Method and system for generating recommendations for parking spaces

Abstract

The present invention relates to a method for generating recommendations for parking spaces (1) of a parking space facility (2) having a plurality of parking spaces (1). From determined and forecast occupation statuses of the parking spaces (1), a determination device (5) determines an overall current occupation status of the parking spaces (1) in addition to the respective positions of the parking spaces (1) within the parking space facility (2), from which a recommendation device (6) creates the recommendation for parking spaces (1). The invention also relates to a system (9) for generating recommendations for parking spaces (1) of a parking space facility (2) having a plurality of parking spaces (1).

Description

[0001] Description

[0002] Method and system for generating parking space recommendations

[0003] The present invention relates to a method for generating parking space recommendations for a parking facility with a plurality of parking spaces. Furthermore, the invention relates to a system for generating parking space recommendations for a parking facility with a plurality of parking spaces.

[0004] High-traffic parking spaces, such as shopping center parking lots or inner-city parking garages, place particularly high demands on the search for a free parking space, especially as parking space occupancy increases. Since deterministic information about the parking space distribution within the parking area is typically lacking, driving directly to a free parking space is generally not possible, so the search for a free parking space can sometimes be very time-consuming.

[0005] If parking information on available parking spaces is not available, those looking for a parking space are usually left with no choice but to use a random search strategy. The goal is usually to find a free parking space in the immediate vicinity of a "point of interest (pole)", such as the entrance to a department store or one of the parking garage exits. To do this, the parking area is generally driven continuously at a moderate speed and turns more or less randomly at aisle intersections so that the distance to one of the poles remains within the individual acceptance limits. During the search, the individual acceptance limits are almost always increased gradually as the search duration increases, initially up to an individual "point of return (PoR)", before reorienting towards the vicinity of one of the poles and continuing the search from there.

[0006] The resulting, high time expenditure can be reduced by implementing a parking space infrastructure for the deterministic detection of vacant parking spaces based on distributed sensors, such as camera modules. However, combined with the required central computer for evaluating the camera data and the display panels for displaying the vacant parking spaces, this results in a complex, costly, and maintenance-intensive system that is only implemented in parking spaces in exceptional cases.

[0007] From the document DE 102013211 632 A1, a method for providing parking information on free parking spaces is known. In this method, historical and current information on available, free parking spaces is determined for at least one street. At least one parking segment comprising one or more streets is determined from the determined information, and statistical parameters on free parking spaces are generated for each parking segment from the determined information. Furthermore, a model is generated for each parking segment, in which the information determined for the parking segment is processed to determine a parking status of the respective parking segment as a probability distribution. Preferably, an updated probability distribution of the parking status is determined from the information on free, available parking spaces in a parking segment determined in real time.

[0008] Document US 2017 / 0287330 A1 discloses a system and method for locating parking spaces. A request from a motor vehicle driver for a parking space in a specific area is forwarded to a server. Using statistical methods and artificial intelligence, as well as current live data, probabilities for available parking spaces are determined, and the resulting parking information is forwarded to the driver. Calendar-related trends, weather, traffic information, and manually provided data can also be used for such a forecast.

[0009] US Pat. No. 10,066,954 B1 discloses a method for identifying a suitable parking space for a motor vehicle. The driver of the motor vehicle can specify parking preferences via an input interface. Furthermore, such preferences can be derived from historical parking data and weather data. A control device determines a suitable parking space based on the preferences and parking space availability and thus supports navigation of the motor vehicle to this parking space.

[0010] Document US 2011 / 0133959 A1 discloses a method for preventing a motor vehicle to be parked from entering an occupied parking area. An estimated arrival time is determined based on navigation data. A check is then performed to determine whether any parking spaces will be available in the parking area at the time of arrival. If no parking spaces are available, the driver can be informed in advance and, if necessary, navigate to an alternative parking area. Therefore, the object of the present invention is to eliminate, or at least partially eliminate, the disadvantages described above in a method and a system for generating parking space recommendations for a parking facility with a plurality of parking spaces.In particular, it is an object of the present invention to provide a method and a system that improves the quality of a parking space recommendation in a simple and cost-effective manner, so that the probability that a recommended parking space is actually free is increased compared to conventional methods and systems.

