Parking lot data analysis system based on Internet of Things

Abstract

The invention relates to the field of data analysis, in particular to a parking lot data analysis system based on the Internet of Things, which comprises an initial recommendation module used for carrying out initial evaluation on use recommendation indexes of recommendation analysis areas and determining whether recommendation evaluation analysis is carried out on the recommendation analysis areas or not; the evaluation analysis module is used for carrying out recommendation evaluation analysis and determining whether regional load analysis and regional use analysis are carried out or not according to the regional charging load parameters; the load analysis module is used for determining whether to adjust the use recommendation index or not according to the charging demand difference parameter; the use analysis module is used for determining whether existing use analysis or confluence use analysis is carried out according to the key reference user proportion index and determining whether adjustment is carried out according to the use recommendation index; and the recommendation execution module is used for determining a recommendation execution area of each target recommendation user based on the recommendation priority coefficient. According to the invention, the data analysis efficiency and analysis quality of the parking space recommendation process are improved.

Description

Technical Field

[0001] This invention relates to the field of data analysis, and more particularly to a parking lot data analysis system based on the Internet of Things. Background Technology

[0002] Based on the existing static traffic situation, in order to ensure the parking management effectiveness of the monitored parking lots, it is necessary to conduct targeted analysis of the actual parking space usage based on IoT analytics. By recommending parking spaces to parking lot users, uneven distribution of parking space usage and charging load imbalance can be avoided. The parking space recommendation analysis process for large parking lots often involves the analysis of many data types, resulting in significant data analysis pressure and consequently low data analysis efficiency. Therefore, how to improve data analysis efficiency while ensuring the quality of parking space recommendation results for parking lot operation and management is an urgent problem to be solved by those skilled in the art.

[0003] Chinese Patent Publication No. CN114255596A discloses a parking space recommendation system and method based on big data, belonging to the field of parking space recommendation technology. The system includes an instruction information acquisition module, a 3D verification module, a multi-source data analysis module, a parking space change prediction module, and a recommendation module. The output of the instruction information acquisition module is connected to the input of the 3D verification module; the output of the 3D verification module is connected to the input of the multi-source data analysis module; the output of the multi-source data analysis module is connected to the input of the parking space change prediction module; and the output of the parking space change prediction module is connected to the input of the recommendation module. Chinese Patent Publication No. CN114067604A discloses a smart parking service method and system based on big data analysis. This method determines the maximum distance a car can travel by acquiring its current remaining battery power, and then identifies the target charging station parking lot the car can reach fastest within the range of this maximum distance. Upon arrival at the target charging station parking lot, it acquires and analyzes the internal environment image to determine available charging station parking spaces. Finally, based on the relative position of the car and the available charging station parking spaces, it instructs the car to park in the available space. This method automatically searches for the target charging station parking lot the car can reach fastest based on its remaining battery power and further instructs the car to quickly park in an available charging station parking space, thereby improving the convenience of finding and parking charging stations and enhancing the intelligence and automation of parking services. However, the above solution has the following problems: it fails to determine a targeted analysis process based on actual conditions to periodically evaluate the recommendation of different parking areas for parked vehicles, resulting in low data analysis efficiency in the actual parking space recommendation process and consequently poor parking lot operation and management quality. Summary of the Invention

[0004] To address this issue, the present invention provides a parking lot data analysis system based on the Internet of Things, which overcomes the problem in the prior art that fails to determine a targeted analysis process based on actual conditions in order to periodically evaluate the recommendation of different parking space areas for parked vehicles, resulting in low data analysis efficiency in the actual parking space recommendation process.

