Smart cloud platform parking guidance management system and method

Abstract

The present invention belongs to the technical field of intelligent parking management, and specifically relates to a parking guidance management system and method for a smart cloud platform. The parking guidance management system of the smart cloud platform monitors each parking area in real time through a pre-set parking lot system, and accurately grasps the parking space occupancy situation. Based on this, the system generates a parking guidance mode, calculates parking space allocation data, and analyzes parking efficiency. The parking guidance strategy is optimized through weight values ​​and matrix conversion, and an abnormal analysis model is input to identify and process abnormal areas, and spare parking areas are matched to guide parking. The method improves the efficiency of parking resource utilization, optimizes management efficiency and driver experience.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent parking management, and specifically relates to a parking guidance management system and method for a smart cloud platform. Background Art

[0002] With the sharp increase in automobile production and the rapid advancement of urbanization, parking has become a major problem in the field of urban transportation. Especially in public places such as commercial centers, airports, and hospitals, it often takes a lot of time to find an empty parking space, which not only affects the driver's parking experience, but also aggravates the problems of vehicle emissions and traffic congestion. Therefore, it is particularly important to efficiently manage parking resources and quickly guide drivers to empty parking spaces.

[0003] Traditional parking guidance methods usually rely on manual inspection or simple electronic display boards to indicate vacant parking space information. These methods have disadvantages such as low accuracy, delayed information update, and inability to provide dynamic guidance. With the development of information technology, although some parking guidance systems based on video surveillance and sensors have emerged, which can provide relatively real-time parking space information, these systems often operate independently, lack integrated analysis and intelligent optimization, and cannot dynamically adjust guidance strategies according to actual parking space usage, making it difficult to maximize the use of parking resources and improve parking efficiency.

[0004] In addition, when abnormal situations occur, such as overcrowding in parking areas or incorrect occupation of parking spaces, the existing systems often lack effective response mechanisms and are unable to identify and handle such abnormalities in a timely manner, let alone dynamically adjust parking guidance strategies based on abnormal situations, further exacerbating the problem of difficulty in parking.

[0005] In summary, the existing technology cannot effectively solve the problems of low parking resource utilization, low parking guidance efficiency and insufficient ability to deal with abnormal situations in parking lots. Summary of the invention

[0006] 1. Technical issues to be resolved

[0007] The present invention mainly aims at the above problems and proposes a smart cloud platform parking guidance management system and method, which aims to solve the problems of low parking resource utilization, low parking guidance efficiency and insufficient ability to deal with abnormal situations in parking lots.

[0008] (II) Technical solution

[0009] To achieve the above-mentioned object, the first aspect of the present invention provides a parking guidance management method for a smart cloud platform, the parking guidance management method comprising:

[0010] Step S100: Based on a preset parking system, multiple parking areas are monitored in real time to obtain the parking space occupancy status of each parking area;

[0011] Step S200: generating a parking guidance mode for each parking area according to the parking space occupancy status, and calculating parking space allocation data for each parking area according to the parking guidance mode;

[0012] Step S300: Analyze the parking space allocation data of each parking area to obtain a parking space distribution index, and calculate the parking efficiency of each parking area according to the parking guidance mode and the parking space allocation data;

[0013] Step S400: sorting the parking space distribution indicators of a plurality of parking areas to obtain a parking space distribution sequence, acquiring a first weight value, and constructing a parking space distribution matrix corresponding to the parking space distribution sequence;

[0014] Step S500: querying a first weight value from the parking lot system according to the parking space distribution index; calculating a weighted value of the parking space distribution sequence according to the first weight value to obtain a weighted parking space distribution sequence;

[0015] Step S600: performing matrix conversion on the weighted parking space distribution sequence to obtain a parking space distribution matrix corresponding to the parking space distribution sequence;

[0016] Step S700: sorting the parking efficiencies of the plurality of parking areas to obtain a parking efficiency sequence, acquiring a second weight value, and constructing a parking efficiency matrix corresponding to the parking efficiency sequence;

[0017] Step S800: query a second weight value from the parking lot system according to the parking efficiency; calculate the weight value of the parking efficiency sequence according to the second weight value to obtain a weighted parking efficiency sequence;

[0018] Step S900: performing matrix conversion on the weighted parking efficiency sequence to obtain a parking efficiency matrix corresponding to the parking efficiency sequence;

[0019] Step S1000: input the parking space distribution matrix and the parking efficiency matrix into a preset parking lot abnormality analysis model to perform parking area abnormality analysis to obtain a target abnormal parking area;

[0020] Step S1100: selecting a parking area abnormality handling strategy according to the target abnormal parking area, matching a spare parking area according to the parking area abnormality handling strategy, and guiding the parking lot system to park through the spare parking area.

