Service session adjustment method and device, storage medium and electronic equipment

Abstract

The invention discloses a service session adjustment method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring a current set bandwidth occupied by a session set consisting of a plurality of service sessions, and acquiring a first reference bandwidth feature matched with the session set; when the current set bandwidth feature determined according to the current set bandwidth is not matched with the first reference bandwidth feature, determining subset bandwidth features corresponding to a plurality of session subsets included in the session set, and obtaining second reference bandwidth features of the plurality of session subsets; determining a target session subset from the plurality of session subsets according to a comparison result between the plurality of subset bandwidth features and respective corresponding second reference bandwidth features; and performing a transmission adjustment operation on at least one service session in the target session subset. According to the invention, the technical problem that the adjustment response speed of the service session is slow is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of computer, in particular, to a method and device for adjusting service session, storage medium and electronic equipment. BACKGROUND

[0002] With the rapid development of the Internet, a large number of online interactive services, such as online search, shopping, live broadcast, etc., need to respond to high-frequency user requests at a very fast speed. In data center, any link that causes delay will greatly affect the access experience of the end user.

[0003] The prior art can usually only reduce the speed of the service session when the congestion state is detected. But this situation has usually caused poor user experience. Therefore, the prior art of adjusting service session has the technical problem of slow response speed.

[0004] For the above problems, there is no effective solution at present. SUMMARY

[0005] The embodiments of the present application provide a method and device for adjusting service session, storage medium and electronic equipment to at least solve the technical problem of slow response speed of service session adjustment.

[0006] According to an aspect of the embodiments of the present application, a method for adjusting service session is provided, comprising: obtaining a current collection bandwidth occupied by a session collection composed of a plurality of service sessions, and obtaining a first reference bandwidth characteristic matched with the session collection, wherein the first reference bandwidth characteristic is used to represent the bandwidth variation of the service collection bandwidth occupied by the session collection in a target statistical period; in the case that the current collection bandwidth characteristic determined according to the current collection bandwidth does not match the first reference bandwidth characteristic, determining a plurality of subset bandwidth characteristics corresponding to a plurality of session subsets included in the session collection respectively, and obtaining a second reference bandwidth characteristic of each of the plurality of session subsets, wherein the second reference bandwidth characteristic is used to represent the bandwidth variation of the service subset bandwidth occupied by the session subset in the target statistical period; determining a target session subset from the plurality of session subsets according to the comparison result between the plurality of subset bandwidth characteristics and the second reference bandwidth characteristic corresponding to each of the plurality of session subsets; and performing a transmission adjustment operation on at least one service session in the target session subset.

[0007] According to another aspect of the present invention, a service session adjustment apparatus is also provided, comprising: an acquisition unit, configured to acquire the current set bandwidth occupied by a session set consisting of multiple service sessions, and acquire a first reference bandwidth feature matching the session set, wherein the first reference bandwidth feature is used to characterize the bandwidth change of the service set bandwidth occupied by the session set within a target statistical period; a first determination unit, configured to determine the subset bandwidth feature corresponding to each of the multiple session subsets included in the session set when the current set bandwidth feature determined based on the current set bandwidth does not match the first reference bandwidth feature, and acquire a second reference bandwidth feature for each of the multiple session subsets, wherein the second reference bandwidth feature is used to characterize the bandwidth change of the service subset bandwidth occupied by the session subset within the target statistical period; a second determination unit, configured to determine a target session subset from the multiple session subsets based on the comparison result between the multiple subset bandwidth features and their respective corresponding second reference bandwidth features; and an adjustment unit, configured to perform a transmission adjustment operation on at least one service session in the target session subset.

[0008] According to another aspect of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer program, wherein the computer program is configured to execute the adjustment method of the above-described business session when it is run.

[0009] According to another aspect of the embodiments of this application, a computer program product is provided, the computer program product including a computer program / instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer program / instructions from the computer-readable storage medium, and executes the computer program / instructions, causing the computer device to perform the adjustment method of the above-described business session.

[0010] According to another aspect of the present invention, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to execute the above-described business session adjustment method through the computer program.

[0011] The implementation method provided in this application enables layer-by-layer drill-down and precise control of bandwidth anomalies in service session sets, thereby significantly improving bandwidth utilization efficiency and service assurance capabilities in leased line congestion scenarios. Specifically, the above-mentioned implementation method of this application first obtains the current set bandwidth of a session set consisting of multiple service sessions, and introduces a first reference bandwidth feature as a historical bandwidth change benchmark within a target statistical period; when the current set bandwidth feature does not match the first reference bandwidth feature, drill-down analysis of the session set is automatically triggered, splitting the session set into multiple session subsets, and obtaining the subset bandwidth feature and its corresponding second reference bandwidth feature for each subset; subsequently, by comparing the subset bandwidth feature with the second reference bandwidth feature, the target session subset with the highest bandwidth anomaly contribution is accurately identified; finally, transmission adjustment operations are performed only on the service sessions in the target session subset, avoiding collateral damage to normal services.

[0012] The above-described implementation method of this application achieves closed-loop control from aggregate-level anomalies to precise subset-level location. Since only the subset of sessions that truly cause bandwidth deviations needs to be rate-limited or scheduled, link resources occupied by abnormal traffic can be dynamically released while ensuring critical service bandwidth. This solves the problems of inadvertently damaging normal services and low bandwidth recovery efficiency caused by "one-size-fits-all" overall rate limiting in related technologies. Attached Figure Description

[0013] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0014] Figure 1 This is an optional hardware structure block diagram according to an embodiment of the present invention;

[0015] Figure 2 This is a flowchart of an optional service session adjustment method according to an embodiment of the present invention;

[0016] Figure 3 This is a flowchart of another optional service session adjustment method according to an embodiment of the present invention;

[0017] Figure 4 This is a flowchart of another optional service session adjustment method according to an embodiment of the present invention;

[0018] Figure 5 This is a schematic diagram of the structure of an optional service session adjustment system according to an embodiment of the present invention;

[0019] Figure 6 This is a schematic diagram of the structure of an optional service session adjustment device according to an embodiment of the present invention;

[0020] Figure 7 This is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present invention. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding access points are provided for users to choose to authorize or refuse. For example, interfaces are set up between this system and relevant users or organizations, providing users with corresponding access points to choose to agree to or refuse automated decision-making results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.

[0024] The methods and embodiments provided in this application can be executed on a server device or a similar computing device. Taking running on a server device as an example, Figure 1 This is a hardware structure block diagram of a server device for a service session adjustment method according to an embodiment of this application. For example... Figure 1 As shown, the server device may include one or more ( Figure 1Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The server device may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the server equipment described above. For example, the server equipment may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0025] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to a method for adjusting the read voltage in the memory according to an embodiment of this application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to server devices via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0026] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider for the server device. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0027] Understandably, during the adjustment of business sessions, conventional traffic control methods typically control and manage the overall traffic. However, this extensive management approach can severely impact the transmission efficiency of business data in specific business scenarios.