[0005] To achieve the above objectives, the present invention provides a parking lot data analysis system based on the Internet of Things, comprising: The initial recommendation module is used to periodically perform an initial evaluation of the usage recommendation index for each recommendation analysis area and determine whether to perform recommendation evaluation analysis for each recommendation analysis area. The usage recommendation index is determined based on the area usage parameters and the area charging load parameters. An evaluation and analysis module, which is connected to the initial recommendation module, is used to perform recommendation evaluation and analysis, and to determine whether to perform regional load analysis and regional usage analysis for the recommended analysis area based on the regional charging load parameters. A load analysis module, connected to the evaluation analysis module, is used to determine whether to adjust the usage recommendation index based on the charging demand difference parameter, wherein the charging demand difference parameter is determined based on the charging demand parameter of each charging service parking space. The analysis module, which is connected to the evaluation analysis module, is used to determine whether to conduct existing usage analysis or cross-use analysis based on the key reference user proportion index, and to determine whether to adjust the usage recommendation index based on the key usage concentration parameters or cross-key parameters. The key reference user proportion index is determined based on the reference parking parameters and parking pattern parameters of each parking space user. The recommendation execution module is connected to the initial recommendation module, the load analysis module, and the usage analysis module, respectively, and is used to determine the recommendation execution area for each target recommended user based on the recommendation priority coefficient, which is determined according to the usage recommendation index and the target association index.

[0006] Furthermore, the usage recommendation index determined by the initial recommendation module for any of the recommendation analysis regions during the initial evaluation is negatively correlated with both the region usage parameters and the region charging load parameters. The initial analysis module performs recommended evaluation analysis for the evaluation analysis area, which is a recommended analysis area where the area usage parameters are greater than the preset area usage parameters or the area charging load parameters are greater than the preset area charging load parameters.

[0007] Furthermore, the load analysis module performs regional load analysis on evaluation and analysis areas where the regional charging load parameters are greater than preset regional charging load parameters, wherein... The charging demand difference parameter for any of the assessment and analysis areas is determined based on the charging demand parameter of each charging service parking space within the corresponding assessment and analysis area.

[0008] Furthermore, the load analysis module adjusts the usage recommendation index of the evaluation and analysis area where the charging demand difference parameter is less than or equal to the preset charging demand difference parameter based on the charging demand difference parameter and the regional charging load parameter. The decrease in the usage recommendation index is negatively correlated with the charging demand difference parameter, and the decrease in the usage recommendation index is positively correlated with the regional charging load parameter.

[0009] Furthermore, the usage analysis module performs regional usage analysis on evaluation and analysis areas where the regional charging load parameters are less than the preset regional charging load parameters or where regional load analysis has been completed. The key reference user percentage index is the percentage of the number of key reference users in the assessment and analysis area to the number of parking spaces in the assessment and analysis area. The key reference user is the parking space user whose reference parking parameter is greater than the preset reference parking parameter and whose parking pattern parameter is greater than the preset parking pattern parameter.

[0010] Furthermore, the usage analysis module performs existing usage analysis on evaluation and analysis areas where the percentage index of any key reference user is greater than the preset percentage index of key reference users, wherein, Determine whether to adjust the usage recommendation index for this assessment and analysis area based on key usage concentration parameters; The key usage set parameter is the percentage of the number of users in a given phase out of the total number of parking spaces in the evaluation and analysis area.

[0011] Furthermore, the usage analysis module adjusts the usage recommendation index by reducing the usage set index for evaluation and analysis areas where the key usage set index is greater than the preset key usage set index, based on the key usage set parameters. The decrease in the recommended index is positively correlated with the key usage set parameters.

[0012] Furthermore, the usage analysis module performs cross-use analysis on any key reference user percentage index that is less than or equal to a preset key reference user percentage index or on evaluation analysis areas that have completed existing usage analysis. Determine whether to adjust the usage recommendation index for this assessment and analysis area based on the key parameters of the intersection.

[0013] Furthermore, the usage analysis module adjusts the usage recommendation index by reducing the value of the evaluation analysis area where the key intersection parameters are greater than the preset key intersection parameters, based on the key intersection parameters. The decrease in the recommended index is positively correlated with the convergence key parameter.

[0014] Furthermore, the recommendation execution module records the recommendation analysis region with a recommendation priority coefficient greater than a preset recommendation priority coefficient as the recommendation execution region of the corresponding target recommendation user; The recommendation priority coefficient is positively correlated with both the recommendation index and the target correlation index.

[0015] Compared with the prior art, the beneficial effects of the present invention are that the technical solution of the present invention determines the usage recommendation index of each recommended analysis area based on the regional usage parameters and regional charging load parameters for initial evaluation and whether to conduct recommendation evaluation analysis, and determines the targeted recommendation evaluation analysis method based on the regional charging load parameters, thereby making targeted adjustments. By conducting effective analysis of the usage recommendation index of each recommended analysis area in advance, the data analysis efficiency of the parking space recommendation process for vehicles entering the parking lot is improved.

