Iot-driven parking management device

Abstract

The present application relates to parking management technical field, specifically relates to internet of things driven parking management equipment, the equipment realizes the appearance analysis to the travel and parking situation of each parking travel passageway in the parking lot in combination with four modules, the passageway that exists appearance difficulty parking is accurately analyzed in combination with neural network technology, forms the initiative management link of " data acquisition-intelligent analysis-immediate disposal", ensures the efficient response and accurate control to current parking difficulty, determines whether the remaining passageways that may be influenced in combination with the appearance parking situation of the current parking travel passageway under the condition that the parking travel passageway does not exist appearance difficulty parking, carries out the appearance situation of pre-analysis to each passageway, deeply excavates whether appearance difficulty parking may appear subsequently in the parking travel passageway, to determine whether the parking travel passageway needs early intervention management, and the management focus is changed from passive response to active prevention and control.

Description

Technical Field

[0001] This invention relates to the field of parking management technology, and more specifically, to Internet of Things-driven parking management devices. Background Technology

[0002] Traditional parking management systems primarily rely on manual patrols, fixed signage guidance, and simple sensor monitoring, making it difficult to cope with the dynamic changes in urban parking demand. For example, in high-traffic areas such as commercial centers and transportation hubs, the lack of accurate quantitative assessment of real-time traffic efficiency and parking resource utilization leads to the following problems:

[0003] Delayed response mechanism: Relying on human experience to judge congestion or parking shortages usually takes a certain amount of time from problem discovery to handling, which can easily lead to regional traffic paralysis.

[0004] Lack of risk prediction: It is impossible to identify potential congestion nodes in advance through historical data and spatial correlation analysis, and the management strategy is limited to "post-event remediation" and lacks the ability to intervene in the difficulty of parking in advance.

[0005] Resource allocation is inefficient: Parking space allocation and access function planning are fixed and difficult to adjust dynamically according to real-time demand, resulting in both congestion in some access channels and idle parking spaces, leading to a low overall turnover rate of the parking lot.

[0006] While existing intelligent parking management solutions incorporate IoT technology, they largely remain at the level of "data display" and fail to achieve in-depth intelligent analysis and decision support. For example:

[0007] Using parking space occupancy as the sole basis for parking guidance has led to a large number of vehicles congesting and parking difficulties by driving into a single lane.

[0008] Management loop broken: Data collection, analysis, and processing are disconnected from each other, failing to form a complete "perception-analysis-response-optimization" chain. The system lacks adaptability and is unable to cope with parking management needs in complex scenarios.

[0009] To address the aforementioned problems, this invention proposes an Internet of Things-driven parking management device. Summary of the Invention

[0010] In view of the shortcomings of existing technologies, the purpose of this invention is to provide an Internet of Things-driven parking management device.

[0011] To achieve the above objectives, the present invention provides the following technical solution:

[0012] The IoT-driven parking management equipment includes a parking difficulty analysis module, a parking difficulty management module, a potential difficulty parking analysis module, and a potential difficulty parking management module.

[0013] The apparent difficulty parking analysis module periodically generates parking status logs for each parking lane in the parking lot to further determine whether there are apparent difficulty parking situations in each parking lane.

[0014] The apparent difficulty parking management module determines that there is an apparent difficulty parking situation in the parking lane and directly puts the parking lane into management.

[0015] The potential difficulty parking analysis module determines whether a potential difficulty parking situation exists in the parking lane if it is determined that there is no apparent difficulty parking situation in the parking lane.

[0016] The "Potential Difficulty Parking Management" module allows parking management personnel to intervene in advance when a parking lane presents a potential difficulty parking situation.

[0017] Furthermore, the lane parking status log includes the lane number and the moving parking dataset.

[0018] Furthermore, the specific steps for generating the driving and parking dataset of the lane parking status log are as follows: periodically collect various driving and parking data of the parking driving lane within a cycle, and integrate the various driving and parking data into a driving and parking dataset in the form of a set.

