CN119131915A - Complex parking lot billing management system based on artificial intelligence - Google Patents
Complex parking lot billing management system based on artificial intelligence Download PDFInfo
- Publication number
- CN119131915A CN119131915A CN202411230447.8A CN202411230447A CN119131915A CN 119131915 A CN119131915 A CN 119131915A CN 202411230447 A CN202411230447 A CN 202411230447A CN 119131915 A CN119131915 A CN 119131915A
- Authority
- CN
- China
- Prior art keywords
- parking
- user
- time
- user behavior
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 15
- 230000008901 benefit Effects 0.000 claims abstract description 32
- 238000004458 analytical method Methods 0.000 claims abstract description 23
- 230000007306 turnover Effects 0.000 claims description 18
- 230000001932 seasonal effect Effects 0.000 claims description 12
- 238000011524 similarity measure Methods 0.000 claims description 10
- 238000000354 decomposition reaction Methods 0.000 claims description 9
- 238000012512 characterization method Methods 0.000 claims description 8
- 238000003491 array Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 2
- 230000006399 behavior Effects 0.000 description 58
- 230000008859 change Effects 0.000 description 15
- 239000000306 component Substances 0.000 description 8
- 238000000034 method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005358 geomagnetic field Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
- G07B15/00—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points
- G07B15/02—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points taking into account a variable factor such as distance or time, e.g. for passenger transport, parking systems or car rental systems
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
- G07B13/00—Taximeters
- G07B13/02—Details; Accessories
- G07B13/08—Tariff-changing arrangements
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明涉及停车管理技术领域，具体的是基于人工智能的停车场复杂计费管理系统，包括：数据采集模块，用于采集用户的停车数据，停车数据包括每个用户的车辆进入和离开的时间、车辆类型和停车位的位置；行为识别模块，用于根据用户的停车数据，生成每个用户对应的用户行为画像；画像分析模块，用于对用户行为画像进行分析，确定用户行为画像对应的停车策略组合，根据得到的停车策略组合，确定用户在不同行为决策下的差异化收益和差异化收益下的时序特征；实现了停车场计费管理的智能化和精细化。
The present invention relates to the technical field of parking management, and specifically to a complex parking lot billing management system based on artificial intelligence, comprising: a data acquisition module, used to collect parking data of users, the parking data including the time of vehicle entry and exit, vehicle type and parking space location of each user; a behavior recognition module, used to generate a user behavior portrait corresponding to each user according to the parking data of the user; a portrait analysis module, used to analyze the user behavior portrait, determine the parking strategy combination corresponding to the user behavior portrait, and determine the differentiated benefits of the user under different behavior decisions and the time series characteristics under the differentiated benefits according to the obtained parking strategy combination; the intelligent and refined parking lot billing management is realized.
Description
Technical Field
The invention relates to the technical field of parking management, in particular to a parking lot complex charging management system based on artificial intelligence.
Background
The important reasons for the urban parking problem are insufficient supply of parking space resources and difficult allocation of parking space resources. In particular, in the latter case, in urban hot spot areas, the parking space supply is relatively fixed, but the parking space demand is very tidal and unplanned, which presents a great challenge for the setting, management and operation of the parking lot.
As disclosed in China patent publication No. CN113808287A, a method and a system for managing regional timing and charging of a parking lot are disclosed, and the method comprises the following steps of S1, drawing a user inherent portrait of a target user, S2, drawing a user demand portrait of the target user, S3, creating a user parking portrait by fusing the user inherent portrait and the user demand portrait, and making special parking service for the target user based on the target parking portrait.
In the prior art, the user demand image and the user inherent image are set to create the user parking image so as to identify the characteristics of different areas when the user parks, so that the current parking can be managed, but when the characteristics are determined, the corresponding change of the parking lot corresponding to the user when the user parks and the corresponding differentiation of each parking space are also required to be determined, for example, when differentiated charge management is carried out in the parking lot, the parking spaces cannot be matched with the related conditions of the current parking lot only through the weight of the user parking image, and meanwhile, dynamic adjustment is required to be carried out so as to avoid the wrong allocation of the parking spaces caused by the different parking lots or image settings.
Disclosure of Invention
In order to solve the technical problems, the technical scheme adopted by the invention is that the parking lot complex charging management system based on artificial intelligence comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring parking data of users, and the parking data comprises time for entering and leaving vehicles of each user, vehicle types and positions of parking spaces.
And the behavior recognition module is used for generating user behavior portraits corresponding to each user according to the parking data of the user.
