Monitoring system, method for operating the monitoring system, and computer program

Abstract

The invention relates to a monitoring system (1) comprising a plurality of monitoring devices (2) for generating monitoring data, an event database (4) for receiving event data on the basis of the monitoring data, and an NL event interpretation module (3) for generating the event data from the monitoring data, wherein the event data are in the form of natural language data, and / or comprising an NL query module (5) for generating queries, wherein the queries are in the form of natural language queries, wherein the monitoring system (1) is designed to output monitoring events as a response to the natural language queries.

Description

[0001] Description

[0002] Title Learn how to operate the

[0003] The invention relates to a monitoring system having the features of the preamble of claim 1. The invention also relates to a method for operating the monitoring system and a computer program

[0004] State of the art

[0005] Traditional surveillance systems only recorded and stored surveillance videos of monitored areas. The surveillance videos can be viewed and reviewed by surveillance personnel during recording or virtually offline. However, such surveillance requires a high level of personnel effort and is prone to errors, compounded by the human factor.

[0006] As a result, surveillance systems were developed that could detect events using digital image processing and report the corresponding events, allowing monitoring personnel, for example, to monitor the events. This limited the monitoring personnel's work to monitoring the detected, highly relevant events, thus ensuring a reduction in monitoring personnel and consistent, albeit automated, monitoring quality.

[0007] The publication DE 10 2005 01915 3 A1 describes a method and system for processing data. The publication discloses methods for processing data comprising the following steps: recording raw data; processing, in particular digitizing, compressing, and / or encoding, the raw data; analyzing, in particular performing a content analysis, of the raw or processed data; evaluating, in particular performing event detection, the analysis results to create a semantic description of the content; indexing the processed data using the semantic description; and processing the indexed data. The semantic description thus provides an abstract, formal description and representation of the event detected by the surveillance system.

[0008] Disclosure of the invention

[0009] The subject matter of the invention is a monitoring system having the features of claim 1, a method having the features of claim 14 and a computer program having the features of claim 15. Preferred or advantageous embodiments of the invention emerge from the subclaims, the following description and the attached figures.

[0010] The subject of the invention is therefore a surveillance system that is suitable and / or designed for monitoring a surveillance area. Such surveillance areas can be, in particular, contiguous and / or distributed surveillance areas in public or private environments.

[0011] The monitoring system comprises a plurality of monitoring devices for generating monitoring data. The monitoring data can be sensor data from the monitoring devices; however, it can also be provided that the monitoring data is already preprocessed by the monitoring device or an intermediate device and is configured as preprocessed monitoring data.

[0012] The monitoring devices can be designed, in particular, as surveillance cameras, such as PTZ cameras or stationary cameras, or 360° cameras. Alternatively or additionally, the monitoring devices can be designed as access control devices,

[0013] Intrusion detection devices, motion detection devices,

[0014] Environmental detection sensor devices, etc. It is also possible for the monitoring devices to be implemented as fire, gas, and / or temperature sensor devices, etc.

[0015] The monitoring system has an event database for recording event data based on the monitoring data. The event data is particularly embodied as further processed monitoring data. The event database can be located on a local data storage device or on a data storage device on a server, in the cloud, etc. The event database can be embodied as a single device, but it is also possible for the event database to be distributed across various digital data processing devices and / or instances. An event database is understood, in particular, to be a data collection independent of the architecture of the event database.

[0016] In its most general form, event data refers to data that can be assigned to a monitoring event in the monitoring data. In particular, the event data includes a description of the monitoring event and a link to the associated monitoring event.

[0017] Within the scope of the invention, it is proposed that the monitoring system has an NL event interpretation module for generating the event data from the monitoring data, wherein the event data are designed as natural language data.

[0018] Alternatively or additionally, the monitoring system comprises an NL query module for generating queries, wherein the queries are implemented as Natural Language queries. The monitoring system is configured to output monitoring events in response to the Natural Language queries.

