128 results about "Abnormality" patented technology

A compound represented by the general Formula (I) below, or a salt or solvate thereof, which is useful as an ALK inhibitor, and is useful for prophylaxis or treatment of a disease accompanied by abnormality in ALK, for example, cancer, cancer metastasis, depression or cognitive function disorder:(meanings of the symbols that are included in the formula are as given in the specification).

The invention provides a meter-reading abnormality analysis method and system of a concentrator. The method comprises the steps of S101, acquiring meter-reading data of the concentrator in real time,analyzing the meter-reading data, and judging whether the meter-reading data is abnormal or not; S102, comparing the meter-reading data with fault historical record if the meter-reading data is abnormal, and determining a meter-reading abnormal behavior type of the concentrator; and S103, performing concentrator fault diagnosis to obtain a diagnosis result according to the abnormal behavior type,wherein the diagnosis result comprises a fault reason and a solution scheme. The system is used for implementing the method. By implementing the method, the meter-reading abnormal condition of the concentrator can be conveniently analyzed, a fault point is rapidly locked, and labor and time consumption during handling the meter-reading abnormal condition of the concentrator is reduced.

The invention intends to provide a technology which makes it possible to diagnose with higher accuracy whether or not abnormality occurs in a filter regeneration system causing excessive execution frequency of a regeneration process. The filter regeneration system initiates execution of the regeneration process, incase an estimated particulate matter (PM) accumulation amount at the filter reaches a pre-determined regeneration requiring accumulation amount; or in case the pressure upstream of the filter or the differential pressure across the filter reaches a pre-determined regeneration requiring value, the value being larger than the pressure or the differential pressure corresponding to the regeneration requiring accumulation amount. Then, the diagnosis is carried out based on a ratio of an estimated PM accumulation amount at the initiation of the execution of the regeneration process to the regeneration requiring accumulation amount.

The invention discloses a self-adaptive anti-crawling method and system based on abnormal behavior detection. The method specifically comprises the steps that S1, conducting abnormal judgment on an IPaddress, the access frequency, the access time and the access history of a user; S2, performing risk level classification on the user through abnormality judgment, performing verification detection on the low-risk user through question asking, slider verification and verification code verification, and detecting the high-risk users through fine-grained risk detection; and S3, performing countering operation on the user who is abnormal for many times in verification detection and risk detection. Rapid updating of the anti-crawling system is achieved through a user abnormal behavior self-adaptive detection mechanism, the accuracy of web crawler recognition is improved, and the access behavior of a normal user is guaranteed.

The present invention relates to a drug suitability assessment method for the prevention or treatment of anxiety disorders using the cholinergic type II theta rhythm, and, more specifically, to a method for detecting individuals suffering from anxiety disorders induced by an abnormality occurring in the cholinergic system using the type II theta rhythm profile which is based on findings that the cholinergic type II theta rhythm is lower in an animal anxiety model than in normal subjects and that cholinergic drug treatment induces the cholinergic type II theta rhythm to return to normal and reduces anxiety and thereby making it possible to determine if a subject can be appropriately administered with a cholinergic drug and to monitor progress after cholinergic drug treatment.

The invention discloses an abnormal behavior sequence association processing method and a device based on a time axis, equipment and a storage medium. The method comprises the steps of collecting logsin a centralized mode, and obtaining formatted logs through unified formatting; screening out abnormal behavior logs from the formatted logs according to a predetermined rule; establishing a time axis according to the timestamp of the abnormal behavior log; displaying the abnormal log information hashed in different time dimensions, and distinguishing different types of field information by adopting different colors; and displaying an abnormal event occurrence condition associated in a preset time range taking the threat alarm occurrence time as a central point on the time axis, so that the abnormal behavior sequence association processing realizes traceability. According to the method, the technical problem of poor detection effect of abnormal behaviors is solved. According to the method, the abnormal event can be effectively detected, and the correlation analysis can reveal the root cause of the abnormality, thereby improving the emergency response capability of a detection system.

