EP3816960A1 - Method and apparatus for outputting alert messages - Google Patents

Abstract

A method for forecasting available parking spaces, comprising the following steps carried out by means of a computing unit: a traffic structure analysis in which significant cells are selected from cells of a cell grid on the basis of a static data set formed by traffic data from a first time period; a calculation in which on A statistical parking situation is determined on the basis of a real-time data set formed by traffic data of the significant cells from a second second space for at least one of the cells of the cell grid, and in which on the basis of a sensor data set formed by sensor data of the cells from a third period for at least one a sensor parking situation is determined for the cells of the cell grid; and a probability prognosis in which a prognosis of available parking spaces is carried out for at least one of the cells of the cell grid on the basis of the statistical parking space situation and the sensor parking space situation.

Description

The present invention relates to a method for forecasting available parking spaces, in particular the forecasting of non-commercial motor vehicle parking spaces, or “on-street” parking spaces, in urban traffic areas on the basis of mobile radio data and other data sets. In addition, the invention also relates to an arrangement for forecasting available parking spaces, which is designed to carry out the method. In addition, the invention relates to a method based on a mobile terminal device for forecasting available parking spaces, as well as a mobile terminal device provided for carrying out the method and a computer program product.

Due to increasing restriction and management, as well as due to the increased volume of traffic, non-commercial car parking spaces, the so-called "on-street" parking spaces, have become a scarce resource in city centers. Traffic searches for parking spaces pollute the environment and impair the quality of life. Around 30 percent of inner-city traffic is caused by looking for a parking space. Drivers produce around 1.3 to 1.5 kg of CO2 per search. The probability of finding a free parking space on a personal smartphone ("app") without a dedicated application is around 30 percent. With parking space search functions, it increases to around 80 percent. The availability of parking spaces is displayed in a desired area per street segment and an app navigates the driver directly in some cities. The use of cellular data for parking space forecast can be extended to the entire cellular area of one or different cellular providers.

Available forecast services can be divided into two classes: first, the deterministic forecasts and second, the probability-based forecasts.

The first class of deterministic forecasts includes all records of dedicated parking spaces via directly assigned sensors or equivalent status records. This type of recording is used in particular in managed parking spaces (e.g. multi-storey car parks). An occupancy image of the parking spaces viewed can be generated directly and online via portal connections. These systems require significant investments.

The second class of probability-based forecasts is based on statistical evaluations and models. For this purpose, a statistical set of measured values must be available that ensures significance and thus allows probability interpretation. In addition to classic mathematical statistics, so-called "machine learning" tools are also used, ie mathematical algorithms that can derive rules or classifiers from large data sets. Statistical methods are used in particular when direct refinancing of sensor equipment is not possible, for example in free parking on the roadside. One possible static method is, for example, the generation of daily cycles, whereby the parking space availability is recorded over a longer period of time for a twenty-four-hour course of the day at suitable time intervals (e.g. every 10 minutes, every quarter hour, hourly) based on a local unit (e.g. street segment, city district). The prediction is based on the assumption that if there was a certain probability of an available / free parking space at a certain time of day at a certain location in the past with sufficient confidence, there will also be a free parking space on another day in the future at this time of day is to be found.

In machine learning, for example, there is a data set that assigns a probability interpretation to certain situations. In addition, there are data sources that are inherently related to the parking space occupancy situation (e.g. lane data from vehicle movements, camera data, calendar data, ultrasonic sensors, selective floor sensors, etc.). The machine learning tools now generate a mapping of this data to the verified situation, the so-called training. For the When used at execution time, the trained model is applied to the current data situation and a forecast is generated in this way.

The following properties are important for machine learning in the present context. The way in which input data is classified in machine learning always remains opaque; a direct interpretation fails. It follows that explicitly available knowledge always has a higher quality than algorithmic-statistical conclusions. Furthermore, machine learning methods have difficulties with the consideration of data on different time scales; In the present context, this concerns the comparison of validated daily cycles (see above) and short-term phenomena (e.g. 15 min). If the population is not chosen correctly, sham inaccuracies are generated on the short-term scale.

The object of the underlying invention is to provide a method for forecasting available parking spaces that is particularly efficient or has low system costs, the accuracy of the forecast for available parking spaces being as high as possible and being determined quickly with the least possible computing effort. In addition, it is an object of the invention to provide an arrangement which can carry out the method. Another object of the invention is to provide a method based on a mobile terminal device for forecasting available parking spaces that is efficient, precise and fast. In addition, a mobile terminal device provided for carrying out the method and a corresponding computer program product are made available.