[0016] Furthermore, this invention determines the regional load analysis and regional usage analysis for the recommended analysis area based on the regional charging load parameters. Combined with the actual parking space usage in different areas, it makes targeted settings for the actual adjustment scheme of the usage recommendation index, ensuring that the adjustment of the usage recommendation index is more in line with the actual situation. This ensures the validity of the final determination result of the usage recommendation index for each recommended analysis area. This invention improves the data analysis efficiency and analysis quality of the parking space recommendation process.

[0017] Furthermore, this invention performs regional load analysis on evaluation and analysis areas where the regional charging load parameters are greater than the preset regional charging load parameters. It quantifies the balance of electricity demand for parking spaces in each recommended analysis area using charging demand difference parameters. When the charging demand difference parameter is small, it indicates a risk of concentrated vehicle charging demand in the area (e.g., most vehicles require high-power fast charging). In this case, by reducing the usage recommendation index for the corresponding area, it is possible to prevent vehicles from flooding into the area, thus avoiding increased regional burden and preventing concentrated demand changes from affecting the charging process of vehicles. Based on precise control of electricity demand differences, the risk of excessive grid load fluctuations can be effectively avoided. This invention not only ensures the continuous stability of charging services but also improves the data analysis efficiency of the parking space recommendation process.

[0018] Furthermore, this invention performs regional usage analysis on evaluation and analysis areas where the regional charging load parameters are less than the preset regional charging load parameters or where regional load analysis has been completed. It determines whether to perform existing usage analysis or convergent usage analysis based on the key reference user proportion index. On one hand, it identifies areas with a high probability of concentrated vehicle exits in the near future by using key usage concentration parameters, reducing their recommendation index to avoid congestion caused by concentrated vehicle exits in these areas. On the other hand, it associates areas with overlapping exit routes by using convergent key parameters, predicting surrounding traffic pressure and reducing the recommendation priority of high-risk areas in advance. This invention, while ensuring the overall traffic efficiency and management order of the parking lot, avoids over-analysis of data through targeted analysis, thus improving the data analysis efficiency of the parking space recommendation process. Attached Figure Description

[0019] Figure 1 This is a module connection diagram of the IoT-based parking data analysis system of the present invention; Figure 2 This is a flowchart illustrating the present invention's determination of whether to perform regional load analysis and regional usage analysis for a recommended analysis area based on regional charging load parameters. Figure 3 This is a flowchart illustrating the present invention's determination of whether to perform existing usage analysis or cross-use analysis based on a key reference user percentage index. Figure 4 This is a flowchart illustrating the present invention for determining whether to adjust the usage recommendation index for the evaluation and analysis area based on key usage set parameters. Detailed Implementation

[0020] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0021] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0022] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0023] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0024] Please see Figures 1 to 4 As shown, the present invention provides a parking lot data analysis system based on the Internet of Things, comprising: The initial recommendation module is used to periodically perform an initial evaluation of the usage recommendation index for each recommendation analysis area and determine whether to perform recommendation evaluation analysis for each recommendation analysis area. The usage recommendation index is determined based on the area usage parameters and the area charging load parameters. An evaluation and analysis module, which is connected to the initial recommendation module, is used to perform recommendation evaluation and analysis, and to determine whether to perform regional load analysis and regional usage analysis for the recommended analysis area based on the regional charging load parameters. A load analysis module, connected to the evaluation analysis module, is used to determine whether to adjust the usage recommendation index based on the charging demand difference parameter, wherein the charging demand difference parameter is determined based on the charging demand parameter of each charging service parking space. The analysis module, which is connected to the evaluation analysis module, is used to determine whether to conduct existing usage analysis or cross-use analysis based on the key reference user proportion index, and to determine whether to adjust the usage recommendation index based on the key usage concentration parameters or cross-key parameters. The key reference user proportion index is determined based on the reference parking parameters and parking pattern parameters of each parking space user. The recommendation execution module is connected to the initial recommendation module, the load analysis module, and the usage analysis module, respectively, and is used to determine the recommendation execution area for each target recommended user based on the recommendation priority coefficient, which is determined according to the usage recommendation index and the target association index.