A method, apparatus and computer program for detecting occurrence of an anomaly. The method can exclude arbitrariness and objectively judge whether a variation of a physical quantity to be detected is abnormal or not even when an external environment is fluctuating. The method includes acquiring multiple primary measurement values from a measurement target. Further, calculating and a reference value for each of the multiple primary measurement values by optimal learning. The method further includes calculating a relationship matrix which indicates mutual relationships between the multiple secondary measurement values. Further the method includes calculating an anomaly score for each of the secondary measurement value which indicates the degree of the measurement target being abnormal. The anomaly score is calculated by comparing the secondary measurement value with a predictive value which is calculated based on the relationship matrix and other secondary measurement values.

Various embodiments provide systems and methods for detecting data abnormalities within data sets relating to a particular agent and comprising both discrete and continuous data features by encoding the one or more discrete features and generating a sequential feature vector representative of both the encoded discrete features and the continuous features, reducing the dimensionality of the generated sequential feature vector to generate a reduced dimension behavioral vector, and comparing the reduced dimension behavioral vector against other reduced dimension behavioral vectors.

The invention discloses a user behavior prediction method and system based on deep walk and ensemble learning. According to the method, preprocessing work is carried out on the problems of repetition,abnormality, redundancy and the like existing in an original data set, statistical information and activeness information capable of reflecting behavioral habits and preference degrees of consumers are extracted from the preprocessed data set to construct a user portrait for the user, then, random walk is carried out through a social network graph structure of commodities purchased by the user toobtain a new behavior sequence; and then, a Word2vec model is used to obtain the upper and lower information of each behavior of the user, and the upper and lower information is added into a machinelearning model for training and learning, so that the prediction reliability and prediction precision of the model are improved.

Provided in the present invention is a method of detecting an abnormal behavior of a user of a computer network system, the method comprising: selecting at least two data sources in the computer network system; extracting data of user behaviors respectively from the corresponding data sources using a configured tensor data structure, and aggregating the extracted data; and detecting abnormality of user behaviors on the basis of the aggregated tensor data. The method of the present invention can efficiently integrate a large volume of irrelevant security data and identify an abnormal behavior automatically.

An analyzing apparatus comprising a processor of a controller and a memory that stores programs executable by the processor to: receive a test result on a test item from a measurement unit; analyze the test result to determine whether the test result indicates an abnormality on the test item; if the test result is determined to indicate an abnormality on the test item, update a history database in which a history of abnormality determinations made on the test item is recorded; review the history database to determine whether a frequency of abnormality determinations made on the test item exceeds a predetermined frequency for the test item; and if the frequency of abnormality is determined to exceed the predetermined frequency for the test item, alert a user on a possible problem is disclosed. An analyzing method and a non-transitory storage medium are also disclosed.

The invention provides a method and a device for detecting abnormal use of an account. The method for detecting the abnormal use of the account comprises the steps of obtaining first behavior characteristic data of a to-be-detected account, wherein the first behavior characteristic data is behavior characteristic data corresponding to first historical behavior data executed for the to-be-detectedaccount in a long time period; acquiring second behavior characteristic data of the to-be-detected account, the second behavior characteristic data being behavior characteristic data corresponding tosecond historical behavior data executed for the to-be-detected account in a short period of time, and the end time of the short period of time being not earlier than the end time of the long period of time; then, providing the first behavioral feature data and the second behavioral feature data to an account anomaly detection model to determine whether usage for the account is abnormal. By utilizing the method, the account use abnormality is detected by using the long-term accumulation behavior and the short-term sudden behavior for the to-be-detected account, so that the account security canbe improved.

The invention relates to the field of big data processing, in particular to an abnormal behavior detection method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a first personnel behavior monitoring table of personnel to be detected; extracting a monitoring index sequence from the first personnel behavior monitoring table; inputting the monitoring index sequence into a personal anomaly detection model obtained based on time feature training to obtain the behavior anomaly probability of the personnel to be detected at each time point andan anomaly time point corresponding to the behavior anomaly probability exceeding a preset threshold, thereby obtaining a first monitoring index; obtaining a second personnel behavior monitoring table, and extracting a second monitoring index; based on the first monitoring index, the second monitoring index and the behavior abnormality probability of the personnel to be detected, generating a behavior index corresponding to the personnel to be detected; and generating an early warning operation instruction corresponding to the personnel to be detected according to the behavior index, and sending the early warning operation instruction to the terminal. By adopting the method, the accuracy of abnormal behavior detection can be improved.

