A wireless communication network alarm method and system based on artificial intelligence

Abstract

The present application provides a wireless communication network alarm method and system based on artificial intelligence, which determines the periodic distribution characteristics of steady-state traffic in wireless home devices through all steady-state traffic information; determines the traffic anomaly index of wireless home devices in wireless networking based on communication traffic information and periodic distribution characteristics; when the traffic anomaly index is greater than the preset traffic threshold, uses the central console of the wireless networking to send event messages to the wireless home devices in a proportional interval manner, monitors the signal receiving interval of the wireless home devices until the signal receiving interval is the same as the initial sending interval, and determines the traffic alarm threshold of the wireless home devices based on all signal receiving intervals of the wireless home devices in the sent event message; when the traffic anomaly index is greater than the traffic alarm threshold, the central console of the wireless networking is alarmed for traffic anomaly based on the location information of the wireless home devices. Based on the above scheme, the false alarm rate of alarms in wireless communication networks can be reduced.

Description

Technical Field

[0001] The present application relates to the field of wireless networking communication security technology, and more specifically, to an artificial intelligence-based wireless communication network alarm method and system. Background Art

[0002] The communication network obtained by wireless networking is a network system that transmits data and information through radio waves or other non-wired methods. Z-Wave is a wireless networking communication protocol with simple structure, low cost and reliable performance. It is also a wireless communication protocol designed specifically for smart home environments. The wireless networking built with Z-Wave technology can not only remotely control home appliances through this network device, but also remotely control home appliances in the Z-Wave network through wireless networks.

[0003] In the prior art, wireless communication networks based on the Z-Wave protocol usually use a preset static alarm threshold to perform abnormal alarms. However, wireless communication networks usually have complex topological structures, and the communication paths and connection relationships between communication nodes are constantly changing, which leads to more drastic changes in communication traffic. When a single static alarm threshold is used to judge traffic anomalies, the system cannot distinguish whether it is due to short-term traffic fluctuations or real abnormal behavior. If the communication traffic exceeds the preset static alarm threshold in a short period of time, an abnormal alarm will be triggered. In fact, these traffic fluctuations may only be normal phenomena for a moment, which can easily lead to frequent false alarms. The dynamic threshold judgment mechanism can effectively deal with frequent false alarms in alarms caused by problems such as topological complexity and large traffic fluctuations in wireless networking. Therefore, how to realize dynamic threshold judgment of traffic anomaly alarms in wireless networking, thereby reducing the false alarm rate of alarms in wireless communication networks, is a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a wireless communication network alarm method and system based on artificial intelligence, which can realize dynamic threshold determination of abnormal traffic alarm in wireless networking, thereby reducing the false alarm rate of alarm in the wireless communication network.

[0005] In a first aspect, the present application provides an artificial intelligence-based wireless communication network alarm method, wherein the wireless communication network is a wireless network formed by connecting multiple wireless home devices according to the Z-wave protocol, and the method comprises the following steps:

[0006] Monitor the communication traffic in the wireless network and collect the historical communication traffic of wireless home devices in the wireless network within a specified time period;

[0007] Through the periodicity of wireless networking, the steady-state traffic information under each communication cycle is extracted from all historical communication traffic, and then the periodic distribution characteristics of the steady-state traffic in the wireless home device are determined from all the steady-state traffic information;

[0008] Real-time monitoring of the communication flow information of the wireless home device in the current communication cycle, feature matching of the period distribution feature based on the steady-state feature of the communication flow information, obtaining the flow feature deviation of the wireless home device, and then determining the flow anomaly index of the wireless home device in the wireless network based on the flow feature deviation;

[0009] When the traffic anomaly index is greater than a preset traffic threshold, the wireless networking central console is used to send event messages to the wireless home devices at proportional intervals, and the signal receiving intervals of the wireless home devices are monitored until the signal receiving intervals are the same as the initial sending intervals, and the traffic alarm threshold of the wireless home devices is determined according to all signal receiving intervals of the wireless home devices in the sent event messages;

[0010] When the traffic anomaly index is greater than the traffic alarm threshold, a traffic anomaly alarm is sent to the central control station of the wireless network based on the location information of the wireless home device.

[0011] In some embodiments, extracting steady-state traffic information in each communication period from all historical communication traffic through the periodicity of wireless networking specifically includes:

[0012] Get the lower limit of communication traffic of wireless home devices;

[0013] Filtering out all normal communication flows from all historical communication flows according to the communication flow lower limit;

[0014] Dividing a specified time period into multiple communication cycles according to the periodicity of wireless networking;

[0015] The steady-state traffic information in each communication cycle is obtained from all normal communication traffic.