[0025] This invention relates to a data analysis process for recommending parking spaces in parking lots equipped with charging piles. By periodically conducting targeted analysis on each parking space area, the efficiency of data analysis in the parking space recommendation process is improved, ensuring the quality of parking lot operation and management. The parking lot under operation and management is designated as the target management parking lot, which contains a number of parking spaces. Users who have used parking spaces in the target management parking lot are designated as parking space users. The parking spaces in the target management parking lot are divided to determine several recommendation analysis areas, each of which contains a number of parking spaces. This invention does not make specific limitations on the division of recommendation analysis areas, as this is easily understood by those skilled in the art and will not be elaborated here. This invention utilizes several recommendation analysis records. Each recommendation analysis record contains at least one instance of regional usage parameters, regional charging load parameters, charging demand difference parameters, reference parking parameters, parking pattern parameters, key reference user percentage index, key usage concentration parameters, intersection key parameters, and recommendation priority coefficient during the parking space recommendation analysis process in the parking lot's operation and management phase. Each recommendation analysis record also has a corresponding qualification mark, which indicates whether the data analysis efficiency and quality of the parking space recommendation process meet user needs. It can be understood that users can determine whether the data analysis efficiency of the parking space recommendation process meets their needs based on their own set indicators.

[0026] Specifically, the usage recommendation index determined by the initial recommendation module for any of the recommendation analysis regions is negatively correlated with both the region usage parameters and the region charging load parameters. The initial analysis module performs recommended evaluation analysis for the evaluation analysis area, which is a recommended analysis area where the area usage parameters are greater than the preset area usage parameters or the area charging load parameters are greater than the preset area charging load parameters.

[0027] In this invention, a cyclical regional evaluation cycle is applied. The duration of the regional evaluation cycle can be determined by the user. The higher the user's requirements for the data analysis efficiency of the parking space recommendation process, the shorter the duration of the regional evaluation cycle. A duration of 30 minutes for the regional evaluation cycle is provided. At the end of each regional evaluation cycle, the regional usage parameters and regional charging load parameters of each recommended analysis area are detected to initially determine the usage recommendation index and determine whether to perform regional load analysis. If the current time is the end of a regional evaluation cycle, an initial evaluation is performed for each recommended analysis region. For a single recommended analysis region, the usage recommendation index and the usage load coefficient are negatively correlated. The usage load coefficient is the sum of the regional usage parameter and the regional charging load parameter. The regional usage parameter is the proportion of the number of parking spaces in use within the recommended analysis region to the total number of parking spaces in that region. This recommendation analyzes the number of currently occupied parking spaces within the recommended area. The recommended analysis area contains the number of parking spaces. The regional charging load parameter is the percentage of the number of charging operation parking spaces within the recommended analysis area to the total number of charging service parking spaces within the target management parking lot. The number of charging operation parking spaces in the recommended analysis area is n, and the number of charging service parking spaces in the target management parking lot is n. The charging operation parking space is the charging service parking space currently used to charge parked vehicles, and the charging service parking space is the parking space equipped with charging piles that can provide charging services for vehicles. The values ​​of the preset area usage parameters and preset area charging load parameters can be determined by the user according to the actual working scenario. For example, the user can set them based on the recommendation analysis records. The higher the user's requirement for the data analysis efficiency of the parking space recommendation process, the smaller the value of the preset area usage parameters and the preset area charging load parameters. A method for determining the value of the preset area usage parameters is provided, which records the minimum value of the area usage parameters of the evaluation analysis area in the recommendation analysis records that meet the user's requirements for the data analysis efficiency of the parking space recommendation process as the preset area usage parameters. A method for determining the value of the preset area charging load parameters is provided, which records the minimum value of the area charging load parameters of the evaluation analysis area in the recommendation analysis records that meet the user's requirements for the data analysis efficiency of the parking space recommendation process as the preset area charging load parameters.

[0028] Specifically, the load analysis module performs regional load analysis on evaluation and analysis areas where the regional charging load parameters are greater than preset regional charging load parameters. The charging demand difference parameter for any of the assessment and analysis areas is determined based on the charging demand parameter of each charging service parking space within the corresponding assessment and analysis area.