The invention provides an early warning method of mental health, including the following steps: acquiring classroom video and audio data of multiple students in different subjects within a preset first duration, wherein the classroom video and audio data include emotional information and body movements; obtaining a first curve of each student's emotion changing with the time according to the emotional information of each student; obtaining a second curve of each student's body movements changing with the time according to the body movements of each student; judging whether the student has psychological abnormality according to the first curve and / or the second curve of each student; generating a first warning prompt message when the student has psychological abnormality; and sending the first warning prompt message to a terminal. Therefore, the early warning of abnormal psychology is realized, so that parents and teachers can pay attention to abnormal conditions in advance so as to promote the healthy development of students and improving the teaching effect.

The invention discloses an abnormal behavior recognition method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining a current frame image, employing a human body key point detection model to detect the current frame image, and obtaining the human body feature information of a monitoring target, wherein the current frame image is an image which is obtained from a monitoring video and contains a monitoring target; matching the human body feature information with preset reference abnormal information to obtain matching information, the matching information indicating a matching result of the human body feature information and the preset reference abnormal information; if the matching information is first type information, acquiring a corresponding related frame image set from the monitoring video, wherein the first type information indicates that the monitoring target is abnormal; and performing behavior recognition on the related frame imageset by adopting a preset behavior recognition model, and determining the behavior information of the monitoring target in the related frame image set, thereby ensuring the accuracy of abnormal behavior recognition of the monitoring target.

The invention discloses an abnormal behavior detection method based on an optical flow algorithm. The method is specifically implemented according to the following steps: step 1, extracting optical flow information by the optical flow algorithm: extracting the optical flow information generated when a human body moves by adopting a Farneback dense optical flow algorithm; step 2, extracting behavior characteristics: counting the optical flow information extracted in the step 1 into a direction amplitude histogram; and step 3, result analysis and abnormality judgment: judging whether an abnormalbehavior occurs or not by calculating the direction and amplitude entropy of the histogram, the larger the direction and amplitude entropy of the histogram is, the more disordered the current motionis, the higher the possibility of the abnormal behavior is, and the problem of misjudgment of the abnormal behavior in the prior art is solved.

The invention discloses a user identity continuous authentication method and system based on a behavior map, and the method comprises the steps: carrying out the depiction of a historical access habit of a user to form a user access behavior map, and obtaining an abnormal behavior of the user deviating from the historical access habit through the comparison of a current access behavior and a historical access behavior; adopting an abnormal behavior detection mode based on behaviors, abnormal behaviors can be detected without setting a strategy in advance, and the characteristics and habits of the user individuals are fully considered; generating a user access time sequence map based on the access time interval of the source IP to each URL corresponding module of the destination site, obtaining an abnormal behavior that the user deviates from a historical access habit through comparison between the current access time interval and a historical access time interval, triggering identity verification failure, and performing access abnormality alarm; due to the fact that the user behavior atlas is dynamically changed, the longer the time is, the more accurate the depiction of the user behaviors is, and the accuracy of identity authentication can be guaranteed through the method.

The invention relates to an abnormal behavior detection method and device, equipment and a storage medium, and the method comprises the steps: obtaining a process operation behavior sequence, dividingthe process operation behavior sequence into a plurality of to-be-detected sequences, enabling each to-be-detected sequence to comprise a plurality of user process operation behaviors, and enabling each user process operation behavior to comprise a plurality of pieces of field information; performing feature extraction based on the attribute values of the plurality of pieces of field informationof each process operation behavior in the to-be-detected sequence to obtain a feature vector corresponding to the to-be-detected sequence; performing abnormal detection on the feature vectors corresponding to the to-be-detected sequences, and determining the feature vectors detected to be abnormal to be abnormal feature vectors; determining an anomaly degree of each dimension feature in the anomaly feature vector; determining an abnormal feature item in the abnormal feature vector based on the abnormality of each dimension feature in the abnormal feature vector; according to the method, the accuracy and efficiency of user abnormal behavior detection can be improved.

