Equipment interference removal method and system, terminal and storage medium
By obtaining device log data and building an AI abnormality detection model, automatically diagnosing and processing interference sources, the problems of low operation efficiency and low accuracy in the existing technology are solved, and efficient and stable communication between devices is achieved.
Patent Information
- Application Number
- CN202411191459.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2024-11-29
AI Technical Summary
In the prior art, operators rely on carrying the frequency sweeping equipment to locate and view the interference source on-site in the equipment signal coverage area. The operation efficiency is low and the accuracy is not high, resulting in poor equipment interference removal effect and affecting the normal operation of the equipment.
By obtaining device log data to calculate the health of the device, building an AI device abnormality detection model, automatically diagnose interference sources and perform interference processing, including device health monitoring, log analysis, deep neural network model training and adaptive frequency band selection.
It improves the efficiency and accuracy of equipment interference inspection, automatically handles interference problems, and ensures efficient communication and stable operation between equipment.
Smart Images

Figure CN119052840A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a device interference removal method, system, terminal and computer-readable storage medium. Background Art
[0002] In the early stage of wireless network construction, due to the imperfect coverage, there are more or less some weak coverage problems in the network. The equipment works in a nonlinear range, which will cause external interference such as uplink noise and intermodulation interference. External interference between devices will seriously affect the normal operation of the equipment. Therefore, it is necessary to promptly check the external interference source and remove the interference to ensure the normal use of the wireless network as a whole.
[0003] In the prior art, the method for troubleshooting external interference sources generally relies on operators carrying scanning equipment to locate the interference source in the area covered by the device signal and conduct on-site inspection. However, this interference troubleshooting method has the problems of low operating efficiency and low accuracy, which results in poor equipment interference removal effect and affects the normal operation of the equipment.
[0004] Therefore, the prior art still needs to be improved and developed. Summary of the invention
[0005] The main purpose of the present invention is to provide a device interference removal method, system, terminal and computer-readable storage medium, aiming to solve the problem that the interference troubleshooting method in the prior art relies on operators to carry scanning equipment, locate the interference source in the area covered by the device signal, and conduct on-site inspection, which has low operation efficiency and low accuracy, resulting in poor device interference removal effect and affecting the normal operation of the device.
[0006] To achieve the above object, the present invention provides a method for removing device interference, which comprises the following steps:
[0007] Obtaining device log data of multiple devices, and calculating the device health of each corresponding device according to each of the device log data;
[0008] If the device health corresponding to the target device among the multiple devices is less than a preset health threshold, the target device is determined to be in an abnormal device state, and the target log data corresponding to the target device is obtained;
[0009] Construct an AI device anomaly detection model, input the target log data into the AI device anomaly detection model, and output device anomaly diagnosis results;
[0010] A corresponding preset interference processing decision is determined according to the device abnormality diagnosis result, and device interference is removed from the target device according to the preset interference processing decision.
[0011] Optionally, in the device interference removal method, the device log data includes device operation log information and device operation events;
[0012] The acquiring of device log data of a plurality of devices and calculating the device health of each corresponding device according to each of the device log data specifically includes:
[0013] Acquire device operation log information and device operation events of each device through the soft bus, and input the device operation log information and the device operation events of each device into the device health monitoring model;
[0014] The health status of each device is evaluated by the device health monitoring model to obtain the device health status of each device.
[0015] Optionally, the device interference removal method, wherein the device operation log information and device operation events of each device are obtained through the soft bus, and the device operation log information and the device operation events of each device are input into the device health monitoring model, further comprising:
[0016] Obtain historical equipment operation log information, historical equipment operation events, and corresponding historical alarm information within a preset time period, and construct a training set and a test set based on the historical equipment operation log information, historical equipment operation events, and the historical alarm information;
[0017] The first preset deep neural network model is trained according to the training set to obtain an initial equipment health monitoring model, and the initial equipment health monitoring model is fine-tuned according to the test set to obtain the equipment health monitoring model.
[0018] Optionally, the device interference removal method, wherein if the device health corresponding to the target device among the multiple devices is less than a preset health threshold, determining that the target device is in an abnormal device state, and obtaining target log data corresponding to the target device, specifically includes:
[0019] Comparing the device health corresponding to the plurality of devices with a preset health threshold, if the device health corresponding to the target device among the plurality of devices is less than the preset health threshold, determining that the target device is in a device abnormal state;
[0020] An index keyword corresponding to the target device is obtained, and a search is performed in a preset log information database according to the index keyword to obtain target log data related to the target device.
[0021] Optionally, the device interference removal method, wherein the step of constructing an AI device anomaly detection model, inputting the target log data into the AI device anomaly detection model, and outputting a device anomaly diagnosis result, specifically includes:
[0022] Obtain historical device log data and corresponding fault information, and train a second preset deep neural network model according to the historical device log data and the fault information to obtain an AI device anomaly detection model;
[0023] The target log data is input into the AI device anomaly detection model, and the target log data is subjected to device anomaly analysis and processing by the AI device anomaly detection model to obtain a device anomaly diagnosis result.
[0024] Optionally, the device interference removal method, wherein the step of determining a corresponding preset interference processing decision according to the device abnormality diagnosis result, and performing device interference removal on the target device according to the preset interference processing decision, specifically includes:
[0025] If it is determined that the device abnormality diagnosis result is a wireless connection abnormality, then obtaining the current wireless environment state of the target device, wherein the wireless environment state includes: wireless signal strength and interference level;
[0026] The interference level of the target device is determined according to the wireless signal strength and the interference level. If the interference level is greater than or equal to a first preset interference level, the target wireless frequency band is determined according to the interference level, and the current frequency band of the target device is switched to the target wireless frequency band.
[0027] Optionally, the device interference removal method, wherein the step of determining the interference level of the target device according to the wireless signal strength and the interference level, further comprises:
[0028] If the interference level is less than the first preset interference level and greater than or equal to the second preset interference level, obtaining wireless connection parameters corresponding to the target device, wherein the wireless connection parameters include channel width and transmit power;
[0029] Parameter adjustment processing is performed on the channel width and the transmission power to obtain an optimized channel width and an optimized transmission power, and the interference level of the target device is made smaller than the second preset interference level according to the optimized channel width and the optimized transmission power.
[0030] In addition, to achieve the above-mentioned purpose, the present invention further provides a device interference removal system, wherein the device interference removal system comprises:
[0031] The device health calculation module is used to obtain device log data of multiple devices and calculate the device health of each corresponding device according to each of the device log data;
[0032] A device status judgment module, configured to determine that the target device among the plurality of devices is in an abnormal device state if the device health corresponding to the target device is less than a preset health threshold, and obtain target log data corresponding to the target device;
[0033] A diagnosis result output module, used to build an AI device anomaly detection model, input the target log data into the AI device anomaly detection model, and output the device anomaly diagnosis result;
[0034] The device interference removal module is used to determine a corresponding preset interference processing decision according to the device abnormality diagnosis result, and remove device interference from the target device according to the preset interference processing decision.
[0035] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a device interference removal program stored in the memory and executable on the processor, and when the device interference removal program is executed by the processor, the steps of the device interference removal method described above are implemented.
[0036] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a device interference removal program, and when the device interference removal program is executed by a processor, the steps of the device interference removal method described above are implemented.
[0037] In the present invention, the device log data of multiple devices are obtained, and the device health of each corresponding device is calculated according to each of the device log data; if the device health corresponding to the target device among the multiple devices is less than the preset health threshold, the target device is determined to be in an abnormal device state, and the target log data corresponding to the target device is obtained; an AI device abnormality detection model is constructed, the target log data is input into the AI device abnormality detection model, and the device abnormality diagnosis result is output; the corresponding preset interference processing decision is determined according to the device abnormality diagnosis result, and the device interference of the target device is removed according to the preset interference processing decision. The present invention detects the operating status of the device by obtaining the log information and event information of each device. When it is found that the operating status of the device is abnormal, all relevant log data are obtained and input into the AI device abnormality detection model to identify the type of interference and automatically switch to the frequency band with less interference, which effectively reduces the interference between devices and ensures efficient communication and stable operation between devices. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] Figure 1 It is a flow chart of a preferred embodiment of the device interference removal method of the present invention;
[0039] Figure 2 It is a structural diagram of a preferred embodiment of the device interference removal system of the present invention;
[0040] Figure 3 It is a structural diagram of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION
[0041] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0042] In the early stage of wireless network construction, due to the imperfect coverage, there are more or less some weak coverage problems in the network. The equipment works in a nonlinear range, which will cause external interference such as uplink noise and intermodulation interference. External interference between devices will seriously affect the normal operation of the equipment. Therefore, it is necessary to promptly check the external interference source and remove the interference to ensure the normal use of the wireless network as a whole.
[0043] In the prior art, the method for troubleshooting external interference sources generally relies on operators carrying scanning equipment to locate the interference source in the area covered by the device signal and conduct on-site inspection. However, this interference troubleshooting method has the problems of low operating efficiency and low accuracy, which results in poor equipment interference removal effect and affects the normal operation of the equipment.
[0044] To solve the above problems, the present invention proposes a method for troubleshooting and removing device interference, which relies on distributed characteristics to provide powerful device management and fault diagnosis capabilities. The core characteristics of the distributed characteristics include: distributed technology advantages, system-level logs, device management, wireless connection optimization, and physical isolation and shielding.
[0045] The advantages of distributed technology include distributed diagnostic tools and inter-device communication monitoring. Distributed diagnostic tools: utilizing the distributed characteristics, a unified set of diagnostic tools is designed to perform troubleshooting across multiple devices; inter-device communication monitoring: monitoring the communication between devices through DSoftBus (distributed soft bus) to find potential sources of interference.
[0046] 1. System-level logs include system log analysis and device health monitoring. System log analysis: Obtain detailed system log records of the device, which can be used to analyze the device's operating status and potential interference problems; Device health monitoring: Evaluate the overall operating status of the device through the health monitoring tools provided by the system.
[0047] 2. Device management includes device manager and intelligent diagnosis, among which, device manager: the device manager can help users manage connected devices and troubleshoot possible interference problems; intelligent diagnosis: use AI technology to assist in diagnosing device failures and identify potential interference sources. Wireless connection optimization includes intelligent connection management and adaptive frequency band selection, among which, intelligent connection management: the present invention can automatically optimize wireless connections according to network conditions and reduce interference; adaptive frequency band selection: the present invention can automatically select the most suitable wireless frequency band according to the surrounding environment to avoid interference.
[0048] 3. Physical isolation and shielding include equipment isolation and shielding measures. Equipment isolation: interference sources can be identified through physical isolation; shielding measures: shielding materials can be used to reduce electromagnetic interference between devices.
[0049] The device interference removal method described in the preferred embodiment of the present invention is as follows: Figure 1 As shown, the device interference removal method includes the following steps:
[0050] Step S10: Obtain device log data of multiple devices, and calculate the device health of each corresponding device according to each device log data. The device log data includes device operation log information and device operation events.
[0051] Distributed diagnostic tools: The present invention utilizes the distributed characteristics to provide a unified set of diagnostic tools that can perform troubleshooting across multiple devices. This toolset includes functions such as system-level logging and device health monitoring, which can help users quickly locate problems. Specifically, the distributed diagnostic tools provided by the present invention support log synchronization between multiple devices, allowing developers or technical support personnel to view the log information of all devices in the entire distributed system on a single device. This cross-device log viewing capability greatly simplifies the problem location process, especially when dealing with distributed inter-device communication problems. In addition, the present invention also provides a visualization tool for inter-device communication, which can intuitively display the communication links and data flows between devices, helping users to more quickly identify potential sources of interference.
[0052] The device log data in the present invention refers to a time-ordered collection of certain operations and operation results of the device specified by the system. Each log file consists of log records, and each log record describes a separate system event. Usually, the system log is a text file that can be read directly by the user, which contains a timestamp and a message or other information specific to the subsystem. The device health in the present invention refers to whether the device can generate logs normally within the corresponding time period.
[0053] Specifically, historical equipment operation log information, historical equipment operation events and corresponding historical alarm information within a preset time period are obtained, and a training set and a test set are constructed according to the historical equipment operation log information, historical equipment operation events and the historical alarm information; a first preset deep neural network model is trained according to the training set to obtain an initial equipment health monitoring model, and the initial equipment health monitoring model is fine-tuned according to the test set to obtain the equipment health monitoring model.
[0054] The device operation log information and device operation events of each device are obtained through the soft bus, and the device operation log information and the device operation events of each device are input into the device health monitoring model; the health of each device is evaluated through the device health monitoring model to obtain the device health corresponding to each device.
[0055] It can be understood that the construction process of the equipment health monitoring model of the present invention includes: randomly extracting the same number of normal operation log information and normal operation events as the distribution network equipment in the historical operation log, and using the normal operation log information and normal operation events as the positive data set; using the abnormal operation log information, abnormal operation events and the corresponding historical alarm information as the negative data set, mixing the positive data set and the negative data set to obtain the total data set, and taking 80% of the data as the training set, and the remaining 20% as the test set.
[0056] After the training set and the test set are constructed, the first preset deep neural network model is trained according to the training set, wherein the present invention preferably adopts a decision tree detection model for the first preset deep neural network model, and other detection models can also be used, and the initial equipment health monitoring model is obtained after training. Afterwards, in order to verify the accuracy of the initial equipment health monitoring model, the test set can be input into the initial equipment health monitoring model, and the similarity of the model output results can be calculated, and the model parameters of the initial equipment health monitoring model can be adjusted according to the similarity to obtain the equipment health monitoring model.
[0057] The process of obtaining the current operation log data of each device is as follows: when the host is in operation or processing system events, continuous log data will be generated in real time. The log data is used to record the host's operating status, operation instructions and other information. For example, the log data can be a host operation log, a host login log, etc.
[0058] When the model is built, the device operation log information and device operation events of each current device can be input into the device health monitoring model. At this time, the trained device health monitoring model can perform health assessment on the input device operation log information and device operation events, and output the corresponding health of each device.
[0059] Regarding the system-level log analysis process: the present invention provides detailed system log records that can be used to analyze the operating status of the device and potential interference problems. The system log contains records of various events generated during the startup and operation of the device. By analyzing these records, the specific cause of the interference can be traced. The log system of the present invention not only records conventional log information, but also captures key system behaviors and abnormal situations, such as changes in network connection status, abnormal process termination, etc. The log system set up by the present invention supports log filtering and search functions. Users can quickly locate related log entries based on keywords, which greatly improves the efficiency of problem troubleshooting. In addition, the system also supports remote log collection. Even if the device is not around, logs can be collected through the network for analysis.
[0060] Step S20: If the device health corresponding to the target device among the multiple devices is less than a preset health threshold, it is determined that the target device is in an abnormal device state, and the target log data corresponding to the target device is obtained.
[0061] Specifically, the device health corresponding to the multiple devices is compared with a preset health threshold. If the device health corresponding to the target device among the multiple devices is less than the preset health threshold, the target device is determined to be in an abnormal device state; the index keyword corresponding to the target device is obtained, and the preset log information database is searched according to the index keyword to obtain the target log data related to the target device.
[0062] Device management: The device manager provided in the present invention can help users manage connected devices and troubleshoot possible interference problems. The device manager can display the status of connected devices, including but not limited to device model, connection method, signal strength and other information. In addition, the device manager can also be used to synchronize configurations between devices to ensure that all devices are in a consistent working state. The device manager of the present invention not only provides basic information about the device, but also supports configuration synchronization between devices. This means that after the user sets the parameters on one device, these parameters can be synchronized to other devices to ensure that the settings of all devices are consistent, thereby reducing interference problems caused by differences in device configuration. In addition, the device manager also provides a remote control function between devices, allowing the user to control another device on one device, which is very helpful for troubleshooting interference between devices.
[0063] Before comparing the health of the devices, a health threshold table of the devices will be set in advance, wherein the health threshold table is set with the health threshold corresponding to each device. If the health of the device is greater than the corresponding health threshold, it proves that the device is operating normally. Otherwise, if it is less than, it proves that there is an abnormality in the device's operating status.
[0064] When the device health is greater than or equal to the corresponding preset health threshold, it indicates that the log transmission of the corresponding device within the preset period is normal, that is, the log collection of the master device is normal, and at this time, it can be determined that the log data of the device corresponding to the device health is in a healthy state. When the device health is less than the corresponding preset health threshold, it indicates that the log transmission of the corresponding device within the preset period is abnormal, that is, the log collection of the device is abnormal, and at this time, it can be determined that the log data of the device corresponding to the device health is in an abnormal state.
[0065] Furthermore, after the present invention determines that there is an abnormal target device based on the device health, it will search in the log database, use the target device name as a keyword, index, and extract all log information and operation events related to the target device in the log database.
[0066] Step S30: construct an AI device anomaly detection model, input the target log data into the AI device anomaly detection model, and output the device anomaly diagnosis result.
[0067] Specifically, historical equipment log data and corresponding fault information are obtained, and a second preset deep neural network model is trained according to the historical equipment log data and the fault information to obtain an AI equipment anomaly detection model; the target log data is input into the AI equipment anomaly detection model, and the target log data is subjected to equipment anomaly analysis and processing by the AI equipment anomaly detection model to obtain an equipment anomaly diagnosis result.
[0068] Historical equipment log data is a historical log generated according to the log generation rules of each component of each device. The historical operation log data can come from the operation and maintenance database, such as the in-band log data file and out-of-band log data file collected from the client when the user repairs the equipment, involving different hardware of the server. It can also be constructed according to the actual historical operation log data, and can also receive input historical operation log data. In order to detect the root cause of the equipment failure, the historical operation log data includes historical fault log data and historical normal log data. The historical fault log data is log data that contains abnormal state monitoring values. Historical normal log data can include regular log data generated by the component that generates the historical fault log data in the adjacent time period when the fault occurs, as well as regular log data generated by other components other than the component that generates the historical fault log data at the time point when the fault occurs.
[0069] After obtaining the historical device log data, the present invention uses the historical device log data as a training set and the corresponding fault information as a training label to implement the training process of the second preset deep neural network model. Among them, the second preset deep neural network model in the present invention preferably adopts a classification model, such as an XGBoost model. When the model training is completed, the AI device anomaly detection model is obtained.
[0070] After the AI device anomaly detection model is trained, the target log data corresponding to the target device with an abnormal status can be input into the AI device anomaly detection model to obtain the device diagnosis result of the target device.
[0071] Intelligent diagnosis: The present invention uses AI technology to assist in the diagnosis of equipment failures and identify potential sources of interference. The intelligent diagnosis function can automatically analyze the log data of the equipment, and give possible causes of failure and suggested solutions, which greatly reduces the time and effort of manual troubleshooting. The intelligent diagnosis function set in the present invention is based on a deep learning model, which can learn the patterns and laws of equipment failures from massive historical log data. When the system detects new log entries, it can quickly identify the association between these entries and known failure modes, and give corresponding fault diagnosis reports. In addition, the intelligent diagnosis function also supports self-learning capabilities, that is, as time goes by, the system can continuously learn new failure modes, thereby improving the accuracy of diagnosis. This method not only reduces the workload of technicians, but also improves the speed and quality of problem solving.
[0072] In addition, the present invention can also set up AI-driven adaptive interference management, and adopt more advanced AI algorithms to achieve adaptive interference management, including: 1. Deep learning prediction model: using deep learning technology to train the prediction model, it can predict possible interference in advance and take preventive measures; 2. Self-learning and optimization: the system can self-learn based on historical data and continuously optimize the interference management strategy to adapt to the ever-changing environment; 3. Situational awareness: through sensors and environmental perception technology, the system can perceive changes in the surrounding environment in real time and adjust the interference management strategy accordingly. This adaptive interference management system can not only reduce human intervention, but also improve the intelligence level of the system, making communication between devices smoother.
[0073] Step S40: determining a corresponding preset interference processing decision according to the device abnormality diagnosis result, and removing device interference from the target device according to the preset interference processing decision.
[0074] Specifically, if it is determined that the abnormal diagnosis result of the device is a wireless connection abnormality, the current wireless environment status of the target device is obtained, wherein the wireless environment status includes: wireless signal strength and interference level; the interference level of the target device is determined according to the wireless signal strength and the interference level, and if the interference level is greater than or equal to a first preset interference level, the target wireless frequency band is determined according to the interference level, and the current frequency band of the target device is switched to the target wireless frequency band.
[0075] When the abnormal diagnosis result of the device is determined to be a wireless connection abnormality, the frequency band of the target device being interfered with is obtained, and a search is performed in the pre-stored channel configuration table to find the frequency band range corresponding to the frequency band of the interfered device. The channel corresponding to the frequency band range is the interfered channel. The current working channel of the target device is obtained to determine whether the current working channel of the target device is consistent with the interfered target device. If they are consistent, the wireless connection of the target device is determined to be abnormal, indicating that the current working channel is being interfered with and needs to be avoided.
[0076] After confirming that the current working channel of the target device is the interfered channel, the present invention avoids signal interference by switching channels. First, the interfered channels are removed from the channel configuration table, and the remaining channels can be used as optional channels to be switched.
[0077] For the frequency bands corresponding to the switchable channels, on the one hand, the present invention will judge the interference level of the target device; on the other hand, the present invention will sort the priorities of the frequency bands. After obtaining the interference level of the target device, the corresponding target frequency band is selected for the target device according to the frequency band configuration table, and the current frequency band of the target device is switched to the target frequency band. In this way, the interference problem of the target device is solved, and at the same time, the frequency band efficiency is maximized.
[0078] Further, if the interference level is less than the first preset interference level and greater than or equal to the second preset interference level, the wireless connection parameters corresponding to the target device are obtained, wherein the wireless connection parameters include channel width and transmit power; parameter adjustment processing is performed on the channel width and the transmit power to obtain an optimized channel width and an optimized transmit power, and the interference level of the target device is made less than the second preset interference level according to the optimized channel width and the optimized transmit power. The first preset interference level is greater than the second preset interference level.
[0079] If the interference level of the target device is less than the first preset interference level and greater than or equal to the second preset interference level, the interference to the target device can be reduced by adjusting the wireless connection parameters. In the present invention, the interference to the target device can be adjusted by adjusting the optimized channel width and the optimized transmission power to achieve normal operation of the target device.
[0080] Wireless connection optimization: The present invention can automatically optimize wireless connections and reduce interference according to network conditions. Specifically, the system can automatically select the most suitable wireless frequency band according to the surrounding environment to avoid interference caused by signal overlap. In addition, the present invention also supports adaptive frequency band selection. When it is detected that the signal quality of a certain frequency band is poor, it can automatically switch to other frequency bands to maintain the best communication quality. The wireless connection optimization function of the present invention is not limited to frequency band selection, but also includes optimization measures in many aspects such as channel width adjustment and transmission power control. The system regularly monitors the status of the current wireless environment, including indicators such as signal strength and interference level, and adjusts the relevant parameters of the wireless connection according to these indicators. For example, when it is detected that the current frequency band is severely interfered, the system will automatically select a frequency band with less interference and adjust the transmission power to achieve the best signal coverage. This automated wireless connection optimization function can significantly improve the communication quality and stability between devices.
[0081] In addition to the above-mentioned frequency band adjustment to achieve interference reduction, the present invention can also adopt physical isolation and shielding methods.
[0082] The present invention adopts physical isolation and shielding measures to reduce electromagnetic interference between devices. Although these measures are not directly controlled by the operating system, the present invention provides guidelines and suggestions to help users take appropriate physical isolation and shielding measures to reduce interference. The physical isolation suggestions provided by the present invention include the minimum safe distance between devices, the use of metal shielding boxes or shielding materials to wrap devices, etc. In addition, the present invention also provides suggestions on how to arrange devices to reduce electromagnetic interference between devices. For example, it is recommended to place wireless routers and Bluetooth devices in different rooms or away from each other to reduce mutual interference between signals. In addition, the present invention also recommends the use of shielded cables and connectors to further reduce signal interference. Although these physical isolation and shielding measures are not directly controlled by the operating system, by following the suggestions provided by the AI device anomaly detection model in the present invention, users can effectively reduce interference problems between devices.
[0083] Intelligent frequency management: The present invention uses intelligent frequency management technology to automatically detect and adjust the wireless frequency bands used by the device to avoid interference with other devices. This technology uses a spectrum sensing algorithm to identify which frequency bands are less interfered with and automatically switch to these frequency bands for communication. The intelligent frequency management function can not only avoid interference between devices, but also improve the throughput and communication quality of the overall network. The intelligent frequency management technology set in the present invention is based on a spectrum sensing algorithm, which can monitor the spectrum usage in a wireless environment in real time. When the system detects that a certain frequency band is subject to more interference, it will automatically switch the device to a frequency band with less interference for communication. In addition, the technology also supports frequency band priority setting, which can allocate the optimal frequency band resources according to the importance of the device and the urgency of the task. This method can not only improve the communication quality between devices, but also effectively utilize spectrum resources and reduce resource waste.
[0084] Through the comprehensive application of the above technical solutions, the present invention provides users with a comprehensive device interference troubleshooting solution, which not only improves the interoperability and user experience between devices, but also lays a solid foundation for building a more stable and reliable Internet of Things environment.
[0085] In summary, the key technologies for device interference troubleshooting in the present invention include 1. Distributed diagnostic tools, supporting log synchronization and visual communication links between multiple devices; 2. System-level log analysis, providing detailed log records and filtering search functions; 3. Device management, realizing device information display, configuration synchronization and remote control; 4. Intelligent diagnosis, using AI technology to automatically analyze logs and give fault diagnosis reports; 5. Wireless connection optimization, automatically selecting the appropriate frequency band and adjusting related parameters to reduce interference; 6. Physical isolation and shielding, providing guidelines to reduce electromagnetic interference; 7. Intelligent frequency management, automatically detecting and adjusting wireless frequency bands to avoid interference between devices. The comprehensive application of these technical solutions ensures efficient communication and stable operation between devices.
[0086] In addition, the present invention can also set up advanced spectrum sensing and dynamic frequency band allocation: With the development of 5G and even 6G technology, the present invention also uses more advanced spectrum sensing technology to optimize wireless communications, including: 1. Advanced spectrum sensing algorithm: Use more advanced algorithms to detect available spectrum and use spectrum resources in a more efficient way; 2. Dynamic frequency band allocation: Dynamically adjust the frequency band used by the device according to actual needs and environmental changes to ensure the best communication quality; 3. Intelligent spectrum sharing: Coordinate the use of spectrum between multiple devices through intelligent algorithms to reduce interference and improve spectrum utilization. This advanced spectrum sensing and dynamic frequency band allocation technology will further improve the communication quality and stability between devices, and also provide the possibility of building a more intelligent and efficient Internet of Things environment.
[0087] Furthermore, if Figure 2 As shown, based on the above-mentioned device interference removal method, the present invention also provides a device interference removal system accordingly, wherein the device interference removal system includes:
[0088] The device health calculation module 51 is used to obtain device log data of multiple devices and calculate the device health of each corresponding device according to each of the device log data;
[0089] The device status judgment module 52 is used to determine that the target device is in an abnormal device state if the device health corresponding to the target device among the multiple devices is less than a preset health threshold, and obtain the target log data corresponding to the target device;
[0090] A diagnosis result output module 53 is used to build an AI device anomaly detection model, input the target log data into the AI device anomaly detection model, and output the device anomaly diagnosis result;
[0091] The device interference removal module 54 is used to determine a corresponding preset interference processing decision according to the device abnormality diagnosis result, and remove device interference from the target device according to the preset interference processing decision.
[0092] Furthermore, if Figure 3 As shown, based on the above-mentioned device interference removal method and system, the present invention also provides a terminal accordingly, and the terminal includes a processor 10, a memory 20 and a display 30. Figure 3 Only some components of the terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.
[0093] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed in the terminal, such as the program code of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a device interference removal program 40 is stored on the memory 20, and the device interference removal program 40 can be executed by the processor 10, thereby realizing the device interference removal method in the present application.
[0094] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the device interference removal method.
[0095] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface. The components 10-30 of the terminal communicate with each other via a system bus.
[0096] In one embodiment, when the processor 10 executes the device interference removal program 40 in the memory 20, the following steps are implemented:
[0097] Obtaining device log data of multiple devices, and calculating the device health of each corresponding device according to each of the device log data;
[0098] If the device health corresponding to the target device among the multiple devices is less than a preset health threshold, the target device is determined to be in an abnormal device state, and the target log data corresponding to the target device is obtained;
[0099] Construct an AI device anomaly detection model, input the target log data into the AI device anomaly detection model, and output device anomaly diagnosis results;
[0100] A corresponding preset interference processing decision is determined according to the device abnormality diagnosis result, and device interference is removed from the target device according to the preset interference processing decision.
[0101] Wherein, the device log data includes device operation log information and device operation events;
[0102] The acquiring of device log data of a plurality of devices and calculating the device health of each corresponding device according to each of the device log data specifically includes:
[0103] Acquire device operation log information and device operation events of each device through the soft bus, and input the device operation log information and the device operation events of each device into the device health monitoring model;
[0104] The health status of each device is evaluated by the device health monitoring model to obtain the device health status of each device.
[0105] Wherein, the device operation log information and device operation events of each device are obtained through the soft bus, and the device operation log information and the device operation events of each device are input into the device health monitoring model, and the above also includes:
[0106] Obtain historical equipment operation log information, historical equipment operation events, and corresponding historical alarm information within a preset time period, and construct a training set and a test set based on the historical equipment operation log information, historical equipment operation events, and the historical alarm information;
[0107] The first preset deep neural network model is trained according to the training set to obtain an initial equipment health monitoring model, and the initial equipment health monitoring model is fine-tuned according to the test set to obtain the equipment health monitoring model.
[0108] If the device health corresponding to the target device among the multiple devices is less than a preset health threshold, it is determined that the target device is in an abnormal device state, and the target log data corresponding to the target device is obtained, specifically including:
[0109] Comparing the device health corresponding to the plurality of devices with a preset health threshold, if the device health corresponding to the target device among the plurality of devices is less than the preset health threshold, determining that the target device is in a device abnormal state;
[0110] An index keyword corresponding to the target device is obtained, and a search is performed in a preset log information database according to the index keyword to obtain target log data related to the target device.
[0111] The step of constructing an AI device anomaly detection model, inputting the target log data into the AI device anomaly detection model, and outputting device anomaly diagnosis results specifically includes:
[0112] Obtain historical device log data and corresponding fault information, and train a second preset deep neural network model according to the historical device log data and the fault information to obtain an AI device anomaly detection model;
[0113] The target log data is input into the AI device anomaly detection model, and the target log data is subjected to device anomaly analysis and processing by the AI device anomaly detection model to obtain a device anomaly diagnosis result.
[0114] The step of determining a corresponding preset interference processing decision according to the device abnormality diagnosis result, and removing device interference from the target device according to the preset interference processing decision, specifically includes:
[0115] If it is determined that the device abnormality diagnosis result is a wireless connection abnormality, then obtaining the current wireless environment state of the target device, wherein the wireless environment state includes: wireless signal strength and interference level;
[0116] The interference level of the target device is determined according to the wireless signal strength and the interference level. If the interference level is greater than or equal to a first preset interference level, the target wireless frequency band is determined according to the interference level, and the current frequency band of the target device is switched to the target wireless frequency band.
[0117] The step of determining the interference level of the target device according to the wireless signal strength and the interference level further includes:
[0118] If the interference level is less than the first preset interference level and greater than or equal to the second preset interference level, obtaining wireless connection parameters corresponding to the target device, wherein the wireless connection parameters include channel width and transmit power;
[0119] Parameter adjustment processing is performed on the channel width and the transmission power to obtain an optimized channel width and an optimized transmission power, and the interference level of the target device is made smaller than the second preset interference level according to the optimized channel width and the optimized transmission power.
[0120] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a device interference removal program, and when the device interference removal program is executed by a processor, the steps of the device interference removal method described above are implemented.
[0121] In summary, the present invention provides a method, system, terminal and computer-readable storage medium for removing device interference, the method comprising: obtaining device log data of multiple devices, and calculating the device health of each corresponding device according to each device log data; if the device health corresponding to the target device in the multiple devices is less than the preset health threshold, the target device is determined to be in an abnormal device state, and the target log data corresponding to the target device is obtained; an AI device abnormality detection model is constructed, the target log data is input into the AI device abnormality detection model, and the device abnormality diagnosis result is output; the corresponding preset interference processing decision is determined according to the device abnormality diagnosis result, and the device interference is removed from the target device according to the preset interference processing decision. The present invention detects the operating status of the device by acquiring the log information and event information of each device. When it is found that the operating status of the device is abnormal, all relevant log data are obtained and input into the AI device abnormality detection model to identify the type of interference and automatically switch to the frequency band with less interference, which effectively reduces the interference between devices and ensures efficient communication and stable operation between devices.
[0122] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or terminal including the element.
[0123] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium that can be read by a computer, and the program can include the processes of the above-mentioned method embodiments when executed. The computer-readable storage medium can be a memory, a disk, an optical disk, etc.
[0124] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.
Claims
1. A method for removing device interference, characterized in that: The device interference removal method comprises: Obtaining device log data of multiple devices, and calculating the device health of each corresponding device according to each of the device log data; If the device health corresponding to the target device among the multiple devices is less than a preset health threshold, the target device is determined to be in an abnormal device state, and the target log data corresponding to the target device is obtained; Construct an AI device anomaly detection model, input the target log data into the AI device anomaly detection model, and output device anomaly diagnosis results; A corresponding preset interference processing decision is determined according to the device abnormality diagnosis result, and device interference is removed from the target device according to the preset interference processing decision.
2. The device interference removal method according to claim 1, characterized in that: The device log data includes device operation log information and device operation events; The acquiring of device log data of a plurality of devices and calculating the device health of each corresponding device according to each of the device log data specifically includes: Acquire device operation log information and device operation events of each device through the soft bus, and input the device operation log information and the device operation events of each device into the device health monitoring model; The health status of each device is evaluated by the device health monitoring model to obtain the device health status of each device.
3. The device interference removal method according to claim 2, characterized in that: The device operation log information and device operation events of each device are obtained through the soft bus, and the device operation log information and the device operation events of each device are input into the device health monitoring model, and the following is also included: Obtain historical equipment operation log information, historical equipment operation events, and corresponding historical alarm information within a preset time period, and construct a training set and a test set based on the historical equipment operation log information, historical equipment operation events, and the historical alarm information; The first preset deep neural network model is trained according to the training set to obtain an initial equipment health monitoring model, and the initial equipment health monitoring model is fine-tuned according to the test set to obtain the equipment health monitoring model.
4. The device interference removal method according to claim 1, characterized in that: If the device health corresponding to the target device among the multiple devices is less than a preset health threshold, determining that the target device is in an abnormal device state, and obtaining target log data corresponding to the target device, specifically includes: Comparing the device health corresponding to the plurality of devices with a preset health threshold, if the device health corresponding to the target device among the plurality of devices is less than the preset health threshold, determining that the target device is in a device abnormal state; An index keyword corresponding to the target device is obtained, and a search is performed in a preset log information database according to the index keyword to obtain target log data related to the target device.
5. The device interference removal method according to claim 1, characterized in that: The constructing of the AI device anomaly detection model, inputting the target log data into the AI device anomaly detection model, and outputting the device anomaly diagnosis result specifically includes: Obtain historical device log data and corresponding fault information, and train a second preset deep neural network model according to the historical device log data and the fault information to obtain an AI device anomaly detection model; The target log data is input into the AI device anomaly detection model, and the target log data is subjected to device anomaly analysis and processing by the AI device anomaly detection model to obtain a device anomaly diagnosis result.
6. The device interference removal method according to claim 1, characterized in that: The determining a corresponding preset interference processing decision according to the device abnormality diagnosis result, and performing device interference removal on the target device according to the preset interference processing decision, specifically includes: If it is determined that the device abnormality diagnosis result is a wireless connection abnormality, then obtaining the current wireless environment state of the target device, wherein the wireless environment state includes: wireless signal strength and interference level; The interference level of the target device is determined according to the wireless signal strength and the interference level. If the interference level is greater than or equal to a first preset interference level, the target wireless frequency band is determined according to the interference level, and the current frequency band of the target device is switched to the target wireless frequency band.
7. The device interference removal method according to claim 6, characterized in that: The step of determining the interference level of the target device according to the wireless signal strength and the interference level further includes: If the interference level is less than the first preset interference level and greater than or equal to the second preset interference level, obtaining wireless connection parameters corresponding to the target device, wherein the wireless connection parameters include channel width and transmit power; Parameter adjustment processing is performed on the channel width and the transmission power to obtain an optimized channel width and an optimized transmission power, and the interference level of the target device is made smaller than the second preset interference level according to the optimized channel width and the optimized transmission power.
8. A device interference removal system, characterized in that: The equipment interference removal system comprises: The device health calculation module is used to obtain device log data of multiple devices and calculate the device health of each corresponding device according to each of the device log data; A device status judgment module, configured to determine that the target device among the plurality of devices is in an abnormal device state if the device health corresponding to the target device among the plurality of devices is less than a preset health threshold, and obtain target log data corresponding to the target device; A diagnosis result output module, used to build an AI device anomaly detection model, input the target log data into the AI device anomaly detection model, and output the device anomaly diagnosis result; The device interference removal module is used to determine a corresponding preset interference processing decision according to the device abnormality diagnosis result, and remove device interference from the target device according to the preset interference processing decision.
9. A terminal, characterized in that: The terminal includes: a memory, a processor, and a device interference removal program stored in the memory and executable on the processor, wherein the device interference removal program implements the steps of the device interference removal method according to any one of claims 1 to 7 when executed by the processor.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a device interference removal program, and when the device interference removal program is executed by a processor, the steps of the device interference removal method according to any one of claims 1 to 7 are implemented.
Citation Information
Cited By
Detection method and system of track lighting equipment, terminal and storage medium
CN119807933A
