Packet loss detection method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a packet loss detection method and device, electronic equipment and a storage medium. The method comprises the following steps: sequentially sending a plurality of first detection data packets to a first equipment end; obtaining at least one first feedback message generated by the first device end, each first feedback message comprising a first type of data content generated by the first device end in response to a second detection data packet, the second detection data packet being a detection data packet received by the first device end in the plurality of first detection data packets, the first type of data content is used for indicating whether the first equipment end receives a second detection data packet or not, and the first type of data content is also used for indicating whether the first equipment end receives a third detection data packet or not; the third detection data packet is the first detection data packet with the sending sequence before the second detection data packet in the plurality of first detection data packets; and determining a packet loss condition of the first transmission path according to the at least one first feedback message. According to the scheme, unidirectional packet loss detection can be realized.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to a packet loss detection method, device, electronic device, and storage medium. Background Art

[0002] Link packet loss rate detection is a crucial component of network quality monitoring and optimization. Mainstream link packet loss rate detection solutions rely on bidirectional data packet transmission. Specifically, the second device sends a data packet to the first device, which then returns the data packet to the second device. The link packet loss rate is calculated by counting the number of data packets lost during the entire round trip. In actual network environments, the link paths from the second device to the first device and from the first device to the second device often differ. These two links may transmit data over different physical links, each with varying transmission performance. These solutions are unable to accurately distinguish the packet loss characteristics of these two independent links, making it impossible to precisely optimize specific links. Summary of the Invention

[0003] The present disclosure provides a packet loss detection method, apparatus, electronic device, and storage medium to implement end-to-end unidirectional packet loss detection.

[0004] In a first aspect, an embodiment of the present disclosure provides a packet loss detection method, wherein the method includes:

[0005] Sequentially sending a plurality of first detection data packets to the first device end, wherein the first detection data packets are used to detect packet loss on a first transmission path from the second device end to the first device end;

[0006] Obtain at least one first feedback message generated by the first device end, each first feedback message including a first type of data content generated by the first device end in response to a second probe data packet, the second probe data packet being a probe data packet received by the first device end among the multiple first probe data packets, the first type of data content being used to indicate whether the first device end has received the second probe data packet, and the first type of data content being further used to indicate whether the first device end has received a third probe data packet, the third probe data packet being a first probe data packet in the multiple first probe data packets whose sending order precedes the second probe data packet;

[0007] Determine the packet loss situation of the first transmission path according to the at least one first feedback message.

[0008] In a second aspect, an embodiment of the present disclosure further provides a packet loss detection device, wherein the device includes:

[0009] a sending module, configured to sequentially send a plurality of first detection data packets to the first device end, wherein the first detection data packets are used to perform packet loss detection on a first transmission path from the second device end to the first device end;

[0010] a receiving module, configured to obtain at least one first feedback message generated by the first device end, each first feedback message including a first type of data content generated by the first device end in response to a second probe data packet, the second probe data packet being a probe data packet received by the first device end among the multiple first probe data packets, the first type of data content being used to indicate whether the first device end has received the second probe data packet, and the first type of data content being further used to indicate whether the first device end has received a third probe data packet, the third probe data packet being a first probe data packet in the multiple first probe data packets that is sent before the second probe data packet;

[0011] A detection module is used to determine the packet loss situation of the first transmission path according to the at least one first feedback message.

[0012] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0013] at least one processor; and

[0014] a memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can perform the packet loss detection method described in any one of the above embodiments.

[0016] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable medium, wherein the computer-readable medium stores computer instructions, and the computer instructions are used to enable a processor to implement the packet loss detection method described in any one of the above embodiments when executed.

[0017] In the technical solution of the embodiment of the present disclosure, the second device end can sequentially send multiple first detection data packets to the first device end, and the first detection data packet is used to detect packet loss on the first transmission path from the second device end to the first device end. For the second detection data packet that can be received by the first device end among the multiple first detection data packets, the first device end will generate a first feedback message in response to the second detection data packet. When generating the first feedback message, the first device end will record whether the second detection data packet and the first detection data packet in the multiple first detection data packets that are sent before the second detection data packet are received by the first device end. When the first device end sends the first feedback message to the second After the device end sends, the second device end only needs to obtain the first feedback message fed back from the first device end to the second device end as much as possible. Based on the first feedback message fed back by the first device end, the second device end can know which first detection data packets the first device end has received and which first detection data packets have not been received. There is no need for the second device end to trigger an additional complex query process, which reduces the interactive performance overhead. The packet loss situation of the entire link from the second device end to the first device end can be fully known, forming a complete end-to-end packet loss detection closed loop, realizing end-to-end unidirectional packet loss detection, and then the transmission path from the second device end to the first device end can be further optimized based on the detected packet loss rate.

[0018] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0020] Figure 1 This is a flow chart of a packet loss detection method provided by an embodiment of the present disclosure;

[0021] Figure 2 This is a schematic diagram of sending a first probe data packet and receiving a first feedback message during a packet loss detection process provided by an embodiment of the present disclosure;

[0022] Figure 3 is a flowchart of another packet loss detection method provided by an embodiment of the present disclosure;

[0023] Figure 4is a schematic diagram of a protocol format adopted when transmitting a first probe data packet and a first feedback message provided by an embodiment of the present disclosure;

[0024] Figure 5 This is a schematic diagram of the structure of a packet loss detection device provided by an embodiment of the present disclosure;

[0025] Figure 6 It is a structural diagram of an electronic device for implementing a packet loss detection method provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0027] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0028] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0029] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0030] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0031] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0032] Figure 1This is a flow chart of a packet loss detection method provided by an embodiment of the present disclosure. The embodiment of the present disclosure is applicable to situations where packet loss detection is performed from end to end, especially situations where one-way packet loss rate detection is performed from end to end. The packet loss detection method can be performed by a packet loss detection device. The packet loss detection device can be implemented in the form of software and / or hardware and is generally integrated into any electronic device with network communication capabilities. The electronic device can be a mobile terminal, PC or server, such as a computer, laptop, smartphone, or tablet computer.

[0033] like Figure 1 As shown, the packet loss detection method of the embodiment of the present disclosure may include the following process:

[0034] S110: Send multiple first detection data packets to the first device end in sequence, where the first detection data packets are used to perform packet loss detection on a first transmission path from the second device end to the first device end.

[0035] The first device can be the device that receives the first probe packet and generates a feedback message in a packet loss detection scenario. The second device can be the device that sends the first probe packet and calculates the packet loss rate in a packet loss detection scenario. The first probe packet is a data packet in a specified protocol format that is proactively sent by the second device. Packet loss refers to the loss of a data packet during network transmission. The first and second devices can be terminal devices, servers, or other network nodes in the network.

[0036] See also Figure 2 , after the second device end generates multiple first detection data packets, the multiple first detection data packets can be sent sequentially to the first device end (for example, the multiple first detection data packets are P1, P2, P3, and P4 respectively). In the process of sending the first detection data packet from the second device end to the first device end along the first transmission path, the first detection data packet cannot reach the first device end due to at least one of the reasons of network congestion, link failure, and device abnormality of the first transmission path, and it is considered that the first detection data packet is lost. The second device end can quantify the packet loss rate of the first transmission path from the second device end to the first device end by counting the reception status of the first detection data packet at the second device end.

[0037] S120. Obtain at least one first feedback message generated by the first device end, each first feedback message including a first type of data content generated by the first device end in response to the second probe data packet, the second probe data packet being a probe data packet received by the first device end among multiple first probe data packets, the first type of data content being used to indicate whether the first device end has received the second probe data packet, and the first type of data content being further used to indicate whether the first device end has received a third probe data packet, the third probe data packet being a first probe data packet in a sending order that precedes the second probe data packet among multiple first probe data packets.

[0038] See also Figure 2 In the process of sequentially sending multiple first probe data packets from the second device end to the first device end, if a first probe data packet successfully reaches the first device end, then the first probe data packet received by the first device end can be used as the second probe data packet, that is, the second probe data packet is the probe data packet that has been received by the first device end among the multiple first probe data packets. At this time, the first device end will generate a first feedback message (for example, the first feedback message can be P1-ACK, P2-ACK, P3-ACK) in response to the second probe data packet. Each first feedback message contains first-type data content. The first-type data content in the first feedback message is used to record whether the first device end has received the second probe data packet and the third probe data packet. The second probe data packet and the third probe data packet are also probe data packets among the multiple first probe data packets. The first-type data content not only indicates whether the first device end has received the second probe data packet, but also indicates whether the first device end has received the first probe data packet that is located before the second probe data packet in the sending order among the multiple first probe data packets. That is, whether at least two first probe data packets that are not located after the second probe data packet are received by the first device end needs to be recorded in the first-type data content.