[0019] It is therefore one consideration of the invention to implement the data storage structure and / or the query structures based on natural language data and / or natural language queries and thus to use natural language processing (NLP). In particular, natural language generation (NLG) is used for the natural language data and / or natural language understanding (NLU) is used for the natural language queries. Natural language is understood to mean, in particular, natural language, so that the natural language data is a description of the monitoring event based on natural language and / or the natural language queries are defined based on natural language.

[0020] Security systems are key components for maintaining safety and surveillance in various areas. With an ever-growing number of cameras and related devices such as access control devices, intrusion sensors, motion sensors, intercoms, perimeter detection systems, etc., monitoring and analyzing the vast amounts of data generated by these systems becomes a challenging task. Existing solutions typically require manual review and specialized knowledge to detect specific events or patterns, which is labor-intensive and often ineffective. Furthermore, these systems do not provide an intuitive way to search for events or patterns based on natural language descriptions or to configure the system using natural language commands.

[0021] As of 2023, large language models (LLMs) such as GPT-4, developed by OpenAI, have significantly advanced the field of natural language processing (NLP) and artificial intelligence (AI). These models are capable of generating human-like text, understanding context, responding to prompts, and even generating poems, stories, and code, among other capabilities. The innovation here lies in the application of advanced language models such as GPT-4, developed by OpenAI, to generate natural language descriptions of events. This means the system can articulate what is happening in a way that anyone can understand. Furthermore, users can search for events using simple voice queries and even configure the system using simple commands.This increases the accessibility and efficiency of the system, which is beneficial for all users. Essentially, this invention utilizes cutting-edge AI technology to make security systems smarter, more user-friendly, and more effective. The monitoring system thus has the advantage that the natural language data is immediately understandable to the user, as it describes the monitoring events in natural language. Alternatively or additionally, the monitoring system has the advantage that the queries are designed as natural language queries and are thus initiated by a user, which corresponds to the user's usual language comprehension.

[0022] The monitoring system can be installed without the monitoring devices on a digital data processing device, one or more servers, and / or in the cloud. If necessary, the monitoring system without the monitoring devices has a data interface to the monitoring devices.

[0023] Further potential benefits, particularly depending on the design, include: Efficient event analysis: Conventional systems often require manual interpretation of events and video footage, which can be labor-intensive and time-consuming. The proposed surveillance system automates this process, thus saving time and resources. Improved accessibility: By creating natural language data as descriptions of events in natural language, the surveillance system makes the surveillance data more accessible and understandable for non-specialist users. This represents a significant improvement over conventional systems, which often require specialized knowledge to interpret the data.Contextual understanding: The surveillance system's ability to incorporate contextual information into its event descriptions can provide valuable insights that might be missed in traditional systems. For example, it can detect if an event occurs at an unusual time or location, which could indicate suspicious activity. Advanced search capabilities: The surveillance system's NL query module allows users to search for events using natural language queries. This makes it easier for users to locate specific events compared to traditional systems, which often require complex query languages ​​or manual video review. Natural language configuration: The surveillance system's ability to accept configuration commands in natural language makes it more user-friendly and easier to manage than traditional systems.This reduces the need for specialized training and can save time when setting up or customizing the system. Increased security: By detecting and alerting you to unusual events or patterns, the surveillance system can increase security and help prevent incidents before they occur. This proactive approach represents a significant improvement over traditional systems, which are often reactive and rely on manual monitoring. Scalability: The surveillance system's automation capabilities make it highly scalable. It can manage an increasing number of cameras and associated devices as surveillance assets without a corresponding increase in labor or resources. This makes it suitable for large installations that are difficult to manage with traditional systems.Integration of AI and ML: By integrating artificial intelligence and machine learning technologies, the monitoring system can continuously improve its performance over time by learning from past data to better interpret future monitoring events. This is another advantage over conventional systems, which typically lack such learning capabilities. Overall, the proposed monitoring system significantly improves the efficiency, accessibility, and performance of security management systems as monitoring systems, making it a valuable tool.

