64 results about "Trend detection" patented technology

Disclosed is a health maintenance system for comprehensive health assessment, abnormality detection, health monitoring, health pattern and trend detection, health strategy development, and health history archiving. The health maintenance system comprises a subscriber segment and a system segment, communicatively coupled. The subscriber segment acquires subscriber personal and health data from at least one subscriber, analyzing the data; identifies specific health abnormalities; prescribes at least one customized subscriber health product, instructs the subscriber on the implementation of the prescribed health product, compiles and preserves the subscriber's health history data—including abnormalities and prescribed health products, and performs monitoring of subscriber health conditions. The subscriber segment acquires subscriber data from the subscriber segment, stores and maintains the data, facilitates retrieval of data by the subscriber and emergency medical personnel analyzes subscriber patterns and trends, develops new health products and modifies existing health products, and monitors the effectiveness of health products.

A method and system for inventory management of pharmacies and for detecting trends includes a pharmacy search and order service that receives information on prescriptions and communicates the prescription information to the pharmacies. The pharmacy search and order service also receives patient information, such as patient demographic data. The prescription information and patient information received by the pharmacy search and order service is transferred to a self-learning service where a rule database analyzes the information to detect trends in usage of medical items. The pharmacy search and order service determines which pharmacies have requested medical items in inventory and provides user output information indicating availability of the medical items at the pharmacies or indicates a nearest pharmacy having the items. An option provides for confirmation from the pharmacy of the item in inventory.

The invention discloses a time window based LDA microblog topic trend detection method and apparatus. The method comprises: extracting a topic word from a word set by utilizing an LDA model in each time window, and obtaining global topics; performing similarity computing on the global topics, and performing K-means clustering to obtain hot topics conforming to public opinion analysis; extracting feature words of each hot topic in each time window in sequence in combination with the hot topic through the LDA topic model; and in combination with results of the feature words, computing a popular value of the hot topic in each time window, and drawing a trend graph of the hot topic. The apparatus comprises a first acquisition module, a second acquisition module, an extraction module and a drawing module. According to the detection method and apparatus, the precision of microblog topic detection is improved, so that a trend index is more expressive, and a more accurate basis is provided for analyzing a hot topic trend.

A method for comparing a data set to a baseline value comprising: providing the data set to be analyzed; locating potentially bad data points in at least a portion of the data set using an odd-man out recursive technique; preparing a baseline set by discarding the potentially bad data points from the at least a portion of the data set; and calculating a baseline value from the baseline set.

The invention discloses a sinus heart rate turbulence trend detection method based on piecewise linearization. The piecewise linearization is adopted for specifically analyzing whether the variation trend of sinus heart rate accelerates first and then decelerates after premature ventricular contractions or not. The method includes the steps: (1) electrocardiosignal preprocessing; (2) self-learning process for first 10 seconds; (3) HRT (heart rate turbulence) sample collection; (4) piecewise trend analysis; and (5) turbulence trend representation based on a cloud model. The variation trend of the sinus heart rate at the RR interval is detected by means of piecewise linearization, and the turbulence trend is further represented by natural language through the cloud model. By the aid of an MATLAB (matrix laboratory) simulation tool, signals in an MIT-BIH heart beat irregularity database are selected for verification, and the variation trend of the sinus heart rate after single-time ventricular premature beat can be detected correctly. In addition, using the exponential smoothing method to predicate QRS complex occurrence positions to facilitate detection of QRS complex, and using a template for judging sinus heart beat is simple to implement and suitable for real-time treatment.

The invention discloses a method for rapidly testing casting blank segregation by utilizing a direct-reading spectrometer, which is suitable for the quantitative and trending detection in the casting blank segregation, belonging to the technical field of metallurgy analyzing and detecting. In the method, the direct-reading spectrometer is adopted to simulate an in-situ analyzer to detect the casting blank segregation; and the direct-reading spectrometer segments and dots a test sample, and simulates the in-situ analyzer to analyze the test sample, so as to quantitatively detect the continuously cast blank macrosegregation. The method can overcome the defects that the in-situ analysis sample preparation is complex, the testing period is long, the detection cost is high and the like, satisfies the generalized quantitative detection to the casting blank in the continuous casting production, and provides a good popularization and reference method for the iron and steel enterprises owning rapid spectrum analyzers in the trending and quantitative detection of the continuously cast blank segregation. Compared with the traditional pickling method for detecting the casting blank segregation, the method has the same trend on the description of the casting blank segregation as that of the pickling method; the casting blank segregation result detected by the direct-reading spectrometer not only can describe the casting blank segregation condition, simultaneously can clearly describe the component segregation curve of each element, and has the visual digitized function.