• eine Verkehrsstrukturanalyse, bei der aus Zellen eines Zellengitters signifikante Zellen auf Grundlage eines durch Verkehrsdaten aus einem ersten Zeitraum gebildeten statischen Datensatzes ausgewählt werden;
• eine Berechnung, bei der auf Grundlage eines durch Verkehrsdaten der signifikanten Zellen aus einem zweiten Zweitraum gebildeten Echtzeit-Datensatzes für zumindest eine der Zellen des Zellengitters eine statistische Parkplatzsituation, insbesondere eine statistische Parkplatzwahrscheinlichkeit, ermittelt wird, und
• bei der auf Grundlage eines durch Sensordaten der Zellen aus einem dritten Zeitraum gebildeten Sensor-Datensatzes für zumindest eine der Zellen des Zellengitters eine Sensorparkplatzsituation, insbesondere eine Sensorparkplatzwahrscheinlichkeit, ermittelt wird; und
• eine Wahrscheinlichkeitsprognose, bei der auf Grundlage der statistischen Parkplatzsituation, insbesondere der statistischen Parkplatzwahrscheinlichkeit, und der Sensorparkplatzsituation, insbesondere der Sensorparkplatzwahrscheinlichkeit, für zumindest eine der Zellen des Zellengitters eine Prognose an verfügbaren Parkplätzen durchgeführt wird.

The present invention solves this problem by a method for forecasting available parking spaces, comprising the following steps carried out by means of a computing unit:

• a traffic structure analysis, in which significant cells are selected from cells of a cell grid on the basis of a static data set formed by traffic data from a first time period;
• a calculation in which a statistical data set is generated for at least one of the cells of the cell grid on the basis of a real-time data set formed by traffic data of the significant cells from a second second space Parking lot situation, in particular a statistical parking space probability, is determined, and
• in which, on the basis of a sensor data record formed by sensor data of the cells from a third period of time, a sensor parking situation, in particular a sensor parking probability, is determined for at least one of the cells of the cell grid; and
• a probability prognosis in which, on the basis of the statistical parking space situation, in particular the statistical parking space probability, and the sensor parking space situation, in particular the sensor parking space probability, a forecast of available parking spaces is carried out for at least one of the cells of the cell grid.

In the traffic structure analysis, the cells that have a comparatively high statistical significance are selected from the totality of the cells in the cell grid. On the basis of the significant cells, a prognosis for the other cells of the cell grid can be made with sufficient statistical certainty. For example, it has been shown that for a city that has a cell grid with 250 cells, only 9 significant cells are sufficient to generate a prognosis for the parking space probability for all cells of the cell grid with sufficient accuracy. The statistical parking situation is calculated on the basis of the real-time data set, with only the traffic data of the significant cells being used for the real-time data set. Since the number of significant cells in the cell grid is significantly less than the number of all cells in the cell grid, significantly less traffic data has to be registered and processed to determine the real-time data set. This advantageously leads to a considerable increase in efficiency and thus to a reduction in system costs. For example, in a test, the underlying method was able to reduce the system costs for the provision of traffic data in the form of cellular data by 90%. In particular, the system costs could be reduced because the number of times an application located on a mobile terminal device needs to access a server, the so-called "API calls", is lower as a result of the method.

The individual steps are carried out on the basis of different data sets so that the traffic structure analysis can be carried out independently of the calculation of the statistical parking space situation and / or the sensor parking space situation. In this way, the available computer resources can be divided up as required. For the traffic structure analysis, for example, a longer first period of time can be used as the basis for the static data set without the computationally expensive traffic structure analysis having a negative effect on the computing time for calculating the statistical parking space situation or the sensor parking space situation. In contrast, the real-time data record is used to calculate the statistical parking situation, which contains significantly less information because, on the one hand, it only contains the traffic data of the significant cells and the second time period can be selected to be shorter. Advantageously, less computing power and / or computing time is required as a result, so that the statistical parking lot situation can also be determined with sufficient accuracy on the basis of a real-time data set obtained shortly before the prognosis time.

The statistical parking space situation determined on the basis of the real-time data set is used in combination with the sensor parking space situation for the probability prognosis. The sensor parking situation is determined using a sensor data record based on sensor data from the cells of the cell grid. The sensor data set is created independently of the other data sets and represents a direct measurement of the parking space situation. The sensor data have the advantage that they can be evaluated immediately and do not require any complex statistical calculation, so that the sensor data set is relatively up-to-date, i.e. it is available shortly before the prognosis time. By combining the statistical parking space situation with the sensor parking space situation, it is advantageously possible to achieve a higher level of accuracy in the forecast of available parking spaces.

A statistical parking space probability is preferably determined for at least one cell of the cell grid on the basis of the significant cells on the basis of the real-time data record. The statistical Parking space probability corresponds to a statistically significant probability of the availability of free parking spaces. In addition, a sensor parking space probability is preferably determined for at least one cell of the cell grid on the basis of the sensor data set. These values indicate the probability of a free / available parking space. The respective statistical parking space probability and the respective sensor parking space probability are preferably determined for each cell and used for the prognosis.