[0016] In some embodiments, determining the periodic distribution characteristics of the steady-state traffic in the wireless home device from all the steady-state traffic information specifically includes:

[0017] For each communication cycle, a steady-state flow mean value in the communication cycle is determined according to the steady-state flow information in the communication cycle;

[0018] Determine all time domain distribution values ​​of the steady-state traffic in the communication cycle according to the steady-state traffic mean and each steady-state traffic value in the steady-state traffic information;

[0019] The time domain distribution sub-features under the communication cycle are determined through all the time domain distribution values, and then the time domain distribution sub-features of the steady-state traffic under each communication cycle are obtained;

[0020] The periodic distribution characteristics of steady-state traffic in wireless home devices are determined by all time-domain distribution sub-characteristics.

[0021] In some embodiments, feature matching is performed on the periodic distribution feature based on the steady-state feature of the communication traffic information to obtain the traffic feature deviation of the wireless home device, specifically including:

[0022] Obtain the communication traffic limit of wireless home devices;

[0023] Matching the steady-state characteristics of the communication traffic information with the periodic distribution characteristics to obtain a traffic anomaly threshold value of the wireless home device;

[0024] Determining a flow characteristic deviation of the communication flow information according to the flow anomaly threshold and the communication flow upper limit;

[0025] The traffic anomaly index of the wireless home device in the wireless network is determined according to the traffic characteristic deviation.

[0026] In some embodiments, determining the traffic alarm threshold of the wireless home device according to all signal reception intervals of the wireless home device in the sending event message specifically includes:

[0027] Get the initial sending interval in the sending event message;

[0028] Determine the total interval for sending the event message according to all signal receiving intervals of the wireless home devices in the event message;

[0029] The flow alarm threshold of the wireless home device is determined according to the total sending interval and the initial sending interval.

[0030] In some embodiments, the signal receiving interval of the wireless home device is a signal receiving time interval of the wireless home device under the integrated communication of the event message signal and the normal signal.

[0031] In some embodiments, the initial sending interval is the minimum interval time for the central control station of the wireless network to send event messages.

[0032] In a second aspect, the present application provides a wireless communication network alarm system based on artificial intelligence, wherein the wireless communication network is a wireless network formed by connecting multiple wireless home devices according to the Z-wave protocol, including:

[0033] A collection module is used to monitor the communication traffic in the wireless network and collect the historical communication traffic of the wireless home devices in the wireless network within a specified time period;

[0034] A processing module, used to extract steady-state traffic information in each communication cycle from all historical communication traffic through the periodicity of wireless networking, and then determine the periodic distribution characteristics of steady-state traffic in wireless home devices from all steady-state traffic information;

[0035] The processing module is also used to monitor the communication flow information of the wireless home device in the current communication cycle in real time, perform feature matching on the period distribution feature based on the steady-state feature of the communication flow information, obtain the flow feature deviation of the wireless home device, and then determine the flow anomaly index of the wireless home device in the wireless network based on the flow feature deviation;

[0036] The processing module is also used to send event messages to the wireless home devices at proportional intervals using the wireless networking console when the traffic anomaly index is greater than a preset traffic threshold, monitor the signal receiving interval of the wireless home devices until the signal receiving interval is the same as the initial sending interval, and determine the traffic alarm threshold of the wireless home devices according to all signal receiving intervals of the wireless home devices in the sent event message;

[0037] The execution module is used to send a traffic anomaly alarm to the central control station of the wireless network based on the location information of the wireless home device when the traffic anomaly index is greater than the traffic alarm threshold.

[0038] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned artificial intelligence-based wireless communication network alarm method.

[0039] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned artificial intelligence-based wireless communication network alarm method when executed.

[0040] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0041] The present application provides an artificial intelligence-based wireless communication network alarm method and system, which monitors the communication traffic in the wireless network and collects the historical communication traffic of the wireless home appliances in the wireless network within a specified time period; extracts the steady-state traffic information in each communication cycle from all the historical communication traffic through the periodicity of the wireless network, and then determines the periodic distribution characteristics of the steady-state traffic in the wireless home appliances from all the steady-state traffic information; monitors the communication traffic information of the wireless home appliances in the current communication cycle in real time, performs feature matching on the periodic distribution characteristics based on the steady-state characteristics of the communication traffic information, obtains the traffic feature deviation of the wireless home appliances, and then determines the traffic anomaly index of the wireless home appliances in the wireless network from the traffic feature deviation; when the traffic anomaly index is greater than the preset traffic threshold, uses the central console of the wireless network to send event messages to the wireless home appliances in a proportional interval manner, monitors the signal receiving interval of the wireless home appliances until the signal receiving interval is the same as the initial sending interval, and determines the traffic alarm threshold of the wireless home appliances according to all the signal receiving intervals of the wireless home appliances in the sent event messages; when the traffic anomaly index is greater than the traffic alarm threshold, sends a traffic anomaly alarm to the central console of the wireless network based on the location information of the wireless home appliances.

