter of each divided parking area and the weight of the convenience distance feature parameter of each divided parking area, the initial convenience index of each divided parking area is quantified;

[0124] Based on the parking lot's divided parking areas, analyze the changing trend of historical user parking data in the divided parking areas, and obtain the convenience index influence coefficient of each divided parking area:

[0125] Based on the convenience index influence coefficient of each divided parking area, the initial convenience index of each divided parking area is corrected to obtain a dynamic convenience index of each divided parking area;

[0126] The initialization convenience index for quantifying each divided parking area is specifically:

[0127]

[0128] In the formula, For the Initial convenience index for dividing parking areas, For the The first parking area Normalized score of convenience distance feature parameter, For the The first parking area Convenience distance feature parameter weight, The total number of parking areas to be divided;

[0129] The method of obtaining the dynamic convenience index of each divided parking area is as follows:

[0130]

[0131] In the formula, For the A dynamic convenience index that divides parking areas. For the The influence coefficient of convenience index for dividing parking areas.

[0132] It is understandable that, since the convenience of the parking area in the parking lot will decline with the increase of vehicles, therefore, in consideration of the convenience of parking, it is also necessary to consider the change trend of other traffic flow data in the divided parking area. For example, a divided parking area is convenient for Class A in the morning, but due to the increase in traffic volume in the area, the convenience decreases to Class B. Therefore, by analyzing the influence coefficient of the convenience index of each divided parking area, correction is made to obtain the dynamic convenience index of the area at the current time;

[0133] The parking area division based on the parking lot, analyzing the change trend of the historical parking data of users in the divided parking area, and obtaining the convenience index influence coefficient of each divided parking area are specifically:

[0134] Based on the historical parking data of users in the divided parking areas, a binary time series scatter plot of the historical parking data of users in the divided parking areas is constructed according to unit time;

[0135] Based on the binary time series scatter plot of historical parking data of users divided into parking areas, the parking quantity corresponding to each scatter point in the binary time series scatter plot of historical parking data of users is screened to obtain the traffic flow characteristic data of the divided parking areas;

[0136] According to the traffic flow characteristic data of the divided parking area, the external influencing factors of each corresponding time node are screened out as restriction conditions; the external influencing factors include: weather factors and holiday factors;

[0137] Based on time series autoregression, a convenience trend assessment model for dividing parking areas is constructed;

[0138] Based on the convenience trend evaluation model of divided parking areas, under the constraints, the traffic flow characteristic data of the divided parking areas are used as input, and the convenience index influence coefficient of each divided parking area is used as output;

[0139] The convenience trend evaluation model for dividing parking areas is specifically as follows:

[0140]

[0141] In the formula, For the The convenience index influence coefficient of dividing parking areas is: For the The parking areas are divided into Traffic flow characteristic data under unit time learning order, is a constant term, is the autoregression coefficient, is the error term under t unit time.

[0142] This solution collects and analyzes historical parking data of users in divided parking areas, combines external factors such as weather and holidays, and uses the time series autoregression method to build a convenience trend evaluation model to accurately calculate the influence coefficient of the convenience index of each parking area, providing a basis for subsequent intelligent control in the parking lot.

[0143] Reference Figure 4 As shown in the figure, the user's parking preference profile is associated and matched with the dynamic convenience index of each divided parking area, and the parking planning area for the user to park is generated, which specifically includes:

[0144] Based on the dynamic convenience index of each divided parking area in the parking lot, a dynamic convenience index matrix for divided parking areas is constructed;

[0145] Based on the user's parking preference profile and the dynamic convenience index matrix of the divided parking areas, the matching value of each divided parking area is obtained;

[0146] Filter out the maximum value of the matching value of each divided parking area and record it as the parking planning area for the user to park;

[0147] The specific matching value of each divided parking area is obtained as follows:

[0148]

[0149] In the formula, For the The matching values ​​for dividing the parking area, For the A user parking preference profile, For the A dynamic convenience indicator that divides parking areas.

[0150] This solution constructs a dynamic convenience index matrix for each area of ​​the parking lot and matches it with the user's parking preference profile to accurately determine the parking planning area that best suits the user.