[0019] Furthermore, the specific steps for determining whether there is a parking difficulty situation in the parking lane are as follows: obtain the driving parking dataset of the parking status log of the corresponding lane, further import the driving parking dataset into the apparent difficulty parking model, derive the apparent difficulty parking index from the apparent difficulty parking model, set the apparent difficulty parking threshold index, and determine that there is an apparent difficulty parking situation in the parking lane when the apparent difficulty parking index is higher than the apparent difficulty parking threshold index.

[0020] Furthermore, when it is determined that there is a parking difficulty situation in the parking lane, the corresponding parking lane is marked as a parking difficulty lane, and a parking difficulty log for the parking difficulty lane is generated simultaneously. The parking difficulty log includes the lane number, the parking difficulty time, and parking management personnel are arranged to intervene in the management of the parking difficulty lane.

[0021] Furthermore, the specific steps for determining whether a parking lane has a potentially difficult parking situation are as follows: Select a parking lane and obtain its independent possible difficulty reference index. Draw a circle with the midpoint of the parking lane as the center and the parking possibility analysis radius as the radius to obtain the possible difficulty analysis range. Mark the remaining parking lanes located within the possible difficulty analysis range as range-affected lanes and obtain the range-affected potential index for each range-affected lane. Based on the independent possible difficulty reference index of the parking lane, the total number of range-affected lanes, and the average range-affected potential index, calculate the possible difficulty parking index of the parking lane. When the possible difficulty parking index of the parking lane is higher than the possible difficulty parking threshold index, it is determined that the parking lane has a potentially difficult parking situation.

[0022] Furthermore, the steps for obtaining the average range potentially affecting the index are as follows: sum the ranges that may affect the index across all range-affected channels and take the average to calculate the average range potentially affecting the index.

[0023] Furthermore, the specific steps for obtaining the range influence index of the range influence channel are as follows: Select a range influence channel, obtain the independent possible difficulty reference index of the range influence channel, simultaneously obtain the apparent difficulty parking index of the range influence channel, sum the independent possible difficulty reference index and the apparent difficulty parking index, and calculate the range influence index of the range influence channel.

[0024] Furthermore, the steps for obtaining the independent possible difficulty reference index of the parking lane are as follows: obtain all apparent difficulty parking logs generated previously for the parking lane, obtain the possible difficulty reference index for each apparent difficulty parking log, sum and average the possible difficulty reference indices of all apparent difficulty parking logs, and calculate the independent possible difficulty reference index.

[0025] Furthermore, the specific steps for obtaining the possible difficulty reference index of the apparent difficulty parking log are as follows: Select an apparent difficulty parking log, determine the apparent difficulty parking time of the apparent difficulty parking log, obtain the S consecutive lane parking status logs generated before the apparent difficulty parking time of the parking lane, sort all lane parking status logs in the order of generation, and label them sequentially in order of generation; obtain the S consecutive lane parking status logs generated before the current time of the parking lane, sort all lane parking status logs in the order of generation, and label them sequentially in order of generation. The sequence number is used to obtain the synchronization degree of the driving and parking phenomenon for each sequence number. The synchronization degrees of the driving and parking phenomena of S sequences are summed and averaged to calculate the average synchronization degree of the driving and parking phenomenon. All synchronization degrees of the driving and parking phenomena are sorted in order of sequence number. The absolute difference between two adjacent synchronization degrees of the driving and parking phenomena after sorting is calculated to calculate the phenomenon synchronization swing degree. All phenomenon synchronization swing degrees are summed and averaged to calculate the average phenomenon synchronization swing degree. Based on the average synchronization degree of the driving and parking phenomena and the average phenomenon synchronization swing degree, the possible difficulty reference index of the parking log of this phenomenon difficulty is calculated.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] This invention's device combines four modules to perform surface analysis of the movement and parking conditions in each parking lane within a parking lot. Using neural network technology, it accurately identifies lanes with apparent parking difficulties, forming a proactive management chain of "data collection - intelligent analysis - immediate response." This ensures efficient response and precise control of current parking challenges. After determining that a parking lane does not have apparent parking difficulties, it identifies other lanes that may be affected based on the current apparent parking conditions. It performs a preliminary analysis of the apparent conditions of each lane, deeply exploring whether apparent parking difficulties might occur later, thus determining whether early intervention is needed. This shifts the management focus from passive response to proactive prevention. These two monitoring and management methods complement each other, forming a closed loop of intelligent parking management: "perception - response - foresight - optimization," improving parking lot traffic efficiency and resource utilization, and providing an efficient and intelligent parking management method. Attached Figure Description