[0011] The above object is achieved by the patent claims. Accordingly, the object is achieved by a method for generating recommendations for parking spaces in a parking facility with a plurality of parking spaces, having the features of independent claim 1, and by a system for generating recommendations for parking spaces in a parking facility with a plurality of parking spaces, having the features of independent claim 10. Further features and details of the invention emerge from the subclaims, the description, and the drawings. Features and details described in connection with the method according to the invention naturally also apply in connection with the system according to the invention, and vice versa, so that with regard to the disclosure of the individual aspects of the invention, reference is and can always be made reciprocally.

[0012] According to a first aspect of the invention, the object is achieved by a method for generating recommendations for parking spaces in a parking facility with a plurality of parking spaces. The method comprises:

[0013] - Determining a first current occupancy status of the parking spaces by executing a determination method by a determination device,

[0014] - Predicting a second current occupancy status of the parking spaces by executing a forecasting method by a forecasting device,

[0015] - Determining an overall current occupancy status of the parking spaces based on the determined first current occupancy status and the predicted second current occupancy status by a determining device, and

[0016] - Creating the recommendation of parking spaces based on the determined overall current occupancy status of the parking spaces by a recommendation device.

[0017] According to the invention, when recommending parking spaces, the recommended parking spaces are assigned to specific positions within the parking facility. Within the scope of the invention, a parking space recommendation is understood in particular to mean the provision of a likely usable parking space for a parking space seeker. A likely usable parking space is, for example, a parking space that is highly likely to be unoccupied or that is highly likely to become available within an acceptable waiting period—for example, between thirty seconds and one minute, one minute and five minutes, or similar. The recommendation can refer to a specific parking space or any parking space from a group of parking spaces, for example, in a specific segment of the parking facility.A segment of a parking facility can, for example, be an entire parking level of a multi-story parking facility or a portion of a parking level. The parking facility can, for example, be designed as a parking garage or a parking level. Within the scope of the invention, a parking space is understood to mean a parking area for a vehicle, particularly one marked as such.

[0018] The first current occupancy status of the parking spaces is determined by the determination device by executing the determination method. The respective positions of the parking spaces within the parking facility are also taken into account here. The determination device can, for example, be designed as a device of a system for generating recommendations for parking spaces in a parking facility with a plurality of parking spaces. The determination device can, for example, be designed to independently determine measurement data for determining the first current occupancy status of the parking spaces and / or to receive such measurement data. Determining an occupancy status of a parking space according to the determination method is understood within the scope of the invention to mean that it is determined, for example by observation, measuring, receiving, or the like, whether the parking space is free or occupied, for example by a vehicle or another obstacle.According to the invention, the first current occupancy status of at least one parking space of the parking facility is determined such that the current occupancy status for the at least one parking space is definitively known at least at the time of the determination. Preferably, the first current occupancy status is determined for a plurality of parking spaces, so that the current occupancy status for each of these parking spaces is definitively known at least at the time of the respective determination.

[0019] The second current occupancy status of the parking spaces is predicted by the forecasting device by executing the forecasting method. Within the scope of the invention, predicting the occupancy status of a parking space according to the forecasting method means predicting, for example, by using a model of the parking facility, calculating, comparing, estimating, other statistical and / or stochastic methods, or the like, whether the parking space is more likely to be free or more likely to be occupied. According to the invention, the second current occupancy status is predicted for at least one parking space of the parking facility.

[0020] Preferably, the second current occupancy status is predicted for a plurality of parking spaces, preferably for all parking spaces. This preferably also takes into account the respective positions of the parking spaces within the parking facility.

[0021] Forecasting the second current occupancy status is preferably carried out continuously, so that the second current occupancy status is always up-to-date, thus ensuring particularly high forecast quality within the limits of forecasting possibilities. There is a correlation between the predictive power of the first current occupancy status and the second current occupancy status.

[0022] The determination device uses the first current occupancy status and the second current occupancy status to determine the overall current occupancy status of the parking spaces, taking into account the respective positions of the parking spaces within the parking facility. The overall current occupancy status is therefore based partly on directly recorded data and partly on forecast data. The overall current occupancy status is intended to indicate what the current occupancy of specifically located parking spaces within the parking facility is most likely to be at a given point in time.