[0151] Reference Figure 5 As shown, estimating the accessible routes in the parking planning area for users to park, building a parking route guidance planning model, and generating the parking planning area guidance routes for users to park specifically include:

[0152] Obtaining the location of the parking user in the parking planning area of ​​the user to be parked and the location information of the parking planning area;

[0153] Filter out all accessible routes between the parking user's location and the parking planning area location information, and construct a road network diagram in the parking lot;

[0154] According to the road network diagram in the parking lot, the historical traffic flow data of each entrance and exit in the road network diagram in the parking lot is screened out to form the historical traffic flow time series data of the road network in the parking lot;

[0155] Based on the historical traffic flow time series data of the road network in the parking lot, the congestion index of the passable roads in the historical traffic flow time series data of the road network is analyzed;

[0156] Taking the congestion index of the drivable road in the historical traffic flow time series data of the road network between the location of the parking user and the location of the parking planning area as the constraint condition to minimize the drivable route;

[0157] The objective function is to minimize the travel time between the traversable routes and the nodes connecting the routes;

[0158] Construct a parking route guidance planning model;

[0159] Based on the parking route guidance planning model, according to the constraint conditions and the objective function, the historical traffic flow time series data of the road network in the parking lot is substituted under the constraint conditions to generate the parking planning area guidance route for the user to be parked;

[0160] Among them, the parking route guidance planning model is specifically as follows:

[0161]

[0162] In the formula, Provide guidance routes for parking area planning for users waiting to park. is the travel time of the e-th pass road in the road network, is the congestion index of the e-th access road in the road network, is the travel time weight, is the congestion index weight.

[0163] It should be noted that the congestion index of the passable roads in the analysis of the historical traffic flow time series data of the road network can be obtained by linear regression based on historical data, and because the traffic flow data allows a range error, the guidance route in this scheme can still be used as an accurate reference vector, and the travel time weight and congestion index weight described in the scheme are averagely weighted, and the range can also be adjusted based on the implementation personnel in this field, which will not be described in detail here.

[0164] Reference Figure 6 As shown, based on the same inventive concept of a data control method based on building intelligence, a data control system based on building intelligence is proposed, comprising:

[0165] A user portrait building module is used to obtain historical parking data of users in the parking lot based on the backend database of the parking lot, analyze the parking preferences of users in the historical parking data, and build a parking preference portrait of the users;

[0166] A dynamic convenience index module is used to divide parking areas based on the parking lot, analyze the parking attributes of each divided parking area, and quantify the dynamic convenience index of each divided parking area;

[0167] A parking area matching module, the parking area matching module is electrically connected to the dynamic convenience index module and the user portrait building module, and the parking area matching module is used to associate and match the user's parking preference portrait with the dynamic convenience index of each divided parking area to generate a parking planning area for the user to be parked;

[0168] A route marking module, the route marking module is electrically connected to the parking area matching module, and the route marking module is used to mark all passable routes between the position of the user to be parked and the position of the parking area to be parked based on the parking area to be parked, and record them as passable routes in the parking area to be parked by the user to be parked;

[0169] A guidance route generation module, the guidance route generation module is electrically connected to the route marking module, and the guidance route generation module is used to estimate the accessible route of the parking planning area for the user to be parked, build a parking route guidance planning model, and generate a guidance route for the parking planning area for the user to be parked;

[0170] The guidance control module is electrically connected to the guidance route generation module. The guidance control module is used to upload the parking planning area guidance route of the user to be parked to the intelligent guidance lights in the parking lot to complete the guidance control task.

[0171] The user portrait construction module includes:

[0172] The data collection unit obtains the historical parking time series data of users in the parking lot based on the backend database of the parking lot by marking the historical parking data of users in the parking lot corresponding to the time.

[0173] The time series data unit is based on the user historical parking time series data of the parking lot, uses the vehicle license plate information as the unique index, and filters according to the time attribute to obtain the user historical parking time series data set of the parking lot;

[0174] A feature extraction unit, which performs normalization processing on a user's historical parking time series data set in the parking lot and extracts the user's historical parking feature data;

[0175] The preference portrait unit uses a clustering algorithm to take the vehicle license plate information per unit time as the centroid of the corresponding data point, and performs cluster analysis on the user's historical parking feature data to obtain the user's parking preference portrait.

