Access control device; method for controlling access to persons to a restricted access area; computer program product

Abstract

The invention relates to an access control device (1) for granting and blocking access by at least one person (10) to an access-restricted area, depending on the access authorization of the person (10), with at least one virtual lock (5) and / or with at least one physical lock (5) and a control unit (2), wherein the control unit (2) is configured and set up to receive an access authorization certificate (30) from a certificate issuer (3) for verifying the access authorization. The invention further relates to a method for access control of persons (10) to an access-restricted area.

Description

[0001] The invention relates to an access control device for releasing and blocking the access of at least one person to a restricted area depending on an access authorization of the person with at least one virtual lock and / or with at least one physical lock and a control unit, wherein the control unit is designed and configured to receive an access authorization proof from a proof provider for checking the access authorization.

[0002] Such devices are used in areas with restricted access, for example at airports, train stations or hotels, or as an access solution for a building or area.

[0003] The object of the present invention is to provide an improved access control device which enables flexible access authorization for several persons based on a single access authorization certificate.

[0004] The object is achieved by an access control device according to claim 1, a method according to claim 14 and a computer program product according to claim 15.

[0005] In particular, the object can be achieved in that the access control device for releasing and blocking the access of at least one person to a restricted area depending on an access authorization of the person with at least one virtual lock and / or with at least one physical lock and a control unit, wherein the control unit is designed and configured to receive an access authorization certificate from a certificate provider for checking the access authorization, wherein a specific number of persons authorized to access is assigned to the access authorization certificate, wherein the number is greater than 1.

[0006] In particular, the control unit can obtain the access authorization credential by receiving, reading, and / or retrieving the access authorization credential from the credential provider. In particular, the access authorization verification can be performed by processing the access authorization credential by the control unit, in particular by comparing it with a database and / or decrypting it.

[0007] In other words, the specific number of authorized access persons is at least 2, who are assigned to a single access authorization credential. Preferably, the specific number is 2 to 30, in particular 2 to 20, in particular 2 to 10, in particular 3, 4, 5, 6, 7, 8, or 9, of authorized access persons assigned to a single access authorization credential.

[0008] This allows multiple people to be granted flexible access to a restricted area with minimal data and / or organizational and / or personnel expenditure, without each person needing their own access authorization credential. This eliminates the need to obtain data from each person and eliminates the need to create access authorization credentials for each person. However, since at least one person in a group of people must have a valid access authorization credential to be granted access, a high level of security is guaranteed. A group of people refers to a group of people for whom access can be granted using a single access authorization credential.

[0009] The term "virtual barrier" refers to a barrier that uses an acoustic and / or optical signal. In particular, the signal can be perceptible from the immediate and / or distant surroundings, allowing for easy monitoring.

[0010] The term "physical barrier" refers to a barrier that is capable of physically blocking access. In particular, the physical barrier can be one of the following: a rotating arm barrier; a turnstile; one or more rotating swing leaves, in particular door leaves; one or more sliding sliding leaves, in particular door leaves.

[0011] Release can occur in such a way that the control unit issues a release signal, which causes the physical barrier to unlock. Alternatively or cumulatively, the release signal can initiate an active opening of the physical barrier. For this purpose, at least one, in particular electromechanical drive, in particular a door drive, can be arranged, which is designed and configured to move the physical barrier, in particular to open and close the barrier.

[0012] A rotating arm barrier is known, for example, from EP 0 718 460 B1. A turnstile is known, for example, from EP 0 655 546 A2. Rotating arm barriers have one, two, three or more physical arms which are rotatably mounted on a housing and are designed to block or open access. In particular, with rotating arm barriers the axis of rotation can be inclined relative to a vertical axis. Rotating arm barriers have the advantage of being space-saving. Turnstiles have two or more barrier wings, which can comprise several arms which are arranged on a rotating column forming the axis of rotation. The rotating column is arranged vertically. Turnstiles can be designed to be person-high, so that a high degree of security for passage can be provided.

[0013] Designing the physical barrier as a rotating arm barrier or turnstile offers the advantage of allowing a count of the number of people passing through the access control device based on the rotations of the rotating arm barrier or turnstile. This allows for a mechanical count of the people passing through the barrier and, at the same time, for a blocking of the barrier by locking the rotating arm barrier or turnstile after the specified number of rotations.