[0039] See also Figure 2 The first feedback message may refer to confirmation information returned by the first device end to the first device end after receiving the first probe data packet, so as to inform the second device end of whether the second probe data packet and the first probe data packet whose sending order is before the second probe data packet have been received by the first device end. The first type of data content in the first feedback message does not only record the reception status of whether the first device end has received the second probe data packet itself, but is used to indicate and record the reception status of whether all first probe data packets in multiple first probe data packets that are not after the second probe data packet in the sending order have been received by the first device end.

[0040] The first feedback message can be a response message to the first probe data packet, and the first type of data content of the first feedback message is used to record whether the first device end has received the second probe data packet and whether the first device end has received the third probe data packet. The first feedback message generated by the first device end can accurately reflect the reception status of the second probe data packet and all first probe data packets that are located before the second probe data packet in the sending order. In this way, the second device end can understand which of the multiple first probe data packets have been successfully sent to the first device end for reception based on the first feedback message, and which first probe data packets may have been lost or transmitted incorrectly and not been sent to the first device end, and can then use this to calculate the packet loss situation from the second device end to the first device end.

[0041] Moreover, since the first feedback message not only includes whether the first device end has received the second detection data packet itself, but also includes whether the first detection data packet before the second detection data packet has been received, even if some first feedback messages corresponding to the first detection data packets are not received, the first device end can also determine whether they have been sent to the first device end based on the first feedback messages corresponding to the subsequent first detection data packets, thereby avoiding the situation where the first feedback messages associated with some first detection data packets cannot be returned to the second device end due to blockage or failure of the transmission path from the first device end to the second device end, and it is mistakenly judged that the first detection data packet cannot be sent from the second device end to the first device end and packet loss occurs.

[0042] As an optional but non-limiting implementation scheme, the first type of data content is recorded using the values ​​of different flag bits in the receiving flag field included in the first feedback message. The value of the flag bit in the receiving flag field is used to indicate whether the first device end has received the second detection data packet, and the value of the flag bit in the receiving flag field is also used to indicate whether the first device end has received the third detection data packet.

[0043] See also Figure 2 , the first device sends at least one first feedback message to the second device, and the first feedback message includes a reception flag field. The reception flag field can be a binary bit segment used to identify whether the first device has received the second probe data packet and whether the first device has received the third probe data packet. The reception flag field can include multiple flag bits. By integrating multiple flag bits into a reception flag field, the reception status of the second probe data packet and the third probe data packet by the first device can be efficiently represented through the parallel combination of binary bits.

[0044] The result of recording the first type of data content in the first feedback message depends on the values ​​of the various flag bits in the reception flag field in the first feedback message. The values ​​of the flag bits in the reception flag field can be used to record whether the second detection data packet is received and whether the first device receives the third detection data packet. Taking the binary bits that describe the reception of the third detection data packet by the first device as an example, the examples of the reception flag values ​​are as follows: If the flag value in the reception flag field is 1, it indicates that the first device successfully receives the third detection data packet; if the flag value in the reception flag field is 0, it indicates that the first device has not received the third detection data packet or has failed to receive the third detection data packet. The flag bits occupy fewer bytes and can quickly and accurately record the reception of the second and third detection data packets by the first device.

[0045] S130. Determine a packet loss situation of a first transmission path according to at least one first feedback message.

[0046] See also Figure 2 For each first feedback message in at least one first feedback message, the first type of data content in the first feedback message indicates whether the first device end has received the second detection data packet and whether the first device end has received the third detection data packet. The third detection data packet is the first detection data packet in the multiple first detection data packets and is sent before the second detection data packet in the order. Once the second device end can receive any first feedback message, the second device end can know whether the second detection data packet and the first detection data sent before the second detection data packet have been received by the first device end or whether they are successfully sent from the second device end to the first device end according to the first type of data content recorded in the first feedback message by the first device end, thereby realizing the end-to-end one-way packet loss statistics from the second device end to the first device end.

[0047] The second device end can count the first number and the second number of the second detection data packets based on at least one first feedback message, the first number being the number of first detection data packets that have not been successfully received by the first device end or have not been successfully sent from the second device end to the first device end among multiple first detection data packets, and the second number being the number of first detection data packets that have been sent from the second device end to the first device end. Furthermore, the packet loss rate of the first transmission path from the second device end to the first device end is determined based on the first number and the second number, so that the transmission path from the second device end to the first device end can be route optimized based on the packet loss rate of the first transmission path from the second device end to the first device end. The packet loss rate may refer to the percentage between the number of first detection data packets lost in the first transmission path from the second device end to the first device end and the number of first detection data packets that have been sent up to the second detection data packet.

[0048] As an optional but non-limiting implementation solution, sequentially sending multiple first detection data packets to the first device includes but is not limited to the following steps:

[0049] Obtain multiple first detection data packets of the same detection group, the detection group identifier associated with each first detection data packet in the multiple first detection data packets is the detection group identifier of the detection group to which the first detection data packet belongs, and the detection group identifier associated with the first detection data packet is used to instruct the first device end to aggregate and count the first detection data packets of the same detection group; and send the multiple first detection data packets of the same detection group to the first device end sequentially.

[0050] See also Figure 2 In order to correctly count the packet loss rate, the second device end can group the batch of first probe data packets to be sent to the first device end into multiple probe groups. Each probe group can include multiple first probe data packets. The first probe data packets of the same probe group can share the probe group identifier of the probe group to which the first probe data belongs. The probe group identifier can be represented by a Group ID. In this way, it is convenient for the first device end to aggregate the first probe data packets of the same probe group based on the probe group identifier, and then the reception status of each first probe data packet from the second device end to the first device end can be counted according to each probe group, thereby calculating the packet loss rate of the first transmission path from the second device end to the first device end.

[0051] See also Figure 2After grouping a batch of first probe data packets to obtain multiple probe groups, the second device can configure the order in which the multiple first probe data packets of the same probe group are sent. The second device sequentially sends the multiple first probe data packets from the second device to the first device according to the order in which the multiple first probe data packets in the same probe group are sent, so that the first device can generate a first feedback message corresponding to the received first probe data packet when it receives any first probe data packet. The first feedback message for the second probe data packet received by the first device in the multiple first probe data packets of each probe group must include the first device's reception status of the second probe data packet and the first probe data packet that precedes the second probe data packet in the multiple first probe data packets. For example, for the multiple first probe data packets that have been sorted, after the nth first probe data packet of the same probe group is sent from the second device to the first device, the first device can generate a first feedback message for the nth first probe data packet. In this case, the first feedback message for the nth first probe data packet includes the first device's reception status of the first n first probe data packets.

[0052] For example, see Figure 2Taking P1, P2, P3, and P4 in the multiple first detection data packets of the detection group as an example, the second device end sends P1, P2, P3, and P4 in sequence. When the first device end receives the first detection data packet, it will respond with a corresponding first feedback message for the received first detection data packet, and set the flag position of the reception flag field in the first feedback message to 1. For example, when the first device end receives P1, P2, and P4, the first flag bit corresponding to P1, the second flag bit corresponding to P2, and the fourth flag bit corresponding to P4 in the reception flag field are respectively changed to 1, indicating that the first device end has received the corresponding first detection data packet; and since P3 is lost during the transmission process from the second device end to the first device end, the third flag bit corresponding to P3 is 0. After receiving P1, the first device records the receipt of P1 and generates a first feedback message P1-ACK to indicate whether the first device has received P1. After receiving P2, the first device records the receipt of P2 and combines the reception status of P1 and P2 to generate a first feedback message P2-ACK to indicate whether the first device has received P1 and P2. When the first device receives P4 but does not receive P3, packet loss occurs. The first device then records the receipt of P3 but does not receive P3, combines the reception status of P1, P2, P3, and P4 to generate a first feedback message P4-ACK to indicate whether the first device has received P1, P2, P3, and P4. When the first feedback message returns from the first device to the second device, the second device learns the second probe data packet received by the first device and can then calculate the packet loss rate from the second device to the first device.

[0053] Optionally, the limit on the number of first probe data packets that can be accommodated by the same probe group is correlated with the maximum amount of data that can be recorded by the receive flag field in the first feedback message. The number of bits in the receive flag field in the first feedback message directly determines the maximum amount of data that can be recorded by the receive flag field, and the maximum amount of data that can be recorded by the receive flag field is strongly correlated with the number of first probe data packets that can be accommodated by the probe group. The limit on the number of first probe data packets for the probe group does not exceed the maximum amount of data that can be recorded by the receive flag field.

