3results about How to "Improve division accuracy" patented technology

This invention discloses a method and application for classifying different water invasion risk levels in carbonate bottom-water gas reservoirs, belonging to the field of oil and gas field development technology. The method includes the following steps: S1, obtaining the relative distribution of gas and water layers in each sublayer of the gas reservoir under study; S2, evaluating the activity of the bottom water body; S3, dividing the block into sealed and unsealed zones; S4, obtaining the distribution of faults, fractures, and high-quality reservoirs in the water invasion channel; S5, based on the bottom water activity obtained in step S2 and the distribution of faults and fractures in the water invasion channel obtained in step S4, classifying the gas reservoir in the study area into five categories: high-risk longitudinal intrusion, low-risk longitudinal intrusion, high-risk transverse intrusion, low-risk transverse intrusion, and low-risk zones. This method is beneficial for the efficient and rational development of bottom-water gas reservoirs, reducing the degree of water invasion damage to the gas reservoir, and improving the final recovery rate of the gas reservoir.

This application relates to the field of tracing the causes of cross-border returns, disclosing a method, apparatus, electronic device, and storage medium for tracing the causes of cross-border returns. The method includes: deeply fusing multilingual text comments and image evidence using joint semantic vector technology; dynamically associating front-end return data with back-end supply chain data through root cause mapping to form a preset root cause map, thereby tracing the causes of returns based on return comment information. The beneficial effects of this invention are: breaking down data silos, accurately identifying deep causal relationships, significantly reducing the root cause misjudgment rate, shortening the root cause location time for cross-border returns, and improving the accuracy of supply chain responsibility allocation, thus achieving precise tracing of the causes of cross-border returns.

The invention provides a training sample making method, a training sample making device and a computer storage medium. The training sample manufacturing method comprises the steps that according to a first video frame and a second video frame which are adjacent, a motion detection frame and an average video frame are generated, and the motion detection frame comprises an unknown area, a motion area and a static area; generating an initial unknown region pixel value according to the first unknown region pixel value of the first video frame and the second unknown region pixel value of the second video frame; establishing a three-dimensional array of pixel values of the initial unknown region according to the average pixel value of the average video frame and the motion pixel value of the motion detection frame; searching a pixel value of a target unknown area according to the three-dimensional array; updating the motion detection frame based on the target unknown region pixel value; and forming a training sample by using the updated motion detection frame, the first video frame and the second video frame. Through the training sample manufacturing method, high-quality training samples can be provided for the motion detection network.