[0176] The dynamic convenience indicator module includes:

[0177] The distance factor unit, based on the divided parking areas of the parking lot, takes the distance between each divided parking area and the entrance and exit and the elevator platform as the convenience influencing factor of the area, and records it as the convenience distance characteristic parameter of each divided parking area;

[0178] A scoring unit performs normalization processing on the convenience distance characteristic parameter of each divided parking area to obtain a normalized score of the convenience distance characteristic parameter of each divided parking area;

[0179] A weighting unit assigns a weight to the convenience distance characteristic parameter of each divided parking area based on a normalized score of the convenience distance characteristic parameter of each divided parking area;

[0180] An initialization index unit, which quantifies an initialization convenience index of each divided parking area based on a normalized score of a convenience distance feature parameter of each divided parking area and a weight of a convenience distance feature parameter of each divided parking area;

[0181] The influence coefficient unit analyzes the changing trend of historical parking data of users in the divided parking areas based on the divided parking areas of the parking lot, and obtains the influence coefficient of the convenience index of each divided parking area:

[0182] The index correction unit corrects the initialization convenience index of each divided parking area based on the convenience index influence coefficient of each divided parking area to obtain a dynamic convenience index of each divided parking area.

[0183] Among them, the parking area matching module includes:

[0184] A matrix unit, based on the dynamic convenience index of each divided parking area in the parking lot, constructs a dynamic convenience index matrix for dividing parking areas;

[0185] A matching unit, which performs correlation matching based on the user's parking preference profile and the dynamic convenience index matrix of the divided parking areas, and obtains a matching value for each divided parking area;

[0186] The screening unit screens out the maximum value of the matching value of each divided parking area and records it as the parking planning area for the user to park.

[0187] Among them, the guidance route generation module includes:

[0188] The road network unit screens out all accessible routes between the parking user's location and the parking planning area location information, and constructs a road network diagram in the parking lot;

[0189] The vehicle flow data unit, based on the road network diagram in the parking lot, screens out the historical vehicle flow data of each entrance and exit in the road network diagram in the parking lot, and forms the historical vehicle flow time series data of the road network in the parking lot;

[0190] A congestion status unit, based on the historical traffic flow time series data of the road network in the parking lot, analyzes the congestion index of the passable roads in the historical traffic flow time series data of the road network;

[0191] A restriction condition unit, which takes a drivable route that minimizes a congestion index of a drivable road in the historical traffic flow time series data of a road network between a parking user's location and a parking planning area location as a restriction condition;

[0192] The objective function unit takes minimizing the travel time between the traversable routes and the route connection nodes as the objective function;

[0193] A model building unit, building a parking route guidance planning model;

[0194] The guidance route unit, based on the parking route guidance planning model, substitutes the historical traffic flow time series data of the road network in the parking lot under the constraints and according to the objective function, to generate a parking planning area guidance route for the user to be parked.

[0195] The use process of a data control system based on building intelligence is as follows:

[0196] Step 1: Obtain historical parking data of users in the parking lot, analyze the parking preferences of users in the historical parking data, and build a parking preference profile of users;

[0197] Step 2: Based on the divided parking areas of the parking lot, analyze the parking attributes of each divided parking area and quantify the dynamic convenience index of each divided parking area;

[0198] Step 3: Generate a parking planning area for users who want to park based on the user's parking preference profile and the dynamic convenience index of each divided parking area;

[0199] Step 4: Based on the parking planning area of ​​the user to be parked, mark all accessible routes between the location of the user to be parked and the location of the parking planning area to be parked, and record them as accessible routes in the parking planning area of ​​the user to be parked;

[0200] Step 5: Estimate the accessible routes of the parking planning area for the users waiting to park, build a parking route guidance planning model, and generate the parking planning area guidance routes for the users waiting to park;

[0201] Step 6: Upload the guidance route of the parking planning area of ​​the user to be parked to the intelligent guidance lights in the parking lot to complete the guidance control task.

