5results about How to "Solve unrecognized" patented technology

The embodiment of the invention discloses an installation and maintenance work order planning method and electronic equipment. The method comprises the steps that target installation and maintenance work order information is acquired, and the target installation and maintenance work order information comprises identification information of one or more broadband access devices to be installed and maintained; according to the identification information of the one or more broadband access devices and a data storage library, determining positioning information of installation and maintenance places corresponding to the one or more broadband access devices in a map; according to the target installation and maintenance work order information, the positioning information of the one or more broadband access devices and a first shortest path planning algorithm, determining path planning information of installation and maintenance personnel for completing installation and maintenance of the one or more broadband access devices; and presenting the path planning information. Through the scheme, intelligent path planning and real-time position visualization of the installation and maintenance work order are realized, and the installation and maintenance efficiency and customer satisfaction of installation and maintenance personnel are effectively improved.

This invention discloses a guidance system for a spiral descending tunnel boring machine (TBM). The guidance system provides three-dimensional guidance using a combination of a planar coordinate system and elevation. The planar coordinate system is established around the center of the spiral descending tunnel plane and includes an X-axis and a Y-axis, both parallel to straight lines around the spiral descending tunnel. This invention's guidance system and method for the spiral descending TBM establish a three-dimensional spatial guidance system based on a planar coordinate system and elevation, solving the problem of traditional guidance systems being unable to recognize overlapping horizontal coordinates in spiral descending tunnels. It also divides the tunnel into zones for control and performs planar coordinate value conversion in the planar coordinate transformation zone, providing intuitive values ​​for left and right deviations of the TBM, facilitating accurate and intuitive steering correction by the TBM operator.

The present invention relates to the field of image processing technology, and in particular to a dynamic target posture measurement method based on multiple exposure technology, firstly, a cooperative marker is set on a target object to determine the feature points on the target object; a feature point coordinate group of the target object at two consecutive moments is obtained, and then the feature point change speed is calculated; a measurement image group of the target object at the next moment is continuously obtained; the first image in the measurement image group at this moment is used as a reference, and the feature point coordinates in the first image are compensated in combination with the feature point change speed, so as to obtain a compensated feature point image coordinate set; finally, the combined feature point image coordinate set is used to calculate the posture of the target object. The present invention detects target features through multiple images collected continuously, and at the same time compensates for the feature points, thereby improving the accuracy of posture solution and reducing the influence of feature misalignment between multiple images caused by target motion on the accuracy.

The invention relates to the technical field of computer vision, in particular to a depression angle face recognition method and system applied to entering a venue. Comprising the following steps: S1, acquiring depression angle face data and corresponding high-definition front face image data; s2, performing three-dimensional face reconstruction on the front face image data by using a three-dimensional reconstruction network, re-mapping a rotated three-dimensional face model to two dimensions, and performing local cutting on two-dimensional depression angle face image data and a front face gallery set; s3, performing weighted fusion on the processed two-dimensional depression angle face image data and front face gallery set data by using a weight prediction network; s4, using the fused data to train a depression angle face recognition model; and S5, inputting depression angle gallery set data into the trained depression angle face recognition model, and counting the recognition precision. According to the invention, depression angle face recognition is applied to the scene of entering the venue, the accuracy of depression angle face recognition is improved, and the efficiency of entering the venue is improved.

The application provides a single-cell rare cell type identification method and system based on a divide-and-conquer strategy, comprising the following steps: S1, using a variational autoencoder to encode single-cell transcriptome data into Gaussian distribution hidden variables; S2, performing spectral clustering on the Gaussian distribution hidden variables to obtain a single-cell coarse-grained clustering result; and S3, optimizing the single-cell coarse-grained clustering result based on intra-class cluster loss and inter-class cluster loss until the intra-class cluster loss and the inter-class cluster loss are minimized to obtain a single-cell clustering result containing rare cell types. The application can overcome the deficiency that previous single-cell clustering and identification methods do not optimize rare cell types, leading to misclassification or difficulty in identifying rare cell types.