[0054] In the technical solution of the embodiment of the present disclosure, the second device end can sequentially send multiple first detection data packets to the first device end, and the first detection data packet is used to detect packet loss on the first transmission path from the second device end to the first device end. For the second detection data packet that can be received by the first device end among the multiple first detection data packets, the first device end will generate a first feedback message in response to the second detection data packet. When generating the first feedback message, the first device end will record whether the second detection data packet and the first detection data packet in the multiple first detection data packets that are sent before the second detection data packet are received by the first device end. When the first device end sends the first feedback message to the second After the device end sends, the second device end only needs to obtain the first feedback message fed back from the first device end to the second device end as much as possible. Based on the first feedback message fed back by the first device end, the second device end can know which first detection data packets the first device end has received and which first detection data packets have not been received. There is no need for the second device end to trigger an additional complex query process, which reduces the interactive performance overhead. The packet loss situation of the entire link from the second device end to the first device end can be fully known, forming a complete end-to-end packet loss detection closed loop, realizing end-to-end unidirectional packet loss detection, and then the transmission path from the second device end to the first device end can be further optimized based on the detected packet loss rate.

[0055] Figure 3 A flow chart of another packet loss detection method provided for an embodiment of the present disclosure. The technical solution of this embodiment further optimizes the process of obtaining at least one first feedback message generated by the first device end in the aforementioned embodiment on the basis of the technical solution of the aforementioned embodiment. This embodiment can be combined with various optional solutions in one or more of the aforementioned embodiments.

[0056] like Figure 3 As shown, the packet loss detection method of the embodiment of the present disclosure may include the following process:

[0057] S310: Send multiple first detection data packets to the first device end in sequence, where the first detection data packets are used to perform packet loss detection on a first transmission path from the second device end to the first device end.

[0058] S320. Receive a first feedback message sent by the first device end in response to the second type of data content in the second detection data packet, where the second type of data content in the second detection data packet is used to indicate whether the first device end triggers the use of at least two second transmission paths to send the first feedback message to the second device end, and each of the at least two second transmission paths is a different heterogeneous network path from the first device end to the second device end.

[0059] Among them, each first feedback message includes a first type of data content generated by the first device end in response to the second probe data packet, the second probe data packet is a probe data packet received by the first device end among multiple first probe data packets, the first type of data content is used to indicate whether the first device end has received the second probe data packet, and the first type of data content is also used to indicate whether the first device end has received the third probe data packet, and the third probe data packet is the first probe data packet in the multiple first probe data packets whose sending order is before the second probe data packet.

[0060] In the packet loss rate detection mechanism, the second device can obtain the statistical information in the first feedback message generated by the first device to calculate the packet loss rate. However, in a feedback mechanism where packet loss occurs on a single transmission path, when the packet loss rate of the transmission path from the first device to the second device (B→A) is high, that is, when the transmission path from the first device to the second device itself is blocked or faulty, even if the first probe data packet has been successfully sent from the second device to the first device, the first feedback message generated by the first device may not be successfully sent to the second device. Specifically, because network congestion in end-to-end transmission is often direction-specific, the forward transmission path (A→B) may be in a low-load state and maintain zero packet loss, while the reverse transmission path (B→A) may experience severe packet loss due to burst traffic overload during the same period.

[0061] It can be seen that according to the direction specificity of the above-mentioned network congestion phenomenon, even if the first detection data packet has been successfully sent from the second device end to the first device end, it will be mistakenly believed that packet loss occurred from the second device end to the first device end because the first feedback message was not sent from the first device end to the second device end. This will cause the second device end to be unable to accurately identify the actual packet loss status of the first transmission path (A→B) from the second device end to the first device end. It can be seen that the loss of part of the first feedback packet may also cause incomplete statistical information, thereby affecting the packet loss detection accuracy of the first transmission path from the second device end to the first device end.

[0062] Based on the above situation, the present application scheme adopts a multi-path redundant feedback mechanism. After the first device end receives the second detection data packet among multiple first detection data, the first device end will generate a first feedback message of the second detection data packet in response to the second detection data, and at the same time parse the second type of data content in the first detection data packet in response to the second detection data packet. According to the parsing result of the second type of data content, the first device end is controlled to trigger the use of at least two second transmission paths to send the first feedback message to the second device end at the same time, so that the second device end can receive the first feedback message triggered by the first device end to use at least two second transmission paths for transmission.

[0063] Since at least two second transmission paths are different heterogeneous network paths from the first device end to the second device end, a heterogeneous network path refers to a transmission path composed of a network combination of different types, technical architectures or communication protocols during data transmission, when the first device end simultaneously uses at least two second transmission paths to send the first feedback message to the second device end, even if one of the second transmission paths is blocked or a network transmission failure occurs, the first device end can still use the remaining second transmission path to continue sending the first feedback message to the second device end, thereby reducing the transmission time of the first feedback message from the first device end to the second device end. The feedback message loss rate that occurs during the transmission process of the two device ends, and the number of first detection data packets that cannot be determined from the second device end to the first device end is reduced to near 0, can reduce the impact of feedback message loss caused by network congestion or network transmission failure from the first device end to the second device end, thereby improving the second device end's accurate statistics of the number of packet losses in the first transmission path from the second device end to the first device end, and solve the problem of unidirectional packet loss that cannot accurately distinguish between the end-to-end forward transmission path (A→B) and the end-to-end reverse transmission path (B→A), thereby improving the accuracy of subsequent packet loss rate calculations.

[0064] As an optional but non-limiting implementation scheme, at least two second transmission paths include a third transmission path, the third transmission path is the return path of the first transmission path, the second transmission path other than the third transmission path in the at least two second transmission paths and the third transmission path in the network topology are more isolated than a preset isolation, and the second transmission path other than the third transmission path in the at least two second transmission paths is used to avoid potential congestion or failure of the third transmission path when the first feedback message is transmitted from the first device end to the second device end.

[0065] The first transmission path is the network path from the second device end to the first device end. The third transmission path is the return path of the first transmission path. The third transmission path is the network path from the first device end to the second device end. The network paths traversed by the first transmission path and the third transmission path can be the same or different, depending on the network topology, routing protocol, and operator policy. The at least two second transmission paths include the third transmission path and a backup transmission path configured for sending the first feedback message from the first device end to the second device end, which is different from the third transmission path. The remaining second transmission paths of the at least two second transmission paths, excluding the third transmission path, are used to avoid potential congestion or failure issues of the third transmission path.

[0066] The isolation degree between two transmission paths in the network topology can measure the degree of independence between the two transmission paths in the network topology. For example, the isolation degree can be determined by at least one of the following: link sharing, node sharing, or routing resource sharing between the two transmission paths in the network topology. The preset isolation degree can be a minimum isolation threshold set in the network topology. If the isolation degree between two transmission paths exceeds the preset isolation degree threshold, the two transmission paths are considered to be sufficiently independent physically or logically.

[0067] The degree of isolation between two transmission paths in the network topology can be quantified using at least one of the following methods: the difference in the number of routing hops between the two transmission paths in the network topology and the bandwidth isolation ratio between the two transmission paths in the network topology; the routing hop count refers to the number of routers a data packet passes through in the network from the source node to the destination node, and the bandwidth isolation ratio refers to the allocation of a specific proportion of bandwidth resources to different transmission paths in network resource allocation to ensure that bandwidth competition between transmission paths does not affect performance, thereby achieving bandwidth isolation.

[0068] The degree of isolation between the second transmission path other than the third transmission path and the third transmission path in at least two second transmission paths exceeds the preset isolation threshold, which means that the second transmission path other than the third transmission path and the third transmission path have a high degree of independence in the network topology. When the transmission quality of the first feedback message is reduced due to network congestion, failure or attack on the third transmission path, the second transmission path other than the third transmission path can still remain unobstructed, avoiding the problems of packet loss, delay surge and the like caused by the first feedback message relying on a single transmission path. It can be seen that if a network anomaly occurs in the area where the third transmission path is located (such as a switch failure or link interruption), since the second transmission path other than the third transmission path is highly isolated from the third transmission path, due to the introduction of the second transmission path other than the third transmission path, the first feedback message can be detoured through the second transmission path other than the third transmission path, ensuring as much as possible that the first feedback message generated by the first device end can be sent to the second device end, and maintaining the stability of the communication link required for the first feedback message.

