WO2024045179A1 - 数据报文的传输方法、通信装置和通信系统 - Google Patents

数据报文的传输方法、通信装置和通信系统 Download PDF

Info

Publication number
WO2024045179A1
WO2024045179A1 PCT/CN2022/116833 CN2022116833W WO2024045179A1 WO 2024045179 A1 WO2024045179 A1 WO 2024045179A1 CN 2022116833 W CN2022116833 W CN 2022116833W WO 2024045179 A1 WO2024045179 A1 WO 2024045179A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
data
transmission path
path information
correspondence
Prior art date
Application number
PCT/CN2022/116833
Other languages
English (en)
French (fr)
Inventor
严学强
赵明宇
习燕
吴建军
颜敏
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to PCT/CN2022/116833 priority Critical patent/WO2024045179A1/zh
Publication of WO2024045179A1 publication Critical patent/WO2024045179A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks

Definitions

  • the embodiments of the present application relate to the field of communication, and, more specifically, to a data packet transmission method, a communication device, and a communication system.
  • Data is generated, flows and consumed in communication networks. With the development of network scale, new technologies, applications, etc., there is more and more data in the network and it is becoming more and more important. Therefore, efficient use of data requires a complete service architecture. In the past, data existed in the form of data islands, that is, an application only used its own data and could not use the data of other applications, nor could it use the data it obtained for other applications. . Data services are about breaking down data silos so that data, as a form of service, can be used by various applications both inside and outside the network to unleash its value.
  • information exchange between two network nodes requires the establishment of a communication path.
  • the intermediate node on the communication path is only responsible for forwarding data packets and does not process them.
  • the destination address is routed and forwarded.
  • data processing processes such as collection, storage, forwarding, and analysis can be performed at different network nodes. How to transmit data between the above network nodes that can process data is an issue that needs to be considered.
  • Embodiments of the present application provide a data message transmission method, communication device, and communication system, which can process data and improve data usage efficiency during the data message transmission process.
  • a data message transmission method may be executed by a first device, which may be a functional network element in the network, or a chip or circuit in a terminal device, network device, core network device or operation, maintenance and management device, or a device that can realize all Or some terminal equipment, network equipment, core network equipment or logical modules or software for operation, maintenance and management equipment functions, this application does not limit this.
  • the method includes: the first device obtains a first data packet, the first data packet includes first transmission path information, the first transmission path information includes information of the first device and the second device, and the first device based on the first A transmission path information determines a second device, and sends a second data packet to the second device.
  • the second data packet includes the second transmission path information, and the data load in the second data packet is based on the first data packet.
  • the data load in is processed.
  • this solution realizes the processing of data messages during the transmission process of data messages, which can meet the demand for distributed processing of data under the trend of communication-aware computing integration and improve the efficiency of data use.
  • the second transmission path information does not include information about the first device.
  • the first device after processing the first data message, the first device can delete its own information in the transmission path information of the second data message, which can save communication resource overhead.
  • the first transmission path information includes identification information of the first device and the second device, or the first transmission path information includes address information of the first device and the second device.
  • the first data message and the second data message further include data service information and/or statistical mode information
  • the statistical mode information is used to indicate statistics of statistical information.
  • the statistical information includes the number information of data packets or the number of bytes of data packets.
  • the processing node of the data message can determine the statistical method of statistical information through the statistical mode information indicated in the message, and then report statistics according to the instructions in the message.
  • the first device sends statistical information to the third device, where the statistical information includes information on the number of data packets or information on the number of bytes of the data packet.
  • the third device can be made aware of the number of data packets/bytes flowing through the first device, which facilitates the third device to coordinate whether to continue to allocate data packets to the first device for processing.
  • the statistical information is obtained based on the granularity of the transmission path information or data service information of the data packet.
  • the third device can determine the number of data packets/bytes on each transmission path passing through the first device. It is assumed that the statistical information is obtained based on the granularity of the transmission path information. If the data service information is obtained through granular statistics, the third device can determine the number of data packets/bytes of different data services processed by the first device, providing a reference for the third device's subsequent overall allocation.
  • a data message transmission method may be executed by a first device, which may be a chip or circuit in a terminal device, network device, core network device, or operation, maintenance and management device, or may be a chip or circuit capable of implementing all or part of the terminal device, network device, core network device, or operation and maintenance management device.
  • Logic modules or software for functions such as equipment or operation, maintenance and management of equipment, this application is not limited to this.
  • the method includes: the first device obtains service data, determines third transmission path information based on data service information, the third transmission path information includes information of the second device, the second device is a processing node of the third data message, and sends the third transmission path information to the third data packet processing node.
  • the second device sends a third data packet, where the third data packet includes the third transmission path information and a data payload corresponding to the service data.
  • the first device can determine the third transmission path information based on the data service information, and then determine the next processing node of the service data, that is, the second device, and combine the processed service data and the third transmission path information.
  • the path information is encapsulated into a third data message and transmitted to the next processing node.
  • the second device may determine the next processing node of the third data packet after the second device based on the third transmission path information.
  • the third transmission path information includes identification information or address information of the second device.
  • the first device receives correspondence information from the third device, the correspondence information indicates the correspondence between the data service information and the transmission path information, and the first device is based on The data service information and the correspondence information determine the third transmission path information.
  • the third device configures the corresponding relationship between the data service information and the transmission path information to the first device.
  • the first device can determine the third transmission path information based on the data service information, and can determine the next transmission path based on the third transmission path information.
  • determining the next processing node and determining the next hop node (physical route) of the data message can be decoupled, and the compatibility is stronger.
  • the data service information includes first data service information
  • the first data service information corresponds to N transmission path information
  • the N transmission path information includes third transmission path information.
  • N is an integer greater than or equal to 1.
  • the correspondence indicated by the correspondence information includes the correspondence between the first data service information and N transmission path information, where N is an integer greater than 1, and the first The device sends N data packets to N second devices, where each second device is associated with one data packet, and one data packet includes one transmission path information among the N transmission path information.
  • this solution can realize multicast and distribution of data packets, that is, it can realize flexible topology of the transmission path of data packets.
  • the N transmission path information includes information of parallel data processing devices, and the parallel data processing devices are processing nodes at the same level of the data message, and N is greater than 1 integer.
  • the parallel processing nodes can be determined through the structure of the transmission path information, so that the data packets can be multicast or distributed to the parallel processing nodes. , to achieve flexible topology of the transmission path of data messages.
  • the correspondence indicated by the correspondence information includes the correspondence between the first data service information and the third transmission path information, and N is an integer greater than 1.
  • the data service information corresponds to N transmission path information
  • the third transmission path information is associated with the first device. That is to say, the N transmission path information corresponds to different first devices.
  • This solution can realize datagram
  • the aggregation of packets means that the initial processing nodes of data packets are different and the final processing nodes are the same, that is, a flexible topology of the transmission path of data packets can be realized.
  • the third transmission path information includes information of data processing devices arranged in order, and the data processing device arranged first processes the data packet in a higher order.
  • the data service information corresponds to N transmission path information
  • N is an integer greater than 1
  • the third transmission path information is associated with the first device. That is to say, the N transmission path information corresponds to different first devices.
  • this solution can realize the aggregation of data packets, that is, it can realize the flexible topology of the transmission path of data packets.
  • the processing nodes arranged in order can be determined through the structure of the transmission path information, so that the data packets can be sent to the processing nodes in order for processing.
  • the first device receives configuration information from the third device, and the configuration information is used to configure at least one of the following: a statistical mode of the data packet, a statistical mode of the data packet, The statistical period and the validity time of the transmission path information.
  • the first device can report statistical information according to the configuration, and can transmit data packets according to the transmission path information within the validity time of the transmission path information.
  • the first device sends confirmation information to the third device, and the confirmation information is used to confirm the configuration information.
  • the third device can know that the configuration has been completed through the confirmation information, thereby avoiding sending the configuration information again and causing a waste of communication resources.
  • the first device receives update information from the third device, and the update information is used to update the transmission path information corresponding to the data service information.
  • the first device can subsequently transmit the data message according to the updated transmission path information.
  • the first device sends confirmation information to the third device, where the confirmation information is used to confirm that the first device has completed updating the transmission path information.
  • the third device can know that the transmission path information has been updated through the confirmation information, thereby avoiding sending update information again, causing a waste of communication resources.
  • the first device receives read information from the third device, and the read information is used to read the transmission path information corresponding to the data service information.
  • the transmission path information can be read by reading the information to confirm whether the transmission path information corresponding to a certain data service information is accurate and improve the performance of the system.
  • the first device sends read response information to the third device, and the read response information may include transmission path information corresponding to the data service information.
  • the transmission path information in the response information can be read to confirm whether the transmission path information corresponding to a certain data service information is accurate, which facilitates troubleshooting by the third device and improves system performance.
  • the first device receives deletion information from the third device, and the deletion information is used to delete the transmission path information corresponding to the data service information.
  • the transmission path information corresponding to the data service information can be deleted, thereby saving the storage resources of the first device.
  • the first device sends confirmation information to the third device, where the confirmation information is used to confirm that the first device has completed deletion of the transmission path information.
  • the third device can know that the first device has completed the deletion operation based on the confirmation information, thereby avoiding sending the deletion instruction again and wasting transmission resources.
  • the third data message also includes data service information and/or statistical mode information.
  • the statistical mode information is used to indicate the statistical mode of the statistical information.
  • the statistical information Including the quantity information of data packets or the byte quantity information of data packets.
  • the processing node of the data message can determine the statistical method of statistical information through the statistical mode information indicated in the message, and then report statistics according to the instructions in the message.
  • the first device sends statistical information to the third device, where the statistical information includes information on the number of data packets or information on the number of bytes of the data packet.
  • the third device can be made aware of the number of data packets/bytes flowing through the first device, which facilitates the third device to coordinate whether to continue to allocate data packets to the first device for processing.
  • the statistical information is obtained by taking the transmission path information or data service information of the data packet as a granularity.
  • the third device can determine the number of data packets/bytes on each transmission path passing through the first device. It is assumed that the statistical information is obtained based on the granularity of the transmission path information. If the data service information is obtained through granular statistics, the third device can determine the number of data packets/bytes of different data services processed by the first device, providing a reference for the third device's subsequent overall allocation.
  • the data service information is any of the following: the identifier of the federated learning service, the identifier of the distributed learning service, or the identifier of the data aggregation service.
  • a data message transmission method may be executed by a third device.
  • the third device may be a functional network element in the network, or may be a chip or circuit in network equipment or core network equipment. It may also be capable of implementing all or part of the network equipment or core network equipment. Functional logic modules or software, this application does not limit this.
  • the method includes: the third device generates correspondence information, the correspondence information indicates the correspondence between the data service information and the transmission path information of the data message, and sends the correspondence information to the first device.
  • the third device configures the corresponding relationship between the data service information and the transmission path information to the first device, so that the first device can determine the transmission path information corresponding to certain data service information based on the corresponding relationship, and transmit based on the transmission path information. data message.
  • the third device can dynamically construct and maintain the transmission path information of the data message, making the transmission and processing of the data message more flexible.
  • the above-mentioned transmission path information includes information of a second device, and the second device is a processing node of the data packet.
  • the transmission path information includes the information of the processing node, which means that the data packet is processed along the way. That is, this scheme enables the processing node to process the data packet during the transmission process, which can satisfy the communication perception. Under the computing convergence trend, there is a need for distributed processing of data and to improve data usage efficiency.
  • the data service information includes first data service information, and the first data service information corresponds to N pieces of transmission path information, where N is an integer greater than or equal to 1.
  • the transmission path information includes identification information of the second device or address information of the second device.
  • the correspondence indicated by the correspondence information includes the correspondence between the first data service information and N transmission path information, where N is an integer greater than 1.
  • one data service information can correspond to multiple transmission paths with the first device as the initial processing node, and multicast and distribution of data messages can be realized, that is, a flexible topology of the transmission paths of data messages can be realized.
  • the N transmission path information includes information of parallel data processing devices, and the parallel data processing devices are processing nodes at the same level of the data message, and N is greater than 1 integer.
  • the parallel processing nodes can be determined through the structure of the transmission path information, so that the data packets can be multicast or distributed to the parallel processing nodes. , to achieve flexible topology of the transmission path of data messages.
  • the third device sends N pieces of correspondence information to N first devices, wherein each first device is associated with one piece of correspondence information, and the one piece of correspondence information
  • the indicated correspondence includes a correspondence between the first data service information and one of the N transmission path information, where N is an integer greater than 1.
  • one data service information can correspond to multiple transmission paths with multiple first devices as initial processing nodes, and the aggregation of data messages can be realized, that is, a flexible topology of the transmission paths of data messages can be realized.
  • each transmission path information in the N transmission path information includes information of data processing devices arranged in order, and the data processing device ranked first processes the datagram.
  • the order of the text is first.
  • the data service information corresponds to N transmission path information
  • the first device is associated with one of the transmission path information.
  • This solution can realize the aggregation of data packets, that is, it can realize the flexible topology of the transmission path of data packets.
  • the processing nodes arranged in order can be determined through the structure of the transmission path information, so that the data packets can be sent to the processing nodes in order for processing.
  • the third device sends configuration information to the first device, and the configuration information is used to configure at least one of the following: a statistical mode of data packets, a statistics mode of data packets Period, the validity time of the transmission path information.
  • the third device receives confirmation information from the first device, and the confirmation information is used to confirm the configuration information.
  • the third device sends update information to the first device, where the update information is used to update the transmission path information corresponding to the data service information.
  • the third device receives confirmation information from the first device, and the confirmation information is used to confirm that the first device completes the update of the transmission path information.
  • the third device sends read information to the first device, and the read information is used to read the transmission path information corresponding to the data service information.
  • the third device receives read response information from the first device, and the read response information may include transmission path information corresponding to the data service information.
  • the third device sends deletion information to the first device, where the deletion information is used to delete the transmission path information corresponding to the data service information.
  • the third device receives confirmation information from the first device, and the confirmation information is used to confirm that the first device has completed deletion of the transmission path information.
  • the third device receives statistical information from the first device, where the statistical information includes information on the number of data packets or information on the number of bytes of the data packet.
  • the statistical information is obtained using transmission path information or data service information as granular statistics.
  • the data service information is any of the following: an identifier of a federated learning service, an identifier of a distributed learning service, or an identifier of a data aggregation service.
  • the fourth aspect provides a data message transmission method.
  • the method can be applied to a communication system including a first device and a third device.
  • the first device may be a functional network element in the network, or may be a chip or circuit in terminal equipment, network equipment, core network equipment, or operation, maintenance and management equipment, or may be a device capable of realizing all or part of terminal equipment, network equipment, core Logic modules or software for network equipment or operation, maintenance and management equipment functions, this application does not limit this.
  • the third device may be a functional network element in the network, or it may be a chip or circuit in network equipment or core network equipment, or it may be a logic module or software that can realize all or part of the functions of network equipment or core network equipment. This application There is no limit to this.
  • the method includes: the third device generates correspondence information, the correspondence information indicates the correspondence between the data service information and the transmission path information of the data message, and sends the correspondence information to the first device; the first device receives the correspondence information.
  • the method further includes: the first device obtains service data, and determines third transmission path information based on the data service information and the corresponding relationship, where the third transmission path information includes the third transmission path information.
  • the second device is the processing node of the third data message and sends the third data message to the second device.
  • the third data message includes the third transmission path information and the data load corresponding to the service data. .
  • the third device configures the corresponding relationship between the data service information and the transmission path information to the first device, so that the first device can determine the transmission path information corresponding to certain data service information based on the corresponding relationship, And transmit data packets based on the transmission path information.
  • the third device can dynamically construct and maintain the transmission path information of the data message, making the transmission process of the data message more flexible.
  • the first device can determine the next processing node of the data message based on the transmission path information, and the processing complexity of the first device is low.
  • the third transmission path information includes identification information or address information of the second device.
  • the data service information includes first data service information, the first data service information corresponds to N transmission path information, and the N transmission path information includes third transmission path information.
  • N is an integer greater than or equal to 1.
  • the correspondence indicated by the correspondence information includes the correspondence between the first data service information and the N transmission path information, where N is an integer greater than 1, so a device Obtain service data, determine N second devices based on the first data service information and the corresponding relationship information, and send N data packets to the N second devices, where each second device is associated with one data packet.
  • a data packet includes one transmission path information among the N transmission path information.
  • the N transmission path information includes information of parallel data processing devices, and the parallel data processing devices are processing nodes at the same level of the data message, and N is greater than 1 integer.
  • the third device sends N pieces of correspondence information to N first devices, where each first device is associated with one piece of correspondence information, and one piece of correspondence information indicates that The corresponding relationship between the first data service information and one of the N transmission path information, where N is an integer greater than 1.
  • each transmission path information in the N transmission path information includes information of data processing devices arranged in order, and the data processing device ranked first processes the data message.
  • the order is first, N is an integer greater than 1.
  • the third device sends configuration information, and the configuration information is used to configure at least one of the following: a statistical mode of the data packet, a statistical period of the data packet, the transmission Valid time of the path information, and the first device receives the configuration information.
  • the first device sends confirmation information
  • the confirmation information is used to confirm the configuration information
  • the third device receives the confirmation information
  • the third device sends update information
  • the update information is used to update the transmission path information corresponding to the data service information
  • the first device receives the update information
  • the first device sends confirmation information
  • the confirmation information is used to confirm that the first device completes the update of the transmission path information
  • the third device receives the confirmation information
  • the third device sends read information, the read information is used to read the transmission path information corresponding to the data service information, and the first device receives the read information .
  • the first device sends read response information, which may include transmission path information corresponding to the data service information, and the third device receives the read response information.
  • the third device sends deletion information
  • the deletion information is used to delete the transmission path information corresponding to the data service information
  • the first device receives the deletion information.
  • the first device sends confirmation information
  • the confirmation information is used to confirm that the first device has completed deletion of the transmission path information
  • the third device receives the confirmation information
  • the third data message also includes data service information and/or statistical mode information, and the statistical mode information is used to indicate the statistical mode of the statistical information.
  • the statistical information Including the number information of data packets or the number of bytes of data packets.
  • the first device sends statistical information
  • the statistical information includes quantity information of data packets or byte quantity information of data packets
  • the third device receives the statistical information .
  • the statistical information is obtained based on granular statistics of transmission path information or data service information of the data packet.
  • beneficial effects that are not described in the implementation of beneficial effects in the above fourth aspect, please refer to the description of the beneficial effects in the corresponding implementation in the second/third aspect, and will not be described again here.
  • the data service information is any of the following: an identifier of a federated learning service, an identifier of a distributed learning service, or an identifier of a data aggregation service.
  • a communication device is provided.
  • the communication device is a first device.
  • the first device may be a functional network element in the network, or it may be a chip or circuit in terminal equipment, network equipment, core network equipment or operation, maintenance and management equipment, or it may be capable of realizing all or This application does not limit the logic modules or software that function as part of terminal equipment, network equipment, core network equipment or operation, maintenance and management equipment.
  • the first device includes a transceiver unit and a processing unit: the transceiver unit is used to obtain a first data message, the first data message includes first transmission path information, and the first transmission path information includes information about the first device and the second device.
  • the processing unit is configured to determine the second device based on the first transmission path information
  • the transceiver unit is configured to send a second data message to the second device, the second data message includes the second transmission path information, and the second The data payload in the data packet is processed based on the data payload in the first data packet.
  • the second transmission path information does not include information about the first device.
  • the first transmission path information includes identification information of the first device and the second device, or the first transmission path information includes address information of the first device and the second device.
  • the first data message and the second data message further include data service information and/or statistical mode information, and the statistical mode information is used to indicate statistics of statistical information.
  • this statistical information includes the number information of data packets or the number of bytes of data packets.
  • the transceiver unit is further configured to send statistical information to a third device, where the statistical information includes information on the number of data packets or byte number information on the data packet.
  • the statistical information is obtained based on granular statistics of transmission path information or data service information of the data packet.
  • a communication device is provided.
  • the communication device is a first device.
  • the first device may be a chip or circuit in a terminal device, a network device, a core network device, or an operation and maintenance management device. It may also be a chip or circuit that can implement all or part of the terminal device, network device, or core network device. Or logic modules or software that operate, maintain and manage equipment and other functions, this application does not limit this.
  • the first device includes a transceiver unit and a processing unit: the transceiver unit is used to obtain service data, and the processing unit is used to determine third transmission path information based on data service information.
  • the third transmission path information includes information of the second device.
  • the device is a processing node for the third data message, and the transceiver unit is also used to send the third data message to the second device.
  • the third data message includes third transmission path information and a data load corresponding to the service data.
  • the third transmission path information includes identification information or address information of the second device.
  • the transceiver unit is also configured to receive correspondence information from a third device, the correspondence information indicating the correspondence between the data service information and the transmission path information, the The processing unit determines the third transmission path information based on the data service information and the correspondence information.
  • the data service information includes first data service information, the first data service information corresponds to N transmission path information, and the N transmission path information includes third transmission path information.
  • N is an integer greater than or equal to 1.
  • the correspondence indicated by the correspondence information includes the correspondence between the first data service information and N transmission path information, where N is an integer greater than 1, and the transceiver The unit is also configured to send N data packets to N second devices, wherein each second device is associated with one data packet, and one data packet includes one transmission path information among the N transmission path information.
  • the N transmission path information includes information of parallel data processing devices, and the parallel data processing devices are processing nodes at the same level of the data message, and N is greater than 1 integer.
  • the correspondence indicated by the correspondence information includes the correspondence between the first data service information and the third transmission path information.
  • N is an integer greater than 1. .
  • the third transmission path information includes information of data processing devices arranged in order, and the data processing device arranged first processes the data packets in a higher order.
  • the transceiver unit is also used to receive configuration information from a third device, where the configuration information is used to configure at least one of the following: statistical mode of data packets, data The statistical period of the packet and the validity time of the transmission path information.
  • the transceiver unit is further configured to send confirmation information to a third device, where the confirmation information is used to confirm the configuration information.
  • the transceiver unit is further configured to receive update information from a third device, where the update information is used to update the transmission path information corresponding to the data service information.
  • the transceiver unit is further configured to send confirmation information to the third device, where the confirmation information is used to confirm that the first device has completed the update of the transmission path information.
  • the transceiver unit is further configured to receive read information from a third device, where the read information is used to read transmission path information corresponding to the data service information.
  • the transceiver unit is further configured to send read response information to a third device, where the read response information may include transmission path information corresponding to the data service information.
  • the transceiver unit is further configured to receive deletion information from a third device, where the deletion information is used to delete the transmission path information corresponding to the data service information.
  • the transceiver unit is further configured to send confirmation information to the third device, where the confirmation information is used to confirm that the first device has completed deletion of the transmission path information.
  • the third data message further includes data service information and/or statistical mode information, and the statistical mode information is used to indicate the statistical mode of the statistical information.
  • the statistical information Including the quantity information of data packets or the byte quantity information of data packets.
  • the transceiver unit is further configured to send statistical information to a third device, where the statistical information includes information on the number of data packets or byte number information on the data packet.
  • the statistical information is obtained by using the transmission path information or data service information of the data packet as a granularity.
  • the data service information is any of the following: an identifier of a federated learning service, an identifier of a distributed learning service, or an identifier of a data aggregation service.
  • a communication device is provided.
  • the communication device is a third device.
  • the third device can be a functional network element in the network, or a chip or circuit in network equipment or core network equipment, or it can realize all or part of the functions of network equipment or core network equipment. Logic modules or software, this application does not limit this.
  • the third device includes a processing unit and a transceiver unit: the processing unit is used to generate correspondence information, the correspondence information indicates the correspondence between the data service information and the transmission path information of the data message, and the transceiver unit is used to send the correspondence information to the first device .
  • the transmission path information includes information of a second device, and the second device is a processing node of the data packet.
  • the transmission path information includes identification information of the second device or address information of the second device.
  • the data service information includes first data service information, and the first data service information corresponds to N pieces of transmission path information, where N is an integer greater than or equal to 1.
  • the correspondence indicated by the correspondence information includes a correspondence between the first data service information and N pieces of transmission path information, where N is an integer greater than 1.
  • the N transmission path information includes information of parallel data processing devices, and the parallel data processing devices are processing nodes at the same level of the data message, and N is greater than 1 integer.
  • the transceiver unit is further configured to send N pieces of correspondence information to N first devices, wherein each first device is associated with one piece of correspondence information, and the one The correspondence information indicates a correspondence between the first data service information and one of the N transmission path information, where N is an integer greater than 1.
  • each of the N transmission path information includes information of data processing devices arranged in order, and the data processing device ranked first processes the datagram.
  • the order of the text is first, and N is an integer greater than 1.
  • the transceiver unit is also used to send configuration information to the first device, where the configuration information is used to configure at least one of the following: statistical mode of data packets, data packets The statistical period of the document and the validity time of the transmission path information.
  • the transceiver unit is further configured to receive confirmation information from the first device, where the confirmation information is used to confirm the configuration information.
  • the transceiver unit is further configured to send update information to the first device, where the update information is used to update the transmission path information corresponding to the data service information.
  • the transceiver unit is further configured to receive confirmation information from the first device, where the confirmation information is used to confirm that the first device has completed updating the transmission path information.
  • the transceiver unit is further configured to send read information to the first device, where the read information is used to read the transmission path information corresponding to the data service information.
  • the transceiver unit is further configured to receive read response information from the first device, where the read response information may include transmission path information corresponding to the data service information.
  • the transceiver unit is further configured to send deletion information to the first device, where the deletion information is used to delete the transmission path information corresponding to the data service information.
  • the transceiver unit is further configured to receive confirmation information from the first device, where the confirmation information is used to confirm that the first device has completed deletion of the transmission path information.
  • the transceiver unit is also configured to receive statistical information from the first device, where the statistical information includes information on the number of data packets or information on the number of bytes of the data packet. .
  • the statistical information is obtained using transmission path information or data service information as granular statistics.
  • the data service information is any of the following: an identifier of a federated learning service, an identifier of a distributed learning service, or an identifier of a data aggregation service.
  • An eighth aspect provides a communication device, which includes a processor coupled to a memory and capable of executing instructions in the memory to implement any one of the above first to second aspects, and the first A method in any possible implementation manner from the aspect to the second aspect.
  • the device further includes a memory, and the memory and the processor may be deployed separately or centrally.
  • the device further includes a communication interface, and the processor is coupled to the communication interface.
  • the communication interface may be a transceiver, or an input/output interface.
  • the device is a first device, and the first device may be a functional network element in the network, or may be a chip or circuit in terminal equipment, network equipment, core network equipment, or operation, maintenance and management equipment, It may also be a logical module or software that can realize all or part of the functions of terminal equipment, network equipment, core network equipment or operation, maintenance and management equipment, and this application is not limited to this.
  • the communication interface may be an input/output interface, interface circuit, output circuit, input circuit, pin or related circuit on the chip or chip system, etc.
  • the processor may also be embodied as a processing circuit or logic circuit.
  • the transceiver may be a transceiver circuit.
  • the input/output interface may be an input/output circuit.
  • the above-mentioned processor can be one or more chips
  • the input circuit can be an input pin
  • the output circuit can be an output pin
  • the processing circuit can be a transistor, a gate circuit, a flip-flop and various logic circuits, etc.
  • the input signal received by the input circuit may be, but is not limited to, received and input by the receiver
  • the signal output by the output circuit may be, but not limited to, output to and transmitted by the transmitter
  • the input circuit and the output circuit may be The same circuit is used as an input circuit and an output circuit at different times.
  • the embodiments of this application do not limit the specific implementation methods of the processor and various circuits.
  • a communication device in a ninth aspect, includes a processor.
  • the processor is coupled to a memory and can be used to execute instructions in the memory to implement the above third aspect and any of the possible implementations of the third aspect.
  • the device further includes a memory, and the memory and the processor may be deployed separately or centrally.
  • the device further includes a communication interface, and the processor is coupled to the communication interface.
  • the communication interface may be a transceiver, or an input/output interface.
  • the device is a third device.
  • the third device may be a functional network element in the network, or may be a chip or circuit in network equipment or core network equipment, or may be capable of implementing all or part of Logic modules or software for network equipment and core network equipment functions are not limited in this application.
  • the communication interface may be an input/output interface, interface circuit, output circuit, input circuit, pin or related circuit on the chip or chip system, etc.
  • the processor may also be embodied as a processing circuit or logic circuit.
  • the transceiver may be a transceiver circuit.
  • the input/output interface may be an input/output circuit.
  • the above-mentioned processor can be one or more chips
  • the input circuit can be an input pin
  • the output circuit can be an output pin
  • the processing circuit can be a transistor, a gate circuit, a flip-flop and various logic circuits, etc.
  • the input signal received by the input circuit may be, but is not limited to, received and input by the receiver
  • the signal output by the output circuit may be, but not limited to, output to and transmitted by the transmitter
  • the input circuit and the output circuit may be The same circuit is used as an input circuit and an output circuit at different times.
  • the embodiments of this application do not limit the specific implementation methods of the processor and various circuits.
  • a communication device in a tenth aspect, includes a logic circuit and an input/output interface.
  • the logic circuit is coupled to the input/output interface and transmits data through the input/output interface to perform the above-mentioned first aspect to the third aspect. Any one of the three aspects, and a method in any possible implementation manner of the first to third aspects.
  • a communication system in an eleventh aspect, includes a first device and a third device.
  • the first device is configured to perform any one of the above first to second aspects, and the first to second aspects.
  • the method in any possible implementation manner; the third device is used to perform the above third aspect, and the method in any possible implementation manner of the third aspect.
  • a computer-readable storage medium stores a computer program (which can also be called a code, or an instruction), and when run on a computer, causes the computer to execute the above-mentioned first aspect. to any one of the third aspects, and the method in any possible implementation manner of the first to third aspects.
  • a computer program which can also be called a code, or an instruction
  • a computer program product includes: a computer program (which may also be called a code, or an instruction).
  • a computer program which may also be called a code, or an instruction.
  • the computer program When the computer program is run, it causes the computer to execute the above first to third aspects. Any one of the aspects, and the method in any possible implementation manner of the first to third aspects.
  • Figure 1 is a network architecture provided by an embodiment of the present application.
  • Figure 2 is a flow interaction diagram of a data packet transmission method provided by an embodiment of the present application.
  • Figure 3 is a flow interaction diagram of another data packet transmission method provided by an embodiment of the present application.
  • Figure 4 is a schematic diagram for a data aggregation scenario provided by an embodiment of the present application.
  • Figure 5 is a schematic diagram of a data aggregation and data distribution scenario provided by an embodiment of the present application.
  • Figure 6 is a schematic block diagram of a communication device provided by an embodiment of the present application.
  • Figure 7 is a schematic structural diagram of a communication device provided by an embodiment of the present application.
  • Figure 8 is a schematic structural diagram of another communication device provided by an embodiment of the present application.
  • Figure 1 is a network architecture provided by an embodiment of the present application.
  • the communication system 100 shown in Figure 1 includes data sources, data planes and data consumers.
  • Data sources (such as data source 00, data source 01) can be devices that generate business data; the data plane is used for data processing, such as data collection, data storage, data preprocessing, data analysis, and data service application program interfaces (application program). interface, API), etc.
  • Data consumers (eg, data consumer 50, data consumer 51) may be devices that use processed data.