The invention discloses a store customer group analysis and stream of people information system and a usage method thereof. The store customer group analysis and stream of people information system comprises a processor, a trend detection unit which is arranged outside a store and detects a trend of a passerby so as to acquire trend information, and an image acquisition unit which is arranged in the store and captures images of customers who go into and out of the store so as to acquire a customer image and an in-out time image. The processor analyzes the trend information so as to generate passerby stream information and analyzes the customer image so as to process the in-out time so as to generate store stream of people information. And then according to the passerby stream information and the store stream of people information, store customer group information is generated. Therefore, by using the system and the method in the invention, an accurate market strategy and marketing can be provided.

The invention relates to a multisource remote sensing sequence image-based dynamic monitoring method, and aims at effectively utilizing space information of data to improve fusion methods, reduce feature differences among multisource remote sensing images and improve the dynamic monitoring effect. The method comprises the following steps of: firstly constructing multisource remote sensing image sequences, and preprocessing sequence remote sensing images by adoption of a proper image preprocessing method so as to ensure that the remote sensing image sequences have the features such as consistent image radiation characteristic, relatively high image registration precision and the like; fusing the remote sensing image sequences on the basis of space-time distribution-based enhanced multisource remote sensing image fusion method-eMulTiFuse, so as to ensure that time sequences have more similar space features; and finally dynamically monitoring time sequence remote sensing images by adoption of a Mann-Kendall trend detection method on the basis of pixel features, so as to obtain a monitoring result. The method has relatively high correctness.

In one example, a process includes receiving a plurality of first communications and a plurality of second communications, each first communication capturing activity of a patient or other monitored person using a first device at a different time and each second communication capturing activity of the patient or other monitored person using a second device at a different time. The process includes identifying a macro trend for all monitored activity of the patient or other monitored person based on data taken from the first and second communications. The process includes comparing data taken from a new communication from at least one of the first and second devices to the identified macro trend. A caregiver may be notified according to the comparison.

Issuance of work orders in response to monitoring signal egress from shielding integrity flaws in a cable communication system by detecting received signal strength from a mobile receiver only during rising trends in received signal strength when the mobile receiver is in motion and tracking the maximum received signal strength peak during each rising trend. Rising trends are detected by computing two rolling averages of received signal strength sample of different lengths and offset from each other and applying a threshold to the difference between the rolling averages to provide hysteresis in switching between rising and falling trend detection. Reported peaks are then compared by proximity to each other and their circle of influence determined in accordance with respective signal strengths to determine if newly reported peaks are duplicates of previously reported peaks and duplicate reported peaks are removed or discarded.

The invention discloses a plant growing trend detection and diagnosis method oriented to cotton targeted fertilizing in the field of agricultural production and detection. The method includes: before flowering and fruiting of cotton, measuring GPS (global positioning system) coordinate values of four border lines of a cotton planting area, planning flying collection route, GPS coordinate values of hover photographing points and distance between flying plane and the ground of an unmanned aerial vehicle loaded with image collection equipment and ultrasonic ranging equipment, taking cotton plant pictures at each hover photographing point by the image collection equipment, and measuring distance between the tops of the cotton plants and the flying plane by the ultrasonic ranging equipment; calculating height and light transmittance of the cotton plants by a computer, respectively comparing the height and the light transmittance with threshold values, and if any diagnosis index of the height or the light transmittance of the cotton plants is abnormal, indicating that growing trend of the cotton plants in the area is abnormal. By the method, large-area cotton plant growing trend targeted diagnosis is realized, and local areas weak or strong in growing trend are recognized, so that automation level is increased, and an effective basis is provided for cotton planting management.

