Abstract: A method for generating traffic demand data of a data center network includes: acquiring traffic demand samples each including a source address, a destination address, a flow interval, and a flow size; acquiring a first interval number by performing equal-frequency binning discretization processing according to the flow interval and acquiring a second interval number by performing equal-frequency binning discretization processing according to the flow size; determining a traffic demand subset according to the source address and the destination address, and acquiring a first parameter matrix and a second parameter matrix by training a latent Dirichlet allocation probability topic model according to the traffic demand subset; and generating the traffic demand data according to the first interval number, the second interval number, the first parameter matrix, and the second parameter matrix.

Abstract: An information transmission method and a related device applied to a cloud service system are provided. The cloud service system includes an arbiter, a first switch, and a first server group. The arbiter is connected to the first server group by using the first switch. The method includes: a first server obtains a first identifier of the first server in the first server group. The first server determines, in a first slot, a first time domain location corresponding to the first identifier. The first time domain location is a time domain location at which the first switch receives a first request to be processed by the arbiter, and different identifiers correspond to different time domain locations in the first slot. The first server sends the first request to the first switch based on the first time domain location.

Abstract: A method for generating traffic demand data of a data center network includes: acquiring traffic demand samples each including a source address, a destination address, a flow interval, and a flow size; acquiring a first interval number by performing equal-frequency binning discretization processing according to the flow interval and acquiring a second interval number by performing equal-frequency binning discretization processing according to the flow size; determining a traffic demand subset according to the source address and the destination address, and acquiring a first parameter matrix and a second parameter matrix by training a latent Dirichlet allocation probability topic model according to the traffic demand subset; and generating the traffic demand data according to the first interval number, the second interval number, the first parameter matrix, and the second parameter matrix.

Abstract: A traffic-aware switch-shared cache scheduling method includes: S1, setting a cache threshold of each outgoing port of a switch according to a traffic state of each outgoing port of the switch; S2, monitoring each outgoing port of the switch to determine whether an event of packet entry queue, packet exit queue, packet loss, buffer overflow or port queue state change occurs; S3, determining a traffic state of the outgoing port according to the event that occurs at the outgoing port and corresponding port queue state information; S4, setting a port control state according to the traffic state of the outgoing port; and S5, adjusting the cache threshold corresponding to the outgoing port according to the port control state, and performing S2 to continue monitoring until the switch stops working.

Abstract: A method for detecting an available bandwidth based on a burstiness of a key frame of a video stream, includes: establishing a video connection between a sender and a receiver, and sending the video stream by the sender to the receiver; recording a sending timestamp of each packet at the sender; recording a receiving timestamp of each packet received by the receiver; calculating a difference between the receiving timestamp and the sending timestamp of each packet, and obtaining the packet with the smallest difference and the packet with the greatest difference by traversing the packets in the key frame; and estimating a currently available bandwidth according to the packet with the smallest difference and the packet with the greatest difference.

Abstract: The present application discloses a method for displaying map information and corresponding apparatus, electronic device, and computer storage medium, which relates to the fields of deep learning, knowledge graphs, and artificial intelligence. The method may include: when a user starts a map, acquiring a user feature of the user and historical click theme information of the user; for any to-be-recommended theme, determining a click probability of the to-be-recommended theme by using a pre-trained recommendation model according to the user feature and the historical click theme information respectively; and displaying the to-be-recommended themes with the click probabilities meeting a predetermined requirement on the map. The efficiency of acquiring information through maps by users and the like can be improved by use of the solutions according to the present application.

Abstract: This application provides a data transmission method and apparatus. The method includes: determining a first sending rate based on a network performance objective of first data and a network status of a first transmission control protocol (TCP) connection of a transport layer protocol, where the first TCP connection is used to send the first data; and sending the first data based on the first sending rate. In this way, network congestion control is more flexible, and TCP-based data transmission efficiency is improved.

Abstract: A multipath transmission control method oriented to deadlines of data blocks, includes: allocating transmission paths and timeslots to multiple data blocks to be sent at a sender according to heterogeneous attributes of the multiple data blocks and current network conditions, wherein the heterogeneous attributes comprise deadlines, sizes and priorities of the multiple data blocks; determining whether sending condition changes; and when the sending condition changes, rescheduling the multiple data blocks to be sent.