[0202] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A data control method based on building intelligence, characterized in that: include: Based on the parking lot's backend database, obtain the user's historical parking data in the parking lot, analyze the user's parking preferences based on the historical parking data, and build a user parking preference profile; Based on the divided parking areas of the parking lot, analyze the parking attributes of each divided parking area and quantify the dynamic convenience index of each divided parking area; According to the user's parking preference profile and the dynamic convenience index of each divided parking area, a parking planning area for the user to park is generated; Based on the parking planning area of ​​the user to be parked, mark all accessible routes between the position of the user to be parked and the position of the parking planning area to be parked, and record them as accessible routes in the parking planning area of ​​the user to be parked; Estimate the accessible routes in the parking planning area for users waiting to park, build a parking route guidance planning model, and generate a parking planning area guidance route for users waiting to park; Upload the guidance route of the parking planning area for the user to be parked to the intelligent guidance lights in the parking lot to complete the guidance control task; Among them, based on the parking area division of the parking lot, the parking attributes of each divided parking area are analyzed, and the dynamic convenience index of each divided parking area is quantified, including: Based on the divided parking areas of the parking lot, the distance between each divided parking area and the entrance and exit and the elevator platform is taken as the convenience influencing factor of the area, which is recorded as the convenient distance characteristic parameter of each divided parking area; Normalizing the convenience distance characteristic parameter of each divided parking area to obtain a normalized score of the convenience distance characteristic parameter of each divided parking area; Based on the normalized score of the convenience distance characteristic parameter of each divided parking area, a weight is assigned to the convenience distance characteristic parameter of each divided parking area; Based on the normalized score of the convenience distance feature parameter of each divided parking area and the weight of the convenience distance feature parameter of each divided parking area, the initial convenience index of each divided parking area is quantified; Based on the parking lot's divided parking areas, analyze the changing trend of historical user parking data in the divided parking areas, and obtain the convenience index influence coefficient of each divided parking area: Based on the convenience index influence coefficient of each divided parking area, the initial convenience index of each divided parking area is corrected to obtain a dynamic convenience index of each divided parking area; The initialization convenience index for quantifying each divided parking area is specifically: ； In the formula, For the Initial convenience index for dividing parking areas, For the The first parking area Normalized score of convenience distance feature parameter, For the The first parking area Convenience distance feature parameter weight, The total number of parking areas to be divided; The method of obtaining the dynamic convenience index of each divided parking area is as follows: ； In the formula, For the A dynamic convenience index that divides parking areas. For the The convenience index influence coefficient of the divided parking area; The parking area division based on the parking lot, analyzing the change trend of the historical parking data of users in the divided parking area, and obtaining the convenience index influence coefficient of each divided parking area are specifically: Based on the historical parking data of users in the divided parking areas, a binary time series scatter plot of the historical parking data of users in the divided parking areas is constructed according to unit time; Based on the binary time series scatter plot of historical parking data of users divided into parking areas, the parking quantity corresponding to each scatter point in the binary time series scatter plot of historical parking data of users is screened to obtain the traffic flow characteristic data of the divided parking areas; According to the traffic flow characteristic data of the divided parking area, the external influencing factors of each corresponding time node are screened out as restriction conditions; the external influencing factors include: weather factors and holiday factors; Based on time series autoregression, a convenience trend assessment model for dividing parking areas is constructed; Based on the convenience trend evaluation model of divided parking areas, under the constraints, the traffic flow characteristic data of the divided parking areas are used as input, and the convenience index influence coefficient of each divided parking area is used as output; The convenience trend evaluation model for dividing parking areas is specifically as follows: ； In the formula, For the The convenience index influence coefficient of dividing parking areas is: For the The parking areas are divided into Traffic flow characteristic data under unit time learning order, is a constant term, is the autoregression coefficient, is the error term under t unit time.