[0042] It can be seen that in the present application, when the traffic anomaly index is greater than the traffic alarm threshold, a traffic anomaly alarm is issued to the central control station of the wireless network based on the location information of the wireless home device; first, the traffic anomaly index is determined through the communication traffic information and the periodic distribution characteristics, and the abnormal degree of the traffic of the wireless home device in the current communication cycle can be obtained. The traffic anomaly index can be used as a basis for the abnormal degree of further alarm. Before the traffic anomaly index exceeds the preset traffic alarm threshold, the system will not directly trigger an alarm. The wireless network can tolerate a certain degree of steady-state traffic fluctuations, reduce the possibility of false alarms caused by instantaneous fluctuations or temporary high loads, and ensure that the alarm system will only issue an alarm when the certainty is high. Among them, determining the periodic distribution characteristics can distinguish the regularity of traffic changes over time, thereby avoiding Normal periodic fluctuations are misjudged as abnormalities. Through periodic division, it can adapt to traffic changes in different time periods and reduce false alarms caused by periodic fluctuations of the load. Secondly, when the traffic anomaly index exceeds the preset traffic threshold, the traffic anomaly is further verified by sending event messages. The system uses a geometric interval to send messages and adjusts the sending interval according to the signal reception situation of the communication node to ensure that the real traffic anomaly is detected. By analyzing the traffic reception interval, the false alarms triggered by temporary traffic fluctuations are effectively reduced, making the alarm triggering more accurate, ensuring that only real traffic anomalies are captured, thereby avoiding false alarms. In summary, based on the above scheme, dynamic threshold judgment of traffic anomaly alarms in wireless networking can be realized, thereby reducing the false alarm rate of alarms in wireless communication networks. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0044] Figure 1 is an exemplary flow chart of an artificial intelligence-based wireless communication network alarm method according to some embodiments of the present application;

[0045] Figure 2 is an abnormal curve diagram of communication traffic according to some embodiments of the present application;

[0046] Figure 3 It is a schematic diagram of a flow chart for determining a flow alarm threshold value according to some embodiments of the present application;

[0047] Figure 4 It is a structural diagram of a wireless communication network alarm system based on artificial intelligence according to some embodiments of the present application;

[0048] Figure 5 It is a structural diagram of a computer device for implementing an artificial intelligence-based wireless communication network alarm method according to some embodiments of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] In order to better understand the technical solution of the present application, the technical solution of the present application will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0051] refer to Figure 1 , which is an exemplary flow chart of a wireless communication network alarm method based on artificial intelligence according to some embodiments of the present application. The wireless communication network described in the present application is a wireless network formed by connecting multiple wireless home devices according to the Z-wave protocol. The wireless communication network alarm method based on artificial intelligence mainly includes the following steps:

[0052] In step 101, the communication traffic in the wireless network is monitored, and the historical communication traffic of the wireless home devices in the wireless network within a specified time period is collected.

[0053] It should be noted that, in the present application, wireless home devices refer to wireless home devices monitored in the wireless network, and other wireless home devices in the wireless network can also use the solution in the present application to perform abnormal traffic alarms; in specific implementation, the traffic monitoring tool in the wireless network can be used to collect the communication traffic of the wireless home device within a specified time period (the default is 2s) at each specified interval, and the collection of all communication traffic can be used as the historical communication traffic of the wireless home device, where the communication traffic includes the traffic value (i.e., the size of the data packet), the transmission rate and the communication time.

[0054] In step 102, the steady-state traffic information in each communication cycle is extracted from all historical communication traffic through the periodicity of wireless networking, and then the periodic distribution characteristics of the steady-state traffic in the wireless home device are determined from all the steady-state traffic information.

[0055] It should be noted that in the present application, the periodicity of the wireless network refers to the regular repetitive behavior characteristics of the traffic in the wireless network within a specific time interval; in the specific implementation, the periodicity of the wireless network is related to the communication control strategy of the wireless network, so the periodic law of the wireless network can be obtained as the periodicity in the central control console of the wireless network.

[0056] In some embodiments, the following steps may be used to extract steady-state traffic information in each communication period from all historical communication traffic through periodic wireless networking:

[0057] Get the lower limit of communication traffic of wireless home devices;

[0058] Filtering out all normal communication flows from all historical communication flows according to the communication flow lower limit;

[0059] Dividing a specified time period into multiple communication cycles according to the periodicity of wireless networking;

[0060] The steady-state traffic information in each communication cycle is obtained from all normal communication traffic.