[0028] To address the aforementioned problems, according to one aspect of the present invention, a method for adjusting a service session is provided, such as... Figure 2 As shown, the above-described method for adjusting business sessions can be applied to the adjustment nodes of business sessions in a distributed system, and may include the following steps:

[0029] S202, obtain the current set bandwidth occupied by the session set consisting of multiple service sessions, and obtain the first reference bandwidth feature matching the session set, wherein the first reference bandwidth feature is used to characterize the bandwidth change of the service set bandwidth occupied by the session set within the target statistical period;

[0030] S204, if the current set bandwidth feature determined based on the current set bandwidth does not match the first reference bandwidth feature, determine the subset bandwidth feature corresponding to each of the multiple session subsets included in the session set, and obtain the second reference bandwidth feature of each of the multiple session subsets, wherein the second reference bandwidth feature is used to characterize the bandwidth change of the service subset bandwidth occupied by the session subset within the target statistical period.

[0031] S206, Based on the comparison results between the bandwidth features of multiple subsets and their respective second reference bandwidth features, determine the target session subset from multiple session subsets;

[0032] S208, Perform a transport adjustment operation on at least one service session in the target session subset.

[0033] It should be noted that the session set in step S202 above can be an abstract bandwidth management unit obtained by logically aggregating several service sessions with the same service attributes (such as the same VPN, the same five-tuple prefix, the same QoS level, or the same customer contract number).

[0034] In this embodiment of the application, the current collection bandwidth can be obtained through one or more second-level sampling interfaces and calculated in real time in Mbps or pps.

[0035] Furthermore, the first reference bandwidth characteristic can be a baseline curve obtained by smoothing or removing extreme values ​​from the historical bandwidth sequence of the same session set within the target statistical period (e.g., the most recent 7×24 hours), which is used to reflect the bandwidth usage change pattern of the service under normal working conditions.

[0036] Optionally, the first reference bandwidth feature can be an hourly range from maximum to minimum value, or a weighted moving average curve. In another optional implementation, weekdays and weekends can be modeled separately to obtain two sets of reference curves to improve the comparison accuracy.

[0037] Furthermore, the aforementioned bandwidth variation can include both the absolute value of the rate and the first-order difference of the rate (i.e., the slope), thereby enabling the simultaneous detection of both sudden events and drift states.

[0038] Furthermore, in step S204 above, the mismatch between the previous set bandwidth characteristics and the first reference bandwidth characteristics can be used to indicate that at least one bandwidth description parameter represented by the current set bandwidth characteristics exceeds the preset upper limit threshold or is lower than the lower limit threshold of the first reference bandwidth characteristics, or that the deviation between the current bandwidth slope and the reference slope exceeds the allowable error band.

[0039] If the bandwidth characteristics of the initial set do not match the first reference bandwidth characteristics, multiple session subsets can be further obtained from the session set. The dimensions of difference between different session subsets include, but are not limited to: source / destination IP address ranges, port number ranges, DSCP labels, application layer protocol types, or client sub-accounts. Each session subset continues to inherit a second reference bandwidth characteristic that matches it. This characteristic is also generated based on the historical bandwidth sequence of the subset within the target statistical period, and is used to measure whether the current bandwidth usage is at a more granular level.

[0040] Optionally, if a session subset in a set of multiple session subsets has insufficient sampling points within a historical period, the clustering benchmark of other subsets in the same class can be used as its second reference bandwidth feature. In another implementation, transfer learning can be used to decompose the set-level reference curve according to the subset weights to obtain the initial second reference bandwidth feature, which can then be continuously corrected through online learning.

[0041] Furthermore, in S206, the method for determining the above comparison results may include, but is not limited to, one or more of the following comparison methods: deviation rate sorting comparison, bandwidth percentage increment sorting comparison, or distribution similarity comparison.

[0042] In one alternative implementation, the deviation rates between the current subset bandwidth rate and the second reference bandwidth feature can be sorted in descending order, and the N (N≥1) session subsets with the highest deviation rates can be marked as candidate target session subsets. Subsequently, if the current bandwidth ratio of a candidate subset is also higher than its historical reference ratio, it is finally determined as the target session subset.

[0043] Furthermore, in another alternative implementation, a machine learning anomaly detection model (such as IsolationForest or LSTM prediction residual) can be introduced to jointly evaluate the bandwidth features of multi-dimensional subsets. The subset of sessions whose anomaly scores output by the model are higher than the preset threshold can be directly used as the target subset of sessions, thereby improving the sensitivity to complex burst traffic.

[0044] It is understood that the transmission adjustment operation in step S208 includes, but is not limited to, at least one of the following:

[0045] Adjustment Method 1: Apply rate limiting to the entire subset of the target sessions. The rate limit value is greater than the peak value of its second reference bandwidth characteristic and less than the remaining available bandwidth of the link.

[0046] Adjustment Method 2: Temporarily discard or reroute the lowest-priority single service session within this subset;

[0047] Adjustment method three: Send a reverse pressure signal to the upstream node to trigger that node to reduce the corresponding data transmission bandwidth.

[0048] By using at least one of the above adjustment methods, precise control can be applied only to the subset of target sessions that actually cause the anomalies, avoiding collateral damage to normal services, thereby achieving differentiated protection and rapid congestion relief in fixed bandwidth leased line scenarios.

[0049] Optionally, after the transmission adjustment operation is performed, the bandwidth recovery of the target session subset can continue to be monitored; when the subset bandwidth characteristics fall back to the allowable range of the second reference bandwidth characteristics within two consecutive monitoring periods, the adjustment strategy is automatically lifted to restore the normal transmission rate and further improve bandwidth utilization and user experience.

[0050] The implementation method provided in this application enables layer-by-layer drill-down and precise control of bandwidth anomalies in service session sets, thereby significantly improving bandwidth utilization efficiency and service assurance capabilities in leased line congestion scenarios. Specifically, the above-mentioned implementation method of this application first obtains the current set bandwidth of a session set consisting of multiple service sessions, and introduces a first reference bandwidth feature as a historical bandwidth change benchmark within a target statistical period; when the current set bandwidth feature does not match the first reference bandwidth feature, drill-down analysis of the session set is automatically triggered, splitting the session set into multiple session subsets, and obtaining the subset bandwidth feature and its corresponding second reference bandwidth feature for each subset; subsequently, by comparing the subset bandwidth feature with the second reference bandwidth feature, the target session subset with the highest bandwidth anomaly contribution is accurately identified; finally, transmission adjustment operations are performed only on the service sessions in the target session subset, avoiding collateral damage to normal services.

[0051] The transmission adjustment method described above will be further explained below. In an optional implementation, performing the transmission adjustment operation on at least one service session in the target session subset includes:

[0052] S1, determine the session bandwidth characteristics of multiple service sessions based on the session bandwidth occupied by each of the multiple service sessions;

[0053] S2, obtain the third reference bandwidth characteristics of each of the multiple service sessions, wherein the third reference bandwidth characteristics are used to characterize the bandwidth change of the session bandwidth occupied by the service session within the target statistical period.