2. A data control method based on building intelligence according to claim 1, characterized in that: Based on the parking lot's backend database, we obtain the historical parking data of users in the parking lot, analyze the parking preferences of users in the historical parking data, and build a user parking preference profile. Specifically: Based on the backend database of the parking lot, the historical parking data of users in the parking lot corresponding to the marking time is obtained to obtain the historical parking time series data of users in the parking lot; Based on the user historical parking time series data of the parking lot, the vehicle license plate information is used as the unique index, and the data is filtered according to the time attribute to obtain the user historical parking time series data set of the parking lot; Normalize the user's historical parking time series data set based on the parking lot, and extract the user's historical parking feature data; The user's historical parking feature data includes: parking time features, parking duration features, and parking frequency features; Through the clustering algorithm, the vehicle license plate information per unit time is used as the centroid of the corresponding data point, and cluster analysis is performed on the user's historical parking feature data to obtain the user's parking preference portrait; The clustering algorithm is specifically: ； In the formula, For the A user parking preference profile, is the sum of the squares of the distances from all samples in the cluster to the centroid of each cluster, for k Clusters of user historical parking feature data, for k The central value of the user's historical parking feature data of each cluster, For the User's Historical parking feature data, for The central value of the user's historical parking feature data of each cluster, is the total number of clusters.

3. A data control method based on building intelligence according to claim 1 or 2, characterized in that: According to the user's parking preference profile and the dynamic convenience index of each divided parking area, the parking planning area for the user to park is generated, including: Based on the dynamic convenience index of each divided parking area in the parking lot, a dynamic convenience index matrix for divided parking areas is constructed; Based on the user's parking preference profile and the dynamic convenience index matrix of the divided parking areas, the matching value of each divided parking area is obtained; Filter out the maximum value of the matching value of each divided parking area and record it as the parking planning area for the user to park; The specific matching value of each divided parking area is obtained as follows: ； In the formula, For the The matching values ​​for dividing the parking area, For the A user parking preference profile, For the A dynamic convenience indicator that divides parking areas.

4. A data control method based on building intelligence according to claim 3, characterized in that: Estimating the accessible routes in the parking planning area for users waiting to park, building a parking route guidance planning model, and generating the guidance routes in the parking planning area for users waiting to park specifically include: Obtaining the location of the parking user in the parking planning area of ​​the user to be parked and the location information of the parking planning area; Filter out all accessible routes between the parking user's location and the parking planning area location information, and construct a road network diagram in the parking lot; According to the road network diagram in the parking lot, the historical traffic flow data of each entrance and exit in the road network diagram in the parking lot is screened out to form the historical traffic flow time series data of the road network in the parking lot; Based on the historical traffic flow time series data of the road network in the parking lot, the congestion index of the passable roads in the historical traffic flow time series data of the road network is analyzed; Taking the congestion index of the drivable road in the historical traffic flow time series data of the road network between the location of the parking user and the location of the parking planning area as the constraint condition to minimize the drivable route; The objective function is to minimize the travel time between the traversable routes and the nodes connecting the routes; Construct a parking route guidance planning model; Based on the parking route guidance planning model, according to the constraint conditions and the objective function, the historical traffic flow time series data of the road network in the parking lot is substituted under the constraint conditions to generate the parking planning area guidance route for the user to be parked; Among them, the parking route guidance planning model is specifically as follows: ； In the formula, Provide guidance routes for parking area planning for users waiting to park. is the travel time of the e-th pass road in the road network, is the congestion index of the e-th access road in the road network, is the travel time weight, is the congestion index weight.

5. A data control system based on building intelligence, characterized in that: A data control method based on building intelligence for implementing any one of claims 1 to 4, comprising: A user portrait building module is used to obtain historical parking data of users in the parking lot based on the backend database of the parking lot, analyze the parking preferences of users in the historical parking data, and build a parking preference portrait of the users; A dynamic convenience index module is used to divide parking areas based on the parking lot, analyze the parking attributes of each divided parking area, and quantify the dynamic convenience index of each divided parking area; A parking area matching module, the parking area matching module is electrically connected to the dynamic convenience index module and the user portrait building module, and the parking area matching module is used to associate and match the user's parking preference portrait with the dynamic convenience index of each divided parking area to generate a parking planning area for the user to be parked; A route marking module, the route marking module is electrically connected to the parking area matching module, and the route marking module is used to mark all passable routes between the position of the user to be parked and the position of the parking area to be parked based on the parking area to be parked, and record them as passable routes in the parking area to be parked by the user to be parked; A guidance route generation module, the guidance route generation module is electrically connected to the route marking module, and the guidance route generation module is used to estimate the accessible route of the parking planning area for the user to be parked, build a parking route guidance planning model, and generate a guidance route for the parking planning area for the user to be parked; The guidance control module is electrically connected to the guidance route generation module. The guidance control module is used to upload the parking planning area guidance route of the user to be parked to the intelligent guidance lights in the parking lot to complete the guidance control task.

