32 results about "Event modeling" patented technology

The present invention provides a method that allows a developer to add complex dependency logic to an existing database without having to modify the underlying structure of the database. One embodiment of the present invention provides a way to flexibly handle record state transitions by using an event model. The event model is a set of one or more items called an event. Each event in the event model has an associated event type and contains dependency logic that interrelates the events in the event model with one another. Each event represents a set of actions that are optionally contingent upon a condition. The actions and conditions that comprise an event are determine when the event is created. Each event may have a different set of actions and conditions. This enables an event to represent a number of different things. An event can represent anything it is defined to represent. In one embodiment of the present invention an event metamodel is instantiated to represent a number of different event models and the corresponding dependencies that interrelate them. The event metamodel enables the model creator to control what happens to each and every event in the event metamodel without having to modify the underlying structure of the database.

Methods and apparatuses to model the relation between the delay samples and congestion losses and to protect media flows against congestion losses are disclosed. In one embodiment, the method comprises measuring congestion by delay samples, and performing a dynamic FEC algorithm that uses convex hull clustering for loss-event classification, including determining an FEC rate according to the loss-event classification. In another embodiment, the method comprises measuring congestion by delay samples, modeling loss events associated with the delay samples by grouping loss events as unions of convex hulls to identify a period of potentially increased congestion, dynamically changing the FEC rate based on the modeling, and applying FEC protection to the media flow during the period based on the FEC rate. In yet another embodiment, the method comprises forming clusters using past loss events and their {FTT, F{dot over (T)}T} or {RTT, R{dot over (T)}T} estimates, and estimating future loss events using most recent {FTT, F{dot over (T)}T} or {RTT, R{dot over (T)}T} estimates and their membership in convex hull clusters.

The present invention relates to the technical field of automatic driving, and discloses a modeling method, device, equipment and storage medium for triggering events. The method includes: obtaining a preset risk concentration point, and using the preset risk concentration point as a first construction Modeling conditions, divide the automatic driving system according to the preset division strategy, obtain the corresponding layer, use the corresponding layer as the second modeling condition, and compare the first modeling condition and the second modeling Combining and analyzing conditions to obtain trigger events, analyzing and refining the automatic driving system, obtaining corresponding process nodes, analyzing the trigger events according to the corresponding process nodes, obtaining target trigger events, and Model the target triggering events described above. The present invention obtains and models triggering events through combined analysis of preset risk concentration points and layers, and can effectively model triggering events, thereby improving driver safety.

The invention discloses an event-driven demand forecasting method for e-commerce based on Prophet-random forest, comprising the steps of: acquiring historical sales data of an e-commerce platform, the sales data including time series data and user data for purchasing related products; cleaning the historical sales data , improve data quality; compress time series data to reduce data volatility; conduct event modeling based on festival activities and e-commerce platform promotion events; add event regressors to the Prophet model, and perform Prophet prediction, eliminate and interpolate as events Outliers within the effect range, and perform random forest prediction; combine Prophet prediction and random forest prediction results; perform accuracy evaluation to observe model generalization ability and prediction effect. Aiming at the characteristics of e-commerce event demand and non-event demand, the present invention uses Prophet and random forest for prediction respectively, and improves the prediction accuracy of the event-driven demand of e-commerce.

The invention relates to a common modeling method and system of heterogeneous disaster events. The method comprises the steps of building a disaster event meta-modeling frame, building a mode structure of a disaster event meta-model and building a heterogeneous disaster event information model. The method and the system have the advantages and positive effects that the problems that existing heterogeneous disaster events lack effective description means and information models are not uniform are solved; the disaster event meta-model is built; four metadata components and eight-tuple node information description models are developed and the mapping relations between the geography markup language, the sensor model language, the event pattern markup language, sensor network common data information models and an event meta-model are designed; compared with existing disaster event management modes, the disaster event meta-model in the method and system provided by the invention comprehensively describes related information of the heterogeneous disaster events, thus providing supports for unified management and accurate discovery of the disaster events and proving that the method is beneficial to modeling of the heterogeneous disaster events and is more practical and reliable in disaster even management.