[0028] Figure 1 This is a mind diagram illustrating the principle of the device of the present invention;

[0029] Figure 2 A flowchart for determining whether there are potential parking difficulties in the parking lane;

[0030] Figure 3 The flowchart shows how the range of the channel may affect the acquisition of the index. Detailed Implementation

[0031] Reference Figures 1 to 3 The IoT-driven parking management equipment includes a parking difficulty analysis module, a parking difficulty management module, a potential difficulty parking analysis module, and a potential difficulty parking management module.

[0032] The apparent difficulty parking analysis module periodically (the periodicity is set according to the actual operational needs and management sophistication of the parking lot) generates parking status logs for each parking lane within the parking lot. (A parking lane refers to the various passages, forks, etc. that a vehicle passes through when entering the parking lot from the entrance and heading towards a parking space, as well as when leaving the parking space and heading towards the exit.) The lane parking status log includes a lane number (used to distinguish different parking lanes, with each parking lane corresponding to a unique number) and a driving parking dataset (and uses IoT technology to upload the lane parking status logs to a network terminal) to further determine whether there are apparent difficulty parking situations in each parking lane.

[0033] The specific steps for generating the driving and parking data set of the lane parking status log are as follows: Periodically collect various driving and parking data for the parking driving lane within a cycle (driving data includes, but is not limited to, the following: lane flow data, average lane speed, and lane idling percentage; lane flow data is the number of vehicles passing through the parking driving lane within the cycle; average lane speed is the average speed of vehicles passing through the parking driving lane within the cycle; lane idling percentage is the proportion of vehicle idling time to total travel time; parking data includes, but is not limited to, the following: overflow vehicle data and parking space turnover rate; all parking data is collected from parking spaces next to the parking driving lane; overflow vehicle data is the number of vehicles overflowing to other lanes due to lack of parking spaces; parking space turnover rate is calculated by cross-lane flow difference; the ratio of the number of vehicles leaving parking spaces next to the parking driving lane within the cycle to the number of parking spaces next to the parking driving lane; all driving and parking data are collected based on corresponding sensors deployed in the parking lot). Integrate all driving and parking data into a driving and parking data set.

[0034] The specific steps for determining whether a parking lane has a seemingly difficult parking situation are as follows: Obtain the driving parking dataset of the corresponding lane parking status log, further import the driving parking dataset into the seemingly difficult parking model, derive the seemingly difficult parking index from the seemingly difficult parking model, set the seemingly difficult parking threshold index, and when the seemingly difficult parking index is higher than the seemingly difficult parking threshold index (the setting of the seemingly difficult parking threshold index is comprehensively set in combination with the training results of the seemingly difficult parking model, and if it is not higher, it indicates that there is no seemingly difficult parking situation), it is determined that there is a seemingly difficult parking situation in the driving parking lane.

[0035] The specific steps for constructing the apparent difficulty parking model are as follows: Collect a driving parking datasets (a≥1000, covering at least one month's time period), build a neural network model, and use the driving parking datasets as the basic data to train the built neural network model. During this process, each driving parking dataset is assigned an apparent difficulty parking index, with the value ranged from -10 to 10. The magnitude of the apparent difficulty parking index has a clear meaning; the larger the value, the more difficult it is to pass through the corresponding parking lane and the more difficult it is to park. Then, the multiple driving parking datasets are divided into training set, validation set, and test set according to a specific ratio of 70%:15%:15%. Stratified sampling is used to ensure that the DBV distribution of each subset is consistent. Calculate the cumulative distribution function (CDF) of the DBV of all samples. Use the training set to repeatedly train the deep learning model, and use the validation set to verify the performance of the training phase. Adjust the model parameters in a timely manner based on the validation results and optimize the model structure. Finally, the apparent difficulty parking model is completed.