[0029] For a single assessment and analysis area, if the regional charging load parameter of the assessment and analysis area is greater than the preset regional charging load parameter, it indicates that there are many parked vehicles in the current assessment and analysis area that need charging services. Under the condition of large electricity demand, it is necessary to ensure the stability of the power grid corresponding to the assessment and analysis area. Therefore, regional load analysis is performed to determine whether there is a concentrated change in electricity demand in the assessment and analysis area, thereby indicating whether the assessment and analysis area is prone to significant power grid fluctuations. For a single assessment and analysis area conducting regional load analysis, the charging demand difference parameter is the standard deviation of the charging demand parameters corresponding to each existing charging service parking space in that assessment and analysis area. For a single charging service parking space, the charging demand parameter is the ratio of the uncharged battery capacity of the parked vehicle corresponding to that charging service parking space to the maximum battery capacity of the corresponding parked vehicle. p1 represents the current remaining battery capacity of the vehicle parked at the charging service parking space, and p0 represents the maximum battery capacity of the vehicle parked at the charging service parking space.

[0030] Specifically, the load analysis module adjusts the usage recommendation index of the evaluation and analysis area where the charging demand difference parameter is less than or equal to the preset charging demand difference parameter based on the charging demand difference parameter and the regional charging load parameter. The decrease in the usage recommendation index is negatively correlated with the charging demand difference parameter, and the decrease in the usage recommendation index is positively correlated with the regional charging load parameter.

[0031] Specifically, for a single assessment area undergoing regional load analysis, if the charging demand difference parameter of that assessment area is less than or equal to a preset charging demand difference parameter, it indicates that the difference in electricity demand among the existing charging service spaces in that area is small. This suggests that the assessment area is prone to concentrated changes in electricity demand, leading to significant grid fluctuations that can impact the charging process. Therefore, the recommended usage parameter for that assessment area is reduced. During the adjustment process, the impact of concentrated changes in electricity demand is quantified based on the charging demand difference parameter and the regional charging load parameter. The reduction in the recommended usage parameter is positively correlated with the demand reference coefficient. E represents the regional charging load parameter for the evaluation and analysis area. Parameters for the differences in charging demand in the assessment and analysis area; The value of the preset charging demand difference parameter can be determined by the user based on the actual working scenario. For example, the user can set it based on the recommendation analysis record. The higher the user's requirement for the data analysis efficiency of the parking space recommendation process, the larger the value of the preset charging demand difference parameter. A method for determining the value of the preset charging demand difference parameter is provided, in which the recommendation analysis record that adjusts the usage recommendation index of the evaluation analysis area according to the charging demand difference parameter and the regional charging load parameter is recorded as the demand reference record, and the average value of the charging demand difference parameter in the demand reference record that meets the user's requirement for the data analysis efficiency of the parking space recommendation process is recorded as the preset charging demand difference parameter.

[0032] Specifically, the usage analysis module performs regional usage analysis on evaluation and analysis areas where the regional charging load parameters are less than the preset regional charging load parameters or where regional load analysis has been completed. The key reference user percentage index is the percentage of the number of key reference users in the assessment and analysis area to the number of parking spaces in the assessment and analysis area. The key reference user is the parking space user whose reference parking parameter is greater than the preset reference parking parameter and whose parking pattern parameter is greater than the preset parking pattern parameter.

[0033] Specifically, for a single assessment and analysis area, if the area charging load parameter of the assessment and analysis area is less than the preset area charging load parameter or the area load analysis has been completed, an area usage analysis is performed on the assessment and analysis area to determine the concentrated risk of vehicle entry and exit in the assessment and analysis area, thereby determining whether the parking space usage in the assessment and analysis area will affect the vehicle entry and exit efficiency of the target management parking lot. For a single evaluation and analysis area, the key reference user percentage index This represents the number of key reference users currently existing within the assessment and analysis area. To determine the number of parking spaces within the assessment and analysis area, for a single parking space user, the reference parking parameter is the number of times that user uses the parking space in the target managed parking lot. The parking pattern parameter is the sum of the parameter difference indices of various usage record parameters. For a single usage record parameter, the parameter difference index... l1 is the standard deviation of the value of the usage record parameter corresponding to the parking space of the target managed parking lot for each time the user uses the parking space, and l0 is the average value of the value of the usage record parameter corresponding to the parking space of the target managed parking lot for each time the user uses the parking space. The categories of usage record parameters used to determine parking pattern parameters include: parking space usage duration, parking space usage start time and parking space usage end time. The values ​​of the preset reference parking parameters and preset parking pattern parameters can be determined by the user based on the actual working scenario. For example, the user can set them based on the recommendation analysis records. The higher the user's requirement for the data analysis efficiency of the parking space recommendation process, the larger the value of the preset reference parking parameters and the larger the value of the preset parking pattern parameters. A method for determining the value of the preset reference parking parameters is provided, in which the reference parking parameters of key users in the recommendation analysis records that meet the user's requirements for the data analysis efficiency of the parking space recommendation process are recorded as the preset reference parking parameters. A method for determining the value of the preset parking pattern parameters is also provided, in which the parking pattern parameters of key users in the recommendation analysis records that meet the user's requirements for the data analysis efficiency of the parking space recommendation process are recorded as the preset parking pattern parameters.