[0054] S3, based on the comparison results of multiple session bandwidth features and multiple third reference bandwidth features, determine the target session from multiple service sessions;

[0055] S4 performs transport adjustment operations on the target session.

[0056] It should be noted that the above-mentioned session bandwidth characteristics can be obtained by performing second-level or sub-second-level rate statistics on each service session within the target session subset through a real-time sampling interface; the characteristics can be either instantaneous rate values, average rate, peak rate, or first-order rate difference (slope) within a unit time window, used to characterize the bandwidth usage level of the service session at the current moment.

[0057] Optionally, if the service session is a TCP stream, the session bandwidth can be directly calculated using "number of bytes / sampling period"; if it is a UDP stream, the equivalent bandwidth can be calculated based on packet length and packet rate. In another implementation, DPI (Deep Packet Inspection) can be combined to identify application layer protocols, and differentiated sampling granularity can be used for different protocol types to improve the accuracy of bandwidth feature calculation.

[0058] Furthermore, when the same service session is transmitted in parallel on multiple links or tunnels, the bandwidth of each path will be aggregated to obtain the aggregated session bandwidth characteristics of the service session, so as to ensure the integrity of subsequent comparison results.

[0059] In the above embodiments, the third reference bandwidth feature is similar to the second reference bandwidth feature and can be generated based on the historical bandwidth sequence of the service session within the target statistical period (such as the most recent 7×24 hours or 4×24 hours). Its form can be an hourly maximum-minimum value interval, a weighted moving average curve, or a quantile array (such as the 95% peak band). In this embodiment, to eliminate diurnal fluctuations, the third reference bandwidth feature can be generated by averaging historical data from the same time period to remove extreme values, thereby improving the robustness of anomaly detection.

[0060] The following combination Figure 3 This describes an optional process for determining the target session.

[0061] S300, obtain the first reference bandwidth characteristics and the current set bandwidth characteristics;

[0062] Then, execute S302 to determine whether the current set bandwidth is abnormal; if the comparison result between the first reference bandwidth feature and the current set bandwidth feature indicates that the current set bandwidth is abnormal, execute the subsequent step S304; otherwise, end.

[0063] In one implementation, if the current set bandwidth features carry real-time bandwidth occupancy information, at least one historical bandwidth occupancy information at a historical moment can be extracted from the first reference bandwidth features. If the real-time bandwidth occupancy information indicates that the real-time bandwidth is greater than the average bandwidth among multiple historical bandwidths, and the difference between the two is greater than the bandwidth control threshold, the current set bandwidth is determined to be in an abnormal state.

[0064] In another implementation, bandwidth values ​​can be fitted based on multiple historical bandwidth usage information to obtain a historical bandwidth trend curve. If the currently acquired real-time bandwidth does not match the historical bandwidth trend curve, it is determined that the current set bandwidth is in an abnormal state.

[0065] At least one historical moment can be a historical moment in the target statistical period that matches the current moment. For example, if the current moment is "Monday, 10:00", then "10:00" of the past seven days can be used as multiple historical moments; or "10:00" of every Monday in the past month can be used as multiple historical moments.

[0066] If the result is "no", the process will end directly without consuming scheduling resources.

[0067] S304, Based on the comparison results between the subset bandwidth characteristics and the second reference bandwidth characteristics, determine the target session subset from multiple session subsets;

[0068] In the above steps, the comparison between the subset bandwidth feature and the second reference bandwidth feature can also refer to the comparison method described in the above embodiments. For example, when the subset bandwidth feature carries subset bandwidth occupancy information, at least one historical bandwidth occupancy information at a historical moment can be extracted from the second reference bandwidth feature. If the real-time subset bandwidth occupancy information indicates that the real-time subset bandwidth is greater than the average bandwidth among multiple historical bandwidths, and the difference between the two is greater than the bandwidth control threshold, it is determined that the current session subset bandwidth is in an abnormal state.

[0069] In another implementation, bandwidth values ​​can be fitted based on bandwidth occupancy information of multiple historical subsets to obtain a historical subset bandwidth trend curve. If the real-time bandwidth of the currently acquired subset does not match the historical subset bandwidth trend curve, the current subset bandwidth is determined as the target session subset.

[0070] S306, Based on the comparison results between the session bandwidth characteristics and the third reference bandwidth characteristics, the target session is determined from multiple session subsets;

[0071] In the above steps, the comparison method between the session bandwidth feature and the third reference bandwidth feature can refer to the aforementioned subset-level comparison method, and be further refined to the single-session granularity. For example, when the session bandwidth feature carries real-time session bandwidth occupancy information, at least one historical session bandwidth occupancy information at a historical moment can be extracted from the third reference bandwidth feature; if the real-time session bandwidth occupancy information indicates that the real-time session bandwidth is greater than the average bandwidth among multiple historical session bandwidths, and the difference between the two is greater than the session-level bandwidth control threshold, it is determined that the current service session bandwidth is in an abnormal state, and the session is identified as the target session.

[0072] In another implementation, bandwidth values ​​can be fitted based on bandwidth usage information from multiple historical sessions to obtain a historical session bandwidth trend curve. If the currently acquired real-time session bandwidth does not match the historical session bandwidth trend curve (e.g., the deviation rate exceeds a preset ratio or the duration exceeds a threshold), the service session corresponding to the real-time session bandwidth is identified as the target session, thereby enabling precise locking of the single session that truly causes the bandwidth mutation within a subset.

[0073] S308, Performs a transport adjustment operation on the target session.

[0074] The implementation of the aforementioned transmission adjustment operation for the target session is further described below. In one optional embodiment, performing the transmission adjustment operation on the target session includes at least one of the following:

[0075] Adjustment Method 1: Determine the target bandwidth threshold based on the comparison results of multiple session bandwidth features and multiple third reference bandwidth features; configure the bandwidth threshold for the target session, wherein the bandwidth threshold is used to perform speed reduction processing on the data path corresponding to the target session when the current session bandwidth corresponding to the target session is greater than the bandwidth threshold indicated by the bandwidth threshold;

[0076] It should be noted that the target bandwidth threshold mentioned above can be obtained by superimposing a preset floating margin on the peak, average or quantile value (such as 95% peak) of the third reference bandwidth characteristic, or it can be dynamically calculated based on the current remaining network bandwidth to ensure that the link resources are not excessively occupied after the speed reduction.

[0077] In the above adjustment method one, after the bandwidth threshold is configured, the current session bandwidth of the target session is monitored in real time. Once it exceeds the bandwidth threshold, the speed reduction process is triggered immediately. The speed reduction magnitude can be positively correlated with the difference exceeding the threshold, and the speed reduction is controlled to be stepped down in order to avoid causing severe jitter to the service.

[0078] Optionally, the rate reduction can be achieved by reducing the token bucket rate of the session on the egress scheduler, adjusting the queue weight, or temporarily marking it as "congested". In another implementation, bandwidth can be recovered without packet loss by sending an ECN or explicit rate reduction message to the data sending node, which will actively reduce its sending window.