A preferred embodiment of the invention is characterized in that, during the traffic structure analysis, the cells of the cell grid are identified on the basis of the static data set. The size, shape and / or position of the cells is particularly preferably determined on the basis of the vehicle density, street density and / or parking lot density. For example, the reference area of the static data set is divided into a multiplicity of cells of a cell grid, the cells being able to vary in size, shape and / or position. In particular, the cells are defined in such a way that they cover the reference area of the static data set as completely as possible without overlapping. The cells of the cell grid are identified before the significant cells are selected. This advantageously increases the accuracy and the efficiency of the prognosis because the cells can already be defined in such a way that certain cells have a higher statistical significance. The cells of the cell grid preferably have a diameter of 50 to 5000 meters, particularly preferably 150 to 2500 meters.

Another preferred embodiment of the invention is characterized in that the selection of the significant cells takes place on the basis of a main component analysis of the static data set. This corresponds to a dimension reduction. Principal component analysis is a well-known statistical method for structuring extensive data sets by approximating a large number of statistical variables using a smaller number of linear combinations that are as meaningful as possible (the "principal components"). The selection of the significant cells on the basis of a principal component analysis has the advantage that known and can apply proven algorithms for the evaluation of the static data set.

• Fahrzeuge können (in einem statistisch relevanten Sinn; Unfälle oder Diebstähle fallen hier nicht ins Gewicht) weder erzeugt noch vernichtet werden. Dies bedeutet, dass bei geeigneter Wahl von Bezugsgebiet und Zeitintervall die Gesamtbilanz der Fahrzeuge Null ist (also alle Pendler im Mittel zu ihren Wohnungen zurückkehren oder alle Büroarbeitsplätze im Mittel abends verlassen werden).
• Fahrzeug, die aus einem Betrachtungsgebiet herausfahren, müssen in ein benachbartes Betrachtungsgebiet einfahren.
• Die Veränderung von Verkehrsstärken ist in einem statistischen Sinne stetig, Sprungverhalten von entsprechenden mathematischen Funktionen treten in der Realität nicht auf.
• Die Transportkapazität eines Straßensegments hat eine obere Grenze, die beispielsweise durch die geltende Höchstgeschwindigkeit, eine mittlere Fahrzeuglänge und den mittleren Abstand zum vorausfahrenden Fahrzeug gegeben ist.
• Der am Straßenrand verfügbare freie Parkraum (sofern nicht explizit bekannt oder über Verkehrsregelung eingeschränkt) hat eine berechenbare obere Grenze.

Durch die Verwendung von expliziten Rahmenbedingungen können bei der Identifizierung der Zellen und der Auswahl der signifikanten Zellen örtliche Gegebenheiten der Zellen berücksichtigt werden, so dass die Genauigkeit der Prognose erhöht wird.In a further preferred embodiment of the invention, for the traffic structure analysis, explicit framework conditions or explicit model knowledge are linked with a statistical evaluation. Examples of explicit model knowledge, respectively explicit framework conditions, in the considered subject area of urban traffic flows are:

• Vehicles can (in a statistically relevant sense; accidents or thefts are irrelevant here) neither be created nor destroyed. This means that with a suitable choice of reference area and time interval, the overall balance of the vehicles is zero (i.e. all commuters return to their homes on average or all office workplaces are left on average in the evening).
• Vehicles driving out of a viewing area must enter an adjacent viewing area.
• The change in traffic volumes is constant in a statistical sense, and jump behavior of corresponding mathematical functions does not occur in reality.
• The transport capacity of a road segment has an upper limit, which is given, for example, by the applicable maximum speed, an average vehicle length and the average distance to the vehicle in front.
• The free parking space available at the roadside (unless explicitly known or restricted by traffic regulations) has a calculable upper limit.

By using explicit framework conditions, local conditions of the cells can be taken into account in the identification of the cells and the selection of the significant cells, so that the accuracy of the prognosis is increased.

Another embodiment of the invention is characterized in that the static data record and the real-time data record are based on traffic data obtained from mobile radio data. The mobile radio data are based on a set of mobile terminals, in particular on a statistical one relevant sample. The localization of mobile devices, which is carried out either by explicit GPS positioning or by logging into cellular radio cells, enables a very precise picture of the mobility patterns in an area under consideration. The high event density of mobile radio-based data records is preferably used in order to generate a particularly accurate image of the traffic situation. On the basis of mobile radio data, lane paths of the terminal devices in particular can be generated, these paths being able to be analyzed with suitable statistical filters. Road users are particularly preferably identified on the basis of their movement characteristics. Vehicles looking for parking spaces can also be identified based on their acceleration and braking behavior. The high event density of mobile radio data advantageously increases the accuracy of the statistical calculation. The use of cellular data for parking space forecast can be extended to the entire cellular area of one or different cellular providers. The static data set and the real-time data set can each be based on several data sets. In particular, cellular network data for the data records can come from different cellular network providers.

A further embodiment of the invention is characterized in that the static data record is available offline, i.e. is based on traffic data from an upstream first period that is already stored on a storage medium and is not recorded immediately before the forecast time. The statistical data record particularly preferably comprises a reference area which is completely covered by the cells of the cell grid. In this way, existing traffic data can advantageously be used to carry out the traffic structure analysis - there is no need for tedious recording of traffic data. Thus, the invention allows a combination of structural off-line analysis with real-time data.