[0069] As an optional but non-limiting implementation solution, sequentially sending multiple first detection data packets to the first device includes but is not limited to the following steps:

[0070] In response to the fourth probe data packet among multiple first probe data packets satisfying the multi-path feedback condition, the second type data content of the fourth probe data packet is configured to instruct the first device end to trigger the use of at least two second transmission paths to send the first feedback message to the second device end; the fourth probe data packet is a first probe data packet to be transmitted to the first device end configured according to the sending order of each first probe data packet among the multiple first probe data packets, and the multi-path feedback condition is used to indicate the conditions that need to be met when the first device end sends the first feedback message generated in response to the fourth probe data packet to the second device end using different transmission paths; the fourth probe data packets are sent sequentially to the first device end.

[0071] Considering that the strategy of using multi-path return feedback messages in the mechanism of multi-path redundant feedback will significantly increase the number of detection messages and introduce additional network performance overhead, the present application solution can set a dynamic and adaptive strategy of multi-path return feedback messages. In the process of sequentially sending multiple first detection data packets to the first device end, for any fourth detection data packet among the multiple first detection data packets that need to be sent sequentially, the second device end will detect whether the fourth detection data packet meets the multi-path feedback condition each time it sends the fourth detection data packet.

[0072] If the fourth probe data packet meets the multi-path feedback condition, the second type data content of the fourth probe data packet is configured to instruct the first device end to trigger the use of at least two second transmission paths to send the first feedback message to the second device end. At this time, once the fourth probe data packet among the multiple first probe data packets is received by the first device end, the first device end will respond with the fourth probe data packet as the second probe data packet to trigger multiple second transmission paths and return the first feedback message to the second device end at the same time. If the fourth probe data packet does not meet the multi-path feedback condition, the second type data content of the fourth probe data packet is still configured to instruct the first device end not to use at least two second transmission paths to send the first feedback message to the second device end. At this time, even if the fourth probe data packet among the multiple first probe data packets is received by the first device end, the first device end still uses a single transmission path to return the first feedback message to the second device end when responding with the fourth probe data packet as the second probe data packet.

[0073] The multi-path feedback condition is a condition that needs to be met for whether multiple second transmission paths are initiated to return to the second device end after the first feedback message generated after the fourth detection data packet among the multiple first detection data packets sent from the second device end to the first device end is received and responded by the first device end. Only when the multi-path feedback condition is met, the first device end will enable the multi-path feedback mechanism.

[0074] As an optional but non-limiting implementation, the second probe data packet satisfies the multipath feedback condition, including at least one of the following:

[0075] Before sending the fourth detection data packet to the first device end, there are multiple fifth detection data packets and the number of the multiple fifth detection data packets is greater than the preset number. The multiple fifth detection data packets are first detection data packets that have been continuously sent to the first device end before the fourth detection data packet and have not been received by the first device end.

[0076] When the fourth detection data packet is sent to the first device end, there are multiple sixth detection data packets and the number of the multiple sixth detection data packets in the multiple first detection data packets is greater than the preset proportion. The multiple sixth detection data packets are the first detection data packets that have been sent to the first device end by the time the fourth detection data packet is sent.

[0077] The fourth detection data packet sent to the first device end belongs to a preset proportion of first detection data packets extracted from the tails of multiple first detection data packets, and the multiple first detection data packets are sequentially sorted according to the sending order.

[0078] The network quality of the third transmission path used when sending the first feedback message from the first device end to the second device end is less than the preset network quality, and the third transmission path is a return path of the first transmission path.

[0079] Before the second device sends a fourth probe packet among the plurality of first probe packets to the first device, it detects whether there are multiple fifth probe packets before the fourth probe packet is sent. The multiple fifth probe packets are first probe packets among the multiple first probe packets that have been continuously sent to the first device and not received by the first device before the second device sends the fourth probe packet to the first device. If the presence of multiple fifth probe packets is detected, it indicates that the first transmission path from the second device to the first device has experienced continuous packet loss. At this time, the second device may not be able to obtain the latest first feedback message. In order to accurately determine the number of packet losses from the second device to the first device, it is necessary to ensure that the first feedback message from the first device to the second device can be successfully transmitted. Transmitting the first feedback message through multiple transmission paths will introduce significant network overhead. Therefore, a preset limit on the number of consecutive packet losses is set. Only when the number of consecutive packet losses exceeds the preset number and when the number of fifth probe packets exceeds the preset number will the first device be required to trigger the multi-path feedback condition so that the first feedback message can be transmitted through multiple transmission paths.

[0080] When the second device end sends the fourth probe data packet among multiple first probe data to the first device end, the number of first probe data packets sent by the second device end to the first device end after the fourth probe data packet is sent is detected, that is, the number of multiple sixth probe data packets. If the proportion of the multiple sixth probe data packets in the multiple first probe data packets is larger, it means that the number of first probe data packets that need to be sent after the fourth probe data packet is gradually decreasing. After the first probe data packet after the fourth probe data packet arrives at the first device end, in order to better obtain the last first probe data packet or the first feedback message corresponding to the last first probe data packet, it is necessary to ensure that the first feedback message from the first device end to the second device end can be successfully transmitted as much as possible. At this time, the first device end is also required to trigger the multi-path feedback condition so as to use multiple transmission paths to transmit the first feedback message, and to ensure that the obtained first feedback message is returned to the second device end as much as possible to avoid the subsequent failure to obtain the first feedback message, thereby failing to know whether each first probe data message is successfully sent to the first device end, and thus failing to accurately calculate the packet loss rate.

[0081] Since multiple first detection data packets have been sorted in the order of sending, when the second device sends the fourth detection data packet among the multiple first detection data packets to the first device, the second device will detect whether the fourth detection data packet to be sent falls into the first detection data packets at the tail preset proportion of the multiple first detection data packets. If it has fallen into the first detection data packets at the tail preset proportion, it indicates that the number of first detection data packets to be sent after the fourth detection data packet is relatively small. At this time, if the second device end has already received the first feedback message regarding whether the subsequent first detection data packet is successfully sent to the first device end, there is no need to use multiple transmission paths to transmit the first feedback message to ensure that the obtained first feedback message is returned to the second device; however, if the first feedback message cannot be received at this time, then the second device end will not be able to know whether the subsequent first detection data packet is successfully sent to the first device end. For this reason, multiple transmission paths can be used to transmit the first feedback message to ensure that the obtained first feedback message is returned to the second device end as much as possible, and to ensure that the first feedback message can be obtained as much as possible, so as to avoid the first feedback message being unable to reach the second device end due to subsequent network congestion or failure from the first device end to the second device end, thereby affecting the statistics of the number of packet losses from the second device end to the first device end.

[0082] When it is detected that the network quality of the third transmission path used when sending the first feedback message from the first device end to the second device end is less than the preset network quality, it indicates that there will be a network quality problem from the first device end to the second device end. At this time, the first device end triggers the multi-path feedback condition and uses multiple transmission paths to feedback the first feedback message. Although additional traffic will be introduced, compared with the routing optimization effect brought by timely obtaining an accurate packet loss rate, the overall routing optimization effect is extremely significant. In other words, at the cost of a small amount of additional traffic, a deep optimization of the network routing is achieved, which has significant advantages in ensuring the data transmission stability of the first feedback message and improving network transmission efficiency. The routing optimization effect is much higher than the overhead generated by the detection. Optionally, the network quality is a measure of the performance of the detection data packet transmitted on the third transmission path, and the network quality is used to measure the performance and reliability of network communication.

[0083] In an optional example, the second probe data packet satisfies the multi-path feedback condition by satisfying the second trigger condition at the same time on the basis of satisfying the first trigger condition; wherein, the first trigger condition is that when the fourth probe data packet is sent to the first device end, there are multiple sixth probe data packets and the number of the multiple sixth probe data packets in the multiple first probe data packets is greater than a preset proportion, and the multiple sixth probe data packets are the first probe data packets that have been sent to the first device end by the time the fourth probe data packet is sent; the second trigger condition is that before the fourth probe data packet is sent to the first device end, there are multiple fifth probe data packets and the number of the multiple fifth probe data packets is greater than a preset number, and the multiple fifth probe data packets are the first probe data packets that have been continuously sent to the first device end before the fourth probe data packet and have not been received by the first device end.

[0084] In another optional example, the second detection data packet satisfies the multi-path feedback condition by satisfying the second trigger condition at the same time as satisfying the third trigger condition; wherein, the third trigger condition is that the fourth detection data packet sent to the first device end belongs to a preset proportion of the first detection data packets extracted from the tail of multiple first detection data packets, and the multiple first detection data packets are sorted in sequence according to the order of sending.