[0061] It should be noted that in the present application, steady-state traffic information refers to the communication traffic information of wireless home devices that completely conforms to normal behavior during the communication process, that is, a data set composed of communication traffic with an abnormality degree of 0; the lower limit of communication traffic refers to the communication traffic value in the wireless home device when the wireless networking maintains basic communication requirements. In actual use, when the communication traffic in the wireless home device is lower than the lower limit of communication traffic, it is considered to be a faulty communication node. At this time, the wireless home device can be sent as a faulty node to the central console of the wireless networking for fault alarm; the communication cycle refers to the period in which the traffic of the wireless home device in the wireless networking presents regular and repetitive behavior. The communication cycle is a historical time period divided according to the communication cycle, and the communication rules in each communication cycle are similar.

[0062] In specific implementation, first, the lower limit of the communication traffic of the wireless home device can be obtained in the central console of the wireless networking; secondly, the average of all traffic values ​​in the historical communication traffic can be used as the upper limit of the normal communication traffic, and the lower limit of the communication traffic can be used as the lower limit of the normal communication traffic. All communication traffic between the lower limit and the upper limit in the historical communication traffic can be used as normal communication traffic, and all normal communication traffic can be obtained; then, the specified time period can be divided into multiple communication cycles according to the periodic law in the periodicity of the wireless networking; finally, for each communication cycle, the set of all normal communication traffic at the communication moment in the communication cycle is screened out from all normal communication traffic as steady-state traffic information, and the steady-state traffic information under each communication cycle can be obtained in the above manner.

[0063] In some embodiments, determining the periodic distribution characteristics of the steady-state traffic in the wireless home device from all the steady-state traffic information can be implemented by the following steps:

[0064] For each communication cycle, a steady-state flow mean value in the communication cycle is determined according to the steady-state flow information in the communication cycle;

[0065] Determine all time domain distribution values ​​of the steady-state traffic in the communication cycle according to the steady-state traffic mean and each steady-state traffic value in the steady-state traffic information;

[0066] The time domain distribution sub-features under the communication cycle are determined through all the time domain distribution values, and then the time domain distribution sub-features of the steady-state traffic under each communication cycle are obtained;

[0067] The periodic distribution characteristics of steady-state traffic in wireless home devices are determined by all time-domain distribution sub-characteristics.

[0068] It should be noted that in the present application, the periodic distribution feature refers to the feature of the steady-state traffic of wireless home devices in the wireless communication network changing with the time period; the time domain distribution value represents the deviation of the steady-state traffic value of the wireless home device relative to its mean value within the communication cycle; the time domain distribution sub-feature is a feature that describes the overall distribution of traffic within the communication cycle.

[0069] In specific implementation, first, for each communication cycle, the average of the flow values ​​of all normal communication flows in the steady-state flow information under the communication cycle can be used as the steady-state flow average under the communication cycle; secondly, for each steady-state flow under the communication cycle, the ratio of the flow value of the steady-state flow to the steady-state flow average can be used as the time domain distribution value corresponding to the steady-state flow, and the time domain distribution value corresponding to each steady-state flow under each communication cycle can be obtained by the above method; then, all the time domain distribution values ​​are sorted from small to large according to their numerical values, and the same values ​​are merged to initialize an empty array, and the merged time domain distribution value is used as the key of the array, and the number of each merged time domain distribution value is counted as the value of each key in the array, so as to obtain all the key-value pairs of the array, and the array composed of all the key-value pairs can be used as the time domain distribution sub-feature under the communication cycle, and the time domain distribution sub-feature of the steady-state flow under each communication cycle can be obtained by the above method; finally, the set of all the time domain distribution sub-features can be used as the periodic distribution feature of the steady-state flow in the wireless home device.

[0070] In step 103, the communication flow information of the wireless home device in the current communication cycle is monitored in real time, and the period distribution characteristics are matched based on the steady-state characteristics of the communication flow information to obtain the flow characteristic deviation of the wireless home device, and then the flow anomaly index of the wireless home device in the wireless network is determined by the flow characteristic deviation.

[0071] It should be noted that, in the present application, communication traffic information refers to the data set of communication traffic in each specified interval under the current communication cycle; the current communication cycle refers to the communication cycle of the wireless network at the current moment; in specific implementation, the traffic monitoring tool in the wireless network is used to monitor the communication traffic of wireless home devices in the specified interval (the default is 2s) in the current communication cycle in real time. The collection of all communication traffic can be used as communication traffic information, where the communication traffic includes traffic value, traffic source and communication time.