[0023] The recommendation device generates the parking space recommendation based on the determined overall current occupancy status of the parking spaces as well as the respective position within the parking facility. The generated recommendation is preferably forwarded to a driver searching for a parking space, for example, to a navigation system in their vehicle, to their mobile device, or as an addition to a printed or virtual parking ticket generated when entering the parking facility. The recommendation is preferably transmitted in response to a driver's request for a free parking space. The request can be made automatically, for example, by entering the parking facility, for example, by passing a detection device such as a light barrier, contact loop, induction loop, camera, RFID reader, or the like, or actively by the driver or other vehicle occupants.A method according to the invention for generating parking space recommendations in a parking facility with multiple parking spaces has the advantage over conventional methods that it provides the driver of the motor vehicle with specific parking spaces and location information using simple means and in a cost-effective manner, so that the search for a parking space can be reduced to a specific parking space. This data can be transmitted, for example, to a vehicle's navigation system, which then guides the driver directly to the location where the vehicle is to be parked. A time-consuming search for a free parking space in a parking facility is thus no longer necessary.

[0024] It is preferred that, to determine the overall current occupancy status, the first current occupancy status is weighted with a first weighting factor and / or the second current occupancy status is weighted with a second weighting factor, wherein the first weighting factor and / or the second weighting factor are functions of time. The occupancy status of a parking space can change at any time due to corresponding vehicle movements. A parking space determined as free can be occupied again the next moment, just as a parking space determined as occupied can become free again. Thus, the quality of the determined first current occupancy status decreases with increasing time interval from the determination time. According to the invention, this loss of quality is taken into account by the first weighting factor.The first weighting factor preferably has a maximum value at the time of determination, since the probability of the first current occupancy status is 100% at the time of determination. Depending on normal vehicle movements in the parking facility, this probability of the first current occupancy status decreases over time, so that the first weighting factor also decreases over time. A minimum value for the first weighting factor with a sufficiently large time interval from the time of determination is preferably 0%. While the probability of the first current occupancy status decreases over time, the probability of the second current occupancy status depends on other factors, namely a forecast possibility, which can fluctuate over time due to a multitude of possible influencing factors.To account for the interrelationship and fluctuations, the second weighting factor is used to weight the second current occupancy status. The second weighting factor preferably has a minimum value at the time of determination, since the probability of the first current occupancy status being true is 100% at the time of determination. The minimum value for the second weighting factor is preferably 0%. As the probability of the first current occupancy status being true decreases, the second weighting factor increases, preferably taking into account the fluctuations explained above. This has the advantage that, using simple means and in a cost-effective manner, the timeliness of the recommendation is particularly high by weighting the determined and forecasted occupancy status of the parking spaces, thus improving the probability of transmitting an accurate recommendation.The risk of transmitting an incorrect recommendation, i.e. that a parking space recommended as free is not free and does not become free within specified tolerance times, is thus reduced compared to conventional methods.

[0025] According to a preferred further development of the invention, a method can be provided that the determination method comprises the detection of occupied parking spaces and / or free parking spaces by a vehicle driving through the parking facility and / or the detection of vehicles in the parking facility by a surveillance camera of the parking facility and / or the targeted detection of vehicles entering and leaving the parking facility and / or areas of the parking facility. Modern motor vehicles have a multitude of sensors, such as ultrasonic sensors, radar sensors, or lidar sensors, which are designed to scan the surroundings of the motor vehicle.Such sensors are used, for example, by parking assistance systems, braking assistance systems, or autonomous driving systems and can advantageously be used when carrying out the method according to the invention to determine the first current occupancy status, for example while the determining motor vehicle is driving past the parking spaces, entering a parking space, or leaving the parking space again. In this case, the determination device is preferably designed as a device of a system for generating recommendations for parking spaces in a parking facility with a plurality of parking spaces and for receiving the data determined by the motor vehicle for determining the first current occupancy status of the parking spaces. The surveillance camera of the parking facility is preferably designed as a determination device of a system for generating recommendations for parking spaces in a parking facility with a plurality of parking spaces.The targeted detection of vehicles entering and leaving the parking facility is preferably carried out via a detection device of a system for generating parking space recommendations in a parking facility with a plurality of parking spaces. For this purpose, for example, light barriers, contact loops, induction loops, or the like can be used. This has the advantage that reliable detection of the first current occupancy status of the parking spaces is ensured using simple means and in a cost-effective manner. According to the invention, it is preferred that the forecasting method comprises the collection of data on historical parking space occupancy and / or events in the vicinity of the parking facility and / or parking space occupancy of neighboring parking facilities and / or the weather and / or traffic and / or the date and / or time for forecasting the second current occupancy status.The forecasting device evaluates the data used within the forecasting method and, based on this data, forecasts the second current occupancy status of the parking spaces. Data on historical parking space occupancy includes parking space occupancy from the past, which can depend, for example, on the acceptance of the parking facility or the surroundings of the parking facility by users of the parking facility, the condition of the parking facility, a time of day, a day of the week, a day of the month, or the like. For upcoming events, such as special sales, concerts, or the like, a higher occupancy rate, a lower parking space turnover frequency, or possibly a longer parking space usage period of the parking facility can be expected.This has the advantage that a reliable forecast of the second current occupancy status of the parking spaces is guaranteed using simple means and in a cost-effective manner.

