Abstract: This application discloses a method and apparatus for improving video target detection performance in surveillance edge computing. This application relates to the technical field of digital image processing. The method includes: determine the size of multiple rectangular sliding windows for scanning according to the input size of the object detection neural network algorithm and the size of the original input image; when each frame is detected, the original input image and the sub-images in each rectangular sliding window are scaled in different proportions; the resolution of the scaled original input image is lower than that of the scaled sliding window sub-images; stitching the scaled images into a rectangular image and using it as a detection input image; the detection is performed by an object detection neural network algorithm corresponding to the size of the detection input image.

Abstract: The present invention discloses a flow regulating push switch conjoined valve, comprising a valve housing, a flow regulation assembly and a push switch assembly. The valve housing has a first chamber and a second chamber which are isolated from each other, a communication channel is disposed between the first chamber and the second chamber, and a first connection pipe and a second connection pipe are devised on the valve housing. The first connection pipe has a first channel which is in communication with the first chamber and the second connection pipe has a second channel which is in communication with the second chamber. The flow regulation assembly is installed in the first chamber for regulating a flow rate of a fluid between the first channel and the communication channel. The push switch assembly is installed in the second chamber for controlling connection and disconnection of a flow path between the second channel and the communication channel.

Abstract: The present invention discloses a flow regulating push switch conjoined valve, comprising a valve housing, a flow regulation assembly and a push switch assembly. The valve housing has a first chamber and a second chamber which are isolated from each other, a communication channel is disposed between the first chamber and the second chamber, and a first connection pipe and a second connection pipe are devised on the valve housing. The first connection pipe has a first channel which is in communication with the first chamber and the second connection pipe has a second channel which is in communication with the second chamber. The flow regulation assembly is installed in the first chamber for regulating a flow rate of a fluid between the first channel and the communication channel. The push switch assembly is installed in the second chamber for controlling connection and disconnection of a flow path between the second channel and the communication channel.

Abstract: Disclosed is a recommendation method and device.

Abstract: Disclosed is a recommendation method and apparatus. The recommendation method comprises: identifying at least one core user of a network service provider and a set of users who have demonstrated one or more network-related behaviors with respect to a first predetermined association item; sampling the set of users to identify a set of sample users; calculating a similarity between the sample users to identify a list of similar users; and sending a recommendation of potential users to a network service provider, the recommendation of potential users based on the list of similar users and the at least one core user of a network service provider. Potential users may be efficiently recommended to a network service provider.

Abstract: Method and apparatus for de-interlacing a television signal are provided. The method includes: determining whether a pixel to be interpolated is in a strictly static mode; if it is in the strictly static mode, obtaining a pixel value of a first pixel in a previous field which corresponds to the pixel to be interpolated, and setting a pixel value of the pixel to be interpolated to be equal to the pixel value of the first pixel; if it is not in the strictly static mode, determining gradient bands along a plurality of directions by taking the pixel to be interpolated as a center, determining a direction of the pixel to be interpolated based on the gradient bands, and setting the pixel value of the pixel to be interpolated by interpolation based on the direction. Accuracy of the pixel value of the pixel to be interpolated may be improved.

Abstract: Method and apparatus for de-interlacing a television signal are provided. The method includes: determining whether a pixel to be interpolated is in a strictly static mode; if it is in the strictly static mode, obtaining a pixel value of a first pixel in a previous field which corresponds to the pixel to be interpolated, and setting a pixel value of the pixel to be interpolated to be equal to the pixel value of the first pixel; if it is not in the strictly static mode, determining gradient bands along a plurality of directions by taking the pixel to be interpolated as a center, determining a direction of the pixel to be interpolated based on the gradient bands, and setting the pixel value of the pixel to be interpolated by interpolation based on the direction. Accuracy of the pixel value of the pixel to be interpolated may be improved.

Abstract: Disclosed is a recommendation method and apparatus. The recommendation method comprises: identifying at least one core user of a network service provider and a set of users who have demonstrated one or more network-related behaviors with respect to a first predetermined association item; sampling the set of users to identify a set of sample users; calculating a similarity between the sample users to identify a list of similar users; and sending a recommendation of potential users to a network service provider, the recommendation of potential users based on the list of similar users and the at least one core user of a network service provider. Potential users may be efficiently recommended to a network service provider.

Abstract: Disclosed is a recommendation method and device.

Abstract: Saving database storage space includes receiving, using a processor, one or more properties associated with a newly released commodity input at a front-end server; determining whether the one or more properties of the newly released commodity match a standard property unit (SPU), wherein the SPU includes a plurality of properties common to at least two commodities of which data is stored at a back-end server; and in the event that the one or more properties of the newly released commodity match the SPU, storing data associated with binding the newly released commodity with the matching SPU at the back-end server.