The portrait analysis module is used for analyzing the user behavior portraits, determining parking strategy combinations corresponding to the user behavior portraits, and determining differentiated benefits of the user under different behavior decisions and time sequence characteristics under the differentiated benefits according to the obtained parking strategy combinations.
The regional analysis module is used for determining the parking requirement, turnover region and corresponding parking constraint condition of each time sequence according to the acquired time sequence characteristics, and determining the parking strategy selected by a user when parking according to the set parking constraint condition.
And the parking adjustment module is used for determining the selected parking strategy and the similarity measure of the user behavior portraits when the user parks, and adjusting the user guidance according to the difference between the combination of the parking strategy and the similarity measure of the user behavior portraits when the user parks.
The invention has the beneficial effects that firstly, the system can dynamically adjust the charging strategy according to the parking behavior and preference of the user through the behavior recognition module and the user portrait analysis, and a personalized charging scheme is provided, thereby improving the flexibility of charging and the satisfaction degree of the user.
2. The regional analysis module provided by the invention can intelligently allocate parking resources according to the parking requirements of different time sequences and the constraint conditions of the turnover region, effectively relieve the problem of parking lot congestion and improve the parking efficiency.
3. According to the method and the device, the differentiated benefits of the user under different action decisions are calculated, and the vehicle guidance is adjusted according to the benefit weight, so that the fine management of the benefits of the parking lot is realized, and the operation benefits of the parking lot are improved.
4. According to the intelligent parking strategy adjustment and user guidance, the system can provide more convenient and efficient parking experience for the user, and the time and cost for the user to find a parking space are reduced.
Drawings
The invention will be further described with reference to the drawings and examples.
Fig. 1 is a system schematic diagram of an artificial intelligence based parking lot complex billing management system.
FIG. 2 is a schematic diagram of the structure of a user behavior portrayal of an artificial intelligence based parking complex billing management system.
Fig. 3 is a schematic structural diagram of an area analysis module of the parking lot complex billing management system based on artificial intelligence.
Detailed Description
Embodiments of the present invention are described in detail below. The following examples are illustrative only and are not to be construed as limiting the invention. The examples are not to be construed as limiting the specific techniques or conditions described in the literature in this field or as per the specifications of the product.
The system comprises a data acquisition module, a behavior recognition module, a portrait analysis module, a regional analysis module and a parking adjustment module, wherein the data acquisition module sends acquired data to the behavior recognition module, the behavior recognition module outputs the data to the portrait analysis module and the regional analysis module after producing related user behavior portraits, the portrait analysis module is used for determining the preference of the current user behavior and the differential benefit of the current adopted strategy combination, the regional analysis module determines the related requirements and the corresponding changes of the parking lot when the current parking is performed, the constraint conditions of the parking are determined, the output results of the portrait analysis module and the regional analysis module are input to the parking adjustment module, and the parking adjustment module finally realizes the adjustment of the parking.
The data acquisition module is used for acquiring parking data of users, wherein the parking data comprises the time of entering and exiting of vehicles of each user, the types of the vehicles and the positions of parking spaces.
And the behavior recognition module is used for generating user behavior portraits corresponding to each user according to the parking data of the user.
The portrait analysis module is used for analyzing the user behavior portraits, determining parking strategy combinations corresponding to the user behavior portraits, and determining differentiated benefits of the user under different behavior decisions and time sequence characteristics under the differentiated benefits according to the obtained parking strategy combinations.
The regional analysis module is used for determining the parking requirement, turnover region and corresponding parking constraint condition of each time sequence according to the acquired time sequence characteristics, and determining the parking strategy selected by a user when parking according to the set parking constraint condition.
And the parking adjustment module is used for determining the selected parking strategy and the similarity measure of the user behavior portraits when the user parks, and adjusting the user guidance according to the difference between the combination of the parking strategy and the similarity measure of the user behavior portraits when the user parks.
The method comprises the steps of determining the requirement of a user at the moment through parking data, determining the behavior mode of the user for parking under the behavior portrait of the user, determining the behavior of the user in a peak period and preferring parking spaces, so as to obtain time preference and position preference of the user during parking, finding a parking strategy corresponding to the preference according to the preference, and carrying out differentiation analysis from the parking strategy to obtain the parking mode most relevant to the current parking lot setting, so that guiding of the user for parking is realized.
In order to determine the accuracy of the current collected data, the situation of the vehicle parking in the current parking lot is determined by arranging equipment such as a high-order camera, a low-order camera, a geomagnetic sensor, a curb camera, a patrol car and the like in the parking lot, and the utilization conditions of the vehicle, the turnover rate, each parking space and the like in the parking lot are judged according to the obtained data.