[0014] In particular, the access control device can comprise one or two or more access-limiting elements. In particular, the access-limiting element can be configured as a housing. In particular, the physical barrier can be mounted on the access-limiting element. Alternatively or additionally, the virtual barrier can be displayed or sounded on the access-limiting element.

[0015] In an advantageous embodiment, the barrier can be arranged at a wall outlet of a building for entry into the building. The access control device can thus comprise a door system, in particular an at least partially automated one, as the barrier.

[0016] Rotatable hinged doors or sliding doors offer the advantage of easy automation, for example, via a drive. Rotatable door leaves have the advantage of saving space.

[0017] Alternatively or cumulatively, in the case of the virtual barrier, the release signal can be sounded and / or displayed visibly.

[0018] A combination of a virtual and a physical barrier can further increase the security of the access control device.

[0019] Overall, this need for flexible access by multiple people arises in all areas where group tariffs or, for example, accompanying persons are used. In such cases, it is advantageous if a single access authorization card can be assigned to multiple authorized persons.

[0020] Preferably, the control unit is designed and configured to receive, in particular process, an input of a desired number of people for the respective access authorization. Once a specific number has been determined for the respective access authorization, it is advantageous if the actual number of people desired for the respective access can be entered. This can minimize unintentional or unauthorized access.

[0021] A request for input can also be made cumulatively. In particular, the person can be informed of the specific number, particularly visually and / or acoustically. If the number entered is less than or equal to the specific number, the entered number can be approved. If no input is made, particularly within a certain period of time, the desired number can be automatically set to a single person. Alternatively, if no input is made, access can be blocked until the input is made. In particular if no input is made, an intensified request for the necessary input can be made, e.g. through visual and / or haptic and / or acoustic signals.

[0022] If the requested number exceeds the specified number, an error message may be displayed and / or a valid entry may be requested. Alternatively or cumulatively, a request for confirmation and / or payment for the additional number of people may be made.

[0023] This enables flexible, automated access with minimal or no personnel required at the access control device.

[0024] Preferably, an input device is designed and configured to enter a desired number of persons for the respective access authorization, wherein the input device is designed as part of the access control device and / or as part of an access authorization carrier to be carried by the person.

[0025] The access authorization carrier can be designed to carry the access authorization credential or information associated with the access authorization credential. The access authorization carrier can include the credential provider.

[0026] If the input device is implemented as part of the access control device, input can be made conveniently at the access control device itself. Conversely, if the input device is implemented as part of the access authorization carrier, the need for an additional input device can be omitted, thus saving components. In particular, if the access authorization carrier is designed as a smartphone, input can also be made conveniently and with fewer components. Combining both variants leaves it up to the user to decide where to make the input, which enables particularly user-friendly operation.

[0027] The input and / or the input device can be designed interactively. The input device can also comprise an output device for outputting information. This allows the person to be guided through the input. The input device can be designed as a display with input options, in particular as a touch display. The input device can comprise a microphone so that the input can also be made acoustically, in particular by voice input. In particular, the output device can comprise a loudspeaker for outputting acoustic information and / or instructions. This creates various input options, even for visually impaired and / or hearing-impaired people.In particular, the input options can be limited to the maximum possible number of authorized persons for the respective access authorization credential, whereby smaller numbers than the maximum possible number of persons can also be made available for selection. The maximum possible number can correspond to the specified number.

[0028] Preferably, the access control device has an output device which outputs the number of currently remaining persons authorized to access, in particular by means of acoustic and / or optical signals.

[0029] Preferably, the type of issue may depend on the access authorization proof.

[0030] Preferably, the access control device is designed and configured, in the event of a positive access authorization, to grant access to the number of authorized persons assigned to the respective access authorization credential or to the desired number of persons. In particular, the granting of access can be limited to a defined time limit, particularly from the start of the granting. This minimizes unauthorized access by persons not belonging to a group of persons.

[0031] For this purpose, the access control device can comprise a controller for controlling the barrier. The barrier is preferably controlled by moving it into a release position.

[0032] Alternatively or cumulatively, however, the barrier can be controlled by unlocking and / or removing a locking mechanism of the barrier, so that the barrier can be passed, in particular by means of a slight physical contact.

