Methods for determining communication service quality benchmarks

Abstract

This application relates to the field of communications and discloses a method for determining a communication service quality benchmark, solving the problem of traditional line selection methods over-reliance on bandwidth indicators. This method actively and systematically introduces additional latency and packet loss of different gradients into a proxy device between the terminal and the server to simulate various network quality conditions and obtains a satisfaction score for the user experience of a specific application on the terminal under each condition. Through this testing process, a direct mapping relationship is established between actual network quality parameters and user satisfaction scores. This application thus determines the maximum acceptable combination of latency and maximum acceptable packet loss rate that the network can tolerate, provided a preset satisfaction threshold is met, and defines this as the service quality benchmark for the application. Using this benchmark, the most cost-effective line that guarantees user satisfaction can be intelligently selected from multiple available communication lines.

Description

Technical Field

[0001] This application relates to the field of communications, and in particular to methods for determining communication service quality benchmarks and selecting communication lines. Background Technology

[0002] The descriptions in this section are intended only to provide background information for the implementation of this application and should not be construed as an admission or implication that they constitute prior art.

[0003] With the development of information technology, individual and business users are becoming increasingly reliant on the internet. Users access the internet through communication lines to use various applications and services, such as web browsing, video conferencing, online games, and data transmission. Typically, these communication lines are provided by different telecommunications service providers and have varying service specifications and costs.

[0004] To measure the quality of network communication, the industry has introduced the concept of Quality of Service (QoS). QoS is a set of technical parameters used to measure network performance, and its key indicators typically include bandwidth, latency, and packet loss rate.

[0005] In current technology, users often primarily rely on the bandwidth offered by telecommunications service providers when choosing communication lines. The common understanding is that higher bandwidth usually means better QoS and a smoother application experience. Therefore, users tend to choose line solutions with higher bandwidth.

[0006] However, this approach of solely relying on bandwidth for selection has several problems. First, high-bandwidth lines are usually accompanied by high costs. For specific users and application scenarios, once bandwidth reaches a certain threshold, further increases may not significantly improve the user experience but could lead to unnecessary expenses and wasted costs. Second, even if two lines have the same nominal bandwidth, their actual QoS can differ significantly. Lines from different telecom service providers may exhibit vastly different latency and packet loss rates due to variations in network architecture, routing strategies, and load conditions. A high-bandwidth line with high latency and packet loss may provide a far worse experience for some applications than a lower-bandwidth line with excellent latency and packet loss.

[0007] This presents users with a dilemma when choosing a network line: they cannot accurately correlate the technical parameters of the network line with the actual user experience satisfaction, making it difficult to find the best line among many options that meets both the user experience requirements and cost-effectiveness. Summary of the Invention

[0008] One objective of this application is to provide a method for determining communication service quality benchmarks, which can select communication lines that both guarantee user satisfaction and are cost-effective.

[0009] This application discloses a method for determining a communication service quality benchmark, wherein a terminal communicates with a server through a proxy device, the proxy device forwarding data packets between the terminal and the server, and the method includes the following steps:

[0010] Step A: Measure the basic latency and basic packet loss rate of data packet transmission between the terminal and the server, provided that the proxy device does not actively introduce additional latency and additional packet loss.

[0011] Step B: In the proxy device, based on a preset set of additional delay duration and additional packet loss rate parameters, the forwarded data packets are subjected to additional delay and additional packet loss.

[0012] Step C: Add the base latency duration to the additional latency duration to determine the actual latency duration; combine the base packet loss rate with the additional packet loss rate to determine the actual packet loss rate;

[0013] Step D: Obtain a satisfaction score representing the application running experience on the terminal, under the conditions of the actual latency and the actual packet loss rate.

[0014] Step E involves changing the additional delay duration and additional packet loss rate parameters and repeating steps B to D to obtain multiple sets of results. Each set of results includes the actual delay duration, the actual packet loss rate, and the corresponding satisfaction score.

[0015] Step F: From the multiple sets of results, determine the combination of the maximum acceptable actual delay time and the maximum acceptable actual packet loss rate that ensures the satisfaction score is not lower than the preset satisfaction threshold.