[0036] The apparent difficulty parking management module, when it determines that there is apparent difficulty parking in the parking lane, marks the corresponding parking lane as an apparent difficulty parking lane and simultaneously generates an apparent difficulty parking log. The apparent difficulty parking log includes the lane number and the apparent difficulty parking time (the apparent difficulty parking time is the same as the time the apparent difficulty parking log is generated, and the apparent difficulty parking log is uploaded to the network terminal with the help of Internet of Things technology). The module also arranges parking management personnel to intervene in the apparent difficulty parking lane (such as guiding subsequent vehicles not to enter the apparent difficulty parking lane, diverting congested vehicles in the apparent difficulty parking lane to other locations, and arranging vehicles to park in the parking spaces next to the apparent difficulty parking lane as soon as possible, etc.).

[0037] The Potential Difficulty Parking Analysis module determines whether a potential difficulty parking situation exists in a parking lane if the apparent difficulty parking situation is not found in that lane.

[0038] The specific steps for determining whether a parking lane presents a potential difficulty level are as follows: Select a parking lane, obtain its independent potential difficulty reference index (TS(e)), obtain the apparent difficulty parking index, calculate the difference between the apparent difficulty parking threshold index and the apparent difficulty parking index, and label it as Ps(R, R). The parking probability analysis radius r(new) is calculated, where r is the system preset radius and v1 is the radius correction parameter. Both the system preset radius and the radius correction parameter are set based on the parking lot area and the dimensions and layout of each parking lane. A circle is drawn with the midpoint of the parking lane as the center and the parking probability analysis radius r(new) as the radius, obtaining the possible difficulty analysis range. All other parking lanes located within the possible difficulty analysis range (excluding the parking lane itself) are marked as range-affected lanes (if only part of a parking lane is within the possible difficulty analysis range, it is not marked as a range-affected lane). The value of each range-affected lane is then obtained. The range may affect the index. The total number of channels affected by the range is labeled L(tu). The range may affect indices of all channels are summed and averaged to calculate the average range may affect index, labeled A(ye). The possible difficulty parking index of the parking lane is calculated by = L(tu)*[TS(e)+A(ye)]. When the possible difficulty parking index of the parking lane is higher than the possible difficulty parking threshold index (the possible difficulty parking threshold index is dynamically set based on historical practice data. If it is not higher, it means that there is no possible difficulty parking situation and no further processing is required), it is determined that there is a possible difficulty parking situation in the parking lane.

[0039] The specific steps for obtaining the range influence index of a range influence channel are as follows: Select a range influence channel, obtain the independent possible difficulty reference index of the range influence channel (the method of obtaining the independent possible difficulty reference index of the parking and driving channel is the same), simultaneously obtain the apparent difficulty parking index of the range influence channel, sum the independent possible difficulty reference index and the apparent difficulty parking index, and calculate the range influence index of the range influence channel.

[0040] The specific steps for determining the midpoint of the parking lane are as follows: Obtain the latitude and longitude coordinates of the two endpoints of the parking lane from the parking lot's map data. Assuming the coordinates of the two endpoints are A(x1, y1) and B(x2, y2), calculate the coordinates of the midpoint M of the parking lane using the midpoint coordinate calculation formula. Among them, (x M y M () is the coordinate of the midpoint of the parking lane.

[0041] The specific steps for obtaining the independent possible difficulty reference index of the parking lane are as follows: obtain all the apparent difficulty parking logs generated in the parking lane before, obtain the possible difficulty reference index of each apparent difficulty parking log, sum and average the possible difficulty reference indices of all apparent difficulty parking logs, and calculate the independent possible difficulty reference index.