[0024] In a preferred embodiment of the invention, the NL event interpretation module and / or the NL query module comprises an NL generator submodule. For the NL event interpretation module, the NL generator submodule is particularly designed to generate the natural language data from detected monitoring events. Examples of such generation are disclosed in Karpathy, A.; Fei-Fei, L. Deep visual-semantic alignments for generating image descriptions. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7-12 June 2015; pp. 3128-3137.

[0025] For the NL query module, the NL generator submodule is specifically designed to generate natural language queries from natural language input, either acoustically or in text form. Examples of such a generation include InstructGPT.

[0026] In particular, the natural language queries are tailored to the natural language data in such a way that they share a common natural language basis. Especially when describing queries or monitoring events in natural language, the descriptions can differ significantly in terms of the choice of expression, the structure of the description, etc. It is advantageous if the NL generator submodules are tailored to each other in such a way that they use the same or a similar language model for the description. In particular, they can be trained with the same training data.

[0027] The NL event interpretation module preferably has an event definition submodule, which defines a surveillance event based on the surveillance data as the basis for the natural language data. In particular, the surveillance event is passed to the NL generator submodule of the NL event interpretation module to generate the natural language data. The event definition submodule can be based on digital image processing, as is known, for example, from video surveillance. Alternatively, the event definition submodule can be embodied as artificial intelligence (AI), in particular as an artificial neural network, which receives the surveillance data as input data and provides the detected surveillance event at the output. In particular, the event definition submodule is based on deep / machine learning.

[0028] In a preferred embodiment of the invention, the NL event interpretation module comprises a configuration submodule and a correlator submodule. The configuration submodule provides system configuration data of the monitoring system and / or event configuration data for correlated monitoring events.

[0029] System configuration data refers, in particular, to data about the monitoring devices. In particular, the data includes the location of the monitoring devices in the monitoring area, the type of monitoring device, etc. Event configuration data for correlated monitoring events refers, in particular, to data that defines special conditions for the correlated monitoring events. This can include special temporal conditions, such as the occurrence of the monitoring event in a specific time window and / or correlations between monitoring devices, such as the occurrence of the monitoring event or a related monitoring event at two or more monitoring devices.For example, a correlation of monitoring devices exists when an actuation of an access control device and at the same time the appearance of an object / person in the monitoring area near the access control device is recorded as monitoring data.

[0030] The correlator submodule is configured to define correlated monitoring events as a basis for the Natural Language data based on the monitoring events and, in addition, the system configuration data and / or the event configuration data of the configuration submodule. The correlator submodule is thus configured to utilize additional information in addition to the results from the event definition submodule. In this way, correlated monitoring events can be combined into a correlated monitoring event as a monitoring event. The ability to access system configuration data allows, for example, the local proximity of monitoring devices to be utilized to correlate monitoring events from two or more neighboring monitoring devices.

[0031] It is particularly preferred that the NL query module is configured to send the natural language queries to the event database in order to receive monitoring events, in particular correlated monitoring events from the correlator submodule or simple monitoring events from the event definition submodule, as a response. This creates a database for storing monitoring events and queries for monitoring events based on natural language. It is particularly preferred that the NL query module is configured to generate natural language queries based on natural language queries. The natural language queries are entered by a user acoustically or textually. In this way, a user can communicate particularly easily with the monitoring system in order to receive monitoring results as responses.

[0032] In an alternative or further development of the invention, the NL query module is designed to generate natural language queries based on natural language queries and to suggest them as possible natural language queries that can be selected by a user. The NL query module thus offers computer-assisted formulation assistance for formulating the natural language queries. This allows the user to communicate with the monitoring system particularly easily.