[0079] Adjustment Method 2: Send a first indication message to the downstream node, wherein the first indication message is used to forward to the data request object and instruct the data request object to postpone sending the data request;

[0080] It is understood that the first indication information can be transmitted along the forwarding path to the final data request object (such as a client, APP, or edge gateway) as an in-band control message or dedicated QoS signaling, to notify the other party that "the current session has triggered the bandwidth limit and please postpone subsequent requests", thereby achieving natural speed reduction at the application layer or transport layer. This method is suitable for services with obvious request-response models (such as HTTP and API calls), and can reduce the issuance of new data at the source end and reduce upstream pressure.

[0081] Optionally, the first indication information may carry a suggested waiting time or backoff window size. Upon receiving the information, the data requesting object performs exponential backoff or suspends fetching until a recovery notification is received. In another implementation, the first indication information may be embedded in TCPOption or QUIC frame extensions to achieve fast transmission and compatibility with the existing network.

[0082] Adjustment method three: Send a second indication message to the upstream node, wherein the second indication message is used to instruct the upstream node to temporarily suspend sending the session data of the target session.

[0083] It should be noted that the second instruction information can be sent through a reverse custom out-of-band API to explicitly declare to upstream nodes (such as content origin servers, CDN edge servers, or cloud gateways) that "the target session is abnormal, please suspend packet sending". After receiving the message, the upstream node can reduce the amount of data entering the dedicated line by reducing the sending thread rate, pausing the reading of file blocks, or adjusting the encoding bitrate, thereby reducing the pressure from the source.

[0084] Optionally, the second indication information may further carry at least one of the following fields: "expected transmission rate", "delay duration" or "recovery threshold", based on which the upstream node performs gradient slowdown;

[0085] In another implementation, if the upstream node supports outbound rate limiting based on the token bucket, the second indication information can be directly mapped to the token bucket parameter update to complete the millisecond-level response.

[0086] By combining at least one of the above adjustment methods, this application can accurately identify anomalies at the session level and then implement speed reduction or pausing at any link in the entire link from the source to the path and from the path to the destination. This avoids collateral damage to other normal sessions and achieves rapid recovery of dedicated line bandwidth and ensures service experience.

[0087] In an optional implementation, after determining the target session subset from multiple session subsets based on the comparison results between the bandwidth features of multiple subsets and their respective corresponding second reference bandwidth features, the process includes:

[0088] S1, obtain the subset tag identifier corresponding to the target session subset;

[0089] S2-1, If ​​the subset label indicates that the service sessions included in the target session subset are of the first type, perform a transmission adjustment operation on the multiple service sessions included in the target session subset;

[0090] S2-2-1, If ​​the subset label indicates that the target session subset includes a second type of business session, determine the target session from the target session subset;

[0091] S2-2-1, If ​​the target session is a service session of type 1, perform a transmission adjustment operation on the target session; if the target session is a service session of type 2, perform a transmission adjustment operation on at least one reference service session in the subset of the target sessions.

[0092] Among them, the business criticality level of the first type of business session is lower than that of the second type of business session.

[0093] In the above implementation, if the subset label indicates that the target session subset contains only first-type service sessions, then a unified transmission adjustment operation is performed on all service sessions within that subset. First-type service sessions have a higher criticality level than second-type sessions; therefore, unified adjustment can quickly release bandwidth without causing additional impact on lower-level services.

[0094] Furthermore, if the subset label indicates that a second type of business session exists within the target session subset, then further filtering is performed within that subset to pinpoint the target session that caused the exception. Subsequently, each session is processed according to its type:

[0095] When the target session is of type 1, only the transmission adjustment operation is performed on that session; when the target session is of type 2, in order to avoid affecting high-level services, at least one reference service session in the subset is selected for adjustment instead. The reference session can be selected from the session with the lowest level or the highest bandwidth usage within the same subset, so as to complete bandwidth recovery while ensuring critical services.

[0096] The tag-driven hierarchical adjustment strategy described above enables differentiated control of business sessions of different critical levels within the same subset, ensuring the stability of high-level services while rapidly suppressing abnormal traffic.

[0097] The following combination Figure 4 A complete implementation method is described.

[0098] S400, obtain the first reference bandwidth characteristics and the current set bandwidth characteristics;

[0099] The bandwidth sequence within the historical statistical period is read, and after smoothing to remove extreme values, a first reference bandwidth feature is generated; simultaneously, the current set bandwidth feature is obtained through a real-time sampling interface. Both features are in Mbps, and the time granularity can be configured to 1 second or 10 seconds.

[0100] Execute judgment S402 to determine if the current set bandwidth is abnormal; if the current set bandwidth is abnormal, proceed with the subsequent steps; otherwise, terminate.

[0101] S404, Based on the comparison results between the subset bandwidth characteristics and the second reference bandwidth characteristics, determine the target session subset from multiple session subsets;

[0102] Execute judgment S406 to determine whether the target session subset includes the second type of business session; if the target session subset does not include the second type of business session, execute S406-2 to determine all business sessions in the target session subset as target sessions;

[0103] If the target session subset includes a second type of business session, execute S406-1 to determine the target session from the target session subset; and execute judgment S408 to determine whether the target session is a second type of business session; if the target session is a second type of business session, execute S408-1 to update the first type of business session in the target session subset to the target session.

[0104] Finally, S410 is executed to perform a transport adjustment operation on the target session.

[0105] Through the above-described implementation method of this application, the set-level anomaly determination is first completed through two-level feature comparison in S400 and S402. The subsequent drill-down process is only triggered after it is confirmed that the overall bandwidth exceeds the historical benchmark, thereby avoiding unnecessary regulation of normal traffic fluctuations and significantly reducing computation and signaling overhead. Subsequently, S404 splits the session set into several subsets and quickly locks the target session subset with the highest anomaly contribution by using the second reference bandwidth feature. At this time, the regulation scope is compressed to the real impact source, and the service traffic of irrelevant subsets can maintain the original forwarding rhythm, thus minimizing the impact.

[0106] Furthermore, S406 to S408 introduce subset labeling to differentiate between subsets containing only the first type and subsets containing the second type: for the first type of services with higher criticality, direct and unified adjustment is allowed, while in mixed scenarios, sessions with the lowest priority or the highest bandwidth share are prioritized for rate limiting, thus ensuring that the bandwidth of high-priority service sessions is not squeezed, solving the drawback of the traditional one-size-fits-all solution that inadvertently damages critical traffic. Next, S410 performs precise control such as rate reduction, deferral, or reverse pressure on the finally selected target sessions. The adjustment range is positively correlated with the difference exceeding the threshold and supports step-by-step reduction, thus enabling bandwidth recovery within seconds after detecting anomalies in milliseconds, while maintaining link stability.

[0107] Furthermore, after issuing the control command, the target session bandwidth is continuously monitored. Once it falls back to the allowable range of the third reference bandwidth characteristic for two consecutive cycles, the rate limit is immediately lifted, and a recovery notification is sent upstream or downstream, allowing link resources to quickly return to normal scheduling and avoiding throughput loss caused by long-term rate suppression. Through the above-mentioned interlocking three-level drill-down of subset sessions and tag-driven hierarchical strategy, the implementation method ensures that abnormal sessions are restricted while achieving refined control of leased line bandwidth and zero packet loss guarantee for critical services, significantly improving the overall network resource utilization efficiency and user service experience.