The present invention provides an optimization method and equipment for marine target cooperative detection equipment, wherein the method includes: determining the management decision cycle, and obtaining at least one dynamic event modeling model; the dynamic event modeling model includes new target appearance or departure, Dynamic events such as equipment relay and replenishment, excessive co-detection, abnormal data, or user-issued instructions; within the time window, if a dynamic event occurs, the first adjustment instruction will be generated immediately; if no dynamic event occurs, the current The time window generates a second adjustment instruction; in response to the adjustment instruction, according to the objective function-based target and detection equipment cooperative scheduling detection efficiency evaluation model, the deviation between the actual detection efficiency and the reference value is calculated; according to the deviation, an equipment scheduling optimization plan is generated, so that The detection equipment is adjusted immediately or in the next time window to the equipment scheduling optimization scheme for target cooperative detection. Through the above solution, the cooperative detection efficiency can be improved and the dispatching response capability can be improved.

The invention discloses a logistics state monitoring method and system based on multi-sensor fusion. The system includes several smart labels, and each smart label is composed of a label shell, a microcontroller, a sensor module, a wireless communication module and a power supply module; the label shell Installed on the surface of the transported goods; the microcontroller is responsible for the task scheduling of the entire system; the sensor module is interconnected through multiple types of sensors to realize sensor data collection and event modeling calculations in the cargo transport environment, including vibration, impact, dumping, falling, demolition Sealing, temperature and humidity imbalance and other events; the wireless communication module sends sensor data, time stamps and event records to the monitoring mobile terminal or remote cloud server; the present invention can effectively monitor the real-time status and events of goods during the delivery of production materials and logistics transportation Record information, and timely alarm when the goods are damaged, so as to accurately and effectively monitor the safe transportation of sensitive products.

The invention discloses a modeling method of a video semantic event, which comprises the steps that an original video image sequence is acquired, and subjected to graying and filtering preprocessing; an initial video image sequence is acquired, and subjected to self-adaption background modeling; an updated background image is acquired; a current image and the updated background image are subjected to pixel differencing correspondingly; a human body area in a foreground is obtained, and tracked by adopting a Meanshift algorithm; new position coordinates of each frame are acquired, and subjected to statistical analysis; and a corresponding movement behavior is judged. With the adoption of the method, under-reporting of an anomalous event is reduced; waste of manpower and material resources is avoided; and the working efficiency of monitoring equipment is improved.

The invention provides an abnormal event alarm high-resolution video intelligent processor. An A / D (Analog to Digital) processing unit in the high-resolution video intelligent processor is accessed to perform digital processing on a high-resolution video, and outputting video streams to an intelligent video analysis unit DSP (Digital Signal Processor); and the intelligent video analysis unit DSP is used for outputting the video stream superimposed with analysis data to a H.246 video encoding unit for compressed encoding, and outputting target detection and feature extraction data to a central processing unit ARM (Advanced RISC Machine) for performing abnormal event management and judgment. Distributed hybrid architecture is adopted, and abnormal event modeling is performing on the basis of a business rule, so that the functions of acquisition, encoding, intelligent analysis, alarming, compression, network transmission and the like are realized on high-resolution video streams of 1080P and more than 1080P, and an integral solution is provided for intelligent analysis and processing of high-resolution video images.

The present invention discloses a method and system for event individualized classification based on event modeling. The method includes 1. Crawling data from daily news, corresponding microblogs and comments on major forums, and establishing a news database ;2. In-depth mining of the data in the news database, establishing a corresponding event model, and generating multiple labels for each event, and then saving the event information in the event database; 3. Guiding different users to input different requirements through the client Classification and keywords of each category; 4. Based on event tags and other attributes, events in the event library are divided into different categories according to category matching and category similarity, and are displayed on the user platform in an intuitive way. This system can make full use of the rapid development of the Internet and a large number of emerging news data to realize personalized classification of news event data according to different requirements, and can easily fully connect with various news platforms to provide personalized information for various platforms Serve.