[0033] In a further alternative or development of the invention, the NL query module has a natural language configuration instruction submodule, wherein the natural language configuration instruction submodule is designed to generate a monitoring query for a predefinable monitoring event as a natural language query. In this way, it is possible for the user or otherwise to set up continuous monitoring for a specific monitoring event, comprising in particular a simple monitoring event and / or a correlated monitoring event. The natural language configuration instruction submodule configures the monitoring system such that the response to the monitoring query is output as a natural language query if / or as soon as the predefinable monitoring event occurs. For example, the natural language configuration instruction submodule communicates with the NL event interpretation module.In this way, the surveillance system can be made aware of a specific surveillance event by the user or by other means.

[0034] On the one hand, it is possible for the Natural Language configuration instruction submodule to act on the configuration submodule to sensitize it and, in particular, to define the monitoring results or correlated monitoring results there. Alternatively or additionally, the Natural Language configuration instruction submodule can act on the input of the event database so that the response is output as soon as the monitoring event occurs. It is also possible for the Natural Language configuration instruction submodule to query the event database in a continuous loop so that the response is output as soon as the monitoring event is entered in the event database.

[0035] In a preferred embodiment of the invention, the monitoring system has an output device for outputting the detected monitoring event. In particular, for example, an alarm can be triggered, a monitoring center can be activated, etc.

[0036] Another object of the invention relates to a method for operating the monitoring system as described above or according to one of the preceding claims. The method provides that the NL event interpretation module generates event data from the monitoring data, wherein the event data is in the form of natural language data.

[0037] Alternatively or additionally, it is provided that the NL query module generates queries, wherein the queries are designed as Natural Language queries, wherein the monitoring system outputs monitoring events in response to the Natural Language queries.

[0038] A further subject matter of the invention relates to a computer program that executes the method once it is implemented on the monitoring system and / or on a digital data processing device. The computer program can be installed, in particular, in an executable manner on a digital data processing device, a server, and / or on the cloud. An optional subject matter of the invention relates to a digital storage medium for storing the computer program, in particular a machine-readable storage medium, preferably a non-volatile machine-readable storage medium, on which the described computer program is stored.

[0039] This invention thus aims to revolutionize the way security systems are managed by introducing an integrated system that leverages natural language processing (NLP) and machine learning (ML) to generate natural language descriptions of the events recorded by the system. This system allows users to search for events using natural language queries and configure the system using natural language commands, significantly improving the accessibility and efficiency of the surveillance system.

[0040] Further features, advantages, and effects of the invention will become apparent from the following description of a preferred embodiment and the accompanying figure. This shows:

[0041] Figure 1 is a schematic block diagram of a monitoring system as an embodiment of the invention.

[0042] Figure 1 shows a schematic block diagram of a surveillance system 1 as an embodiment of the invention. The surveillance system has the function of monitoring a surveillance area with respect to a surveillance event. The surveillance event can be any event, such as entry into a secured area, a content event, in particular a gathering of people, an unguarded object such as a suitcase in a train station, a fire, a gas concentration, etc.

[0043] The monitoring system 1 comprises a plurality of monitoring devices 2, which generate monitoring data during operation. The monitoring devices 2 can be arbitrarily selected from a group of: surveillance cameras, in particular stationary or mobile surveillance cameras, PTZ cameras, 360° cameras, fire alarm devices, temperature sensor devices,

[0044] Access control devices, etc. The surveillance data is provided as raw surveillance data or as pre-processed surveillance data.

[0045] The monitoring system 1 has an NL event interpretation module 3. The NL event interpretation module 3 is configured to generate event data of monitoring events based on the monitoring data. The event data is configured as natural language data. The natural language data describes the monitoring events in natural language. For example, the natural language data can describe the monitoring events as follows:

[0046] - an object enters the surveillance scene;

[0047] - a fire occurs in the surveillance scene;

[0048] - an access control device has been activated;

[0049] - a fire alarm system has registered a fire.

[0050] This may include, for example, a description of the location and / or time of the monitoring event, particularly also as natural language data.