[0042] The specific steps for obtaining the potential difficulty reference index of the apparent difficulty parking log are as follows: Select an apparent difficulty parking log, determine the apparent difficulty parking time of the apparent difficulty parking log, obtain the S consecutive lane parking status logs generated before the apparent difficulty parking time of the parking lane, sort all lane parking status logs in the order of generation, and label them sequentially (numbered 1, 2, ..., S). Obtain the S consecutive lane parking status logs generated before the current time of the parking lane, sort all lane parking status logs in the order of generation, and label them sequentially (numbered 1, 2, ..., S). The sequence is then sequentially numbered (numbered 1, 2, ..., S), and the synchronization degree of the moving-stop phenomenon is obtained for each number. The synchronization degrees of the moving-stop phenomenon of the S numbers are summed and averaged to calculate the average moving-stop phenomenon synchronization degree, which is labeled as DCL(yl). All moving-stop phenomenon synchronization degrees are sorted in sequential order, and the absolute difference between two adjacent moving-stop phenomenon synchronization degrees is calculated to calculate the phenomenon synchronization sway degree. All phenomenon synchronization sway degrees are summed and averaged to calculate the average phenomenon synchronization sway degree, which is labeled as PMH(as). Calculate the possible difficulty reference index TS(e) for this apparent difficulty parking log.

[0043] The specific steps for obtaining the synchronization degree of the driving and stopping phenomenon for a given sequence number are as follows: Select two channel parking status logs with the same sequence number, vectorize the driving and stopping dataset of one of the channel parking status logs, and transform it into a vector A = (a1, a2, ..., a...). n Let n be the total number of items in the travel and parking data. The travel and parking dataset from the parking status log of another lane is vectorized and transformed into a vector B = (b1, b2, ..., b...). n ), Calculate the synchronization degree of the moving and stopping phenomenon for this sequence number.

[0044] The "Potential Difficulty Parking Management" module allows parking management personnel to intervene in advance when a parking lane presents a potential difficulty parking situation (e.g., by assigning parking management personnel to the parking lane in advance to guide parking).

[0045] The above-described parking management device of this invention combines four modules to perform superficial analysis of the movement and parking conditions in each parking lane within the parking lot. Using neural network technology, it accurately identifies lanes with apparent parking difficulties, forming a proactive management chain of "data collection - intelligent analysis - immediate response." This ensures efficient response and precise control to current parking challenges. After determining that no apparent parking difficulties exist in a given lane, it identifies other lanes that may be affected based on the current apparent parking conditions. It performs a preliminary analysis of the apparent conditions in each lane, deeply exploring whether apparent parking difficulties might arise later, thus determining whether early intervention is needed. This shifts the management focus from passive response to proactive prevention. The two monitoring and management methods complement each other, forming a closed loop of intelligent parking management: "perception - response - foresight - optimization," improving parking lot traffic efficiency and resource utilization, and providing an efficient and intelligent parking management method.

[0046] The above formulas are all dimensionless calculations, and the preset parameters in the formulas should be set by those skilled in the art according to the actual situation.