[0108] Furthermore, the following provides a further explanation of how to determine the target session subset and the target session method.

[0109] In one optional implementation, a target session subset is determined from multiple session subsets based on comparison results between multiple subset bandwidth features and their respective corresponding second reference bandwidth features, including at least one of the following:

[0110] Method 1: Determine the reference subset bandwidth distribution corresponding to the first reference time based on multiple second reference bandwidth features; determine the current subset bandwidth distribution based on multiple subset bandwidth features; determine the target session subset from multiple session subsets based on the comparison results between the reference subset bandwidth distribution and the current subset bandwidth distribution, wherein the first reference time is the reference time corresponding to the current time within the target statistical period, and the current subset bandwidth ratio of the target session subset is higher than the reference bandwidth subset ratio of the target session subset in the reference subset bandwidth distribution features;

[0111] It should be noted that the reference subset bandwidth distribution is constructed using bandwidth samples from the same historical time period, while the current subset bandwidth distribution is obtained through real-time sampling. Comparing the two at the same time granularity can directly reflect the change in the share of each subset in the overall traffic. When the current share of a subset is significantly higher than its historical share, it can be identified as an abnormal contribution source and thus selected as the target session subset.

[0112] In another implementation, a duration filter can be set for the distribution comparison results, and locking will only be triggered when the abnormal proportion continues to exceed the set duration, so as to avoid misjudgment caused by instantaneous jitter.

[0113] Method 2: Based on multiple subset bandwidth characteristics and multiple second reference bandwidth characteristics, determine the first bandwidth deviation rate between the current subset bandwidth rate and the reference subset bandwidth rate of each of the multiple session subsets; determine the target session subset based on the multiple first bandwidth deviation rates, wherein the first bandwidth deviation rate corresponding to the target session subset is greater than or equal to the first deviation threshold.

[0114] It should be noted that the first bandwidth deviation rate is calculated using the relative difference between the current rate and the reference rate, which can eliminate the impact of differences in the basic bandwidth of different subsets and make the comparison results more universal; the first deviation threshold can be set as a fixed percentage or dynamically changed according to the remaining bandwidth of the entire network, so as to ensure the detection sensitivity while taking into account the overall network load.

[0115] In another implementation, a deviation rate sorting mechanism can be introduced to simultaneously list the N subsets with the highest deviation rates as target session subsets, thereby enabling multi-point parallel control and accelerating bandwidth recovery.

[0116] In one optional implementation, a target session is determined from multiple service sessions based on the comparison results of multiple session bandwidth features and multiple third reference bandwidth features, including at least one of the following:

[0117] Method 1: Determine the reference session bandwidth distribution corresponding to the first reference time based on multiple third reference bandwidth features; determine the current session bandwidth distribution based on multiple session bandwidth features; determine the target session from multiple service sessions based on the comparison results between the reference session bandwidth distribution and the current session bandwidth distribution, wherein the current session bandwidth ratio of the target session is higher than the reference bandwidth subset ratio of the target session subset in the reference session bandwidth distribution features;

[0118] In the above implementation, a reference session bandwidth distribution at a first reference time point can be constructed using multiple third reference bandwidth features. This distribution provides a baseline for the bandwidth share of each service session in the same historical time period. Subsequently, the current session bandwidth distribution is formed using multiple session bandwidth features obtained through real-time sampling. The two are compared at the same granularity. If the current share of a certain service session is significantly higher than its historical share, and the difference exceeds the distribution control threshold, then that session is identified as the target session. This allows for rapid identification of the source of sudden traffic spikes, preventing a single abnormal session from dragging down the entire subset.

[0119] To further improve accuracy, a duration filter can be added, which will only trigger a lock if the percentage of abnormalities remains above a set time, thereby blocking instantaneous jitter.

[0120] Method 2: Based on multiple session bandwidth characteristics and multiple third reference bandwidth characteristics, determine the second bandwidth deviation rate between the current session bandwidth rate and the reference session bandwidth rate of each of the multiple service sessions; determine the target session based on the multiple second bandwidth deviation rates, wherein the second bandwidth deviation rate corresponding to the target session is greater than or equal to the second deviation threshold.

[0121] In the above implementation, the second bandwidth deviation rate between the current session bandwidth rate of each service session and the corresponding third reference bandwidth characteristic is calculated using a relative difference formula to eliminate differences in the basic rates of different sessions, making the results comparable horizontally. If the second bandwidth deviation rate of a session is greater than or equal to the second deviation threshold, it is determined to be abnormal and selected as the target session. The threshold can be set as a fixed percentage or can be dynamically changed with the remaining network bandwidth, taking into account both sensitivity and overall load.

[0122] In addition, a deviation rate sorting mechanism can be introduced to simultaneously target the top N sessions with the highest deviation rates, enabling multi-point parallel control, accelerating bandwidth recovery, and shortening congestion duration.

[0123] In an optional implementation, before obtaining the current set bandwidth occupied by the session set consisting of multiple service sessions and obtaining the first reference bandwidth feature matching the session set, the method further includes:

[0124] S1, obtain the current business session from multiple business sessions;

[0125] S2, Configure a first session label for the current business session according to the business type of the current business session, wherein the business sessions in the session subset are configured with the same first session label;

[0126] S3, Configure a second session label for the current service session based on the reference bandwidth occupied by the current service session within the target statistical period;

[0127] S4, add the first session tag and the second session tag to the data packet of the current business session.

[0128] In the above embodiments of this application, the DSCP field in the message can be used to mark the session message, which can be divided into traffic pre-marking and automatic fine marking.

[0129] In the traffic pre-labeling stage, based on business characteristics, business traffic levels can be manually divided into four categories: core (CS4), important (CS3), general (CS2), and unimportant (CS1), that is, each session is labeled with a first session tag.

[0130] Furthermore, in the automatic fine-tagging stage, categories with larger traffic volumes can be automatically subdivided based on their size, potentially into four subcategories: 0, 1, 2, and 3. These can be categorized as core (cs4\af41\af42\af43), important (cs3\af31\af32\af33), general (cs2\af21\af22\af23), and unimportant (cs1\af11\af22\af23). This assigns a second session tag to each session. In contrast, larger categories with smaller traffic volumes are not further subdivided, ultimately ensuring that the traffic rates within each subcategory are not significantly different.

[0131] The following combination Figure 5 This application describes a business session processing system. For example... Figure 5 As shown, the session processing system 500 involved in this embodiment includes four functional modules, including a traffic marking module 502, a traffic information acquisition module 504, an analysis and alarm module 506, and a bandwidth allocation module 508.

[0132] The following section explains the specific functions of each module in conjunction with the implementation process.