The high-level camera can provide a wider view field and is suitable for monitoring a plurality of parking spaces, the low-level camera can provide more detailed vehicle information such as license plate numbers and the like, the geomagnetic sensor is a core component of the geomagnetic sensing parking charging system and is arranged above the parking spaces and used for detecting the entrance and exit of vehicles by sensing geomagnetic field changes on underground parking spaces, when the vehicles are parked in or leave the parking spaces, the geomagnetic sensor can accurately sense and transmit signals to the data processor for recording and charging, the curb camera is equipment arranged beside the parking spaces and used for identifying the vehicle entrance and the license plate information, vehicle detection and license plate identification can be achieved, license plate-free vehicle detection is supported, the patrol vehicle is usually driven by a parking lot manager, a parking lot is regularly patrol to monitor the use condition of the parking spaces, the patrol vehicle is possibly provided with the camera and the sensor and used for detecting and recording the state of the parking spaces in real time, and the manager can timely find and process illegal parking and occupy a plurality of parking spaces through the patrol vehicle.
The generation mode of the user behavior portraits comprises the steps of determining the time preference, the position preference, the parking duration preference and the parking cost preference of the user when the user parks according to the acquired parking data, and generating the user behavior portraits based on the time preference and the position preference of the user when the user parks.
The time preference is expressed as acquiring the number of times the user parks and the duration of the parking, and determining the time preference of the user parks, wherein the time preference of the user parks comprises a day time preference, a Zhou Shiduan preference and a long-term preference.
The daily time interval preference is expressed by counting the parking times and time periods of a user in different time periods, determining the parking demand difference of the user in different time periods, calculating the parking time ratio and the parking time ratio of each time period, obtaining the parking demand difference of the user in different time periods, and taking the average value of the parking demand difference of the user in different time periods as the daily time interval preference of the current output.
The method comprises the steps of calculating the parking times and the parking time of each day type according to the working day, the rest day, the holiday and the corresponding specific time, and calculating the parking time ratio and the parking time ratio of each day type to determine the parking demand difference of the user on different dates.
And determining the change rate of the parking times and the parking time in each period by combining the daily period preference and the Zhou Shiduan preference according to the set period, and taking the moving average value of the parking times and the parking time in the adjacent period as the change amount of the parking demand difference of the current user in the continuous period.
In order to enable the currently set period to cope with more scenes, when the preset period is set, the behavior change rate of the user behavior index in the current period and the user behavior index in the last period is calculated, the user behavior index represents the average value of corresponding data in a user behavior portrait, the behavior change rate is obtained by calculating the difference value of the user behavior index in the current period and the user behavior index in the last period and calculating the ratio of the difference value to the user behavior index in the last period, at the moment, the behavior change of a user in different periods can be reflected, when the obtained behavior change exceeds the preset change amount threshold, the circumference is shortened to half, and when the three continuous periods are lower than half of the preset change amount threshold, the period is prolonged by one time, and the period of currently detecting the user behavior is adjusted.
And acquiring the parking space of the user when the user parks according to the parking position preference, determining the regional characteristics of the parking space in the parking lot, wherein the regional characteristics comprise the distance characteristics of the current parking space and the entrance, the exit and the elevator hoistway of the parking lot and the convenience characteristics corresponding to the current parking space, and acquiring the position preference according to the regional characteristics of the parking lot.
The calculation mode of the distance features is that the distances between the current parking space and the entrance, the exit and the elevator entrance of the parking lot are subjected to standardized processing, and the weighted sum of the standardized processed distance values is used as the output distance feature: Where D represents the normalized distance of the current parking space, D represents the distance of the current parking space to the entrance, exit or elevator hoistway of the parking space, D max represents the maximum distance of the current parking space to the entrance, exit and elevator hoistway of the parking space, and D min represents the minimum distance of the current parking space to the entrance, exit and elevator hoistway of the parking space.
The minimum distance refers to the shortest travel distance from this parking space that can reach the entrance, exit or elevator hoistway directly or through the shortest path, the maximum distance refers to the longest travel distance from this parking space that can reach all possible paths of the entrance, exit or elevator hoistway, this does not mean that a far-around path is taken, but means that the layout within the parking lot is such that some critical locations are naturally farther relative to the parking space, assuming that a parking space is located on one side of the parking lot and that the parking lot has two exits, one on the same side but closer and the other on the opposite side and farther. In this case, the distance from the parking spot to the closer exit will be the minimum distance to the exit and the distance to the opposite exit will be the maximum distance.