[0047] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0048] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0049] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0050] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0051] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0052] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An Internet of Things-driven parking management device, characterized in that, include The apparent difficulty parking analysis module periodically generates parking status logs for each parking lane in the parking lot to further determine whether there are apparent difficulty parking situations in each parking lane. The apparent difficulty parking management module determines that there is an apparent difficulty parking situation in the parking lane and directly puts the parking lane into management. The potential difficulty parking analysis module determines whether a potential difficulty parking situation exists in the parking lane if it is determined that there is no apparent difficulty parking situation in the parking lane. The specific steps for determining whether a parking lane presents a potential difficulty level are as follows: Select a parking lane, obtain its independent potential difficulty reference index (TS(e)), obtain the apparent difficulty parking index, calculate the difference between the apparent difficulty parking threshold index and the apparent difficulty parking index, and label it as Ps(R, R). The parking possibility analysis radius r(new) is calculated, where r is the system preset radius and v1 is the radius correction parameter. The system preset radius and the radius correction parameter are set according to the area of ​​the parking lot and the size and layout of each parking lane. A circle is drawn with the midpoint of the parking lane as the center and the parking possibility analysis radius r(new) as the radius to obtain the possible difficulty analysis range. The remaining parking lanes located within the possible difficulty analysis range are marked as range influence lanes. The range possible influence index of each range influence lane is obtained. The total number of range influence lanes is marked as L(tu). The range possible influence indices of all range influence lanes are summed and averaged to calculate the average range possible influence index, which is marked as A(ye). The possible difficulty parking index of the parking lane is calculated by L(tu)*[TS(e)+A(ye)]. When the possible difficulty parking index of the parking lane is higher than the possible difficulty parking threshold index, it is determined that the parking lane has a possible difficulty parking situation. The specific steps for obtaining the range influence index of a range influence channel are as follows: Select a range influence channel, obtain the independent possible difficulty reference index of the range influence channel, simultaneously obtain the apparent difficulty parking index of the range influence channel, sum the independent possible difficulty reference index and the apparent difficulty parking index, and calculate the range influence index of the range influence channel. The steps for obtaining the independent possible difficulty reference index of the parking lane are as follows: obtain all apparent difficulty parking logs generated in the parking lane before, obtain the possible difficulty reference index of each apparent difficulty parking log, sum and average the possible difficulty reference indices of all apparent difficulty parking logs, and calculate the independent possible difficulty reference index. The specific steps for obtaining the possible difficulty reference index of the apparent difficulty parking log are as follows: Select an apparent difficulty parking log, determine the apparent difficulty parking time of the apparent difficulty parking log, obtain the S consecutive channel parking status logs generated before the apparent difficulty parking time of the parking lane, sort all channel parking status logs in the order of generation, and label them sequentially. Obtain the S consecutive channel parking status logs generated before the current time of the parking lane, sort all channel parking status logs in the order of generation, and label them sequentially. Obtain the synchronization degree of the driving and parking phenomenon for each number, sum the synchronization degrees of the driving and parking phenomenon of the S numbers and take the average to calculate the average driving and parking phenomenon synchronization degree, and label it as DCL(yl). Sort all driving and parking phenomenon synchronization degrees in the order of sequence, calculate the absolute difference between two adjacent driving and parking phenomenon synchronization degrees after sorting, calculate the phenomenon synchronization swing degree, sum all phenomenon synchronization swing degrees and take the average to calculate the average phenomenon synchronization swing degree, and label it as PMH(as). Calculate the possible difficulty reference index TS(e) of the parking log that represents the apparent difficulty. The specific steps for obtaining the synchronization degree of the driving and stopping phenomenon for a given sequence number are as follows: Select two channel parking status logs with the same sequence number, vectorize the driving and stopping dataset of one of the channel parking status logs, and transform it into a vector A = (a1, a2, ..., a...). n Let n be the total number of items in the travel and parking data. The travel and parking dataset from the parking status log of another lane is vectorized and transformed into a vector B = (b1, b2, ..., b...). n ), Calculate the synchronization degree of the moving and stopping phenomena for this sequence number; The "Potential Difficulty Parking Management" module allows parking management personnel to intervene in advance when a parking lane presents a potential difficulty parking situation.

2. The IoT-driven parking management device according to claim 1, characterized in that, The lane parking status log includes the lane number and the moving parking dataset.

3. The IoT-driven parking management device according to claim 2, characterized in that, The specific steps for generating the driving and parking dataset of the lane parking status log are as follows: periodically collect various driving and parking data of the parking driving lane within a cycle, and integrate the various driving and parking data into a driving and parking dataset in the form of a set.

4. The IoT-driven parking management device according to claim 1, characterized in that, The specific steps for determining whether a parking lane has a seemingly difficult parking situation are as follows: Obtain the driving parking dataset of the corresponding lane parking status log, further import the driving parking dataset into the seemingly difficult parking model, derive the seemingly difficult parking index from the seemingly difficult parking model, set the seemingly difficult parking threshold index, and when the seemingly difficult parking index is higher than the seemingly difficult parking threshold index, it is determined that the parking lane has a seemingly difficult parking situation.

5. The IoT-driven parking management device according to claim 1, characterized in that, When a parking lane is determined to have apparent difficulty parking, the corresponding parking lane is marked as an apparent difficulty parking lane, and an apparent difficulty parking log is generated simultaneously for that lane. The apparent difficulty parking log includes the lane number, the apparent difficulty parking time, and parking management personnel are assigned to intervene in the management of the apparent difficulty parking lane.

Images