[0133] Before traffic enters the dedicated line, the traffic labeling module 502 first writes the level into the DSCP field of the packet. Manual pre-labeling divides the service into four categories: core, important, general, and unimportant. If a certain type of traffic continues to exceed the preset threshold, the system automatically enables fine labeling, further splitting the category into four sub-flows, with DSCP values ​​of af41~af43, af31~af33, af21~af23, and af11~af13 in sequence. When the traffic is small, the original value is maintained without further subdivision, ultimately resulting in several small categories with similar rates, providing uniform granularity for subsequent scheduling.

[0134] After marking, the traffic information acquisition module 504 sends the interface byte count, packet count, and five-tuple information to the traffic information analysis and alarm module in real time via SNMP or full mirroring. This module first removes extreme values ​​according to either a "week-day" or "month-week" cycle to generate a trend curve. The curve hierarchy covers total traffic, major traffic categories, minor traffic categories, and single IP or single session traffic. For single IPs, the top 100 in bandwidth are selected, and the single session threshold can be set to 10 Mbps. Real-time sampled values ​​are compared layer by layer with the corresponding trend: if total traffic deviates from the trend, it is broken down to major categories; if a major category deviates, it is further broken down to minor categories; if a minor category deviates, the specific IP or session is located, ultimately pinpointing the source of the anomaly. Once the deviation reaches the preset threshold and continues for a preset time, the analysis and alarm module 506 will immediately generate an alarm. The alarm objects include the proportion of total traffic to the dedicated line, the remaining bandwidth, the difference between total traffic and the trend, the difference between major categories, the difference between minor categories, the difference between each minor category within the same major category, and the difference between high-bandwidth IPs or sessions. All events exceeding the threshold will be summarized and reported uniformly.

[0135] After an alarm is issued, the bandwidth allocation module 508 enters the adjustment phase. The basic allocation pre-divides bandwidth ratios for each sub-category on an hourly basis, automatically increasing the ratio during peak periods and decreasing it during off-peak periods. This can be refreshed multiple times within the same calendar day. The adjustment process is triggered based on the alarm location results: if the anomaly originates from a single session, the session is rate-limited, with the limit value higher than its historical trend while ensuring the total bandwidth of the sub-category does not trigger an alarm; if the anomaly is caused by a sub-category, the entire sub-category is rate-limited, with the limit value higher than the sub-category trend while ensuring the overall category does not exceed its threshold; if the anomaly escalates to the entire category, the entire category is rate-limited, with the limit value higher than the category trend while ensuring the total traffic is below the dedicated line capacity. The rate-limiting policy remains in place until traffic stabilizes, at which point the system automatically removes the rate-limiting flag, and the bandwidth ratio reverts to the daily basic allocation scheme, completing one closed-loop control cycle.

[0136] In the above implementation, the traffic labeling module divides the service into several clearly defined subcategories at the entry stage and provides uniform granularity for each subsequent level of scheduling. This makes bandwidth allocation no longer dependent on manual static strategies, but based on automatically refined DSCP labels, laying the foundation for refined management.

[0137] The traffic information collection and analysis module, through layer-by-layer trend comparison and threshold alarm, can quickly delve into a single session after an anomaly in total traffic. The localization process is seamless from macro to micro, avoiding the false alarms caused by the traditional solution of "one-size-fits-all" rate limiting of irrelevant traffic, and significantly improving the speed and accuracy of anomaly identification.

[0138] The bandwidth allocation module implements tiered rate limiting based on the location results. The rate limit value is always higher than the historical trend and ensures that the upstream bandwidth does not exceed the warning level. The policy is automatically lifted after the traffic stabilizes. This not only quickly recovers bandwidth during periods of sudden traffic but also releases resources in a timely manner upon recovery, achieving high utilization of the dedicated line link and zero interruption guarantee for critical services.

[0139] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0140] According to another aspect of the present invention, an apparatus for adjusting a service session for implementing the above-described service session adjustment method is also provided. For example... Figure 6 As shown, the device includes:

[0141] The acquisition unit 602 is used to acquire the current set bandwidth occupied by the session set consisting of multiple service sessions, and to acquire a first reference bandwidth feature that matches the session set, wherein the first reference bandwidth feature is used to characterize the bandwidth change of the service set bandwidth occupied by the session set within the target statistical period.

[0142] The first determining unit 604 is used to determine the subset bandwidth characteristics corresponding to each of the multiple session subsets included in the session set when the current set bandwidth characteristics determined based on the current set bandwidth do not match the first reference bandwidth characteristics, and to obtain the second reference bandwidth characteristics of each of the multiple session subsets. The second reference bandwidth characteristics are used to characterize the bandwidth change of the service subset bandwidth occupied by the session subset within the target statistical period.

[0143] The second determining unit 606 is used to determine the target session subset from multiple session subsets based on the comparison results between the bandwidth features of multiple subsets and their respective corresponding second reference bandwidth features.

[0144] The adjustment unit 608 is used to perform a transmission adjustment operation on at least one service session in the target session subset.

[0145] Optionally, the above-mentioned service session adjustment device is further configured to: determine the session bandwidth characteristics of multiple service sessions based on the session bandwidth occupied by each of the multiple service sessions; obtain the third reference bandwidth characteristics of each of the multiple service sessions, wherein the third reference bandwidth characteristics are used to characterize the bandwidth change of the session bandwidth occupied by the service session within the target statistical period; determine the target session from the multiple service sessions based on the comparison results of the multiple session bandwidth characteristics and the multiple third reference bandwidth characteristics; and perform a transmission adjustment operation on the target session.

[0146] Optionally, the aforementioned service session adjustment device is further configured to: obtain a subset label identifier corresponding to a target session subset; perform a transmission adjustment operation on multiple service sessions included in the target session subset when the subset label identifier indicates that the service sessions included in the target session subset are of a first type; determine a target session from the target session subset when the subset label identifier indicates that the target session subset includes a second type of service session; perform a transmission adjustment operation on the target session when the target session is of the second type of service session; and perform a transmission adjustment operation on at least one reference service session in the target session subset when the target session is of the first type of service session; wherein the service criticality level of the first type of service session is higher than that of the second type of service session.

[0147] Optionally, the aforementioned service session adjustment device is configured to: determine a reference subset bandwidth distribution corresponding to a first reference time based on multiple second reference bandwidth features; determine a current subset bandwidth distribution based on multiple subset bandwidth features; determine a target session subset from multiple session subsets based on a comparison result between the reference subset bandwidth distribution and the current subset bandwidth distribution, wherein the first reference time is a reference time corresponding to the current time within a target statistical period, and the current subset bandwidth ratio of the target session subset is higher than the reference bandwidth subset ratio of the target session subset in the reference subset bandwidth distribution features; determine a first bandwidth deviation rate between the current subset bandwidth rate and the reference subset bandwidth rate of each of the multiple session subsets based on multiple subset bandwidth features and multiple second reference bandwidth features; and determine a target session subset based on multiple first bandwidth deviation rates, wherein the first bandwidth deviation rate corresponding to the target session subset is greater than or equal to a first deviation threshold.

[0148] Optionally, the aforementioned service session adjustment device is used for at least one of the following: determining a reference session bandwidth distribution corresponding to a first reference time based on a plurality of third reference bandwidth features; determining a current session bandwidth distribution based on a plurality of session bandwidth features; determining a target session from a plurality of service sessions based on a comparison result between the reference session bandwidth distribution and the current session bandwidth distribution, wherein the current session bandwidth ratio of the target session is higher than the reference bandwidth subset ratio of the target session subset in the reference session bandwidth distribution features; determining a second bandwidth deviation rate between the current session bandwidth rate and the reference session bandwidth rate of each of the plurality of service sessions based on the plurality of session bandwidth features and the plurality of third reference bandwidth features; determining the target session based on a plurality of second bandwidth deviation rates, wherein the second bandwidth deviation rate corresponding to the target session is greater than or equal to a second deviation threshold.

[0149] Optionally, the aforementioned service session adjustment device is used to: determine a target bandwidth threshold based on the comparison results of multiple session bandwidth features and multiple third reference bandwidth features; configure a bandwidth threshold for the target session, wherein the bandwidth threshold is used to perform speed reduction processing on the data path corresponding to the target session when the current session bandwidth corresponding to the target session is greater than the bandwidth threshold indicated by the bandwidth threshold; send a first indication information to the downstream node, wherein the first indication information is used to forward to the data request object and instruct the data request object to postpone sending the data request; and send a second indication information to the upstream node, wherein the second indication information is used to instruct the upstream node to postpone sending the session data of the target session.

[0150] Optionally, the above-mentioned service session adjustment device is further configured to: obtain the current service session from multiple service sessions; configure a first session label for the current service session according to the service type of the current service session, wherein the service sessions in the session subset are configured with the same first session label; configure a second session label for the current service session according to the reference bandwidth occupied by the current service session within the target statistical period; and add the first session label and the second session label to the data packet of the current service session.

[0151] Optionally, in this embodiment, the implementation of each of the above-mentioned unit modules can be referred to the above-mentioned method embodiments, which will not be repeated here.

[0152] According to another aspect of the present invention, an electronic device for implementing the above-described adjustment method for a service session is also provided. This electronic device may be... Figure 7 The terminal device or server shown. This embodiment uses this electronic device as an example for illustration. Figure 7 As shown, the electronic device includes a memory 702 and a processor 704. The memory 702 stores a computer program, and the processor 704 is configured to execute the steps in any of the above method embodiments via the computer program.

[0153] Optionally, in this embodiment, the aforementioned electronic device may be located in at least one of a plurality of network devices in a computer network.

[0154] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0155] S1, obtain the current set bandwidth occupied by the session set consisting of multiple service sessions, and obtain the first reference bandwidth feature matching the session set, wherein the first reference bandwidth feature is used to characterize the bandwidth change of the service set bandwidth occupied by the session set within the target statistical period;

[0156] S2, if the current set bandwidth feature determined based on the current set bandwidth does not match the first reference bandwidth feature, determine the subset bandwidth feature corresponding to each of the multiple session subsets included in the session set, and obtain the second reference bandwidth feature of each of the multiple session subsets, wherein the second reference bandwidth feature is used to characterize the bandwidth change of the service subset bandwidth occupied by the session subset within the target statistical period.

[0157] S3, Based on the comparison results between the bandwidth features of multiple subsets and their respective second reference bandwidth features, determine the target session subset from multiple session subsets;

[0158] S4. Based on the comparison results between the bandwidth features of multiple subsets and their respective second reference bandwidth features, determine the target session subset from multiple session subsets.

[0159] Alternatively, as those skilled in the art will understand, Figure 7 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 7 This does not limit the structure of the aforementioned electronic devices or electronic equipment. For example, electronic devices or electronic equipment may also include components that are more... Figure 7 The more or fewer components shown (such as network interfaces, etc.), or having the same Figure 7 The different configurations shown.

[0160] The memory 702 can be used to store software programs and modules, such as the program instructions / modules corresponding to the service session adjustment method and apparatus in this embodiment of the invention. The processor 704 executes various functional applications and data processing by running the software programs and modules stored in the memory 702, thereby realizing the aforementioned service session adjustment method. The memory 702 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 702 may further include memory remotely located relative to the processor 704, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, enterprise intranets, local area networks, mobile communication networks, and combinations thereof. Specifically, the memory 702 may be used, but is not limited to, to store various elements in the scene screen, service session adjustment information, and other information. As an example, such as... Figure 7 As shown, the memory 702 may include, but is not limited to, the acquisition unit 602, the first determination unit 604, the second determination unit 606, and the adjustment unit 608 from the service session adjustment device. Furthermore, it may include, but is not limited to, other module units from the service session adjustment device, which will not be elaborated upon in this example.

[0161] Optionally, the aforementioned transmission device 708 is used to receive or send data via a network. Specific examples of the network may include wired and wireless networks. In one example, the transmission device 708 includes a Network Interface Controller (NIC), which can be connected to other network devices and a router via a network cable to communicate with the Internet or a local area network. In another example, the transmission device 708 is a Radio Frequency (RF) module used to communicate with the Internet wirelessly. Furthermore, the aforementioned electronic device also includes: a display 708 for displaying a virtual scene in the interface; and a connection bus 710 for connecting the various module components in the aforementioned electronic device.

[0162] In other embodiments, the aforementioned terminal device or server can be a node in a distributed system, wherein the distributed system can be a blockchain system, which is a distributed system formed by connecting multiple nodes through network communication. The nodes can form a peer-to-peer (P2P) network, and any form of computing device, such as a server, terminal, or other electronic device, can become a node in the blockchain system by joining this peer-to-peer network.

[0163] According to one aspect of this application, a computer program product is provided, comprising a computer program / instructions containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit, it performs various functions provided in embodiments of this application.

[0164] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0165] According to one aspect of this application, a computer-readable storage medium is provided, from which a processor of a computer device reads computer instructions, and executes the computer instructions, causing the computer device to perform the aforementioned adjustment method for a business session. Optionally, in this embodiment, the aforementioned computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0166] S1, obtain the current set bandwidth occupied by the session set consisting of multiple service sessions, and obtain the first reference bandwidth feature matching the session set, wherein the first reference bandwidth feature is used to characterize the bandwidth change of the service set bandwidth occupied by the session set within the target statistical period;

[0167] S2, if the current set bandwidth feature determined based on the current set bandwidth does not match the first reference bandwidth feature, determine the subset bandwidth feature corresponding to each of the multiple session subsets included in the session set, and obtain the second reference bandwidth feature of each of the multiple session subsets, wherein the second reference bandwidth feature is used to characterize the bandwidth change of the service subset bandwidth occupied by the session subset within the target statistical period.

[0168] S3, Based on the comparison results between the bandwidth features of multiple subsets and their respective second reference bandwidth features, determine the target session subset from multiple session subsets;

[0169] S4. Based on the comparison results between the bandwidth features of multiple subsets and their respective second reference bandwidth features, determine the target session subset from multiple session subsets.