[0026] Further preferably, the forecasting method is carried out by artificial intelligence, wherein the artificial intelligence determines a probability of the forecasted second current occupancy status being correct and determines the second weighting factor depending on the determined probability. Such a probability can be determined, for example, by comparing the forecast data with historical data, which were preferably recorded under the same or at least similar conditions. Furthermore, the probability can be determined or at least influenced by comparing it with the first current occupancy status and / or by using the first weighting factor. If the probability is relatively low, a lower second weighting factor is preferably determined than if the probability is relatively high.The artificial intelligence is preferably self-learning so that causes of inaccurate or incorrect forecasts are identified and reduced where possible. This has the advantage that a reliable forecast of the second current occupancy status of the parking spaces is improved using simple means and in a cost-effective manner. In a particularly preferred embodiment of the invention, a method can be provided that the recommendation device also makes recommendations for parking spaces based on a known parking space change frequency. In the context of the invention, a parking space change frequency is understood to mean the frequency with which vehicles occupy and vacate a parking space. The longer a parking space is parked, the lower the parking space change frequency.This has the advantage that the quality of the parking recommendation can be improved using simple means and in a cost-effective manner.

[0027] It is preferred that the recommendation device generates the parking space recommendation in such a way that the recommendation probability is increased for parking spaces determined as occupied with a relatively high parking space change frequency compared to parking spaces determined as occupied with a relatively low parking space change frequency, and / or that the recommendation probability is increased for parking spaces determined as free with a relatively low parking space change frequency compared to parking spaces determined as free with a relatively high parking space change frequency. If a parking space is occupied, it is usually not available to a vehicle searching for a parking space. Nevertheless, it can happen that, for example, all of the parking spaces in the parking facility are temporarily occupied.In this case, the probability that a parking space with a relatively high turnover frequency will become available next is particularly high, so it is recommended preferentially over occupied parking spaces with a relatively low turnover frequency. Likewise, free parking spaces with a relatively low turnover frequency are more likely to remain free than free parking spaces with a relatively high turnover frequency, and are therefore recommended preferentially. This has the advantage that the quality of the parking space recommendation can be improved using simple and cost-effective means.

[0028] According to a preferred embodiment of the invention, a manual input from a user of the parking facility regarding the occupancy status of at least one parking space in the parking facility is recorded, wherein the determination of the overall current occupancy status of the parking spaces is also carried out on the basis of the manual input. A manual input can, for example, be feedback from a user of the parking facility regarding a parking space recommendation, for example, whether the recommendation was successful or not. A manual input can, for example, also be a notification from the user of one or more free parking spaces. This has the advantage that the quality of the parking space recommendation can be improved using simple means and in a cost-effective manner.

[0029] Particularly preferably, the manual input is weighted with a third weighting factor, wherein the third weighting factor is a function of time. The weighting factor preferably decreases as time progresses, since the manual input increasingly becomes less up-to-date. Furthermore, it is preferred that the third weighting factor depends on the user. For example, it can be provided that a user is given influence on the third weighting factor, which takes into account historical behavior or reliability of the user. A user who has already made a manual input several times, which has led to an improvement in the quality of the recommendations, can, for example, result in a higher weighting factor than a user who has made a manual input for the first time or whose manual entries have turned out to be incorrect.This has the advantage that the quality of the parking recommendation can be improved using simple means and in a cost-effective manner.

[0030] According to a second aspect of the invention, the object is achieved by a system for generating recommendations for parking spaces in a parking facility having a plurality of parking spaces. The system comprises a determination device for determining a first current occupancy status of the parking spaces by executing a determination method, a prediction device for predicting a second current occupancy status of the parking spaces by executing a prediction method, a determination device for determining an overall current occupancy status of the parking spaces based on the determined first current occupancy status and the predicted second current occupancy status, and a recommendation device for creating the recommendation for parking spaces based on the determined overall current occupancy status of the parking spaces. According to the invention, the system is designed to carry out a method according to the invention.