[0016] Step G uses the combination of the determined maximum acceptable actual delay duration and the actual packet loss rate as a benchmark for selecting the service quality of the communication line.

[0017] In a preferred embodiment, step G is followed by:

[0018] Based on the service quality benchmark, at least one candidate communication line is determined from multiple available communication lines, wherein the service quality parameters of the candidate communication line satisfy the maximum acceptable actual delay duration and the maximum acceptable actual packet loss rate.

[0019] If the number of candidate communication lines is greater than 1, then the communication line with the lowest cost is selected from the candidate communication lines for communication between the terminal and the server.

[0020] In a preferred embodiment, step D specifically includes:

[0021] Each time a new set of additional latency and additional packet loss is introduced into the data packets in the proxy device, the user interface of the terminal is refreshed;

[0022] The user interface displays a preset prompt message to request the user to input a satisfaction rating for the current application's running experience;

[0023] The user-inputted satisfaction score, corresponding to the current actual latency and actual packet loss rate, is obtained from the user interface.

[0024] In a preferred embodiment, in step E, the additional delay duration and additional packet loss rate parameters are changed in an increasing or decreasing order according to a preset gradient value.

[0025] In a preferred embodiment, the satisfaction rating is a MOS (Mean Orientation of Satisfaction) that conforms to telecommunications industry standards, with a rating scale of 1 to 5 points.

[0026] In a preferred embodiment, the agent device is one of the following two:

[0027] Software agent integrated within the terminal operating system or application;

[0028] A hardware gateway device deployed in the local network accessed by the terminal.

[0029] In a preferred embodiment, steps A to G are executed separately in at least two preset different time periods, thereby determining a corresponding maximum acceptable combination of actual delay duration and actual packet loss rate for each of the different time periods, which serves as a benchmark for selecting the service quality of communication lines within that time period.

[0030] At any given time period, based on the combination of the maximum acceptable actual latency and the actual packet loss rate determined for that time period, the proxy device selects from multiple available communication lines the communication line that meets its corresponding quality of service benchmark and has the lowest cost within that time period.

[0031] In a preferred embodiment, step D is performed automatically by measuring one or more key performance indicators of the application through an automated script running on the terminal.

[0032] Based on the measured values ​​of the key performance indicators, they are automatically converted into the satisfaction score through a preset mapping relationship;

[0033] The key performance indicators include the application's frame rate, loading time, or response latency.

[0034] In a preferred embodiment, in step C, the actual packet loss rate = 1 - (1 - additional packet loss rate) * (1 - base packet loss rate).

[0035] In a preferred embodiment, it also includes,

[0036] For each terminal within the local area network:

[0037] Run one or more applications on the terminal, and repeat steps A through E for each application to determine a maximum acceptable combination of actual latency and actual packet loss rate as a service quality benchmark for each combination of terminal and application.

[0038] When the proxy device processes a data packet originating from a specific application on a specific terminal, it dynamically selects the communication line that meets the service quality benchmark and has the lowest cost from multiple currently available communication lines based on the service quality benchmark determined for the combination of the terminal and the application, and uses it to forward the data packet.

[0039] In the embodiments of this application, by actively simulating and superimposing additional network latency and packet loss in the proxy device, and combining this with the user experience satisfaction score of the terminal application, a direct correspondence between actual network quality parameters (latency duration, packet loss rate) and user subjective satisfaction is systematically established. This eliminates reliance on traditional, universal Quality of Service (QoS) standards, instead determining a more precise and practically meaningful QoS benchmark centered on the actual user experience for specific applications. This benchmark represents the maximum latency and maximum packet loss the network can tolerate while ensuring user satisfaction does not fall below a preset threshold. Therefore, it enables more rational, efficient, and economical decisions regarding communication line selection and network resource allocation, ultimately guided by user experience.

[0040] Furthermore, by using the established quality of service (QoS) benchmarks to filter available communication lines and selecting the lowest-cost candidate line that meets the benchmarks, an intelligent network routing mechanism that balances user experience and operating costs can be achieved, ensuring that network communication costs are optimized without sacrificing user satisfaction.