The invention discloses a method and a device for diagnosing abnormality of a current sampling loop. The method comprises the steps of: in response to a startup abnormality diagnosis operation, carrying out precise alignment on obtained dynamic record data based on adaptive discrimination of an abrupt change; in response to certain branch dynamic record data in the acquired dynamic record data, performing homologous detection on the certain branch dynamic record data; judging whether the certain branch dynamic record data is abnormal or not based on a homologous detection result; and if the certain branch dynamic record data is abnormal, performing difference detection on the dynamic record data containing the certain branch dynamic record data. By adopting the combination of homologous detection and differential flow detection, remote and accurate positioning of a current sampling abnormal loop can be achieved, the abnormality types cover abnormality conditions such as disconnection,shunting and two-point grounding, remote, real-time and high-efficiency automatic diagnosis can be realized, the manual leading pressure is reduced, the weak link of the system is sensed in time, andearly warning for potential safety problems is realized.

The invention provides a family safety management method and system. The method comprises the following steps: acquiring video monitoring data of a specified camera in a specified area; recognizing amonitored person and behavior data of the monitored person based on the video monitoring data; and if the behavior of the monitored person is judged to be abnormal based on the behavior data of the monitored person according to a rule matched with the monitored person, giving an alarm. Therefore, behaviors of special personnel such as old people, children and babies in designated areas such as a family can be monitored respectively, and an alarm can be given in time when an abnormality occurs, so that the safety of the family is effectively managed, and accidents and the like are prevented from being sent.

The invention discloses an identity recognition method based on abnormal behavior detection. The main technical scheme comprises the following steps of firstly, pre-embedding multiple behavioral habitmechanisms, then collecting behavior data based on a sensor and generating features by adopting a standardized preprocessing method; and according to the historical behavior characteristics of the password input by the target user, adopting an OCSVM algorithm training model to obtain the probability of behavior abnormality, combining results of multiple preset behavior habit mechanisms and finally, acquiring an identity authentication result in a linear combination mode. Only the target user sample exists in the training process, whether the new sample is the target user can be accurately andstably recognized, and therefore the judgment accuracy and stability can be improved.

The invention discloses a user security behavior baseline analysis method based on a fusion machine learning algorithm. The method comprises the following steps: establishing a behavior feature matrixfor a user or equipment to be monitored; establishing a two-dimensional feature matrix based on time dimension; positioning users or equipment with abnormal behavior baselines; extracting feature vectors of time dimensions from users or equipment with abnormal behaviors; and positioning the time when the baseline abnormality occurs. According to the invention, based on the fusion machine learningalgorithm, abnormal matching is carried out on the security of user behaviors from two aspects of behavior features and behavior occurrence frequency, so that whether the behaviors of the user threaten the network security or have the possibility of penetration attack is judged.

There is provided a method for use in monitoring a physiological characteristic of a subject, the method comprising: obtaining a general variability measure of the physiological characteristic, wherein the general variability measure is based on a historical data set of values of the physiological characteristic from a plurality of further subjects; calculating a personalization factor specific to the subject, based on physiological data relating to the subject; generating at least one personalized abnormality criterion for the physiological characteristic, based on the obtained general variability measure and the calculated personalization factor; receiving a measured value of the physiological characteristic of the subject; and determining whether the received measured value is abnormal by comparing it to the at least one personalized abnormality criterion, wherein the received measured value is determined to be abnormal if it meets the at least one personalized abnormality criterion.