A computer implemented method, apparatus, and computer-usable program product for identifying marketing trends in unique cohort groups. Information describing a plurality of unique cohort groups associated with a public environment is retrieved. Each member of a cohort group in the plurality of unique cohort groups shares at least one common attribute. Sets of attributes associated with the plurality of unique cohort groups are identified. The sets of attributes are analyzed by a cohort trend detection engine to identify attribute trends associated with the sets of attributes and a frequency of occurrence of the attribute trends in the plurality of unique cohort groups to form current attribute trends. In response to a query to an inference engine requesting inferences associated with the marketing trends, inferences describing future occurrences of the attributes in the plurality of cohort groups are received to form a set of future attribute trends. A set of marketing trends are generated using the current attribute trends and the set of future attribute trends. The set of marketing trends describes probable future marketing trends in the given environment.

The invention provides a telephone traffic abnormity detection method and device. The method includes the following steps: a historical trend threshold regular calculation step: cleaning historical telephone traffic data and regularly calculating a historical trend threshold on the basis of the cleaned historical telephone traffic data; a historical threshold detection step; a real-time trend detection step: calculating a real-time trend threshold on the basis of telephone traffic data ahead of a current detection point within a first period of time, and detecting whether the current telephonetraffic quantity exceeds the real-time trend threshold; a historical trend detection step: detecting whether the current telephone traffic quantity exceeds the historical trend threshold; and a warning sending step: if the current telephone traffic quantity exceeds a historical threshold, the real-time trend threshold and the historical trend threshold, sending out warning information. On the basis of detection of the historical threshold, real-time trend detection and historical trend detection are added, thereby overcoming the disadvantage of warning setting through direct collection of historical telephone traffic quantity and improving the accuracy of telephone traffic abnormality detection.

The invention discloses a dynamic drilling data abnormal trend detection method. The method comprises the following steps: s1, reading and converting real-time data; s2, integrating five different algorithms to calculate trend change indexes of the time series drilling data; s3, obtaining a final risk index through joint voting calculation of the trend detection indexes; s4, automatically updatingan alarm threshold value along with the change of the data by utilizing a dynamic threshold value calculation method; and s5, judging whether the final risk index exceeds a threshold value or not, and deciding whether to trigger an alarm or not. According to the invention, the data driving method is used for detecting the abnormal trend of the real-time data, so that the uncertainty of the real-time data can be solved; the invention can be used for monitoring drilling data exception caused by various reasons and warning risks in a physical application range, and the calculation process is simple and rapid; the invention can be applied to accurately evaluating data exception caused by working condition change in the drilling process so as to effectively realize risk in-time early warning in a drilling management system and reduce the misjudgment probability.

The invention discloses a telephone traffic exception automatic detection method and system, a storage medium and an electronic device. The telephone traffic exception automatic detection method comprises the following steps of obtaining historical data of telephone traffic in a first time period away from a current detection point; according to the historical data in the first time period, selecting a time dimension of data aggregation; classifying the historical data of the telephone traffic in the first time period; obtaining historical data of the telephone traffic in a second time periodaway from the current detection point; according to the selected time dimension, aggregating the historical data in the second time period, and performing segmentation to form multiple time slices; calculating an upper limit value and a lower limit value of threshold detection of each time slice through Gaussian distribution; calculating an upper limit value and a lower limit value of change ratedetection of each time slice through the Gaussian distribution; and performing the threshold detection and the change rate detection on the current detection point, if any detection result is exceptional, performing trend detection, and if the trend detection is exceptional, giving an alarm.

The invention discloses an unequal space time sequence abnormal trend analysis method for disaster prediction and belongs to the technical field of disaster prediction. Firstly, dynamic observation data with set indexes of a to-be-studied disaster are acquired, and the optimal space of an unequal space time sequence is determined; then, noise components of the dynamic observation data are removed;finally, abnormal trend detection is performed on the obtained dynamic observation data. The concept of the optimal space of the unequal space time sequence and a calculation method are provided, calculation is convenient, and the unequal space time sequence is converted into an equal space time sequence by use of the optimal space. The method can recognize the abnormal trend in the unequal spacetime sequence quickly and assist related experts in disaster prediction.