Another embodiment of the invention is characterized in that the sensor data record is created on the basis of sensors that register events relevant to parking spaces, in particular an occupancy image is generated. The sensors are, for example, floor sensors, vehicle-based sensors, distance meters, cameras and / or infrastructure sensors. Through the Inexpensive and large-scale connection of sensor infrastructures, more and more areas of public life can be analytically recorded more and more extensively, including the environment of vehicle-based mobility. Sensor data must be differentiated into stationary units that register parking space occupancy at a location and mobile sensors (e.g. installed in motor vehicles) that detect parking space occupancy at the roadside. For example, the sensor data record is created by a third party and made available for further use.

Another embodiment of the invention is characterized in that the time periods on which the data records are based are different, the first time period of the static data record being before the second time period of the real-time data record and the third time period of the sensor data record. The second time period of the real-time data record is preferably also before the third time period of the sensor data record. The periods of time preferably have different temporal orders of magnitude, in particular the first period of the static data set being recorded years before the prognosis point in time and taking traffic data from years into account. The first period preferably begins one to two years before the forecast time and comprises a period of several months, ideally one year, in order to statistically record seasonal fluctuations in the traffic situation. The second period of the real-time data set begins preferably 1.5 to 5 hours before the forecast time, particularly preferably two to three hours, and comprises a period of at least one hour in order to obtain a statistically validated statement about the traffic balance in the cells under consideration. The third period of the sensor data record preferably begins 1 to 15 minutes before the prognosis time, particularly preferably 5 to 10 minutes, and collects the current image of the sensor data for the traffic area or reference area under consideration. It has been found that with these values it is advantageously possible to achieve as precise a prognosis as possible for the time periods.

Another embodiment of the invention is characterized in that a suitable mathematical combination of the statistical parking space probability and the sensor parking space probability is formed in the probability prognosis. The forecast of available parking spaces for a cell is preferably the suitably weighted mean value of the statistical parking space probability and the sensor parking space probability. Advantageously, a correction / adaptation of the statistical calculation using actually available sensor data is thereby achieved with little computational effort.

Another embodiment of the invention is characterized in that the method has a machine learning function in which a certain statistical parking lot situation is assigned to a certain sensor parking lot situation, in particular the traffic structure analysis, the calculation and / or the probability prognosis being adapted / corrected. Advantageously, the accuracy of the prognosis is improved by a machine learning function. In an exemplary embodiment of the invention, the machine learning function includes the mapping of a vector of measured sensor data at a few explicit locations at a point in time to the probable parking space occupancy situation at the same point in time for the entire traffic area under consideration. This mapping then functions as a further, now mathematically generated data set for the previously described data fusion.

Another embodiment of the invention is characterized in that a correction factor is used in the probability prognosis if there is a systematic difference between the statistical parking space probability and the sensor parking space probability. For example, in the averaging, the statistical parking space probability is multiplied by a correction factor if the statistical parking space probability systematically deviates from the sensor parking space probability. The correction factor is preferably variable and is adapted as a function of the difference between the probabilities.

• eine Speichereinheit, die dazu ausgebildet ist einen durch Verkehrsdaten aus einem ersten Zeitraum gebildeten statischen Datensatz zu speichern;
• eine Echtzeitdatenverarbeitungseinheit, die dazu ausgebildet ist durch Verkehrsdaten signifikanter Zellen aus einem zweiten Zweitraum einen Echtzeit-Datensatz zu bestimmen;
• eine Sensorkommunikationseinheit, die dazu ausgebildet aus Sensordaten aus einem dritten Zeitraum einen Sensor-Datensatz zu bestimmen; und eine
• Rechnereinheit, die dazu ausgebildet ist die Verfahrensschritte des vorgenannten Verfahrens auszuführen.

The object on which the invention is based is also achieved by an arrangement for forecasting available parking spaces, comprising:

• a storage unit which is designed to store a static data set formed by traffic data from a first time period;
• a real-time data processing unit which is designed to determine a real-time data set from traffic data of significant cells from a second second space;
• a sensor communication unit which is designed to determine a sensor data set from sensor data from a third time period; and a
• Computer unit which is designed to carry out the method steps of the aforementioned method.

The arrangement is designed to carry out the aforementioned method. For this purpose, the arrangement has a storage unit for the static data record, a real-time processing unit for the real-time data record and a sensor communication unit for the sensor data record. The computer unit is intended to carry out the method steps that are carried out on the basis of the data records. The mobile radio data of the significant cells from the second time period are evaluated by means of the real-time processing unit in order to determine the real-time data record. The sensor communication unit receives the sensor data from the sensors that measure events relevant to parking spaces, for example floor sensors, vehicle-based sensors, distance meters, cameras and / or infrastructure sensors. The sensor data set is determined from the sensor data by means of the sensor communication unit. On the basis of the data sets, the computing unit determines the statistical parking space situation, in particular the statistical parking space probability, and the sensor parking space situation, in particular the sensor parking space probability. The units of the arrangement can be arranged spatially separated from one another or form a spatial unit. The processing unit is preferably a server on which the method steps are carried out and with which the other units communicate.