[0085] From a network operation perspective, when a network is unstable, such as during sudden traffic spikes, link failures, or heterogeneous network handovers, single-path transmission is prone to packet backlogs, increased transmission latency, and even connection loss. In these situations, a redundant multi-path feedback mechanism dynamically adjusts data transmission strategies by simultaneously sending first feedback messages over multiple secondary transmission paths. This dynamic routing adjustment significantly improves data transmission reliability and efficiency compared to traditional passive retransmission mechanisms. In real-world networks, while the use of multiple secondary transmission paths incurs some additional traffic overhead, this additional overhead is negligible compared to the benefits of route optimization. For example, in the case of data transmission between data centers, while the use of multiple secondary transmission paths increases the traffic required for message feedback, by promptly avoiding congested third transmission paths used to transmit first feedback messages, this demonstrates that, even in poor network conditions, the use of multiple secondary transmission paths can increase the probability of first feedback messages being transmitted to the second device at the expense of a small amount of additional traffic. This allows for accurate packet loss rate detection based on the first feedback message, and further optimization of the transmission path from the second device to the first device based on the detected packet loss rate.

[0086] S330: Determine a packet loss situation of the first transmission path according to at least one first feedback message.

[0087] Based on the above embodiment, optionally, determining the packet loss situation of the first transmission path according to at least one first feedback message includes but is not limited to the following steps:

[0088] Determine a second feedback message from at least one first feedback message; the order in which second probe data packets associated with the second feedback message are sent to the first device end is located after the order in which second probe data packets associated with the remaining first feedback messages other than the second feedback message in at least one first feedback message are sent to the first device end; determine the packet loss rate of the first transmission path based on the second feedback message.

[0089] The order in which the second probe data packets associated with the second feedback message are configured to be sent to the first device is later than the order in which the second probe data packets associated with the remaining first feedback messages other than the second feedback message in at least one first feedback message are configured to be sent to the first device. In other words, the second feedback message is the first feedback message generated in response to the last second probe data packet received by the first device in at least one first feedback message. The total number of second probe data packets and third probe data packets recorded in the first type data content of the second feedback message is greater than the total number of second probe data packets and third probe data packets recorded in the first type data content of the remaining first feedback messages other than the second feedback message in at least one first feedback message.

[0090] Optionally, determining a second feedback message from at least one first feedback message includes: obtaining third-type data content in each first feedback message in at least one first feedback message, the third-type data content recorded in the first feedback message being used to indicate an order in which second probe data packets associated with the first feedback message are sent among multiple first probe data packets; determining a second feedback message from at least one first feedback message based on the third-type data content in each first feedback message; wherein, the order in which the second probe data packets indicated by the third-type data content in the second feedback message are sent to the first device end is later than the order in which the second probe data packets indicated by the third-type data content in the remaining first feedback messages other than the second feedback message in at least one first feedback message are sent to the first device end.

[0091] Optionally, determining the packet loss rate of the first transmission path based on the second feedback message includes: the second device end can count a first number and a second number of second probe data packets based on the second feedback message, where the first number is the number of first probe data packets that have not been successfully received by the first device end or have not been successfully sent from the second device end to the first device end, and the second number is the number of first probe data packets that have been sent from the second device end to the first device end. Furthermore, the packet loss rate of the first transmission path from the second device end to the first device end is determined based on the first number and the second number.

[0092] As an optional but non-limiting implementation, in which a multipath feedback condition is triggered during the process of sending a first feedback message from a first device end to a second device end, and the first feedback message is sent from the first device end to the second device end using different transmission paths, determining the packet loss rate of the first transmission path based on the second feedback message includes the following steps:

[0093] In response to the second feedback message being the first feedback message sent by the first device end to the second device end after the multi-path feedback condition is triggered, the packet loss rate of the first transmission path is determined according to the first information, and the first device end is used to send the unsent first feedback message to the second device end using a different transmission path in response to the triggering of the multi-path feedback condition. The first information is determined based on whether the first device end has received the second probe data packet and whether the first device end has received the third probe data packet indicated by the first type of data content of the second feedback message; in response to the second feedback message being the first feedback message that has been sent by the first device end to the second device end before the multi-path feedback condition is triggered, the packet loss rate of the first transmission path is determined according to the first information and the second information, and the second information is used to indicate the number of first probe data packets sent after the second probe data packet associated with the second feedback message.

[0094] Optionally, the first information includes the reception status of whether the first device end has received the second probe data packet and whether the first device end has received the third probe data packet, as indicated by the first type of data content of the second feedback message, and the total number of second probe data packets and third probe data packets that the first device end has not received until the second probe data packet. The third information is the number of first probe data packets that the second device end has sent to the first device end until the second probe data packet. The third information can also be the total number of second probe data packets and third probe data packets recorded for the first type of data content of the second feedback message or the sending sequence number recorded for the third type of data content of the second feedback message. Determining the packet loss rate of the first transmission path based on the first information can include: determining the packet loss rate of the first transmission path based on the ratio of the first information to the third information.

[0095] Optionally, the second information can be determined based on a difference between the number of the plurality of first probe data packets and a numerical value indicated by the third information, and is used to describe the number of first probe data packets sent after the second probe data packet associated with the second feedback message. Determining the packet loss rate of the first transmission path based on the first information and the second information includes: determining the packet loss rate of the first transmission path based on a ratio between the numerical values ​​of the first information and the second information and the number of the plurality of first probe data packets.

[0096] For example, assuming that the total number of first probe data packets of a probe group is n, the sending order number of the third type data content record of the second feedback message is i, and the first type data content record of the first feedback message has m first probe data packets that are not received on the first device end, considering that multiple transmission paths are introduced for the first probe packets at a preset proportion of the tails of multiple first probe data packets to perform a return strategy for the first feedback message, the following two cases are discussed:

[0097] In the first case, i∈((1-α)n, n], that is, the second feedback message is the first feedback message sent by the first device end to the second device end after the multipath feedback condition is triggered. The number of first probe data packets successfully sent from the second device end to the first device end can be counted as m according to the reception status of whether the first device end receives the second probe data packet and whether the first device end receives the third probe data packet recorded in the first type data of the last received second feedback message. At the same time, packets that cannot be judged can be ignored. At this time, the packet loss rate of the first transmission path from the second device end to the first device end is: At this time, the first information may include the number m of first detection data packets successfully sent from the second device end to the first device end, and the third information may be the sending sequence number i of the third type of data content record of the second feedback message.

[0098] In the second case, i∈(0, (1-α)n], that is, the second feedback message belongs to the first feedback message that has been sent by the first device end to the second device end before the multi-path feedback condition is triggered, representing the first detection packet at the tail of a preset proportion of multiple first detection data packets. Even if the multi-path feedback condition is triggered and multiple transmission paths are introduced to perform the return strategy of the first feedback message, no first feedback message is sent to the second device end after the second feedback message. At this time, the packet loss rate calculation accuracy is low, and the remaining first detection data packets after the second detection data packet associated with the second feedback message in the multiple first detection data packets are regarded as packet loss. Then, according to the reception status of whether the first device end receives the second detection data packet and whether the first device end receives the third detection data packet recorded in the first type data in the last received first feedback message, the number of first detection data packets successfully sent from the second device end to the first device end is counted as m. At this time, the packet loss rate is: The second information is the difference between the number n of the plurality of first detection data packets and the sending sequence number i of the third type data content record of the second feedback message indicated by the third information.

[0099] In addition to the first and second cases mentioned above, there is a third case, which is an optional but non-limiting implementation scheme. When the first device end uses different transmission paths to send at least one first feedback message to the second device end, in response to the second device end not receiving any first feedback message generated by the first device end, since the second device end did not receive any first feedback message, it indicates that each of the multiple first detection data packets has caused packet loss. At this time, it is determined that the packet loss rate of the first transmission path from the second device end to the first device end is 100%.

[0100] It can be understood that in the actual transmission process, the two situations that the second feedback message received by the second device end falls into the interval range corresponding to (0, (1-α)n] and the second device end does not receive any second feedback message should be avoided as much as possible, because it will reduce the accuracy of the packet loss rate calculation. It should be ensured that the first detection data packets extracted from the tail of the preset proportion of multiple first detection data packets should have at least one first detection data packet's first feedback message reach the second device end. Assuming that the packet loss rate when transmitting data packets from the first device end to the second device end using a heterogeneous network path is loss dp_ack , when the first transmission path is used to transmit data packets from the second device to the first device, the packet loss rate is loss. At this time, it should be ensured that Assuming loss dp_ack <0.5, when n=30, α=0.3, then It is ensured that at least one of the first feedback messages corresponding to the first detection data packets extracted from the tails of the first feedback messages corresponding to the multiple first detection data packets can reach the second device end.

