Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

81 results about "Similar time" patented technology

Method and device for generating video abstraction

The invention discloses a method and a device for generating video abstraction. The method includes: acquiring key frames according to intelligent video stream frame-grabbing algorithm; extracting and classifying backgrounds and objects in the key frames using background compensation algorithm; dividing into a plurality of video data having similar time duration on the basis of a time shaft according to motion track of the objects, and overlapping with the backgrounds having the same time duration to generate the video abstraction. By the method, more historical video data can be saved with less storage space.
Owner:CHINA TELECOM CORP LTD

Data capture system

A system that facilitates collecting data is described herein. The system includes a digital camera that is configured to capture images in a visible light spectrum and a near-infrared camera that is configured to capture near infrared images, wherein a field of view of the digital camera and the field of view of the near-infrared camera are substantially similar. The system further includes a trigger component that is configured to cause the digital camera and the near-infrared camera to capture images at a substantially similar point in time, and also includes a mounting mechanism that facilitates mounting the digital camera and the near-infrared camera to an automobile.
Owner:MICROSOFT TECH LICENSING LLC

Position prediction method by fusion of movement law of individual and neighbors

The invention discloses a position prediction method by fusion of a movement law of an individual and neighbors. The position prediction method comprises the steps of extracting time position information of an important (key) location in moving data of a user firstly to obtain a user track data; then performing mapping to find out K users which are located around the user and have similar time and space distribution; deeply finding a position movement mode which is in the shape of <A-B-C, T> from the historical user track data; and searching K neighbors having the same position movement mode, and taking the similarity of the predicted user and the adjacent neighbors as the weight, and performing fusion on the predicted user (individual). The similarity of the K neighbor users and the influence on the predicted user by taking the similarity as the weight are taken into consideration; meanwhile, the associated movement law, namely the position movement mode, is searched to perform the position prediction; and therefore, compared with the conventional position prediction method, the position prediction method with such technological thought is more robust, higher in noise resistance, higher in accuracy, and can better satisfy the sociology law.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

A building energy consumption prediction method based on a recurrent neural network and a multi-task learning model

The invention discloses a building energy consumption prediction method based on a recurrent neural network and a multi-task learning model, relates to the technical field of comprehensive energy management, and solves the technical problems of parallel prediction of multiple types of energy consumption, guarantee of prediction precision and shortening of model training time. The method comprisesthe following steps: acquiring a building energy consumption data sample; The method comprises the following steps of: carrying out missing data processing by utilizing a plurality of similar time point data averaging, constructing a plurality of learning tasks according to an energy consumption type, a time step length and initial time, then normalizing a data set of each learning task, and measuring the similarity among a plurality of task training sets by using a Pearson correlation coefficient. After the similarity among multiple tasks is ensured, a neural network model is created and trained, and finally, a multi-task CIFG-LSTM neural network model is used for predicting composite energy consumption. According to the energy consumption prediction method, the multivariate energy consumption can be predicted at the same time, close connection and interaction between the energy consumption are fully utilized, and the prediction precision and speed are improved.
Owner:XI'AN POLYTECHNIC UNIVERSITY

Photovoltaic power station ultra-short-term power prediction method based on meteorological data similarity analysis and LSTM neural network

The invention relates to a photovoltaic power station ultra-short-term power prediction method based on meteorological data similarity analysis and an LSTM neural network. The method comprises steps of selecting power generation power and corresponding meteorological data in the same time period of each day of one month before a day the predicted time period belongs to; carrying out Pearson correlation degree analysis on each meteorological data and the power output; selecting meteorological data with the highest correlation degree, and selecting an initial value, an average value and a tail value of the data in the time period to form a three-dimensional coordinate point; carrying out similarity analysis on meteorological data of unit time before the prediction time and a corresponding meteorological data set of a selected time period by utilizing Euclidean metric; and obtaining meteorological data and power data in a similar time period in which the Euclidean value is smaller than aspecified value, and finally predicting the generated power by adopting the trained LSTM model. According to the method, the generated power of the ultra-short-term photovoltaic power station can be predicted quickly and accurately.
Owner:FUZHOU UNIV

Mobile query suggestions with time-location awareness

The invention disclose a mobile query suggestions with time-location awareness. The techniques describe recommending mobile query suggestions by integrating time and location in response to a query input submitted on a mobile computing device. A process constructs a bipartite graph by extracting users that submitted queries from mobile search logs and associating time and location with the submitted queries. The process determines the users are similar having submitted similar queries at similar times and at similar locations. The process receives a query input associated with a current time and a current location of a mobile computing device. Next, the process computes a relatedness of candidate queries to the query input based on a similarity between the user groups having submitted both the candidate queries and the query input, and distances of times and locations at which the user previously issued the query input and the candidate queries.
Owner:MICROSOFT TECH LICENSING LLC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products