The object on which the invention is based is moreover achieved by a computer program product which, when the program is executed by an arrangement, causes the latter to carry out the steps of the method described above. The arrangement with the storage unit, the real-time data processing unit, the sensor communication unit and the computer unit is controlled by the computer program product in such a way that it carries out the traffic structure analysis, the calculation of the statistical parking lot situation and the sensor parking lot situation as well as the probability prognosis for at least one cell of the cell grid.

• Kommunikation des mobilen Endgerätes mit der Recheneinheit der zuvor beschriebenen Anordnung;
• Übermittlung von der Prognose an verfügbaren Parkplätzen für zumindest eine der Zellen des Zellengitters von der Recheneinheit zum mobilen Endgerät;
• Verwendung der Prognose an verfügbaren Parkplätzen für zumindest eine der Zellen des Zellengitters zur Wiedergabe einer Parkplatzsituation und/oder zur Navigation eines Nutzers des mobilen Endgerätes.

The object of the underlying invention is also achieved by a method for forecasting available parking spaces, which comprises the following steps carried out by means of the computer unit and a mobile terminal:

• Communication of the mobile terminal with the computing unit of the arrangement described above;
• Transmission of the forecast of available parking spaces for at least one of the cells of the cell grid from the computing unit to the mobile terminal;
• Use of the forecast of available parking spaces for at least one of the cells of the cell grid to reproduce a parking space situation and / or to navigate a user of the mobile terminal.

The method is based on the fact that a mobile terminal communicates with the arrangement described above, the forecast determined by the arrangement for available parking spaces for at least one cell being transmitted to the mobile terminal. The forecast is used by the mobile terminal to reproduce the parking space situation and / or to carry out a navigation to an available / free parking space. For example, the respective forecast for available parking spaces is displayed in the form of a numerical value or a color scale for the cells in which the mobile terminal is located and for neighboring cells. Using this information, the user of the mobile terminal can find the cells in which he is most likely to get a free parking space. However, the forecast can also be used, for example, by a navigation unit, the Navigation unit automatically guides the user to the cell in which the user is most likely to get a free parking space. The mobile terminal can for example be a smartphone, a tablet, a navigation device or on-board electronics, for example a head-up display.

The object on which the invention is based is also achieved by a further computer program product which, when the program is executed by a mobile terminal, causes the latter to carry out the steps of the method described immediately above.

For example, the computer program product is an app that is executed on the mobile terminal and results in the mobile terminal communicating with the computing unit of the arrangement, the forecast for available parking spaces being transmitted to the mobile terminal. The transmitted forecast is used by the app to reproduce the parking situation and / or to navigate to an available / free parking space.

Fig. 1a:

zeigt eine schematische Darstellung eines durch Zellen gebildeten Zellengitters,

Fig. 1b:

zeigt eine schematische Darstellung einer Zelle eines Zellengitters.

Fig. 2:

zeigt schematisch die von einer Recheneinheit durchgeführten Verfahrensschritte zur Prognose von verfügbaren Parkplätzen und die Datensätze auf denen diese basieren,

Fig. 3:

zeigt eine schematische Darstellung einer Anordnung mit der Recheneinheit, die dazu eingerichtet ist das in Fig. 2 dargestellte Verfahren auszuführen, und

Fig. 4:

zeigt schematisch die von einem mobilen Endgerät durchgeführten Verfahrensschritte zur Prognose von verfügbaren Parkplätzen.

In the following, preferred exemplary embodiments of the present invention are explained with reference to the figures:

Fig. 1a:

shows a schematic representation of a cell grid formed by cells,

Fig. 1b:

shows a schematic representation of a cell of a cell grid.

Fig. 2:

shows schematically the process steps carried out by a computing unit for forecasting available parking spaces and the data sets on which these are based,

Fig. 3:

FIG. 11 shows a schematic representation of an arrangement with the computing unit which is set up for the purpose of Fig. 2 perform the procedures outlined above, and

Fig. 4:

shows schematically the method steps carried out by a mobile terminal device for forecasting available parking spaces.

Features of the present invention are explained below on the basis of preferred embodiments. The present disclosure is not limited to the specifically mentioned combinations of features. Rather, the features mentioned here can be combined as desired to form embodiments according to the invention, unless this is expressly excluded below.

