Abstract: A system receives a neural network model that includes asymmetric operations. Each asymmetric operation includes one or more fixed-point operands that are asymmetrically-quantized from corresponding floating-point operands. The system compiles a given asymmetric operation of the neural network model into a symmetric operation that includes a combined bias value. A compiler computes the combined bias value is a constant by merging at least zero points of input and output of the given asymmetric operation. The system then generates a symmetric neural network model including the symmetric operation for inference hardware to execute in fixed-point arithmetic.

Abstract: A method for detecting people entering and leaving a field is provided in an embodiment of the disclosure. The method includes the following. An event detection area corresponding to an entrance is set, and the event detection area includes an upper boundary, a lower boundary, and an internal area, and the lower boundary includes a left boundary, a right boundary, and a bottom boundary; a person image corresponding to a person in an image stream is detected and tracked; and whether the person passes through or does not pass through the entrance is determined according to a first detection result and a second detection result.

Abstract: A method for detecting people entering and leaving a field is provided in an embodiment of the disclosure. The method includes the following. An event detection area corresponding to an entrance is set, and the event detection area includes an upper boundary, a lower boundary, and an internal area, and the lower boundary includes a left boundary, a right boundary, and a bottom boundary; a person image corresponding to a person in an image stream is detected and tracked; and whether the person passes through or does not pass through the entrance is determined according to a first detection result and a second detection result.

Abstract: The present invention provides an electronic device including a plurality of processing circuits is disclosed, wherein the apparatus includes a circuitry configured to perform the steps of: receiving a model an input data for execution; analyzing the model to obtain a graph partition size of the model; partitioning the model into a plurality of graphs based on the graph partition size, wherein each of the graphs comprises a portion of operations of the model; deploying the plurality of graphs to at least two of the processing circuits, respectively; and generating output data according to results of the at least two of the processing circuits executing the plurality of graphs.

Abstract: An image positioning method having following steps is provided. The steps include: obtaining world coordinates of two reference points and image coordinates of two projection points corresponding to the two reference points; calculating a plurality of coordinate transformation parameters relative to transformation between any image coordinates and any world coordinates corresponding to a camera according only to the world coordinates of the two reference points, the image coordinates of the two projection points, and world coordinates of the camera; obtaining an second image having an object image corresponding to an object through the camera; and positioning world coordinates of the object according to the coordinate transformation parameters.

Abstract: An image positioning method having following steps is provided. The steps include: obtaining world coordinates of two reference points and image coordinates of two projection points corresponding to the two reference points; calculating a plurality of coordinate transformation parameters relative to transformation between any image coordinates and any world coordinates corresponding to a camera according only to the world coordinates of the two reference points, the image coordinates of the two projection points, and world coordinates of the camera; obtaining an second image having an object image corresponding to an object through the camera; and positioning world coordinates of the object according to the coordinate transformation parameters.

Abstract: The disclosure provides a load balancing system, a load balancing device and a topology management method. The topology management method includes configuring and maintaining a transmission progress value for each of edge servers; grouping the edge servers into server groups, wherein the edge servers of each of the server groups provide one of a plurality of video streams, and each of the edge servers is grouped into at least one server group among the server groups; selecting a first video stream from at least one video stream corresponding of a first edge server having bandwidth usage rate higher than a high load threshold; synchronizing video data of the first video stream to a second edge server; setting a transmission progress value of the second edge server as a transmission progress value of the first edge server; and adding the second edge server into the server group corresponding to the first video stream.

Abstract: The disclosure provides a load balancing method, a load balancing system, a load balancing device and a topology reduction method. The load balancing method includes configuring a transmission progress value for each of the edge servers; grouping the edge servers into server groups, wherein each of the edge servers is grouped into at least one server group among the server groups; receiving a download request corresponding to a first video stream from a user device, wherein a first server group among the server groups provides the first video stream; and selecting one of the edge servers from the edge servers of the first server group as a first edge server to provide video data of the first video stream to the user device according to the transmission progress values of the edge servers of the first server group.

Abstract: According to one exemplary embodiment, a parallel scheduling method for network data transmission is provided. This method generates a corresponding modulus condition set for each weight in a weight set, with each modulus condition of the modulus condition set having a modulus operation, and a divisor and a remainder for the modulus operation, uses a network node to transmit the modulus condition set corresponding to said each weight to a transmitting node corresponding to the weigh. Based on the modulus condition set, the transmitting node transmits a plurality of data chunks, and at least one receiving node receives the plurality of data chunks, wherein each data chunk corresponding to a sequence number, and the sequence number matches a corresponding modulus condition in the modulus condition set.

Abstract: A system for accessing data among at least two different electronic devices is provided. The system includes a demanding electronic device and a providing electronic device. The demanding electronic device is utilized to establish an input virtual device to execute an application on the demanding electronic device. The providing electronic device is utilized to establish an output virtual device for transmitting data from the providing electronic device to the demanding electronic device via the output virtual device, wherein the data corresponds to the application, and the providing electronic device is physically separated from the demanding electronic device. The input virtual device is established to use a first peripheral of the providing electronic device as a built-in peripheral of the demanding electronic device.