The distance characteristic obtained at the moment can represent the relative position of the current vehicle relative to the corresponding outlet, the corresponding inlet and the elevator hoistway, so that the position condition corresponding to the current user can be conveniently determined.
The set convenience characteristic is used for determining whether the parking space of the current user is convenient to drive out or not, when the ratio of the size of the parking space to the surrounding space is smaller, the current parking space distribution is crowded, congestion events are easy to occur, vehicles with larger vehicle types are inconvenient to park, and when the ratio of the size of the parking space to the surrounding space is larger, the parking space is convenient to pass, and vehicles with larger size are also convenient to park.
The parking duration preference indicates the average time of the parking duration of the user when parking and the corresponding parking type when parking each time, wherein the parking types are short-parking, medium-parking, long-parking and the like, so as to determine the parking time of the user when parking.
The charging type comprises time charging, month/season/year charging, time-sharing charging, step charging, membership charging and dynamic charging to determine the mode of preference of the user for settlement of the corresponding fee.
The fee is calculated according to the parking time, and the common way is to charge according to minutes, hours or days.
And charging according to the time, namely charging a fixed fee every time the vehicle enters the parking lot no matter how long the vehicle is parked.
And charging in the month of Baozhen/season/year, wherein the user can choose to purchase infinite parking service within a certain period of time, and the method is suitable for users who frequently park in the same place.
Time-sharing charging, namely charging different fees according to different time periods (such as peak time and peaked time) in one day.
Stepwise charging, namely lower charging in the first hours and gradually increasing the charging along with the time extension.
Membership charging-enjoying discounts or other additional services by purchasing membership.
Dynamic charging, namely, the charging standard is adjusted according to the real-time occupancy rate of the parking lot, the cost is increased when the parking space is tense, and the cost is reduced when the parking space is abundant.
The final obtained user behavior portraits are the values of corresponding data of time preference, position preference, parking duration preference and parking cost preference and the corresponding average value to determine the main behaviors of the current user when the user parks.
The parking habit of the user is analyzed in detail, key information such as when, where, how long the user is parked, how much the user is willing to pay and the like can be accurately known, a basis is provided for personalized service, based on the user behavior portrait, the parking lot can more effectively allocate resources, such as manual guidance in a peak period or additionally arrange parking spaces in a preferred area of the user, customer satisfaction degree and parking lot operation efficiency are improved, the user behavior portrait can be used as an important input of an intelligent parking system, development of a more intelligent parking recommendation, reservation and navigation system is facilitated, and user experience is improved.
The processing mode for analyzing the user behavior portraits comprises the steps of determining inherent characteristics existing in the current area and time sequence characteristics of the current area under time sequence according to the user behavior portraits, and screening the corresponding parking strategy combination from a parking strategy library based on the acquired time sequence characteristics and the inherent characteristics.
The combination of parking strategies is represented as a set of parking strategies associated with the current user behavior representation, at least two parking strategies, the inherent features of the user are represented as general features analyzed from the user behavior representation, and the temporal features are represented as features that may occur over a particular period of time.
The intrinsic feature and the time series feature are obtained by inputting the user behavior representation into the time series decomposition model, using the random component identified in the time series decomposition model as the intrinsic feature, and using the trend component and the seasonal component identified in the time series decomposition model as the time series feature.
The implementation of the time series decomposition model is as follows.
Wherein Y t represents an index value of the observed user behavior representation at a time point T, T t represents an index value of the trend component at a time point T, T t-1 represents an index value of the trend component at a time point T-1, S t represents an index value of the seasonal component at a time point T, R t represents an index value of the random component at a time point T, T represents the number of time points, k represents the size of the time window, Y i represents an index value of the user behavior representation at an i-th time point in the time window, α represents a smoothing coefficient, m represents the number of time points of the seasonal period, Y j represents an index value of the user behavior representation at a j-th time point in the seasonal period, T j represents a value of the trend component at a j-th time point in the seasonal period, i=t+1, T-k+2, T, j=1, 2, m, and the currently set seasonal period belongs to a set corresponding to the set of the set time point T.
At this time, the user behavior portraits are decomposed to obtain the inherent characteristics and the time sequence characteristics, and the inherent characteristics and the time sequence characteristics are compared with a parking policy library according to the time preferred by the user to obtain the parking policy combination.