[0033] After the specified or desired number of people have passed, access should be blocked again.

[0034] Preferably, the access control device comprises a sensor unit with at least one sensor, which is designed and configured to count persons who pass through the access control device.

[0035] A sensor unit for counting passing persons is known, for example, from EP 3 680 814 A1.

[0036] The sensor unit can comprise a detection zone that lies at least partially in front of the barrier in the direction of entry and / or at least partially behind the barrier in the direction of entry. The sensor unit can thus detect, in particular track, one or more persons. When the detected person(s) leave the detection zone in the direction of the entrance, i.e., in the direction of entry, the sensor unit can count the number of persons who have entered. The counted number of persons who have entered can be reported to the control unit, so that further access can be granted or blocked depending on the counted number.

[0037] Preferably, the counting of passing people is carried out using an artificial intelligence system. Alternatively, or cumulatively, the counting of passing people can be supported by an artificial intelligence system.

[0038] The artificial intelligence system is abbreviated here as AI system.

[0039] In particular, the access control device may include the AI ​​system. The AI ​​system may be located within the access control device, near the access control device, or remotely from the access control device.

[0040] According to one embodiment of the present invention, the AI ​​system may comprise and / or implement a machine learning system, a deep learning system, a neural network, contour detection, and / or pattern recognition. The AI ​​system serves to reliably recognize individuals.

[0041] In one embodiment, the AI ​​system includes an underlying machine learning model. Suitable machine learning models are based on a convolutional neural network (CNN) or a recurrent neural network (RNN), or a combination thereof. CNNs and RNNs are both types of deep learning algorithms commonly used in machine learning applications. A CNN is a type of neural network particularly well-suited for image and video recognition tasks.

[0042] Generally, a CNN uses convolutional layers to extract features from input data, followed by pooling layers to reduce the dimensionality of the feature maps. The output of the convolutional and pooling layers is then flattened and fed into one or more fully connected layers, which are responsible for the final classification decision. The main advantage of CNNs is their ability to automatically learn hierarchical representations of input data, making them very effective at detecting complex patterns in images and videos.

[0043] An RNN, on the other hand, is a type of neural network particularly well-suited for sequential data, such as time series or natural language. An RNN uses recurrent connections to pass information from one time step to the next. This allows the network to maintain an internal state or memory for previous inputs, which is useful for tasks such as speech recognition or language translation. The main advantage of RNNs is their ability to capture temporal dependencies in the input data, making them very effective at modeling sequential data.

[0044] A key difference between CNNs and RNNs is that CNNs are designed to process input data of fixed size (e.g., fixed-resolution images), while RNNs can process input data of variable length (e.g., sequences of different lengths). Another difference is that CNNs are better suited for tasks that involve spatial information (e.g., image classification), while RNNs are better suited for tasks that involve temporal information (e.g., speech recognition).

[0045] In one embodiment of the present invention, a combination of CNNs and RNNs can be provided, since both spatial and temporal information are important for video recognition tasks. A CNN can be used to extract spatial features from each frame of the video, which are then fed into an RNN to model the temporal dependencies between frames.

[0046] The machine learning model can be trained on a large dataset of labeled examples, where each example consists of a time series of data points and a corresponding label indicating the person type. The training data is used to adjust the model's weights and biases so that it can accurately classify new, unseen examples. The training process typically involves an iterative approach, where the model is presented with a set of training examples and the weights and biases are adjusted to minimize the difference between the predicted output and the actual label. This process is repeated over many epochs until the model has learned to accurately classify a person in the training data.

[0047] The type of artificial intelligence that can be used in this context is typically supervised learning, where the model is trained on a labeled dataset. However, unsupervised learning approaches such as clustering and anomaly detection can also be used within the scope of the present invention, for example, to populate the aforementioned database.

[0048] Certain embodiments of the invention may be based on the use of a machine learning model or a machine learning algorithm. Machine learning may refer to algorithms and statistical models that computer systems can use to perform a specific task without explicit instructions, relying instead on models and inferences. For example, instead of a rule-based transformation of data, machine learning may use a transformation of data derived from an analysis of historical and / or training data. For example, the content of images may be analyzed using a machine learning model or a machine learning algorithm. In order for the machine learning model to analyze the content of an image, the machine learning model may be trained with training images as input and training content information as output.By training the machine learning model with a large number of training images and / or training sequences (e.g., words or sentences) and associated training content information (e.g., labels or annotations), the machine learning model "learns" to recognize the content of the images, allowing the content of images not included in the training data to be recognized using the machine learning model. The same principle can also be used for other types of sensor data: By training a machine learning model with training sensor data and a desired output, the machine learning model "learns" a transformation between the sensor data and the output, which can be used to provide an output based on non-training sensor data provided to the machine learning model. The provided data (e.g.,Sensor data, metadata, and / or image data) can be preprocessed to obtain a feature vector that is used as input to the machine learning model.

[0049] Machine learning models can be trained using training data. In the examples above, a training method called "supervised learning" is used. In supervised learning, the machine learning model is trained using a large number of training samples, where each sample can include a large number of input data values ​​and a large number of desired output values, meaning that each training sample is associated with a desired output value. By specifying both training samples and desired output values, the machine learning model "learns" what output value it should produce based on an input sample that is similar to the samples provided during training. In addition to supervised learning, semi-supervised learning can also be used. In semi-supervised learning, some of the training samples lack a corresponding desired output value.Supervised learning can be based on a supervised learning algorithm (e.g., a classification algorithm, a regression algorithm, or a similarity learning algorithm). Classification algorithms can be used when the output values ​​are restricted to a limited set of values ​​(categorical variables), meaning the input is assigned to one of the limited set of values. Regression algorithms can be used when the outputs can have any numerical value (within a range). Similarity learning algorithms can be similar to both classification and regression algorithms, but are based on learning from examples using a similarity function that measures how similar or related two objects are. In addition to supervised or semi-supervised learning, unsupervised learning can also be used to train the machine learning model.In unsupervised learning, (only) input data can be provided, and an unsupervised learning algorithm can be used to find structure in the input data (e.g., by grouping or clustering the input data, finding commonalities in the data). Clustering is the assignment of input data, which includes a large number of input values, to subsets (clusters) such that input values ​​within the same cluster are similar according to one or more (predefined) similarity criteria, while differing from input values ​​contained in other clusters. Reinforcement learning is a third group of machine learning algorithms that can be used to train the machine learning model. In reinforcement learning, one or more software actors (so-called "software agents") are trained to perform actions in an environment.A reward is calculated based on the actions performed. In reinforcement learning, one or more software agents are trained to choose actions in such a way that the cumulative reward increases, resulting in the software agents becoming increasingly better at completing the task assigned to them (which translates into increasing rewards).

[0050] Furthermore, some techniques can be applied to some machine learning algorithms. For example, feature learning can be used. In other words, the machine learning model can be trained at least partially using feature learning and / or the machine learning algorithm can include a feature learning component. Feature learning algorithms, which can also be called representation learning algorithms, can preserve the information in their inputs but also transform it to make it useful, often as a preprocessing step before performing classification or prediction. Feature learning can be based on, for example, principal component analysis or cluster analysis.

[0051] In particular, the AI ​​system can be designed and configured, especially trained, to identify human characteristics from the sensor data, especially to separate them, and to assign these characteristics to a single person. This allows the number of detected persons to be determined. Thus, the people passing by can be reliably counted. The human characteristics can be limited to the person's lower extremities. The human characteristics can be implemented as parts of a person pattern to be recognized by the AI ​​system. This allows the process to be automated.

[0052] Preferably, the sensor unit is designed and configured to distinguish people from other objects. This can advantageously be done with the help of the described AI system.

[0053] In particular, Suitcases can be recognized based on one or more suitcase patterns learned in the AI ​​system and / or bags based on one or more bag patterns learned in the AI ​​system and / or pets can be recognized based on one or more pet patterns learned in the AI ​​system and thus distinguished from the persons authorized to access the system.

[0054] The detection of suitcases or bags allows you to count luggage or block it from access to restricted areas. Pet detection is also advantageous for many applications where pets are not allowed in restricted areas or are limited in number.

[0055] In further embodiments, these described objects can also be counted and controlled by the access control device.