[0101] As an optional but non-limiting implementation scheme, the protocol format used when the first detection data packet and the first feedback message are transmitted in this application is as follows: Figure 4 As shown, the payload of the header structure of the first detection data packet and the first feedback message of the present application is 22 bytes. The header structure of the first detection data packet and the first feedback message includes the following flag bit fields:

[0102] Magic flag field: 3 bytes, message check bit.

[0103] Version Flag Field & Packet Type Flag Field: Version and packet type each occupy 4 bits. A version value of 1 indicates the latest version number. The device can use the version flag field to distinguish between new and old versions. A packet type value of 0 indicates that a single transmission path returns the first feedback message, a value of 1 indicates that multiple transmission paths return the first feedback message, and a value of 2 indicates that no first feedback message is required.

[0104] timestamp flag field: WAN detection timestamp (millisecond accuracy), covering the range of 0-65535ms (about 65 seconds).

[0105] Group ID flag field: The detection group ID of the message, which is the last 16 bits of the seconds when the group detection is started.

[0106] seq ID in group flag field: the sending sequence number of the first detection data packet among multiple first detection data packets in the detection group.

[0107] The recv flags flag field, referred to as the receive flag field in this application, is a bitmap that marks the first detection data packet received by the first device end in the detection group (eg, 0x07 indicates that the first three first detection data packets have been received).

[0108] dst IP flag field: destination IP address.

[0109] srcID flag field: the logical number of the detection IP on the client (supports scenarios where the detection node has multiple IPs).

[0110] Dual ack IP flag field: The highly reliable target IP address for returning the first feedback message via multiple transmission paths. This field uses a pre-configured highly reliable target IP address (such as a carrier-grade BGP interconnection node or other physical direct connection to the node) to ensure that the first feedback message can bypass potential congestion or failures on the primary link and return to the secondary device via a highly reliable channel with a considerable degree of isolation from the primary link topology.

[0111] As can be seen from the above, the first type of data content is used to indicate the value result of the recv flags flag field, the second type of data content is used to indicate the value result of the packet type flag field and the dual ack IP flag field, and the third type of data content is used to indicate the value result of the group ID flag field.

[0112] This application program analyzes the performance of this application program from three aspects: recall rate, precision rate, and cost.

[0113] In terms of recall rate, in packet loss detection, whether it is conventional two-way detection or unidirectional packet loss detection in the present application, when packet loss occurs, it can be detected and there is no packet loss omission. Therefore, the recall rate of both methods is 100%.

[0114] In terms of accuracy, in order to more clearly illustrate the technical advantages of the present invention, we will take the network packet loss scenario as an example to compare and analyze the difference in measurement accuracy between the conventional two-way detection method for packet loss detection and the solution of this application. In actual scenarios, when the packet loss rate statistics are within a certain range compared with the actual value (for example, <1%), it can be considered accurate. As the gap between the calculated value and the actual value gradually increases, the detection accuracy gradually decreases. When the gap is large enough (for example, >10%), it can be considered that the detected packet loss rate value is meaningless, and the detection accuracy is 0. Assuming that the forward packet loss rate is loss data, the packet loss rate is loss, and the accuracy of the packet loss detection method is defined as follows:

[0115]

[0116] Assuming that the number of detected packet losses is m and the actual number of packet losses is k, the corresponding accuracy rates are divided into the following three cases:

[0117] 1. Completely accurate: When |mk| = 0, Precision = 1.

[0118] 2. Linear decrease: When |mk| = 1 or 2 (|loss-loss data |=3.33% or 6.67%), the accuracy is calculated as linear difference:

[0119] 3. Meaningless: When |mk| ≥ 3, precision = 0. Therefore, the following relationship holds:

[0120]

[0121] Therefore, the overall accuracy is as follows:

[0122] Precision overall =P(|mk|=0)+0.7407*P(|mk=1)+0.3704*P(|mk|=2).

[0123] Next, we verify the accuracy of conventional detection and unidirectional packet loss detection methods respectively:

[0124] For conventional detection of packet loss, assume that the forward packet loss rate is loss data , the reverse packet loss rate is loss ack During a typical detection process, if no packets are lost on the forward path (A→B), but are lost on the reverse path (B→A), a misjudgment will occur. The three cases of |mk| = 0, |mk| = 1, and |mk| = 2 correspond to 0, 1, and 2 misjudged packets, respectively. The calculation results are as follows:

[0125]

[0126] Afterwards, the comprehensive accuracy can be calculated according to the formula described above.

[0127] For one-way packet loss detection, assume that the sequence number of the last received data packet is i. Given that there are differences in the methods for calculating the packet loss rate in the cases of i = 0, i ∈ (0, (1 - α)n], and i ∈ ((1 - α)n, n], in order to achieve accurate calculation of the precision rate, the following discussion is carried out according to the sequence number i of the last received data packet in the following cases:

[0128] When i = 0, it indicates that the first feedback packet of the first detection packet of this detection group has not received any response, meaning that all first detection packets are lost on the forward path (A → B) or the reverse path (B → A). At this time, all first detection packets are regarded as lost. The three cases of |m - k| = 0, |m - k| = 1, and |m - k| = 2 correspond to the following situations respectively: all first detection packets are lost on the forward path (A → B); one first detection packet is not lost on the forward path (A → B), but is lost on the reverse path (B → A); two first detection packets are not lost on the forward path (A → B), but are lost on the reverse path (B → A). Therefore, the following calculations exist:

[0129]

[0130]

[0131] It should be noted that there are differences in the packet loss rate of the first detection packet on the reverse path (B → A) before and after adopting the multi-path redundant feedback strategy.

[0132] When 0 < i ≤ n - nα, that is, the last received first feedback packet (ACK) is in the stage before the return strategy of using multiple transmission paths for the first feedback packet. At this time, it can be known about the packet loss situation of the first detection packet i and the first detection packets before it on the forward path (A → B), and the subsequent first detection packets are regarded as lost. When calculating the precision rate, only the accuracy of calculating the packet loss rate of the subsequent data packets needs to be considered. The three cases of |m - k| = 0, |m - k| = 1, and |m - k| = 2 correspond to the following situations respectively: all first detection packets after the first detection packet i are all lost on the forward path (A → B); one of all the first data packets after the first detection packet i is not lost on the forward path (A → B), but is lost on the reverse path (B → A); two of all the first detection packets after the first detection packet i are not lost on the forward path (A → B), but are lost on the reverse path (B → A). At this time, the following calculations exist:

[0133]

[0134] When \(n - n\alpha < i\leq n\), that is, the last received first feedback message (ACK) is in the stage after the return strategy of the first feedback message using multiple transmission paths. At this time, the subsequent packets are ignored, and the one-way packet loss detection accuracy is approximately equal to 1. At this time, the probability \(P\) of this situation occurring i is as follows:

[0135] \(P\) i \(=(1 - loss\) data )·(1 - loss\) ack ·loss\) dp_ack )·[loss\) data +(1 - loss\) data )·loss\) ack ·loss\) dp_ack n- ;

[0136] Among them, in the above formula, \((1 - loss\) data )·(1 - loss\) ack ·loss\) dp_ack ) represents the probability of receiving the ACK packet with sequence number \(i\); \((loss\) data +(1 - loss\) data )·loss\) ack ·loss\) dp_ack ) n-i represents the probability that all packets after the ACK packet with sequence number \(i\) are lost after starting to adopt the return strategy of the first feedback message using multiple transmission paths. At this time, the following calculations are as follows:

[0137]

[0138] In summary, the overall reported packet loss rate using one-way packet loss detection is:

[0139] [[ID=�3]]

[0140] The following Table 1 shows the accuracy rates of packet loss detection by conventional detection and one-way packet loss detection under different \(loss\) when \(n = 30\), \(\alpha = 0.3\), data and \(loss\) ack conditions:

[0141] Table 1

[0142]

[0143] It can be seen from the first three groups of data that when \(loss\) data = 0 and \(loss\) ack ≠ 0, the accuracy rate of conventional detection cannot detect \(loss\) ack ​≠0, the loss ack The increase in loss may lead to misjudgment, which in turn leads to a decrease in accuracy. At the same time, the one-way packet loss detection method of this application solution can still ensure a high accuracy. data =0.05, that is, when a small amount of data packets are lost on the corresponding link, the accuracy of the one-way packet loss detection method of the present application solution is still high in the network environment. data =0.3, that is, when the link packet loss rate further increases, the accuracy of the one-way packet loss detection method of the present application solution is still much higher than that of the conventional detection method. In summary, compared with conventional detection, the one-way packet loss detection proposed in the present application solution has a higher accuracy rate.

[0144] In terms of cost control, optimizing conventional detection to one-way packet loss detection significantly improves the accuracy of network detection data. This one-way packet loss detection mechanism allows for more accurate link status information, reduces the probability of transit along the path, and effectively reduces the cost of transit bandwidth. This optimization is particularly applicable to specific scenarios, such as domestic cross-provincial scenarios and global long-distance transmission scenarios involving cross-continental and cross-ISP networks. In these scenarios, the complexity of path transit and the cost pressure of bandwidth resources are particularly prominent. A one-way packet loss detection strategy can optimize routes at a lower cost.

[0145] In the technical solution of the embodiment of the present disclosure, the second device end can sequentially send multiple first detection data packets to the first device end, and the first detection data packet is used to detect packet loss on the first transmission path from the second device end to the first device end. For the second detection data packet that can be received by the first device end among the multiple first detection data packets, the first device end will generate a first feedback message in response to the second detection data packet. When generating the first feedback message, the first device end will record whether the second detection data packet and the first detection data packet in the multiple first detection data packets that are sent before the second detection data packet are received by the first device end. When the first device end sends the first feedback message to the second After the device end sends, the second device end only needs to obtain the first feedback message fed back from the first device end to the second device end as much as possible. Based on the first feedback message fed back by the first device end, the second device end can know which first detection data packets the first device end has received and which first detection data packets have not been received. There is no need for the second device end to trigger an additional complex query process, which reduces the interactive performance overhead. The packet loss situation of the entire link from the second device end to the first device end can be fully known, forming a complete end-to-end packet loss detection closed loop, realizing end-to-end unidirectional packet loss detection, and then the transmission path from the second device end to the first device end can be further optimized based on the detected packet loss rate.

[0146] Figure 5This is a structural schematic diagram of a packet loss detection device provided in an embodiment of the present disclosure. The embodiment of the present disclosure is applicable to situations where packet loss detection is performed from end to end, especially situations where one-way packet loss rate detection is performed from end to end. The packet loss detection device can be implemented in the form of software and / or hardware and is generally integrated into any electronic device with network communication capabilities. The electronic device can be a mobile terminal, PC or server, such as a computer, laptop, smartphone, or tablet computer.

[0147] like Figure 5 As shown, the packet loss detection device of the embodiment of the present disclosure may include the following:

[0148] A sending module 510 is configured to sequentially send a plurality of first detection data packets to the first device end, wherein the first detection data packets are used to perform packet loss detection on a first transmission path from the second device end to the first device end;

[0149] A receiving module 520 is configured to obtain at least one first feedback message generated by the first device end, each first feedback message including first-type data content generated by the first device end in response to a second probe data packet, the second probe data packet being a probe data packet received by the first device end among the multiple first probe data packets, the first-type data content being used to indicate whether the first device end has received the second probe data packet, and the first-type data content being further used to indicate whether the first device end has received a third probe data packet, the third probe data packet being a first probe data packet in the multiple first probe data packets that is sent before the second probe data packet;

[0150] The detection module 530 is configured to determine a packet loss condition of the first transmission path according to the at least one first feedback message.

[0151] Based on the above embodiment, optionally, the sequentially sending the plurality of first detection data packets to the first device includes:

[0152] Obtain multiple first detection data packets of the same detection group, the detection group identifier associated with each first detection data packet in the multiple first detection data packets is the detection group identifier of the detection group to which the first detection data packet belongs, and the detection group identifier associated with the first detection data packet is used to instruct the first device end to aggregate and count the first detection data packets of the same detection group; and send the multiple first detection data packets of the same detection group to the first device end sequentially.

[0153] Based on the above embodiment, optionally, the first type of data content is recorded using the values ​​of different flag bits in the receiving flag field included in the first feedback message, the value of the flag bit in the receiving flag field is used to indicate whether the first device end has received the second detection data packet, and the value of the flag bit in the receiving flag field is also used to indicate whether the first device end has received the third detection data packet.

[0154] Based on the above embodiment, optionally, obtaining at least one first feedback message generated by the first device includes:

[0155] Receive a first feedback message sent by the first device end in response to the second type of data content in the second detection data packet, where the second type of data content in the second detection data packet is used to indicate whether the first device end triggers the use of at least two second transmission paths to send the first feedback message to the second device end, and each transmission path of the at least two second transmission paths is a different heterogeneous network path from the first device end to the second device end.

[0156] Based on the above embodiment, optionally, the at least two second transmission paths include a third transmission path, the third transmission path is a return path of the first transmission path, the second transmission path other than the third transmission path in the at least two second transmission paths and the third transmission path in network topology are more isolated from each other than a preset isolation degree, and the second transmission path other than the third transmission path in the at least two second transmission paths is used to avoid potential congestion or failure of the third transmission path when the first feedback message is transmitted from the first device end to the second device end.

[0157] Based on the above embodiment, optionally, the sequentially sending the plurality of first detection data packets to the first device includes:

[0158] In response to a fourth probe data packet among the multiple first probe data packets satisfying a multi-path feedback condition, the second type data content of the fourth probe data packet is configured to instruct the first device end to trigger the use of at least two second transmission paths to send the first feedback message to the second device end; the fourth probe data packet is a first probe data packet to be transmitted to the first device end configured according to the sending order of each first probe data packet among the multiple first probe data packets, and the multi-path feedback condition is used to indicate the conditions that need to be met when the first device end sends the first feedback message generated by the fourth probe data packet to the second device end using different transmission paths;

[0159] The fourth detection data packet is sent sequentially to the first device end.

[0160] Based on the above embodiment, optionally, the fourth probe data packet satisfies a multipath feedback condition including at least one of the following:

[0161] Before the fourth probe data packet is sent to the first device end, there are multiple fifth probe data packets and the number of the multiple fifth probe data packets is greater than a preset number, and the multiple fifth probe data packets are first probe data packets that have been continuously sent to the first device end before the fourth probe data packet and have not been received by the first device end;

[0162] When the fourth probe data packet is sent to the first device end, there are multiple sixth probe data packets and the number of the multiple sixth probe data packets in the multiple first probe data packets accounts for more than a preset proportion, and the multiple sixth probe data packets are the first probe data packets that have been sent to the first device end by the time the fourth probe data packet is sent;

[0163] The fourth probe data packet sent to the first device end belongs to a preset proportion of first probe data packets extracted from the tails of the multiple first probe data packets, and the multiple first probe data packets are sequentially sorted according to the sending order;

[0164] The network quality of a third transmission path used when sending the first feedback message from the first device end to the second device end is less than a preset network quality, and the third transmission path is a return path of the first transmission path.

[0165] Based on the foregoing embodiment, optionally, determining the packet loss situation of the first transmission path according to the at least one first feedback message includes:

[0166] Determining a second feedback message from the at least one first feedback message; the sending order of the second probe data packet associated with the second feedback message to the first device end is located after the sending order of the second probe data packets associated with the remaining first feedback messages other than the second feedback message in the at least one first feedback message to the first device end;

[0167] Determine a packet loss rate of the first transmission path according to the second feedback message.

[0168] Based on the above embodiment, optionally, when a multipath feedback condition is triggered during the process of sending the first feedback message from the first device end to the second device end, and the first feedback message is sent from the first device end to the second device end using different transmission paths, determining the packet loss rate of the first transmission path according to the second feedback message includes:

[0169] In response to the second feedback message being the first feedback message sent by the first device end to the second device end after a multipath feedback condition is triggered, determining a packet loss rate of the first transmission path based on first information, the first device end being configured to send the unsent first feedback message to the second device end using a different transmission path in response to the triggering of the multipath feedback condition, wherein the first information is determined based on whether the first device end has received the second probe data packet and whether the first device end has received the third probe data packet, as indicated by a first type of data content in the second feedback message;

[0170] In response to the second feedback message being the first feedback message that has been sent by the first device end to the second device end before the multipath feedback condition is triggered, the packet loss rate of the first transmission path is determined based on the first information and the second information, and the second information is used to indicate the number of first probe data packets sent after the second probe data packet associated with the second feedback message.

[0171] In the technical solution of the embodiment of the present disclosure, the second device end can sequentially send multiple first detection data packets to the first device end, and the first detection data packet is used to detect packet loss on the first transmission path from the second device end to the first device end. For the second detection data packet that can be received by the first device end among the multiple first detection data packets, the first device end will generate a first feedback message in response to the second detection data packet. When generating the first feedback message, the first device end will record whether the second detection data packet and the first detection data packet in the multiple first detection data packets that are sent before the second detection data packet are received by the first device end. When the first device end sends the first feedback message to the second After the device end sends, the second device end only needs to obtain the first feedback message fed back from the first device end to the second device end as much as possible. Based on the first feedback message fed back by the first device end, the second device end can know which first detection data packets the first device end has received and which first detection data packets have not been received. There is no need for the second device end to trigger an additional complex query process, which reduces the interactive performance overhead. The packet loss situation of the entire link from the second device end to the first device end can be fully known, forming a complete end-to-end packet loss detection closed loop, realizing end-to-end unidirectional packet loss detection, and then the transmission path from the second device end to the first device end can be further optimized based on the detected packet loss rate.