[0041] Furthermore, by refreshing the user interface and explicitly prompting the user to rate the data after each adjustment of network parameters, the user's immediate subjective feelings under specific network conditions can be accurately captured, ensuring a high degree of correlation and accuracy between the collected satisfaction ratings and the corresponding actual latency and packet loss parameters.

[0042] Furthermore, by systematically changing additional latency and packet loss parameters according to preset gradient values, changes in network quality can be systematically scanned and tested, ensuring that the collected data can comprehensively cover various network conditions from excellent to poor, thereby more reliably determining the critical point of user satisfaction.

[0043] Furthermore, by adopting the Mean Opinion Score (MOS), a standard used in the telecommunications industry, as the satisfaction rating criterion, the rating results are standardized and quantified, possessing industry-recognized objectivity and comparability, and enhancing the universality and credibility of the benchmark determined by this method.

[0044] Furthermore, the proxy device can be a built-in software proxy or an external hardware gateway, which provides flexibility for the deployment of this method, enabling it to adapt to different terminal environments and network architectures, and expanding the applicability of the technology.

[0045] Furthermore, by repeatedly executing the benchmark determination process within different preset time periods and applying its own service quality benchmark to select communication lines for each time period, the network selection strategy can dynamically adapt to changes in network load and user demand during different time periods (such as peak and off-peak periods), achieving more refined and intelligent network resource management and cost control.

[0046] Furthermore, by using automated scripts to measure the application's objective key performance indicators (such as frame rate and loading time) and mapping them to satisfaction scores, the subjectivity and inconvenience of manual scoring can be eliminated, enabling the entire benchmark determination process to be executed automatically and efficiently, and the results to be more objective and consistent.

[0047] Furthermore, by independently determining a dedicated Quality of Service (QoS) benchmark for each application on each terminal within the local area network, and dynamically selecting communication lines at the proxy device level based on the source of data packets (specific terminal and specific application) according to the corresponding benchmark, a fine-grained, application-aware network traffic scheduling can be achieved. This method can provide differentiated service guarantees for different applications (such as video conferencing, online games, and web browsing) with varying sensitivities to network quality, thereby maximizing network resource utilization efficiency and cost-effectiveness while satisfying the experience of all applications.

[0048] The various technical features disclosed in the above-described invention, the various technical features disclosed in the following embodiments and examples, and the various technical features disclosed in the accompanying drawings can be freely combined with each other to form various new technical solutions (all of which should be considered as having been described in this specification), unless such combination of technical features is technically infeasible. Attached Figure Description

[0049] Figure 1This is a schematic flowchart of a method for determining a communication service quality benchmark according to an embodiment of this application. Detailed Implementation

[0050] In the following description, many technical details are presented to help the reader better understand this application. However, those skilled in the art will understand that the technical solutions claimed in this application can be implemented even without these technical details and various variations and modifications based on the following embodiments.

[0051] Explanation of some concepts:

[0052] Bandwidth: refers to the amount of data a network can transmit per unit of time, usually measured in bits per second (bps). It is the most frequently referenced indicator when users choose network services.

[0053] Latency refers to the time it takes for a data packet to travel from one end of a network to the other. High latency can significantly negatively impact the experience of highly interactive applications such as video calls and online games.

[0054] Packet loss rate: This refers to the percentage of data packets lost during data transmission out of the total number of data packets sent. A high packet loss rate can affect the integrity of data transmission and may cause application stuttering, video pixelation, or file corruption.

[0055] A terminal is a computing device that a user directly operates and runs one or more applications, ultimately presenting the application experience. It is the starting point of the entire communication link and the source of Quality of Service (QoS) satisfaction scores. Terminals establish connections with remote servers through proxy devices to obtain data or services. Terminals can be smartphones, personal computers, tablets, game consoles, smart TVs, TV boxes, thin clients, etc.

[0056] A server is a remote computer system that provides specific content, services, or computing power over a network. It is the target endpoint for communication between applications on a terminal. A terminal initiates a request, which passes through a proxy device and ultimately reaches the server. The server processes the request and returns the data to the terminal. Servers can be game servers, video streaming servers, video conferencing servers, web servers, communication servers, cloud storage servers, and so on.

[0057] Proxy devices are network entities located between terminals and servers, and can be either software or hardware. Their core function is to intercept and forward data packets between the terminal and the server, and can actively and controllably introduce additional latency and packet loss into the data packets according to preset parameters to simulate different network quality conditions.