[0056] In one embodiment of the invention, a wheelchair or other type of walking aid can be recognized based on one or more wheelchair and / or walking aid patterns learned in the AI ​​system. This information can then be processed, for example, to request assistance and / or to control the barrier accordingly.

[0057] In particular, the patterns mentioned may include one or more associated features.

[0058] Preferably, the counting of passing people is based on the detection of human legs, especially human feet. This detection includes the detection of shoes. This can be advantageously achieved with the help of the AI ​​system. This eliminates data protection considerations during the recording process, as no personal data can be evaluated; instead, people can be detected based solely on their lower extremities. Furthermore, the sensor of the sensor unit can be positioned at a low height, starting from the floor.

[0059] Preferably, the sensor of the sensor unit can be arranged at a low height starting from a floor, with people passing through the access control device via this floor. The sensor is preferably arranged at a maximum height of 1.5 meters, in particular 1.3 meters, in particular 1 meter, in particular 0.7 meters, in particular 0.5 meters, 0.3 meters, in particular 0.1 meters above the floor. This ensures that the access control device according to the invention can fulfill its function even in a low design. In particular, the detection range of the sensor unit can extend up to the specified height. Preferably, the specified detection range does not permit any personal detection. Preferably, the detection range only permits the detection of anonymized characteristics for counting the number of people. This can dispel data protection concerns regarding the collection of personal data.

[0060] The sensor is preferably designed as a 2D or 3D camera. A 2D camera is advantageous because it captures less data, but in conjunction with an AI system, this is still sufficient to reliably detect a person. 3D cameras have the advantage of providing more detail, allowing more details to be recognized when processing the data.

[0061] Alternatively, the separation sensor can be designed as a time-of-light sensor or lidar sensor or stereo camera.

[0062] A time-of-light sensor is based on a time-of-flight measurement. A lidar sensor is based on a time-of-flight measurement, particularly using pulsed laser beams. With a stereo camera, the environment is recorded simultaneously with two cameras positioned at a distance, specifically the eye distance, from each other.

[0063] The sensor unit preferably comprises an image processing unit for processing the sensor data. The image processing unit can, in particular with the aid of an AI system, create a 3D view from the sensor data and thus contribute to increased reliability in the detection and / or counting of people.

[0064] Preferably, the sensor unit is designed and configured to track the person within a detection range of the sensor unit, in particular continuously, so that access to the restricted area by the person can be detected by the sensor unit. This tracking of the person can preferably be supported and / or carried out with the aid of an AI system.

[0065] The sensor unit comprises a detection area that lies at least partially in front of the barrier in the direction of entry and / or behind the barrier in the direction of entry. The sensor unit can thus detect and track one or more people. This can advantageously be done with the help of the AI ​​system. The AI ​​system can set a feature marker for this purpose, which is recognizable in the sensor data. If the detected person or people leave the detection area in the direction of the entrance, i.e. in the direction of entry, the sensor unit can count the access of the person or people. The counted number can be reported to the control unit so that further access can be granted or blocked depending on the counted number and the determined number and / or the desired number.If the person leaves the detection area in the direction of the exit, i.e. in the direction of exit, a person leaving the restricted access area can also be detected.

[0066] In particular, the sensor can be arranged such that its detection range encompasses an area in front of the barrier in the direction of entry and an area behind the barrier in the direction of entry. This allows for even more reliable detection of access, particularly by reporting it to the control unit. This also allows for reliable detection of people exiting the restricted area.

[0067] Alternatively or cumulatively, the sensor unit can include another sensor whose detection range lies behind the barrier in the direction of entry, so that access by the person can be reliably detected and, in particular, reported to the control unit. Preferably, this tracking of the person can be supported and / or carried out with the help of an AI system. This also allows people exiting the restricted area to be reliably detected.

[0068] The access control device can preferably be designed to be bidirectionally passable. This means that the access control device can also allow people exiting the restricted-access area to pass through. In particular, people exiting the restricted-access area can be counted using the sensor unit described above. Alternatively or additionally, a further access control device can be provided to count exiting people. This allows the current total occupancy of the restricted-access area to be determined.

[0069] Preferably, the specific number of persons authorized to access the restricted area can be made dependent on a time of day and / or an occupancy status, in particular the total occupancy.