The identification of the intrinsic characteristic at this time may be expressed as basic information of the sex, age, occupation, etc. of the user, long-term parking preference of the user, such as preference of an indoor parking lot or an outdoor parking lot, average parking duration of the user, which may be relatively stable for different periods of time, and the intrinsic characteristic at this time does not change significantly with time.
The time sequence characteristic can be expressed as that the parking times of the user on the working day gradually increase and the parking times of the user on the weekend gradually decrease, and the parking behavior of the user can be changed remarkably during the specific holiday of each year, such as the increase of the parking times or the extension of the parking time length, at the moment, the time sequence characteristic is easy to be influenced by time, and corresponding trend changes can occur at different times, so that the time sequence characteristic can be identified by a time sequence decomposition model.
The implementation mode of screening the obtained time sequence features and the obtained inherent features from the parking strategy library to obtain the corresponding parking strategy combination is represented by calculating cosine similarity of the inherent features and the time sequence features with the parking strategy library and taking the scheme with the maximum similarity as the output parking strategy combination, wherein the selected parking strategy combination comprises the parking strategy with the maximum cosine similarity with the currently set time sequence features, the parking strategy with the maximum cosine similarity with the inherent features and the parking strategy with the maximum cosine similarity product value with the time sequence features and the inherent features, so that verification of whether each set parking strategy can maximize the final parking income is facilitated.
The implementation mode of determining the differentiated benefits of the user under different behavior decisions is represented by determining the change value of the parking stall benefits under the currently set parking policy combination, marking the parking policy combination capable of generating the benefits change at the moment, recording the time sequence characteristics of generating the differentiated benefits, and taking the identified content as the output result of the portrait analysis module.
Specifically, charging information of a current user is obtained, whether the current charging information is matched with preset charging information is judged, parking fees of vehicles in a parking lot are verified according to set charging standards, the charging information is divided into a plurality of target arrays according to different parking fees, data of the target arrays are ordered according to a sequence from big to small, different charging information in the target arrays and the preset charging information is extracted, parking strategies corresponding to the extracted charging information are combined and output, and the parking strategies are used as differentiated benefits of the user under different behavior decisions.
The charging information obtained at this time is used for indicating whether the current user has historical data in the parking lot and the charging type corresponding to the current user so as to obtain the charging condition related to the user, the charging information is modified and adjusted based on the corresponding condition in the historical data, and the user can complete the guiding control of the user according to different benefits in the parking lot according to the obtained differentiated benefits and the subsequent calculation mode of the user benefits.
For example, when the parking strategies A and B exist at the moment, the parking strategies A are used to approach the exit when the seasonal parking peak is processed, or the benefits of the parking spaces of the set members and the benefits of the circulation of the parking spaces are increased, but the benefits generated by the parking strategies B are different from the benefits generated by the parking strategies A, the parking strategies are selected at the moment, the time sequence characteristics of the parking strategies at the moment are determined, the time sequence characteristics are the time sequence characteristics recognized in the user portraits, and meanwhile, whether the time sequence characteristics correspond to the corresponding trend changes of the parking spaces in the relevant areas or not is compared, so that the parking strategies which are seriously adopted in the reverse aspect have certain limiting conditions, the parking strategies are adjusted according to the limiting conditions, the scheme which is the most accordant with the benefits of the current parking strategies can be obtained, the overall benefits are adjusted, and at the moment, the system can intelligently allocate the parking resources according to the parking requirements of different time sequences and the constraint conditions of the turnover areas, so that the congestion problem of the parking lot is effectively relieved, and the parking efficiency is improved.
The specific implementation mode of the area analysis module comprises the steps of firstly determining parking requirements under different time sequences according to the acquired time sequence characteristics, wherein the parking requirements set at the moment are expressed as the number of parking spaces required in a specific time period and the relative parking areas.
Then, according to the geographic position of the parking lot and the number of vehicles, the parking lot is divided into different turnover areas, and each turnover area is responsible for meeting the parking requirements in a certain range, so that the vehicles can enter and exit the parking lot quickly.
According to the turnover areas and the parking requirements, parking constraint conditions existing in each turnover area are determined.
Finally, the parking strategy with the maximum cosine similarity with the parking constraint condition is selected as the parking strategy selected by the user when the user parks, so that the analysis of the parking area is realized.
For the aspects of capacity limitation, demand change in different time periods, vehicle type, charging standard and payment mode, environmental protection requirement, user satisfaction degree and convenience of the parking lot, for example, the parking lot A is always full in the peak period of the working day, the parking lot B has higher empty space rate during the weekend, at the moment, it is indicated that the parking lot has certain conditions in different time periods, and then the selected parking strategy needs to be corresponding to the corresponding conditions, so that the final parking strategy can meet the parking requirement of the current parking lot.