  • the data plane includes data processing devices (for example, data processing device 10 , data processing device 11 , data processing device 20 , data processing device 21 , data processing device 22 , data processing device 23 ) and a data arrangement device 30 .
  • the data processing device may be a processing node for business data.
  • the data orchestration device can configure basic information for the data processing device, such as configuration identification information, etc.
  • the data processing nodes involved in different data services can be different, so the transmission paths corresponding to different data services can be different.
  • Figure 1 shows two paths of data transmission, the first path: data source 00 ⁇ data processing device 10 ⁇ data processing device 21 ⁇ data processing device 23 ⁇ data consumer 51, the second path: data source 01 ⁇ data processing Device 11 ⁇ data processing device 20 ⁇ data processing device 22 ⁇ data consumer 50, “ ⁇ ” indicates the transmission direction of business data.
  • the data communication network shown in Figure 1 can work as a message bus for data exchange between different data processing devices.
  • the data processing device can be a data agent (data agent, DA), which can collect, store, preprocess, analyze and other processing work on data.
  • the data processing device can be deployed independently, such as in the network in the form of a network function (NF) or a network element.
  • the data processing device can also be built into a network node, such as a terminal device or a radio access network.
  • network, RAN) node core network (core network, CN) node, operation and maintenance management (operation administration and maintenance, OAM) node.
  • OAM operation administration and maintenance
  • the data processing device can also be evolved from the above-mentioned nodes.
  • the data processing device is evolved from the network data analysis function (network data analysis function, NWDAF), including the ability to realize the existing functions of NWDAF, and the functions implemented based on NWDAF. Scenario use cases, etc., this application does not limit this.
  • NWDAF network data analysis function
  • the data orchestration device can be a data orchestrator (DO), which can receive data service requirements from applications (data service requirements such as data collection, federated learning training or inference based on network collected data, etc.), and based on the requirements Determining the data processing device is to dynamically establish an end-to-end (E2E) upper-layer topology network (topology) for data applications.
  • the upper-layer topology network is the data processing network, and the network nodes in the network (i.e. The data processing device) is the data processing node.
  • the DO can arrange the flow of data between DAs in the data communication network, and can feed back the response to the demand to the application, for example, feed back to the application that the upper topology network has been established.
  • the data orchestration device can be deployed independently, for example, in the form of NF or network element in the network.
  • the data orchestration device can also be built into a network node, for example, into a RAN node or a CN node. This application does not limit this.
  • the upper layer network is relative to the underlying network (underlay) and is a logical network built on the underlying network.
  • the underlying network underlay
  • the underlying network Through network virtualization technology, one or more virtual logical networks can be built on the same underlying network.
  • Different upper-layer networks can share equipment and lines in the underlying network, but the services in the upper-layer network and the physical networking and interconnection technologies in the underlying network can be decoupled from each other.
  • the data plane also includes a trusted device 40, which is used to ensure data credibility and protect data from attacks.
  • a trusted device 40 which is used to ensure data credibility and protect data from attacks.
  • the trusted device can be a trusted anchor (trust anchor, TA), which can provide security services such as authentication authorization accounting (AAA), and store tamper-proof data and user equipment (UE).
  • AAA authentication authorization accounting
  • UE user equipment
  • NE network element
  • the data plane also includes a storage device 24.
  • the storage device can be used as a storage extension of the data processing device.
  • the storage device is, for example, a data storage function (DSF) network element, which is not limited in this application.
  • DSF data storage function
  • the method provided by the embodiment of the present application may also involve devices or communication nodes not shown in Figure 1.
  • the communication method provided by the embodiment of the present application may also include only some of the devices or communication nodes shown in Figure 1.
  • the embodiment of the present application There is no limit to this.
  • the above network architecture applied to the embodiments of the present application is an illustration.
  • the network architecture applicable to the embodiments of the present application is not limited to this. Any network architecture that can realize the functions of some or all of the above devices is suitable for the embodiments of the present application. .
  • the terminal device may be a wireless terminal device capable of receiving network device scheduling and indication information.
  • An end device may be a device that provides voice and/or data connectivity to a user, or a handheld device with wireless connectivity capabilities, or other processing device connected to a wireless modem.
  • Terminal equipment can also be called terminal, access terminal, user unit, user equipment (UE), user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, wireless communication equipment, User agent or user device.
  • An end device is a device that includes wireless communication capabilities (providing voice/data connectivity to the user). For example, handheld devices with wireless connection functions, or vehicle-mounted devices.
  • the terminal in the embodiment of the present application can be a mobile phone (mobile phone), a tablet computer (pad), a computer with wireless transceiver functions, a train, an airplane, a mobile internet device (mobile internet device, MID), virtual reality (virtual reality, VR) terminals, augmented reality (AR) terminals, wireless terminals in industrial control (such as robots, etc.), wireless terminals in the Internet of Vehicles (such as vehicle-mounted equipment, vehicle equipment, vehicle-mounted modules, vehicles, etc.
  • wireless terminals in self-driving wireless terminals in remote medical, wireless terminals in smart grid, wireless terminals in transportation safety, smart cities ( Wireless terminals in smart city, wireless terminals in smart city, wireless terminals in smart home, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local Wireless local loop (WLL) station, personal digital assistant (PDA), handheld device with wireless communication capabilities, computing device or other processing device connected to a wireless modem, vehicle-mounted device, wearable device, 5G Terminals in the network or terminals in future evolution networks (such as 6G), etc.
  • SIP session initiation protocol
  • WLL wireless local Wireless local loop
  • PDA personal digital assistant
  • wearable devices can also be called wearable smart devices. It is a general term for applying wearable technology to intelligently design daily wear and develop wearable devices, such as glasses, gloves, watches, clothing and shoes, etc.
  • a wearable device is a portable device that is worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not just hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly defined wearable smart devices include full-featured, large-sized devices that can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to cooperate with other devices such as smartphones. Use, such as various types of smart bracelets, smart jewelry, etc. for physical sign monitoring.
  • An access network node may be a device in a wireless network.
  • the access network node may be a device deployed in the wireless access network to provide wireless communication functions for terminal devices.
  • the access network node may be a radio access network (RAN) node that connects the terminal device to the wireless network, and may also be called an access network device.
  • RAN radio access network
  • Access network nodes include but are not limited to: evolved Node B (evolved Node B, eNB), wireless network controller (radio network controller, RNC), Node B (Node B, NB), base station controller (base station controller, BSC), base transceiver station (BTS), home base station (home evolved NodeB, HeNB, or home Node B, HNB), baseband unit (baseBand unit, BBU), server, wearable device, vehicle equipment, WIFI
  • the base station may be a macro base station, a micro base station, a pico base station, a small station, a relay station or a balloon station, etc.
  • gNB may include centralized units (CUs) and DUs.
  • the gNB may also include an active antenna unit (AAU).
  • CU implements some functions of gNB
  • DU implements some functions of gNB.
  • CU is responsible for processing non-real-time protocols and services, implementing radio resource control (RRC), and packet data convergence protocol (PDCP) layer functions.
  • RRC radio resource control
  • PDCP packet data convergence protocol
  • DU is responsible for processing physical layer protocols and real-time services, and implementing the functions of the radio link control (RLC) layer, media access control (MAC) layer and physical (physical, PHY) layer.
  • RLC radio link control
  • MAC media access control
  • PHY physical layer
  • the RRC layer information is generated by the CU, and will eventually be encapsulated by the PHY layer of the DU into PHY layer information, or converted from the PHY layer information. Therefore, under this architecture, high-level signaling, such as RRC layer signaling, can also be considered to be sent by DU, or sent by DU+AAU.
  • the network device may be a device including one or more of a CU node, a DU node, and an AAU node.
  • the CU can be divided into network equipment in the access network (radio access network, RAN), or the CU can be divided into network equipment in the core network (core network, CN), which is not limited in this application.
  • the function of the core network node is to provide user connections, manage users, and carry session services.
  • V2X can include vehicle to network (V2N), vehicle to vehicle (V2V), vehicle to infrastructure (V2I), vehicle to pedestrian (V2P), etc., Workshop communication long-term evolution technology (long term evolution-vehicle, LTE-V), Internet of Vehicles, machine type communication (MTC), Internet of things (IoT), machine-to-machine communication long term evolution technology (
  • the data generated in the communication network will be transmitted to each data processing node in the form of data packets.
  • network perception data, user data, artificial intelligence (AI) data, IoT data, etc. need to be carried by a data pipeline (DP) including collection, processing, transmission, storage, analysis and other functions.
  • a data pipeline can understand For a path in the upper topological network (such as the first path or the second path shown in Figure 1), which processing nodes are in a data pipeline can be determined by the data orchestration device.
  • the data orchestration device can establish a data pipeline based on the data service request and the capabilities of each data processing device.
  • the data pipeline can be one-way. After the data pipeline is established, the processing nodes in the data pipeline can be determined. Each processing node needs to process the data. Operations determine that data flows within a data pipeline and that processing operations are completed at the processing nodes through which it flows.
  • Each processing node on the data pipeline needs to perform on-path-packet-processing (such as collection, preprocessing, transmission, storage, analysis, etc.) on the data packets containing the data, and then forward them to the next node.
  • Processing nodes Communication between different processing nodes in the data pipeline can depend on the communication path of the underlying network, but how each processing node in the data pipeline determines the next processing node of the data message can be decoupled from the underlying network. The following describes the method provided by this application for transmitting data packets between processing nodes.
  • Figure 2 is a flow interaction diagram of a data packet transmission method provided by an embodiment of the present application.
  • the method 200 shown in Figure 2 includes:
  • Data processing device #0 obtains business data.
  • data processing device #0 is a device that collects business data, or is the first processing node of business data, that is, the initial processing node.
  • the data processing device #0 is an entrance DA of a data pipeline (for example, the data processing device 10 or the data processing device 11 shown in FIG. 1 ), and the entrance DA is used to obtain business data from a data source.
  • the data source is the source of data generation, such as sensors, built-in collectors of network function parameters, etc.
  • Business data is data collected/collected at the data source.
  • business data includes data sensed by sensors, performance data of network functions in network data, or resource utilization information, etc.
  • the types of business data corresponding to different data sources can be different. For example, when the data source is a temperature sensor, the business data is data representing temperature. When the data source is a pressure sensor, the business data is data representing pressure. This application does not limit this.
  • data processing device #0 determines data processing device #1.
  • the data processing device #0 determines the transmission path information (corresponding to the third transmission path information in the content of the invention) based on the data service (DS) information.
  • the transmission path information includes the transmission path information of the data processing device #1.
  • Information, data processing device #1 is the processing node of data message #1, and data message #1 includes the data load corresponding to the service data and the transmission path information.
  • data services are based on a framework for data collection, storage, forwarding, analysis and other processing, meet the requirements of data laws and regulations, take into account the sharing and security of data, and provide data as a service product.
  • the data service information can be the identifier of the data service. Different applications (data consumers) may have different data service requirements, so the data services corresponding to different applications are also different. The data service information can distinguish different data services.
  • data services include federated learning, distributed learning, and data aggregation, etc.
  • the data service information is a data service identifier.
  • the identifier (ID) of the federated learning service is DS_ID 1
  • the identifier of the distributed learning service is DS_ID 2
  • the identifier of the data aggregation service is DS_ID 3. Only some data services are listed above, and the identifiers of the listed data services are only examples, and this application does not limit them.
  • the data processing device #0 can determine the data service information based on the acquired business data, and determine the transmission path information corresponding to a certain data service based on the correspondence between the data service information and the transmission path information of the data message.
  • the data processing device #0 obtains the business data and the data service information corresponding to the business data, determines the transmission path information corresponding to a certain data service according to the correspondence between the data service information and the transmission path information of the data message, and transmits Path information can be encapsulated into data packets.
  • the data processing device #0 locally stores the corresponding relationship between the data service information and the transmission path information of the data message, or the data processing device #0 can obtain the corresponding relationship from the data orchestration device. This application is for obtaining the corresponding relationship. There are no restrictions on the method.
  • the business data obtained by data processing device #0 is data for federated learning
  • the data service identifier of the federated learning service is DS_ID 1.
  • the data service identifier can also be understood as a data pipeline identifier (because the data corresponding to different data services
  • the pipelines can be different, that is, the data processing devices in the data pipelines corresponding to different data services can be different).
  • the data pipeline identification corresponding to the federated learning service is DP_ID 1
  • DS_ID 1/DP_ID 1 corresponds to the transmission path information #1.
  • Transmission path information #1 includes information on one or more data processing devices that process business data for federated learning. Different data pipeline identifiers or different data service identifiers correspond to different transmission path information.
  • the transmission path information includes identification information of one or more data processing devices.
  • the identification information of the data processing devices may be pre-allocated by a data arrangement device (such as the data arrangement device shown in Figure 1). That is to say, the data orchestration device can assign an identifier to each data processing device (including data processing device #0 and data processing device #1) on the overlay network.
  • the transmission path information includes information about parallel data processing devices, and the parallel data processing devices are processing nodes at the same level of the data packet.
  • the transmission path information includes information about the data processing devices arranged in order, and the data processing devices arranged first process the data packets in a higher order.
  • the transmission path information #1 is ⁇ DA_ID1,[DA_ID 2(DA_ID 4)
  • DAj) means that DAi and DAj are parallel data processing devices, that is, the same level processing nodes of data messages, which can process different data loads.
  • (DAi,DAj) or (DAi(DAj) means that DAi and DAj are Sequential relationship, and DAj is ranked lower, that is, DAj is the next processing node of DAi.
  • DA_ID1 ⁇ DA_ID2 ⁇ DA_ID4 there are two paths: DA_ID1 ⁇ DA_ID2 ⁇ DA_ID4; DA_ID1 ⁇ DA_ID3 ⁇ DA_ID5.
  • DA_ID 2 and DA_ID3 are parallel
  • DA_ID4 and DA_ID5 is parallel
  • DA_ID1 and DA_ID 2 and DA_ID3 are in a sequential relationship.
  • the device corresponding to DA_ID1 can send a data packet to the device corresponding to DA_ID 2 and DA_ID3 to let it process the data load in the data packet.
  • this scenario is a data multicast scenario; if the data payloads in the sent data packets are different, this scenario is a data distribution scenario.
  • transmission path information #1 is only an example, and this application does not limit it.
  • the transmission path information includes the address information of one or more data processing devices.
  • the address information may be the routing address information of the one or more data processing devices in the underlying network. This application does not cover this. Make restrictions.
  • the transmission path information #1 is ⁇ Add1,[Add 2(Add 4)
  • Add j means that Add i and Add j are parallel data processing devices, that is, the same level processing nodes of data packets.
  • (Add i, Add j) or (Addi(Addj)) means that Add i and Add j are in a sequential relationship, and Add j is arranged later, that is, Add j is the next processing node of Add i.
  • Add2 and Add3 are parallel
  • Add4 and Add5 are parallel
  • Add1 and Add 2 and Add3 are sequential relationships.
  • the device corresponding to Add1 can send data packets to the devices corresponding to Add 2 and Add3 to let them process the data payload in the data packet. If the data payload in the data packets sent is the same, then this scenario is a data multicast scenario. If If the data payloads in the sent data packets are different, then this scenario is a data distribution scenario.
  • transmission path information #1 is only an example, and this application does not limit it.
  • Data processing device #0 sends data message #1 to data processing device #1.
  • Data message #1 includes transmission path information and a data load corresponding to the service data.
  • data processing device #1 receives the data message #1.
  • the data processing device #0 processes the service data into a data payload and encapsulates it into the data message #1.
  • the header of the data message #1 includes transmission path information, and the transmission path information includes the data message #1. information of processing nodes.
  • data packet #1 has two processing nodes, namely data processing device #1 and data processing device #2, then the transmission path information includes information about data processing device #1 and data processing device #2.
  • data message #1 also includes a data service identifier or a data pipeline identifier (such as DS_ID 1/DP_ID 1).
  • data packet #1 also includes statistical mode information.
  • the statistical mode information is used to indicate the statistical mode of the statistical information.
  • the statistical information includes the number information of the data packet or the byte number information of the data packet, or the statistical information includes Other quantitative information is not limited by this application.
  • the data packet includes statistical mode information, which allows the processing node of the data packet to determine the statistical method of statistical information through the statistical mode information indicated in the data packet, so as to report statistical information according to the instructions in the data packet.
  • the statistical mode information is statistical mode encoding.
  • the following introduces the meanings of different statistical mode encodings:
  • 000 Indicates the number of packet statistics based on data service information as the granularity
  • 001 Indicates the number of packets counted based on the transmission path information as the granularity
  • 010 Indicates the number of bytes counted based on data service information as the granularity
  • 011 Indicates the number of bytes counted based on the transmission path information
  • the data processing device #0 can report statistical information to the data arrangement device after the data message is sent, and the data processing device #1 can report the statistical information to the data arrangement device after the data message arrives or is sent. This application is for There is no restriction on this.
  • data processing device #0 and data processing device #1 are nodes in the overlay network. Therefore, during the actual transmission of data message #1, data processing device #0 can determine the data processing through the addressing mode of the underlying network. The routing path from device #0 to data processing device #1, thereby sending data packet #1 to data processing device #1.
  • the identifier of data processing device #1 in the overlay network is the same as the address of data processing device #1 in the underlying network.
  • Data processing device #0 can determine the location of data processing device #0 in the underlying network based on the identifier of data processing device #1.
  • the identifier of data processing device #1 in the overlay network and the address in the underlying network are different.
  • data processing device #0 can locally store the identifier of data processing device #1 in the overlay network and the address in the underlying network. and then determine the address of data processing device #1 based on the corresponding relationship, and determine the routing path from data processing device #0 to data processing device #1 in the underlying network, and send data message #1 through this routing path. Transfer to data processing unit #1.
  • method 200 also includes:
  • the data orchestration device sends correspondence information, which indicates the correspondence between data service information and transmission path information.
  • data processing device #0 receives the correspondence information.
  • the data processing node (for example, the data processing device shown in Figure 1, including data processing device #0 and data processing device #1) sends registration information to the data orchestration device, and the registration information can indicate its own capabilities/functions.
  • the data orchestration device generates an overlay network composed of processing nodes based on the registration information of each processing node. And the data orchestration device can assign an identifier to each data processing device on the overlay network.
  • the above-mentioned process of allocating identifiers to each data processing device can be called the initialization process of the overlay network.
  • the data orchestration device calculates transmission paths for different data service requests based on the data service request of the application and the network node capabilities/functions in the overlay network.
  • the data orchestration device calculates the transmission path of the federated learning data message according to the data service request of the federated learning application as DA#1 ⁇ DA#2 ⁇ upper-layer application.
  • DA#1 is the entrance DA (corresponding to data processing device # 0), which is the first processing node of the data packet, and can also be understood as the network node that generates the data packet.
  • the data orchestration device After the data orchestration device calculates the transmission paths for different data services, it generates a correspondence between the data service information and the transmission path information, and sends the correspondence information to the corresponding data processing device #0, where the correspondence indicates the data service information and the transmission path information. corresponding relationship.
  • the corresponding relationship generated by the data arrangement device is, for example, Table 1.
  • one data service identifier can correspond to multiple transmission path information, and the multiple transmission path information can correspond to one data processing device #0 or multiple data processing devices #0.
  • DS_ID 1 corresponds to two data processing devices #0 and two transmission path information.
  • DA#1 is associated with transmission path information 1 (DA#2, upper-layer application)
  • DA#3 is associated with transmission path information 2 (DA#6 , upper layer application)
  • the data orchestration device sends the correspondence information between DS_ID 1 and the transmission path information 1 to DA#1
  • the data orchestration device sends the correspondence information between DS_ID 1 and the transmission path information 2 to DA#3.
  • Data aggregation means that multiple data processing devices send data packets to a network node (such as a data processing device or application), and the data packets sent by different data processing devices belong to the same data service identifier.
  • DS_ID2 corresponds to a data processing device #0 and corresponds to two transmission path information.
  • DA#1 is associated with transmission path information 3 (DA#2, DA#4) and transmission path information 4 (DA#2, DA#5 ), the data arrangement device sends the correspondence information between DS_ID 2 and transmission path information 3 and transmission path information 4 to DA#1.
  • the initial processing nodes of transmission path information 3 and transmission path information 4 are the same, but the final processing nodes are different, which is suitable for data distribution or multicast scenarios.
  • Data multicast means that one data processing device sends the same data packet to two or more data processing devices (the same data packet corresponds to a data service identifier, for example, the same data packet corresponds to data service identifier #1),
  • Data distribution means that one data processing device sends different data packets to two or more data processing devices (different data packets correspond to a data service identifier, for example, different data packets correspond to data service identifier #2).
  • S201 may precede S210, or S201 may precede S220, and this application does not limit this.
  • Table 1 is only an example, and Table 1 can also be converted in other forms, which is not limited in this application.
  • Table 1 is transformed into the first column indicating the data processing device #0 and the second column indicating the data service information, which will not be listed one by one here.
  • the correspondence information sent by the data arrangement device to a data processing device #0 in S201 may indicate the correspondence between one or more data service information and transmission path information. That is, the data orchestration device can send the corresponding relationship between the data service information and the transmission path information to the relevant data processing device #0 for a piece of data service information. For example, see Table 1. For DS_ID 1, the data orchestration device sends the corresponding relationship information between DS_ID 1 and (DA#2, upper-layer application) to DA#1, and sends the corresponding relationship information between DS_ID 1 and (DA#6, upper-layer application). Message sent to DA#3.
  • the data arrangement device may send to each data processing device #0 the correspondence between the data service information and the transmission path information related to the data processing device #0.
  • the data orchestration device sends the correspondence information between DS_ID 1 and (DA#2, upper-layer application), and the correspondence information between DS_ID 2 and (DA#2, DA#4
  • DA#1 can select and use the corresponding relationship among the corresponding relationship information sent by the above-mentioned data arrangement device according to the acquired data service information.
  • the transmission path information of the data packet corresponding to DS_ID 1 can be determined as (DA#2, upper-layer application) through the corresponding relationship of different data service information mentioned above.
  • data processing device #0 After receiving the correspondence information, data processing device #0 stores the transmission path information corresponding to the data service information.
  • data processing device #0 locally stores a correspondence table between data service information and transmission path information. After receiving the correspondence information, data processing device #0 writes the transmission path information corresponding to the data service information into the correspondence table. .
  • data processing device #0 after data processing device #0 stores the transmission path information corresponding to the data service information, it sends confirmation information to the data orchestration device.
  • the confirmation message indicates that data processing device #0 has stored the transmission path information corresponding to the data service information.
  • the data arrangement device can confirm that the data processing device #0 has stored the transmission path information corresponding to the data service information.
  • the data service information in S201 includes data service information #1.
  • Data service information #1 corresponds to N pieces of transmission path information, where N is an integer greater than or equal to 1.
  • S230 can be replaced with:
  • Data processing device #0 sends N1 data packets to at least one data processing device #1, where each data processing device #1 is associated with at least one data packet, and each data packet includes one of N1 transmission path information Transmission path information, N1 is an integer greater than 1.
  • data service information #1 corresponds to the first data service information in the content of the invention.
  • data processing device #0 sends data message #2 to DA#2, and the header of data message #2 includes transmission path information #2; it sends data message #3 to DA#3, and the header of data message #3 includes transmission path information #3; sends data message #4 to DA#4, and the header of data message #4 includes transmission path information #4.
  • the data payloads in data packet #2, data packet #3 and data packet #4 are the same.
  • the data service information in S201 includes data service information #2.
  • Data service information #2 corresponds to N2 transmission path information, and N2 is an integer greater than 1.
  • data service information #2 corresponds to the first data service information in the content of the invention.
  • S230 can be replaced with:
  • Data processing device #0 sends N2 data packets to at least one data processing device #1, where each data processing device #1 is associated with at least one data packet, and each data packet includes one of the N2 transmission path information.
  • a transmission path information, N2 data packets include two data packets with different data loads.
  • data service information #2 is DS_ID 1.
  • 3 transmission path information corresponds to three data processing devices #1, namely DA#5, DA#6, and DA#7.
  • transmission path information #5 corresponds to DA#5
  • transmission path information #6 corresponds to DA#6, and transmission path information #7 Corresponds to DA#7.
  • data processing device #0 sends data message #5 to DA#5, and the header of data message #5 includes transmission path information #5; it sends data message #6 to DA#6, and the header of data message #6 includes transmission path information #6; sends data message #7 to DA#7, and the header of data message #7 includes transmission path information #7.
  • two data packets among data packet #5, data packet #6 and data packet #7 have different data payloads.
  • Data service information #3 corresponds to M transmission path information.
  • the M transmission path information corresponds to M1 data processing devices #0.
  • M is an integer greater than 1, and M1 is less than or equal to M.
  • the correspondence information in S201 indicates the correspondence between the data service information #3 and one of the M transmission path information.
  • data service information #3 corresponds to the first data service information in the content of the invention.
  • data service information #3 is DS_ID 2.
  • the data processing device #0 corresponding to the information #a is DA#0
  • the data processing device #0 corresponding to the transmission path information #b is DA#1
  • DA#0 sends data packet #8, and the header of data packet #8 includes transmission path information #a; DA#1 sends data packet #9, and the header of data packet #9 includes transmission path information #b. ;
  • DA#2 sends data message #10, and the header of data message #10 includes transmission path information #c.
  • the final processing node of data packet #8, data packet #9 and data packet #10 may be the same node.
  • 0 is DA#0
  • the data processing device #0 corresponding to the transmission path information #b is DA#1
  • DA#0 sends data packet #11, and the header of data packet #11 includes transmission path information #a
  • DA#1 sends data packet #12
  • the header of data packet #12 includes transmission path information #b.
  • DA#1 sends data message #13
  • the header of data message #13 includes transmission path information #c.
  • the final processing node of data packet #11, data packet #12 and data packet #13 may be the same node.
  • method 200 also includes:
  • the data orchestration device sends configuration information.
  • the configuration information is used to configure at least one of the following: the statistical mode of the data packet, the statistical period of the data packet, and the validity time of the transmission path information.
  • data processing device #0 receives the configuration information.
  • the data processing device #0 can count the data packet according to the statistical mode, and can encapsulate the statistical mode information in the data packet to inform the data packet of the process. In which mode the processing node counts data packets. For specific statistical modes, please refer to the examples in S230 and will not be described in detail here.
  • the configuration information configures a statistical period of data packets
  • data processing device #0 can count data packets according to the statistical period.
  • the configuration information configures the valid time of the transmission path information
  • the data processing device #0 can transmit the data message according to the transmission path information within the valid time of the transmission path information.
  • the data processing device #0 sends confirmation information to the data arrangement device, and the confirmation information is used to confirm the configuration information.
  • the data arrangement device determines that the configuration information has been accurately received by the data processing device #0, that is to say, the configuration operation has been completed.
  • method 200 also includes:
  • the data orchestration device sends update information, which is used to update the transmission path information corresponding to the data service information.
  • data processing device #0 receives the update information.
  • data processing device #0 locally stores the corresponding relationship between data service information and transmission path information.
  • data processing device #0 receives the update information, it can update the transmission path information corresponding to certain data service information based on the update information.
  • data processing device #0 locally stores the corresponding relationship between DS_ID 1 and transmission path information #1, and the update information includes the corresponding relationship between DS_ID 1 and transmission path information #2.
  • Data processing device #0 can combine DS_ID 1 and transmission path information #2 based on the update information.
  • the correspondence between transmission path information #1 is updated to the correspondence between DS_ID 1 and transmission path information #2.
  • the data message for DS_ID 1 is transmitted based on transmission path information #2.
  • the data processing device #0 sends confirmation information to the data arrangement device, and the confirmation information is used to confirm the updated information.
  • the data arrangement device determines that the update information has been accurately received by the data processing device #0, that is to say, the update operation has been completed.
  • the transmission path information can be updated instead of being fixed all the time. Therefore, the data processing device can transmit data messages according to the updated transmission path information, thereby improving the flexibility of data message transmission and processing.
  • method 200 also includes:
  • the data arrangement device sends read information, which is used to read the transmission path information corresponding to certain data service information.
  • data processing device #0 receives the read information.
  • the read information includes DS_ID 0, indicating that the data processing device #0 is allowed to send the transmission path information corresponding to DS_ID 0.
  • the data processing device #0 sends read response information to the data orchestration device, where the read response information includes transmission path information corresponding to certain data service information.
  • the data arrangement device determines that the read information has been accurately received by the data processing device #0, that is to say, the read operation has been completed.
  • the read response information includes transmission path information #0 corresponding to DS_ID 0.
  • the data orchestration device can read the transmission path information in the response information to confirm whether the transmission path information corresponding to a certain data service information is accurate, which facilitates the data orchestration device to troubleshoot and improve system performance.
  • method 200 also includes:
  • the data orchestration device sends deletion information, which is used to delete the transmission path information corresponding to certain data service information.
  • data processing device #0 receives the deletion information.
  • the data orchestration device can instruct the data processing device #0 to delete the transmission path information corresponding to the data service information through deletion information.
  • the deletion information can include the transmission path information that needs to be deleted. .
  • the data orchestration device obtains or receives a data service request.
  • the data service request is used to request deletion of the transmission path information corresponding to the data service information.
  • the data orchestration device sends deletion information to instruct the data processing device #0 to delete the transmission corresponding to the data service information.
  • Path information the deletion information may include the transmission path information that needs to be deleted.
  • the data processing device #0 sends confirmation information to the data arrangement device, and the confirmation information is used to confirm the deletion information.
  • the data arrangement device determines that the deletion information has been accurately received by the data processing device #0, which means that the deletion operation of the transmission path information has been completed.
  • the data arrangement device may also delete the transmission path information corresponding to the data service information.
  • the data processing device #0 deletes the transmission path information in response to the instruction of the data arrangement device.
  • the data processing device #0 can trigger the deletion of the transmission path information corresponding to the data service information at regular intervals without the need for instructions from the data arrangement device. .
  • the data arrangement device is notified, and the data arrangement device can also delete the transmission path information corresponding to the data service information.
  • the transmission path information corresponding to certain data service information is deleted, which can save storage resources of the data orchestration device or the data processing device.
  • the above confirmation information in S231 to S234 can enable the data arrangement device to confirm whether the data processing device #0 correctly receives the information (for example, configuration information, update information, read information or delete information), and whether the information is completed. command operation to avoid the data arrangement device not knowing whether the information has been correctly received by the data processing device #0 and whether the command operation of the information has been completed, causing the information to be resent, resulting in a waste of communication resources.
  • the information for example, configuration information, update information, read information or delete information
  • method 200 also includes:
  • Data processing device #0 sends statistical information, which includes information on the number of data packets or information on the number of bytes of data packets.
  • the data arrangement device receives the statistical information.
  • the statistical information is obtained by taking the transmission path information or data service information of the data packet as a granularity.
  • Example #1 the format of the statistics packet including statistical information is as follows in Table 2:
  • the identifier DP_ID 0 is used to identify that the statistical information is based on the transmission path information as the granularity of statistical packets.
  • the statistical value in the statistical packet is the corresponding DP_ID 0 (which can be understood as the data corresponding to the transmission path information #0).
  • the number of data packets (pipeline identifier), time #1 is the time when the statistical information is counted, or the time when the statistical packet is encapsulated. This application does not limit this, and the timestamps in the following text are also understood accordingly. The article will not go into details.
  • nPacket(DS j ) represents the number of data packets corresponding to a data service of DP_ID 0
  • m represents the data corresponding to DP_ID 0. Quantity served.
  • Example #2 the format of the statistical packet including statistical information is as follows Table 3:
  • the identifier DP_ID 0 is used to identify that the statistical information counts the number of bytes based on the transmission path information as the granularity.
  • the statistical value in the statistical packet is the number of bytes corresponding to DP_ID 0.
  • nByte(DS j ) represents the number of bytes of a data service corresponding to DP_ID 0
  • m represents the data corresponding to DP_ID 0. Quantity served.
  • Example #3 the format of the statistics packet including statistical information is as follows Table 4:
  • the identifier DS_ID 0 is used to identify that the statistical information is to count the number of packets based on the data service information as the granularity.
  • the statistical value in the statistical packet is the number of data packets corresponding to DS_ID 0.
  • nPacket(DP j ) represents the number of data packets corresponding to a certain transmission path of DS_ID 0
  • m represents the transmission corresponding to DS_ID 0. The number of paths.
  • Example #4 the format of the statistics packet including statistical information is as follows in Table 5:
  • the identifier DS_ID 0 is used to identify that the statistical information counts the number of bytes based on the data service information as the granularity.
  • the statistical value in the statistical packet is the number of bytes corresponding to DS_ID 0.
  • nByte(DP j ) represents the number of bytes of a transmission path corresponding to DS_ID 0
  • m represents the transmission corresponding to DS_ID 0. The number of paths.
  • Example #5 statistical information can also be reported according to the granularity of DS
  • nPacket(DS i ,DP j ) nPacket(DS i
  • DP j ), nByte(DS i ,DP j ) nByte(DS i
  • DP j ), for example, nPacket(DS 0 ,DP 0 ) nPacket(DS 0
  • DP 0 ), nByte(DS 0 ,DP 0 ) nByte(DS 0
  • DP 0 ) represents the number of data packets with the data service identifier DS_ID 0 and the data pipeline identifier DP_ID 0.
  • DP 0 ) represents the data service identifier DS_ID 0 and the data The number of bytes in the data packet with the pipe ID DP_ID 0.
  • reporting of statistical information can be triggered regularly, that is, the data processing device #0 can regularly report the statistical information to the data arrangement device, or the data arrangement device sends a request to the data processing device #0, and the data processing device #0 responds to the request for statistics. Report statistical information. This application does not limit this.
  • Tables 2 to 5 are only examples, and Tables 2 to 5 may have other transformations.
  • the format of Tables 2 to 5, and the order of the contents in rows or columns may be changed, or Tables 2 to 5 may include part of the content in the above example table, or Tables 2 to 5 may be part of the content in the above example table. More content is included on the basis, and this application does not limit this.
  • the data processing device sends statistical information to the data arrangement device, which allows the data arrangement device to know the number of data packets/bytes flowing through the data processing device, and facilitates the data arrangement device to coordinate whether to continue to allocate data packets to the data processing device in the future. its processing. Assuming that the statistical information is obtained based on the transmission path information as a granularity, the data orchestration device can determine the number of data packets/bytes on each transmission path flowing through the data processing device. Assume that the statistical information is obtained based on the data service information. If the granularity statistics are obtained, the data orchestration device can determine the number of data packets/bytes of different data services processed by the data processing device, and provide a reference for the data orchestration device to coordinate and distribute the subsequent processing of data packets.
  • method 200 also includes:
  • Data processing device #1 sends statistical information, where the statistical information includes information on the number of data packets or information on the number of bytes of data packets.
  • the data arrangement device receives the statistical information.
  • data processing device #0 corresponds to the first device in the content of the invention
  • data processing device #1 corresponds to the second device in the content of the invention
  • the data arrangement device corresponds to the third device in the content of the invention.
  • the data processing device #0 after the data processing device #0 obtains the business data, it can determine the transmission path information based on the data service information, and then determine the next processing node of the business data, and combine the processed business data and the transmission path information Encapsulated into data packets and transmitted to the next processing node.
  • the subsequent data processing device #1 can determine the next processing node of the data message after the data processing device #1 based on the transmission path information.
  • this solution enables other nodes to process data messages during the transmission process, which can meet the demand for distributed processing of data under the trend of communication-aware computing fusion and improve data usage efficiency.
  • Figure 3 is a flow interaction diagram of another data packet transmission method provided by an embodiment of the present application.
  • the method 300 shown in Figure 3 includes:
  • data processing device #1 obtains data message #A.
  • the first data message includes transmission path information #A (corresponding to the first transmission path information in the content of the invention).
  • the transmission path information #A includes data processing device #1. information and the information of data processing device #2, which is the next processing node of data processing device #1.