[0021] Further, in step S200, generating a parking guidance mode for each parking area according to the parking space occupancy status, and calculating parking space allocation data for each parking area according to the parking guidance mode, including:

[0022] Step S201, extracting features of the parking space occupancy status to obtain multiple occupancy features;

[0023] Step S202: clustering parking features for each parking area according to the multiple occupancy features, and generating a parking guidance mode for each parking area;

[0024] Step S203: Calculate parking space allocation data for each parking area according to the parking guidance mode.

[0025] Furthermore, in step S300, the method for calculating the parking space distribution index includes:

[0026] Step S301: collect statistics on the parking space occupancy of each parking area, and calculate the average occupancy rate as a parking space distribution index. The calculation formula of the average occupancy rate is:

[0027] ;

[0028] Step S302: Based on the spatial density and dwell time around the parking spaces, the congestion of the parking area is calculated as another parking space distribution indicator.

[0029] Furthermore, in step S300, the method for calculating parking efficiency includes:

[0030] Step S303: Count the parking time of each parking area and calculate the average parking time as a parking efficiency indicator. The calculation formula for the average parking time is:

[0031]

[0032] in, is the number of vehicles in the parking area and the parking duration i It is The length of time the vehicle is parked.

[0033] Step S304: Count the vehicle entry and exit frequencies of each parking area, and calculate the average entry and exit frequency as another parking efficiency indicator, wherein the calculation formula of the entry and exit frequency is:

[0034] .

[0035] Furthermore, in step S400, the step of constructing a parking space distribution matrix corresponding to the parking space distribution sequence includes:

[0036] Step S401, determining parking space distribution indicators of multiple parking areas, wherein the parking space distribution indicators include average occupancy rate and congestion degree;

[0037] Step S402: Arrange the parking space distribution indicators of each parking area into a sequence according to a predefined order;

[0038] Step S403: sorting the parking space distribution sequence, and obtaining a sorted parking space distribution sequence based on the parking space distribution index;

[0039] Step S404: obtaining a first weight value, where the first weight value is determined based on real-time data analysis;

[0040] Step S405: using the first weight value, converting the parking space distribution sequence into a weighted sequence;

[0041] Step S406: convert the weighted parking space distribution sequence into a matrix form, where each element corresponds to a weighted parking space distribution index.

[0042] Furthermore, in step S1000, the step of obtaining the target abnormal parking area includes:

[0043] Performing matrix fusion on the parking space distribution matrix and the parking efficiency matrix to obtain a target fusion matrix;

[0044] Inputting the target fusion matrix into a preset parking lot anomaly analysis model, wherein the parking lot anomaly analysis model includes: a convolutional network, a threshold recurrent network, and a fully connected network;

[0045] Perform parking area anomaly analysis on the target fusion matrix through the parking lot anomaly analysis model to obtain matrix anomaly elements;

[0046] According to the abnormal elements of the matrix, the target abnormal parking area is queried.

[0047] Furthermore, in step S700, the step of constructing a parking efficiency matrix corresponding to the parking efficiency sequence includes:

[0048] Step S701: Count the parking efficiency index of each parking area, where the parking efficiency index includes the average parking time and the average entry and exit frequency;

[0049] Step S702: Arrange the parking efficiency indicators into a sequence according to a certain order;

[0050] Step S703: sorting the parking efficiency sequence, and obtaining a sorted parking efficiency sequence based on the parking efficiency index;

[0051] Step S704: obtaining a second weight value;

[0052] Step S705: using the second weight value, converting the parking efficiency sequence into a weighted sequence;

[0053] Step S706: Convert the weighted parking efficiency sequence into a matrix form, where each element corresponds to a weighted parking efficiency index.

[0054] Furthermore, in step S900, the step of performing matrix conversion on the weighted parking efficiency sequence includes:

[0055] Step S901, arranging the weighted parking efficiency sequence in the format of a row vector or a column vector;

[0056] Step S902: According to the actual layout of the parking area, adjust the structure of the sequence to convert it into a two-dimensional matrix form, wherein each element of the two-dimensional matrix represents a weighted parking efficiency index.

[0057] Furthermore, in the step S1100, it also includes: detecting the parking state of the spare parking area through the parking lot system, and guiding the parking lot system to park through the spare parking area.