[0034] Specifically, the usage analysis module performs existing usage analysis on evaluation and analysis areas where the percentage of key reference users is greater than a preset percentage of key reference users. Determine whether to adjust the usage recommendation index for this assessment and analysis area based on key usage concentration parameters; The key usage set parameter is the percentage of the number of users in a given phase out of the total number of parking spaces in the evaluation and analysis area.

[0035] Specifically, the usage analysis module adjusts the usage recommendation index by reducing the usage concentration index for evaluation and analysis areas where the key usage concentration parameter is greater than the preset key usage concentration parameter, based on the key usage concentration parameter. The decrease in the recommended index is positively correlated with the key usage set parameters.

[0036] Specifically, for a single assessment and analysis area, if the key reference user percentage index is greater than the preset key reference user percentage index, it indicates that the parking space occupancy in that area is relatively high, but the proportion of key reference users is also relatively large. In this case, the existing parking space users exhibit a clear pattern. Based on existing parking space usage habits, the probability of parking space users in that assessment and analysis area collectively leaving the area in the near future is determined. The key usage concentration parameter... This represents the number of users currently using the technology within the assessment and analysis area. The evaluation criteria define the number of parking spaces within the evaluation area. The "stage user" refers to a parking space user whose reference end time or key usage time is within or before the evaluation stage. For a single parking space user, the reference end time is the median of the end times of each use of a parking space in the target managed parking lot. The key usage time is the time the user is at the current start time of parking space use, delayed by a reference usage duration. The reference usage duration is the average of the usage durations of each use of a parking space in the target managed parking lot. The start time of the evaluation stage is the current time. The duration of the evaluation stage can be determined by the user based on their actual work scenario. For example, the user can set it based on recommendation analysis records. The higher the user's requirement for the data analysis efficiency of the parking space recommendation process, the longer the evaluation stage duration. One evaluation stage duration is provided: 30 minutes. If the key usage concentration parameter of the assessment and analysis area is greater than the preset key usage concentration parameter, it indicates that there is a high risk of concentrated vehicle exits in the assessment and analysis area in the near future. Therefore, the usage recommendation index for the assessment and analysis area is reduced to avoid vehicle congestion affecting the operation and management efficiency of the parking lot. The values ​​of the preset key reference user ratio index and the preset key usage concentration parameter can be determined by the user according to the actual work scenario. For example, the user can set them based on the recommendation analysis records. One method for determining the preset key reference user ratio index is to record the existing usage analysis records for the assessment and analysis area as usage reference records, and record the minimum value of the key reference user ratio index in the usage reference records that meet the user's data analysis efficiency requirements for the parking space recommendation process as the preset key reference user ratio index. Another method for determining the preset key usage concentration parameter is to record the minimum value of the key usage concentration parameter of the assessment and analysis area that meets the user's data analysis efficiency requirements for the parking space recommendation process as the preset key usage concentration parameter.

[0037] Specifically, the usage analysis module performs cross-use analysis on any key reference user percentage index that is less than or equal to a preset key reference user percentage index or on an evaluation analysis area that has completed existing usage analysis. Determine whether to adjust the usage recommendation index for this assessment and analysis area based on the key parameters of the intersection.

[0038] Specifically, the usage analysis module adjusts the usage recommendation index of the evaluation analysis area where the intersection key parameters are greater than the preset intersection key parameters based on the intersection key parameters. The decrease in the recommended index is positively correlated with the convergence key parameter.