[0072] In some embodiments, feature matching is performed on the periodic distribution feature based on the steady-state feature of the communication traffic information to obtain the traffic feature deviation of the wireless home device, which can be achieved by using the following steps:

[0073] Obtain the communication traffic limit of wireless home devices;

[0074] Matching the steady-state characteristics of the communication traffic information with the periodic distribution characteristics to obtain a traffic anomaly threshold value of the wireless home device;

[0075] The flow characteristic deviation of the communication flow information is determined according to the flow anomaly threshold and the communication flow upper limit.

[0076] It should be noted that the traffic characteristic deviation is the degree of deviation between the actual traffic and the normal traffic; the steady-state characteristic is a parameter that reflects the traffic behavior of wireless home devices under normal working conditions; the traffic anomaly threshold is a parameter used to determine whether the current communication traffic exceeds the normal range; the communication traffic upper limit refers to the maximum data transmission capacity that the wireless home device can withstand within a specific time period, which is usually determined by the hardware capabilities of the device, the limitations of the network protocol or the business requirements of the system design.

[0077] In specific implementation, first, the upper limit of the communication flow of the wireless home device can be obtained in the central console of the wireless networking; then, the mean of the flow values ​​of all the communication flows in the communication flow information can be used as the steady-state feature to initialize a time series model based on a neural network (for example, an autoregressive integrated moving average model), and the steady-state feature is used as the prediction value of the time series model, and all the time domain distribution sub-features in the periodic distribution feature are used as the training base of the time series model. The time series model is used to predict the maximum value of the steady-state flow of the wireless home device in the current communication cycle, and the result of the maximum value prediction can be used as the flow anomaly threshold of the wireless home device; finally, for each communication flow in the communication flow information, the difference between the communication flow and the flow anomaly threshold is used as the anomaly difference, the difference between the upper limit of the communication flow and the flow anomaly threshold is used as the anomaly interval range, and the ratio of the anomaly difference to the anomaly interval range can be used as the characteristic deviation value of the communication flow. In the above manner, the characteristic deviation value of each communication flow in the communication flow information can be obtained, and the set of all characteristic deviation values ​​can be used as the value range of the flow characteristic deviation, so as to obtain the flow characteristic deviation of the communication flow information.

[0078] In some embodiments, determining the traffic anomaly index of the wireless home device in the wireless networking by the traffic characteristic deviation can be implemented in the following manner, namely: the standard deviation of all values ​​in the traffic characteristic deviation can be used as the traffic anomaly index of the wireless home device in the wireless networking; it should be noted that in the present application, the traffic anomaly index is an indicator used to quantify the degree of abnormality of communication traffic information.

[0079] In some embodiments, reference Figure 2 The figure is an abnormal curve diagram of communication traffic in some embodiments of the present application, and the abnormal curve diagram describes the change of traffic abnormality degree with traffic value, wherein the abnormality degree is the traffic abnormality index in the present application, Indicates the lower limit of communication flow. It represents the fuzzy maximum flow, which refers to the maximum flow from normal flow to abnormal flow. The product of the average flow and the preset coefficient can be used as the fuzzy maximum flow. Indicates the upper limit of communication traffic.

[0080] In step 104, when the traffic anomaly index is greater than a preset traffic threshold, an event message is sent to the wireless home device at a proportional interval using the wireless networking central console, and the signal reception interval of the wireless home device is monitored until the signal reception interval is the same as the initial sending interval. The traffic alarm threshold of the wireless home device is determined based on all signal reception intervals of the wireless home device in the sent event message.

[0081] It should be noted that, in the present application, the traffic threshold refers to the degree of abnormality that requires abnormal alarm judgment, which can be preset through historical experience combined with the historical communication traffic in the wireless home device; the event message in the present application is a communication message used for abnormal alarm verification, which is well known in the art and will not be elaborated here; the signal reception interval of the wireless home device is the signal reception time interval of the wireless home device under the comprehensive communication of the event message signal and the normal signal; the initial sending interval is the minimum interval time for the central console of the wireless network to send the event message, and the initial sending interval can be obtained at the central console of the wireless network.

[0082] In some embodiments, when the traffic anomaly index is greater than a preset traffic threshold, the wireless networking console is used to send event messages to the wireless home device in a proportional interval, and the signal reception interval of the wireless home device is monitored until the signal reception interval is the same as the initial transmission interval. In specific implementation, when the traffic anomaly index is greater than the preset traffic threshold, the wireless networking console is used to send an event message to the wireless home device, and after a fixed interval (i.e., the initial transmission interval), the wireless networking console is used to re-send the event message to the wireless home device, and the event message is sent again at the second time. After the message is sent, the signal receiving interval of the wireless home device is counted in the wireless home device, and the signal receiving interval is used as the sending interval. After the sending interval, the wireless networking central console is used to resend the event message to the wireless home device for the third time, and the above steps are repeated until the signal receiving interval is the same as the sending interval or the absolute value of the difference between the signal receiving interval and the sending interval is lower than the preset interval threshold, wherein the interval threshold is usually set to 0.1s. It should be noted that if the number of times the event message is sent exceeds 10 times and has not been terminated, the wireless home device is determined to be in normal state and the message sending is stopped.