[0051] The monitoring system 1 has an event database 4, which stores the event data generated based on the monitoring data. The event database 4 can be centralized or decentralized in any architecture. In particular, monitoring data from the monitoring devices 2 is assigned to the event data, so that the event data contains the Natural Language data and a connection, such as a pointer or reference, to the generated monitoring data.

[0052] The monitoring system 1 has an NL query module that can generate queries, wherein the queries are embodied as natural language queries. Thus, the queries are posed in natural language. The monitoring system 1 is configured to output appropriate monitoring events in response to the natural language queries.

[0053] The monitoring system 1 thus allows the monitoring events to be stored as event data in the form of natural language data in the event database 4 and queried in natural language via the NL query module 5. The main advantage of the monitoring system 1 lies in the fact that monitoring events are no longer stored and queried in a formal, semantic computer language, but rather that the event data and the query are implemented on a natural language basis. Thus, the monitoring system 1 allows access to and control of the event data in a user-friendly and intuitively understandable natural language sphere or coding.

[0054] The NL event interpretation module 3 can be designed as a class that evaluates the monitoring data based on deep and / or machine learning and generates the event data as natural language data.

[0055] The NL event interpretation module 3 is, in particular, the first point of contact for raw data originating from various security devices, known as monitoring devices 2, in the monitoring system 1. It serves to interpret and categorize various monitoring events that occur in the security system. For example, if an access system device, known as monitoring device 2, is activated at the main entrance, this module interprets the event as "activation of the access system at the main entrance." This module analyzes the events in real time and, particularly in the correlator submodule 8, ultimately correlates related events to obtain a more comprehensive overview of the situation.For example, if a motion detection event occurs followed by an activation of the access system, the system could correlate these events and interpret them as a single event: "Motion detected near the main entrance and the access system activated at the same time."

[0056] As an example, Figure 1 shows an optional substructure in the NL event interpretation module 3:

[0057] The NL event interpretation module 3 has an event definition submodule 6. The event definition submodule is designed to define the monitoring events based on the monitoring data, in particular to recognize them and describe them in any desired manner. The definition of the monitoring events can be implemented using known digital image processing algorithms. Alternatively, any artificial neural network, in particular based on deep / machine learning, can be implemented to recognize, describe, and thus define the monitoring events. Optionally, the NL event interpretation module has a memory device 7, wherein the memory device 7 is designed as a FIFO memory, which represents a buffer in the information and / or data flow. The input of the memory device 7 is connected to the event definition submodule 6 for data purposes.

[0058] The NL event interpretation module 3 has a correlator submodule 8, wherein the correlator submodule 8 is connected to the output of the storage device 7, so that the monitoring events from the event definition submodule 6 are provided to the correlator submodule 8.

[0059] Optionally, the NL event interpretation module 3 can have a configuration submodule 9, wherein the configuration submodule 9 holds system configuration data of the monitoring system 1, in particular of the monitoring devices 2. In particular, the system configuration data can include a type of the respective monitoring device 2 (surveillance camera, sensor device, etc.). Alternatively or additionally, the system configuration data includes a spatial arrangement and / or a model of the monitoring area with the monitoring devices 2, so that the local, relative relationship between the monitoring devices 2 and the monitoring area is known.

[0060] It may also be provided that the configuration submodule 9 includes event configuration data for correlated monitoring events. The event configuration data may include special conditions for evaluating and / or evaluating and / or linking the monitoring events.

[0061] The special conditions can, for example, define time ranges for monitoring events: For example, a relevant monitoring event occurs if the monitoring event occurs in a time range in which, for example, no people should be present in the monitoring area.

[0062] The event configuration data may also relate to special conditions relating to the simultaneous or related occurrence of monitoring events: For example, a special condition may relate to the activation of an access control device as monitoring device 2 as a monitoring event and the detection of an object in a monitoring area specified for this purpose by a monitoring camera as another monitoring device 2 as a monitoring event.