[0039] In a single assessment and analysis area, if the key reference user ratio index is less than or equal to the preset key reference user ratio index, it indicates that the parking space occupancy in the assessment and analysis area is relatively heavy, but the proportion of key reference users is small. At this time, there is no obvious regularity in the use of parking spaces, and it is impossible to effectively determine whether there is a risk of concentrated exit based on the usage of the target management parking lot. Therefore, for assessment and analysis areas where the key reference user ratio index is less than or equal to the preset key reference user ratio index or where the existing usage analysis has been completed, a convergence usage analysis is performed. The convergence key parameters characterize whether there is a large risk of concentrated vehicle traffic in the surrounding vehicle driving areas of the assessment and analysis area in the near future. The convergence key parameters are the average value of the key usage concentration parameters of each convergence analysis area of ​​the assessment and analysis area. For any two recommended analysis areas, if the exit routes corresponding to the parking spaces in the two recommended analysis areas overlap, the two recommended analysis areas are recorded as mutual convergence analysis areas. For a single assessment and analysis area, if the intersection key parameter of the assessment and analysis area is greater than the preset intersection key parameter, it indicates that there is a significant risk of concentrated vehicle traffic in the surrounding vehicle driving areas of the assessment and analysis area in the near future. Therefore, the usage recommendation index for the assessment and analysis area is reduced to avoid continuously burdening the target parking lot. The value of the preset intersection key parameter can be determined by the user according to the actual working scenario. For example, the user can set it based on the recommendation analysis records. A method for determining the value of the preset intersection key parameter is provided, in which the recommendation analysis records that reduce the usage recommendation index based on the intersection key parameter are recorded as intersection reference records, and the minimum value of the intersection key parameter in the intersection reference records that meets the user's data analysis efficiency requirements for the parking space recommendation process is recorded as the preset intersection key parameter.

[0040] Specifically, the recommendation execution module records the recommendation analysis region with a recommendation priority coefficient greater than a preset recommendation priority coefficient as the recommendation execution region of the corresponding target recommendation user; The recommendation priority coefficient is positively correlated with both the recommendation index and the target correlation index.

[0041] The target recommended users are those who currently need to use parking spaces within the target managed parking lot. Parking space recommendations are made based on the current usage of the target managed parking lot, prioritizing recommendation analysis areas with higher priority coefficients to avoid imbalances in parking space allocation within the target managed parking lot, which could affect the actual operation and management quality of the parking lot. For a single target recommended user, the recommendation priority coefficient for any recommendation analysis area is the sum of the currently determined usage recommendation index and the target correlation index for that recommendation analysis area. The target correlation index for a single recommendation analysis area for that target recommended user is... This refers to the number of currently associated users within the recommended analysis area. The number of parking spaces in the recommended analysis area is given. The associated users are those whose interval between the reference end time or key usage time and the target estimated time is less than the preset association time. The target estimated time is the time when the target recommended user is at the current parking space usage start time after the reference usage time. If the target recommended user has no usage record for the target managed parking lot, the target association index is recorded as 1. The preset recommendation priority coefficient and preset association duration can be determined by the user based on the actual work scenario. For example, the user can set them based on the recommendation analysis records. The higher the user's requirements for the data analysis quality of the parking space recommendation process, the larger the preset recommendation priority coefficient and the smaller the preset association duration. A method for determining the preset recommendation priority coefficient is provided, which is the average value of the recommendation priority coefficients of the recommendation execution area in the recommendation analysis records that meet the user's requirements for the data analysis quality of the parking space recommendation process. A preset association duration value of 10 minutes is also provided.