[0083] It should be noted that through frequent message interactions, the abnormal status of nodes can be captured more quickly and accurately, rather than simply relying on single or small amounts of data detection. This helps to improve the accuracy of traffic anomaly detection, reduce missed reports and false alarms, and reduce the pressure on each communication node in the wireless network. Especially in large-scale network environments, it helps wireless networks save network resources while ensuring communication performance.

[0084] In some embodiments, the flow alarm threshold of the wireless home device is determined according to all signal reception intervals of the wireless home device in the sending event message, referring to Figure 3 As described above, the figure is a schematic diagram of a flow chart for determining a flow alarm threshold in some embodiments of the present application. In this embodiment, determining the flow alarm threshold can be implemented by the following steps:

[0085] In step 1041, the initial sending interval in the sending event message is obtained;

[0086] In step 1042, the total interval for sending the event message is determined according to all signal receiving intervals of the wireless home devices in the event message;

[0087] In step 1043, a flow alarm threshold of the wireless home device is determined according to the total sending interval and the initial sending interval.

[0088] It should be noted that, in the present application, the traffic alarm threshold is used to determine the alarm limit of traffic anomalies. Exceeding the traffic alarm threshold triggers the traffic alarm in the wireless network. In specific implementation, first, obtain the initial sending interval in the sending event message; then, obtain all signal receiving intervals in the sending event message, and the sum of all signal receiving intervals can be used as the total sending interval of the sending event message; finally, count the number of times the event message is sent as the number of transmissions n, and the ratio of the initial sending interval to the nth power to the total sending interval can be used as the traffic alarm threshold of the wireless home device.

[0089] In step 105, when the traffic anomaly index is greater than the traffic alarm threshold, a traffic anomaly alarm is sent to the central control station of the wireless network based on the location information of the wireless home device.

[0090] In some embodiments, issuing an abnormal traffic alarm to the central console of the wireless network based on the location information of the wireless home device means sending the location information of the wireless home device to the central console of the wireless network as an abnormal location to complete the abnormal alarm of the wireless home device in the wireless network.

[0091] In specific implementation, when the traffic anomaly index is less than or equal to the traffic alarm threshold, the wireless home device is in a normal communication state. When the traffic anomaly index is greater than the traffic alarm threshold, the wireless home device is in an abnormal communication state. It should be noted that other wireless home devices in the wireless network can use the alarm method in this solution to send an alarm.

[0092] In the present application, when the traffic anomaly index is greater than the traffic alarm threshold, a traffic anomaly alarm is sent to the central control station of the wireless networking based on the location information of the wireless home device; first, the traffic anomaly index is determined by the communication traffic information and the periodic distribution characteristics, and the abnormal degree of the traffic of the wireless home device in the current communication cycle can be obtained. The traffic anomaly index can be used as a basis for the abnormal degree of further alarm. Before the traffic anomaly index exceeds the preset traffic alarm threshold, the system will not directly trigger the alarm. The wireless networking can tolerate a certain degree of steady-state traffic fluctuations, reduce the possibility of false alarms caused by instantaneous fluctuations or temporary high loads, and ensure that the alarm system will only issue an alarm when the certainty is high. Among them, determining the periodic distribution characteristics can distinguish the regularity of traffic changes over time, thereby avoiding the normal The common periodic fluctuations are misjudged as abnormalities. Through periodic division, it can adapt to the traffic changes in different time periods and reduce the false alarms caused by periodic fluctuations of the load. Secondly, when the traffic anomaly index exceeds the preset traffic threshold, the traffic anomaly is further verified by sending event messages. The system uses a geometric interval to send messages and adjusts the sending interval according to the signal reception situation of the communication node to ensure that the real traffic anomaly is detected. Through the analysis of the traffic reception interval, the false alarms triggered by temporary traffic fluctuations are effectively reduced, making the alarm triggering more accurate, ensuring that only real traffic anomalies are captured, thereby avoiding false alarms. In summary, based on the above scheme, the dynamic threshold judgment of the traffic anomaly alarm in the wireless network can be realized, thereby reducing the false alarm rate of the alarm in the wireless communication network.