[0170] Optionally, in this embodiment, those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0171] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0172] In the above embodiments of the present invention, the descriptions of each embodiment have their own emphasis. Parts not described in detail in a certain embodiment can be referred to in the relevant descriptions of other embodiments. It should be understood that the disclosed object account terminal can be implemented in other ways in the several embodiments provided in this application. The device embodiments described above are merely illustrative. For example, the division of the above units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of units or modules, and may be electrical or other forms.

[0173] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units.

[0174] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for adjusting a business session, characterized in that, include: Obtain the current set bandwidth occupied by a set of sessions consisting of multiple service sessions, and obtain a first reference bandwidth feature that matches the set of sessions, wherein the first reference bandwidth feature is used to characterize the bandwidth change of the service set bandwidth occupied by the set of sessions within a target statistical period; If the current set bandwidth feature determined based on the current set bandwidth does not match the first reference bandwidth feature, the subset bandwidth feature corresponding to each of the multiple session subsets included in the session set is determined, and the second reference bandwidth feature of each of the multiple session subsets is obtained, wherein the second reference bandwidth feature is used to characterize the bandwidth change of the service subset bandwidth occupied by the session subset within the target statistical period. Based on the comparison results between the bandwidth features of the multiple subsets and their respective corresponding second reference bandwidth features, a target session subset is determined from the multiple session subsets; Perform a transport adjustment operation on at least one of the service sessions in the target session subset.

2. The method according to claim 1, characterized in that, Performing a transport adjustment operation on at least one of the service sessions in the target session subset includes: Based on the session bandwidth occupied by each of the multiple service sessions, determine the session bandwidth characteristics of the multiple service sessions; Obtain the third reference bandwidth feature for each of the multiple service sessions, wherein the third reference bandwidth feature is used to characterize the bandwidth change of the session bandwidth occupied by the service session within the target statistical period; The target session is determined from the multiple service sessions based on the comparison results of multiple session bandwidth features and multiple third reference bandwidth features; Perform a transport adjustment operation on the target session.

3. The method according to claim 2, characterized in that, After determining the target session subset from the multiple session subsets based on the comparison results between the bandwidth features of the multiple subsets and their respective corresponding second reference bandwidth features, the process includes: Obtain the subset tag identifier corresponding to the target session subset; If the subset label indicates that the service sessions included in the target session subset are of the first type, a transmission adjustment operation is performed on the multiple service sessions included in the target session subset. If the subset label indicates that the target session subset includes the second type of service session, the target session is determined from the target session subset; If the target session is a service session of the first type, a transmission adjustment operation is performed on the target session; if the target session is a service session of the second type, a transmission adjustment operation is performed on at least one reference service session in the subset of the target sessions. The business criticality level of the first type of business session is lower than that of the second type of business session.

4. The method according to claim 2, characterized in that, Based on the comparison results between the bandwidth features of the plurality of subsets and their respective corresponding second reference bandwidth features, a target session subset is determined from the plurality of session subsets, including at least one of the following: A reference subset bandwidth distribution corresponding to a first reference time is determined based on multiple second reference bandwidth features; a current subset bandwidth distribution is determined based on multiple subset bandwidth features; a target session subset is determined from multiple session subsets based on the comparison result between the reference subset bandwidth distribution and the current subset bandwidth distribution, wherein the first reference time is the reference time corresponding to the current time within the target statistical period, and the current subset bandwidth ratio of the target session subset is higher than the reference bandwidth subset ratio of the target session subset in the reference subset bandwidth distribution features; Based on the multiple subset bandwidth characteristics and the multiple second reference bandwidth characteristics, a first bandwidth deviation rate is determined between the current subset bandwidth rate and the reference subset bandwidth rate of each of the multiple session subsets; the target session subset is determined based on the multiple first bandwidth deviation rates, wherein the first bandwidth deviation rate corresponding to the target session subset is greater than or equal to a first deviation threshold.

5. The method according to claim 4, characterized in that, Based on the comparison results of multiple session bandwidth features and multiple third reference bandwidth features, a target session is determined from multiple service sessions, including at least one of the following: A reference session bandwidth distribution corresponding to the first reference time is determined based on multiple third reference bandwidth features; a current session bandwidth distribution is determined based on multiple session bandwidth features; and a target session is determined from multiple service sessions based on the comparison result between the reference session bandwidth distribution and the current session bandwidth distribution, wherein the current session bandwidth ratio of the target session is higher than the reference bandwidth subset ratio of the target session subset in the reference session bandwidth distribution features. Based on multiple session bandwidth characteristics and multiple third reference bandwidth characteristics, a second bandwidth deviation rate is determined between the current session bandwidth rate and the reference session bandwidth rate of each of the multiple service sessions; the target session is determined based on the multiple second bandwidth deviation rates, wherein the second bandwidth deviation rate corresponding to the target session is greater than or equal to a second deviation threshold.

6. The method according to claim 2, characterized in that, The transmission adjustment operation performed on the target session includes at least one of the following: Based on the comparison results of multiple session bandwidth features and multiple third reference bandwidth features, a target bandwidth threshold is determined; a bandwidth threshold is configured for the target session, wherein the bandwidth threshold is used to perform speed reduction processing on the data path corresponding to the target session when the current session bandwidth corresponding to the target session is greater than the bandwidth threshold indicated by the bandwidth threshold; Send a first indication message to the downstream node, wherein the first indication message is used to forward to the data request object and instruct the data request object to postpone sending the data request; Send a second indication message to the upstream node, wherein the second indication message is used to instruct the upstream node to postpone sending the session data of the target session.

7. The method according to any one of claims 1 to 6, characterized in that, Before obtaining the current set bandwidth occupied by a set of sessions consisting of multiple service sessions, and before obtaining the first reference bandwidth feature matching the set of sessions, the method further includes: Obtain the current business session from among the multiple business sessions; Based on the service type of the current service session, a first session tag is configured for the current service session, wherein the service sessions in the session subset are configured with the same first session tag; Configure a second session tag for the current service session based on the reference bandwidth occupied by the current service session within the target statistical period; Add the first session tag and the second session tag to the data packet of the current business session.

8. A device for adjusting a business session, characterized in that, include: The acquisition unit is used to acquire the current set bandwidth occupied by a set of sessions consisting of multiple service sessions, and to acquire a first reference bandwidth feature that matches the set of sessions, wherein the first reference bandwidth feature is used to characterize the bandwidth change of the service set bandwidth occupied by the set of sessions within a target statistical period. The first determining unit is configured to determine the subset bandwidth characteristics corresponding to each of the multiple session subsets included in the session set when the current set bandwidth characteristics determined based on the current set bandwidth do not match the first reference bandwidth characteristics, and to obtain the second reference bandwidth characteristics of each of the multiple session subsets, wherein the second reference bandwidth characteristics are used to characterize the bandwidth change of the service subset bandwidth occupied by the session subset within the target statistical period. The second determining unit is used to determine a target session subset from the multiple session subsets based on the comparison results between the bandwidth features of the multiple subsets and their respective corresponding second reference bandwidth features; An adjustment unit is used to perform a transmission adjustment operation on at least one of the service sessions in the target session subset.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method described in any one of claims 1 to 7.

10. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method described in any one of claims 1 to 7 through the computer program.

Images