[0031] The system according to the invention provides all the advantages already described for a method according to the first aspect of the invention. Accordingly, the system according to the invention has the advantage over conventional systems that specific parking spaces with location information can be provided to the driver of the motor vehicle using simple means and in a cost-effective manner, so that the search for a parking space can be reduced to a specific parking space. This data can be transmitted, for example, to a navigation system of the motor vehicle, which then guides the driver directly to the location from which the motor vehicle is to be parked. A time-consuming search for a free parking space in a parking facility is thus no longer necessary.

[0032] A method according to the invention for generating recommendations for parking spaces in a parking facility with a plurality of parking spaces, as well as a system according to the invention for generating recommendations for parking spaces in a parking facility with a plurality of parking spaces, are explained in more detail below with reference to the drawings. They show schematically:

[0033] Figure 1 shows a schematic representation of a system according to a preferred first embodiment of the invention,

[0034] Figure 2 shows a side view of a motor vehicle for detecting occupied parking spaces,

[0035] Figure 3 shows a plan view of a parking facility during implementation of a preferred embodiment of a method according to the invention,

[0036] Figure 4 shows a plan view of a recommendation map for parking spaces of a parking facility, and

[0037] Figure 5 shows a flow chart of a preferred embodiment of a method according to the invention.

[0038] Elements with the same function and mode of operation are provided with the same reference numerals in Figures 1 to 5.

[0039] Fig. 1 shows a schematic representation of a system 9 according to a preferred first embodiment of the invention. The system 9 comprises a determination device 3, a prediction device 4, a determination device 5, and a recommendation device 6. The determination device 3 is designed to determine a first current occupancy status of parking spaces 1 (see Fig. 3) by executing a determination method. The prediction device 4 is designed to predict a second current occupancy status of the parking spaces 1 by executing a prediction method.The determination device 5 is designed to determine an overall current occupancy status of the parking spaces 1 based on the determined first current occupancy status, the predicted second current occupancy status, and a manual input by a user B, as well as taking into account a first weighting factor, a second weighting factor, and a third weighting factor. The recommendation device 6 is designed to generate the recommendation of parking spaces 1 based on the determined overall current occupancy status of the parking spaces 1. Preferably, the recommendation device 6 is designed to transmit the recommendation to a motor vehicle 7 (see Fig. 2).

[0040] Fig. 2 shows a schematic side view of a motor vehicle 7 for detecting occupied parking spaces 1. The motor vehicle 7 has several sensors 10 for detecting occupied parking spaces 1 (see Fig. 3) and a transmitting device 11 for transmitting data about the detected occupied parking spaces 1 to the detection device 3 of the system 9.

[0041] Fig. 3 schematically depicts a plan view of a parking facility 2 during the implementation of a preferred embodiment of a method according to the invention. A surveillance camera 8 configured as a detection device 3 of the system 9 detects vehicle movements of vehicles 7 on the parking facility 2, thus determining the occupancy status of the parking spaces 1. Furthermore, a sensor 10 of a moving vehicle 7 can detect the occupancy status of the parking spaces 1 and transmit this information to the detection device 3. Using the prediction device 4, the determination device 5, and the recommendation device 6, recommendations for free parking spaces 1 can be generated and transmitted to the motor vehicle 7.

[0042] Fig. 4 shows a recommendation map 12 for parking spaces 1 of a parking facility 2, schematically in a plan view. The recommendation map 12 can be created, for example, by the recommendation device 6 based on the determined current occupancy status of the parking spaces 1. The occupancy status of the parking spaces 1 can be identified by marking the parking spaces 1, for example by colors, hatching, or the like. A white parking space 1, for example, can mean that these parking spaces 1 are most likely free and thus particularly recommended. Light hatching can mean, for example, that these parking spaces 1 are more likely to be free than occupied and thus more recommendable. Heavy hatching can mean, for example, that they are most likely to be occupied and therefore not recommended.Using such a recommendation card 12, the recommendations of free parking spaces 1 can be transmitted from the recommendation device to a vehicle 7 searching for a parking space. A preferred embodiment of a method according to the invention is schematically depicted in a flowchart in Fig. 5. According to a first method action 100, a first current occupancy status of the parking spaces 1 is determined by executing a determination method by a determination device 3. Upon determining the first current occupancy status, the parking spaces 1 are registered together with their positions within the parking facility 2. According to a second method action 200, a second current occupancy status of the parking spaces 1 is forecast by executing a forecast method by a forecast device 4. Upon forecasting the second current occupancy status, the parking spaces 1 are registered together with their positions within the parking facility 2.