The present invention provides a voltage adjustment method and a terminal. The method comprises a step of detecting the volume change trend in playing sound by the terminal, a step of adjusting the voltage outputted by a terminal power supply module according to the detected volume change trend such that a voltage change trend is consistent with the volume change trend. The terminal comprises a volume change trend detection module for detecting the volume change trend in playing the sound by the terminal, a voltage adjusting module for adjusting the voltage outputted by the terminal power supply module according to the detected volume change trend such that the voltage change trend is consistent with the volume change trend.

In one example, a process includes receiving a plurality of first communications and a plurality of second communications, each first communication capturing activity of a patient using a first device at a different time and each second communication capturing activity of the patient using a second device at a different time. The process includes identifying a macro trend for all monitored activity of the patient based on data taken from the first and second communications. The process includes comparing data taken from a new communication from at least one of the first and second devices to the identified macro trend. A caregiver may be notified according to the comparison.

Information concerning a height of a shape of a workpiece is acquired accurately at high speed. A plurality of segments arrayed in one direction are set on a distance image including height information in a surface shape of a workpiece (S1). A type of a representative value concerning height information in each pixel included in each segment is selected, and this selected representative value is obtained for each segment (S2). An abnormality in a specific representative value is detected from an acquired trend, and is outputted (S4).

Provided are methods, apparatuses, systems, and non-transitory computer readable media for image trend detection and curation. A method includes collecting image content created in association with each of events and performing image clustering with respect to each of the events; detecting information about a representative event that represents an image trend based on a cluster according to the image clustering; and providing information about the representative event to an electronic device, in response to a service request received from the electronic device over a network.

A method for temporal trend detection employing non-parametric techniques. A set of discrete data is provided and a rank is assigned to the data based on both sensitivity and severity of the data. The method statistically ranks the ranked data by categorizing the data in bins defined by an average positional ranking that identifies the severity of the data for each sensitivity category provided by a bin. The method then clusters the statistically ranked data that has been categorized by average positional ranking so as to detect changes in the data. Clustering the statistically ranked data can include using a multi-nominal hypothesis testing procedure. The method then identifies trends in the data based on the detected changes.

The invention discloses a design and realization method for preventing a low-profile reel from bursting lines and relates to a low-profile reel of a fishing rod and a use method of the low-profile reel. The technical problems are solved that the braking force of existing line burst prevention brakes of low-profile reels in the use process cannot be adjusted dynamically, the structures of the electronic brakes are too complicated, and the cost is high. The design comprises a line cup rotation speed detection system, a braking force adjustment system and a PE line burst trend detection system, wherein the line cup rotation speed detection system comprises a visible-light emitting diode, a light receiving triode, a visible-light absorption semi-circular ring and a light reflecting semi-circular ring; when a line cup rotates, a receiving circuit receives a pulse signal, correspondingly the rotation speed of the line cup is thus detected, and the braking force of the braking system is dynamically adjusted according to the rotation speed. The braking force adjustment system comprises two main parts, namely an electromagnet and a soft magnet on the line cup, and braking is carried out under the action of a magnetic force and a friction force. According to the design, different braking forces can be provided according to different flying speeds of artificial lure baits, so that the purpose of preventing line burst is achieved.

The invention discloses a test detection system and method for scaling of a voltage-sharing electrode of a high-voltage direct current converter valve. The system comprises a voltage-sharing electrodescaling inhibiting device, a voltage-sharing electrode scaling detection device, a central control and processing device and a scaling trend detection and analysis background, wherein the voltage-sharing electrode scaling detection device is used for adjusting the water environment of cooled water in the mounting position of the voltage-sharing electrode and inhibiting scaling of the voltage-sharing electrode; the voltage-sharing electrode scaling detection device is used for detecting the PH value, conductivity, oxidoreduction reaction potential, AL ion concentration, CL ion concentration and leakage current of the cooled water in the mounting position of the voltage-sharing electrode; the central control and processing device and the scaling trend detection and analysis background calculate the scaling trend of the voltage-sharing electrode and judges the effectiveness of the voltage-sharing electrode scaling inhibiting device in inhibiting scaling of the voltage-sharing electrode.The test detection system and method can evaluate the scaling trend of the voltage-sharing electrode and the scaling inhibiting effect of each scaling inhibiting device and can be widely applied to annual overhaul, fault analysis and system optimization of the high-voltage direct current converter valve.