[0042] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. An Internet of Things based parking lot data analysis system, characterized by, Comprising an initial recommendation module, configured to periodically perform initial evaluation on a use recommendation index of each recommendation analysis region, and determine whether to perform recommendation evaluation analysis on each recommendation analysis region, wherein the use recommendation index is determined according to a region use parameter and a region charging load parameter; an evaluation analysis module, connected to the initial recommendation module, configured to perform recommendation evaluation analysis, and determine whether to perform region load analysis and region use analysis on the recommendation analysis region according to the region charging load parameter; a load analysis module, connected to the evaluation analysis module, configured to determine whether to adjust the use recommendation index according to a charging demand difference parameter, wherein the charging demand difference parameter is determined according to a charging demand parameter of each charging service parking space; a use analysis module, connected to the evaluation analysis module, configured to determine whether to perform existing use analysis or intersection use analysis according to a key reference user proportion index, and determine whether to adjust the use recommendation index according to a key use concentration parameter or an intersection key parameter, wherein the key reference user proportion index is determined based on a reference parking parameter and a parking regularity parameter of a user of each parking space; a recommendation execution module, connected to the initial recommendation module, the load analysis module, and the use analysis module respectively, configured to determine a recommendation execution region of each target recommendation user based on a recommendation priority coefficient, wherein the recommendation priority coefficient is determined according to the use recommendation index and a target correlation index.

2. The Internet of Things-based parking lot data analysis system according to claim 1, wherein the use recommendation index determined by the initial evaluation of the initial recommendation module on any of the recommendation analysis regions is in a negative correlation relationship with the region use parameter and the region charging load parameter respectively; the initial analysis module performs recommendation evaluation analysis on the evaluation analysis region, wherein the evaluation analysis region is a recommendation analysis region with a region use parameter greater than a preset region use parameter or a region charging load parameter greater than a preset region charging load parameter.

3. The Internet of Things-based parking lot data analysis system according to claim 2, wherein the load analysis module performs region load analysis on the evaluation analysis region with a region charging load parameter greater than a preset region charging load parameter, wherein the charging demand difference parameter of any of the evaluation analysis regions is determined according to the charging demand parameter of each charging service parking space in the corresponding evaluation analysis region.

4. The Internet of Things-based parking lot data analysis system according to claim 3, wherein the load analysis module reduces the use recommendation index of the evaluation analysis region with a charging demand difference parameter less than or equal to a preset charging demand difference parameter according to the charging demand difference parameter and the region charging load parameter; the reduction value of the use recommendation index is in a negative correlation relationship with the charging demand difference parameter, and in a positive correlation relationship with the region charging load parameter.

5. The Internet of Things-based parking lot data analysis system according to claim 4, wherein The use analysis module performs regional use analysis on the evaluation analysis region whose regional charging load parameter is less than a preset regional charging load parameter or whose regional load analysis is completed, wherein The key reference user proportion index is a proportion of a number of key reference users existing in the evaluation analysis region in a number of parking spaces existing in the evaluation analysis region. The key reference user is a parking space user whose reference parking parameter is greater than a preset reference parking parameter and whose parking regularity parameter is greater than a preset parking regularity parameter.

6. The Internet of Things-based parking lot data analysis system according to claim 5, wherein The use analysis module performs existing use analysis on the evaluation analysis region whose arbitrary key reference user proportion index is greater than a preset key reference user proportion index, wherein Whether to adjust the use recommendation index of the evaluation analysis region is determined according to a key use concentration parameter. The key use concentration parameter is a proportion of a number of stage use users in a number of parking spaces existing in the evaluation analysis region.

7. The Internet of Things-based parking lot data analysis system according to claim 6, wherein The use analysis module decreases the use recommendation index of the evaluation analysis region whose key use concentration parameter is greater than a preset key use concentration parameter according to the key use concentration parameter. The decrease value of the use recommendation index is in a positive correlation with the key use concentration parameter.

8. The Internet of Things-based parking lot data analysis system according to claim 7, wherein The use analysis module performs intersection use analysis on the evaluation analysis region whose arbitrary key reference user proportion index is less than or equal to a preset key reference user proportion index or whose existing use analysis is completed, wherein Whether to adjust the use recommendation index of the evaluation analysis region is determined according to an intersection key parameter.

9. The Internet of Things-based parking lot data analysis system according to claim 8, wherein The use analysis module decreases the use recommendation index of the evaluation analysis region whose intersection key parameter is greater than a preset intersection key parameter according to the intersection key parameter. The decrease value of the use recommendation index is in a positive correlation with the intersection key parameter.

10. The Internet of Things-based parking lot data analysis system according to claim 1, wherein The recommendation execution module records the recommendation analysis region whose recommendation priority coefficient is greater than a preset recommendation priority coefficient as a recommendation execution region of a corresponding target recommendation user. The recommendation priority coefficient is in a positive correlation with the use recommendation index and the target association index, respectively.

Images