[0058] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0059] The embodiments of this application relate to a method for determining a communication service quality benchmark, the process of which is as follows: Figure 1 As shown. The terminal communicates with the server through a proxy device, which forwards data packets between the terminal and the server. The proxy device can be a software proxy integrated into the terminal's operating system or application, or a hardware gateway device deployed in the local network accessed by the terminal, etc. The method includes the following steps:

[0060] Step A: Measure the base latency and base packet loss rate of data packet transmission between the terminal and the server, provided that the proxy device does not actively introduce additional latency or additional packet loss.

[0061] Step B: In the proxy device, based on a preset set of additional delay duration and additional packet loss rate parameters, the forwarded data packets are subjected to additional delay and additional packet loss.

[0062] Step C: Add the base latency and the additional latency to determine the actual latency. Combine the base packet loss rate and the additional packet loss rate to determine the actual packet loss rate. The actual packet loss rate can be calculated as: Actual packet loss rate = 1 - (1 - Additional packet loss rate) * (1 - Base packet loss rate).

[0063] Step D: Obtain a satisfaction score representing the application's performance on the terminal, under the conditions of actual latency and actual packet loss rate. Optionally, the satisfaction score can be a MOS (Mean Oriented Score) conforming to telecommunications industry standards, with a rating scale of 1 to 5. Optionally, in one embodiment, the terminal's user interface is refreshed each time a new set of additional latency and packet loss is introduced into the data packets in the proxy device. A preset prompt message is displayed on the user interface to request the user to input a satisfaction score for the current application's performance. The user-input satisfaction score corresponding to the current actual latency and actual packet loss rate is obtained from the user interface.

[0064] Step E involves changing the additional latency and additional packet loss rate parameters and repeating steps B to D to obtain multiple sets of results. Each set of results includes the actual latency, the actual packet loss rate, and the corresponding satisfaction score. Optionally, in one embodiment, the additional latency and additional packet loss rate parameters are changed in an increasing or decreasing order according to a preset gradient value.

[0065] Step F: From multiple sets of results, determine the combination of the maximum acceptable actual delay time and the maximum acceptable actual packet loss rate that ensures the satisfaction score is not lower than the preset satisfaction threshold.

[0066] Step G uses the combination of the determined maximum acceptable actual delay duration and the actual packet loss rate as a benchmark for selecting the quality of service of the communication line.

[0067] Step H: Based on the service quality benchmark, at least one candidate communication line is determined from multiple available communication lines. The service quality parameters of the candidate communication line meet the maximum acceptable actual latency and the maximum acceptable actual packet loss rate.

[0068] Step I: If the number of candidate communication lines is greater than 1, then select the communication line with the lowest cost from the candidate communication lines for communication between the terminal and the server.

[0069] Optionally, in one embodiment, steps A to G are executed separately in at least two preset different time periods, thereby determining a corresponding maximum acceptable combination of actual latency and actual packet loss rate for each different time period, serving as a benchmark for selecting the service quality of communication lines within that time period. In each different time period, based on the maximum acceptable combination of actual latency and actual packet loss rate determined for that time period, the proxy device selects from multiple available communication lines the communication line that meets its corresponding service quality benchmark and has the lowest cost within that time period.

[0070] Optionally, in one embodiment, step D is performed automatically by measuring one or more key performance indicators (KPIs) of the application using an automated script running on the terminal. Based on the measured values ​​of the KPIs, they are automatically converted into satisfaction scores using a preset mapping relationship. The KPIs include the application's frame rate, loading time, or response latency.

[0071] Optionally, in one embodiment, for each terminal within the local area network: one or more applications are run on the terminal, and steps A to E are repeated for each application, thereby determining a maximum acceptable combination of actual latency and actual packet loss rate as a service quality benchmark for each combination of terminal and application; when the proxy device processes a data packet originating from a specific application of a specific terminal, based on the service quality benchmark determined for the combination of terminal and application, the communication line that meets the service quality benchmark and has the lowest cost from multiple currently available communication lines is dynamically selected for forwarding the data packet.