[0058] To achieve the above-mentioned object, the second aspect of the present invention provides a smart cloud platform parking guidance management system, including a pre-installed parking system, wherein the parking system is configured with:

[0059] A real-time monitoring module is used to monitor multiple parking areas in real time to obtain the parking space occupancy status of each parking area;

[0060] a parking guidance module, which generates a parking guidance mode for each parking area according to the parking space occupancy status, and calculates parking space allocation data for each parking area according to the parking guidance mode;

[0061] A data analysis module, for analyzing the parking space allocation data of each parking area to obtain a parking space distribution index, and calculating the parking efficiency of each parking area according to the parking guidance mode and the parking space allocation data;

[0062] A sequence sorting module is used to sort the parking space distribution indicators of multiple parking areas to obtain a parking space distribution sequence, obtain a first weight value, and construct a parking space distribution matrix corresponding to the parking space distribution sequence;

[0063] A weighted calculation module, according to the parking space distribution index and the parking efficiency, queries the corresponding first weight value and the second weight value from the parking lot system, calculates the weighted values ​​of the parking space distribution sequence and the parking efficiency sequence respectively, and obtains a weighted parking space distribution sequence and a weighted parking efficiency sequence;

[0064] A matrix conversion module, used for performing matrix conversion on the weighted parking space distribution sequence and the weighted parking efficiency sequence to obtain a parking space distribution matrix and a parking efficiency matrix corresponding to the parking space distribution sequence and the parking efficiency sequence respectively;

[0065] An abnormality analysis module, which performs parking area abnormality analysis by inputting the parking space distribution matrix and the parking efficiency matrix into a preset parking lot abnormality analysis model to obtain a target abnormal parking area;

[0066] The abnormality handling matching module selects a parking area abnormality handling strategy according to the obtained target abnormal parking area, matches a spare parking area according to the parking area abnormality handling strategy, and then guides the parking lot system to park through the spare parking area.

[0067] (III) Beneficial effects

[0068] Compared with the prior art, the present invention provides a smart cloud platform parking guidance management system and method, which solves the above technical problems by building a smart cloud platform that integrates real-time monitoring, intelligent analysis and dynamic guidance. First, a plurality of parking areas are monitored in real time through a preset parking system to accurately obtain the parking space occupancy situation of each parking area; then, based on the parking space occupancy data, a parking guidance mode is generated and the parking space allocation data is calculated, and then the parking space distribution index is analyzed and the parking efficiency is calculated; then, through the introduction of weight values ​​and matrix conversion, the parking space distribution and parking efficiency are sorted and weighted to obtain an optimized parking guidance strategy; finally, this information is input into a preset parking lot abnormality analysis model to identify and process abnormal parking areas, and guide parking through spare parking areas. This series of intelligent operations makes the use of parking resources more efficient, greatly improving the management efficiency of parking lots and the parking experience of drivers. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 This is a flow chart of a smart cloud platform parking guidance management method disclosed in this application.

[0070] Figure 2 This application discloses a parking lot real-time monitoring and data processing framework.

[0071] Figure 3 A logic judgment diagram for selecting a parking area abnormality handling strategy disclosed in this application.

[0072] Figure 4 This is a weighted processing framework diagram of parking space distribution disclosed in this application.

[0073] Figure 5 This is a weighted processing framework diagram of parking efficiency disclosed in this application.

[0074] Figure 6 This is a framework diagram of a smart cloud platform parking guidance management system disclosed in this application. DETAILED DESCRIPTION

[0075] The present invention will be described in detail below in conjunction with the accompanying drawings, and the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0076] This embodiment provides a smart cloud platform parking guidance management system and method, which aims to optimize parking guidance and management by real-time monitoring of parking space occupancy in parking areas and analyzing parking efficiency. The following is a detailed explanation of the solution.

[0077] like Figure 1-Figure 5 As shown, the first aspect of this embodiment provides a parking guidance management method for a smart cloud platform, the management method comprising:

[0078] Step S100: Based on a preset parking lot system, multiple parking areas are monitored in real time to obtain the parking space occupancy status of each parking area.

[0079] First, deploy vehicle identification technology, such as video analysis or license plate recognition systems, at the entrance and exit locations of each parking area to track the occupancy status of parking spaces in each parking area in real time. Use sensor technology, such as geomagnetic sensors or ultraviolet sensors, installed on each parking space to obtain accurate information on whether each parking space is occupied, such as which parking spaces are occupied and which are vacant. Through wireless communication technology, such as Wi-Fi or LoRaWAN, the collected vehicle occupancy data is sent to the central processing system in real time for analysis.

[0080] Step S200: Generate a parking guidance pattern for each parking area according to the parking space occupancy status, and calculate parking space allocation data for each parking area according to the parking guidance pattern.