[0070] The sensor unit is preferably designed and configured to detect so-called tailgating. Tailgating refers to an attempt by at least two people to pass through an access control device simultaneously. In other words, tailgating involves an attempt by multiple people to use the access authorization for a single person by merging the accesses of the at least two people into one access. Upon detection of tailgating, the access control device can block access and / or trigger an acoustic and / or visual alarm and / or an error message. This allows anti-tailgating to occur. Tailgating can preferably be reliably detected by the AI ​​system. This allows the process to be automated.

[0071] Tailgating can be detected based on one or more tailgating patterns learned in the AI ​​system. For example, tailgating can be detected when legs assigned to different people are separated by too little or no distance. The distance can be defined in advance. The pattern can include multiple tailgating characteristics.

[0072] Alternatively, a tailgating attempt can be detected and allowed or no alarm and / or error message is issued if the number of people still authorized to access is greater than or equal to the number of people participating in the tailgating attempt.

[0073] Preferably, a data record about the specific number of persons authorized to access assigned to the access authorization proof is stored in a data memory of the access control device, in particular the control unit, and / or in a data memory of the proof provider.

[0074] One advantage of the memory on the access control device is the secure storage of the data, so that manipulation of the data can be ruled out with a high degree of certainty.

[0075] However, storing data directly on the verifier can also offer the advantage that the data set can be flexibly adapted depending on a purchase made on the smartphone, particularly a wallet purchase, when using a smartphone as the access authorization carrier and the verifier as part of the access authorization carrier. A wallet is a virtual wallet on a standard Apple or Android device, where purchases made can be stored in the wallet in a tamper-proof manner.

[0076] Alternatively, the data set may be stored in a data storage device remote from the access control device, in which case the access control device, in particular the control unit, and / or the verification device is configured and designed to query the data set from the remote data storage device.

[0077] Preferably, the verification device is designed as part of the control unit or as part of an access authorization carrier carried by the person. If the verification device is designed as part of the access authorization carrier, the access authorization carrier can be configured, for example, as a smartphone and can obtain access authorization via wireless networks. This enables decentralized administration and control of such an access control device. If the access control device is located in a remote location with poor or nonexistent data connectivity, such a decentralized solution offers a beneficial solution.

[0078] Preferably, the access authorization credential to be read by the person providing the access authorization is associated with a data set of an access authorization carrier carried by the person and / or with the person's identity. The access authorization carrier can be implemented as a smartphone and / or a QR code and / or a barcode and / or a ticket.

[0079] On the other hand, the correct access authorization credential and thus also the specific number can be read simply by recognizing the person's identity, for example through facial recognition and / or retina recognition and / or fingerprint recognition.

[0080] Almost all signals and / or data sets and / or data described here can be transmitted and / or received, preferably wirelessly or wired. The wireless design allows for flexible transmission without the need to lay cables. Wired transmission, on the other hand, is characterized by data security and tamper resistance.

[0081] In particular, the transmission between the verification provider and the control unit can be wireless. Alternatively or cumulatively, the transmission between the access authorization carrier and the verification provider and / or the control unit can be wireless.

[0082] For example, ultra-wideband (UWB) technology can be used for wireless transmission. UWB utilizes a wide spectrum, specifically a frequency bandwidth of more than 500 MHz. It can tolerate overlaps with other frequency bands because it uses lower power levels. Due to its wide spectrum, UWB can achieve high data rates, specifically several gigabits per second. UWB technologies are power-efficient, especially compared to other wireless connections, making them sustainable and advantageous for battery-operated devices. UWB can be used to determine a device's position with an accuracy of up to a few centimeters. This is a critical advantage for real-time location systems and Internet of Things (IoT) applications. UWB signals can penetrate physical barriers better than conventional wireless technologies.This is especially useful in densely built-up areas where conventional signals may be blocked.

[0083] A further object of the present invention is a system comprising the access control device and at least one access authorization carrier.

[0084] Another object of the present invention is a method for controlling access of persons to a restricted area comprising the following steps: Reading an access authorization certificate from a certificate provider; determining a specific number of authorized persons assigned to the access authorization certificate, where the number is greater than 1; controlling a virtual lock and / or a physical lock depending on the determined number of authorized persons.