[0063] The correlator submodule 8 is configured to detect and / or define correlated monitoring events based on the monitoring events and the system configuration data and / or event configuration data. A correlated monitoring event thus includes, in particular, individual monitoring events from different monitoring devices 2, the occurrence of a monitoring event in a specific time range, or other more complex monitoring events in which the special conditions are met.

[0064] The correlator submodule 8 can operate according to a user-supported and / or manually created set of rules, wherein the input data, comprising individual monitoring events, system configuration data and / or

[0065] Event configuration data is evaluated according to the rule set. Alternatively, the correlator submodule 8 can be designed as an artificial neural network, in particular based on deep / machine learning, which fuses the input data and defines and outputs correlated monitoring events.

[0066] The monitoring events, in particular the individual monitoring events and / or the correlated monitoring events, are passed to an N L generator submodule 10.

[0067] The NL generator submodule 10 translates the monitoring events into natural language data, i.e., a description of the respective monitoring event in natural language. The NL generator submodule 10 can, in particular, be designed as an artificial neural network.

[0068] The NL Generator submodule 10 is a natural language generator: This component converts the interpreted events into detailed, natural language descriptions. It uses advanced natural language generation (NLG) techniques to create human-like, easily understandable descriptions of the events. For example, it could describe a series of events as follows: "The access system to the main entrance was activated at 10:15 a.m. At the same time, movement was detected near the main entrance, possibly indicating that someone entered the building." This component would add relevant context to the generated descriptions, making them more informative and useful. For example, if the activation of the access system occurred at an unusual time, the Natural Language Generator could insert this context into the description, e.g."The main entrance access system was activated at 3:00 a.m., an unusual time for this location." The events are written to the event database 4 as a natural language database. The natural language generator is customizable to the needs of each system installation. This component would adapt the generated descriptions to the preferences of the system configurator. For example, some customers prefer concise descriptions, while others prefer more detailed narratives. A personalization component could learn these preferences over time and adapt the descriptions accordingly. The system also provides a feedback mechanism for the module. This mechanism would allow system configurators to provide feedback on the generated descriptions, which the natural language generator 10 could use to improve its performance over time.

[0069] Optionally, the NL event interpretation module 3 has an NL video generator submodule 11, which is configured to output surveillance scenes in the surveillance data of the surveillance cameras as surveillance devices 2 as natural language data, i.e., to describe them in natural language. The NL video generator submodule 11 can, in particular, be configured as an artificial neural network. The natural language data is stored in the event database 4.

[0070] The NL video generator submodule 11 is a video description generator: This module is responsible for analyzing the recorded video footage and generating natural language descriptions of the scenes. It uses available computer vision techniques to identify objects, people, and activities in the video footage. For example, it could generate a description such as "A tall person in a blue jacket entered the main entrance at 10:15 a.m. carrying a large box." The events are stored in the event database 4 as a natural language database.

[0071] The monitoring system 1 has an NL query module 5, an NL query module for generating queries, wherein the queries are designed as natural language queries.

[0072] The NL Query Module 5 is a search module: This component of the system is supported by a state-of-the-art language model, available on-premises or in the cloud. It processes complex natural language queries and provides users with an intuitive and powerful tool for exploring event data. For example, it can process queries such as "Show me events where the main entrance was entered at unusual times" or "Find instances of movement detected near the main entrance while the access system was activated." Existing language models are capable of generating accurate and context-appropriate results when fed with comprehensive historical data in the form of natural language descriptions of events. To enhance the functionality of this module, a predictive search function is incorporated.This feature suggests search queries based on the most common or recent searches as the user types, improving the user experience and accelerating the search process. This component understands the context of the user's search query and leverages it to deliver more relevant search results. For example, if the user searches for "unusual access events," the search component understands that the user is likely interested in access events that occurred at unusual times or locations.