6. A data control system based on building intelligence according to claim 5, characterized in that: The user portrait building module includes: The data collection unit obtains the historical parking time series data of users in the parking lot based on the backend database of the parking lot by marking the historical parking data of users in the parking lot corresponding to the time. The time series data unit is based on the user historical parking time series data of the parking lot, uses the vehicle license plate information as the unique index, and filters according to the time attribute to obtain the user historical parking time series data set of the parking lot; A feature extraction unit, which performs normalization processing on a user's historical parking time series data set in the parking lot and extracts the user's historical parking feature data; The preference portrait unit uses a clustering algorithm to take the vehicle license plate information per unit time as the centroid of the corresponding data point, and performs cluster analysis on the user's historical parking feature data to obtain the user's parking preference portrait.

7. A data control system based on building intelligence according to claim 5, characterized in that: The dynamic convenience indicator module includes: The distance factor unit, based on the divided parking areas of the parking lot, takes the distance between each divided parking area and the entrance and exit and the elevator platform as the convenience influencing factor of the area, and records it as the convenience distance characteristic parameter of each divided parking area; A scoring unit performs normalization processing on the convenience distance characteristic parameter of each divided parking area to obtain a normalized score of the convenience distance characteristic parameter of each divided parking area; A weighting unit assigns a weight to the convenience distance feature parameter of each divided parking area based on a normalized score of the convenience distance feature parameter of each divided parking area; An initialization index unit, which quantifies an initialization convenience index of each divided parking area based on a normalized score of a convenience distance feature parameter of each divided parking area and a weight of a convenience distance feature parameter of each divided parking area; The influence coefficient unit analyzes the changing trend of historical parking data of users in the divided parking areas based on the divided parking areas of the parking lot, and obtains the influence coefficient of the convenience index of each divided parking area: The index correction unit corrects the initialization convenience index of each divided parking area based on the convenience index influence coefficient of each divided parking area to obtain a dynamic convenience index of each divided parking area.

8. A data control system based on building intelligence according to claim 5, characterized in that: The parking area matching module includes: A matrix unit, based on the dynamic convenience index of each divided parking area in the parking lot, constructs a dynamic convenience index matrix for dividing parking areas; A matching unit, which performs correlation matching based on the user's parking preference profile and the dynamic convenience index matrix of the divided parking areas, and obtains a matching value for each divided parking area; The screening unit screens out the maximum value of the matching value of each divided parking area and records it as the parking planning area for the user to park.

9. A data control system based on building intelligence according to claim 5, characterized in that: The guided route generation module includes: The road network unit screens out all accessible routes between the parking user's location and the parking planning area location information, and constructs a road network diagram in the parking lot; The vehicle flow data unit, based on the road network diagram in the parking lot, screens out the historical vehicle flow data of each entrance and exit in the road network diagram in the parking lot, and constructs the historical vehicle flow time series data of the road network in the parking lot; A congestion status unit, based on the historical traffic flow time series data of the road network in the parking lot, analyzes the congestion index of the passable roads in the historical traffic flow time series data of the road network; A restriction condition unit, which takes a drivable route that minimizes a congestion index of a drivable road in the historical traffic flow time series data of a road network between a parking user's location and a parking planning area location as a restriction condition; The objective function unit takes minimizing the travel time between the traversable routes and the route connection nodes as the objective function; A model building unit, building a parking route guidance planning model; The guidance route unit, based on the parking route guidance planning model, substitutes the historical traffic flow time series data of the road network in the parking lot under the constraints and according to the objective function, to generate a guidance route for the parking planning area for the user to park.

Images