[0081] After obtaining the real-time parking space occupancy status of each parking area, this information is used to generate a parking guidance mode specific to each parking area. This process includes analyzing the current parking space utilization rate, identifying which areas have a high demand for parking spaces and which areas have more vacant parking spaces. Then, based on this data, the parking space allocation data for each parking area is calculated, that is, the number of vehicles reasonably allocated to each area is determined to achieve the best parking efficiency and user satisfaction. This step can use intelligent algorithms, such as machine learning models, to predict the demand for each parking area in different time periods and optimize the parking space allocation accordingly.

[0082] Step S300: Analyze the parking space allocation data of each parking area to obtain a parking space distribution index, and calculate the parking efficiency of each parking area according to the parking guidance mode and the parking space allocation data.

[0083] Next, the system analyzes the parking space allocation data for each parking area to derive parking space distribution indicators, such as the average parking space utilization rate, peak utilization rate, and number of free parking spaces in each area. Based on the parking guidance pattern and parking space allocation data, the parking efficiency of each parking area is calculated, for example, taking into account factors such as the diversion speed of arriving vehicles and parking search time. In this way, the performance of each parking area can be comprehensively evaluated and possible bottlenecks and room for improvement can be identified.

[0084] Step S400: sort the parking space distribution indicators of multiple parking areas to obtain a parking space distribution sequence, obtain a first weight value, and construct a parking space distribution matrix corresponding to the parking space distribution sequence.

[0085] This step involves ranking the parking space distribution indicators of all parking areas to form a clear parking space distribution sequence, which can intuitively show which areas have more parking space usage. In addition, the system will obtain the first weight value and then build a matrix reflecting the parking space distribution of different parking areas. This weight value is determined based on historical data, real-time traffic conditions or other relevant factors, and is used to adjust the importance of each item in the parking space distribution sequence to ensure that the analysis results are more in line with the actual situation.

[0086] Step S500: query a first weight value from the parking lot system according to the parking space distribution index; calculate a weighted value of the parking space distribution sequence according to the first weight value to obtain a weighted parking space distribution sequence.

[0087] In this step, based on the previous parking space distribution indicators and the first weight value, the weighted parking space distribution sequence is retrieved and calculated from the parking system database. During this process, the indicators of each parking area are adjusted according to its corresponding weight value, thereby generating a new sequence that reflects the weighted parking space usage. This helps to highlight those areas that have a greater impact on the overall parking efficiency and provide a basis for priority setting.

[0088] Step S600: Perform matrix conversion on the weighted parking space distribution sequence to obtain a parking space distribution matrix corresponding to the parking space distribution sequence.

[0089] The above weighted parking space distribution sequence is transformed into a matrix to obtain the corresponding parking space distribution matrix. This step is to structure the sequence data and express it in matrix form, making the data easier to further mathematically process and analyze. After the matrix transformation, matrix operations can be used to process the data more efficiently, facilitating subsequent abnormal analysis and optimization strategies.

[0090] Step S700: sort the parking efficiencies of the plurality of parking areas to obtain a parking efficiency sequence, acquire a second weight value, and construct a parking efficiency matrix corresponding to the parking efficiency sequence.

[0091] After analyzing the parking space distribution, the system further sorts the parking efficiency of each parking area to form a parking efficiency sequence and obtains a second weight value. Similar to the first weight value, the second weight value is also based on certain standards or conditions to evaluate and adjust the importance of each item in the parking efficiency sequence. Then, this weight value is used to construct a parking efficiency matrix, which shows the efficiency of each parking area in a structured way and reflects the contribution of each area to the overall parking management through weight adjustment.

[0092] Step S800: query a second weight value from the parking lot system according to the parking efficiency; calculate a weighted value of the parking efficiency sequence according to the second weight value to obtain a weighted parking efficiency sequence.

[0093] In this step, the system queries and calculates the weighted parking efficiency sequence from the parking system based on the parking efficiency and the second weight value. Here, each indicator of parking efficiency is adjusted according to its corresponding weight, so as to obtain a comprehensive and objective parking efficiency evaluation result, which helps to accurately identify inefficient parking areas.

[0094] Step S900: Perform matrix conversion on the weighted parking efficiency sequence to obtain a parking efficiency matrix corresponding to the parking efficiency sequence.

[0095] Perform matrix transformation on the weighted parking efficiency sequence to generate the corresponding parking efficiency matrix. This step is also intended to organize the data for more complex data analysis and processing. Through the matrix form, it is more convenient to apply mathematical and statistical methods to analyze parking efficiency.