[0093] In addition, in another aspect of the present application, in some embodiments, the present application provides an artificial intelligence-based wireless communication network alarm system, wherein the wireless communication network is a wireless network formed by connecting multiple wireless home devices according to the Z-wave protocol, referring to Figure 4 , which is a schematic diagram of the structure of a wireless communication network alarm system based on artificial intelligence according to some embodiments of the present application. The wireless communication network alarm system based on artificial intelligence includes: a collection module 201, a processing module 202 and an execution module 203, which are respectively described as follows:

[0094] The collection module 201 in this application is mainly used to monitor the communication traffic in the wireless network and collect the historical communication traffic of the wireless home devices in the wireless network within a specified time period;

[0095] Processing module 202, in the present application, is used to extract steady-state traffic information in each communication cycle from all historical communication traffic through the periodicity of wireless networking, and then determine the periodic distribution characteristics of steady-state traffic in wireless home devices from all steady-state traffic information;

[0096] It should be noted that the processing module 202 is also used to monitor the communication flow information of the wireless home device in the current communication cycle in real time, perform feature matching on the period distribution feature based on the steady-state feature of the communication flow information, obtain the flow feature deviation of the wireless home device, and then determine the flow anomaly index of the wireless home device in the wireless network based on the flow feature deviation;

[0097] In addition, the processing module 202 is further used to send event messages to the wireless home devices at proportional intervals using the wireless networking console when the traffic anomaly index is greater than a preset traffic threshold, monitor the signal receiving interval of the wireless home devices until the signal receiving interval is the same as the initial sending interval, and determine the traffic alarm threshold of the wireless home devices according to all signal receiving intervals of the wireless home devices in the sent event message;

[0098] Execution module 203, in the present application, execution module 203 is mainly used to send a traffic anomaly alarm to the central control station of the wireless network based on the location information of the wireless home device when the traffic anomaly index is greater than the traffic alarm threshold.

[0099] The above describes in detail the examples of the wireless communication network alarm method and system based on artificial intelligence provided by the embodiments of the present application. It can be understood that in order to realize the above functions, the corresponding device includes hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0100] In some embodiments, the present application also provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned artificial intelligence-based wireless communication network alarm method.

[0101] In some embodiments, reference Figure 5, the dotted line in the figure indicates that the unit or the module is optional, and the figure is a schematic diagram of the structure of a computer device for implementing an artificial intelligence-based wireless communication network alarm method according to an embodiment of the present application. The artificial intelligence-based wireless communication network alarm method described in the above embodiment can be Figure 5 The computer device shown in the figure is implemented, and the computer device includes at least one processor 301, a memory 302 and at least one communication unit 305. The computer device can be a terminal device, a server or a chip.

[0102] The processor 301 may be a general-purpose processor or a special-purpose processor. For example, the processor 301 may be a central processing unit (CPU), which may be used to control the computer device, execute software programs, and process data of the software programs. The computer device may also include a communication unit 305 to implement signal input (reception) and output (transmission).

[0103] For example, the computer device may be a chip, the communication unit 305 may be an input and / or output circuit of the chip, or the communication unit 305 may be a communication interface of the chip, and the chip may be a component of a terminal device, a network device, or other devices.

[0104] For another example, the computer device may be a terminal device or a server, and the communication unit 305 may be a transceiver of the terminal device or the server, or the communication unit 305 may be a transceiver circuit of the terminal device or the server.

[0105] The computer device may include one or more memories 302, on which a program 304 is stored. The program 304 can be executed by the processor 301 to generate instructions 303, so that the processor 301 performs the method described in the above method embodiment according to the instructions 303. Optionally, data (such as a target audit model) can also be stored in the memory 302. Optionally, the processor 301 can also read the data stored in the memory 302, and the data can be stored at the same storage address as the program 304, or the data can be stored at a different storage address from the program 304.

[0106] The processor 301 and the memory 302 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of the terminal device.

[0107] It should be understood that each step of the above method embodiment can be completed by a hardware-based logic circuit or software-based instructions in the processor 301. The processor 301 can be a CPU, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, such as discrete gates, transistor logic devices, or discrete hardware components.

[0108] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0109] For example, in some embodiments, the present application also provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned artificial intelligence-based wireless communication network alarm method when executed.