[0043] According to a third procedural action 300, an overall current occupancy status of the parking spaces 1 is determined by a determination device 5 based on the determined first current occupancy status weighted by a first weighting factor and the predicted second current occupancy status weighted by a second weighting factor. According to a fourth procedural action 400, a recommendation of parking spaces 1 is created by a recommendation device 6 based on the determined overall current occupancy status of the parking spaces 1 and transmitted, together with the respective positions of the recommended parking spaces 1 within the parking facility 2, to a vehicle 7 searching for a parking space on the parking facility 2.

[0044] List of reference symbols

[0045] 1 Parking space Parking facility Determination device Prediction device Determination device Recommendation device Vehicle

[0046] 8 surveillance cameras

[0047] 9 System

[0048] 10 Sensor

[0049] 11 Transmitting device

[0050] 12 Recommendation card

[0051] 100 first procedural action

[0052] 200 second procedural action

[0053] 300 third procedural action

[0054] 400 fourth procedural action

[0055] B User

Claims

Patent claims Method for generating recommendations of parking spaces (1) of a parking facility (2) with a plurality of parking spaces (1), comprising: Determining a first current occupancy status of the parking spaces (1) by executing a determination method by a determination device (3), predicting a second current occupancy status of the parking spaces (1) by executing a forecasting method by a forecasting device (4), determining an overall current occupancy status of the parking spaces (1) on the basis of the determined first current occupancy status and the forecast second current occupancy status by a determination device (5), and Creating the recommendation of parking spaces (1) based on the determined overall current occupancy status of the parking spaces (1) by a recommendation device (6), characterized in that, during the recommendation of parking spaces (1), the recommended parking spaces (1) are assigned to specific positions within the parking facility (2). Method according to claim 1, characterized in that, for determining the overall current occupancy status, the first current occupancy status is weighted with a first weighting factor and / or the second current occupancy status is weighted with a second weighting factor, wherein the first weighting factor and / or the second weighting factor are functions of time.Method according to claim 1 or 2, characterized in that the determination method comprises the detection of occupied parking spaces (1) and / or free parking spaces (1) by a vehicle (7) driving over the parking facility (2) and / or the detection of vehicles (7) on the parking facility (2) by a surveillance camera (8) of the parking facility (2) and / or the targeted detection of vehicles (7) driving into and away from the parking facility (2) and / or areas of the parking facility (2). Method according to one of the preceding claims, characterized in that the forecasting method comprises the acquisition of data on historical parking space occupancy and / or events in the vicinity of the parking facility (2) and / or parking space occupancy of neighboring parking facilities (2) and / or the weather and / or traffic and / or the date and / or the time to forecast the second current occupancy status. Method according to claim 4, characterized in that the forecasting method is carried out by artificial intelligence, wherein the artificial intelligence determines a probability of the forecasted second current occupancy status being correct. Method according to one of the preceding claims, characterized in that the creation of the recommendation of parking spaces (1) by the recommendation device (6) is also carried out on the basis of a known parking space change frequency of the parking spaces (1).Method according to claim 6, characterized in that the recommendation of parking spaces (1) is created by the recommendation device (6) in such a way that for parking spaces (1) determined to be occupied with a relatively high parking space change frequency, a recommendation probability is increased compared to parking spaces (1) determined to be occupied with a relatively low parking space change frequency and / or that for parking spaces (1) determined to be free with a relatively low parking space change frequency, the recommendation probability is increased compared to parking spaces (1) determined to be free with a relatively high parking space change frequency.Method according to one of the preceding claims, characterized in that a manual input of a user (B) of the parking facility (2) about the occupancy status of at least one parking space (1) of the parking facility (2) is recorded, wherein the determination of the entire current occupancy status of the parking spaces (1) is also carried out on the basis of the manual input. Method according to claim 8, characterized in that the manual input is weighted with a third weighting factor, wherein the third weighting factor is a function of time.System (9) for generating recommendations for parking spaces (1) of a parking facility (2) with a plurality of parking spaces (1), comprising a determination device (3) for determining a first current occupancy status of the parking spaces (1) by executing a determination method, a forecasting device (4) for forecasting a second current occupancy status of the parking spaces (1) by executing a forecasting method, a determination device (5) for determining an overall current occupancy status of the parking spaces (1) on the basis of the determined first current occupancy status and the forecast second current occupancy status, and a recommendation device (6) for creating the recommendation for parking spaces (1) on the basis of the determined overall current occupancy status of the parking spaces (1), characterized in that the system (9) is designed to carry out a method according to one of claims 1 to 9.

Images