Abstract: A technique, as well as select implementations thereof, pertaining to cross-mounting a device is described. The technique may involve an apparatus detecting a presence of a device not a part of the apparatus. The technique may also involve the apparatus performing an update in response to the detecting of the presence of the device. The technique may additionally involve the apparatus establishing a communication connection with the device. The technique may further involve the apparatus utilizing the device to perform one or more tasks.

Abstract: The disclosure provides a load balancing system, a load balancing device and a topology management method. The topology management method includes configuring and maintaining a transmission progress value for each of edge servers; grouping the edge servers into server groups, wherein the edge servers of each of the server groups provide one of a plurality of video streams, and each of the edge servers is grouped into at least one server group among the server groups; selecting a first video stream from at least one video stream corresponding of a first edge server having bandwidth usage rate higher than a high load threshold; synchronizing video data of the first video stream to a second edge server; setting a transmission progress value of the second edge server as a transmission progress value of the first edge server; and adding the second edge server into the server group corresponding to the first video stream.

Abstract: The disclosure provides a load balancing method, a load balancing system, a load balancing device and a topology reduction method. The load balancing method includes configuring a transmission progress value for each of the edge servers; grouping the edge servers into server groups, wherein each of the edge servers is grouped into at least one server group among the server groups; receiving a download request corresponding to a first video stream from a user device, wherein a first server group among the server groups provides the first video stream; and selecting one of the edge servers from the edge servers of the first server group as a first edge server to provide video data of the first video stream to the user device according to the transmission progress values of the edge servers of the first server group.

Abstract: A method for processing hardware or software service requests, applied in a first electronic device, including: receiving a first hardware or software service request; determining whether there is a need to use hardware or software of a second electronic device to process the first hardware or software service request; transmitting the first hardware or software service request to the second electronic device when there is a need to use the hardware or software of the second electronic device; receiving a first response message from the second electronic device, wherein the first response message indicates that the hardware or software of the second electronic device provides the first hardware or software service; and providing the first hardware or software service according to the first response message.

Abstract: A communications system for accessing a cross-platform service is provided. The communications system includes a first communication device including a service demander and a second communication device including a service provider. The service demander transmits an advanced device information request to a second communication device for requesting advanced device information according to an IP address of the second communication device via a network. The service provider transmits a device information response including the advanced device information to the service demander of the first communication device, wherein the advanced device information at least includes a service list.

Abstract: A system for accessing data among at least two different electronic devices is provided. The system includes a demanding electronic device and a providing electronic device. The demanding electronic device is utilized to establish an input virtual device to execute an application on the demanding electronic device. The providing electronic device is utilized to establish an output virtual device for transmitting data from the providing electronic device to the demanding electronic device via the output virtual device, wherein the data corresponds to the application, and the providing electronic device is physically separated from the demanding electronic device. The input virtual device is established to use a first peripheral of the providing electronic device as a built-in peripheral of the demanding electronic device.

Abstract: A technique, as well as select implementations thereof, pertaining to cross-mounting a device is described. The technique may involve an apparatus detecting a presence of a device not a part of the apparatus. The technique may also involve the apparatus performing an update in response to the detecting of the presence of the device. The technique may additionally involve the apparatus establishing a communication connection with the device. The technique may further involve the apparatus utilizing the device to perform one or more tasks.

Abstract: According to one exemplary embodiment, a parallel scheduling method for network data transmission is provided. This method generates a corresponding modulus condition set for each weight in a weight set, with each modulus condition of the modulus condition set having a modulus operation, and a divisor and a remainder for the modulus operation, uses a network node to transmit the modulus condition set corresponding to said each weight to a transmitting node corresponding to the weigh. Based on the modulus condition set, the transmitting node transmits a plurality of data chunks, and at least one receiving node receives the plurality of data chunks, wherein each data chunk corresponding to a sequence number, and the sequence number matches a corresponding modulus condition in the modulus condition set.

Abstract: A method for controlling a task migration of a task in a heterogeneous multi-core system having at least a first cluster and a second cluster is provided. The method may include at least the following steps: dynamically adjusting a migration threshold; comparing a load of the task running on one core of the first cluster with the migration threshold, and accordingly generating a comparison result; and selectively controlling the task to migrate to the second cluster according to at least the comparison result, wherein each core in the first cluster has first processor architecture, and each core in the second cluster has second processor architecture different from the first processor architecture.

Abstract: A wireless communication network, including a destination node, a first node transmitting a first routing message, wherein the first node has a first routing table including a first entry for the destination node, and the first entry includes a first list field for child node(s). The network further includes a second node generating and transmitting a second routing message according to the first routing message, wherein the second routing message includes a second parent node field, and the second parent node field is marked as the first node that transmitted the first routing message. The first node further receives the second routing message and stores a first mark in the first list field for child node(s) of the first entry after determining that the second parent node field of the second routing message is marked as the first node, and the first mark denotes the second node.