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

65results about How to "Efficient use of time" patented technology

System and method to provide maintenance for an electrical power generation, transmission and distribution system

A method for providing maintenance to an electrical power generation, transmission and distribution system, and an information system and one or more computer program software means for carrying out same. A method to provide maintenance to an electrical power generation facility and / or an electrical power transmission and distribution network system operated by a Utility. Maintenance personnel visit a site to inspect a condition of said apparatus, and examine information from an Information System operated in co-ordination with a Help Desk. The method comprises further steps such as preparing a report of the apparatus with a mobile web camera, making a report comprising a graphic image of the condition of said apparatus, receiving at said Help Desk and Information System the report and graphic image from the inspector / repairman, finding stored information about said apparatus and / or said system in said Information System, comparing said stored information with the report and / or graphic image, the inspector / repairman making in consultation with the Help Desk an assessment of the condition of said apparatus and providing a recommendation such as a repair, a temporary repair or making a plan for a repair at a later time.
Owner:ABB AS +1

Vehicle trajectory prediction model establishment and prediction method

The invention relates to a vehicle trajectory prediction model establishment and prediction method. The vehicle trajectory prediction model establishment method comprises the following steps: acquiring historical driving trajectory data of a vehicle, and constructing single vehicle trajectory data and road network vehicle trajectory data of the vehicle; carrying out screening to obtain screened single vehicle trajectory data and screened road network vehicle trajectory data; carrying out bayonet completion to obtain effective single vehicle trajectory data and effective road network vehicle trajectory data; establishing a prediction model of the effective single vehicle trajectory data; establishing a prediction model of the effective road network vehicle trajectory data; according to theprediction model of the effective single vehicle trajectory data and the prediction model of the effective road network vehicle trajectory data, constructing a fusion training set; and according to the fusion training set, training a set prediction model and generating a vehicle trajectory prediction model. According to the method in the invention, the data is effectively processed, the calculation amount is reduced, and the prediction is enabled to be more accurate and closer to the actual condition.
Owner:PCI TECH GRP CO LTD +2

Reagent centrifugal system

The invention relates to the technical field of centrifuges and discloses a reagent centrifugal system which comprises a centrifuge, a turnover unit, an image acquisition device and a control unit; the centrifuge is provided with a top cover capable of being opened and closed and a centrifugal portion provided with a plurality of placing grooves for centrifugal tubes; the turnover unit is used incooperation with the centrifuge and is provided with a mechanical arm capable of taking and placing the centrifugal tubes; the image acquisition device can obtain an image of the centrifugal portion in the centrifuge in a state that the top cover is opened; and the control unit is in communication connection with both the image acquisition device and the mechanical arm and can control the taking and placing action of the mechanical arm by analyzing a stop position of the centrifugal portion according to the image obtained by the image acquisition device. For the reagent centrifugal system, byarranging the image acquisition device and the turnover unit and using the control unit to control the actions of the two of the image acquisition device and the turnover unit, taking, placing and position transferring of a reagent in the reagent centrifugal system can be automatically and mechanizedly achieved without manual operation, the taking, placing and position transferring efficiency of the reagent are greatly improved, and thus the centrifugal efficiency of the reagent centrifugal system is correspondingly improved.
Owner:上海宏滩生物科技有限公司

Online exercise personalized recommendation system based on machine learning algorithm

InactiveCN112749336AImprove online learning efficiencyAvoid sea tacticsData processing applicationsDigital data information retrievalPersonalizationData set
The invention discloses an online exercise personalized recommendation system based on a machine learning algorithm, and the system comprises a question selection module which comprises an automatic question selection module and a manual question selection module, the automatic question selection module employs an algorithm to automatically output a selected question set, and the manual selected question is autonomously selected by a user; the online learning knowledge base comprises learning resources such as exercises, test papers, hearing materials and online lesson videos, and the knowledge base comprises a learning resource feature extraction algorithm; learning a resource feature extraction algorithm: using a machine learning algorithm to obtain a hiding rule contained in the data set; and the recommendation engine is used for inferring knowledge mastering conditions and weak points of the user according to user behaviors by using a machine learning technology and matching learning resources suitable for the user from the knowledge base, and the recommendation engine comprises a user portrait algorithm and a recommendation algorithm. According to the invention, exercises can be recommended in a targeted manner for user knowledge weak points and pain points, the time is efficiently utilized, and the learning efficiency is improved.
Owner:徐州金林人工智能科技有限公司

System and method to provide maintenance for an electrical power generation, transmission and distribution system

A method for providing maintenance to an electrical power generation, transmission and distribution system, and an information system and one or more computer program software means for carrying out same. A method to provide maintenance to an electrical power generation facility and / or an electrical power transmission and distribution network system operated by a Utility. Maintenance personnel visit a site to inspect a condition of said apparatus, and examine information from an Information System operated in co-ordination with a Help Desk. The method comprises further steps such as preparing a report of the apparatus with a mobile web camera, making a report comprising a graphic image of the condition of said apparatus, receiving at said Help Desk and Information System the report and graphic image from the inspector / repairman, finding stored information about said apparatus and / or said system in said Information System, comparing said stored information with the report and / or graphic image, the inspector / repairman making in consultation with the Help Desk an assessment of the condition of said apparatus and providing a recommendation such as a repair, a temporary repair or making a plan for a repair at a later time.
Owner:ABB AS +1

Human body abnormal behavior detection method based on T-TINY-YOLO network

The invention discloses a human body abnormal behavior detection method based on a T-TINY-YOLO network, and belongs to the technical field of image and video analysis and processing in computer vision. The method comprises the following specific steps: firstly, according to different monitoring scenes, selecting a video sequence within a period of time, converting the video sequence into a picture, storing and preprocessing the picture; labeling four human abnormal behaviors which comprises finger, push, hug and standing in each picture by using a labeling tool, and generating an xml file as adata set; then, dividing the data set into a training sample and a verification sample, and inputting the training sample and the verification sample into an improved T-TINY-YOLO network model for training and verification; and finally, for a new monitoring video frame picture, directly inputting the new monitoring video frame picture into the trained T-TINY-YOLO network model after preprocessing, and outputting the category to which the calibration result of the human abnormal behavior belongs, thereby realizing end-to-end abnormal behavior classification. According to the invention, the size of the network is cut, the problem of network redundancy is solved, and the algorithm is accelerated, so that the network detection and time utilization are more effective.
Owner:BEIHANG UNIV
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