[0096] Step S1000: Input the parking space distribution matrix and the parking efficiency matrix into a preset parking lot abnormality analysis model to perform parking area abnormality analysis to obtain a target abnormal parking area.

[0097] The parking space distribution matrix and parking efficiency matrix are input into the pre-set parking lot anomaly analysis model. Based on advanced data analysis technologies such as artificial intelligence and machine learning, this model conducts in-depth analysis of the performance of parking areas and identifies parking areas with abnormal performance.

[0098] Step S1100: selecting a parking area abnormality handling strategy according to the target abnormal parking area, matching a spare parking area according to the parking area abnormality handling strategy, and guiding the parking lot system to park through the spare parking area.

[0099] According to the identified target abnormal parking area, the system will select the appropriate parking area abnormal handling strategy, such as adding guidance signs, optimizing parking guidance mode, adjusting parking space allocation, etc. Then, the corresponding backup parking area is matched according to the selected strategy, and the parking system is guided through these backup areas to relieve the pressure of abnormal areas and optimize the overall parking environment. This step ensures that the parking system can flexibly respond to various abnormal situations and maintain parking order and efficiency.

[0100] like Figure 2 As shown, in step S200, a parking guidance pattern for each parking area is generated according to the parking space occupancy situation, and parking space allocation data for each parking area is calculated according to the parking guidance pattern, including: extracting features from the parking space occupancy situation, such as parking space location, size, occupancy time, etc.; inputting the extracted features into a K-means clustering algorithm, and clustering the parking areas according to the similarity of the parking spaces; the cluster center of each parking area represents the parking guidance pattern of the area, that is, represents the most common parking situation in the area, and the parking space allocation data for each parking area is calculated according to the parking guidance pattern.

[0101] The following are the specific calculation steps for the parking space distribution index and parking efficiency.

[0102] 1. The calculation of parking space distribution index includes the calculation of average occupancy rate and congestion degree, see Figure 4 .

[0103] The calculation method of average occupancy rate is:

[0104] The average occupancy rate indicates the proportion of parking spaces occupied, and its calculation formula is:

[0105] .

[0106] The calculation method of congestion is:

[0107] Congestion refers to the density and time distribution of parking space occupancy. It can be estimated by calculating the number of vehicles around each parking space and their stay time.

[0108] 2. Parking efficiency calculation includes average parking time calculation and entry and exit frequency calculation, see Figure 5 .

[0109] The calculation method for the average parking time is:

[0110] Average Parking Duration refers to the average time a vehicle spends in a parking space. The calculation formula is:

[0111] ,

[0112] is the number of vehicles in the parking area and the parking duration i It is The length of time the vehicle is parked.

[0113] The calculation method of the entry and exit frequency is:

[0114] In-Out Frequency refers to the frequency of vehicles entering and exiting parking spaces. The calculation formula is:

[0115] .

[0116] These calculation formulas can help evaluate parking lot usage and efficiency and provide data support for parking guidance management.

[0117] In step S400 of this embodiment, the step of constructing a parking space distribution matrix corresponding to the parking space distribution sequence includes: first, the system determines the key parking space distribution indicators of each parking area, including the average occupancy rate and the degree of congestion. The average occupancy rate reflects the average occupancy of parking spaces in the parking area, while the degree of congestion measures the use pressure of parking spaces during peak hours. Then, these parking space distribution indicators are arranged into a sequence according to a certain order, and this order can be defined based on geographical location, frequency of use or other relevant factors. Next, the parking space distribution sequence is sorted according to the parking space distribution indicators determined previously, so that it can be intuitively seen which areas are more crowded or have a higher utilization rate. A first weight value is obtained, which is obtained based on real-time data analysis and can reflect the relative importance or priority of each parking area in the current situation. Using the first weight value obtained above, the parking space distribution sequence is weighted so that certain indicators have greater influence in the overall evaluation. Finally, the weighted parking space distribution sequence is converted into a matrix form, in which each element corresponds to a weighted parking space distribution indicator, which is convenient for subsequent more in-depth analysis and processing.

[0118] In step S1000 of the present embodiment, the step of obtaining the target abnormal parking area includes: fusing the matrices of parking space distribution and parking efficiency to generate a target fusion matrix that comprehensively reflects the parking lot status; inputting the target fusion matrix into a preset parking lot abnormality analysis model, which uses deep learning technologies such as convolutional networks, threshold recurrent networks, and fully connected networks to analyze the overall status of the parking lot; identifying abnormal elements in the matrix through the abnormality analysis model, and these abnormal elements represent parking areas that may have problems; based on these abnormal elements, querying and determining the target abnormal parking area, providing a basis for taking corresponding adjustment measures.

