Abstract: A method and apparatus for intelligent visual analysis and display of cross-source heterogeneous data including: when a visual display command for the target heterogeneous data is detected, creating a connector in the distributed in-memory database corresponding to each target data source where the target heterogeneous data is located via a JDBC driver; in the visual data intelligence platform, the python driver of the distributed in-memory database and the SQLAlchemy framework create the connection between the visual data intelligence platform and the distributed in-memory database, and generating SQL table building statements in the visual data intelligence platform based on the association information corresponding to the target heterogeneous data; generating the target data table with plurality of table associations in the distributed in-memory database based on the SQL table building statements; the target heterogeneous data is visualized and displayed in the visual data intelligence platform based on th

Abstract: A method and apparatus for intelligent visual analysis and display of cross-source heterogeneous data including: when a visual display command for the target heterogeneous data is detected, creating a connector in the distributed in-memory database corresponding to each target data source where the target heterogeneous data is located via a JDBC driver; in the visual data intelligence platform, the python driver of the distributed in-memory database and the SQLAlchemy framework create the connection between the visual data intelligence platform and the distributed in-memory database, and generating SQL table building statements in the visual data intelligence platform based on the association information corresponding to the target heterogeneous data; generating the target data table with plurality of table associations in the distributed in-memory database based on the SQL table building statements; the target heterogeneous data is visualized and displayed in the visual data intelligence platform based on th

Abstract: AI modeling process choreography method and system based on a graph algorithm is provided. The method includes: according to graph data obtained from a front end, generating a graph structure including a plurality of nodes; traversing nodes according to an execution sequence of the nodes in the graph structure, and adding, into a list to be executed, a target node needing to be executed; and traversing the nodes again according to the execution sequence, executing the current node when the current node is in the list, recording and outputting, otherwise, skipping the current node, recording and outputting, and writing states and execution results of the nodes into a database after traversing is completed, wherein the graph data includes node information of the nodes in the AI modeling process, and the node information includes input, output and parameters, so that data processing and model choreography can be combined together.

Abstract: The present invention relates to technical field of communications and provides a method and a device for site selection for a monitoring station. The method comprises acquiring a site list comprising multiple relay stations and a connection relationship of optical cables among the relay stations; sequentially setting each relay station to be a starting site, and traversing the relay stations in the site list according to a preset coverage range from the starting site, and determining a set of uncovered relay stations corresponding to each starting site; according to a preset intersection base, traversing the set of relay stations that cannot be covered corresponding to each starting site to get an intersection, and determining one or more relay stations corresponding to a set of whose intersection result is empty as a target monitoring station. The method improves efficiency and accuracy of site selections and has wide applicability.

Abstract: The present invention relates to technical field of communications and provides a method and a device for site selection for a monitoring station. The method comprises acquiring a site list comprising multiple relay stations and a connection relationship of optical cables among the relay stations; sequentially setting each relay station to be a starting site, and traversing the relay stations in the site list according to a preset coverage range from the starting site, and determining a set of uncovered relay stations corresponding to each starting site; according to a preset intersection base, traversing the set of relay stations that cannot be covered corresponding to each starting site to an intersection, and determining one or more relay stations corresponding to a set of whose intersection result is empty as a target monitoring station. The method improves efficiency and accuracy of site selections and has wide applicability.

Abstract: Disclosed is a method for detecting an OTDR curve tail end event to locate an optical fiber break point in an online mode, comprising following steps: 1, an OTDR emits detection light to an optical fiber operation link, and receives reflection light to form reflection sampling point data containing tail end event; 2, head end reflection point in sampling point is found out; 3, traversal is carried out to find search region end point; 4, segmented line fitting is carried out in region of [search region end point, head end reflection point] in reversed direction, start point of section of line meeting predetermined condition is used as a search region start point; 5, if absolute value of difference between largest sampling value in search region and sampling value of search region start point is larger than second preset threshold value, tail end event is judged as reflection tail end event.

Abstract: Disclosed is a method for detecting an OTDR curve tail end event to locate an optical fibre break point in an online mode, comprising following steps: 1, an OTDR emits detection light to an optical fibre operation link, and receives reflection light to form reflection sampling point data containing tail end event; 2, head end reflection point in sampling point is found out; 3, traversal is carried out to find search region end point; 4, segmented line fitting is carried out in region of [search region end point, head end reflection point] in reversed direction, start point of section of line meeting predetermined condition is used as a search region start point; 5, if absolute value of difference between largest sampling value in search region and sampling value of search region start point is larger than second preset threshold value, tail end event is judged as reflection tail end event.