[0085] The method according to the invention is in particular a computer-implemented method in which one, several or all steps of the method are carried out in a computer-implemented manner.

[0086] The method is preferably carried out using the access control device according to the invention. In particular, the individual components of the access control device can be controlled by computer implementation.

[0087] A further subject matter of the present invention is a computer program product, wherein the computer program product comprises instructions which, when the computer program product is executed by a computer, in particular a preferably electronic control device of the access control device, cause the computer to execute a method according to an embodiment of the present invention. The computer is preferably designed partially or entirely as part of the access control device and / or partially or entirely external to the access control device. The computer is preferably designed to control the lock and / or the sensor unit and / or the input device and / or the output device. It is conceivable that the computer is a single computer device or that the computer comprises several distributed computer devices.The plurality of computer devices can in particular be arranged at different locations, for example partly as part of the access control device and partly as part of a monitoring device for security personnel.

[0088] Another subject matter of the present invention is a computer-readable storage medium comprising a computer program product according to an embodiment of the present invention.

[0089] For the method according to the invention, the computer program product according to the invention and the computer-readable storage medium according to the invention, the features, embodiments and advantages that have already been described in connection with the access control device according to the invention or in connection with an embodiment of the lock according to the invention can be applied.

[0090] Further advantages and details of the invention will be explained below with reference to the exemplary embodiments illustrated in the figures. Herein: Fig. 1 is a schematic representation of an access control device according to a first embodiment of the present invention; Fig. 2 is a representation of an input device; Fig. 3 is a perspective representation of an access control device according to the invention.

[0091] The reference symbols are used, as far as possible, with the same designation in all figures.

[0092] The Figure 1shows an access control device 1 according to the invention with two rotatable wings as barriers 5. The barriers are each rotatably mounted on a housing 7 and can each be rotated by means of a drive 11 depending on an access authorization and can thus block or open access. A person 10 stands in front of the access control device 1 in the access direction and carries an access authorization carrier 100 in the form of a smartphone. In this example, the verification device 3 is designed as part of the access authorization carrier 100 and delivers an access authorization certificate 30 to a control unit 2, which receives and checks the access authorization certificate 30. The control unit 2 is designed in this example as part of the access control device 1. The control unit 2 is arranged on site at the access control device 1, but in other embodiments can be arranged remotely from the physical barrier 5.In other embodiments, the detection device 3 can be formed as part of the control unit 2.

[0093] The access control device 1 has a combined input device 4 with an output device 40, which in Figure 2 is shown in detail and is designed as a touch display on the housing 7. Furthermore, a sensor unit 6 with an image processing unit 8 and an AI system 9 is arranged on the housing 7. In other embodiments, the installation location of the image processing unit 8 and the AI ​​system 9 can be arranged remotely from the physical barrier 7.

[0094] When checking the access authorization certificate 30 of person 10, it was determined that a certain number of three authorized persons are assigned to the access authorization certificate 30. Therefore, the combined input device 4 with an output device 40 displays the representation of the Figure 2The upper number 3 indicates the maximum permitted number and prompts the person to select one of the numbers 1, 2, or 3 as the desired number of people to grant access to that number. Meanwhile, the sensor unit 6 detects objects within its detection range. With the help of the AI ​​system 9, it detects and tracks the number of people within its detection range.

[0095] If the person now selects the number 2 on the input device 4, the sensor unit 6 counts the people who pass through the barrier 7 in the direction of entry. As soon as the following persons 10a, 10b enter the detection range of the sensor unit 6, they are also detected. If first person 10 and then person 10a have passed through the access control device 1 or the barrier 7 in the direction of entry, the control unit 2 would initiate a blocking of access. In this case, this can be done both by immediately closing the barriers 5 and by means of the output device 40, which indicates that further attempted access by person 10b is not permitted without another received access authorization credential 30. This can also be supported by acoustic signals.Immediately after person 10 passes, the output device 40 displays only the number 1, indicating the number of persons currently authorized to access the facility. This makes it clear to the following person 10a that only one person is authorized to access this facility.