In Fig. 1a cells 1 of a cell grid 2 are shown. A specific reference area is covered by the cells 1 of the cell grid 2, which can be, for example, a city, a country or a traffic area, however defined. The cells 1 can have a different size or shape. The honeycomb shape shown is only an example. The cells 1 of the cell grid 2 preferably completely cover the relevant reference area, in particular without an overlap of neighboring cells 1. As in FIG Figure 1b shown, a cell 1 represents a selected area of the reference area in which, for example, parking lots 4 and streets 5 are located. Various road users are located in cell 1, for example vehicles 6a, 6b or pedestrians 6c. Using mobile radio data from road users 6a, 6b, 6c, their position can be determined as a function of time either by explicit GPS positioning or by booking in mobile radio cells. For example, lane formation is possible for road users 6a, 6b, 6c, with a path of the corresponding terminal being available as a data record. The large number of mobile terminals provides an accurate picture of the mobility pattern in the reference area. On the basis of the mobile radio data of the road users 6a, 6b, 6c as traffic data, a probability-based prognosis for the availability of parking spaces can be created. Ideally, only cellular data from motor vehicles or from mobile devices located in vehicles are used for the parking space forecast. The data record is accordingly divided / split into the different types of road users beforehand.

One embodiment of the method according to the invention for forecasting available parking spaces is shown in FIG Fig. 2 shown schematically. The method is based on a traffic structure analysis 11, a calculation 13 and a Probability prognosis 15. These method steps are carried out on the basis of different data sets 10, 12, 14. The time axis marked with t shows the time sequence of the implementation of the individual method steps 10, 12, 14, the probability prognosis 15 taking place at the prognosis time TP. The timeline is not true to scale.

The traffic structure analysis 11 is carried out on the basis of a static data record 10. The static data record 10 is based on traffic data from a first time period T1, with traffic data from all cells 1 of the cell grid 2 being used as a basis. The first time period T1 is long before the forecast time TP and takes into account traffic data that have been recorded over a longer period of time. The first period T1 preferably begins one to two years before the point in time for the forecast and comprises a period of several months, ideally one year. The traffic structure analysis 11 is thus created on the basis of a data record which has a high statistical significance. In this way, seasonal fluctuations in traffic are recorded statistically.

In the traffic structure analysis 11, on the basis of the static data set 10, significant cells 3 are selected from the cells 1, cell grid 2. The significant cells 3 have a comparatively high statistical significance, so that, on the basis of the significant cells 3, a statistical prognosis for other cells 1, cell grid 2, can be made with sufficient statistical certainty. The selection of the significant cells 3 takes place on the basis of a principal component analysis of the static data set 10.

In a preferred embodiment of the invention, in the traffic structure analysis 11, the cells 1, cell grid 2, are identified on the basis of the static data set 10. The cells 1 are identified before the significant cells 3 are selected. As part of the identification of the cells 1 of the cell grid 2, the size, shape and / or position of the cells 1 is determined, this based on the vehicle density, street density and / or parking lot density he follows. For example, cells 1 in metropolitan areas are smaller than cells 1 in rural areas. The cells 1 become preferably defined in such a way that they do not overlap and cover the reference area under consideration as completely as possible.

A real-time data record 12 and a sensor data record 14 are used for the calculation 13.

The real-time data record 12 is formed by traffic data from the significant cells 3, the traffic data from a second time period T2 being used. For the real-time data record 12, traffic data are used that lie shortly before the prognosis time TP and have been recorded over a comparatively short time. The second period of time T2 preferably begins two to three hours before the prognosis time and comprises a period of at least one hour. The traffic data are the mobile radio data of the road users who are in the significant cells 3 in the second period of time T2. As a result, the amount of data used for the real-time data record 12 can be significantly reduced, so that the efficiency of the forecasting method is improved or the system costs are reduced.

In the calculation 13, a statistical parking lot situation is determined on the basis of the real-time data record 12 for at least one of the cells 1 of the cell grid 2. A statistical parking space probability is preferably determined for the at least one cell 1, with the respective cell 1 being assigned a numerical value between 0 and 1, for example. The statistical parking space situation of the respective cell 1 is determined accordingly on the basis of the traffic data of the significant cells 3. A statistical method that is inverse to the main component analysis is used for the calculation. Because the real-time data record 12 is comparatively small, the statistical parking space situation can be calculated quickly and with less computational effort.

The sensor data record 14 is based on sensor data from sensors that register events relevant to parking spaces. In terms of sensor data, a distinction is made between stationary sensors, which register parking space occupancy at a location, and mobile sensors installed, for example, on motor vehicles, which detect parking space occupancy at the roadside. For the sensor data record 14 sensor data are used that are before the forecast time TP. The third time period T3 preferably begins 5 to 10 minutes before the prognosis time and collects the current image of the sensor data for the traffic area under consideration. The sensor data are recorded for all or a selection of cells 1, cell grid 2.

In the calculation 13, a sensor parking space situation is calculated on the basis of the sensor data record 14 for at least one of the cells 1 of the cell grid 2. A sensor parking space probability is preferably determined for at least one cell 1, a numerical value between 0 and 1 being assigned to the respective cell, for example. By using the current sensor data by calculating the sensor parking lot situation, the accuracy of the prognosis for available parking spaces can be improved because the actual situation is taken into account in addition to the statistical calculation.