[0119] In step S700 of the present embodiment, the step of constructing a parking efficiency matrix corresponding to the parking efficiency sequence includes: firstly, counting the parking efficiency index of each parking area, including the average parking time and the average entry and exit frequency, which are directly related to the parking experience of the user; arranging the parking efficiency indexes into a sequence in a certain order, and the order may be based on factors such as region and parking demand intensity; sorting the parking efficiency sequence to form a clear sequence sorted by efficiency based on the parking efficiency index; obtaining a second weight value, which is used to adjust the parking efficiency indexes between different parking areas to reflect their relative importance or priority; using the second weight value, converting the parking efficiency sequence into a weighted sequence, further strengthening the identification and analysis of parking efficiency differences; finally, converting the weighted parking efficiency sequence into a matrix form, so that each element corresponds to a weighted parking efficiency index, which facilitates subsequent analysis.

[0120] In step S900 of this embodiment, the step of performing matrix conversion on the weighted parking efficiency sequence includes: arranging the weighted parking efficiency sequence in the format of a row vector or a column vector to meet the format requirements of the matrix; and adjusting the sequence structure according to the actual layout of the parking area to convert it into a two-dimensional matrix form. This ensures that each element in the matrix accurately represents the weighted parking efficiency index of the corresponding parking area, which is convenient for further analysis.

[0121] In step S1000 of this embodiment, the specific steps of constructing a parking lot anomaly analysis model include: defining the goals and standards of anomaly analysis, and clarifying the types of anomalies that need to be identified; collecting and preparing data, including historical parking data, time information, weather conditions, etc.; designing a model architecture, combining a convolutional network (for extracting spatial features), a threshold recurrent network (for extracting time series features), and a fully connected network (for advanced feature fusion and classification or regression tasks); training the model using the collected data, and optimizing the model parameters through methods such as cross-validation; evaluating the model performance on a test set, and adjusting the model structure or parameters based on the results; deploying the model to a production environment, and analyzing parking area anomalies in real time in an actual parking lot system.

[0122] In step S1100 of this embodiment, it also includes: before executing the parking area exception handling strategy, the current parking status of the spare parking area is detected by the parking lot system to ensure that the decision to guide the vehicle is based on the latest data; then, these spare parking areas are used to guide the parking lot system, optimize the parking process, reduce the pressure in crowded areas, and ensure the efficiency of parking lot operations and user satisfaction.

[0123] like Figure 6 As shown, the second aspect of this embodiment provides a smart cloud platform parking guidance management system, including a pre-installed parking system, and the parking system is configured with:

[0124] A real-time monitoring module is used to monitor multiple parking areas in real time to obtain the parking space occupancy status of each parking area;

[0125] a parking guidance module, which generates a parking guidance mode for each parking area according to the parking space occupancy status, and calculates parking space allocation data for each parking area according to the parking guidance mode;

[0126] A data analysis module, for analyzing the parking space allocation data of each parking area to obtain a parking space distribution index, and calculating the parking efficiency of each parking area according to the parking guidance mode and the parking space allocation data;

[0127] A sequence sorting module is used to sort the parking space distribution indicators of multiple parking areas to obtain a parking space distribution sequence, obtain a first weight value, and construct a parking space distribution matrix corresponding to the parking space distribution sequence;

[0128] A weighted calculation module, according to the parking space distribution index and the parking efficiency, queries the corresponding first weight value and the second weight value from the parking lot system, calculates the weighted values ​​of the parking space distribution sequence and the parking efficiency sequence respectively, and obtains a weighted parking space distribution sequence and a weighted parking efficiency sequence;

[0129] A matrix conversion module, used for performing matrix conversion on the weighted parking space distribution sequence and the weighted parking efficiency sequence to obtain a parking space distribution matrix and a parking efficiency matrix corresponding to the parking space distribution sequence and the parking efficiency sequence respectively;

[0130] An abnormality analysis module, which performs parking area abnormality analysis by inputting the parking space distribution matrix and the parking efficiency matrix into a preset parking lot abnormality analysis model to obtain a target abnormal parking area;

[0131] The abnormality handling matching module selects a parking area abnormality handling strategy according to the obtained target abnormal parking area, matches a spare parking area according to the parking area abnormality handling strategy, and then guides the parking lot system to park through the spare parking area.