  • the data processing device is an intermediate or final processing node of the data message
  • the data message #A may be sent from the data processing device #0 shown in Figure 2
  • the transmission path information #A is the data processing device #0 Encapsulated into data message #A.
  • Data processing device #1 determines data processing device #2 based on transmission path information #A.
  • the transmission path information #A is (DA_ID 3, DA_ID 5), where DA_ID 3 is the identifier of the data processing device #1, DA_ID 5 is the identifier of the data processing device #2, and the data processing device #1 is based on (DA_ID 3 ,DA_ID5) determines data processing device #2.
  • identifiers of data processing device #1 and data processing device #2 may be configured by the data arrangement device.
  • the transmission path information #A is (Add3, Add5), where Add 3 is the address of the data processing device #1, Add5 is the address of the data processing device #2, and the data processing device #1 determines based on (Add3, Add5) Data Processing Device #2.
  • addresses of data processing device #1 and data processing device #2 may be multiplexed addresses in the underlying network, and this application does not limit this.
  • data processing device #1 sends data message #B.
  • the data message #B includes transmission path information #B (corresponding to the second transmission path information in the content of the invention), and the data payload in the data message #B Processed based on the data payload in data message #A.
  • data processing device #2 receives the data message #B.
  • data packet #A and data packet #B also include a data service identifier (such as DS_ID 1).
  • data packet #A and data packet #B also include statistical mode information.
  • the statistical mode information is used to indicate the statistical mode of statistical information.
  • the statistical information includes quantity information of data packets or the number of bytes of data packets.
  • Information, or statistical information includes other quantitative information, which is not limited by this application.
  • the transmission path information #A also includes the information of the next processing node of the data processing device #2, and the data processing device #2 processes the data in the data message #B.
  • the next processing node of the data processing device #2 can be determined according to the transmission path information #A, so that the processed data message #B can be transmitted to the next processing node for processing.
  • the transmission path information #B does not include the information of the data processing device #1.
  • the data processing device #1 After the data message #B is sent, the operation of the data processing device #1 has been completed.
  • the data processing device #1 encapsulates the data message #B, it can encapsulate the transmission path information #B into the data message #B.
  • the transmission path information #B is the transmission path information #A with the information of the data processing device #1 deleted.
  • the data packet sent may not contain its own information.
  • the data processing device #1 determines that the next processing node is multiple data processing devices #2 based on the transmission path information, it can refer to the relevant description in S230 to determine the multiple data processing devices #2 and provide the data to the multiple data processing devices #2. #2 Send a data message, the specific content will not be repeated.
  • method 300 also includes:
  • Data processing device #1 sends statistical information, which includes information on the number of data packets or information on the number of bytes of data packets. Correspondingly, the data arrangement device receives the statistical information.
  • method 300 also includes:
  • Data processing device #2 sends statistical information, which includes information on the number of data packets or information on the number of bytes of data packets. Correspondingly, the data arrangement device receives the statistical information.
  • Method 200 and method 300 can be used in combination.
  • content not specifically described in method 300 please refer to the relevant description in method 200.
  • details will not be described again.
  • the data processing device #1 ie, the intermediate processing node of the data message
  • the data processing device #1 can determine the next processing node of the data message based on the transmission path information in the data message. And the processed data message and transmission path information are encapsulated into data messages and transmitted to the next processing node.
  • This solution enables the data processing device to process the data messages during the transmission process, can meet the demand for distributed processing of data under the trend of communication-aware computing fusion, and can improve the efficiency of data use.
  • data processing device #1 corresponds to the first device in the content of the invention
  • data processing device #2 corresponds to the second device in the content of the invention
  • the data arrangement device corresponds to the third device in the content of the invention.
  • Methods 200 and 300 introduce a data packet forwarding mechanism.
  • data processing device #0 has state (for example, some forwarding information configured by the data orchestration device (i.e., transmission path information) will be stored locally).
  • Data processing device #1 is stateless (for example, the forwarding information configured by the data orchestration device is not saved locally), that is, when forwarding the data packet, the next processing node of the data packet is determined based on the transmission path information in the data packet. , thereby transmitting data packets. Therefore, the data processing device #1 may not locally store the corresponding relationship between the data service information and the transmission path information. If data processing device #0 and data processing device #1 have other forwarding mechanisms when forwarding data packets. Then data processing device #0 and data processing device #1 can select the forwarding mechanism through the following method.
  • the forwarding mechanism of data processing device #0 can be determined by the configuration, and the configuration can be determined based on information such as the capabilities of data processing device #0.
  • the data processing device #0 can transmit the data packet based on the method 200. If the data processing device #0 does not locally configure the corresponding relationship between the data service information and the transmission path information, that is, the data processing device #0 is stateless, the data processing device #0 can transmit the data packet based on other forwarding mechanisms besides method 200. , this application does not limit this.
  • data processing device #1 or data processing device #2 can select an appropriate forwarding mechanism based on its own status and the status of the forwarded data packet.
  • data processing device #1 is stateless, and the data packet includes a status field, and the status field is set to stateful, then data processing device #1 selects the forwarding mechanism provided by method 300 to forward the data packet. If data processing device #1 is stateful, the status field included in the data message is set to stateless; or if data processing device #1 is stateful, the status field included in the data message is set to stateful, or the data Processing device #1 is stateless, and the status field included in the data message is set to stateless. Then data processing device #1 can choose other forwarding mechanisms other than method 300 to forward the data message. This application does not Make restrictions.
  • the data packet is stateful, that is, the data packet contains forwarding information (such as transmission path information), so that the data processing device along the data packet path does not need to save the forwarding information.
  • the data packet is stateless, that is, the data packet does not carry forwarding information (such as transmission path information), so the data processing device along the data packet path needs to save the forwarding information.
  • the data processing device can select an appropriate forwarding mechanism as needed to improve the flexibility and/or efficiency of data message transmission.
  • the following describes from a system perspective how the data orchestration device configures the transmission path information corresponding to the data service information in some special scenarios mentioned in method 200, and how the data processing device transmits data messages based on the transmission path information.
  • Figure 4 is a schematic diagram for a data aggregation scenario provided by an embodiment of the present application.
  • the data arrangement device is DO as an example
  • the data processing device is as DA as an example
  • the information of the data processing device is as the identification of DA
  • one data service information corresponding to three transmission path information is introduced as an example. This application does not Limited to this.
  • DO determines the three transmission paths corresponding to DS_ID 3 based on certain data service information, such as DS_ID 3 indicating data aggregation, and the capabilities/functions of each processing node, namely transmission path #A1, transmission path #B1 and transmission path #C1, where Transmission path #A1 is DA#4 ⁇ DA#3 ⁇ DA#13, transmission path #B1 is DA#7 ⁇ DA#11 ⁇ DA#13, transmission path #C1 is DA#17 ⁇ DA#19 ⁇ DA#13 .
  • DO sends correspondence information 1 to DA#4 (corresponding to data processing device #0 above).
  • Correspondence information 1 indicates the correspondence between DS_ID 3 and transmission path information #A1.
  • Transmission path information #A1 is (DA_ID 3, DA_ID 13); DO sends correspondence information 2 to DA#7 (corresponding to data processing device #0 above).
  • Correspondence information 2 indicates the correspondence between DS_ID 3 and transmission path information #B1.
  • Transmission path information #B1 is (DA_ID 11, DA_ID 13); DO sends correspondence information 3 to DA#17 (corresponding to data processing device #0 above).
  • Correspondence information 3 indicates the correspondence between DS_ID 3 and transmission path information #C1.
  • Transmission path information #C1 is (DA_ID 19,DA_ID 13).
  • DA#4 is used to collect the temperature of area #1 at different times within a period of time
  • DA#7 is used to collect the temperature of area #2 at different times within a period of time
  • DA#17 is used to collect the temperature of area #3 at different times of time. temperature at different times.
  • DA#4 After DA#4 collects the temperatures of area #1 at different times within a period of time, it encapsulates the collected temperatures into data message #A1.
  • the header of data message #A1 includes (DA_ID 3, DA_ID 13), where, DA_ID 3 is the identification of DA#3, and DA_ID 13 is the identification of DA#13.
  • DA#4 sends data message #A1 to DA#3 (corresponding to data processing device #1 above).
  • DA#3 After receiving data message #A1, DA#3 processes the data (i.e. temperature) in data message #A1. Perform processing, for example, process the average temperature #1 of area #1, and determine the next processing node, that is, DA#13, based on (DA_ID 3, DA_ID 13).
  • DA#3 sends data message #A2 to DA#13.
  • Data message #A2 includes the average temperature #1 and DA_ID 13 of area #1.
  • DA#7 After DA#7 collects the temperatures of area #2 at different times within a period of time, it encapsulates the collected temperatures into data message #B1.
  • the header of data message #B1 includes (DA_ID 11, DA_ID 13), where, DA_ID 11 is the identification of DA#11.
  • DA#7 sends data message #B1 to DA#11 (corresponding to data processing device #1 above).
  • DA#11 After receiving data message #B1, DA#11 processes the data (i.e. temperature) in data message #B1. Perform processing, for example, process the average temperature #2 of area #2, and determine the next processing node, which is DA#13, based on (DA_ID 11, DA_ID 13).
  • DA#11 sends data message #B2 to DA#13.
  • Data message #B2 includes the average temperature #2 and DA_ID 13 of area #2.
  • DA#17 After DA#17 collects the temperatures of area #3 at different times within a period of time, it encapsulates the collected temperatures into data message #C1.
  • the header of data message #C1 includes (DA_ID 19, DA_ID 13), where, DA_ID 19 is the identification of DA#19.
  • DA#17 sends data message #C1 to DA#19 (corresponding to data processing device #1 above).
  • DA#19 After receiving data message #C1, DA#19 processes the data (i.e. temperature) in data message #C1. Perform processing, for example, process the average temperature #3 of area #3, and determine the next processing node, which is DA#13, based on (DA_ID 19, DA_ID 13).
  • DA#19 sends data message #C2 to DA#13.
  • Data message #C2 includes the average temperature #3 and DA_ID 13 of area #3.
  • DA#13 After receiving data message #A2, data message #B2 and data message #C2, DA#13 processes the average temperature #1, average temperature #2 and average temperature #3 in the message into area #1, area The average temperature #4 of #2 and area #3, then the average temperature #4 is the processing result of the data aggregation service. And DA#13 knows that there is no next processing node according to data message #A2, data message #A2 and DA_ID 13 in data message #A2, that is, there is no need to send the average temperature #4 to other devices. At this point, the data aggregation service processing ends.
  • Figure 5 is a schematic diagram for data aggregation and data distribution scenarios provided by the embodiment of the present application.
  • the data arrangement device is DO as an example
  • the data processing device is as DA as an example
  • the information of the data processing device is as an identification of DA as an example
  • one data service information corresponding to three transmission path information is introduced as an example. This application does not Limited to this.
  • DO determines the three transmission paths corresponding to DS_ID 1 based on certain data service information, such as DS_ID 1 representing federated learning, and the capabilities/functions of each processing node, namely transmission path #A2, transmission path #B2, and transmission path #C2.
  • the transmission path of the data message corresponding to transmission path #A2 is DA#5 (corresponding to DA_ID: 5) ⁇ DA#3 (corresponding to DA_ID: 3) ⁇ DA#7 (corresponding to DA_ID: 7), and the transmission path corresponding to transmission path #B2
  • the transmission path of the data message is DA#13 (corresponding to DA_ID: 13) ⁇ DA#11 (corresponding to DA_ID: 11) ⁇ DA#7.
  • the transmission path of the data message corresponding to transmission path #C2 is DA#23 (corresponding to DA_ID :23) ⁇ DA#19 (corresponding to DA_ID: 19) ⁇ DA#7.
  • DA#5, DA#13, and DA#23 are federated learning clients.
  • Local model training is performed based on locally acquired business data, and then the trained local model parameters are processed into data loads, and Encapsulate it and the transmission path information into data packets and send them to DA#3, DA#11, and DA#19.
  • DA#3, DA#11, and DA#19 can perform model compression on the data payload (corresponding to local model parameters) in the received data message, and encapsulate the compressed model parameters and transmission path information into the data message for sending.
  • DA#7 aggregates the received compressed model parameters. After aggregation, DA#7 needs to distribute the aggregated global model parameters to clients DA#5, DA#13, and DA#23.
  • DO calculates how to send correspondence information #1, correspondence information #2, and correspondence information #3 to DA#5, DA#13, and DA#23 after determining the federated learning path.
  • FIG. 5 does not show the arrow directions of transmission path #A2, transmission path #B2, and transmission path #C2. The following mainly introduces the relevant content about data distribution in federated learning.
  • DS_ID 1 also corresponds to 3 transmission paths, namely transmission path #A3, transmission path #B3 and transmission path #C3.
  • Transmission path #A3 is DA#7 ⁇ DA#3 ⁇ DA#5
  • transmission path #B3 is DA#7 ⁇ DA#11 ⁇ DA#13
  • transmission path #C3 is DA#7 ⁇ DA#19 ⁇ DA#23 .
  • DO sends correspondence information #4 to DA#7, which is DS_ID 1: (DA_ID 3,DA_ID5)
  • DA#7 (corresponding to data processing device #0 above) is used to distribute the aggregated global model parameters to the client. If DA#7 divides the global model parameters into global sub-model parameters #1, global sub-model Parameter #2 and global sub-model parameter #3 send data message #a1 to DA#3 (corresponding to data processing device #1 above). Data message #a1 includes the data load corresponding to global sub-model parameter #1 and (DA_ID 3,DA_ID 5). DA#7 sends data message #b1 to DA#11 (corresponding to data processing device #1 above). Data message #b1 includes the data load corresponding to global sub-model parameter #2 and (DA_ID 11, DA_ID 13). DA#7 sends data message #c1 to DA#19 (corresponding to data processing device #1 above). Data message #c1 includes the data load corresponding to global sub-model parameter #3 and (DA_ID19, DA_ID 23).
  • DA#3 After receiving the data message #a1, DA#3 processes the data load corresponding to the global sub-model parameter #1 in the data message #a1, such as decompressing the data load corresponding to the global sub-model parameter #1, and based on (DA_ID 3 , DA_ID 5) Determine the next processing node, that is, DA#5, and send data message #a2 to DA#5.
  • Data message #a2 includes the data load corresponding to the decompressed global submodel parameter #1 and DA_ID 5.
  • DA#11 After receiving the data message #b1, DA#11 processes the data load corresponding to the global sub-model parameter #2 in the data message #b1, such as decompressing the data load corresponding to the global sub-model parameter #2, and based on (DA_ID 11 , DA_ID 13) Determine the next processing node, that is, DA#13, and send data message #b2 to DA#13.
  • Data message #b2 includes the data load corresponding to the decompressed global submodel parameter #2 and DA_ID 13.
  • DA#19 After DA#19 receives the data message #c1, it processes the data load corresponding to the global sub-model parameter #3 in the data message #c1, such as decompressing the data load corresponding to the global sub-model parameter #3, and based on (DA_ID 19 , DA_ID 23) Determine the next processing node, that is, DA#23, and send data message #c2 to DA#23.
  • Data message #c2 includes the data load corresponding to the decompressed global submodel parameter #3 and DA_ID 23.
  • multiple means two or more.
  • At least one item refers to one item or multiple items
  • at least two items and “multiple items” refer to two items. ) or two or more items.
  • At least one of the following” or similar expressions thereof refers to any combination of these items, including any combination of a single item (items) or a plurality of items (items).
  • at least one of a, b, or c can mean: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, c can be single or multiple .
  • execution subjects illustrated in Figures 2 and 3 are only examples.
  • the execution subjects may also be chips, chip systems, or processors that support the execution subjects in implementing the methods shown in Figures 2 and 3. This application does not No restrictions.
  • the methods and operations implemented by the data processing device #0 can also be implemented by components (such as chips or circuits) in the data processing device #0 and implemented by the data processing device #1
  • the methods and operations may also be implemented by components (such as chips or circuits) in the data processing device #1.
  • the methods and operations implemented by the data orchestration device can also be implemented by components (such as chips or circuits) in the data orchestration device.
  • each device such as a transmitting end device or a receiving end device, includes a corresponding hardware structure and/or software module for performing each function.
  • a transmitting end device or a receiving end device includes a corresponding hardware structure and/or software module for performing each function.
  • the present application can be implemented in the form of hardware or a combination of hardware and computer software with the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein. Whether a function is performed by hardware or computer software driving the hardware depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each specific application, but such implementations should not be considered beyond the scope of this application.
  • Embodiments of the present application can divide the transmitting end device or the receiving end device into functional modules according to the above method examples.
  • each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. middle.
  • the above integrated modules can be implemented in the form of hardware or software function modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. In actual implementation, there may be other division methods. The following is an example of dividing each functional module according to each function.
  • FIG. 6 is a schematic block diagram of a communication device provided by an embodiment of the present application.
  • the communication device 600 shown in FIG. 6 includes a transceiver unit 610 and a processing unit 620.
  • the transceiver unit 610 can communicate with the outside, and the processing unit 620 is used for data processing.
  • the transceiver unit 610 may also be called a communication interface or a communication unit.
  • the transceiver unit 610 may include a sending unit and a receiving unit.
  • the sending unit is used to perform the sending operation in the above method embodiment.
  • the receiving unit is used to perform the receiving operation in the above method embodiment.
  • the communication device 600 may include a sending unit but not a receiving unit.
  • the communication device 600 may include a receiving unit instead of a transmitting unit. Specifically, it may depend on whether the above solution executed by the communication device 600 includes a sending action and a receiving action.
  • the communication device 600 may also include a storage unit, which may be used to store instructions and/or data, and the processing unit 620 may read the instructions and/or data in the storage unit.
  • a storage unit which may be used to store instructions and/or data
  • the processing unit 620 may read the instructions and/or data in the storage unit.
  • the communication device 600 can be used to perform the actions performed by the data processing device #1 in the above method embodiment.
  • Data processing device #1 may be a functional network element in the network, or may be a chip or circuit in terminal equipment, network equipment, core network equipment, or operation, maintenance and management equipment, or may be capable of implementing all or part of terminal equipment and network equipment.
  • core network equipment or logical modules or software for operation, maintenance and management equipment functions this application does not limit this.
  • the communication device 600 can be data processing device #1, the transceiver unit 610 is used to perform the receiving or sending operation of the data processing device #1 in the above method embodiment, and the processing unit 620 is used to perform the above method implementation.
  • the communication device 600 may be a device including the data processing device #1.
  • the communication device 600 may be a component configured in the data processing device #1, for example, a chip in the data processing device #1.
  • the transceiver unit 610 may be an interface circuit, a pin, or the like.
  • the interface circuit may include an input circuit and an output circuit
  • the processing unit 620 may include a processing circuit.
  • the transceiver unit 610 is used to obtain a first data message, the first data message includes first transmission path information, and the first transmission path information includes data processing device #1 and data processing device # 2 information, the processing unit 620 is configured to determine the data processing device #2 based on the first transmission path information, and the transceiver unit 610 is configured to send a second data message to the data processing device #2, where the second data message includes the Two transmission path information, and the data payload in the second data packet is processed based on the data payload in the first data packet.
  • the second transmission path information does not include information about the data processing device #1.
  • the first transmission path information includes identification information of the first device and the second device, or the first transmission path information includes address information of the first device and the second device.
  • the first data packet and the second data packet further include data service information and/or statistical mode information.
  • the statistical mode information is used to indicate the statistical mode of the statistical information.
  • the statistical information includes the data packet. The number of packets or the number of bytes of data packets.
  • the transceiver unit is also used to send statistical information to the data orchestration device, where the statistical information includes information on the number of data packets or information on the number of bytes of the data packet.
  • the statistical information is obtained based on granular statistics of transmission path information or data service information of data packets.
  • the data service information is any of the following: the identifier of the federated learning service, the identifier of the distributed learning service, or the identifier of the data aggregation service.
  • the communication device 600 may be used to perform the actions performed by the data processing device #0 in the above method embodiment.
  • Data processing device #0 may be a functional network element in the network, or may be a chip or circuit in terminal equipment, network equipment, core network equipment, or operation, maintenance and management equipment, or may be capable of implementing all or part of terminal equipment and network equipment.
  • core network equipment or logical modules or software for operation, maintenance and management equipment functions this application does not limit this.
  • the communication device 600 can be a data processing device #0
  • the transceiver unit 610 is used to perform the receiving or sending operation of the data processing device #0 in the above method embodiment
  • the processing unit 620 is used to perform the above method implementation.
  • the communication device 600 may be a device including the data processing device #0.
  • the communication device 600 may be a component configured in the data processing device #0, for example, a chip in the data processing device #0.
  • the transceiver unit 610 may be an interface circuit, a pin, or the like.
  • the interface circuit may include an input circuit and an output circuit
  • the processing unit 620 may include a processing circuit.
  • the transceiver unit 610 is used to obtain service data, and the processing unit 620 is used to determine third transmission path information based on data service information.
  • the third transmission path information includes information of data processing device #1, Data processing device #1 is the processing node of the third data message.
  • the transceiver unit 610 is also used to send the third data message to data processing device #1.
  • the third data message includes the third transmission path information and the service. The data payload corresponding to the data.
  • the third transmission path information includes identification information or address information of the second device.
  • the transceiver unit 610 is also configured to receive correspondence information from the data arrangement device, the correspondence information indicating the correspondence between the data service information and the transmission path information, and the processing unit 620 is configured to The service information and the correspondence information determine the third transmission path information.
  • the data service information includes first data service information.
  • the first data service information corresponds to N pieces of transmission path information.
  • the N pieces of transmission path information include third transmission path information. N is greater than or equal to 1. integer.
  • the correspondence relationship indicated by the correspondence relationship information includes the correspondence relationship between the first data service information and N pieces of transmission path information, where N is an integer greater than 1, and the transceiver unit 610 is also used to transmit data to the N pieces of information.
  • Data processing device #1 sends N data packets, wherein each data processing device #1 is associated with one data packet, and one data packet includes one transmission path information among the N transmission path information.
  • the N transmission path information includes information about parallel data processing devices.
  • the parallel data processing devices are processing nodes at the same level of the data packet, and N is an integer greater than 1.
  • the correspondence relationship indicated by the correspondence relationship information includes the correspondence relationship between the first data service information and the third transmission path information.
  • N is an integer greater than 1.
  • the third transmission path information includes information about data processing devices arranged in order, and the data processing device arranged first processes the data packets in a higher order.
  • the transceiver unit is also used to receive configuration information from the data orchestration device, and the configuration information is used to configure at least one of the following: the statistical mode of the data packet, the statistical period of the data packet, the transmission Validity time of path information.
  • the transceiver unit 610 is also configured to receive update information from the data orchestration device, where the update information is used to update the transmission path information corresponding to the data service information.
  • the transceiver unit 610 is also configured to receive read information from the data arrangement device, where the read information is used to read the transmission path information corresponding to the data service information.
  • the transceiver unit 610 is also configured to receive deletion information from the data arrangement device, where the deletion information is used to delete the transmission path information corresponding to the data service information.
  • the third data packet also includes data service information and/or statistical mode information.
  • the statistical mode information is used to indicate the statistical mode of statistical information.
  • the statistical information includes quantity information of data packets or The number of bytes in the data packet.
  • the transceiver unit 610 is also configured to send statistical information to the data orchestration device, where the statistical information includes information on the number of data packets or information on the number of bytes of data packets.
  • the statistical information is obtained based on granular statistics of transmission path information or data service information of data packets.
  • the data service information is any of the following: the identifier of the federated learning service, the identifier of the distributed learning service, or the identifier of the data aggregation service.
  • the communication device 600 shown in Figure 6 can be used to perform the actions performed by the data orchestration device in the above method embodiment.
  • the communication device 600 can be a data orchestration device
  • the transceiver unit 610 is used to perform the receiving or sending operation of the data orchestration device in the above method embodiment
  • the processing unit 620 is used to perform the data orchestration in the above method embodiment.
  • the data orchestration device can be a functional network element in the network, or a chip or circuit in network equipment or core network equipment, or it can be logic that can realize all or part of the functions of network equipment or core network equipment. Module or software, this application does not limit this.
  • the communication device 600 may be a device including a data orchestration device.
  • the communication device 600 may be a component configured in the data orchestration device, for example, a chip in the data orchestration device.
  • the transceiver unit 610 may be an interface circuit, a pin, or the like.
  • the interface circuit may include an input circuit and an output circuit
  • the processing unit 620 may include a processing circuit.
  • the processing unit 620 is used to generate correspondence information, the correspondence information indicates the correspondence between the data service information and the transmission path information of the data message, and the transceiver unit is used to send the correspondence to the data processing device #0 information.
  • the transmission path information includes information about data processing device #1, which is a processing node for data packets.
  • the transmission path information includes identification information or address information of data processing device #1.
  • the data service information includes first data service information, and the first data service information corresponds to N pieces of transmission path information, where N is an integer greater than or equal to 1.
  • the correspondence relationship indicated by the correspondence relationship information includes the correspondence relationship between the first data service information and N pieces of transmission path information, where N is an integer greater than 1.
  • the N transmission path information includes information about parallel data processing devices.
  • the parallel data processing devices are processing nodes at the same level of the data packet, and N is an integer greater than 1.
  • the transceiver unit is also used to send N pieces of correspondence information to N data processing devices #0, where each data processing device #0 is associated with one piece of correspondence information, and the piece of correspondence information indicates The corresponding relationship between the first data service information and one of the N transmission path information, where N is an integer greater than 1.
  • each transmission path information in the N transmission path information includes information of data processing devices arranged in order, and the data processing device ranked first processes the data packets in the first order, and N is An integer greater than 1.
  • the transceiver unit 610 is also used to send configuration information to the data processing device #0.
  • the configuration information is used to configure at least one of the following: the statistical mode of the data packet, the statistical period of the data packet, The validity time of the transmission path information.
  • the transceiver unit 610 is also configured to send update information to the data processing device #0, where the update information is used to update the transmission path information corresponding to the data service information.
  • the transceiver unit 610 is also used to send read information to the data processing device #0, where the read information is used to read the transmission path information corresponding to the data service information.
  • the transceiver unit 610 is also configured to send deletion information to the data processing device #0, where the deletion information is used to delete the transmission path information corresponding to the data service information.
  • the transceiver unit 610 is also configured to receive statistical information from the data processing device #0, where the statistical information includes information on the number of data packets or information on the number of bytes of data packets.
  • the statistical information is obtained based on granular statistics of transmission path information or data service information.
  • the data service information is any of the following: the identifier of the federated learning service, the identifier of the distributed learning service, or the identifier of the data aggregation service.
  • an embodiment of the present application also provides a communication device 700.
  • the communication device 700 includes a processor 710.
  • the processor 710 is coupled to a memory 720.
  • the memory 720 is used to store computer programs or instructions and/or data.
  • the processor 710 is used to execute the computer programs or instructions and/or data stored in the memory 720. , so that the method in the above method embodiment is executed.
  • the communication device 700 includes one or more processors 710 .
  • the communication device 700 may further include a memory 720 .
  • the communication device 700 may include one or more memories 720 .
  • the memory 720 may be integrated with the processor 710 or provided separately.
  • the communication device 700 may also include a transceiver 730 and/or a communication interface, and the transceiver 730 and/or the communication interface are used for receiving and/or transmitting signals.
  • the processor 710 is used to control the transceiver 730 and/or the communication interface to receive and/or send signals.
  • the components in the transceiver 730 used to implement the receiving function can be regarded as receiving modules, and the components in the transceiver 730 used to implement the transmitting function can be regarded as the transmitting module, that is, the transceiver 730 includes a receiver and a transmitter.
  • a transceiver may also be called a transceiver, a transceiver module, or a transceiver circuit.
  • the receiver may also be called a receiver, receiving module, or receiving circuit.
  • a transmitter can sometimes be called a transmitter, transmitter, transmit module or transmit circuit.
  • the communication device 700 is used to implement the operations performed by the data processing device #0 in the above method embodiment.
  • the processor 710 is used to implement the operations (such as the operations of S210 and S220) performed internally by the data processing device #0 in the above method embodiment
  • the transceiver 730 is used to implement the operations performed by the data processing device #0 in the above method embodiment.
  • the receiving or sending operation performed (such as the operations of S201, S230, S231, S232, S233, S234, and S240).
  • the communication device 700 is used to implement the operations performed by the data processing device #1 in the above method embodiment.
  • the processor 710 is used to implement the operations (such as the operations of S310 and S320) performed internally by the data processing device #1 in the above method embodiment
  • the transceiver 730 is used to implement the operations performed by the data processing device #1 in the above method embodiment. 1
  • the receiving or sending operation performed (such as the operations of S230, S241, S330, and S340).
  • the communication device 700 is used to implement the operations performed by the data orchestration device in the above method embodiment.
  • the processor 710 is used to implement the operations performed internally by the data orchestration device in the above method embodiment
  • the transceiver 730 is used to implement the receiving or sending operations performed by the data orchestration device in the above method embodiment (for example, S201, S231, S232, S233, S234, S240, S241, S340, S341 operation).
  • an embodiment of the present application also provides a communication device 800.
  • the communication device 800 includes a logic circuit 810 and an input/output interface 820.
  • the logic circuit 810 may be a processing circuit in the communication device 800 .
  • the logic circuit 810 can be coupled to the storage unit and call instructions in the storage unit, so that the communication device 800 can implement the methods and functions of various embodiments of the present application.
  • the input/output interface 820 may be an input/output circuit in the communication device 800, which outputs information processed by the communication device 800, or inputs data or signaling information to be processed into the communication device 800 for processing.
  • the communication device 800 is used to implement the operations performed by the data processing device #0 in each of the above method embodiments.
  • the logic circuit 810 is used to implement processing-related operations performed by the data processing device #0 in the above method embodiment, such as the processing operations of the data processing device #0 in S210 and S220.
  • the input/output interface 820 is used to implement the sending and/or receiving related operations performed by the data processing device #0 in the above method embodiment, such as the data processing device # in S201, S230, S231, S232, S233, S234, and S240. 0 sending and receiving operations.
  • the operations performed by the logic circuit 810 please refer to the above description of the processing unit 620.
  • the operations performed by the input/output interface 820 please refer to the above description of the transceiver unit 610, which will not be described again here.
  • the communication device 800 is used to implement the operations performed by the data processing device #1 in each of the above method embodiments.
  • the logic circuit 810 is used to implement processing-related operations performed by the data processing device #1 in the above method embodiment, such as the processing operations of the data processing device #1 in S310 and S320.
  • the input/output interface 820 is used to implement the sending and/or receiving related operations performed by the data processing device #1 in the above method embodiment, such as the sending and receiving operations of the data processing device #1 in S230, S241, S330, and S340.
  • the operations performed by the logic circuit 810 please refer to the above description of the processing unit 620.
  • the operations performed by the input/output interface 820 please refer to the above description of the transceiver unit 610, which will not be described again here.
  • the communication device 800 is used to implement the operations performed by the data orchestration device in each of the above method embodiments.
  • the logic circuit 810 is used to implement the processing-related operations performed by the data orchestration device in the above method embodiment, such as the processing-related operations performed by the data orchestration device in the method embodiment, and the input/output interface 820 is used to implement The sending and/or receiving related operations performed by the data orchestration device in the above method embodiments, such as the sending and receiving operations of the data orchestration device in S201, S231, S232, S233, S234, S240, S241, S340, and S341.
  • the operations performed by the logic circuit 810 please refer to the above description of the processing unit 820.
  • the operations performed by the logic circuit 810 please refer to the above description of the processing unit 620.
  • the operations performed by the input/output interface 820 please refer to the above description of the transceiver unit 610, which will not be described again here.
  • the above communication device may be one or more chips.
  • the communication device can be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), or It can be a central processing unit (CPU), a network processor (NP), a digital signal processing circuit (DSP), or a microcontroller unit , MCU), it can also be a programmable logic device (PLD) or other integrated chip.
  • FPGA field programmable gate array
  • ASIC application specific integrated circuit
  • SoC system on chip
  • CPU central processing unit
  • NP network processor
  • DSP digital signal processing circuit
  • MCU microcontroller unit
  • PLD programmable logic device
  • each step of the above method can be completed by instructions in the form of hardware integrated logic circuits or software in the processor.
  • the steps of the methods disclosed in conjunction with the embodiments of the present application can be directly implemented by a hardware processor for execution, or can be executed by a combination of hardware and software modules in the processor.
  • the software module can be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other mature storage media in this field.
  • the storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.
  • the processor in the embodiment of the present application may be an integrated circuit chip with signal processing capabilities.
  • each step of the above method embodiment can be completed through an integrated logic circuit of hardware in the processor or instructions in the form of software.
  • the above-mentioned processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
  • DSP digital signal processor
  • ASIC application-specific integrated circuit
  • FPGA field programmable gate array
  • a general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.
  • the steps of the method disclosed in conjunction with the embodiments of the present application can be directly implemented by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor.
  • the software module can be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other mature storage media in this field.
  • the storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
  • non-volatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable programmable read-only memory (erasable PROM, EPROM), electrically removable memory. Erase electrically programmable read-only memory (EPROM, EEPROM) or flash memory. Volatile memory can be random access memory (RAM), which is used as an external cache.
  • RAM random access memory
  • RAM static random access memory
  • DRAM dynamic random access memory
  • SDRAM synchronous dynamic random access memory
  • double data rate SDRAM double data rate SDRAM
  • DDR SDRAM double data rate SDRAM
  • ESDRAM enhanced synchronous dynamic random access memory
  • SLDRAM synchronous link dynamic random access memory
  • direct rambus RAM direct rambus RAM
  • the present application also provides a computer-readable medium.
  • the computer-readable medium stores program code.
  • the program code When the program code is run on a computer, it causes the computer to execute the steps shown in the method embodiment. method.
  • the computer program when executed by a computer, the computer can implement the method executed by the data arrangement device in the above method embodiment, or the method executed by the data processing device.
  • Embodiments of the present application also provide a computer program product containing instructions.
  • the instructions When the instructions are executed by a computer, the computer implements the method executed by the data arrangement device in the above method embodiment, or the method executed by the data processing device.
  • An embodiment of the present application also provides a communication system, including a data orchestration device and a data processing device.
  • the computer program product includes one or more computer instructions.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.
  • the computer instructions may be stored in or transmitted from one computer-readable storage medium to another, e.g., the computer instructions may be transferred from a website, computer, server, or data center Transmission to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more available media integrated.
  • the available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVD)), or semiconductor media (e.g., solid state drives, SSD)) etc.
  • magnetic media e.g., floppy disks, hard disks, magnetic tapes
  • optical media e.g., high-density digital video discs (DVD)
  • DVD digital video discs
  • semiconductor media e.g., solid state drives, SSD
  • the data arrangement device and data processing device in each of the above device embodiments correspond to the data arrangement device and data processing device in the method embodiment, and the corresponding steps are executed by corresponding modules or units, for example, the communication unit (transceiver) executes the method implementation.
  • the communication unit transmits the method implementation.
  • other steps except sending and receiving may be executed by the processing unit (processor).
  • the processing unit processor
  • a component may be, but is not limited to, a process, a processor, an object, an executable file, a thread of execution, a program and/or a computer running on a processor.
  • applications running on the computing device and the computing device may be components.
  • One or more components can reside in a process and/or thread of execution and a component can be localized on one computer and/or distributed between two or more computers. Additionally, these components can execute from various computer-readable media having various data structures stored thereon.
  • a component may, for example, be based on a signal having one or more data packets (eg, data from two components interacting with another component, such as a local system, a distributed system, and/or a network, such as the Internet, which interacts with other systems via signals) Communicate through local and/or remote processes.
  • data packets eg, data from two components interacting with another component, such as a local system, a distributed system, and/or a network, such as the Internet, which interacts with other systems via signals
  • the disclosed systems, devices and methods can be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or can be integrated into another system, or some features can be ignored, or not implemented.
  • the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, and the indirect coupling or communication connection of the devices or units may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application can be integrated into one processing unit, each unit can exist physically alone, or two or more units can be integrated into one unit.
  • the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product.
  • the computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and other media that can store program code. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本申请实施例提供一种数据报文的传输方法、通信装置和通信系统。该方法包括：第一装置基于数据服务信息确定数据报文的传输路径信息，传输路径信息包括第二装置的信息，第一装置可以基于传输路径信息确定第二装置，向第二装置发送第一装置处理后的数据报文。或者第一装置基于获取的数据报文中的传输路径信息确定第二装置，并向第二装置发送第一装置处理后的该数据报文。本申请提供的方案能够在数据报文传输的过程中，实现对数据的处理，提高数据的使用效率。