The probability prognosis 15 for available parking spaces is carried out at the prognosis time TP on the basis of the statistical parking space situation and the sensor parking space situation. A suitable mathematical combination of the statistical parking space probability and the sensor parking space probability is preferably formed in the probability prognosis 15 for at least one cell 1 of the cell grid 2. This is preferably a suitably weighted mean. As a result, the statistical calculation can be corrected in a simple manner by the actually present parking lot situation detected by means of the sensors.
In an embodiment of the method according to the invention, which is not shown, it has a machine learning function in which a specific statistical parking lot situation is assigned to a specific sensor parking space situation. In particular, the traffic structure analysis 11, the calculation 13 and / or the probability prognosis 15 are adapted or corrected by the machine learning function. The machine learning function generates a mapping of the statistical parking space situation to the sensor parking space situation, the so-called training. For use at the time of the forecast, the trained model is applied to the current data situation.

A practical example of a machine learning function is that a correction factor is used in the probability prognosis 15 if there is a systematic difference between the statistical parking space probability and the sensor parking space probability. If, for example, it is established that the statistical parking space probability for a cell 1 is regularly twice as high as the sensor parking space probability, the statistical probability for this cell 1 is multiplied by a factor of 0.5.

Fig. 3 shows a schematic representation of an arrangement 20 and a mobile terminal 30 for forecasting available parking spaces. The arrangement 20 has a storage unit 21 which is designed to store the static data record 10 and to make it available for further calculation, for example the traffic structure analysis 11. In addition, the arrangement 20 has a real-time data processing unit 22, which is designed to determine the real-time data record 12 from the traffic data of the significant cells 3. For this purpose, the real-time data processing unit 22 is able to read out and evaluate the mobile radio data of the road users 6a, 6b, 6c who are located in the significant cells 3 in the second time period T2. When evaluating the mobile radio data, road users 6a, 6b, 6c in particular are identified on the basis of their movement characteristics. For example, vehicles 6a looking for a parking space can be identified on the basis of their acceleration and braking behavior. The arrangement 20 also has a sensor communication unit 23 which is set up to determine the sensor data record 14 from sensor data. For this purpose, the sensor communication unit 23 establishes a connection with the sensors present in the reference area and creates a sensor data record 14 immediately before the prognosis time TP. The traffic structure analysis 11, the calculation 13 and the probability prognosis 15 are carried out by means of a computing unit 24. The computing unit 24 is designed to identify the cells 1 of the cell grid 2 from the static data record 10 and the significant cells 3 of the cell grid 2 to select. In addition, the statistical parking space situation is calculated with the computing unit 24 on the basis of the real-time data record 12 and the sensor parking space situation is calculated on the basis of the sensor data record 14. The components of the arrangement 20 can be spatially separated or form a spatial unit. The arrangement 20 and / or the computing unit 24 is preferably a server.

The mobile terminal device 30 is connected to the arrangement 20 via a network 25. The mobile terminal 30 is, for example, a smartphone, a navigation device or on-board electronics of a motor vehicle. The mobile terminal device 30 is designed to communicate with the arrangement 20, in particular its computing unit 24, and to receive a forecast of the available spaces of at least one of the cells 1 of the cell grid 2 from the arrangement 20. The forecast received from the arrangement 20 is used by the mobile terminal 30 to reproduce the parking space situation and / or to carry out a navigation for the user of the mobile terminal 30.

In Fig. 4 a method is shown in which the forecast of available parking spaces is carried out by means of the arrangement 20 and the mobile terminal 30. First, a communication 40 is established or carried out between the mobile terminal 30 and the arrangement 20. During the communication 40 there is a transmission 41 of the forecast of available parking spaces for at least one of the cells 1 of the cell grid 2 from the arrangement 20 to the mobile terminal 30. Using 42 the forecast of available parking spaces, the parking space situation is reproduced by the mobile terminal 30 and / or used by means of the mobile terminal 30 to navigate a user. For example, the current position is recorded by the mobile terminal 30 and the parking space situation of the corresponding cell 1 and / or the neighboring cells 1 is represented by numerical values or color coding. This in Fig. 4 The method shown can be carried out by a program product or an app executed on the mobile terminal device 30.

Those looking for a parking space, cities and the environment all benefit from the procedure, the arrangement and the program product. Drivers get to their destination faster and more relaxed. Municipalities optimize traffic and thus increase the attractiveness of inner cities for residents, trade and tourism. In addition, the air is less polluted with pollutants.

List of reference symbols:

1

cell

2

Cell grid

3

significant cell

4th

parking spot

5

road

6a

Road user / vehicle (looking for a parking space)

6b

Road users / vehicles (not looking for a parking space)

6c

Road users / pedestrians

10

static data set

11

Traffic structure analysis

12th

Real-time data set

13th

calculation

14th

Sensor data set

15th

Probability forecast

20th

arrangement

21

Storage unit

22nd

Real-time data processing unit

23

Sensor communication unit

24

Computing unit

25th

network

30th

mobile device

40

communication

41

Transmission of the forecast

42

Use (playback / navigation)

T1

first period

T2

second period

T3

third period

TP

Forecast time

Claims (15)