The parking constraint conditions in each turnover area can be determined according to the average parking time of each turnover area, the turnover area is divided into a first type area, a second type area, a third type area and a fourth type area, vehicles in the first type area have complete access data and charging information, vehicles in the second type area have entry data but no exit data and corresponding charging information, vehicles in the third type area have exit data and charging information but no entry data, and vehicles in the fourth type area have no data of a related parking lot, and the parking constraint conditions are determined according to the types corresponding to the turnover area.
The first type of area is a normal parking area, which is usually located in the core area of the parking lot for easy management and monitoring, the design and management of these areas pay attention to efficiency and convenience to ensure that vehicles can get in and out smoothly, the second type of area is a parking area to be verified, which may be located in a deeper or less conspicuous position of the parking lot to reduce the influence on normal operation, these areas may be provided with special identification or monitoring measures, the third type of area is a temporary parking area, which may be located near the entrance of the parking lot or in a position easy to monitor, these areas may be provided with temporary parking marks, and the fourth type of area is an unregistered vehicle area, which may be located at the edge or hidden position of the parking lot, and these areas may be provided with isolation measures to prevent unauthorized vehicles from getting in randomly.
According to the recognized vehicle-related data, the corresponding area where the vehicle is parked is divided into four areas according to the matching condition of the vehicle-related information, and different supervision measures are adopted for the four areas to manage the controlled parking.
The average parking time of the first type of area is obtained by comparing the average value of the vehicle entrance and exit time, the parking spaces in the first type of area are ordered according to the vehicle parking time of each parking space, the average parking time is obtained for the second type of area by patrol time of the second type of area and recorded entrance time, patrol is carried out on the related area according to the average parking time, the average parking time in the third type of area is calculated according to the charging record, and the average parking time of the corresponding vehicle is determined for the fourth type of area by interval time of patrol each time.
And sequentially generating corresponding parking constraint conditions according to the four category areas set in the turnover area, and determining a corresponding parking strategy according to the generated parking constraint conditions.
In this case, the related parking constraint conditions are selected in four set areas, firstly, the type of the area is searched from a preset condition library, the searched data are divided according to the average parking time at the moment, each divided data is identified with the parking space and the position of the current actual parking space, the parking constraint condition corresponding to the parking space is selected, for example, the parking space is provided with a parking duration or a vehicle type limit and a related cost limit, then the parking strategy needs to be matched with the parking constraint condition, and the parking strategy which currently accords with the set condition in the parking lot is determined to finish the guiding of the user vehicle.
And in the parking adjustment module, the similarity measurement of the parking strategy and the user behavior portraits is obtained by calculating the pearson correlation coefficient of the parking strategy and the user behavior portraits, and the calculated pearson correlation coefficient is used as the similarity measurement.
The following is a way of adjusting the user guidance according to the difference between the combination of parking strategies and the similarity measure of the user behavior portraits when the user parks.
When the verification needs to be charged, the circulation exchange rate of each parking space in the fixed time and the characterization income existing on the premise of the circulation exchange rate are verified.
According to the different characterizations of the gains, the gain loss and gain trend of each parking space in different time are calculated, the gain weight of each parking space is calculated according to the gain loss and gain trend, and the guidance of the vehicle is adjusted according to the gain weight of each parking space.
The circulation exchange rate refers to the number of times that one parking space is used by different users in a fixed time, and the higher the circulation exchange rate is, the higher the utilization rate of the parking space is.
The characterization profit refers to the sum of the profit generated by each parking space in a fixed time, and the characterization profit is expressed as the product of the circulation exchange rate, the average parking time and the parking cost.
The profit loss refers to a decrease in profit due to a change in the circulation rate if the user chooses to stop at different time periods, and is expressed as a change value representing the profit generated when the circulation rate is changed.
The benefit trend refers to the ratio of the characterization benefit of the current parking spot to the highest characterization benefit over a different period of time.
And the gain weight is obtained by subtracting the gain loss from the set standard value and multiplying the gain trend after the gain loss and the gain trend are normalized, and the set standard value is divided by the total time according to the current parking space using time.
According to the calculated gain weight, a vehicle guiding strategy can be adjusted, a user is preferentially guided to a parking space with higher gain weight, so that overall gain of a parking lot is improved, at the moment, the parking space with the highest gain weight in parking measurement is selected as the current vehicle-guided parking space, and the system achieves fine management of the gain of the parking lot by calculating differentiated gain of the user under different action decisions and adjusting the vehicle guiding according to the gain weight, so that the operation benefit of the parking lot is improved.
While embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention, which is also intended to be covered by the present invention.
Claims (10)
1. Parking area complex billing management system based on artificial intelligence, its characterized in that includes:
the data acquisition module is used for acquiring parking data of users, wherein the parking data comprises the time of entering and leaving of vehicles of each user, the types of the vehicles and the positions of parking spaces;
The behavior recognition module is used for generating a user behavior portrait corresponding to each user according to the parking data of the user;
the portrait analysis module is used for analyzing the user behavior portraits, determining parking strategy combinations corresponding to the user behavior portraits, and determining differentiated benefits of the user under different behavior decisions and time sequence characteristics under the differentiated benefits according to the obtained parking strategy combinations;
The regional analysis module is used for determining the parking requirement, turnover region and corresponding parking constraint condition of each time sequence according to the acquired time sequence characteristics;
And the parking adjustment module is used for determining the selected parking strategy and the similarity measure of the user behavior portraits when the user parks, and adjusting the user guidance according to the difference between the combination of the parking strategy and the similarity measure of the user behavior portraits when the user parks.
2. The complex billing management system of claim 1 wherein the means for generating a representation of user behavior comprises determining a time preference, a location preference, a duration preference, and a cost preference for parking of the user based on the obtained parking data, and generating a representation of user behavior based on the time preference and the location preference for parking of the user.
3. The complex billing management system for the parking lot based on the artificial intelligence according to claim 1, wherein the processing mode for analyzing the user behavior representation comprises determining the inherent characteristics existing in the current area and the time sequence characteristics of the current area under the time sequence according to the user behavior representation, and screening the corresponding parking policy combination from the parking policy library based on the acquired time sequence characteristics and the inherent characteristics.
4. The complex billing management system for parking lots based on artificial intelligence according to claim 3, wherein the intrinsic characteristics and the time series characteristics are obtained by inputting a user behavior representation into a time series decomposition model, using a random component identified in the time series decomposition model as the intrinsic characteristics, and using a trend component and a seasonal component identified in the time series decomposition model as the time series characteristics;
The implementation of the time series decomposition model is as follows:
Yt＝Tt+St+Rt;
Tt＝αYt+(1-α)Tt-1;
Wherein Y t represents an index value of the observed user behavior representation at a time point T, T t represents an index value of the trend component at a time point T, T t-1 represents an index value of the trend component at a time point T-1, S t represents an index value of the seasonal component at a time point T, R t represents an index value of the random component at a time point T, T represents the number of time points, k represents the size of the time window, Y i represents an index value of the user behavior representation at an i-th time point in the time window, α represents a smoothing coefficient, m represents the number of time points of the seasonal period, Y j represents an index value of the user behavior representation at a j-th time point in the seasonal period, T j represents a value of the trend component at a j-th time point in the seasonal period, i=t+1, T-k+2, T, j=1, 2, m.
5. The complex billing management system for parking lots based on artificial intelligence according to claim 3, wherein the implementation manner of screening the parking policy library based on the acquired time sequence features and the inherent features to obtain the corresponding parking policy combination is represented by calculating cosine similarity of each inherent feature and the time sequence features to the parking policy library, and taking the scheme with the maximum similarity as the output parking policy combination, wherein the selected parking policy combination comprises a parking policy with the maximum cosine similarity to the currently set time sequence features, a parking policy with the maximum cosine similarity to the inherent features, and a parking policy with the maximum cosine similarity product value to the time sequence features and the inherent features.
6. The complex billing management system of parking lot based on artificial intelligence according to claim 1, wherein the implementation manner of determining differentiated profits of users under different behavior decisions is represented by acquiring charging information of current users, judging whether the current charging information is matched with preset charging information, verifying parking fees of vehicles in the parking lot according to set charging standards, dividing the charging information into a plurality of target arrays according to different parking fees, sorting data of the target arrays according to the order from large to small, extracting different charging information in the target arrays and the preset charging information, and outputting parking policy combinations corresponding to the extracted charging information as differentiated profits of users under different behavior decisions.
7. The complex charging management system for the parking lot based on the artificial intelligence according to claim 1, wherein the specific implementation mode of the regional analysis module comprises the steps of firstly determining parking requirements under different time sequences according to acquired time sequence characteristics, dividing the parking lot into different turnover areas according to geographic positions of the parking lot and the number of vehicles, determining parking constraint conditions existing in each turnover area according to the turnover areas and the parking requirements, and selecting a parking strategy with the maximum cosine similarity with the parking constraint conditions as a parking strategy selected when a user parks.