Description

数据报文的传输方法、通信装置和通信系统 技术领域
本申请实施例涉及通信领域，并且，更具体地，涉及数据报文的传输方法、通信装置和通信系统。
背景技术
数据在通信网络中产生、流动并消费，随着网络规模、新技术、应用等的发展，网络中的数据越来越多，越来越重要。因此对数据的高效使用需要完整的服务架构，以往数据是以数据孤岛的形式存在的，即某个应用只使用自己的数据，无法使用其他应用的数据，也无法给其他应用使用自己获得的数据。数据服务即要打破数据孤岛，使得数据作为一种服务的形式为网络内部和外部各类应用所用，发挥其价值。
目前，两个网络节点之间的信息交互需要建立通信路径，该通信路径上的中间节点，只负责数据报文的转发，并不对其进行处理，在转发的过程中根据数据报文的报头中的目的地址进行路由转发。在数据服务过程中，收集、存储、转发、分析等数据的处理过程可在不同的网络节点，如何将数据在上述可对数据进行处理的网络节点之间传输是需要考虑的问题。
发明内容
本申请实施例提供一种数据报文的传输方法、通信装置和通信系统，能够在数据报文传输的过程中，实现对数据的处理，提高数据的使用效率。
第一方面，提供了一种数据报文的传输方法。该方法可以由第一装置执行，第一装置可以是网络中的功能网元，也可以是终端设备、网络设备、核心网设备或操作维护管理设备中的芯片或电路，也可以是能实现全部或部分终端设备、网络设备、核心网设备或操作维护管理设备功能的逻辑模块或软件，本申请对此不作限定。该方法包括：第一装置获取第一数据报文，该第一数据报文包括第一传输路径信息，该第一传输路径信息包括第一装置和第二装置的信息，第一装置基于该第一传输路径信息确定第二装置，向第二装置发送第二数据报文，该第二数据报文包括第二传输路径信息，且该第二数据报文中的数据载荷基于第一数据报文中的数据载荷处理得到。
在上述方案中，第一装置对数据报文中的数据载荷进行处理后，可以基于第一数据报文中的传输路径信息确定该数据报文的下一个处理节点，并将处理后的数据报文传输至下一个处理节点。也就是说，本方案在数据报文的传输过程中，实现了对数据报文的处理，能够满足通信感知计算融合趋势下对数据的分布式处理的需求并提高数据的使用效率。
结合第一方面，在第一方面的某些实现方式中，该第二传输路径信息中不包括所述第一装置的信息。
基于上述方案，第一装置将第一数据报文处理后，可以在第二数据报文的传输路径信 息中将自身的信息删掉，能够节约通信资源开销。
结合第一方面，在第一方面的某些实现方式中，第一传输路径信息包括第一装置和第二装置的标识信息，或者第一传输路径信息包括第一装置和第二装置的地址信息。
结合第一方面，在第一方面的某些实现方式中，第一数据报文和第二数据报文还包括数据服务信息和/或统计模式信息，该统计模式信息用于指示统计信息的统计方式，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
基于上述方案，数据报文的处理节点可以通过报文中指示的统计模式信息确定统计信息的统计方式，从而按照报文中的指示统计上报。结合第一方面，在第一方面的某些实现方式中，第一装置向第三装置发送统计信息，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
基于上述方案，可以使得第三装置知晓流经第一装置的数据报文/字节数量的情况，便于第三装置统筹后续是否继续给第一装置分配数据报文让其处理。
结合第一方面，在第一方面的某些实现方式中，该统计信息是以数据报文的传输路径信息或数据服务信息为粒度统计得到的。
基于上述方案，假设统计信息是以传输路径信息为粒度统计得到，则第三装置可以确定流经第一装置的每条传输路径上的数据报文/字节数量的情况，假设统计信息是以数据服务信息为粒度统计得到，则第三装置可以确定第一装置处理的不同数据服务的数据报文/字节数量的情况，为第三装置后续统筹分配提供参考。
第二方面，提供了一种数据报文的传输方法。该方法可以由第一装置执行，第一装置可以是终端设备、网络设备、核心网设备或操作维护管理设备中的芯片或电路，也可以是能实现全部或部分终端设备、网络设备、核心网设备或操作维护管理设备等功能的逻辑模块或软件，本申请对此不作限定。该方法包括：第一装置获取业务数据，基于数据服务信息确定第三传输路径信息，该第三传输路径信息包括第二装置的信息，第二装置为第三数据报文的处理节点，向第二装置发送第三数据报文，该第三数据报文包括该第三传输路径信息和该业务数据对应的数据载荷。
在上述方案中，第一装置获取业务数据后，可以基于数据服务信息确定第三传输路径信息，继而确定业务数据的下一个处理节点即第二装置，并将处理后的业务数据和第三传输路径信息封装为第三数据报文传输至下一个处理节点。后续第二装置可以基于该第三传输路径信息确定第三数据报文在第二装置后的下一个处理节点。也就是说，本方案使得数据报文在传输的过程中，可以实现其他节点对数据报文的处理，能够满足通信感知计算融合趋势下对数据的分布式处理的需求并提高数据的使用效率。
结合第二方面，在第二方面的某些实现方式中，第三传输路径信息包括第二装置的标识信息或地址信息。
结合第二方面，在第二方面的某些实现方式中，第一装置接收来自第三装置的对应关系信息，该对应关系信息指示该数据服务信息和传输路径信息的对应关系，第一装置基于数据服务信息和该对应关系信息确定第三传输路径信息。
基于上述方案，第三装置将数据服务信息和该传输路径信息的对应关系配置给第一装置，第一装置可以根据数据服务信息确定第三传输路径信息，并且可以基于第三传输路径信息确定下一个处理节点，对于第一装置而言，确定下一个处理节点和确定数据报文的下 一跳节点(物理路由)可以解耦，兼容性更强。
结合第二方面，在第二方面的某些实现方式中，该数据服务信息包括第一数据服务信息，第一数据服务信息对应N个传输路径信息，N个传输路径信息包括第三传输路径信息，N为大于或等于1的整数。
结合第二方面，在第二方面的某些实现方式中，该对应关系信息指示的对应关系包括该第一数据服务信息和N个传输路径信息的对应关系，N为大于1的整数，第一装置向N个第二装置发送N个数据报文，其中，每个第二装置关联一个数据报文，一个数据报文包括该N个传输路径信息中的一个传输路径信息。
基于上述方案，当N个数据报文中的数据载荷相同时，即为数据报文多播场景，当N个数据报文中有两个数据报文的数据载荷不同时，即为数据报文分发场景。也就是说该方案可以实现数据报文的多播和分发，即可以实现数据报文的传输路径的灵活拓扑。
结合第二方面，在第二方面的某些实现方式中，该N个传输路径信息包括并列的数据处理装置的信息，并列的数据处理装置为数据报文的同一级处理节点，N为大于1的整数。
基于上述方案，当数据服务信息对应多个(2个及以上)传输路径信息时，可通过传输路径信息的结构确定并列的处理节点，从而可以将数据报文多播或分发至并列的处理节点，实现数据报文的传输路径的灵活拓扑。
结合第二方面，在第二方面的某些实现方式中，该对应关系信息指示的对应关系包括第一数据服务信息和第三传输路径信息的对应关系，N为大于1的整数。
基于上述方案，该数据服务信息对应N个传输路径信息，关联第一装置的是其中的第三传输路径信息，也就是说N个传输路径信息对应不同的第一装置，该方案可以实现数据报文的汇聚，即数据报文的初始处理节点不同，最终处理节点相同，即可以实现数据报文的传输路径的灵活拓扑。
结合第二方面，在第二方面的某些实现方式中，该第三传输路径信息包括按序排列的数据处理装置的信息，排列靠前的数据处理装置处理数据报文的顺序靠前。
基于上述方案，该数据服务信息对应N个传输路径信息，N为大于1的整数，关联第一装置的是其中的第三传输路径信息，也就是说N个传输路径信息对应不同的第一装置，该方案可以实现数据报文的汇聚，即可以实现数据报文的传输路径的灵活拓扑。并且可通过传输路径信息的结构确定按序排列的处理节点，从而可以将数据报文按序发送至处理节点进行处理。
结合第二方面，在第二方面的某些实现方式中，第一装置接收来自第三装置的配置信息，该配置信息用于配置以下至少一项：数据报文的统计模式、数据报文的统计周期、该传输路径信息的有效时间。
基于上述方案，第一装置可以根据配置上报统计信息，并且可以在传输路径信息的有效时间内按照该传输路径信息传输数据报文。
结合第二方面，在第二方面的某些实现方式中，第一装置向第三装置发送确认信息，该确认信息用于对该配置信息进行确认。
基于上述方案，第三装置可以通过确认信息知晓已经完成了配置，避免再次发送配置信息，造成通信资源的浪费。
结合第二方面，在第二方面的某些实现方式中，第一装置接收来自第三装置的更新信 息，该更新信息用于更新该数据服务信息对应的传输路径信息。
基于上述方案，第一装置后续可以根据更新后的传输路径信息传输数据报文。
结合第二方面，在第二方面的某些实现方式中，第一装置向第三装置发送确认信息，该确认信息用于确认第一装置完成了传输路径信息的更新。
基于上述方案，第三装置可以通过确认信息知晓传输路径信息已经更新，避免再次发送更新信息，造成通信资源的浪费。
结合第二方面，在第二方面的某些实现方式中，第一装置接收来自第三装置的读取信息，该读取信息用于读取该数据服务信息对应的传输路径信息。
基于上述方案，在调试或者故障排除阶段可以通过读取信息读取传输路径信息，以便确认某一数据服务信息对应的传输路径信息是否准确，提高系统的性能。
结合第二方面，在第二方面的某些实现方式中，第一装置向第三装置发送读取响应信息，该读取响应信息可以包括该数据服务信息对应的传输路径信息。
基于上述方案，在调试或者故障排除阶段可以通过读取响应信息中的传输路径信息，确认某一数据服务信息对应的传输路径信息是否准确，便于第三装置排除故障，提高系统的性能。
结合第二方面，在第二方面的某些实现方式中，第一装置接收来自第三装置的删除信息，该删除信息用于删除该数据服务信息对应的传输路径信息。
基于上述方案，可以在某数据服务结束后，删除该数据服务信息对应的传输路径信息，节约第一装置的存储资源。
结合第二方面，在第二方面的某些实现方式中，第一装置向第三装置发送确认信息，该确认信息用于确认第一装置完成了传输路径信息的删除。
基于上述方案，第三装置可根据确认信息知晓第一装置已完成删除操作，避免再次发送删除指令，浪费传输资源。
结合第二方面，在第二方面的某些实现方式中，该第三数据报文还包括数据服务信息和/或统计模式信息，该统计模式信息用于指示统计信息的统计模式，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
基于上述方案，数据报文的处理节点可以通过报文中指示的统计模式信息确定统计信息的统计方式，从而按照报文中的指示统计上报。
结合第二方面，在第二方面的某些实现方式中，第一装置向第三装置发送统计信息，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
基于上述方案，可以使得第三装置知晓流经第一装置的数据报文/字节数量的情况，便于第三装置统筹后续是否继续给第一装置分配数据报文让其处理。
结合第二方面，在第二方面的某些实现方式中，该统计信息是以数据报文的传输路径信息或数据服务信息为粒度统计得到的。
基于上述方案，假设统计信息是以传输路径信息为粒度统计得到，则第三装置可以确定流经第一装置的每条传输路径上的数据报文/字节数量的情况，假设统计信息是以数据服务信息为粒度统计得到，则第三装置可以确定第一装置处理的不同数据服务的数据报文/字节数量的情况，为第三装置后续统筹分配提供参考。
结合第二方面，在第二方面的某些实现方式中，数据服务信息为以下任一项：联邦学 习服务的标识，分布式学习服务的标识，或数据汇聚服务的标识。
第三方面，提供了一种数据报文的传输方法。该方法可以由第三装置执行，第三装置可以是网络中的功能网元，也可以是网络设备、核心网设备中的芯片或电路，也可以是能实现全部或部分网络设备、核心网设备功能的逻辑模块或软件，本申请对此不作限定。该方法包括：第三装置生成对应关系信息，对应关系信息指示数据服务信息和数据报文的传输路径信息的对应关系，向第一装置发送对应关系信息。
基于上述方案，第三装置将数据服务信息和该传输路径信息的对应关系配置给第一装置，使得第一装置可以根据该对应关系确定某数据服务信息对应的传输路径信息，基于传输路径信息传输数据报文。该方案中，第三装置可以动态构建和维护数据报文的传输路径信息，使得数据报文的传输以及处理过程更为灵活。
结合第三方面，在第三方面的某些实现方式中，上述传输路径信息包括第二装置的信息，所述第二装置为数据报文的处理节点。
基于上述方案，传输路径信息包括处理节点的信息，表示数据报文在随路处理，即本方案使得数据报文在传输的过程中，可以实现处理节点对数据报文的处理，能够满足通信感知计算融合趋势下对数据的分布式处理的需求并提高数据的使用效率。
结合第三方面，在第三方面的某些实现方式中，该数据服务信息包括第一数据服务信息，第一数据服务信息对应N个传输路径信息，N为大于或等于1的整数。
结合第三方面，在第三方面的某些实现方式中，传输路径信息包括第二装置的标识信息或第二装置的地址信息。
结合第三方面，在第三方面的某些实现方式中，该对应关系信息指示的对应关系包括该第一数据服务信息和N个传输路径信息的对应关系，N为大于1的整数。
基于上述方案，一个数据服务信息可以对应以第一装置为初始处理节点的多个传输路径，可以实现数据报文的多播和分发，即可以实现数据报文的传输路径的灵活拓扑。
结合第三方面，在第三方面的某些实现方式中，该N个传输路径信息包括并列的数据处理装置的信息，并列的数据处理装置为数据报文的同一级处理节点，N为大于1的整数。
基于上述方案，当数据服务信息对应多个(2个及以上)传输路径信息时，可通过传输路径信息的结构确定并列的处理节点，从而可以将数据报文多播或分发至并列的处理节点，实现数据报文的传输路径的灵活拓扑。
结合第三方面，在第三方面的某些实现方式中，第三装置向N个第一装置发送N个对应关系信息，其中，每个第一装置关联一个对应关系信息，该一个对应关系信息指示的对应关系包括该第一数据服务信息和该N个传输路径信息中的一个传输路径信息的对应关系，N为大于1的整数。
基于上述方案，一个数据服务信息可以对应以多个第一装置为初始处理节点的多个传输路径，可以实现数据报文的汇聚，即可以实现数据报文的传输路径的灵活拓扑。
结合第三方面，在第三方面的某些实现方式中，该N个传输路径信息中的每个传输路径信息包括按序排列的数据处理装置的信息，排列靠前的数据处理装置处理数据报文的顺序靠前。
基于上述方案，该数据服务信息对应N个传输路径信息，关联第一装置的是其中的一个传输路径信息，该方案可以实现数据报文的汇聚，即可以实现数据报文的传输路径的灵 活拓扑。并且可通过传输路径信息的结构确定按序排列的处理节点，从而可以将数据报文按序发送至处理节点进行处理。
结合第三方面，在第三方面的某些实现方式中，第三装置向第一装置发送配置信息，该配置信息用于配置以下至少一项：数据报文的统计模式、数据报文的统计周期、该传输路径信息的有效时间。
结合第三方面，在第三方面的某些实现方式中，第三装置接收来自第一装置的确认信息，该确认信息用于对该配置信息进行确认。
结合第三方面，在第三方面的某些实现方式中，第三装置向第一装置发送更新信息，该更新信息用于更新该数据服务信息对应的传输路径信息。
结合第三方面，在第三方面的某些实现方式中，第三装置接收来自第一装置的确认信息，该确认信息用于确认第一装置完成了传输路径信息的更新。
结合第三方面，在第三方面的某些实现方式中，第三装置向第一装置发送读取信息，该读取信息用于读取该数据服务信息对应的传输路径信息。
结合第三方面，在第三方面的某些实现方式中，第三装置接收来自第一装置的读取响应信息，该读取响应信息可以包括该数据服务信息对应的传输路径信息。
结合第三方面，在第三方面的某些实现方式中，第三装置向第一装置发送删除信息，该删除信息用于删除该数据服务信息对应的传输路径信息。
结合第三方面，在第三方面的某些实现方式中，第三装置接收来自第一装置的确认信息，该确认信息用于确认第一装置完成了传输路径信息的删除。
结合第三方面，在第三方面的某些实现方式中，第三装置接收来自第一装置的统计信息，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
结合第三方面，在第三方面的某些实现方式中，该统计信息是以传输路径信息或数据服务信息为粒度统计得到的。
结合第三方面，在第三方面的某些实现方式中，数据服务信息为以下任一项：联邦学习服务的标识，分布式学习服务的标识，或数据汇聚服务的标识。
上述第三方面未描述有益效果的实现方式的有益效果可以参考第二方面对应实现方式中有益效果的描述，此处不再赘述。
第四方面，提供了一种数据报文的传输方法。该方法可以应用于通信系统，该通信系统包括第一装置和第三装置。第一装置可以是网络中的功能网元，也可以是终端设备、网络设备、核心网设备或操作维护管理设备中的芯片或电路，也可以是能实现全部或部分终端设备、网络设备、核心网设备或操作维护管理设备功能的逻辑模块或软件，本申请对此不作限定。第三装置可以是网络中的功能网元，也可以是网络设备、核心网设备中的芯片或电路，也可以是能实现全部或部分网络设备、核心网设备功能的逻辑模块或软件，本申请对此不作限定。该方法包括：第三装置生成对应关系信息，对应关系信息指示数据服务信息和数据报文的传输路径信息的对应关系，向第一装置发送对应关系信息；第一装置接收该对应关系信息。
结合第四方面，在第四方面的某些实现方式中，方法还包括：第一装置获取业务数据，基于数据服务信息以及该对应关系确定第三传输路径信息，该第三传输路径信息包括第二装置的信息，第二装置为第三数据报文的处理节点，向第二装置发送该第三数据报文，该 第三数据报文包括第三传输路径信息和该业务数据对应的数据载荷。
基于上述方案，在通信系统中，第三装置将数据服务信息和该传输路径信息的对应关系配置给第一装置，使得第一装置可以根据该对应关系确定某数据服务信息对应的传输路径信息，并基于传输路径信息传输数据报文。该方案中，第三装置可以动态构建和维护数据报文的传输路径信息，使得数据报文的传输过程更为灵活。第一装置可以基于传输路径信息确定数据报文的下一个处理节点，第一装置的处理复杂度较低。
结合第四方面，在第四方面的某些实现方式中，第三传输路径信息包括第二装置的标识信息或地址信息。
结合第四方面，在第四方面的某些实现方式中，该数据服务信息包括第一数据服务信息，第一数据服务信息对应N个传输路径信息，N个传输路径信息包括第三传输路径信息，N为大于或等于1的整数。
结合第四方面，在第四方面的某些实现方式中，对应关系信息指示的对应关系包括第一数据服务信息和该N个传输路径信息的对应关系，N为大于1的整数，所一装置获取业务数据，基于第一数据服务信息和该对应关系信息确定N个第二装置，第一装置向N个第二装置发送N个数据报文，其中，每个第二装置关联一个数据报文，一个数据报文包括该N个传输路径信息中的一个传输路径信息。
结合第四方面，在第四方面的某些实现方式中，该N个传输路径信息包括并列的数据处理装置的信息，并列的数据处理装置为数据报文的同一级处理节点，N为大于1的整数。
结合第四方面，在第四方面的某些实现方式中，第三装置向N个第一装置发送N个对应关系信息，其中每个第一装置关联一个对应关系信息，一个对应关系信息指示该第一数据服务信息和该N个传输路径信息中的一个传输路径信息的对应关系，N为大于1的整数。
结合第四方面，在第四方面的某些实现方式中，N个传输路径信息中的每个传输路径信息包括按序排列的数据处理装置的信息，排列靠前的数据处理装置处理数据报文的顺序靠前，N为大于1的整数。
结合第四方面，在第四方面的某些实现方式中，第三装置发送配置信息，该配置信息用于配置以下至少一项：数据报文的统计模式、数据报文的统计周期、该传输路径信息的有效时间，第一装置接收该配置信息。
结合第四方面，在第四方面的某些实现方式中，第一装置发送确认信息，该确认信息用于对该配置信息进行确认，第三装置接收该确认信息。
结合第四方面，在第四方面的某些实现方式中，第三装置发送更新信息，该更新信息用于更新该数据服务信息对应的传输路径信息，第一装置接收该更新信息。
结合第四方面，在第四方面的某些实现方式中，第一装置发送确认信息，该确认信息用于确认第一装置完成了传输路径信息的更新，第三装置接收该确认信息。
结合第四方面，在第四方面的某些实现方式中，第三装置发送读取信息，该读取信息用于读取该数据服务信息对应的传输路径信息，第一装置接收该读取信息。
结合第四方面，在第四方面的某些实现方式中，第一装置发送读取响应信息，该读取响应信息可以包括该数据服务信息对应的传输路径信息，第三装置接收该读取响应信息。
结合第四方面，在第四方面的某些实现方式中，第三装置发送删除信息，该删除信息 用于删除该数据服务信息对应的传输路径信息，第一装置接收该删除信息。
结合第四方面，在第四方面的某些实现方式中，第一装置发送确认信息，该确认信息用于确认第一装置完成了传输路径信息的删除，第三装置接收该确认信息。
结合第四方面，在第四方面的某些实现方式中，该第三数据报文还包括数据服务信息和/或统计模式信息，该统计模式信息用于指示统计信息的统计模式，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
结合第四方面，在第四方面的某些实现方式中，第一装置发送统计信息，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息，第三装置接收该统计信息。
结合第四方面，在第四方面的某些实现方式中，该统计信息是以数据报文的传输路径信息或数据服务信息为粒度统计得到的。
上述第四方面未描述有益效果的实现方式的有益效果可以参考第二/三方面对应实现方式中有益效果的描述，此处不再赘述。
结合第四方面，在第四方面的某些实现方式中，数据服务信息为以下任一项：联邦学习服务的标识，分布式学习服务的标识，或数据汇聚服务的标识。
第五方面，提供了一种通信装置。该通信装置是第一装置，第一装置可以是网络中的功能网元，也可以是终端设备、网络设备、核心网设备或操作维护管理设备中的芯片或电路，也可以是能实现全部或部分终端设备、网络设备、核心网设备或操作维护管理设备功能的逻辑模块或软件，本申请对此不作限定。第一装置包括收发单元和处理单元：该收发单元用于获取第一数据报文，该第一数据报文包括第一传输路径信息，第一传输路径信息包括第一装置和第二装置的信息，处理单元用于基于该第一传输路径信息确定第二装置，该收发单元用于向第二装置发送第二数据报文，该第二数据报文包括第二传输路径信息，且该第二数据报文中的数据载荷基于第一数据报文中的数据载荷处理得到。
结合第五方面，在第五方面的某些实现方式中，上述第二传输路径信息中不包括所述第一装置的信息。
结合第五方面，在第五方面的某些实现方式中，第一传输路径信息包括第一装置和第二装置的标识信息，或者第一传输路径信息包括第一装置和第二装置的地址信息。
结合第五方面，在第五方面的某些实现方式中，第一数据报文和第二数据报文还包括数据服务信息和/或统计模式信息，该统计模式信息用于指示统计信息的统计模式，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
结合第五方面，在第五方面的某些实现方式中，该收发单元还用于向第三装置发送统计信息，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
结合第五方面，在第五方面的某些实现方式中，该统计信息是以数据报文的传输路径信息或数据服务信息为粒度统计得到的。
第六方面，提供了一种通信装置。该通信装置是第一装置，第一装置可以是终端设备、网络设备、核心网设备或操作维护管理设备中的芯片或电路，也可以是能实现全部或部分终端设备、网络设备、核心网设备或操作维护管理设备等功能的逻辑模块或软件，本申请对此不作限定。第一装置包括收发单元和处理单元：该收发单元用于获取业务数据，该处理单元用于基于数据服务信息确定第三传输路径信息，该第三传输路径信息包括第二装置的信息，第二装置为第三数据报文的处理节点，该收发单元还用于向第二装置发送第三数 据报文，该第三数据报文包括第三传输路径信息和该业务数据对应的数据载荷。
结合第六方面，在第六方面的某些实现方式中，第三传输路径信息包括第二装置的标识信息或地址信息。
结合第六方面，在第六方面的某些实现方式中，该收发单元还用于接收来自第三装置的对应关系信息，该对应关系信息指示该数据服务信息和传输路径信息的对应关系，该处理单元基于数据服务信息和该对应关系信息确定第三传输路径信息。
结合第六方面，在第六方面的某些实现方式中，该数据服务信息包括第一数据服务信息，第一数据服务信息对应N个传输路径信息，N个传输路径信息包括第三传输路径信息，N为大于或等于1的整数。
结合第六方面，在第六方面的某些实现方式中，该对应关系信息指示的对应关系包括该第一数据服务信息和N个传输路径信息的对应关系，N为大于1的整数，该收发单元还用于向N个第二装置发送N个数据报文，其中，每个第二装置关联一个数据报文，一个数据报文包括该N个传输路径信息中的一个传输路径信息。
结合第六方面，在第六方面的某些实现方式中，该N个传输路径信息包括并列的数据处理装置的信息，并列的数据处理装置为数据报文的同一级处理节点，N为大于1的整数。
结合第六方面，在第六方面的某些实现方式中，该对应关系信息指示的对应关系包括第一数据服务信息和第三传输路径信息的对应关系，该实现方式中N为大于1的整数。
结合第六方面，在第六方面的某些实现方式中，该第三传输路径信息包括按序排列的数据处理装置的信息，排列靠前的数据处理装置处理数据报文的顺序靠前。
结合第六方面，在第六方面的某些实现方式中，该收发单元还用于接收来自第三装置的配置信息，该配置信息用于配置以下至少一项：数据报文的统计模式、数据报文的统计周期、该传输路径信息的有效时间。
结合第六方面，在第六方面的某些实现方式中，该收发单元还用于向第三装置发送确认信息，该确认信息用于对该配置信息进行确认。
结合第六方面，在第六方面的某些实现方式中，该收发单元还用于接收来自第三装置的更新信息，该更新信息用于更新该数据服务信息对应的传输路径信息。
结合第六方面，在第六方面的某些实现方式中，该收发单元还用于向第三装置发送确认信息，该确认信息用于确认第一装置完成了传输路径信息的更新。
结合第六方面，在第六方面的某些实现方式中，该收发单元还用于接收来自第三装置的读取信息，该读取信息用于读取该数据服务信息对应的传输路径信息。
结合第六方面，在第六方面的某些实现方式中，该收发单元还用于向第三装置发送读取响应信息，该读取响应信息可以包括该数据服务信息对应的传输路径信息。
结合第六方面，在第六方面的某些实现方式中，该收发单元还用于接收来自第三装置的删除信息，该删除信息用于删除该数据服务信息对应的传输路径信息。
结合第六方面，在第六方面的某些实现方式中，该收发单元还用于向第三装置发送确认信息，该确认信息用于确认第一装置完成了传输路径信息的删除。
结合第六方面，在第六方面的某些实现方式中，该第三数据报文还包括数据服务信息和/或统计模式信息，该统计模式信息用于指示统计信息的统计模式，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
结合第六方面，在第六方面的某些实现方式中，该收发单元还用于向第三装置发送统计信息，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
结合第六方面，在第六方面的某些实现方式中，该统计信息是以数据报文的传输路径信息或数据服务信息为粒度统计得到的。结合第六方面，在第六方面的某些实现方式中，数据服务信息为以下任一项：联邦学习服务的标识，分布式学习服务的标识，或数据汇聚服务的标识。
第七方面，提供了一种通信装置。该通信装置是第三装置，第三装置可以是网络中的功能网元，也可以是网络设备、核心网设备中的芯片或电路，也可以是能实现全部或部分网络设备、核心网设备功能的逻辑模块或软件，本申请对此不作限定。第三装置包括处理单元和收发单元：处理单元用于生成对应关系信息，对应关系信息指示数据服务信息和数据报文的传输路径信息的对应关系，收发单元用于向第一装置发送对应关系信息。
结合第七方面，在第七方面的某些实现方式中，该传输路径信息包括第二装置的信息，所述第二装置为数据报文的处理节点。
结合第七方面，在第七方面的某些实现方式中，传输路径信息包括第二装置的标识信息或第二装置的地址信息。
结合第七方面，在第七方面的某些实现方式中，该数据服务信息包括第一数据服务信息，第一数据服务信息对应N个传输路径信息，N为大于或等于1的整数。
结合第七方面，在第七方面的某些实现方式中，该对应关系信息指示的对应关系包括该第一数据服务信息和N个传输路径信息的对应关系，N为大于1的整数。
结合第七方面，在第七方面的某些实现方式中，该N个传输路径信息包括并列的数据处理装置的信息，并列的数据处理装置为数据报文的同一级处理节点，N为大于1的整数。
结合第七方面，在第七方面的某些实现方式中，该收发单元还用于向N个第一装置发送N个对应关系信息，其中，每个第一装置关联一个对应关系信息，该一个对应关系信息指示该第一数据服务信息和该N个传输路径信息中的一个传输路径信息的对应关系，N为大于1的整数。
结合第七方面，在第七方面的某些实现方式中，该N个传输路径信息中的每个传输路径信息包括按序排列的数据处理装置的信息，排列靠前的数据处理装置处理数据报文的顺序靠前，N为大于1的整数。
结合第七方面，在第七方面的某些实现方式中，该收发单元还用于向第一装置发送配置信息，该配置信息用于配置以下至少一项：数据报文的统计模式、数据报文的统计周期、该传输路径信息的有效时间。
结合第七方面，在第七方面的某些实现方式中，该收发单元还用于接收来自第一装置的确认信息，该确认信息用于对该配置信息进行确认。
结合第七方面，在第七方面的某些实现方式中，该收发单元还用于向第一装置发送更新信息，该更新信息用于更新该数据服务信息对应的传输路径信息。
结合第七方面，在第七方面的某些实现方式中，该收发单元还用于接收来自第一装置的确认信息，该确认信息用于确认第一装置完成了传输路径信息的更新。
结合第七方面，在第七方面的某些实现方式中，该收发单元还用于向第一装置发送读取信息，该读取信息用于读取该数据服务信息对应的传输路径信息。
结合第七方面，在第七方面的某些实现方式中，该收发单元还用于接收来自第一装置的读取响应信息，该读取响应信息可以包括该数据服务信息对应的传输路径信息。
结合第七方面，在第七方面的某些实现方式中，该收发单元还用于向第一装置发送删除信息，该删除信息用于删除该数据服务信息对应的传输路径信息。
结合第七方面，在第七方面的某些实现方式中，该收发单元还用于接收来自第一装置的确认信息，该确认信息用于确认第一装置完成了传输路径信息的删除。
结合第七方面，在第七方面的某些实现方式中，该收发单元还用于接收来自第一装置的统计信息，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
结合第七方面，在第七方面的某些实现方式中，该统计信息是以传输路径信息或数据服务信息为粒度统计得到的。
结合第七方面，在第七方面的某些实现方式中，数据服务信息为以下任一项：联邦学习服务的标识，分布式学习服务的标识，或数据汇聚服务的标识。
第八方面，提供一种通信装置，该装置包括处理器，该处理器与存储器耦合，可用于执行存储器中的指令，以实现上述第一方面至第二方面中的任一方面，以及第一方面至第二方面中任一种可能实现方式中的方法。可选地，该装置还包括存储器，该存储器与处理器可能是分离部署的，也可能是集中部署的。可选地，该装置还包括通信接口，处理器与通信接口耦合。
在一种实现方式中，该通信接口可以是收发器，或，输入/输出接口。
在另一种实现方式中，该装置为第一装置，第一装置可以是网络中的功能网元，也可以是终端设备、网络设备、核心网设备或操作维护管理设备中的芯片或电路，也可以是能实现全部或部分终端设备、网络设备、核心网设备或操作维护管理设备功能的逻辑模块或软件，本申请对此不作限定。当该装置为芯片时，该通信接口可以是该芯片或芯片系统上的输入/输出接口、接口电路、输出电路、输入电路、管脚或相关电路等。该处理器也可以体现为处理电路或逻辑电路。
可选地，该收发器可以为收发电路。可选地，所述输入/输出接口可以为输入/输出电路。
在具体实现过程中，上述处理器可以为一个或多个芯片，输入电路可以为输入管脚，输出电路可以为输出管脚，处理电路可以为晶体管、门电路、触发器和各种逻辑电路等。输入电路所接收的输入的信号可以是但不限于接收器接收并输入的，输出电路所输出的信号可以是但不限于输出给发射器并由发射器发射的，且输入电路和输出电路可以是同一电路，该电路在不同的时刻分别用作输入电路和输出电路。本申请实施例对处理器及各种电路的具体实现方式不做限定。
第九方面，提供一种通信装置，该装置包括处理器，该处理器与存储器耦合，可用于执行存储器中的指令，以实现上述第三方面，以及第三方面中任一种可能实现方式中的方法。可选地，该装置还包括存储器，该存储器与处理器可能是分离部署的，也可能是集中部署的。可选地，该装置还包括通信接口，处理器与通信接口耦合。
在一种实现方式中，该通信接口可以是收发器，或，输入/输出接口。
在另一种实现方式中，该装置为第三装置，第三装置可以是网络中的功能网元，也可以是网络设备、核心网设备中的芯片或电路，也可以是能实现全部或部分网络设备、核心 网设备功能的逻辑模块或软件，本申请对此不作限定。当该装置为芯片时，该通信接口可以是该芯片或芯片系统上的输入/输出接口、接口电路、输出电路、输入电路、管脚或相关电路等。该处理器也可以体现为处理电路或逻辑电路。
可选地，该收发器可以为收发电路。可选地，所述输入/输出接口可以为输入/输出电路。
在具体实现过程中，上述处理器可以为一个或多个芯片，输入电路可以为输入管脚，输出电路可以为输出管脚，处理电路可以为晶体管、门电路、触发器和各种逻辑电路等。输入电路所接收的输入的信号可以是但不限于接收器接收并输入的，输出电路所输出的信号可以是但不限于输出给发射器并由发射器发射的，且输入电路和输出电路可以是同一电路，该电路在不同的时刻分别用作输入电路和输出电路。本申请实施例对处理器及各种电路的具体实现方式不做限定。
第十方面，提供一种通信装置，该装置包括逻辑电路和输入/输出接口，该逻辑电路用于与输入/输出接口耦合，通过该输入/输出接口传输数据，以执行上述第一方面至第三方面中的任一方面，以及第一方面至第三方面中任一种可能实现方式中的方法。
第十一方面，提供一种通信系统，该系统包括第一装置和第三装置，第一装置用以执行上述第一方面至第二方面中的任一方面，以及第一方面至第二方面中任一种可能实现方式中的方法；第三装置用以执行上述第三方面，以及第三方面中任一种可能实现方式中的方法。
第十二方面，提供了一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序(也可以称为代码，或指令)当其在计算机上运行时，使得计算机执行上述第一方面至第三方面中的任一方面，以及第一方面至第三方面中任一种可能实现方式中的方法。
第十三方面，提供了一种计算机程序产品，该计算机程序产品包括：计算机程序(也可以称为代码，或指令)，当该计算机程序被运行时，使得计算机执行上述第一方面至第三方面中的任一方面，以及第一方面至第三方面中任一种可能实现方式中的方法。
上述第五方面至第十三方面带来的有益效果可以参考第一方面至第三方面中有益效果的描述，此处不再赘述。
附图说明
图1是本申请实施例提供的一种网络架构。
图2是本申请实施例提供的一种数据报文的传输方法的流程交互图。
图3是本申请实施例提供的另一种数据报文的传输方法的流程交互图。
图4是本申请实施例提供的用于数据汇聚场景的示意图。
图5是本申请实施例提供的用于数据汇聚以及数据分发场景的示意图。
图6是本申请实施例提供的通信装置的示意性框图。
图7是本申请实施例提供的一种通信装置的结构示意图。
图8是本申请实施例提供的另一种通信装置的结构示意图。
具体实施方式
下面将结合附图，对本申请实施例中的技术方案进行描述。
图1是本申请实施例提供的一种网络架构。
图1示出的通信系统100包括数据源、数据平面和数据消费者。数据源(例如数据源00、数据源01)可以是产生业务数据的装置；数据平面用于数据的处理，例如数据收集、数据存储、数据预处理、数据分析、数据服务应用程序接口(application program interface，API)等等。数据消费者(例如数据消费者50、数据消费者51)可以是处理后的数据的使用装置。数据平面包括数据处理装置(例如数据处理装置10、数据处理装置11、数据处理装置20、数据处理装置21、数据处理装置22、数据处理装置23)、数据编排装置30。其中，数据处理装置可以是业务数据的处理节点。数据编排装置可以为数据处理装置配置基本信息，例如配置标识信息等，不同的数据服务涉及的数据的处理节点可以不同，因此不同的数据服务对应的传输路径可以不同。图1示出了数据传输的两个路径，第一路径：数据源00→数据处理装置10→数据处理装置21→数据处理装置23→数据消费者51，第二路径：数据源01→数据处理装置11→数据处理装置20→数据处理装置22→数据消费者50，“→”指示业务数据的传输方向。图1示出的数据通信网络可以作为不同数据处理装置间进行数据交换的消息总线工作。
示例地，数据处理装置可以为数据代理(data agents，DA)，可以对数据进行收集、存储、预处理、分析等处理工作。数据处理装置可以独立部署，例如以网络功能(network function，NF)或网元的形式部署在网络中，数据处理装置也可以内置于网络节点中，例如内置于终端设备、无线接入网(radioaccess network，RAN)节点、核心网(core network，CN)节点、操作维护管理(operation administration and maintenance，OAM)节点中。数据处理装置非独立部署时可以和上述节点中已有功能合并实现处理数据的功能。数据处理装置也可以是由上述节点演进而来，例如，数据处理装置是由网络数据分析功能(network data analysis function，NWDAF)演进而来，包括能够实现NWDAF已有的功能，以及基于NWDAF实现的场景用例等，本申请对此不做限制。
示例地，数据编排装置可以为数据编排(data orchestrator，DO)，可以接收来自应用的数据服务需求(数据服务需求例如数据采集、基于网络采集数据的联邦学习训练或推理等)，并基于该需求确定数据处理装置，即为数据应用动态建立一个端到端(endto end，E2E)的上层(overlay)拓扑网络(topology)，该上层拓扑网络即为数据处理网络，该网络中的网络节点(即数据处理装置)为数据的处理节点，DO可以编排DA间数据在该数据通信网络中流动，并可以将针对该需求的响应反馈至应用，例如向应用反馈上层拓扑网络已经建立完成。数据编排装置可以独立部署，例如以NF或网元的形式部署在网络中，数据编排装置也可以内置于网络节点中，例如内置于RAN节点、CN节点中，本申请对此不做限制。
可以理解，上层网络是相对于底层网络(underlay)而言的，是建立在底层网络上的逻辑网络。通过网络虚拟化技术，可以在同一张底层网络上构建出一张或者多张虚拟的逻辑网络。不同的上层网络可以共享底层网络中的设备和线路，但是上层网络中的业务与底层网络中的物理组网和互联技术可以相互解耦。
可选地，数据平面还包括可信装置40，可信装置用于数据可信性，保护数据不受攻击。
示例地，可信装置可以为可信锚点(trust anchor，TA)，可以提供认证授权计费 (authentication authorization accounting，AAA)等安全服务，存储不可篡改的数据、用户设备(user equipment，UE)或网元(net element，NE)的公钥，数据量小、但有不能篡改的特性的数据或不能被篡改的重要数据。
可选地，数据平面还包括存储装置24。
示例地，当大量数据需要被存储，或者当数据需要长期进行存储，此时存储设备可以作为数据处理装置的存储扩展。存储装置例如是数据存储功能(data storage function，DSF)网元，本申请对此不做限制。
本申请实施例提供的方法还可以涉及图1中未示出的设备或通信节点，当然本申请实施例提供的通信方法也可以只包括图1示出的部分设备或通信节点，本申请实施例对此不作限定。
可以理解，上述描述或图中所示的名称(例如数据编排装置、数据处理装置、DO、DA、TA等)仅为示例，上述装置还可以是其他的名称，本申请对此不做限制。
上述应用于本申请实施例的网络架构是一种举例说明，适用本申请实施例的网络架构并不局限于此，任何能够实现上述部分或全部设备的功能的网络架构都适用于本申请实施例。
终端设备可以是能够接收网络设备调度和指示信息的无线终端设备。终端设备可以是指向用户提供语音和/或数据连通性的设备，或具有无线连接功能的手持式设备、或连接到无线调制解调器的其他处理设备。
终端设备：也可以称为终端、接入终端、用户单元、用户设备(user equipment，UE)、用户站、移动站、移动台、远方站、远程终端、移动设备、用户终端、无线通信设备、用户代理或用户装置。终端设备是包括无线通信功能(向用户提供语音/数据连通性)的设备。例如，具有无线连接功能的手持式设备、或车载设备等。本申请的实施例中的终端可以是手机(mobile phone)、平板电脑(pad)、带无线收发功能的电脑、列车、飞机、移动互联网设备(mobile internet device，MID)、虚拟现实(virtual reality，VR)终端、增强现实(augmented reality，AR)终端、工业控制(industrial control)中的无线终端(例如机器人等)、车联网中的无线终端(例如车载设备、整车设备、车载模块、车辆等)、无人驾驶(self driving)中的无线终端、远程医疗(remote medical)中的无线终端、智能电网(smart grid)中的无线终端、运输安全(transportation safety)中的无线终端、智慧城市(smart city)中的无线终端、智慧城市(smart city)中的无线终端、智慧家庭(smart home)中的无线终端、蜂窝电话、无绳电话、会话启动协议(session initiation protocol，SIP)电话、无线本地环路(wireless local loop，WLL)站、个人数字助理(personal digital assistant，PDA)、具有无线通信功能的手持设备、计算设备或连接到无线调制解调器的其它处理设备、车载设备、可穿戴设备，5G网络中的终端或者未来演进网络(例如6G)中的终端等。
其中，可穿戴设备也可以称为穿戴式智能设备，是应用穿戴式技术对日常穿戴进行智能化设计、开发出可以穿戴的设备的总称，如眼镜、手套、手表、服饰及鞋等。可穿戴设备即直接穿在身上，或是整合到用户的衣服或配件的一种便携式设备。可穿戴设备不仅仅是一种硬件设备，更是通过软件支持以及数据交互、云端交互来实现强大的功能。广义穿戴式智能设备包括功能全、尺寸大、可不依赖智能手机实现完整或者部分的功能，例如： 智能手表或智能眼镜等，以及只专注于某一类应用功能，需要和其它设备如智能手机配合使用，如各类进行体征监测的智能手环、智能首饰等。
接入网节点可以是无线网络中的设备。例如，接入网节点可以是部署在无线接入网中为终端设备提供无线通信功能的设备。例如，接入网节点可以为将终端设备接入到无线网络的无线接入网(radio access network，RAN)节点，又可以称为接入网设备。
接入网节点包括但不限于：演进型节点B(evolved Node B，eNB)、无线网络控制器(radio network controller，RNC)、节点B(Node B，NB)、基站控制器(base station controller，BSC)、基站收发台(base transceiver station，BTS)、家庭基站(home evolved NodeB，HeNB，或home Node B，HNB)、基带单元(baseBand unit，BBU)、服务器、可穿戴设备、车载设备，WIFI系统中的接入点(access point，AP)、无线中继节点、无线回传节点、传输点(transmission point，TP)或者发送接收点(transmission and reception point，TRP)等，还可以为5G，如NR系统中的gNB，或传输点(TRP或TP)，5G系统中的基站的一个或一组(包括多个天线面板)天线面板，或者，还可以为构成gNB或传输点的网络节点，如基带单元(BBU)，或分布式单元(distributed unit，DU)等。也可以为6G中接入网节点，本申请不予限制。其中，基站可以是宏基站、微基站、微微基站、小站、中继站或气球站等。
在一些部署中，gNB可以包括集中式单元(centralized unit，CU)和DU。gNB还可以包括有源天线单元(active antenna unit，AAU)。CU实现gNB的部分功能，DU实现gNB的部分功能。比如，CU负责处理非实时协议和服务，实现无线资源控制(radio resource control，RRC)，分组数据汇聚层协议(packet data convergence protocol，PDCP)层的功能。DU负责处理物理层协议和实时服务，实现无线链路控制(radio link control，RLC)层、媒体接入控制(media access control，MAC)层和物理(physical，PHY)层的功能。AAU实现部分物理层处理功能、射频处理及有源天线的相关功能。RRC层的信息由CU生成，最终会经过DU的PHY层封装变成PHY层信息，或者，由PHY层的信息转变而来。因而，在这种架构下，高层信令如RRC层信令，也可以认为是由DU发送的，或者，由DU+AAU发送的。可以理解的是，网络设备可以为包括CU节点、DU节点、AAU节点中一项或多项的设备。此外，可以将CU划分为接入网(radio access network，RAN)中的网络设备，也可以将CU划分为核心网(core network，CN)中的网络设备，本申请对此不做限定。
核心网节点的功能是提供用户连接、对用户的管理以及对会话类业务完成承载。
本申请实施例的技术方案可以应用于各种通信系统，例如：长期演进(long term evolution，LTE)系统、高级的长期演进(LTE advanced，LTE-A)系统，LTE频分双工(frequency division duplex，FDD)系统、LTE时分双工(time division duplex，TDD)、无线保真(wireless fidelity,Wi-Fi)通信系统、通用移动通信系统(universal mobile telecommunication system，UMTS)、全球互联微波接入(worldwide interoperability for microwave access，WiMAX)通信系统、第五代(5th Generation，5G)系统或未来演进的通信系统(例如，6G移动通信系统)，车到其它设备(vehicle-to-X V2X)，其中V2X可以包括车到互联网(vehicle to network，V2N)、车到车(vehicle to vehicle，V2V)、车到基础设施(vehicle to infrastructure，V2I)、车到行人(vehicle to pedestrian，V2P)等、 车间通信长期演进技术(long term evolution-vehicle，LTE-V)、车联网、机器类通信(machine type communication，MTC)、物联网(Internet of things，IoT)、机器间通信长期演进技术(long term evolution-machine，LTE-M)，机器到机器(machine to machine，M2M)等。
通信网络中产生的数据会以数据报文的形式传输到各个数据处理节点。例如网络感知数据、用户数据、人工智能(artificial intelligence，AI)数据，IoT数据等需要包括收集、处理、传输、存储、分析等功能的数据管道(data pipeline，DP)承载，一个数据管道可以理解为上层拓扑网络中的一条路径(例如图1所示的第一路径，或第二路径)，一个数据管道内有哪些处理节点可以由数据编排装置确定。例如，数据编排装置可以基于数据服务请求和各数据处理装置的能力建立数据管道，数据管道可以是单向的，数据管道建立以后，数据管道内处理节点可确定，各处理节点需要对数据进行的操作可确定，数据在数据管道内流动，并在流经的处理节点处完成处理操作。
可以理解，数据管道是为更清楚的描述本申请的方案所起名称，数据管道还可以替换为其他名称，本申请对此不做限制。
数据管道上的每个处理节点需要对包括数据的数据报文作相应处理(on-path-packet-processing)(例如收集、预处理、传输、存储、分析等)后，将其转发至下一个处理节点。数据管道中不同处理节点间的通信可以依赖于底层网络的通信路径，但数据管道中的每一个处理节点如何确定数据报文的下一个处理节点与底层网络可以解耦。下面介绍本申请提供的在处理节点间传输数据报文的方法。
图2是本申请实施例提供的一种数据报文的传输方法的流程交互图。图2所示的方法200包括：
S210，数据处理装置#0获取业务数据。
一种可能的实施方式，数据处理装置#0是收集业务数据的装置，或者是业务数据的第一个处理节点，即初始处理节点。
示例地，数据处理装置#0为数据管道的入口DA(例如图1所示的数据处理装置10或数据处理装置11)，该入口DA用于从数据源获取业务数据。数据源为产生数据的源头，例如传感器、内置的网络功能参数的采集器等。业务数据即在数据源收集/采集的数据，例如，业务数据包括传感器感知的数据、网络数据中网络功能的性能数据、或资源利用信息等。不同数据源对应的业务数据种类可以不同，例如数据源是温度传感器时，业务数据为表征温度的数据，数据源为压力传感器时，业务数据为表征压力的数据，本申请对此不做限制。
S220，数据处理装置#0确定数据处理装置#1。
一种可能的实施方式，数据处理装置#0基于数据服务(data service，DS)信息确定传输路径信息(对应发明内容中的第三传输路径信息)，该传输路径信息包括数据处理装置#1的信息，数据处理装置#1为数据报文#1的处理节点，数据报文#1包括该业务数据对应的数据载荷以及该传输路径信息。
应理解，数据服务是基于数据收集、存储、转发、分析等处理的框架，满足数据法律法规的要求，兼顾数据的共享和安全，将数据作为一种服务产品提供。数据服务信息可以是数据服务的标识，不同应用(数据消费者)的数据服务需求可能不同，因此不同应用对应的数据服务也不同，数据服务信息可以区分不同的数据服务。
示例地，数据服务包括联邦学习、分布式学习、以及数据汇聚等，数据服务信息为数据服务标识。例如，联邦学习服务的标识(identifier，ID)为DS_ID 1，分布式学习服务的标识为DS_ID 2，数据汇聚服务的标识为DS_ID 3。以上只列举了部分数据服务，并且列举的数据服务的标识仅为示例，本申请对此不做限制。
具体地，数据处理装置#0可基于获取的业务数据确定数据服务信息，并根据数据服务信息和数据报文的传输路径信息之间的对应关系确定某一数据服务对应的传输路径信息。
或者，数据处理装置#0获取业务数据，并获取业务数据对应的数据服务信息，根据数据服务信息和数据报文的传输路径信息之间的对应关系确定某一数据服务对应的传输路径信息，传输路径信息可以封装到数据报文中。
可以理解，数据处理装置#0本地存储数据服务信息和数据报文的传输路径信息之间的对应关系，或者数据处理装置#0可以从数据编排装置处获取该对应关系，本申请对获取对应关系的方式不做限制。
示例地，数据处理装置#0获取的业务数据为用于联邦学习的数据，并且联邦学习服务的数据服务标识为DS_ID 1，数据服务标识也可以理解为数据管道标识(因为不同数据服务对应的数据管道可以不同，即不同数据服务对应的数据管道中的数据处理装置可以不同)，例如，联邦学习服务对应的数据管道标识为DP_ID 1，DS_ID 1/DP_ID 1对应传输路径信息#1。传输路径信息#1包括一个或多个处理用于联邦学习的业务数据的数据处理装置的信息。不同数据管道标识或不同数据服务标识对应的传输路径信息不同。
一种可能的实施方式，传输路径信息中包括一个或多个数据处理装置的标识信息，数据处理装置的标识信息可以是数据编排装置(例如图1所示的数据编排装置)预先分配的。也就是说，数据编排装置可以为overlay网络上的每一个数据处理装置(包括数据处理装置#0和数据处理装置#1)分配标识。
可选地，传输路径信息中包括并列的数据处理装置的信息，并列的数据处理装置为数据报文的同一级处理节点。
可选地，传输路径信息中包括按序排列的数据处理装置的信息，排列靠前的数据处理装置处理数据报文的顺序靠前。
示例地，传输路径信息#1为{DA_ID1,[DA_ID 2(DA_ID 4)|(DA_ID 3(DA_ID 5)]}，其中，DA_ID1、DA_ID 2、DA_ID3、DA_ID4、DA_ID5为数据编排装置预先分配的标识。(DAi|DAj)表示DAi与DAj为并列的数据处理装置，即数据报文的同一级处理节点，可以处理不同的数据载荷。(DAi,DAj)或(DAi(DAj)表示DAi与DAj为顺序关系，并且DAj排列靠后，即DAj是DAi的下一个处理节点。在该示例中有两条路径：DA_ID1→DA_ID2→DA_ID4；DA_ID1→DA_ID3→DA_ID5。其中，DA_ID 2和DA_ID3并列，DA_ID4和DA_ID5并列，DA_ID1与DA_ID 2、DA_ID2与DA_ID4、DA_ID1与DA_ID3、DA_ID3与DA_ID5是顺序关系。DA_ID1对应的装置可以向DA_ID 2和DA_ID3对应的装置发送数据报文让其处理数据报文中的数据载荷，若发送的数据报文中的数据载荷相同，则此场景为数据多播场景，若发送的数据报文中的数据载荷不同，则此场景为数据分发场景。
可以理解，传输路径信息#1的上述格式仅为示例，本申请对此不做限制。
另一种可能的实施方式，传输路径信息中包括一个或多个数据处理装置的地址信息， 该地址信息可以是底层网络中该一个或多个数据处理装置的路由地址信息，本申请对此不做限制。
示例地，传输路径信息#1为{Add1,[Add 2(Add 4)|Add 3(Add 5)]}，其中，Add1、Add2、Add3、Add4、Add5为数据处理装置的地址信息。(Add i|Add j)表示Add i与Add j为并列的数据处理装置，即数据报文的同一级处理节点。(Add i,Add j)或(Addi(Addj))表示Add i与Add j为顺序关系，并且Add j排列靠后，即Add j是Add i的下一个处理节点。在该示例中有两条路径：Add1→Add2→Add4；Add1→Add3→Add5。其中，Add2和Add3并列，Add4和Add5并列，Add1与Add 2、Add2与Add 4、Add1与Add3、Add3与Add5是顺序关系。Add1对应的装置可以向Add 2和Add3对应的装置发送数据报文让其处理数据报文中的数据载荷，若发送的数据报文中的数据载荷相同，则此场景为数据多播场景，若发送的数据报文中的数据载荷不同，则此场景为数据分发场景。
可以理解，传输路径信息#1的上述格式仅为示例，本申请对此不做限制。
S230，数据处理装置#0向数据处理装置#1发送数据报文#1，数据报文#1包括传输路径信息和该业务数据对应的数据载荷。对应地，数据处理装置#1接收该数据报文#1。
示例地，数据处理装置#0将业务数据处理为数据载荷，将其封装到数据报文#1中，数据报文#1的报头中包括传输路径信息，该传输路径信息包括数据报文#1的处理节点的信息。例如数据报文#1有2个处理节点，分别是数据处理装置#1和数据处理装置#2，则该传输路径信息包括数据处理装置#1和数据处理装置#2的信息。
可选地，数据报文#1还包括数据服务标识或数据管道标识(例如DS_ID 1/DP_ID 1)。
可选地，数据报文#1还包括统计模式信息，统计模式信息用于指示统计信息的统计模式，统计信息包括数据报文的数量信息或者数据报文的字节数量信息，或者统计信息包括其他的数量信息，本申请对此不做限制。
数据报文中包括统计模式信息，可以使得数据报文的处理节点通过数据报文中指示的统计模式信息确定统计信息的统计方式，从而按照数据报文中的指示统计上报统计信息。
示例地，统计模式信息为统计模式编码，以下介绍不同统计模式编码表示的含义：
000：表示以数据服务信息为粒度统计报文数；
001：表示以传输路径信息为粒度统计报文数；
010：表示以数据服务信息为粒度统计字节数；
011：表示以传输路径信息为粒度统计字节数；
100：表示以数据服务信息为粒度统计报文和字节数
101：表示以传输路径信息为粒度统计报文和字节数
111：表示不统计上报
应注意：数据处理装置#0可在数据报文发出后向数据编排装置统计上报统计信息，数据处理装置#1可在数据报文到达或发出后向数据编排装置统计上报统计信息，本申请对此不做限制。
可以理解，上述统计模式编码和其对应的含义是数据编排装置和各处理节点(例如数据处理装置#0、数据处理装置#1)预定义或预配置的。需要说明的是，上述不同统计模式编码表示的含义可以互换，本申请不予限定。
示例地，数据处理装置#0和数据处理装置#1为overlay网络中的节点，因此数据报文 #1在实际传输的过程中，数据处理装置#0可通过底层网络的寻址方式确定数据处理装置#0到数据处理装置#1的路由路径，从而向数据处理装置#1发送数据报文#1。
例如，数据处理装置#1在overlay网络的标识和底层网络中的数据处理装置#1的地址相同，数据处理装置#0可根据数据处理装置#1的标识确定在底层网络中数据处理装置#0到数据处理装置#1的路由路径，将数据报文#1通过该路由路径传输至数据处理装置#1。
再例如，数据处理装置#1在overlay网络的标识和底层网络中的地址不同，此实施方式中，数据处理装置#0本地可以存储数据处理装置#1在overlay网络的标识和底层网络中的地址之间的对应关系，然后根据对应关系确定数据处理装置#1的地址，并确定在底层网络中数据处理装置#0到数据处理装置#1的路由路径，将数据报文#1通过该路由路径传输至数据处理装置#1。
可选地，方法200还包括：
S201，数据编排装置发送对应关系信息，该对应关系信息指示数据服务信息和传输路径信息的对应关系。对应地，数据处理装置#0接收该对应关系信息。
可选地，数据的处理节点(例如图1所示的数据处理装置，包括数据处理装置#0和数据处理装置#1)向数据编排装置发送注册信息，注册信息可以指示自己的能力/功能。数据编排装置基于各处理节点的注册信息生成由处理节点组成的overlay网络。并且数据编排装置可以为overlay网络上的每一个数据处理装置分配标识。
上述为各数据处理装置分配标识的过程可称之为overlay网络的初始化过程。
可选地，数据编排装置在发送对应关系信息之前，数据编排装置根据应用的数据服务请求，以及overlay网络中的网络节点能力/功能计算出针对不同数据服务请求的传输路径。
示例地，数据编排装置根据联邦学习应用的数据服务请求计算出联邦学习数据报文的传输路径为DA#1→DA#2→上层应用，此时DA#1为入口DA(对应数据处理装置#0)，即数据报文的第一个处理节点，也可以理解为生成数据报文的网络节点。
数据编排装置计算好针对不同数据服务的传输路径后，生成数据服务信息和传输路径信息的对应关系，并向对应的数据处理装置#0发送对应关系信息，对应关系指示数据服务信息和传输路径信息的对应关系。
示例地，数据编排装置生成的对应关系例如表1。
表1
Figure PCTCN2022116833-appb-000001
如表1，一个数据服务标识可以对应多个传输路径信息，其中多个传输路径信息可以对应一个数据处理装置#0，也可以对应多个数据处理装置#0。例如，DS_ID 1对应两个数据处理装置#0，且对应两个传输路径信息，DA#1关联传输路径信息①(DA#2，上层应用)，DA#3关联传输路径信息②(DA#6，上层应用)，数据编排装置将DS_ID 1与传输路径信息①的对应关系信息发送至DA#1，数据编排装置将DS_ID 1与传输路径信息②的对应关系信息发送至DA#3。传输路径信息①和传输路径信息②的初始处理节点不同，最终处理节点相同，适用于数据汇聚场景。数据汇聚即多个数据处理装置向一个网络节点(例如数 据处理装置或应用)发送数据报文，且不同数据处理装置发送的数据报文属于同一数据服务标识。
再例如，DS_ID2对应一个数据处理装置#0，且对应两个传输路径信息，DA#1关联传输路径信息③(DA#2，DA#4)以及传输路径信息④(DA#2，DA#5)，数据编排装置将DS_ID 2与传输路径信息③和传输路径信息④的对应关系信息发送至DA#1。传输路径信息③和传输路径信息④的初始处理节点相同，最终处理节点不同，适用于数据分发或者多播场景。数据多播即一个数据处理装置向两个或两个以上数据处理装置发送相同的数据报文(相同的数据报文对应一个数据服务标识，例如相同的数据报文对应数据服务标识#1)，数据分发即一个数据处理装置向两个或两个以上数据处理装置发送不同的数据报文(不同的数据报文对应一个数据服务标识，例如不同的数据报文对应数据服务标识#2)。
应理解，S201可以在S210之前，或者S201可以在S220之前，本申请对此不做限制。
可以理解，表1仅为示例，表1还可以有其他形式的转换，本申请对此不做限制。例如表1变换为第一列是数据处理装置#0，第二列是数据服务信息，在此不一一列举。
还可以理解，S201中数据编排装置向一个数据处理装置#0发送的对应关系信息可以指示一个或多个数据服务信息和传输路径信息的对应关系。即数据编排装置可以针对一个数据服务信息，将该数据服务信息与传输路径信息的对应关系发送给相关数据处理装置#0。例如，参见表1，针对DS_ID 1，数据编排装置将DS_ID 1和(DA#2，上层应用)的对应关系信息发送至DA#1，将DS_ID 1和(DA#6，上层应用)的对应关系信息发送至DA#3。或者数据编排装置可以针对数据处理装置#0，向每个数据处理装置#0发送该数据处理装置#0涉及的数据服务信息与传输路径信息的对应关系。例如，针对DA#1，数据编排装置将DS_ID 1和(DA#2，上层应用)的对应关系信息，以及DS_ID 2与(DA#2，DA#4|DA#5)的对应关系信息发送给DA#1，上述不同数据服务信息的对应关系可以同时发送，也可以分开发送，本申请对此不做限制。DA#1可以根据获取的数据服务信息在上述数据编排装置发送的对应关系信息中选择对应关系使用。例如，DA#1获取的数据服务信息为DS_ID 1，则可以通过上述不同数据服务信息的对应关系确定DS_ID 1对应的数据报文的传输路径信息为(DA#2，上层应用)。
可选地，数据处理装置#0接收该对应关系信息后，存储该数据服务信息对应的传输路径信息。
示例地，数据处理装置#0本地存储数据服务信息和传输路径信息的对应关系表，数据处理装置#0接收该对应关系信息后，将该数据服务信息对应的传输路径信息写入该对应关系表。
可选地，数据处理装置#0存储该数据服务信息对应的传输路径信息后，向数据编排装置发送确认信息，该确认信息后表示数据处理装置#0已存储该数据服务信息对应的传输路径信息。数据编排装置接收到该确认信息后可确认数据处理装置#0已存储该数据服务信息对应的传输路径信息。
一种可能的实施方式，可用于数据多播的场景，S201中的数据服务信息包括数据服务信息#1，数据服务信息#1对应N个传输路径信息，N为大于或等于1的整数。
S230可替换为：
数据处理装置#0向至少一个数据处理装置#1发送N1个数据报文，其中，每个数据处 理装置#1关联至少一个数据报文，每个数据报文包括N1个传输路径信息中的一个传输路径信息，N1为大于1的整数。
可以理解，数据服务信息#1对应发明内容中的第一数据服务信息。
示例地，数据服务信息#1为DS_ID0，若DS_ID 0对应3个传输路径信息(即N1＝3)，3个传输路径信息(传输路径信息#2、传输路径信息#3、传输路径信息#4)对应3个数据处理装置#1，分别是DA#2、DA#3、DA#4，例如传输路径信息#2对应DA#2、传输路径信息#3对应DA#3、传输路径信息#4对应DA#4。则数据处理装置#0向DA#2发送数据报文#2，数据报文#2的报头中包括传输路径信息#2；向DA#3发送数据报文#3，数据报文#3的报头中包括传输路径信息#3；向DA#4发送数据报文#4，数据报文#4的报头中包括传输路径信息#4。其中，数据报文#2、数据报文#3和数据报文#4中的数据载荷相同。
一种可能的实施方式，可用于数据分发的场景，S201中的数据服务信息包括数据服务信息#2，数据服务信息#2对应N2个传输路径信息，N2为大于1的整数。
可以理解，数据服务信息#2对应发明内容中的第一数据服务信息。
S230可替换为：
数据处理装置#0向至少一个数据处理装置#1发送N2个数据报文，其中，每个数据处理装置#1关联至少一个数据报文，每个数据报文包括该N2个传输路径信息中的一个传输路径信息，N2个数据报文中包括两个数据载荷不同的数据报文。
示例地，数据服务信息#2为DS_ID 1，若DS_ID 1对应3个传输路径信息(N2＝3)，3个传输路径信息(传输路径信息#5、传输路径信息#6、传输路径信息#7)对应3个数据处理装置#1，分别是DA#5、DA#6、DA#7，例如传输路径信息#5对应DA#5、传输路径信息#6对应DA#6、传输路径信息#7对应DA#7。则数据处理装置#0向DA#5发送数据报文#5，数据报文#5的报头中包括传输路径信息#5；向DA#6发送数据报文#6，数据报文#6的报头中包括传输路径信息#6；向DA#7发送数据报文#7，数据报文#7的报头中包括传输路径信息#7。其中，数据报文#5、数据报文#6和数据报文#7中有两个数据报文的数据载荷不同。
一种可能的实施方式，可用于数据汇聚的场景，数据服务信息#3对应M个传输路径信息，该M个传输路径信息对应M1个数据处理装置#0，M为大于1的整数，M1小于或等于M，S201中的对应关系信息指示该数据服务信息#3和该M个传输路径信息中的一个传输路径信息的对应关系。
可以理解，数据服务信息#3对应发明内容中的第一数据服务信息。
示例地，数据服务信息#3为DS_ID 2，若DS_ID 2对应3个传输路径信息(即M＝3)，分别是传输路径信息#a、传输路径信息#b、传输路径信息#c，传输路径信息#a对应的数据处理装置#0为DA#0，传输路径信息#b对应的数据处理装置#0为DA#1，传输路径信息#c对应的数据处理装置#0为DA#2(即M1＝M＝3)。则DA#0发送数据报文#8，数据报文#8的报头中包括传输路径信息#a；DA#1发送数据报文#9，数据报文#9的报头中包括传输路径信息#b；DA#2发送数据报文#10，数据报文#10的报头中包括传输路径信息#c。数据报文#8、数据报文#9和数据报文#10的最终处理节点可以是同一个节点。
示例地，若DS_ID 2对应3个传输路径信息(即M＝3)，分别是传输路径信息#a、传输路径信息#b、传输路径信息#c，传输路径信息#a对应的数据处理装置#0为DA#0，传输 路径信息#b对应的数据处理装置#0为DA#1，传输路径信息#c对应的数据处理装置#0为DA#1(即M1＝2)。则DA#0发送数据报文#11，数据报文#11的报头中包括传输路径信息#a；DA#1发送数据报文#12，数据报文#12的报头中包括传输路径信息#b；DA#1发送数据报文#13，数据报文#13的报头中包括传输路径信息#c。数据报文#11、数据报文#12和数据报文#13的最终处理节点可以是同一个节点。
可以理解，不同的数据服务标识可以对应相同的传输路径信息，或者不同的数据服务标识可以对应不同的传输路径信息，本申请对此不做限制，上述示例不对本申请的保护范围造成限制。
上述列举的数据报文处理并转发的应用场景，例如数据多播、数据分发以及数据汇聚等实现了数据报文的不同传输路径的灵活拓扑，提高了数据报文处理及转发的灵活性。
可选地，方法200还包括：
S231，数据编排装置发送配置信息，该配置信息用于配置以下至少一项：数据报文的统计模式、数据报文的统计周期、传输路径信息的有效时间。对应地，数据处理装置#0接收该配置信息。
示例地，当配置信息配置了数据报文的统计模式时，数据处理装置#0可以根据该统计模式统计数据报文，并且可以将该统计模式信息封装在数据报文中，告知数据报文经过的处理节点以哪种模式统计数据报文。具体统计模式有哪些可以参见S230中的示例，在此不做赘述。当配置信息配置了数据报文的统计周期时，数据处理装置#0可以根据该统计周期统计数据报文。当配置信息配置了传输路径信息的有效时间时，数据处理装置#0可以在该传输路径信息的有效时间内，依据该传输路径信息传输数据报文。
可选地，数据处理装置#0向数据编排装置发送确认信息，该确认信息用于对该配置信息进行确认。数据编排装置接收到该确认信息后确定配置信息已经被数据处理装置#0准确接收，也就是说配置操作已经完成。
可选地，方法200还包括：
S232，数据编排装置发送更新信息，该更新信息用于更新该数据服务信息对应的传输路径信息。对应地，数据处理装置#0接收该更新信息。
示例地，数据处理装置#0本地存有数据服务信息和传输路径信息的对应关系，当数据处理装置#0接收到更新信息后，可以依据更新信息更新某数据服务信息对应的传输路径信息。例如数据处理装置#0本地存有DS_ID 1和传输路径信息#1的对应关系，更新信息中包括DS_ID 1和传输路径信息#2的对应关系，数据处理装置#0可以基于更新信息将DS_ID 1和传输路径信息#1的对应关系更新为DS_ID 1和传输路径信息#2的对应关系，更新后针对DS_ID 1的数据报文基于传输路径信息#2传输。
可选地，数据处理装置#0向数据编排装置发送确认信息，该确认信息用于对该更新信息进行确认。数据编排装置接收到该确认信息后确定更新信息已经被数据处理装置#0准确接收，也就是说更新操作已经完成。
传输路径信息可以更新，而非一直固定，因此数据处理装置可以根据更新后的传输路径信息传输数据报文，提高数据报文传输以及处理的灵活性。
可选地，方法200还包括：
S233，数据编排装置发送读取信息，该读取信息用于读取某数据服务信息对应的传输 路径信息。对应地，数据处理装置#0接收该读取信息。
示例地，读取信息包括DS_ID 0，表示让数据处理装置#0发送DS_ID 0对应的传输路径信息。
可选地，数据处理装置#0向数据编排装置发送读取响应信息，该读取响应信息包括某数据服务信息对应的传输路径信息。数据编排装置接收到该读取响应信息后确定读取信息已经被数据处理装置#0准确接收，也就是说读取操作已经完成。
示例地，读取响应信息包括DS_ID 0对应的传输路径信息#0。
应理解，数据编排装置在调试或者故障排除阶段可以通过读取响应信息中的传输路径信息，确认某一数据服务信息对应的传输路径信息是否准确，便于数据编排装置排除故障，提高系统的性能。
可选地，方法200还包括：
S234，数据编排装置发送删除信息，该删除信息用于删除某数据服务信息对应的传输路径信息。对应地，数据处理装置#0接收该删除信息。
示例地，当某数据服务信息对应的数据服务已经结束，数据编排装置可以通过删除信息指示数据处理装置#0删除该数据服务信息对应的传输路径信息，删除信息中可以包括需要删除的传输路径信息。
示例地，数据编排装置获取或接收数据服务请求，数据服务请求用于请求删除该数据服务信息对应的传输路径信息，数据编排装置发送删除信息指示数据处理装置#0删除该数据服务信息对应的传输路径信息，删除信息中可以包括需要删除的传输路径信息。
可选地，数据处理装置#0向数据编排装置发送确认信息，该确认信息用于对该删除信息进行确认。数据编排装置接收到该确认信息后确定删除信息已经被数据处理装置#0准确接收，也就是说传输路径信息的删除操作已经完成。对应地，数据编排装置也可以删除该数据服务信息对应的传输路径信息。
在S234中，数据处理装置#0是应数据编排装置的指示删除传输路径信息，除此之外，数据处理装置#0可以定时的触发删除数据服务信息对应的传输路径信息，无需数据编排装置指示。删除完成后告知数据编排装置，数据编排装置也可以删除数据服务信息对应的传输路径信息。
在某数据服务结束后，或应数据服务请求删除某数据服务信息对应的传输路径信息，可以节约数据编排装置或数据处理装置的存储资源。
可以理解，上述S231至S234中的确认信息，可以使得数据编排装置确认数据处理装置#0是否正确接收信息(例如，配置信息、更新信息、读取信息或删除信息)，以及是否完成了该信息的指令操作，避免数据编排装置不知道该信息是否已经被数据处理装置#0正确接收，以及是否完成了该信息的指令操作导致重新发送该信息，造成通信资源的浪费。
可选地，方法200还包括：
S240，数据处理装置#0发送统计信息，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。对应地，数据编排装置接收该统计信息。
一种可能的实施方式，该统计信息是以数据报文的传输路径信息或数据服务信息为粒度统计得到的。
示例#1，包括统计信息的统计报文的格式如下表2：
表2
标识 统计模式 统计值 时间戳
DP_ID 0 001 nPacket 时间#1
在该示例中，标识DP_ID 0用于标识该统计信息是以传输路径信息为粒度统计报文数，该统计报文中的统计值为对应DP_ID 0(可以理解为传输路径信息#0对应的数据管道标识)的数据报文的数量，时间#1为统计该统计信息的时间，或者封装该统计报文的时间，本申请对此不做限制，后文中的时间戳也按此理解，在后文不再赘述。
统计值：
Figure PCTCN2022116833-appb-000002
其中，nPacket(Dp i)表示对应DP_ID i的数据报文的数量(i＝0)，nPacket(DS j)表示对应DP_ID 0的某数据服务的数据报文的数量，m表示DP_ID 0对应的数据服务的数量。
示例#2，包括统计信息的统计报文的格式如下表3：
表3
标识 统计模式 统计值 时间戳
DP_ID 0 011 nByte 时间#2
在该示例中，标识DP_ID 0用于标识该统计信息是以传输路径信息为粒度统计字节数，该统计报文中的统计值为对应DP_ID 0的字节数。
统计值：
Figure PCTCN2022116833-appb-000003
其中，nByte(DP i)表示对应DP_ID i的数据报文的字节数量(i＝0)，nByte(DS j)表示对应DP_ID 0的某数据服务的字节数，m表示DP_ID 0对应的数据服务的数量。
示例#3，包括统计信息的统计报文的格式如下表4：
表4
标识 统计模式 统计值 时间戳
DS_ID 0 000 nPacket 时间#3
在该示例中，标识DS_ID 0用于标识该统计信息是以数据服务信息为粒度统计报文数，该统计报文中的统计值为对应DS_ID 0的数据报文的数量。
统计值：
Figure PCTCN2022116833-appb-000004
其中，nPacket(DP i)表示对应DS_ID i的数据报文的数量(i＝0)，nPacket(DP j)表示对应DS_ID 0的某传输路径的数据报文的数量，m表示DS_ID 0对应的传输路径的数量。
示例#4，包括统计信息的统计报文的格式如下表5：
表5
标识 统计模式 统计值 时间戳
DS_ID 0 010 nByte 时间#4
在该示例中，标识DS_ID 0用于标识该统计信息是以数据服务信息为粒度统计字节数，该统计报文中的统计值为对应DS_ID 0的字节数。
统计值：
Figure PCTCN2022116833-appb-000005
其中，nByte(DP i)表示对应DS_ID i的数据报文的字节数量(i＝0)，nByte(DP j)表示对应DS_ID 0的某传输路径的字节数，m表示DS_ID 0对应的传输路径的数量。
示例#5，统计信息还可以按照DS|DP为粒度统计上报，适用于一个数据服务对应多个传输路径(不同传输路径以数据管道标识即DP_ID区分)，或者一个传输路径对应多个数据服务的场景。例如，DS_ID 0对应DP_ID 0、DP_ID 1和DP_ID 2。nPacket(DS i,DP j)＝ nPacket(DS i|DP j)，nByte(DS i,DP j)＝nByte(DS i|DP j)，例如nPacket(DS 0,DP 0)＝nPacket(DS 0|DP 0)，nByte(DS 0,DP 0)＝nByte(DS 0|DP 0)。其中，nPacket(DS 0|DP 0)表示数据服务标识为DS_ID 0，且数据管道标识为DP_ID 0的数据报文的数量，nByte(DS 0|DP 0)表示数据服务标识为DS_ID 0，且数据管道标识为DP_ID 0的数据报文的字节数量。
可以理解，统计信息的上报可以是定时触发的，即数据处理装置#0可以定时向数据编排装置上报统计信息，或者数据编排装置向数据处理装置#0发送请求，数据处理装置#0应请求统计上报统计信息。本申请对此不做限制。
还可以理解，上述表2至表5仅为示例，表2至表5可以有其他变换。例如，表2至表5的格式、行或列中内容的顺序的变换，或者表2至表5可以包括上述示例表中的部分内容，或者表2至表5可以在上述示例表中内容的基础上包括更多的内容，本申请对此不做限制。
数据处理装置向数据编排装置发送统计信息，可以使得数据编排装置知晓流经数据处理装置的数据报文/字节数量的情况，便于数据编排装置统筹后续是否继续给数据处理装置分配数据报文让其处理。假设统计信息是以传输路径信息为粒度统计得到，则数据编排装置可以确定流经数据处理装置的每条传输路径上的数据报文/字节数量的情况，假设统计信息是以数据服务信息为粒度统计得到，则数据编排装置可以确定数据处理装置处理的不同数据服务的数据报文/字节数量的情况，为数据编排装置后续统筹分配数据报文的处理提供参考。
可选地，方法200还包括：
S241，数据处理装置#1发送统计信息，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。对应地，数据编排装置接收该统计信息。
与S240类似，具体内容可参见S240中相关描述，不再赘述。
可以理解，方法200中，数据处理装置#0对应发明内容中的第一装置，数据处理装置#1对应发明内容中的第二装置，数据编排装置对应发明内容中的第三装置。
通过本申请提供的方法200，数据处理装置#0获取业务数据后，可以基于数据服务信息确定传输路径信息，继而确定业务数据的下一个处理节点，并将处理后的业务数据和该传输路径信息封装为数据报文传输至下一个处理节点。后续数据处理装置#1可以基于该传输路径信息确定数据报文在数据处理装置#1后的下一个处理节点。也就是说，本方案使得数据报文在传输的过程中，可以实现其他节点对数据报文的处理，能够满足通信感知计算融合趋势下对数据的分布式处理的需求并提高数据的使用效率。
图3是本申请实施例提供的另一种数据报文的传输方法的流程交互图。图3所示的方法300包括：
S310，数据处理装置#1获取数据报文#A，该第一数据报文包括传输路径信息#A(对应发明内容中的第一传输路径信息)，传输路径信息#A包括数据处理装置#1的信息和数据处理装置#2的信息，数据处理装置#2是数据处理装置#1的下一个处理节点。
示例地，数据处理装置为数据报文的中间或最终的处理节点，数据报文#A可以是从图2所示的数据处理装置#0发送的，传输路径信息#A是数据处理装置#0封装到数据报文#A中的。
S320，数据处理装置#1基于传输路径信息#A确定数据处理装置#2。
示例地，传输路径信息#A为(DA_ID 3,DA_ID 5)，其中，DA_ID 3为数据处理装置#1的标识，DA_ID 5为数据处理装置#2的标识，数据处理装置#1基于(DA_ID 3,DA_ID5)确定数据处理装置#2。
可以理解，数据处理装置#1和数据处理装置#2的标识可以是数据编排装置配置的。
示例地，传输路径信息#A为(Add3,Add5)，其中，Add 3为数据处理装置#1的地址，Add5为数据处理装置#2的地址，数据处理装置#1基于(Add3,Add5)确定数据处理装置#2。
可以理解，数据处理装置#1和数据处理装置#2的地址可以是复用的底层网络中地址，本申请对此不做限制。
S330，数据处理装置#1发送数据报文#B，该数据报文#B包括传输路径信息#B(对应发明内容中的第二传输路径信息)，且该数据报文#B中的数据载荷基于数据报文#A中的数据载荷处理得到。对应地，数据处理装置#2接收该数据报文#B。
可选地，数据报文#A、数据报文#B还包括数据服务标识(例如DS_ID 1)。
可选地，数据报文#A、数据报文#B还包括统计模式信息，统计模式信息用于指示统计信息的统计模式，统计信息包括数据报文的数量信息或者数据报文的字节数量信息，或者统计信息包括其他的数量信息，本申请对此不做限制。
可以理解，如果数据处理装置#2为数据报文的最终处理节点，则数据处理装置#2对数据报文#B中的数据载荷处理后，该数据报文的传输和处理过程结束。如果数据处理装置#2不是数据报文的最终处理节点，传输路径信息#A中还包括数据处理装置#2的下一个处理节点的信息，数据处理装置#2对数据报文#B中的数据载荷处理后，可以根据传输路径信息#A确定数据处理装置#2的下一个处理节点，从而将处理后的数据报文#B传输至下一个处理节点让其处理。
一种可能的实施方式，传输路径信息#B中不包括数据处理装置#1的信息。
可以理解，数据报文#B发出去后，数据处理装置#1的操作已经完成，数据处理装置#1在封装数据报文#B时，可将传输路径信息#B封装至数据报文#B的报头，传输路径信息#B即为删去数据处理装置#1的信息的传输路径信息#A。同样地，数据处理装置#2后的数据处理装置基于传输路径信息传输数据报文时，发出去的数据报文中可以不包含自身的信息。
另外，若数据处理装置#1根据传输路径信息确定下一个处理节点为多个数据处理装置#2时，可参考S230中相关描述，确定多个数据处理装置#2，并向多个数据处理装置#2发送数据报文，具体内容不再赘述。
可选地，方法300还包括：
S340，数据处理装置#1发送统计信息，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。对应地，数据编排装置接收该统计信息。
与S241类似，具体内容可参见S241中相关描述，不再赘述。
可选地，方法300还包括：
S341，数据处理装置#2发送统计信息，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。对应地，数据编排装置接收该统计信息。
与S241类似，具体内容可参见S241中相关描述，不再赘述。
方法200和方法300可以结合使用，方法300中没有具体描述的内容可参考方法200中的相关描述，为简洁，不再赘述。
通过本申请提供的方法300，数据处理装置#1(即数据报文的中间处理节点)接收到数据报文后，可以基于数据报文中的传输路径信息确定数据报文的下一个处理节点，并将处理后的数据报文和传输路径信息封装为数据报文传输至下一个处理节点。本方案使得数据报文在传输的过程中，可以实现数据处理装置对数据报文的处理，能够满足通信感知计算融合趋势下对数据的分布式处理的需求，可以提高数据的使用效率。
可以理解，方法300中与方法200相似的步骤或实施方式的有益效果可以参考方法200中相关内容的描述，在此不再赘述。
还可以理解，方法300中，数据处理装置#1对应发明内容中的第一装置，数据处理装置#2对应发明内容中的第二装置，数据编排装置对应发明内容中的第三装置。
方法200和300介绍了一种数据报文的转发机制，在该转发机制中，数据处理装置#0有状态(例如，本地会存一些数据编排装置配置的转发信息(即传输路径信息))，数据处理装置#1则是无状态(例如，本地不保存由数据编排装置配置的转发信息)，即转发数据报文的时候依据数据报文中的传输路径信息确定数据报文的下一个处理节点，从而传输数据报文。因此数据处理装置#1本地可以不存数据服务信息和传输路径信息之间的对应关系。如果数据处理装置#0和数据处理装置#1在转发数据报文的时候还有其他的转发机制。则数据处理装置#0和数据处理装置#1可以通过以下方法选择转发机制。
一种可能的实施方式，数据处理装置#0的转发机制可以由配置确定，配置可以基于数据处理装置#0的能力等信息确定。
示例地，若数据处理装置#0本地配置了数据服务信息和传输路径信息的对应关系，即数据处理装置#0有状态，则数据处理装置#0可以基于方法200传输数据报文。若数据处理装置#0本地没有配置数据服务信息和传输路径信息的对应关系，即数据处理装置#0无状态，则数据处理装置#0可以基于除了方法200之外的其他转发机制传输数据报文，本申请对此不做限制。
一种可能的实施方式，数据处理装置#1或数据处理装置#2可以通过自身的状态和转发的数据报文的状态选择合适的转发机制。
示例地，数据处理装置#1为无状态，数据报文中包括状态字段，该状态字段被设置为有状态，则数据处理装置#1选择方法300提供的转发机制转发该数据报文。如果数据处理装置#1为有状态，数据报文中包括的状态字段被设置为无状态；或者数据处理装置#1为有状态，数据报文中包括的状态字段被设置为有状态，或者数据处理装置#1为无状态，数据报文中包括的状态字段被设置为无状态，则数据处理装置#1可以选择除了方法300之外的其他的转发机制转发数据报文，本申请对此不做限制。
可以理解，数据报文有状态即数据报文中带有转发信息(例如传输路径信息)，这样数据报文途径的数据处理装置就可以不用保存转发信息。数据报文无状态即数据报文中没有携带转发信息(例如传输路径信息)，这样数据报文途径的数据处理装置就需要保存转发信息。
数据处理装置可以按需选择合适的转发机制，提高数据报文传输的灵活性和/或效率。
下面以系统的角度描述方法200中提及的一些特殊场景中数据编排装置如何配置数 据服务信息对应的传输路径信息，以及数据处理装置如何基于传输路径信息传输数据报文。
图4是本申请实施例提供的用于数据汇聚场景的示意图。
在图4中，数据编排装置以DO示例，数据处理装置以DA示例，数据处理装置的信息以DA的标识示例，以一个数据服务信息对应3个传输路径信息为例展开介绍，本申请并不限于此。
DO基于某数据服务信息，例如表示数据汇聚的DS_ID 3，以及各处理节点的能力/功能确定DS_ID 3对应的3条传输路径，即传输路径#A1、传输路径#B1和传输路径#C1，其中传输路径#A1为DA#4→DA#3→DA#13，传输路径#B1为DA#7→DA#11→DA#13，传输路径#C1为DA#17→DA#19→DA#13。
DO向DA#4(对应上文中的数据处理装置#0)发送对应关系信息1，对应关系信息1指示DS_ID 3与传输路径信息#A1的对应关系，传输路径信息#A1为(DA_ID 3,DA_ID 13)；DO向DA#7(对应上文中的数据处理装置#0)发送对应关系信息2，对应关系信息2指示DS_ID 3与传输路径信息#B1的对应关系，传输路径信息#B1为(DA_ID 11,DA_ID 13)；DO向DA#17(对应上文中的数据处理装置#0)发送对应关系信息3，对应关系信息3指示DS_ID 3与传输路径信息#C1的对应关系，传输路径信息#C1为(DA_ID 19,DA_ID 13)。
例如，DA#4用于收集区域#1在一段时间内不同时间的温度，DA#7用于收集区域#2在一段时间内不同时间的温度，DA#17用于收集区域#3在一段时间内不同时间的温度。
DA#4收集好区域#1在一段时间内不同时间的温度后，将收集的温度封装到数据报文#A1中，数据报文#A1的报头中包括(DA_ID 3,DA_ID 13)，其中，DA_ID 3为DA#3的标识，DA_ID 13为DA#13的标识。DA#4向DA#3(对应上文中的数据处理装置#1)发送数据报文#A1，DA#3接收到数据报文#A1后，对数据报文#A1中的数据(即温度)进行处理，例如处理为区域#1的平均温度#1，并根据(DA_ID 3,DA_ID 13)确定下一个处理节点，即DA#13。DA#3向DA#13发送数据报文#A2，数据报文#A2包括区域#1的平均温度#1和DA_ID 13。
DA#7收集好区域#2在一段时间内不同时间的温度后，将收集的温度封装到数据报文#B1中，数据报文#B1的报头中包括(DA_ID 11,DA_ID 13)，其中，DA_ID 11为DA#11的标识。DA#7向DA#11(对应上文中的数据处理装置#1)发送数据报文#B1，DA#11接收到数据报文#B1后，对数据报文#B1中的数据(即温度)进行处理，例如处理为区域#2的平均温度#2，并根据(DA_ID 11,DA_ID 13)确定下一个处理节点，即DA#13。DA#11向DA#13发送数据报文#B2，数据报文#B2包括区域#2的平均温度#2和DA_ID 13。
DA#17收集好区域#3在一段时间内不同时间的温度后，将收集的温度封装到数据报文#C1中，数据报文#C1的报头中包括(DA_ID 19,DA_ID 13)，其中，DA_ID 19为DA#19的标识。DA#17向DA#19(对应上文中的数据处理装置#1)发送数据报文#C1，DA#19接收到数据报文#C1后，对数据报文#C1中的数据(即温度)进行处理，例如处理为区域#3的平均温度#3，并根据(DA_ID 19,DA_ID 13)确定下一个处理节点，即DA#13。DA#19向DA#13发送数据报文#C2，数据报文#C2包括区域#3的平均温度#3和DA_ID 13。
DA#13接收到数据报文#A2、数据报文#B2和数据报文#C2后，将报文中的平均温度#1、平均温度#2和平均温度#3处理为区域#1、区域#2和区域#3的平均温度#4，则平均温度#4即为该数据汇聚服务的处理结果。并且DA#13根据数据报文#A2、数据报文#A2和 数据报文#A2中的DA_ID 13可知没有下一个处理节点，即无需向其他装置发送该平均温度#4。至此该数据汇聚服务处理结束。
图5是本申请实施例提供的用于数据汇聚和数据分发场景的示意图。
在图5中，数据编排装置以DO示例，数据处理装置以DA示例，数据处理装置的信息以DA的标识示例，以一个数据服务信息对应3个传输路径信息为例展开介绍，本申请并不限于此。
DO基于某数据服务信息，例如表示联邦学习的DS_ID 1，以及各处理节点的能力/功能确定DS_ID 1对应的3条传输路径，即传输路径#A2、传输路径#B2和传输路径#C2。其中传输路径#A2对应的数据报文的传输路径为DA#5(对应DA_ID：5)→DA#3(对应DA_ID：3)→DA#7(对应DA_ID：7)，传输路径#B2对应的数据报文的传输路径为DA#13(对应DA_ID：13)→DA#11(对应DA_ID：11)→DA#7，传输路径#C2对应的数据报文的传输路径为DA#23(对应DA_ID：23)→DA#19(对应DA_ID：19)→DA#7。
图5的示例中，假设DA#5、DA#13、DA#23为联邦学习的客户端，基于本地获取的业务数据进行本地模型训练，然后把训练好的本地模型参数处理为数据载荷，并将其和传输路径信息封装至数据报文中发送至DA#3、DA#11、DA#19。DA#3、DA#11、DA#19可以将接收到的数据报文中的数据载荷(对应本地模型参数)进行模型压缩，将压缩后的模型参数以及传输路径信息封装至数据报文中发送至DA#7。DA#7对收到的压缩模型参数进行聚合，聚合后DA#7需要将聚合得到的全局模型参数分发给客户端DA#5、DA#13、DA#23。
具体地，DO计算确定联邦学习的路径后如何将对应关系信息#1、对应关系信息#2和对应关系信息#3发送至DA#5、DA#13、DA#23。对应关系信息#1、对应关系信息#2和对应关系信息#3包括的具体内容，以及DA#5、DA#13、DA#23如何基于对应关系信息#1、对应关系信息#2和对应关系信息#3传输数据报文，数据报文中具体包括哪些内容，可参考图4描述的数据汇聚的示例，在此不再赘述。图5未示出传输路径#A2、传输路径#B2和传输路径#C2的箭头指向。下面主要介绍联邦学习中关于数据分发的相关内容。
DS_ID 1还对应3条传输路径，即传输路径#A3、传输路径#B3和传输路径#C3。传输路径#A3为DA#7→DA#3→DA#5，传输路径#B3为DA#7→DA#11→DA#13，传输路径#C3为DA#7→DA#19→DA#23。
DO向DA#7发送对应关系信息#4，该对应关系信息#4为DS_ID 1：(DA_ID 3,DA_ID5)|(DA_ID 11,DA_ID 13)|(DA_ID 19,DA_ID 23)。也就是说该对应关系信息#4指示：DS_ID 1与传输路径信息#A3的对应关系，DS_ID 1与传输路径信息#B3的对应关系，DS_ID 1与传输路径信息#C3的对应关系。其中，传输路径信息#A3为(DA_ID 3,DA_ID5)，传输路径信息#B3为(DA_ID 11,DA_ID 13)，传输路径信息#C3为(DA_ID 19,DA_ID23)。
例如，DA#7(对应上文中的数据处理装置#0)用于将聚合得到的全局模型参数分发给客户端，若DA#7将全局模型参数分为全局子模型参数#1、全局子模型参数#2和全局子模型参数#3，向DA#3(对应上文中的数据处理装置#1)发送数据报文#a1，数据报文#a1包括全局子模型参数#1对应的数据载荷以及(DA_ID 3,DA_ID 5)。DA#7向DA#11(对应上文中的数据处理装置#1)发送数据报文#b1，数据报文#b1包括全局子模型参数#2对 应的数据载荷以及(DA_ID 11,DA_ID 13)。DA#7向DA#19(对应上文中的数据处理装置#1)发送数据报文#c1，数据报文#c1包括全局子模型参数#3对应的数据载荷以及(DA_ID19,DA_ID 23)。
DA#3接收到数据报文#a1后，对数据报文#a1中全局子模型参数#1对应的数据载荷进行处理，例如解压全局子模型参数#1对应的数据载荷，并根据(DA_ID 3,DA_ID 5)确定下一个处理节点，即DA#5，向DA#5发送数据报文#a2，数据报文#a2包括解压后的全局子模型参数#1对应的数据载荷和DA_ID 5。
DA#11接收到数据报文#b1后，对数据报文#b1中全局子模型参数#2对应的数据载荷进行处理，例如解压全局子模型参数#2对应的数据载荷，并根据(DA_ID 11,DA_ID 13)确定下一个处理节点，即DA#13，向DA#13发送数据报文#b2，数据报文#b2包括解压后的全局子模型参数#2对应的数据载荷和DA_ID 13。
DA#19接收到数据报文#c1后，对数据报文#c1中全局子模型参数#3对应的数据载荷进行处理，例如解压全局子模型参数#3对应的数据载荷，并根据(DA_ID 19,DA_ID 23)确定下一个处理节点，即DA#23，向DA#23发送数据报文#c2，数据报文#c2包括解压后的全局子模型参数#3对应的数据载荷和DA_ID 23。
可以理解，联邦学习过程中，上述数据汇聚和数据分发的过程可以有多次，直至全局模型训练完成。
上述流程图中虚线步骤为可选地步骤，且各步骤的先后顺序依照方法的内在逻辑确定，上述流程图中所示的序号仅为示例，不对本申请步骤的先后顺序造成限制。
还应理解，本申请实施例提供的方法可以单独使用，也可以结合使用，本申请对此不做限制。本申请实施例提供的各种实施方式可以单独使用，也可以结合使用，本申请对此不做限制。本申请实施例提供的各种示例可以单独使用，也可以结合使用，本申请对此不做限制。
应理解，本申请中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况，其中A，B可以是单数或者复数。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系，但也可能表示的是一种“和/或”的关系，具体可参考前后文进行理解。
本申请实施例中，若无特殊说明，多个指两个或两个以上。
本申请实施例中，“至少一项(个)“是指一项(个)或者多项(个)，“至少两项(个)“以及“多项(个)”是指两项(个)或两项(个)以上。“以下至少一项(个)”或其类似表达，是指的这些项中的任意组合，包括单项(个)或复数项(个)的任意组合。例如，a,b,或c中的至少一项(个)，可以表示：a,b,c,a-b,a-c,b-c,或a-b-c，其中a,b,c可以是单个，也可以是多个。
需注意的是，图2、3中示意的执行主体仅为示例，该执行主体也可以是支持该执行主体实现图2、3所示方法的芯片、芯片系统、或处理器，本申请对此不作限制。
上文结合附图描述了本申请实施例的方法实施例，下面描述本申请实施例的装置实施例。可以理解，方法实施例的描述与装置实施例的描述可以相互对应，因此，未描述的部分可以参见前面方法实施例。
可以理解的是，上述各个方法实施例中，由数据处理装置#0实现的方法和操作，也可以由数据处理装置#0中的部件(例如芯片或者电路)实现，由数据处理装置#1实现的方法和操作，也可以由数据处理装置#1中的部件(例如芯片或者电路)实现。由数据编排装置实现的方法和操作，也可以由数据编排装置中的部件(例如芯片或者电路)实现。
上述主要从各个装置之间交互的角度对本申请实施例提供的方案进行了介绍。可以理解的是，各个装置，例如发射端设备或者接收端设备，为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，本申请能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
本申请实施例可以根据上述方法示例对发射端设备或者接收端设备进行功能模块的划分，例如，可以对应各个功能划分各个功能模块，也可以将两个或两个以上的功能集成在一个处理模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。需要说明的是，本申请实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。下面以采用对应各个功能划分各个功能模块为例进行说明。
图6是本申请实施例提供的通信装置的示意性框图。图6所示的通信装置600包括收发单元610和处理单元620。收发单元610可以与外部进行通信，处理单元620用于进行数据处理。收发单元610还可以称为通信接口或通信单元。
可选的，收发单元610可以包括发送单元和接收单元。发送单元用于执行上述方法实施例中的发送操作。接收单元用于执行上述方法实施例中的接收操作。
需要说明的是，通信装置600可以包括发送单元，而不包括接收单元。或者，通信装置600可以包括接收单元，而不包括发送单元。具体可以视通信装置600执行的上述方案中是否包括发送动作和接收动作。
可选地，该通信装置600还可以包括存储单元，该存储单元可以用于存储指令或者和/或数据，处理单元620可以读取存储单元中的指令或者和/或数据。
在一种设计中，通信装置600可以用于执行上文方法实施例中数据处理装置#1所执行的动作。数据处理装置#1可以是网络中的功能网元，也可以是终端设备、网络设备、核心网设备或操作维护管理设备中的芯片或电路，也可以是能实现全部或部分终端设备、网络设备、核心网设备或操作维护管理设备功能的逻辑模块或软件，本申请对此不作限定。
可选地，该通信装置600可以为数据处理装置#1，收发单元610用于执行上文方法实施例中数据处理装置#1的接收或发送的操作，处理单元620用于执行上文方法实施例中数据处理装置#1内部处理的操作。
可选地，该通信装置600可以为包括数据处理装置#1的设备。或者，该通信装置600可以为配置在数据处理装置#1中的部件，例如，数据处理装置#1中的芯片。这种情况下，收发单元610可以为接口电路、管脚等。具体地，接口电路可以包括输入电路和输出电路，处理单元620可以包括处理电路。
一种可能的实现方式中，该收发单元610用于获取第一数据报文，该第一数据报文包 括第一传输路径信息，第一传输路径信息包括数据处理装置#1和数据处理装置#2的信息，处理单元620用于基于该第一传输路径信息确定数据处理装置#2，该收发单元610用于向数据处理装置#2发送第二数据报文，该第二数据报文包括第二传输路径信息，且该第二数据报文中的数据载荷基于第一数据报文中的数据载荷处理得到。
一种可能的实现方式中，上述第二传输路径信息中不包括所述数据处理装置#1的信息。
一种可能的实现方式中，第一传输路径信息包括第一装置和第二装置的标识信息，或者第一传输路径信息包括第一装置和第二装置的地址信息。
一种可能的实现方式中，第一数据报文和第二数据报文还包括数据服务信息和/或统计模式信息，该统计模式信息用于指示统计信息的统计模式，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
一种可能的实现方式中，该收发单元还用于向数据编排装置发送统计信息，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
一种可能的实现方式中，该统计信息是以数据报文的传输路径信息或数据服务信息为粒度统计得到的。
一种可能的实现方式中，数据服务信息为以下任一项：联邦学习服务的标识，分布式学习服务的标识，或数据汇聚服务的标识。
在另一种设计中，通信装置600可以用于执行上文方法实施例中数据处理装置#0所执行的动作。数据处理装置#0可以是网络中的功能网元，也可以是终端设备、网络设备、核心网设备或操作维护管理设备中的芯片或电路，也可以是能实现全部或部分终端设备、网络设备、核心网设备或操作维护管理设备功能的逻辑模块或软件，本申请对此不作限定。
可选地，该通信装置600可以为数据处理装置#0，收发单元610用于执行上文方法实施例中数据处理装置#0的接收或发送的操作，处理单元620用于执行上文方法实施例中数据处理装置#0内部处理的操作。
可选地，该通信装置600可以为包括数据处理装置#0的设备。或者，该通信装置600可以为配置在数据处理装置#0中的部件，例如，数据处理装置#0中的芯片。这种情况下，收发单元610可以为接口电路、管脚等。具体地，接口电路可以包括输入电路和输出电路，处理单元620可以包括处理电路。
一种可能的实现方式中，该收发单元610用于获取业务数据，该处理单元620用于基于数据服务信息确定第三传输路径信息，该第三传输路径信息包括数据处理装置#1的信息，数据处理装置#1为第三数据报文的处理节点，该收发单元610还用于向数据处理装置#1发送第三数据报文，该第三数据报文包括第三传输路径信息和该业务数据对应的数据载荷。
一种可能的实现方式中，第三传输路径信息包括第二装置的标识信息或地址信息。
一种可能的实现方式中，该收发单元610还用于接收来自数据编排装置的对应关系信息，该对应关系信息指示该数据服务信息和传输路径信息的对应关系，该处理单元620用于基于数据服务信息和该对应关系信息确定第三传输路径信息。
一种可能的实现方式中，该数据服务信息包括第一数据服务信息，第一数据服务信息对应N个传输路径信息，N个传输路径信息包括第三传输路径信息，N为大于或等于1 的整数。
一种可能的实现方式中，该对应关系信息指示的对应关系包括该第一数据服务信息和N个传输路径信息的对应关系，N为大于1的整数，该收发单元610还用于向N个数据处理装置#1发送N个数据报文，其中，每个数据处理装置#1关联一个数据报文，一个数据报文包括该N个传输路径信息中的一个传输路径信息。
一种可能的实现方式中，该N个传输路径信息包括并列的数据处理装置的信息，并列的数据处理装置为数据报文的同一级处理节点，N为大于1的整数。
一种可能的实现方式中，该对应关系信息指示的对应关系包括第一数据服务信息和第三传输路径信息的对应关系，该实现方式中N为大于1的整数。
一种可能的实现方式中，该第三传输路径信息包括按序排列的数据处理装置的信息，排列靠前的数据处理装置处理数据报文的顺序靠前。
一种可能的实现方式中，该收发单元还用于接收来自数据编排装置的配置信息，该配置信息用于配置以下至少一项：数据报文的统计模式、数据报文的统计周期、该传输路径信息的有效时间。
一种可能的实现方式中，该收发单元610还用于接收来自数据编排装置的更新信息，该更新信息用于更新该数据服务信息对应的传输路径信息。
一种可能的实现方式中，该收发单元610还用于接收来自数据编排装置的读取信息，该读取信息用于读取该数据服务信息对应的传输路径信息。
一种可能的实现方式中，该收发单元610还用于接收来自数据编排装置的删除信息，该删除信息用于删除该数据服务信息对应的传输路径信息。
一种可能的实现方式中，该第三数据报文还包括数据服务信息和/或统计模式信息，该统计模式信息用于指示统计信息的统计模式，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
一种可能的实现方式中，该收发单元610还用于向数据编排装置发送统计信息，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
一种可能的实现方式中，该统计信息是以数据报文的传输路径信息或数据服务信息为粒度统计得到的。
一种可能的实现方式中，数据服务信息为以下任一项：联邦学习服务的标识，分布式学习服务的标识，或数据汇聚服务的标识。
在又一种设计中，图6所示的通信装置600可以用于执行上文方法实施例中数据编排装置所执行的动作。
可选地，该通信装置600可以为数据编排装置，收发单元610用于执行上文方法实施例中数据编排装置的接收或发送的操作，处理单元620用于执行上文方法实施例中数据编排装置内部处理的操作，数据编排装置可以是网络中的功能网元，也可以是网络设备、核心网设备中的芯片或电路，也可以是能实现全部或部分网络设备、核心网设备功能的逻辑模块或软件，本申请对此不作限定。
可选地，该通信装置600可以为包括数据编排装置的设备。或者，该通信装置600可以为配置在数据编排装置中的部件，例如，数据编排装置中的芯片。这种情况下，收发单元610可以为接口电路、管脚等。具体地，接口电路可以包括输入电路和输出电路，处理 单元620可以包括处理电路。
一种可能的实现方式中，处理单元620用于生成对应关系信息，对应关系信息指示数据服务信息和数据报文的传输路径信息的对应关系，收发单元用于向数据处理装置#0发送对应关系信息。
一种可能的实现方式中，该传输路径信息包括数据处理装置#1的信息，所述数据处理装置#1为数据报文的处理节点。
一种可能的实现方式中，该传输路径信息包括数据处理装置#1的标识信息或地址信息。
一种可能的实现方式中，该数据服务信息包括第一数据服务信息，第一数据服务信息对应N个传输路径信息，N为大于或等于1的整数。
一种可能的实现方式中，该对应关系信息指示的对应关系包括该第一数据服务信息和N个传输路径信息的对应关系，N为大于1的整数。
一种可能的实现方式中，该N个传输路径信息包括并列的数据处理装置的信息，并列的数据处理装置为数据报文的同一级处理节点，N为大于1的整数。
一种可能的实现方式中，该收发单元还用于向N个数据处理装置#0发送N个对应关系信息，其中，每个数据处理装置#0关联一个对应关系信息，该一个对应关系信息指示该第一数据服务信息和该N个传输路径信息中的一个传输路径信息的对应关系，N为大于1的整数。
一种可能的实现方式中，该N个传输路径信息中的每个传输路径信息包括按序排列的数据处理装置的信息，排列靠前的数据处理装置处理数据报文的顺序靠前，N为大于1的整数。
一种可能的实现方式中，该收发单元610还用于向数据处理装置#0发送配置信息，该配置信息用于配置以下至少一项：数据报文的统计模式、数据报文的统计周期、该传输路径信息的有效时间。
一种可能的实现方式中，该收发单元610还用于向数据处理装置#0发送更新信息，该更新信息用于更新该数据服务信息对应的传输路径信息。
一种可能的实现方式中，该收发单元610还用于向数据处理装置#0发送读取信息，该读取信息用于读取该数据服务信息对应的传输路径信息。
一种可能的实现方式中，该收发单元610还用于向数据处理装置#0发送删除信息，该删除信息用于删除该数据服务信息对应的传输路径信息。
一种可能的实现方式中，该收发单元610还用于接收来自数据处理装置#0的统计信息，该统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
一种可能的实现方式中，该统计信息是以传输路径信息或数据服务信息为粒度统计得到的。
一种可能的实现方式中，数据服务信息为以下任一项：联邦学习服务的标识，分布式学习服务的标识，或数据汇聚服务的标识。
如图7所示，本申请实施例还提供一种通信装置700。该通信装置700包括处理器710，处理器710与存储器720耦合，存储器720用于存储计算机程序或指令或者和/或数据，处理器710用于执行存储器720存储的计算机程序或指令和/或者数据，使得上文方法实 施例中的方法被执行。
可选地，该通信装置700包括的处理器710为一个或多个。
可选地，如图7所示，该通信装置700还可以包括存储器720。
可选地，该通信装置700包括的存储器720可以为一个或多个。
可选地，该存储器720可以与该处理器710集成在一起，或者分离设置。
可选地，如图7所示，该通信装置700还可以包括收发器730和/或通信接口，收发器730和/或通信接口用于信号的接收和/或发送。例如，处理器710用于控制收发器730和/或通信接口进行信号的接收和/或发送。
可选地，可以将收发器730中用于实现接收功能的器件视为接收模块，将收发器730中用于实现发送功能的器件视为发送模块，即收发器730包括接收器和发送器。收发器有时也可以称为收发机、收发模块、或收发电路等。接收器有时也可以称为接收机、接收模块、或接收电路等。发送器有时也可以称为发射机、发射器、发射模块或者发射电路等。
作为一种方案，该通信装置700用于实现上文方法实施例中由数据处理装置#0执行的操作。例如，处理器710用于实现上文方法实施例中由数据处理装置#0内部执行的操作(例如S210、S220的操作)，收发器730用于实现上文方法实施例中由数据处理装置#0执行的接收或发送的操作(例如S201、S230、S231、S232、S233、S234、S240的操作)。
作为另一种方案，该通信装置700用于实现上文方法实施例中由数据处理装置#1执行的操作。例如，处理器710用于实现上文方法实施例中由数据处理装置#1内部执行的操作(例如S310、S320的操作)，收发器730用于实现上文方法实施例中由数据处理装置#1执行的接收或发送的操作(例如S230、S241、S330、S340的操作)。
作为另一种方案，该通信装置700用于实现上文方法实施例中由数据编排装置执行的操作。例如，处理器710用于实现上文方法实施例中由数据编排装置内部执行的操作，收发器730用于实现上文方法实施例中由数据编排装置执行的接收或发送的操作(例如S201、S231、S232、S233、S234、S240、S241、S340、S341的操作)。
如图8，本申请实施例还提供了一种通信装置800。该通信装置800包括逻辑电路810以及输入/输出接口(input/output interface)820。
其中，逻辑电路810可以为通信装置800中的处理电路。逻辑电路810可以耦合连接存储单元，调用存储单元中的指令，使得通信装置800可以实现本申请各实施例的方法和功能。输入/输出接口820，可以为通信装置800中的输入输出电路，将通信装置800处理好的信息输出，或将待处理的数据或信令信息输入通信装置800进行处理。
作为一种方案，该通信装置800用于实现上文各个方法实施例中由数据处理装置#0执行的操作。
例如，逻辑电路810用于实现上文方法实施例中由数据处理装置#0执行的处理相关的操作，如，S210、S220中数据处理装置#0的处理操作。输入/输出接口820用于实现上文方法实施例中由数据处理装置#0执行的发送和/或接收相关的操作，如S201、S230、S231、S232、S233、S234、S240中数据处理装置#0的收发操作。逻辑电路810执行的操作具体可以参见上文对处理单元620的说明，输入/输出接口820执行的操作可以参见上文对收发单元610的说明，这里不再赘述。
作为另一种方案，该通信装置800用于实现上文各个方法实施例中由数据处理装置#1 执行的操作。
例如，逻辑电路810用于实现上文方法实施例中由数据处理装置#1执行的处理相关的操作，如，S310、S320中数据处理装置#1的处理操作。输入/输出接口820用于实现上文方法实施例中由数据处理装置#1执行的发送和/或接收相关的操作，如S230、S241、S330、S340中数据处理装置#1的收发操作。逻辑电路810执行的操作具体可以参见上文对处理单元620的说明，输入/输出接口820执行的操作可以参见上文对收发单元610的说明，这里不再赘述。
作为另一种方案，该通信装置800用于实现上文各个方法实施例中由数据编排装置执行的操作。
例如，逻辑电路810用于实现上文方法实施例中由数据编排装置执行的处理相关的操作，如，方法实施例中的数据编排装置执行的处理相关的操作，输入/输出接口820用于实现上文方法实施例中由数据编排装置执行的发送和/或接收相关的操作，如S201、S231、S232、S233、S234、S240、S241、S340、S341中数据编排装置的收发操作。逻辑电路810执行的操作具体可以参见上文对处理单元820的说明。逻辑电路810执行的操作具体可以参见上文对处理单元620的说明，输入/输出接口820执行的操作可以参见上文对收发单元610的说明，这里不再赘述。
应理解，上述通信装置可以是一个或多个芯片。例如，该通信装置可以是现场可编程门阵列(field programmable gate array，FPGA)，可以是专用集成芯片(application specific integrated circuit，ASIC)，还可以是系统芯片(system on chip，SoC)，还可以是中央处理器(central processor unit，CPU)，还可以是网络处理器(network processor，NP)，还可以是数字信号处理电路(digital signal processor，DSP)，还可以是微控制器(micro controller unit，MCU)，还可以是可编程控制器(programmable logic device，PLD)或其他集成芯片。
在实现过程中，上述方法的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。结合本申请实施例所公开的方法的步骤可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上述方法的步骤。为避免重复，这里不再详细描述。
应注意，本申请实施例中的处理器可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法实施例的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器可以是通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上述方法的步 骤。
可以理解，本申请实施例中的存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(read-only memory，ROM)、可编程只读存储器(programmable ROM，PROM)、可擦除可编程只读存储器(erasable PROM，EPROM)、电可擦除可编程只读存储器(electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(dynamic RAM，DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM，DR RAM)。应注意，本文描述的系统和方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
根据本申请实施例提供的方法，本申请还提供一种计算机可读介质，该计算机可读介质存储有程序代码，当该程序代码在计算机上运行时，使得该计算机执行方法实施例所示的方法。例如，该计算机程序被计算机执行时，使得该计算机可以实现上述方法实施例中由数据编排装置执行的方法，或由数据处理装置执行的方法。
本申请实施例还提供一种包含指令的计算机程序产品，该指令被计算机执行时使得该计算机实现上述方法实施例中由数据编排装置执行的方法，或由数据处理装置执行的方法。
本申请实施例还提供一种通信系统，包括数据编排装置和数据处理装置。
上述提供的任一种通信装置中相关内容的解释及有益效果均可参考上文提供的对应的方法实施例，此处不再赘述。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机指令时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，高密度数字视频光盘(digital video disc，DVD))、或者半导体介质(例如，固态硬盘(solid state drive，SSD))等。
上述各个装置实施例中的数据编排装置，数据处理装置与方法实施例中的数据编排装置，数据处理装置对应，由相应的模块或单元执行相应的步骤，例如通信单元(收发器)执行方法实施例中接收或发送的步骤，除发送、接收外的其它步骤可以由处理单元(处理器)执行。具体单元的功能可以参考相应的方法实施例。其中，处理器可以为一个或多个。
在本说明书中使用的术语“部件”、“模块”、“系统”等用于表示计算机相关的实体、硬件、固件、硬件和软件的组合、软件、或执行中的软件。例如，部件可以是但不限于，在处理器上运行的进程、处理器、对象、可执行文件、执行线程、程序和/或计算机。通过图示，在计算设备上运行的应用和计算设备都可以是部件。一个或多个部件可驻留在进程和/或执行线程中，部件可位于一个计算机上和/或分布在两个或更多个计算机之间。此外，这些部件可从在上面存储有各种数据结构的各种计算机可读介质执行。部件可例如根据具有一个或多个数据分组(例如来自与本地系统、分布式系统和/或网络间的另一部件交互的二个部件的数据，例如通过信号与其它系统交互的互联网)的信号通过本地和/或远程进程来通信。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(read-only memory，ROM)、随机存取存储器(random access memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (50)

  1. 一种数据报文的传输方法，其特征在于，包括：
    第一装置获取第一数据报文，所述第一数据报文包括第一传输路径信息，所述第一传输路径信息包括所述第一装置和第二装置的信息；
    所述第一装置基于所述第一传输路径信息确定所述第二装置；
    所述第一装置向所述第二装置发送第二数据报文，所述第二数据报文包括第二传输路径信息，且所述第二数据报文中的数据载荷基于所述第一数据报文中的数据载荷处理得到。
  2. 根据权利要求1所述的方法，其特征在于，所述第二传输路径信息中不包括所述第一装置的信息。
  3. 根据权利要求1或2所述的方法，其特征在于，所述第一数据报文和所述第二数据报文还包括统计模式信息，所述统计模式信息用于指示统计信息的统计模式，所述统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
  4. 根据权利要求1至3中任一项所述的方法，其特征在于，所述第一传输路径信息包括所述第一装置和所述第二装置的标识信息，或者所述第一传输路径信息包括所述第一装置和所述第二装置的地址信息。
  5. 一种数据报文的传输方法，其特征在于，包括：
    第一装置获取业务数据；
    所述第一装置基于数据服务信息确定第三传输路径信息，所述第三传输路径信息包括第二装置的信息，所述第二装置为第三数据报文的处理节点；
    所述第一装置向所述第二装置发送所述第三数据报文，所述第三数据报文包括所述第三传输路径信息和所述业务数据对应的数据载荷。
  6. 根据权利要求5所述的方法，其特征在于，所述第三传输路径信息包括所述第二装置的标识信息或地址信息。
  7. 根据权利要求5或6所述的方法，其特征在于，所述方法还包括：
    所述第一装置接收来自第三装置的对应关系信息，所述对应关系信息指示所述数据服务信息和传输路径信息的对应关系；
    所述第一装置基于数据服务信息确定第三传输路径信息，包括：
    所述第一装置基于数据服务信息和所述对应关系信息确定第三传输路径信息。
  8. 根据权利要求5至7所述的方法，其特征在于，所述数据服务信息包括第一数据服务信息，所述第一数据服务信息对应N个传输路径信息，所述N个传输路径信息包括所述第三传输路径信息，所述N为大于或等于1的整数。
  9. 根据权利要求8所述的方法，其特征在于，所述对应关系信息指示的对应关系包括所述第一数据服务信息和所述N个传输路径信息的对应关系，所述N为大于1的整数，所述第一装置向所述第二装置发送所述第三数据报文，包括：
    所述第一装置向N个第二装置发送N个数据报文，其中，每个第二装置关联一个数据报文，所述一个数据报文包括所述N个传输路径信息中的一个传输路径信息。
  10. 根据权利要求8或9所述的方法，其特征在于，所述N个传输路径信息包括并列 的数据处理装置的信息，所述并列的数据处理装置为数据报文的同一级处理节点，所述N为大于1的整数。
  11. 根据权利要求8所述的方法，其特征在于，所述对应关系信息指示的对应关系包括第一数据服务信息和所述第三传输路径信息的对应关系，所述N为大于1的整数。
  12. 根据权利要求5至11中任一项所述的方法，其特征在于，所述第三传输路径信息包括按序排列的数据处理装置的信息，排列靠前的数据处理装置处理数据报文的顺序靠前，所述N为大于1的整数。
  13. 根据权利要求5至12中任一项所述的方法，其特征在于，所述方法还包括：
    所述第一装置接收来自第三装置的配置信息，所述配置信息用于配置以下至少一项：数据报文的统计模式、数据报文的统计周期、所述第三传输路径信息的有效时间。
  14. 根据权利要求5至13中任一项所述的方法，其特征在于，所述方法还包括：
    所述第一装置接收来自第三装置的更新信息，所述更新信息用于更新所述数据服务信息对应的传输路径信息。
  15. 根据权利要求5至14中任一项所述的方法，其特征在于，所述方法还包括：
    所述第一装置接收来自第三装置的读取信息，所述读取信息用于读取所述数据服务信息对应的传输路径信息。
  16. 根据权利要求5至15中任一项所述的方法，其特征在于，所述方法还包括：
    所述第一装置接收来自第三装置的删除信息，所述删除信息用于删除所述数据服务信息对应的传输路径信息。
  17. 根据权利要求5至16中任一项所述的方法，其特征在于，所述第三数据报文还包括统计模式信息，所述统计模式信息用于指示统计信息的统计模式，所述统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
  18. 根据权利要求1至17中任一项所述的方法，其特征在于，所述方法还包括：
    所述第一装置向第三装置发送统计信息，所述统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
  19. 根据权利要求18所述的方法，其特征在于，所述统计信息是以数据报文的传输路径信息或数据服务信息为粒度统计得到的。
  20. 根据权利要求5至19中任一项所述的方法，其特征在于，所述数据服务信息为以下任一项：联邦学习服务的标识，分布式学习服务的标识，或数据汇聚服务的标识。
  21. 一种数据报文的传输方法，其特征在于，包括：
    第三装置生成对应关系信息，所述对应关系信息指示数据服务信息和数据报文的传输路径信息的对应关系；
    所述第三装置向第一装置发送对应关系信息，所述对应关系信息指示所述对应关系。
  22. 根据权利要求21所述的方法，其特征在于，所述传输路径信息包括第二装置的信息，所述第二装置为数据报文的处理节点。
  23. 根据权利要求21或22所述的方法，其特征在于，所述传输路径信息包括所述第二装置的标识信息或所述第二装置的地址信息。
  24. 根据权利要求21至23中任一项所述的方法，其特征在于，所述数据服务信息包括第一数据服务信息，所述第一数据服务信息对应N个传输路径信息，所述N为大于或 等于1的整数。
  25. 根据权利要求24所述的方法，其特征在于，所述对应关系信息指示的对应关系包括所述第一数据服务信息和所述N个传输路径信息的对应关系，所述N为大于1的整数。
  26. 根据权利要求24或25所述的方法，其特征在于，所述N个传输路径信息包括并列的数据处理装置的信息，所述并列的数据处理装置为数据报文的同一级处理节点，所述N为大于1的整数。
  27. 根据权利要求24所述的方法，其特征在于，所述第三装置向第一装置发送对应关系信息，包括：
    所述第三装置向N个第一装置发送N个对应关系信息，其中，每个第一装置关联一个对应关系信息，一个对应关系信息指示的对应关系包括所述第一数据服务信息和所述N个传输路径信息中的一个传输路径信息的对应关系，所述N为大于1的整数。
  28. 根据权利要求24或27所述的方法，其特征在于，所述N个传输路径信息中的每个传输路径信息包括按序排列的数据处理装置的信息，排列靠前的数据处理装置处理数据报文的顺序靠前，所述N为大于1的整数。
  29. 根据权利要求21至28中任一项所述的方法，其特征在于，所述方法还包括：
    所述第三装置向所述第一装置发送配置信息，所述配置信息用于配置以下至少一项：数据报文的统计模式、数据报文的统计周期、所述传输路径信息的有效时间。
  30. 根据权利要求21至29中任一项所述的方法，其特征在于，所述方法还包括：
    所述第三装置向所述第一装置发送更新信息，所述更新信息用于更新所述数据服务信息对应的传输路径信息。
  31. 根据权利要求21至30中任一项所述的方法，其特征在于，所述方法还包括：
    所述第三装置向所述第一装置发送读取信息，所述读取信息用于读取所述数据服务信息对应的传输路径信息。
  32. 根据权利要求21至31中任一项所述的方法，其特征在于，所述方法还包括：
    所述第三装置向所述第一装置发送删除信息，所述删除信息用于删除所述数据服务信息对应的传输路径信息。
  33. 根据权利要求21至32中任一项所述的方法，其特征在于，所述方法还包括：
    所述第三装置接收来自所述第一装置的统计信息，所述统计信息包括数据报文的数量信息或者数据报文的字节数量信息。
  34. 根据权利要求33所述的方法，其特征在于，所述统计信息是以传输路径信息或数据服务信息为粒度统计得到的。
  35. 根据权利要求21至34中任一项所述的方法，其特征在于，所述数据服务信息为以下任一项：联邦学习服务的标识，分布式学习服务的标识，或数据汇聚服务的标识。
  36. 一种数据报文的传输方法，其特征在于，所述方法应用于通信系统，所述通信系统包括第一装置和第三装置，所述方法包括：
    所述第三装置生成对应关系信息，所述对应关系信息指示数据服务信息和数据报文的传输路径信息的对应关系，
    所述第三装置向所述第一装置发送所述对应关系信息；
    所述第一装置接收所述对应关系信息。
  37. 根据权利要求36所述的方法，其特征在于，所述方法还包括：
    所述第一装置获取业务数据，基于所述数据服务信息和所述对应关系信息确定第三传输路径信息，所述第三传输路径信息包括第二装置的信息，所述第二装置为第三数据报文的处理节点；
    所述第一装置向所述第二装置发送所述第三数据报文，所述第三数据报文包括所述第三传输路径信息和所述业务数据对应的数据载荷。
  38. 根据权利要求37所述的方法，其特征在于，所述第三传输路径信息包括所述第二装置的标识信息或地址信息。
  39. 根据权利要求36至38所述的方法，其特征在于，所述数据服务信息包括第一数据服务信息，所述第一数据服务信息对应N个传输路径信息，所述N个传输路径信息包括第三传输路径信息，所述N为大于或等于1的整数。
  40. 根据权利要求39所述的方法，其特征在于，所述对应关系信息指示的对应关系包括所述第一数据服务信息和所述N个传输路径信息的对应关系，所述N为大于1的整数，
    所述第一装置获取业务数据，基于所述数据服务信息和所述对应关系信息确定第二装置，包括：
    所述第一装置获取业务数据，基于所述第一数据服务信息和所述对应关系信息确定N个第二装置；
    所述第一装置向所述第二装置发送所述第三数据报文，包括：
    所述第一装置向所述N个第二装置发送N个数据报文，其中，一个第二装置关联一个数据报文，所述一个数据报文包括所述N个传输路径信息中的一个传输路径信息。
  41. 根据权利要求39或40所述的方法，其特征在于，所述N个传输路径信息包括并列的数据处理装置的信息，所述并列的数据处理装置为数据报文的同一级处理节点，所述N为大于1的整数。
  42. 根据权利要求39所述的方法，其特征在于，所述第三装置向所述第一装置发送对应关系信息，包括：
    所述第三装置向N个第一装置发送N个对应关系信息，其中每个第一装置关联一个对应关系信息，所述一个对应关系信息指示的对应关系包括所述第一数据服务信息和所述N个传输路径信息中的一个传输路径信息的对应关系，所述N为大于1的整数。
  43. 根据权利要求39或42所述的方法，其特征在于，所述N个传输路径信息中的每个传输路径信息包括按序排列的数据处理装置的信息，排列靠前的数据处理装置处理数据报文的顺序靠前，所述N为大于1的整数。
  44. 根据权利要求36至43中任一项所述的方法，其特征在于，所述数据服务信息为以下任一项：联邦学习服务的标识，分布式学习服务的标识，或数据汇聚服务的标识。
  45. 一种通信装置，其特征在于，所述装置包括用于执行如权利要求1至20中任一项所述方法的步骤的单元，或所述装置包括用于执行如权利要求21至35中任一项所述方法的步骤的单元。
  46. 一种通信装置，其特征在于，所述装置包括处理器，所述处理器与存储器耦合， 所述存储器存储有指令，所述指令被所述处理器运行时，使得所述处理器执行如权利要求1至20中任一项所述的方法，或执行如权利要求21至35中任一项所述的方法。
  47. 一种通信装置，其特征在于，所述装置包括逻辑电路，所述逻辑电路用于与输入/输出接口耦合，通过所述输入/输出接口传输数据，以执行如权利要求1至20中任一项所述的方法，或执行如权利要求21至35中任一项所述的方法。
  48. 一种通信系统，其特征在于，所述系统包括第一装置和第三装置，所述第一装置用于执行如权利要求1至20中任一项所述的方法，所述第三装置用于执行如权利要求21至35中任一项所述的方法。
  49. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质用于存储计算机程序，当所述计算机程序在计算机上运行时，使得所述计算机执行如权利要求1至20中任一项所述的方法，或执行如权利要求21至35中任一项所述的方法。
  50. 一种计算机程序产品，其特征在于，所述计算机程序产品包括：计算机程序代码，当所述计算机程序代码被运行时，实现如权利要求1至20中任一项所述的方法，或执行如权利要求21至35中任一项所述的方法。
PCT/CN2022/116833 2022-09-02 2022-09-02 数据报文的传输方法、通信装置和通信系统 WO2024045179A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/116833 WO2024045179A1 (zh) 2022-09-02 2022-09-02 数据报文的传输方法、通信装置和通信系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/116833 WO2024045179A1 (zh) 2022-09-02 2022-09-02 数据报文的传输方法、通信装置和通信系统

Publications (1)

Publication Number Publication Date
WO2024045179A1 true WO2024045179A1 (zh) 2024-03-07

Family

ID=90100168

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/116833 WO2024045179A1 (zh) 2022-09-02 2022-09-02 数据报文的传输方法、通信装置和通信系统

Country Status (1)

Country Link
WO (1) WO2024045179A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107896195A (zh) * 2017-11-16 2018-04-10 锐捷网络股份有限公司 服务链编排方法、装置及服务链拓扑结构
CN110119420A (zh) * 2018-02-03 2019-08-13 快板智能株式会社 数据编配平台管理
CN112202671A (zh) * 2020-09-09 2021-01-08 中盈优创资讯科技有限公司 一种通过代理实现业务编排的方法及装置
CN114327392A (zh) * 2021-12-30 2022-04-12 北京百度网讯科技有限公司 一种数据处理方法、装置及电子设备
CN114374634A (zh) * 2020-10-15 2022-04-19 华为技术有限公司 报文转发方法以及网络设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107896195A (zh) * 2017-11-16 2018-04-10 锐捷网络股份有限公司 服务链编排方法、装置及服务链拓扑结构
CN110119420A (zh) * 2018-02-03 2019-08-13 快板智能株式会社 数据编配平台管理
CN112202671A (zh) * 2020-09-09 2021-01-08 中盈优创资讯科技有限公司 一种通过代理实现业务编排的方法及装置
CN114374634A (zh) * 2020-10-15 2022-04-19 华为技术有限公司 报文转发方法以及网络设备
CN114327392A (zh) * 2021-12-30 2022-04-12 北京百度网讯科技有限公司 一种数据处理方法、装置及电子设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
WANGGEN LIU, ZHENG HUAICHENG, RONG GUOPING: "A Scheduler System for Large-Scale Distributed Data Computing in Cloud", BIG DATA, CN, vol. 6, no. 1, 1 January 2020 (2020-01-01), CN, pages 81 - 98, XP093145021, ISSN: 2096-0271, DOI: 10.11959/j.issn.2096-0271.2020007 *

Similar Documents

Publication Publication Date Title
CN113329431B (zh) 一种无线承载的配置方法、终端、存储介质及芯片
WO2020103833A1 (zh) 信息传输方法及其装置
TWI602465B (zh) An air interface protocol stack configuration method, data transmission method and device
WO2022205234A1 (zh) 一种通信方法及装置
JP2019519945A (ja) 中継伝送方法及び装置
WO2021081696A1 (zh) 传输数据的方法和通信装置
WO2022151420A1 (zh) 一种数据包传输的方法、装置和系统
WO2021134577A1 (zh) 一种数据传输方法及装置
WO2021026902A1 (zh) 一种配置方法、通信装置和通信系统
WO2024045179A1 (zh) 数据报文的传输方法、通信装置和通信系统
WO2024045177A1 (zh) 数据报文的传输方法、通信装置和通信系统
WO2024045180A1 (zh) 数据报文的传输方法、通信装置和通信系统
WO2023284551A1 (zh) 通信方法、装置和系统
WO2023024119A1 (zh) 一种应用于短距无线通信的数据传输方法及通信装置
WO2017177438A1 (zh) 一种控制信息的传输方法及装置
WO2021062717A1 (zh) 一种缓冲区状态报告传输方法及装置
WO2024007221A1 (zh) 通信方法及装置
WO2024092697A1 (zh) 通信方法、装置及系统
WO2023066168A1 (zh) 一种通信方法、装置及系统
WO2023246746A1 (zh) 一种通信方法及相关设备
WO2023065155A1 (zh) 无线通信的方法、终端设备、接入网设备和核心网设备
WO2023213159A1 (zh) 通信方法及装置
WO2024051313A1 (zh) 通信资源管理方法、装置、系统及存储介质
WO2023201733A1 (zh) 无线通信的方法和设备
WO2023070684A1 (zh) 无线通信的方法和设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22956999

Country of ref document: EP

Kind code of ref document: A1