Method for forecasting available parking spaces, comprising the following steps carried out by means of a computing unit (24): - A traffic structure analysis (11) in which significant cells (3) are selected from cells (1) of a cell grid (2) on the basis of a static data set (10) formed by traffic data from a first time period (T1); - A calculation (13) in which, on the basis of a real-time data record (12) formed by traffic data from the significant cells (3) from a second second space (T2), a statistical parking space situation for at least one of the cells (1) of the cell grid (2) , in particular a statistical parking space probability, is determined, and - in which, on the basis of a sensor data set (14) formed by sensor data from the cells (1) from a third period (T3), a sensor parking space situation, in particular a sensor parking space probability, is determined for at least one of the cells (1) of the cell grid (2); and - A probability prognosis (15) in which a prognosis of available parking spaces is carried out for at least one of the cells (1) of the cell grid (2) on the basis of the statistical parking space situation, in particular the statistical parking space probability, and the sensor parking space situation, in particular the sensor parking space probability. Method for forecasting available parking spaces according to Claim 1, characterized in that during the traffic structure analysis (11) the cells (1) of the cell grid (2) are identified on the basis of the static data set (10), in particular where the size, shape and / or The position of the cells (1) can be determined on the basis of the vehicle density, road density and / or parking lot density. Method for forecasting available parking spaces according to Claim 1 or 2, characterized in that the selection of the significant cells (3) takes place on the basis of a principal component analysis of the static data set (10), or another mathematical method for dimensional reduction. Method for forecasting available parking spaces according to one of the preceding claims, characterized in that during the traffic structure analysis (11) explicit framework conditions are linked with a statistical evaluation, in particular where the framework conditions are, for example, that the overall balance of vehicles with a suitable choice of reference area and time interval is equal to zero, that the change in traffic is continuous, that the transport capacity of a road segment has an upper limit, and / or that the available parking space of a road segment has an upper limit. Method for forecasting available parking spaces according to one of the preceding claims, characterized in that the static data set (10) and the real-time data set (12) are based on traffic data obtained from mobile radio data, in particular whereby road users are identified on the basis of their movement characteristics, and In particular, vehicles looking for parking spaces are identified on the basis of their acceleration and braking behavior. Method for forecasting available parking spaces according to one of the preceding claims, characterized in that the static data record (10) is available offline, in particular wherein the statistical data record (10) comprises a reference area which is defined by the cells (1) of the cell grid (2 ) is completely covered. Method for forecasting available parking spaces according to one of the preceding claims, characterized in that the sensor data set (14) is created on the basis of sensors that register events relevant to parking spaces, for example the sensors are floor sensors, vehicle-based sensors, distance meters, cameras and / or infrastructure sensors. Method for forecasting available parking spaces according to one of the preceding claims, characterized in that the time periods (T1, T2, T3) are different, the first period (T1) being before the second period (T2) and the third period (T3) , in particular wherein the second time period (T2) is before the third time period (T3). Method for forecasting available parking spaces according to one of the preceding claims, characterized in that in the probability prognosis (15) a mean value is formed from the statistical parking space probability and the sensor parking space probability. Method for forecasting available parking spaces according to one of the preceding claims, characterized in that the method has a machine learning function in which a specific statistical parking space situation is assigned to a specific sensor parking space situation, in particular the traffic structure analysis (11), the calculation (13) and / or adjust and / or correct the probability prognosis (15). Method for forecasting available parking spaces according to Claims 9 and 10, characterized in that a correction factor is used in the probability prognosis (15) if there is a systematic difference between the statistical parking space probability and the sensor parking space probability. Arrangement (20) for forecasting available parking spaces, comprising - A storage unit (21) which is designed to store a static data set (10) formed by traffic data from a first time period (T1); - A real-time data processing unit (22) which is designed to determine a real-time data set (12) from a second second space (T2) using traffic data from significant cells (3); - A sensor communication unit (23) which is designed to determine a sensor data set (14) from sensor data from a third time period (T3); and a - Computer unit (24) which is designed to carry out the method steps of claim 1. Method for forecasting available parking spaces, comprising the following steps carried out by means of a computing unit (24) and a mobile terminal (30): - Communication (40) of a mobile terminal (30) with the computing unit (24) of an arrangement (20) according to claim 12; - Transmission (41) of the forecast of available parking spaces for at least one of the cells (1) of the cell grid (2) from the computing unit (24) to the mobile terminal (30); - Use (42) of the forecast of available parking spaces for at least one of the cells (1) of the cell grid (2) to reproduce a parking space situation and / or to navigate a user of the mobile terminal (30). Mobile terminal (30) for forecasting available parking spaces, which is designed for this purpose - to communicate with an arrangement (20) from claim 12; - Retrieve from the arrangement (20) the forecast of available parking spaces for at least one of the cells (1) of the cell grid (2); and - To use the retrieved forecast for at least one cell (1) of the cell grid (2) to reflect a parking space situation and / or for the navigation of the user of the mobile terminal (30). Computer program product which, when the program is executed by a mobile terminal (30), causes the latter to carry out the steps of the method according to Claim 13.

Images