[0073] The NL query module 5 can thus act on the monitoring system 1, in particular on the NL event interpretation module 3, in different ways: Optionally, the NL query module 5 has a further NL generator submodule 12, which is designed to translate requests in natural language as natural language requests from a user 13 into queries in the form of natural language queries. This enables the user 3 to submit a natural language request, which is converted by the NL generator submodule 12 into a natural language query, which is subsequently submitted to the monitoring system 1, in particular to the event database 4. The advantage of the further NL generator submodule 12 is that the natural language queries are standardized on a natural language language basis.

[0074] In response, the NL query module 5 receives monitoring events, in particular comprising simple / individual and / or correlated monitoring events. In particular, the responses are output as natural language responses and provided to an output device 14. The output device 14 can be configured as a monitoring center and make the natural language responses available to the user 13.

[0075] In one possible variation, it can be provided that the user 13 submits a Natural Language query, and the NL query module 5, in particular the NL generator submodule 12, provides several Natural Language queries as options, which are subsequently selected by the user 13, for example, via a human-machine interface. The selected Natural Language query is then transferred to the monitoring system 1, as previously described.

[0076] Optionally, the NL query module 5 can have a natural language configuration instruction submodule 15, which is designed to generate a monitoring request, in particular a natural language request, from the user 13 from a predefinable monitoring event as a monitoring natural language query. The natural language configuration instruction submodule 15 is designed to configure the monitoring system 1 such that the response to the monitoring query is output as a natural language response if or as soon as the predefinable monitoring event occurs. The natural language configuration instruction submodule 15 can be used, in particular, to generate continuous queries or specific queries that are answered as soon as the content of the query occurs.

[0077] The monitoring natural language query can be sent to the event database 4, so that the monitoring event is issued as a response to the monitoring natural language query as soon as the requested monitoring event is entered in the event database 4.

[0078] Alternatively, the monitoring Natural Language query can be sent to the NL event interpretation module 3, whereby a monitoring result is issued in response to the monitoring Natural Language query as soon as the NL event interpretation module 3 detects the queried monitoring event.

[0079] It is also possible for the configuration submodule 9 to be configured to define a predeterminable monitoring event as a correlated monitoring event based on the monitoring natural language query. In this case, the correlated monitoring event is detected by the correlator submodule 8 and can be output via the N L generator submodule 10 as a response to the monitoring natural language query as soon as it occurs.

[0080] From a data perspective, the response can be returned directly from the NL event interpretation module 3, in particular the correlator submodule 8 and / or the NL generator submodule 10 or the event database 4, to the NL query module 3 and forwarded to the output device 14. It is possible for the response to be provided as a natural language response at the output device 14 and transmitted to the user 13.

[0081] Alternatively or additionally, the natural language configuration instruction submodule 15 can be configured to allow the user 13 to configure the monitoring system 1 with natural language commands, i.e., commands in natural language, in order to increase usability. The commands can relate to the integration of new monitoring devices 2 or their parameters. In particular, the configuration takes place in the configuration submodule 9.

[0082] The Natural Language Configuration Instruction submodule 15 is specifically a natural language configuration module: This component was designed to provide a user-friendly interface for configuring the system. It allows users to use commands in natural language, making the system more accessible and intuitive. For example, users can issue commands such as "Generate an alarm at night if a person attempts to enter a specific area" or "Trigger an alarm if someone presents their badge at an access system after regular working hours." A learning mechanism can be integrated into this module. This mechanism would learn from the user's configuration commands and improve the system's ability to understand and execute these commands over time.For example, if the user frequently configures certain types of alerts, the natural language configuration module could learn to suggest these alerts when the user begins configuring a new alert. A feedback mechanism is built into the module. This mechanism would allow users to provide feedback on the system's interpretation of their commands, which the natural language configuration instruction submodule 15 could leverage to improve its performance over time.

[0083] Specifically, a user command is input into the natural language configuration instruction submodule 15, which then interprets the command and translates it into a system configuration. The module also includes a contextual understanding component that provides contextual configurations based on the user command, as well as a learning mechanism that improves the module's ability to interpret commands over time.