[0110] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0111] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A wireless communication network alarm method based on artificial intelligence, wherein the wireless communication network is a wireless network formed by connecting multiple wireless home devices according to the Z-wave protocol, characterized in that: The steps include: Monitor the communication traffic in the wireless network and collect the historical communication traffic of wireless home devices in the wireless network within a specified time period; Through the periodicity of wireless networking, the steady-state traffic information under each communication cycle is extracted from all historical communication traffic, and then the periodic distribution characteristics of the steady-state traffic in the wireless home device are determined from all the steady-state traffic information; Real-time monitoring of the communication flow information of the wireless home device in the current communication cycle, feature matching of the period distribution feature based on the steady-state feature of the communication flow information, obtaining the flow feature deviation of the wireless home device, and then determining the flow anomaly index of the wireless home device in the wireless network based on the flow feature deviation; When the traffic anomaly index is greater than a preset traffic threshold, the wireless networking central console is used to send event messages to the wireless home devices at proportional intervals, and the signal receiving intervals of the wireless home devices are monitored until the signal receiving intervals are the same as the initial sending intervals, and the traffic alarm threshold of the wireless home devices is determined according to all signal receiving intervals of the wireless home devices in the sent event messages; When the traffic anomaly index is greater than the traffic alarm threshold, a traffic anomaly alarm is sent to the central control station of the wireless network based on the location information of the wireless home device.

2. The method according to claim 1, characterized in that The steady-state traffic information under each communication cycle is extracted from all historical communication traffic through the periodicity of wireless networking, including: Get the lower limit of communication traffic of wireless home devices; Filtering out all normal communication flows from all historical communication flows according to the communication flow lower limit; Dividing a specified time period into multiple communication cycles according to the periodicity of wireless networking; The steady-state traffic information in each communication cycle is obtained from all normal communication traffic.

3. The method according to claim 1, characterized in that The periodic distribution characteristics of the steady-state traffic in the wireless home device are determined by all the steady-state traffic information, specifically including: For each communication cycle, a steady-state flow mean value in the communication cycle is determined according to the steady-state flow information in the communication cycle; Determine all time domain distribution values ​​of the steady-state traffic in the communication cycle according to the steady-state traffic mean and each steady-state traffic value in the steady-state traffic information; The time domain distribution sub-features under the communication cycle are determined through all the time domain distribution values, and then the time domain distribution sub-features of the steady-state traffic under each communication cycle are obtained; The periodic distribution characteristics of steady-state traffic in wireless home devices are determined by all time-domain distribution sub-characteristics.

4. The method according to claim 1, characterized in that Performing feature matching on the periodic distribution feature based on the steady-state feature of the communication traffic information to obtain the traffic feature deviation of the wireless home device specifically includes: Get the communication traffic limit of wireless home devices; Matching the steady-state characteristics of the communication traffic information with the periodic distribution characteristics to obtain a traffic anomaly threshold value of the wireless home device; The flow characteristic deviation of the communication flow information is determined according to the flow anomaly threshold and the communication flow upper limit.

5. The method according to claim 1, characterized in that Determining the traffic alarm threshold of the wireless home device according to all signal receiving intervals of the wireless home device in the sending event message specifically includes: Get the initial sending interval in the sending event message; Determine the total interval for sending the event message according to all signal receiving intervals of the wireless home devices in the event message; The flow alarm threshold of the wireless home device is determined according to the total sending interval and the initial sending interval.

6. The method according to claim 1, characterized in that The signal receiving interval of the wireless home device is the signal receiving time interval of the wireless home device under the comprehensive communication of the event message signal and the normal signal.

7. The method according to claim 1, characterized in that The initial sending interval is the minimum interval time for the central control station of the wireless networking to send event messages.

8. A wireless communication network alarm system based on artificial intelligence, wherein the wireless communication network is a wireless network formed by connecting multiple wireless home devices according to the Z-wave protocol, characterized in that: include: A collection module is used to monitor the communication traffic in the wireless network and collect the historical communication traffic of the wireless home devices in the wireless network within a specified time period; A processing module, used to extract steady-state traffic information in each communication cycle from all historical communication traffic through the periodicity of wireless networking, and then determine the periodic distribution characteristics of steady-state traffic in wireless home devices from all steady-state traffic information; The processing module is also used to monitor the communication flow information of the wireless home device in the current communication cycle in real time, perform feature matching on the period distribution feature based on the steady-state feature of the communication flow information, obtain the flow feature deviation of the wireless home device, and then determine the flow anomaly index of the wireless home device in the wireless network based on the flow feature deviation; The processing module is also used to send event messages to the wireless home devices at proportional intervals using the wireless networking console when the traffic anomaly index is greater than a preset traffic threshold, monitor the signal receiving interval of the wireless home devices until the signal receiving interval is the same as the initial sending interval, and determine the traffic alarm threshold of the wireless home devices according to all signal receiving intervals of the wireless home devices in the sent event message; The execution module is used to send a traffic anomaly alarm to the central control station of the wireless network based on the location information of the wireless home device when the traffic anomaly index is greater than the traffic alarm threshold.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the artificial intelligence-based wireless communication network alarm method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions or codes, and when the instructions or codes are executed on a computer, the computer implements the artificial intelligence-based wireless communication network alarm method as described in any one of claims 1 to 7.

Images