Abstract: A method for detecting an available bandwidth based on a burstiness of a key frame of a video stream, includes: establishing a video connection between a sender and a receiver, and sending the video stream by the sender to the receiver; recording a sending timestamp of each packet at the sender; recording a receiving timestamp of each packet received by the receiver; calculating a difference between the receiving timestamp and the sending timestamp of each packet, and obtaining the packet with the smallest difference and the packet with the greatest difference by traversing the packets in the key frame; and estimating a currently available bandwidth according to the packet with the smallest difference and the packet with the greatest difference.

Abstract: A traffic-aware switch-shared cache scheduling method includes: S1, setting a cache threshold of each outgoing port of a switch according to a traffic state of each outgoing port of the switch; S2, monitoring each outgoing port of the switch to determine whether an event of packet entry queue, packet exit queue, packet loss, buffer overflow or port queue state change occurs; S3, determining a traffic state of the outgoing port according to the event that occurs at the outgoing port and corresponding port queue state information; S4, setting a port control state according to the traffic state of the outgoing port; and S5, adjusting the cache threshold corresponding to the outgoing port according to the port control state, and performing S2 to continue monitoring until the switch stops working.

Abstract: Disclosed is an adaptive bitrate adjustment method for multi-user interactive live broadcast, comprising the following steps: 1) calculating a target bitrate of each pair of sending end and receiving end by using a non-linear programming method; 2) adjusting and online updating target bitrate by buffer feedback to eliminate system errors during modeling and measurement; and 3) clustering the target bitrate based on the QoE loss to obtain final actual bitrate. In the present invention, the user experience of the broadcaster is maximized and real-time interaction is achieved by reasonably adjusting the bitrate of each broadcaster end in a multi-user interactive live broadcast scenario and considering various constraint conditions.

Abstract: The present disclosure discloses a method and an apparatus for generating a map, relating to a field of intelligent transportation technologies in the field of computer technologies. The method includes the following. A street view image corresponding to a target road is obtained. The street view image is input into a preset deep learning model to obtain data of a candidate isolation belt corresponding to the street view image. The data of the candidate isolation belt includes information of the candidate isolation belt and a probability corresponding to the information of the candidate isolation belt. The information of the candidate isolation belt is corrected based on a preset correction strategy and the probability to obtain information of a target isolation belt. An icon corresponding to the information of the target isolation belt is added on a base map including the target road to generate a map.

Abstract: Disclosed is an adaptive bitrate adjustment method for multi-user interactive live broadcast, comprising the following steps: 1) calculating a target bitrate of each pair of sending end and receiving end by using a non-linear programming method; 2) adjusting and online updating target bitrate by buffer feedback to eliminate system errors during modeling and measurement; and 3) clustering the target bitrate based on the QoE loss to obtain final actual bitrate. In the present invention, the user experience of the broadcaster is maximized and real-time interaction is achieved by reasonably adjusting the bitrate of each broadcaster end in a multi-user interactive live broadcast scenario and considering various constraint conditions.

Abstract: An organic light-emitting diode (OLED) substrate includes: a base substrate including a display region having a plurality of luminous regions and a non-luminous region separating one or more adjacent luminous regions, the non-luminous region including a plurality of first connection regions; a first electrode layer over the base substrate including a plurality of first electrodes having their projections on the base substrate cover the plurality of luminous regions; a pixel defining layer over the first electrode layer and located at the non-luminous region and defining the plurality of luminous regions, the pixel defining layer is hollowed out at the first connection regions; an electroluminescent functional layer provided over the pixel defining layer; a second electrode layer over the electroluminescent functional layer; and a plurality of conductive structures located at the plurality of first connection regions respectively, and electrically coupled to the second electrode layer.

Abstract: A herbicidal composition includes two active components of A and B. The component A is selected from a compound shown in the following formula I: The component B is selected from glyphosate and an applicable salt or ester thereof. When a solid formulation is prepared, the active component A is firstly absorbed by an absorption carrier, and the absorbed product is then mixed with the component B, auxiliaries and fillers to obtain a stable solid formulation.

Abstract: The present application discloses a method for displaying map information and corresponding apparatus, electronic device, and computer storage medium, which relates to the fields of deep learning, knowledge graphs, and artificial intelligence. The method may include: when a user starts a map, acquiring a user feature of the user and historical click theme information of the user; for any to-be-recommended theme, determining a click probability of the to-be-recommended theme by using a pre-trained recommendation model according to the user feature and the historical click theme information respectively; and displaying the to-be-recommended themes with the click probabilities meeting a predetermined requirement on the map. The efficiency of acquiring information through maps by users and the like can be improved by use of the solutions according to the present application.