8. The complex billing management system for parking lots based on artificial intelligence according to claim 7, wherein the parking constraints existing in each turn-around area can be determined according to the average parking time of each turn-around area, the turn-around area is divided into a first type area, a second type area, a third type area and a fourth type area, the vehicles in the first type area are the complete in-out data and billing information, the vehicles in the second type area are the entry data, but not the exit data and corresponding billing information, the vehicles in the third type area are the exit data and billing information, but not the entry data, and the vehicles in the fourth type area are the data of the related parking lot, and the parking constraints are determined according to the type corresponding to the turn-around area.
9. The complex billing management system of claim 1 wherein the user guidance is adjusted according to the combination of parking strategies and similarity measure of user behavior portraits when the user parks in the following manner:
Verifying the circulation exchange rate of each parking space in a fixed time and the characterization benefits existing on the premise of the circulation exchange rate when the charging is required;
According to the different characterizations of the gains, the gain loss and gain trend of each parking space in different time are calculated, the gain weight of each parking space is calculated according to the gain loss and gain trend, and the guidance of the vehicle is adjusted according to the gain weight of each parking space.
10. The complex billing management system of claim 1 wherein the similarity measure of the parking policy and the user behavior representation in the parking adjustment module is determined by calculating pearson correlation coefficients of the parking policy and the user behavior representation using the calculated pearson correlation coefficients as the similarity measure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411230447.8A CN119131915A (en) | 2024-09-04 | 2024-09-04 | Complex parking lot billing management system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411230447.8A CN119131915A (en) | 2024-09-04 | 2024-09-04 | Complex parking lot billing management system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119131915A true CN119131915A (en) | 2024-12-13 |
Family
ID=93753097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411230447.8A Pending CN119131915A (en) | 2024-09-04 | 2024-09-04 | Complex parking lot billing management system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119131915A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119741766A (en) * | 2025-03-04 | 2025-04-01 | 陕西华贝金服网络科技有限公司 | Regional timing charging method and system for intelligent parking lot |
-
2024
- 2024-09-04 CN CN202411230447.8A patent/CN119131915A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119741766A (en) * | 2025-03-04 | 2025-04-01 | 陕西华贝金服网络科技有限公司 | Regional timing charging method and system for intelligent parking lot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109416879B (en) | Parking position grading dynamic pricing method with priority short parking | |
| CN109191898B (en) | Online intelligent parking system | |
| US7312722B2 (en) | System and method for assessing parking space occupancy and for reserving same | |
| CN119131915A (en) | Complex parking lot billing management system based on artificial intelligence | |
| CN111613085A (en) | Parking lot management system based on big data | |
| CN113380071B (en) | Parking space level parking demand state evaluation method for large complex | |
| CN118314728A (en) | Traffic flow dynamic prediction and precision optimization method based on independent thermal coding | |
| CN110555917A (en) | Differentiated charging method for parking lot based on RFID technology | |
| CN106934470A (en) | Parking service method and its service system | |
| CN111798357A (en) | Full-city intelligent parking integrated service SaaS management system | |
| CN118740911B (en) | Intelligent parking cloud service system and method | |
| CN111785073A (en) | A parking lot guidance system based on human factors | |
| CN117576943A (en) | Intelligent analysis management system for vehicle information of parking lot | |
| CN118246597A (en) | Parking space idle period prediction system for new energy charging station | |
| CN114387816B (en) | Mall traffic guiding system and method based on consumer behavior prediction analysis | |
| Assemi et al. | On-street parking occupancy inference based on payment transactions | |
| CN118334900A (en) | Intelligent cloud parking management method and management platform for digital twins | |
| CN118486186A (en) | Big data management method for intelligent parking | |
| CN118609411A (en) | An intelligent toll collection and optimization road parking robot system | |
| CN112116124B (en) | Auditing method of bus network optimization scheme based on traveler visual angle | |
| CN113380070A (en) | Space-time characteristic acquisition method for parking space level parking demand of large complex | |
| CN118645007A (en) | A parking space prediction management system based on big data | |
| CN119227911A (en) | A tourism management optimization method and system based on tourist behavior analysis | |
| CN117173899B (en) | A smart city transportation quality evaluation method | |
| CN119091518A (en) | A comprehensive management background operation and maintenance system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |