33results about How to "Improve Anomaly Detection Efficiency" patented technology

The invention discloses a sensor anomaly detection method based on a conditional diffusion probability model and a related system, the system comprises a data acquisition processing unit, a detection model unit and an anomaly detection unit, anomaly is detected by using the conditional probability diffusion model, noise is predicted by adding and removing noise and using a U-Net model, and data is reconstructed. Completing the training of a detection model, and obtaining a trained detection model; and taking the distance between the to-be-detected data and the noise reconstruction data obtained by the trained detection model corresponding to the to-be-detected data as an abnormal score, and if the abnormal score exceeds a threshold value, determining that the data is abnormal. According to the invention, the monitoring accuracy is improved, the false alarm is reduced, the anti-noise capability is enhanced, the noise is effectively identified, and the pertinence is high.

The invention discloses a railway fastener anomaly detection method and device, a medium and a product, and relates to the field of railway fastener anomaly detection. The method comprises the following steps: acquiring image data of a target rail; inputting the image data of the target rail into the fastener identification model to obtain an identification result; the identification result comprises position information of a target fastener in the image data of the target rail; the fastener identification model is obtained by training a neural network through a training data set; inputting the identification result and the image data corresponding to the identification result into a fastener anomaly detection model to obtain a detection result; detecting the position information of the abnormal fastener, the non-abnormal fastener and the abnormal fastener; wherein the fastener anomaly detection model is obtained by training an image classification neural network model through a training data set; the training data set comprises fastener image sample data and corresponding category labels; the category labels include normality, looseness and shielding. According to the invention, the railway fastener abnormity detection efficiency can be improved.

The invention relates to the technical field of data processing, in particular to a coating equipment fault real-time early warning method, which comprises the following steps of: acquiring pressure data and vibration data, acquiring instability of each pressure data according to surrounding data of each pressure data, and determining whether each pressure data is unstable or not according to the instability of each pressure data. Obtaining a characteristic value of each piece of pressure data, obtaining the optimal degree of each clustering result according to the characteristic value of each piece of pressure data and the correlation of the abnormal degree of each piece of pressure data in each clustering result, obtaining the optimal number of midpoints, obtaining the optimal clustering result, and obtaining the optimal clustering result according to the optimal clustering result. The final anomaly degree of each piece of pressure data is obtained, then the fault of the coating equipment is judged, and the anomaly detection accuracy is improved.

The invention relates to the field of video inspection, in particular to an active video inspection system based on Internet of Things driving, which comprises a current analysis module, an image input module, an image input detection module, an image output detection module and an audio detection module. According to the method, the current of the conference room equipment is monitored, abnormal equipment is found in time, rapid fault diagnosis is achieved, the effectiveness of the video stream is effectively judged by obtaining and processing the video stream and analyzing the grayscale image, it is ensured that the input picture is always in an available state, the blank screen phenomenon and picture distortion are avoided, and the user experience is improved. The image output detection module verifies the display effect, ensures the accuracy of an output picture and determines an abnormal area when the output picture is abnormal, the audio detection module plays a test audio and collects feedback, the sound receiving effect of a microphone is effectively evaluated, the conference room equipment is automatically and actively inspected, the equipment state is continuously monitored and evaluated, and the sound receiving efficiency is improved. Potential faults can be found and prevented in time, and the sudden fault risk of equipment is remarkably reduced.

The invention provides a multi-edge collaborative anomaly detection system and method based on a double-flow parallel neural network, and the scheme employs a multi-edge collaborative task unloading method, can effectively improve the network anomaly detection efficiency of the Internet of Things, improves the defects when a single-edge gateway faces a large number of task processing requests, and improves the utilization rate of an overall edge system. Meanwhile, by adopting an anomaly detection model based on a double-flow parallel network, while the deep meaning and the context relationship of the traffic are extracted, a traffic data structure and a feature visual representation form can be effectively concerned, and a data anomaly mode can be visually described, so that the features of the abnormal traffic can be more comprehensively extracted and analyzed, and accurate detection is realized.

The invention provides a motor self-checking system and method for an infusion pump. A drive control subsystem drives a motor to operate, sets the target rotating direction of the motor, controls the rotating speed of the motor and controls the working state of a power supply of the motor; the state detection subsystem detects whether the motor is abnormal or not based on a driving signal of motor operation, a target rotation direction, a power supply working state of the motor and two paths of level signals; when the state detection subsystem detects that the motor is abnormal, an abnormal signal representing that the motor is abnormal is sent to the driving control subsystem; and the driving control subsystem controls the motor to stop running when receiving the abnormal signal. The infusion pump motor abnormity detection method can relieve the problem of low infusion pump motor abnormity detection efficiency in the prior art.

The embodiment of the invention provides a data exception detection method and device and an exception detection method and device for equipment monitoring indexes. The data exception detection method comprises the steps that to-be-detected time series data are acquired; based on the change characteristic of the to-be-tested time series data along with time, classifying the to-be-tested time series data, and determining a target evolution type of the to-be-tested time series data; according to the target evolution type, a corresponding target anomaly detection mode is determined, and different evolution types correspond to different anomaly detection modes; and performing anomaly detection on the to-be-detected time series data according to the target anomaly detection mode, and determining an anomaly detection result of the to-be-detected time series data. Data classification and anomaly detection are performed based on the change characteristics of the to-be-detected time series data along with time, different evolution types correspond to different anomaly detection modes, and the anomaly detection modes can flexibly adapt to the change characteristics of the to-be-detected time series data and adapt to various different application scenes.

The present invention relates to the field of data processing technology, and in particular to a distribution transformer fault detection method and system. The method includes: acquiring data sequences of various position areas on the distribution transformer in real time; determining the noise performance degree of each data point in each data sequence; correcting the noise performance degree of the data point according to the correlation between the data sequence and the preset local range sequence of the corresponding data point in other data sequences in its neighborhood; determining the noise influence degree of each data sequence; determining the number of adaptive segmentation trees when the corresponding position area is detected using the RRCF model according to the noise influence degree of each data sequence; and performing detection through the RRCF model to perform distribution transformer fault detection. By analyzing the noise influence degree of each data sequence, the number of segmentation trees in the adaptive RRCF model is adjusted, thereby saving distribution transformer fault detection computing resources, improving computing efficiency and detection accuracy.

The invention relates to the field of data processing, in particular to a stiffening plate production quality data processing method based on big data, and the method comprises the steps: obtaining the production quality data of a stiffening plate, and calculating the distribution uniformity of all data in the production quality data; any item of data in the production quality data is used as target item data, the ratio of the distribution uniformity degree of the target item data to the average value of the distribution uniformity degrees of all items of data is calculated and multiplied by the initial segmentation segment number, the segmentation segment number of the target item data is obtained, the optimal segmentation ratio is determined based on the segmentation segment number, and the eccentric optimization degree is calculated; and taking the eccentric optimization degree as a segmentation optimization degree to carry out isolated tree division on each item of data to obtain a division result, constructing an isolated forest according to the division result, and carrying out anomaly detection on the data points. According to the method, the optimal segmentation ratio and the segmentation optimization degree are dynamically calculated, so that different data distribution and characteristics can be adapted, and the accuracy of data processing is improved.

The invention provides a 1553 bus data anomaly detection method, which comprises the following steps of: processing periodically acquired to-be-detected data transmitted on a 1553 bus through a fault diagnosis neural network model to obtain a diagnosis result of whether an attack message exists or not; when the diagnosis result is that the attack information exists, the currently detected data is abnormal; when the diagnosis result is that the attack information does not exist, the currently detected data is normal; through the method, the fault diagnosis neural network model can quickly process and judge the input to-be-detected data, the anomaly detection efficiency is improved, the abnormal condition in the 1553 bus system can be found and processed in time, and the safety and reliability of the system are guaranteed; normal and abnormal conditions in the 1553 bus data can be finely distinguished, and the false alarm rate and the missing report rate can be reduced.

The application discloses a vehicle-mounted camera anomaly detection method and device, equipment and a storage medium, relates to the field of vehicle engineering, and is applied to a target cloud and comprises the following steps: sending an anomaly detection instruction to a target vehicle terminal of a target vehicle based on a preset trigger condition to obtain a target media file; analyzing a target statistical characteristic of the target media file to obtain a first analysis result, determining a target detection model based on a target camera corresponding to the target media file, and performing reference area checking on the target media file by using the target detection model to obtain a corresponding second analysis result; determining a first confidence degree corresponding to the first analysis result and a second confidence degree corresponding to the second analysis result by using a target confidence degree algorithm, and fusing the first analysis result and the second analysis result based on the first confidence degree and the second confidence degree to obtain an anomaly detection result corresponding to the target camera. The application improves the accuracy and efficiency of vehicle-mounted camera anomaly detection.

The embodiment of the application provides a kind of neutron flux abnormality detection method and device, electronic equipment and storage medium, belong to nuclear power plant safety technical field.The method comprises: screening reference nuclear power reaction unit.Get the first reference counting rate detection module in multiple continuous preset time steps under the core neutron counting rate.Acquire concentration influence factor, original neutron source source intensity and reference neutron source source intensity.According to the first detection sensitivity, the first reference sensitivity, the core neutron counting rate, the concentration influence factor, the original neutron source source intensity and the reference neutron source source intensity, the predicted neutron flux of the core basket is obtained by calculation.The first loading of pressurized water reactor nuclear power reaction unit is carried out, and the target neutron counting rate is obtained.According to the target neutron counting rate and the first detection sensitivity, the target neutron flux is obtained by calculation, and the abnormality is detected based on the target neutron flux and the predicted neutron flux.The embodiment of the application can improve the efficiency of neutron flux abnormality detection.

The invention belongs to the field of artificial intelligence, and relates to an anomaly detection method, which comprises the following steps that: a central server broadcasts an initial global model to a plurality of clients; and the client uses local data and an optimization algorithm to train a model within a preset time, and sends model parameters to the edge server of the corresponding subnet. And the edge server carries out local aggregation on the received parameters to form an aggregation model in the subnet, and sends the aggregation model to the central server. And the central server globally aggregates the aggregation models to obtain a target global model, and broadcasts the target global model back to the client. And the client updates parameters by using a global model combiner to obtain an anomaly detection model for anomaly detection of local financial behavior data. The invention further provides a system, equipment and a medium. In addition, the invention also relates to a block chain technology, and the local training data and the local financial behavior data can be stored in a block chain. The data exception detection efficiency can be improved.

The invention provides a detection circuit, a dry node communication system and a detection method, the detection circuit is applied to the dry node communication system, the dry node communication system comprises a sender, a receiver and a transmission link, the sender is provided with a dry node and a detection circuit, the detection circuit comprises a sending detection circuit, a transmission detection circuit and a controller, the sending detection circuit and the transmission detection circuit are both connected with the dry node; the sending detection circuit is used for controlling the dry node to be opened or closed according to an instruction of the controller and outputting a corresponding sending detection signal; the transmission detection circuit is used for outputting a transmission detection signal of a transmission link when the dry node is disconnected; the controller is used for determining whether the sender has a fault according to the sending detection signal; and determining whether the transmission link has a fault according to the transmission detection signal. According to the invention, the fault position in the dry node communication system can be accurately determined through the sending detection circuit and the transmission detection circuit.

The embodiment of the invention provides an anomaly detection method and device, electronic equipment and a storage medium, and relates to the technical field of network communication, and the method comprises the steps: obtaining a high-level log of network equipment, and extracting a signaling message of a terminal from the high-level log; comparing the extracted signaling message with a preset standard signaling message, and judging whether the high level of the network equipment is abnormal or not; under the condition that the upper layer is abnormal, acquiring a layer 2 log of the network equipment, detecting whether target information exists in the layer 2 log, and judging whether the layer 2 is abnormal based on a detection result of the target information; an abnormality detection result indicating the detected abnormality is generated. By applying the scheme provided by the embodiment of the invention, the anomaly detection efficiency can be improved.

The application relates to an exception detection method and device in performance testing, a computer device, a storage medium and a computer program product. By sending a test message to a target execution device in a business system, the target execution device is instructed to obtain a test script based on a test identifier and start target performance testing. In the target performance testing, the running state information at the current time point is compared with the running state prediction information at the corresponding time point predicted based on a target long short-term memory model. If the comparison result represents that the running state information at the current time point is abnormal running state information, the corresponding running snapshot of the target execution device is collected and saved. Compared with the traditional method of determining whether retesting is needed for the exception after one stress test, the present application trains the target long short-term memory model to timely detect the abnormality of the test state at the corresponding time point when the target execution device executes the test, timely capture the corresponding running snapshot, and improve the efficiency of the exception detection.

The invention discloses a transport capacity data processing method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of obtaining a first waybill number; querying planning trajectory data and first actual trajectory data corresponding to the first waybill number, and performing comparison calculation to obtain a first overlap ratio; in response to determining that the first overlap ratio is within a preset first threshold range, querying an operation data set corresponding to the first waybill number, the operation data set comprising a plurality of operation index data corresponding to a plurality of sampling moments; and combining the operation data set and the first coincidence degree, and inputting the operation data set and the first coincidence degree into a trained anomaly recognition model to obtain an anomaly probability corresponding to each sampling moment so as to correspondingly mark the first waybill number. Therefore, the embodiment of the invention can solve the technical problem that the existing transport capacity data anomaly detection efficiency is low.

The application relates to the technical field of network security, in particular to an abnormal network intrusion detection system based on FPGA and artificial intelligence. The system obtains and analyzes network message information of a network link entering the FPGA through a network perception unit, generates a data packet for AI intrusion detection model reasoning based on the obtained data information; an intrusion detection unit is constructed based on an AI model, outputs an intrusion detection result based on the input data packet, so that an intrusion response unit can more accurately determine a response processing mechanism based on the intrusion detection result and adjust the response processing mechanism; the analysis unit determines the intrusion detection state based on the detection rate in the preset period after the adjustment of the response processing mechanism, adjusts the corresponding parameters based on the intrusion detection state, generates AI detection model fine-tuning parameters, so that the intrusion detection state can be more effectively adjusted to be qualified. The application improves the abnormal detection efficiency of high-speed network traffic.

The invention provides a detection data generation method and an electric equipment energy consumption processing method and device, which can be applied to the technical fields of intelligent equipment, intelligent industry, artificial intelligence and Internet of Things. The detection data generation method comprises the steps that multiple pieces of sensor detection data matched with a target area and a target scene are obtained, the target area represents a functional area in a building object, the target scene represents a use scene of electric equipment, and the sensor detection data comprise detection data collected by at least one sensor; in response to detection that missing data exists in the multiple pieces of sensor detection data, reconstructing the missing data based on the data missing category to obtain sensor reconstruction data corresponding to the missing data; and generating target detection data according to complete data in the sensor reconstruction data and the sensor detection data.

The invention provides an anomaly detection method and device for graph data. The detection method comprises the steps that graph data of a target graph are obtained, the graph data comprise n nodes and the connection relation between the nodes, and each node has first feature data composed of d attributes; and partial nodes in the n nodes have labels representing the abnormal degrees thereof. And then determining second feature data, related to the graph structure, of each node, including processing the first feature data of each node by using a group of band-pass filters determined according to the connection relationship to obtain high-frequency abnormal features. The table data is constructed, and the single row data records the comprehensive feature data of the single node and comprises the first feature data and the second feature data. Then, the table data and the labels of the partial nodes are input into the table basic model, and the abnormal degree of the other nodes without the labels is predicted.

The invention relates to the technical field of data processing, and discloses a financial reconciliation system and method based on AI intelligence, and the system and method achieve the comprehensive collection, analysis, calculation and analysis of financial data through the cooperative work of a plurality of modules. The system greatly improves the automation and accuracy of data processing, reduces the risk of human errors, improves the efficiency of anomaly detection, enables enterprises to recognize and cope with financial risks in time and optimize fund flow and management strategies through rapid generation of anomaly judgment and positioning, improves the financial transparency of the enterprises, and improves the safety of the enterprises. In addition, data support is provided for decision making, sustainable and healthy development of enterprises is promoted, and the system can provide a more quantitative and objective anomaly evaluation mode by introducing a calculation formula of the financial anomaly magnitude CYL.

The invention relates to a database anomaly detection method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring each operation data of a database; wherein the operation data is used for representing the performance of the database; inputting each operation data into a pre-trained and constructed state detection model to obtain a state coefficient of each operation data; wherein the state detection model comprises a plurality of state prediction sub-models; each state prediction sub-model is used for predicting a state coefficient of operation data; performing weighting processing on the state coefficient predicted by each state prediction sub-model to obtain a target state coefficient of the operation data; and determining abnormal operation data in a database according to the state coefficient of each operation data. By adopting the method, the database anomaly detection efficiency can be improved.

The present invention discloses a network anomaly detection method, device, equipment and medium based on deep learning, the method comprising: in response to the received initial log data, extracting features from the initial log data according to a preset constant event template to generate a template symbol sequence, segmenting the template symbol sequence by setting a sliding rule according to a preset sliding window to generate a target log sequence and a label template symbol, detecting the target log sequence according to a preset anomaly detection model to generate a target template symbol corresponding to the target log sequence, and determining that the network behavior corresponding to the initial log data is abnormal when the target template symbol does not match the label template symbol. Thus, by parsing and extracting features from the log data, determining the log data abnormality according to the anomaly detection model, and then detecting the network abnormal behavior caused by the network attack, the efficiency of network anomaly detection is improved.

The invention discloses a page anomaly detection method and device and a storage medium. The method comprises the steps that whether a document object model tree of a to-be-detected page is constructed or not is determined; in response to completion of construction of the document object model tree, obtaining attribute information of key elements in the document object model tree; and determining whether the to-be-detected page is abnormal or not based on the attribute information. In this way, the page anomaly detection efficiency can be improved.

The invention belongs to the technical field of electric quantity data identification, and discloses a hierarchy-based multi-dimensional electric quantity abnormity identification method, system and device and a medium. The method comprises the steps of obtaining power consumption of a target region or a target industry in a preset time period and total power consumption of a power grid, and dividing a power consumption ratio based on the power consumption; acquiring a preset change range corresponding to each electric quantity abnormity type, identifying whether the electric quantity of the target region or the target industry deviates from each change range, if so, regarding the electric quantity as abnormity, and scoring and counting an abnormal integral; and dividing a priority level based on the power consumption ratio and the abnormal integral, and formulating a corresponding power abnormality response strategy. According to the method, through combination of hierarchical division and multi-dimensional detection, rapid and accurate identification of electric quantity abnormity is realized, the problems of information redundancy and low calculation efficiency possibly existing in a traditional method are avoided, the abnormity detection efficiency is improved, the detection accuracy is enhanced, and the method is suitable for popularization and application. And firm and powerful support is provided for safe operation of a power grid.

The disclosed embodiments provide a method, device, storage medium and electronic device for detecting anomalies in SQL logs, which relate to the fields of network technology and security technology, and are used to solve the problem of low efficiency of SQL log anomaly detection methods in related technologies. The SQL log anomaly detection method involved includes: obtaining a structured query language SQL log to be tested; extracting SQL operation data from the SQL log to be tested, and obtaining a test sequence based on the SQL operation data; generating a word vector for each word in the test sequence based on the test sequence and the word vector library obtained by pre-training, and obtaining a test word vector sequence; calculating the similarity between the word vectors in the test word vector sequence; and determining whether there is an abnormal SQL operation in the SQL log to be tested based on the similarity. The disclosed embodiments can quickly locate anomalies in SQL logs and reduce data loss caused by SQL log anomalies.

The invention discloses a video anomaly detection method and system fusing a key frame and a multi-task hybrid model, and the method comprises the steps: firstly employing a segmented clustering inter-frame difference key frame extraction technology, taking an extracted key frame as a model input, saving the storage space, and improving the detection efficiency; then, on the basis of human skeleton feature extraction, a reconstruction-based method and a prediction-based method are fused, and a hybrid model is constructed; in the aspect of multi-task learning, on the basis of the constructed hybrid model, the historical frame is comprehensively utilized to reconstruct and predict a future frame, the future frame is utilized to reconstruct and predict the historical frame, and the historical frame and the future frame are utilized to reconstruct and predict a current frame; and finally, performing video anomaly detection based on the trained hybrid model. According to the method, the problems that the abnormal data misjudgment rate of a reconstruction method and a prediction method is high and is easily influenced by environmental noise are effectively solved, multi-source information is comprehensively utilized through the hybrid model, the advantages of the two methods are combined, and the practicability and accuracy of the model are improved.

The application discloses an image anomaly detection method and device, computer equipment and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: determining a plurality of superpixel regions of an image, wherein the superpixel regions comprise a plurality of pixel points in the image; extracting k first superpixel features of different scales from each superpixel region, wherein k is an integer greater than 1; fusing the k first superpixel features of different scales of each superpixel region to obtain a superpixel fusion feature of each superpixel region; and determining an anomaly detection result of each superpixel region based on the superpixel fusion feature of each superpixel region, wherein the anomaly detection result represents a probability that the superpixel region in the image is abnormal. The application extracts and fuses local features in units of superpixel regions to identify the probability that each superpixel region is abnormal, can reduce unnecessary global operation, reduces the operation complexity, and improves the efficiency of anomaly detection.

The invention discloses an abnormal job flow detection method and system for a cloud platform. The method comprises the following steps: acquiring job flow information and job flow operation information of the cloud platform; classifying the job flow information to obtain a plurality of types of job flows; for each type of job flow, whether the type of job flow is abnormal or not is judged according to the job flow operation information; if yes, generating abnormal job flow details according to the category job flow; inputting the abnormal job flow details into a pre-trained abnormal job flow classification model to obtain abnormal types corresponding to the abnormal job flow details; and feeding back the abnormal job flow details and the corresponding abnormal types to the front end. Therefore, abnormal detection is not manually carried out on the job flow any more, whether the job flow is abnormal or not is monitored through abnormal job flow monitoring, the abnormal detection efficiency is effectively improved, the job flow is classified according to the service logic requirement, and the difference early warning rule of the model is formulated so that the abnormal type of the job flow can be effectively obtained.