[0172] The packet loss detection device provided in the embodiments of the present disclosure can execute the packet loss detection method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects for executing the packet loss detection method.

[0173] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

[0174] Figure 6 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Figure 6 , which shows an electronic device (eg Figure 6 The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0175] like Figure 6 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the electronic device 600 are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0176] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0177] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for executing the packet loss detection method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the packet loss detection method of the embodiment of the present disclosure are performed.

[0178] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0179] The electronic device provided in the embodiment of the present disclosure and the packet loss detection method provided in the above embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0180] An embodiment of the present disclosure provides a computer storage medium having a computer program stored thereon. When the program is executed by a processor, the packet loss detection method provided in the above embodiment is implemented.

[0181] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0182] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0183] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0184] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: sequentially sends multiple first probe data packets to the first device end, and the first probe data packet is used to detect packet loss on the first transmission path from the second device end to the first device end; obtains at least one first feedback message generated by the first device end, each first feedback message includes a first type of data content generated by the first device end in response to the second probe data packet, the second probe data packet is a probe data packet received by the first device end among the multiple first probe data packets, the first type of data content is used to indicate whether the first device end has received the second probe data packet, and the first type of data content is also used to indicate whether the first device end has received a third probe data packet, and the third probe data packet is a first probe data packet in the multiple first probe data packets whose sending order is before the second probe data packet; determines the packet loss situation of the first transmission path according to the at least one first feedback message.

[0185] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0186] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0187] The units involved in the embodiments described in this disclosure may be implemented in software or hardware. In some cases, the name of a unit does not limit the unit itself. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses."

[0188] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0189] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0190] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0191] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0192] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A packet loss detection method, characterized in that: The method comprises: Sending a plurality of first detection data packets to the first device end in sequence, wherein the first detection data packets are used to detect packet loss on a first transmission path from the second device end to the first device end; Obtain at least one first feedback message generated by the first device end, each first feedback message including a first type of data content generated by the first device end in response to a second probe data packet, the second probe data packet being a probe data packet received by the first device end among the multiple first probe data packets, the first type of data content being used to indicate whether the first device end has received the second probe data packet, and the first type of data content being further used to indicate whether the first device end has received a third probe data packet, the third probe data packet being a first probe data packet in the multiple first probe data packets whose sending order precedes the second probe data packet; Determine a packet loss situation of the first transmission path according to the at least one first feedback message.

2. The method according to claim 1, characterized in that The sequentially sending the plurality of first detection data packets to the first device end includes: Obtain multiple first detection data packets of the same detection group, where the detection group identifier associated with each first detection data packet in the multiple first detection data packets is the detection group identifier of the detection group to which the first detection data packet belongs, and the detection group identifier associated with the first detection data packet is used to instruct the first device end to perform aggregate statistics on the first detection data packets of the same detection group; Multiple first detection data packets of the same detection group are sequentially sent to the first device end.

3. The method according to claim 1, characterized in that The first type of data content is recorded using the values ​​of different flag bits in the receiving flag field included in the first feedback message. The value of the flag bit in the receiving flag field is used to indicate whether the first device end has received the second detection data packet. The value of the flag bit in the receiving flag field is also used to indicate whether the first device end has received the third detection data packet.

4. The method according to claim 1, wherein The obtaining of at least one first feedback message generated by the first device includes: Receive a first feedback message sent by the first device end in response to the second type of data content in the second detection data packet, where the second type of data content in the second detection data packet is used to indicate whether the first device end triggers the use of at least two second transmission paths to send the first feedback message to the second device end, and each transmission path of the at least two second transmission paths is a different heterogeneous network path from the first device end to the second device end.

5. The method according to claim 4, characterized in that The at least two second transmission paths include a third transmission path, where the third transmission path is a return path of the first transmission path. The second transmission paths other than the third transmission path among the at least two second transmission paths have a network topology isolation from the third transmission path that is greater than a preset isolation. The second transmission paths other than the third transmission path among the at least two second transmission paths are used to avoid potential congestion or failure of the third transmission path when the first feedback message is transmitted from the first device end to the second device end.

6. The method according to claim 1 or 4, characterized in that The sequentially sending the plurality of first detection data packets to the first device end includes: In response to a fourth probe data packet among the multiple first probe data packets satisfying a multi-path feedback condition, the second type data content of the fourth probe data packet is configured to instruct the first device end to trigger the use of at least two second transmission paths to send the first feedback message to the second device end; the fourth probe data packet is a first probe data packet to be transmitted to the first device end configured according to the sending order of each first probe data packet among the multiple first probe data packets, and the multi-path feedback condition is used to indicate the conditions that need to be met when the first device end sends the first feedback message generated by the fourth probe data packet to the second device end using different transmission paths; The fourth detection data packet is sent sequentially to the first device end.

7. The method according to claim 6, characterized in that The fourth probe data packet satisfies the multipath feedback condition including at least one of the following: Before the fourth probe data packet is sent to the first device end, there are multiple fifth probe data packets and the number of the multiple fifth probe data packets is greater than a preset number, and the multiple fifth probe data packets are first probe data packets that have been continuously sent to the first device end before the fourth probe data packet and have not been received by the first device end; When the fourth probe data packet is sent to the first device end, there are multiple sixth probe data packets and the number of the multiple sixth probe data packets in the multiple first probe data packets accounts for more than a preset proportion, and the multiple sixth probe data packets are the first probe data packets that have been sent to the first device end by the time the fourth probe data packet is sent; The fourth probe data packet sent to the first device belongs to a preset proportion of the first probe data packets extracted from the tails of the multiple first probe data packets, and the multiple first probe data packets are sequentially sorted according to the sending order; The network quality of a third transmission path used when sending the first feedback message from the first device end to the second device end is less than a preset network quality, and the third transmission path is a return path of the first transmission path.

8. The method according to claim 1 or 4, characterized in that The determining, according to the at least one first feedback message, a packet loss condition of the first transmission path includes: Determining a second feedback message from the at least one first feedback message; the sending order of the second probe data packet associated with the second feedback message to the first device end is located after the sending order of the second probe data packets associated with the remaining first feedback messages other than the second feedback message in the at least one first feedback message to the first device end; Determine a packet loss rate of the first transmission path according to the second feedback message.

9. The method according to claim 8, characterized in that When a multipath feedback condition is triggered during the process of sending the first feedback message from the first device end to the second device end, and the first feedback message is sent from the first device end to the second device end using different transmission paths, determining a packet loss rate of the first transmission path according to the second feedback message includes: In response to the second feedback message being the first feedback message sent by the first device end to the second device end after a multipath feedback condition is triggered, determining a packet loss rate of the first transmission path based on first information, the first device end being configured to send the unsent first feedback message to the second device end using a different transmission path in response to the triggering of the multipath feedback condition, wherein the first information is determined based on whether the first device end has received the second probe data packet and whether the first device end has received the third probe data packet, as indicated by a first type of data content in the second feedback message; In response to the second feedback message being the first feedback message that has been sent by the first device end to the second device end before the multipath feedback condition is triggered, the packet loss rate of the first transmission path is determined based on the first information and the second information, and the second information is used to indicate the number of first probe data packets sent after the second probe data packet associated with the second feedback message.

10. A packet loss detection device, characterized in that: The device comprises: a sending module, configured to sequentially send a plurality of first detection data packets to the first device end, wherein the first detection data packets are used to perform packet loss detection on a first transmission path from the second device end to the first device end; a receiving module, configured to obtain at least one first feedback message generated by the first device end, each first feedback message including a first type of data content generated by the first device end in response to a second probe data packet, the second probe data packet being a probe data packet received by the first device end among the multiple first probe data packets, the first type of data content being used to indicate whether the first device end has received the second probe data packet, and the first type of data content being further used to indicate whether the first device end has received a third probe data packet, the third probe data packet being a first probe data packet in the multiple first probe data packets that is sent before the second probe data packet; A detection module is used to determine the packet loss situation of the first transmission path according to the at least one first feedback message.

11. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the packet loss detection method according to any one of claims 1 to 9.

12. A storage medium comprising computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, are used to perform the packet loss detection method according to any one of claims 1 to 9.

Images