The invention provides an abnormal behavior detection method and device, and the method comprises the steps: determining at least one monitoring region in advance, and storing at least one abnormal behavior feature corresponding to each monitoring region; for each current monitoring area in the at least one monitoring area, obtaining a monitoring video of at least one pedestrian moving in the current monitoring area; for each current pedestrian in the at least one pedestrian, extracting at least one current behavior feature of the current pedestrian from the monitoring video; determining whether the behavior of the current pedestrian is abnormal or not according to at least one abnormal behavior feature and the at least one current behavior feature corresponding to the current monitoring area; when the behavior of the current pedestrian is abnormal, obtaining identity information of the current pedestrian; and storing the identity information and an abnormal monitoring video, wherein the abnormal monitoring video comprises the current behavior characteristics of the current pedestrian abnormality. According to the scheme, the workload of monitoring video workers can be reduced.

The invention discloses a self-learning human body behavior recognition and anomaly detection method, which comprises the following steps of: generating a salient region vector in a monitoring video,and updating a salient region in a timing self-learning manner; for the same salient region, calculating a state feature vector and an action value of the current frame according to the human body behavior state of the current frame, a human body behavior state prediction value and an award value after the current frame is transferred to the next frame, and an action in the state; executing the current target network, calculating the current human body behavior action value, and updating the target action network and the target value network; and after the network parameters converge or meet the maximum number of iterations, counting the weighted sum of the feedback reward value of the current action network and the human body behavior action value of the target value network within the time T to obtain a behavior abnormality level. The method disclosed by the invention has the advantages of low complexity, real-time performance, high detection efficiency and high detection accuracy.

The invention provides an abnormity detection method and system for developer behaviors in an open source community and a medium. The abnormity detection method comprises: a sequence construction step, i.e., constructing time sequences of different behavior times according to the developer behaviors; a behavior data discretization step, i.e., dividing the behavior frequency time sequence into different categories of which the differences in intervals are lower than a preset range and the differences between the intervals are higher than the preset range, and reaching a preset category number;a behavior frequent sequence mining step, i.e., performing behavior frequent sequence mining on the behavior sequences of other personnel and the historical behavior sequence of the to-be-detected person; and a behavior abnormality judgment step, i.e., judging whether the behavior of the developer is abnormal or not. According to the invention, the determinacy of the open source project is improved, and the project progress risk is reduced; and, according to the invention, historical data can be traced back, and past abnormal data can be identified.

The embodiment of the invention discloses a user abnormal behavior detection method and device, and the method comprises the steps: obtaining the historical features of a plurality of historical userbehaviors in advance, wherein the historical features comprise historical time features; carrying out the time kernel density estimation according to the values of a plurality of historical time features, and obtaining a time kernel density curve; in this way, after the current characteristics of the current user behavior are obtained, the current characteristics comprise the current time characteristics, and the behavior abnormality index corresponding to the current user behavior can be calculated based on the time kernel density curve and the current time characteristics. Since the time kernel density curve is determined according to the historical characteristics of the historical user behaviors, a large amount of calculation is needed, the time kernel density curve can be obtained inadvance, and when the user behaviors are detected in real time, the obtained time kernel density curve can be directly used for determining whether the user behaviors are normal or not; therefore, thecalculation amount in the abnormal behavior detection process is reduced, and the real-time performance of abnormal behavior detection is improved.

The invention relates to a system for detecting abnormal gathering behaviors in a bus. The system comprises a video acquisition module, a video analysis module, an abnormality judgment module and an abnormality alarm module, wherein the video acquisition module acquires video data in a bus, preprocesses the video data and models the internal space of the bus; the video analysis module is used forcarrying out coding identification on a head in a video in the bus; the abnormality judgment module calculates an abnormality judgment index, calculates a comprehensive weight according to the abnormality judgment index, and further judges whether the abnormality exists or not; if it is judged that the abnormal alarm module is abnormal, an alarm is given; wherein the video acquisition module is electrically connected with the video analysis module, the video analysis module is electrically connected with the exception judgment module, and the exception judgment module is electrically connectedwith the exception alarm module. Aiming at the problem that the detection algorithm in the bus lacks consideration of the actual background of the bus, the method practically considers the actual scene in the bus and accurately judges the abnormal gathering behavior.