The invention discloses a unit state monitoring and intelligent early warning method comprising the following steps: determining a first monitoring system used for monitoring the operation state of a water-turbine generator set, the first monitoring system comprising at least one type of monitoring variable; judging whether the current unit working condition data meets the working condition judgment condition corresponding to each type of monitoring variable or not; and when the current unit working condition data meets the working condition judgment condition corresponding to each type of monitoring variable, obtaining a type of detection result of each type of monitoring variable through a continuous increasing trend detection method according to the obtained monitoring record text of each type of monitoring variable. The invention also discloses a transformer state monitoring and intelligent early warning method and an auxiliary machine state monitoring and intelligent early warning method. According to the invention, the change trend of state monitoring data of different hydropower station equipment can be intelligently analyzed, and the timeliness and accuracy of trend early warning can be effectively improved.

The invention is applied to the field of service provider individual client consumption trend identification, and provides a cluster analysis identification algorithm based on consumption time sequence data. The cluster analysis identification algorithm is used for communication consumption. The algorithm comprises steps of establishing a consumption sequence of historical consumption data of a client, carrying out clustering calculation of a consumption time sequential sequence of the client, and determining a client consumption trend according to a time sequence clustering result. The algorithm can effectively resist abnormal consumption interference data, distinguish starting and ending time of different consumption periods and different consumption levels, and provide an accurate data basis for client consumption trend analysis. The algorithm can be used for consumption trend identification of individuals and groups at other aspects such as income losses, consumption abnormity, consumption periods and the like.

The invention discloses a method and a device for determining a temperature change trend and electronic equipment. The method comprises the following steps: collecting a plurality of temperature observation data of a target observation point in a target time period corresponding to a sunset moment of the same day to a sunrise moment of the next day; according to the obtained temperature observation data corresponding to different moments, performing fitting operation on a preset fitting function by using a preset fitting algorithm until an error value between the temperature observation data and corresponding fitting data in a fitting result meets a preset error condition, and obtaining cooling intensity according to the fitting result; calculating according to the steps to obtain the cooling intensity of each day in multiple consecutive days; According to the cooling intensity of each day in the continuous multi-day, determining the temperature change trend in the multi-day by using a preset trend detection algorithm. The temperature characteristic of the day is represented by extracting the cooling intensity capable of representing the stable cooling trend, the advantage in the aspect of high-frequency disturbance resistance is obvious, and the accuracy of a temperature trend analysis result is improved.

In one example, a process includes receiving a plurality of first communications and a plurality of second communications, each first communication capturing activity of a patient or other monitored person using a first device at a different time and each second communication capturing activity of the patient or other monitored person using a second device at a different time. The process includes identifying a macro trend for all monitored activity of the patient or other monitored person based on data taken from the first and second communications. The process includes comparing data taken from a new communication from at least one of the first and second devices to the identified macro trend. A caregiver may be notified according to the comparison.

In one example, a process includes receiving a plurality of first communications and a plurality of second communications, each first communication capturing activity of a patient using a first device at a different time and each second communication capturing activity of the patient using a second device at a different time. The process includes identifying a macro trend for all monitored activity of the patient based on data taken from the first and second communications. The process includes comparing data taken from a new communication from at least one of the first and second devices to the identified macro trend. A caregiver may be notified according to the comparison.

The invention increases the fidelity of gas turbine engine module performance estimates that in turn enhance performance tracking and visibility. The methodology obviates input signal filtering since filtering may mask the onset and detection of a rapid measurement shift indicative of serious engine performance issues. The invention supports trend detection processes for timely detection, isolation and alerting of performance and engine system related faults.