Abstract: A method of decision tree based search result ranking includes obtaining a training data set for generating at least one decision tree, the training data set having N training features and N greater than or equal to 2. The method further includes dividing a computational system of decision trees into N feature work groups corresponding to the N training features respectively, and by use of the feature work groups, computing splitting nodes and splitting values corresponding to the splitting nodes for the decision trees. The method also includes generating the decision trees using the computed splitting nodes and the corresponding splitting values; and ranking search results using the decision trees.

Abstract: A video anti-shaking method and a video anti-shaking device are provided. The method includes: obtaining a first GRMV (global relative motion vector) of a current video frame relative to its previous video frame, and a sequence of second GRMVs of reference video frames relative to their respective previous video frames; calculating a sequence of third GRMVs of the reference video frames relative to the current video frame, respectively, based on the first GRMV and the sequence of second GRMVs; and filtering the sequence of third GRMVs to obtain a motion vector for compensating shaking of the current video frame. Camera shaking and intended motion can be distinguished.

Abstract: A video anti-shaking method and a video anti-shaking device are provided. The method includes: obtaining a first GRMV (global relative motion vector) of a current video frame relative to its previous video frame, and a sequence of second GRMVs of reference video frames relative to their respective previous video frames; calculating a sequence of third GRMVs of the reference video frames relative to the current video frame, respectively, based on the first GRMV and the sequence of second GRMVs; and filtering the sequence of third GRMVs to obtain a motion vector for compensating shaking of the current video frame. Camera shaking and intended motion can be distinguished.

Abstract: Saving database storage space includes receiving, using a processor, one or more properties associated with a newly released commodity input at a front-end server; determining whether the one or more properties of the newly released commodity match a standard property unit (SPU), wherein the SPU includes a plurality of properties common to at least two commodities of which data is stored at a back-end server; and in the event that the one or more properties of the newly released commodity match the SPU, storing data associated with binding the newly released commodity with the matching SPU at the back-end server.

Abstract: Saving database storage space includes receiving, using a processor, one or more properties associated with a newly released commodity input at a front-end server; determining whether the one or more properties of the newly released commodity match a standard property unit (SPU), wherein the SPU includes a plurality of properties common to at least two commodities of which data is stored at a back-end server; and in the event that the one or more properties of the newly released commodity match the SPU, storing data associated with binding the newly released commodity with the matching SPU at the back-end server.

Abstract: Saving database storage space includes receiving, using a processor, one or more properties associated with a newly released commodity input at a front-end server; determining whether the one or more properties of the newly released commodity match a standard property unit (SPU), wherein the SPU includes a plurality of properties common to at least two commodities of which data is stored at a back-end server; and in the event that the one or more properties of the newly released commodity match the SPU, storing data associated with binding the newly released commodity with the matching SPU at the back-end server.

Abstract: Saving database storage space includes extracting a standard property unit from a database of commodity information and including the SPU in a SPU library, generating a sequence document of the standard property unit and sending the sequence document to a front-end device, determining whether a newly released commodity matches the standard property unit of the sequence document of the standard property unit and in the event that the newly released commodity matches the standard property unit of the sequence document, binding the new released commodity and the matched standard property unit.

Abstract: Saving database storage space includes extracting a standard property unit from a database of commodity information and including the SPU in a SPU library, generating a sequence document of the standard property unit and sending the sequence document to a front-end device, determining whether a newly released commodity matches the standard property unit of the sequence document of the standard property unit and in the event that the newly released commodity matches the standard property unit of the sequence document, binding the new released commodity and the matched standard property unit.

Abstract: Methods and systems are provided for partitioning data of a database or data store into several independent parts as part of a data mining process. The methods and systems use a mining application having content-based partitioning logic to partition the data. Once the data is partitioned, the partitioned data may be grouped and distributed to an associated processor for further processing. The mining application and content-based partitioning logic may be used in a computing system, including shared memory and distributed memory multi-processor computing systems. Other embodiments are described and claimed.

Abstract: Apparatus, methods, and machine readable media that segment audio streams based upon application of three models to the audio stream are disclosed. One method includes extracting audio features from an audio stream and identifying a set of candidate change points between segments of the audio stream based upon the extracted audio features. The method further includes discarding a candidate change point between a first segment and a second segment in response to determining that a single multivariate Gaussian model represents the extracted audio features of the first segment and the second segment better than a first multivariate Gaussian model represents the extracted audio features of the first segment and a second multivariate Gaussian model represents the extracted audio features of the second segment.