[0132] To further explain the solution of this embodiment, a specific scenario is taken as an example to illustrate the application of the parking guidance management method:

[0133] Suppose there is a shopping mall with a large parking lot divided into multiple parking areas, with a total of 1,000 parking spaces. The management team of the shopping mall hopes to improve the utilization rate and management efficiency of the parking lot through the parking guidance management method of the smart cloud platform.

[0134] Sensors are installed on each parking space to monitor the occupancy of the parking space in real time. The smart cloud platform collects and processes sensor data in real time through the pre-installed parking system. Based on the sensor data, the smart cloud platform clusters the parking characteristics of each parking area. For example, the parking spaces in a certain area are mostly occupied by small vehicles, while the parking spaces in another area are more suitable for large vehicles. Based on these characteristics, a parking guidance pattern is generated and the allocation data of parking spaces is calculated to optimize the use of parking areas. Based on the parking space allocation data of the parking area, the smart cloud platform analyzes the parking efficiency. For example, whether the allocation of parking spaces in a certain area is reasonable, whether there is congestion, etc. The parking space distribution matrix and the parking efficiency matrix are input into the parking lot anomaly analysis model for analysis. The model identifies anomalies in the parking lot, such as an abnormally high parking space utilization rate in a certain area, or an abnormally low parking efficiency. Based on the anomaly analysis results, the smart cloud platform determines the target abnormal parking area. For abnormal parking areas, corresponding processing strategies are adopted, such as adding warning signs or adjusting parking space allocation. At the same time, the spare parking area is matched according to the strategy, and the parking status of the spare parking area is monitored. If there are vacant parking spaces in the alternative parking area, the smart cloud platform will guide vehicles to the alternative parking area to reduce congestion in the parking area.

[0135] Through this smart cloud platform parking guidance management method, shopping malls can better manage parking lots, improve the utilization rate of parking spaces, reduce congestion in parking areas, and provide customers with a better parking experience.

[0136] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present application is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by the same unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0137] The above embodiments are only used to illustrate the technical solution of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person skilled in the art should understand that the technical solution of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present application.

Claims

1. A parking guidance management method for a smart cloud platform, characterized in that: The parking guidance management method comprises: Step S100: Based on a preset parking system, multiple parking areas are monitored in real time to obtain the parking space occupancy status of each parking area; Step S200: generating a parking guidance mode for each parking area according to the parking space occupancy status, and calculating parking space allocation data for each parking area according to the parking guidance mode; Step S300: Analyze the parking space allocation data of each parking area to obtain a parking space distribution index, and calculate the parking efficiency of each parking area according to the parking guidance mode and the parking space allocation data; Step S400, sorting the parking space distribution indicators of multiple parking areas to obtain a parking space distribution sequence; Step S500: query a first weight value from the parking lot system according to the parking space distribution index; calculate a weight value of the parking space distribution sequence according to the first weight value to obtain a weighted parking space distribution sequence; the first weight value is obtained based on real-time data analysis and can reflect the relative importance or priority of each parking area in the current situation; Step S600: performing matrix conversion on the weighted parking space distribution sequence to obtain a parking space distribution matrix corresponding to the parking space distribution sequence; Step S700, sorting the parking efficiencies of the plurality of parking areas to obtain a parking efficiency sequence; Step S800: querying a second weight value from the parking lot system according to the parking efficiency; calculating a weight value of the parking efficiency sequence according to the second weight value to obtain a weighted parking efficiency sequence; the second weight value is used to adjust the parking efficiency of different parking areas to reflect relative importance or priority; Step S900: performing matrix conversion on the weighted parking efficiency sequence to obtain a parking efficiency matrix corresponding to the parking efficiency sequence; Step S1000: input the parking space distribution matrix and the parking efficiency matrix into a preset parking lot abnormality analysis model to perform parking area abnormality analysis to obtain a target abnormal parking area; Step S1100: selecting a parking area abnormality handling strategy according to the target abnormal parking area, matching a spare parking area according to the parking area abnormality handling strategy, and guiding the parking lot system to park through the spare parking area; In step S300, the method for calculating the parking space distribution index includes: Step S301: collect statistics on the parking space occupancy of each parking area, and calculate the average occupancy rate as a parking space distribution index. The calculation formula of the average occupancy rate is: ； Step S302: Calculate the congestion of the parking area as another parking space distribution indicator based on the spatial density and residence time around the parking space; In step S300, the method for calculating parking efficiency includes: Step S303: Count the parking time of each parking area and calculate the average parking time as a parking efficiency indicator. The calculation formula for the average parking time is: Among them, is the number of vehicles in the parking area, and parking duration i is the parking duration of the th vehicle; Step S304: Count the vehicle entry and exit frequencies of each parking area, and calculate the average entry and exit frequency as another parking efficiency indicator, wherein the calculation formula of the entry and exit frequency is: 。 2. The parking guidance management method of a smart cloud platform according to claim 1 is characterized in that: In step S200, a parking guidance mode for each parking area is generated according to the parking space occupancy status, and parking space allocation data for each parking area is calculated according to the parking guidance mode, including: Step S201, extracting features of the parking space occupancy status to obtain multiple occupancy features; Step S202: clustering parking features for each parking area according to the multiple occupancy features, and generating a parking guidance mode for each parking area; Step S203: Calculate parking space allocation data for each parking area according to the parking guidance mode.