Claims

Claims 1. Monitoring system (1) with at least one, preferably a plurality of monitoring devices (2) for generating monitoring data, with an event database (4) for recording event data on the basis of the monitoring data, characterized by an NL event interpretation module (3) for generating the event data from the monitoring data, wherein the event data is designed as natural language data, and / or an NL query module (5) for generating queries, wherein the queries are designed as natural language queries, wherein the monitoring system (1) is designed to output monitoring events in response to the natural language queries.

2. Monitoring system (1) according to claim 1, characterized in that the NL event interpretation module (3) and / or the NL query module (5) comprises an NL generator submodule (10, 12).

3. Monitoring system (1) according to claim 1 or 2, characterized in that the monitoring system (1) is designed to output the monitoring results as natural language responses.

4. Monitoring system (1) according to one of the preceding claims, characterized in that the NL event interpretation module (3) has an event definition sub-module (6), wherein the event definition sub-module (6) is designed to be based on the Monitoring data to define a monitoring event as the basis for the natural language data.

5. Monitoring system (1) according to claim 4, characterized in that the NL event interpretation module (3) has a configuration submodule (9) and a correlator submodule (8), wherein the configuration submodule (9) has system configuration data of the monitoring system (1) and / or event configuration data for correlated monitoring events, wherein the correlator submodule (8) is designed to define correlated monitoring events as a basis for the natural language data based on the monitoring events and the system configuration data and / or the event configuration data of the configuration submodule (8).

6. Monitoring system (1) according to one of the preceding claims, characterized in that the NL query module (5) is designed to send the natural language queries to the event database (4) in order to receive monitoring events in response to the natural language queries.

7. Monitoring system (1) according to one of the preceding claims, characterized in that the NL query module (5) is designed to generate natural language queries based on natural language queries from a user (13).

8. Monitoring system (1) according to one of the preceding claims, characterized in that the NL query module (5) is designed to generate natural language queries on the basis of natural language queries and to propose them as possible natural language queries which can be selected by a user or the user (13).

9. Monitoring system (1) according to one of the preceding claims, characterized in that the NL query module (5) has a natural language configuration instruction submodule (15), wherein the natural language configuration instruction submodule (15) is designed to generate a monitoring query for a predeterminable monitoring event as a monitoring natural language query, wherein the natural language Language configuration instruction submodule (15) is designed to configure the monitoring system (1) such that the response to the monitoring query is output as a natural language response when / as soon as the predefinable monitoring event occurs.

10. Monitoring system (1) according to claim 9, characterized in that the natural language configuration instruction submodule (15) is designed to send the monitoring natural language query to the event database (4) in order to obtain monitoring events in response to the monitoring natural language query.

11. Monitoring system (1) according to claim 9 or 10, characterized in that the natural language configuration instruction submodule (15) is designed to send the monitoring natural language query to the NL event interpretation module (3) in order to receive monitoring events in response to the monitoring natural language query.

12. Monitoring system (1) according to claim 10 or 11, characterized in that the configuration submodule (9) is designed to define a predeterminable monitoring event as a correlated monitoring event on the basis of the monitoring natural language query.

13. Monitoring system (1) according to one of the preceding claims, characterized by an output device (14) for outputting the monitoring events.

14. Method for operating the monitoring system (1), in particular a monitoring system (1) according to one of the preceding claims, wherein at least one monitoring device (2) generates monitoring data, wherein an event database (4) records event data on the basis of the monitoring data, characterized in that an NL event interpretation module (3) generates event data from the monitoring data, the event data being presented as Natural Language Data are formed, and / or an NL query module (5) generates queries, wherein the queries are formed as natural language queries, wherein monitoring events are output in response to the natural language queries.

15. Computer program for carrying out the method according to claim 14, when the program is executed on the monitoring system (1) or on a digital data processing device.

Images