[0096] The sensor unit 6 with the AI ​​system 9 is further designed and configured to detect tailgating, for example, by persons 10a, 10b, and to block or unlock access depending on the number of persons currently still authorized to access. In the described procedure, for example, a block could occur because after person 10 has passed, only one person is still authorized to access, but tailgating is detected for persons 10a, 10b. A corresponding notification can be issued via the output device 40. If tailgating is no longer detected for this person, access can be granted again for person 10a.

[0097] In addition, access can be granted subject to predefined time limits.

[0098] The Figure 3 shows a perspective view of an access control device 1 according to Figure 1with a freely accessible area 14, an entry direction 15, and an access-restricted area 16. Furthermore, a sensor 60 is arranged as part of the sensor unit 6, which comprises a detection area that at least partially comprises an area in the entry direction 15 in front of the barrier 5 and an area behind the barrier 5. This enables reliable detection of completed passages and thus a counting of the people passing through by the sensor unit 6. List of reference symbols

[0099] 1Access control device 2Control unit 3Certifier 4, 40Input device / Output device 5Lock 6Sensor 7Housing 8Image processing unit 9AI system 10Person 10a, 10bAnother person 11Drive 14Freely accessible area 15Entry direction 16Restricted access area 30Access authorization proof 60Sensor 100 access authorization carriers

Claims

1. Access control device (1) for enabling and blocking access of at least one person (10) to a restricted access area (16) depending on an access authorization of the person (10) with at least one virtual lock and / or with at least one physical lock (5) and with a control unit (2), wherein the control unit (2) is designed and configured to receive an access authorization proof (30) from a proof provider (3) for checking the access authorization, characterized in that a specific number of persons (10) authorized to access is assigned to the access authorization proof (30), wherein the number is greater than 1.

2. Access control device according to claim 1, wherein the control unit (2) is designed and configured to receive an input of a desired number of persons (10) for the respective access authorization.

3. Access control device according to claim 2, wherein an input device (4, 40) is designed and configured to input the desired number of persons (10) for the respective access authorization, wherein the input device is designed as part of the access control device and / or as part of an access authorization carrier (100) to be carried by the person (10).

4. Access control device according to one of the preceding claims, wherein the access control device (1) is designed and configured, in the case of a positive access authorization, to release access for the number of authorized persons (10) assigned to the respective access authorization proof (30) or for the desired number of persons (10).

5. Access control device according to one of the preceding claims, comprising a sensor unit (6) with at least one sensor (60) which is designed and configured to count persons (10) passing through the access control device (1).

6. Access control device according to claim 5, wherein the counting of the passing persons (10) is supported and / or carried out with the aid of an artificial intelligence system (9).

7. Access control device according to one of the preceding claims 5 or 6, wherein the sensor unit (6) is designed and configured to distinguish persons (10) from other objects.

8. Access control device according to one of the preceding claims 5 to 7, wherein the counting of the passing persons (10) is based on a detection of human legs, in particular human feet.

9. Access control device according to one of the preceding claims 5 to 8, wherein the sensor (60) is designed as a 2D camera or 3D camera.

10. Access control device according to one of the preceding claims 5 to 9, wherein the sensor unit (6) is designed and configured to track the person (10) in a detection area of ​​the sensor unit (6), in particular continuously, so that access to the restricted area by the person (10) can be detected by the sensor unit (6).

11. Access control device according to one of the preceding claims 5 to 10, wherein the sensor unit (6) is designed and configured to detect tailgating.

12. Access control device according to one of the preceding claims, wherein a data record about the specific number of persons (10) authorized to access assigned to the access authorization proof (30) is stored in a data memory of the access control device (1), in particular the control unit (2), and / or in a data memory of the proof transmitter (3).

13. Access control device according to one of the preceding claims, wherein the verification device (3) is designed as part of the control unit (2) or as part of an access authorization carrier (100) to be carried by the person (10).

14. A method for controlling access of persons (10) to a restricted area, comprising the following steps: - receiving an access authorization certificate (30) from a certificate provider (3); - determining a specific number of persons (10) authorized to access that is assigned to the access authorization certificate (30), wherein the number is greater than 1; - controlling a virtual barrier and / or a physical barrier (5) depending on the determined number of persons (10) authorized to access.

15. A computer program product, wherein the computer program product comprises instructions which, when the computer program product is executed by a computer, in particular a preferably electronic control device of the access control device, cause the computer to execute a method according to claim 14.

Images