3. The parking guidance management method of a smart cloud platform according to claim 1 is characterized in that: In step S1000, the step of obtaining the target abnormal parking area includes: Performing matrix fusion on the parking space distribution matrix and the parking efficiency matrix to obtain a target fusion matrix; Inputting the target fusion matrix into a preset parking lot anomaly analysis model, wherein the parking lot anomaly analysis model includes: a convolutional network, a threshold recurrent network, and a fully connected network; Perform parking area anomaly analysis on the target fusion matrix through the parking lot anomaly analysis model to obtain matrix anomaly elements; According to the abnormal elements of the matrix, the target abnormal parking area is queried.

4. The parking guidance management method of a smart cloud platform according to claim 1 is characterized in that: In step S900, the step of performing matrix conversion on the weighted parking efficiency sequence includes: Step S901, arranging the weighted parking efficiency sequence in the format of a row vector or a column vector; Step S902: According to the actual layout of the parking area, adjust the structure of the sequence to convert it into a two-dimensional matrix form, wherein each element of the two-dimensional matrix represents a weighted parking efficiency index.

5. The parking guidance management method of a smart cloud platform according to claim 1, characterized in that: In the step S1100, it also includes: detecting the parking state of the spare parking area by the parking lot system, and guiding the parking lot system to park by the spare parking area.

6. A smart cloud platform parking guidance management system, characterized in that: A pre-installed parking system is included, wherein the parking system is configured with: A real-time monitoring module is used to monitor multiple parking areas in real time to obtain the parking space occupancy status of each parking area; a parking guidance module, which generates a parking guidance mode for each parking area according to the parking space occupancy status, and calculates parking space allocation data for each parking area according to the parking guidance mode; A data analysis module, for analyzing the parking space allocation data of each parking area to obtain a parking space distribution index, and calculating the parking efficiency of each parking area according to the parking guidance mode and the parking space allocation data; A sequence sorting module is used to sort the parking space distribution indicators and parking efficiency of multiple parking areas to obtain a parking space distribution sequence and a parking efficiency sequence; A weighted calculation module, according to the parking space distribution index and the parking efficiency, queries the corresponding first weight value and the second weight value from the parking lot system, calculates the weighted values ​​of the parking space distribution sequence and the parking efficiency sequence respectively, and obtains a weighted parking space distribution sequence and a weighted parking efficiency sequence; The first weight value is obtained based on real-time data analysis and can reflect the relative importance or priority of each parking area under the current situation; The second weight value is used to adjust the parking efficiency of different parking areas to reflect the relative importance or priority; A matrix conversion module, used for performing matrix conversion on the weighted parking space distribution sequence and the weighted parking efficiency sequence to obtain a parking space distribution matrix and a parking efficiency matrix corresponding to the parking space distribution sequence and the parking efficiency sequence respectively; An abnormality analysis module, which performs parking area abnormality analysis by inputting the parking space distribution matrix and the parking efficiency matrix into a preset parking lot abnormality analysis model to obtain a target abnormal parking area; An exception handling matching module selects a parking area exception handling strategy according to the obtained target abnormal parking area, matches a spare parking area according to the parking area exception handling strategy, and then guides the parking lot system to park through the spare parking area; The calculation method of parking space distribution index includes: The parking space occupancy of each parking area is counted, and the average occupancy rate is calculated as the parking space distribution index. The calculation formula of the average occupancy rate is: ； Based on the spatial density and dwelling time around parking spaces, the congestion of the parking area is calculated as another parking space distribution indicator; The calculation method of parking efficiency includes: The parking time of each parking area is counted, and the average parking time is calculated as the parking efficiency indicator. The calculation formula for the average parking time is: Among them, is the number of vehicles in the parking area, and parking duration i is the parking duration of the th vehicle; The vehicle entry and exit frequency of each parking area is counted, and the average entry and exit frequency is calculated as another parking efficiency indicator. The calculation formula of the entry and exit frequency is: 。

Images