[0072] To better understand the technical solution of this application, a specific example is provided below. The details listed in this example are mainly for ease of understanding and are not intended to limit the scope of protection of this application. This embodiment describes a typical modern office scenario.

[0073] An office with 20 employees has its internal local area network (LAN) connected to the internet via a smart hardware gateway acting as a "proxy device." This smart hardware gateway is provided by an intermediary service provider. This intermediary service provider has three different communication lines, all connected to the smart hardware gateway: Line X: A high-quality fiber optic leased line provided by telecom service provider A, with a bandwidth of 1000Mbps and a monthly fee of 3000 yuan. Its basic latency is extremely low (e.g., 5ms), and its basic packet loss rate is negligible. Line Y: Standard commercial broadband provided by telecom service provider B, with a bandwidth of 500Mbps and a monthly fee of 800 yuan. Its basic latency is moderate (e.g., 20ms), and its basic packet loss rate is low (e.g., 0.1%). Line Z: 5G wireless broadband, used as a backup and supplementary line, provided by telecom service provider C, with a bandwidth of 200Mbps, billed by traffic. Its basic latency and packet loss rate are affected by signal strength and fluctuate significantly (e.g., 40-100ms latency, 0.5%-2% packet loss rate).

[0074] The office contains various terminal devices running applications with varying network quality requirements. Terminal 1 (conference room host) is dedicated to running high-definition video conferencing applications and is extremely sensitive to latency and packet loss. Terminal 2 (designer's computer) primarily runs design software, requiring frequent uploading and downloading of large design files (GB level), and is relatively sensitive to packet loss (high packet loss leads to retransmissions, slowing down the process), but is not sensitive to latency. Terminal 3 (sales department employee's mobile phone) mainly uses VoIP to communicate with clients, and is extremely sensitive to latency and jitter (variations in latency), but has a certain tolerance for packet loss. Terminal 4 (general employee's computer): mainly used for web browsing, sending and receiving emails, and using online documents, with generally lower network quality requirements.

[0075] This embodiment is divided into two stages: the baseline determination stage and the dynamic routing stage.

[0076] Phase 1: Determine service quality benchmarks for different applications.

[0077] The smart hardware gateway (agent device) executes a baseline determination process for each critical application. Here, we take the video conferencing application of terminal 1 as an example. First, basic network parameters are measured. The gateway first selects the currently best-quality line X, measures and records the basic latency of video conferencing data packets to its server as 5ms, and the basic packet loss rate as 0.01%. Then, iterative testing and scoring are performed. The gateway initiates an automated testing process, including the following steps:

[0078] Automated Scoring: A corresponding automated script runs on Terminal 1. This script analyzes the video conferencing application's API or screen analytics to monitor key performance indicators (KPIs) in real time, such as video frame rate, audio latency, and image pixelation. The script has a built-in mapping model that converts these KPI measurements into a standard 5-point MOS score. Under these network conditions, the application runs perfectly, and the script outputs a MOS score of 5.0.

[0079] Gradual Changes and Repetitions: The gateway continuously increases additional latency and packet loss according to preset gradient values ​​(e.g., latency increases by 10ms each time, packet loss rate increases by 0.1% each time), and repeats the above scoring process.

[0080] When the actual latency reached 60ms and the actual packet loss rate reached 0.8%, the script detected very slight stuttering in the video, and the MOS score dropped to 4.0. When the actual latency reached 90ms and the actual packet loss rate reached 1.5%, the script detected significant audio-video desynchronization and frequent video stuttering, and the MOS score dropped to 3.4. The test continued until the MOS score fell below an unacceptable value (e.g., 2.0).

[0081] Next, the maximum acceptable combination is determined. A preset satisfaction threshold is set; for critical applications like video conferencing, this threshold can be set relatively high, for example, a MOS score of no less than 4.0. The system analyzes all test results to identify combinations that meet the MOS score requirement. Under these conditions, the combination of the maximum tolerable latency and the maximum packet loss rate is determined. In this example, the determined combination is: a maximum acceptable actual latency of 80ms and a maximum acceptable actual packet loss rate of 1.2%.

[0082] Subsequently, a QoS benchmark was established, and the combination of {latency ≤ 80ms, packet loss rate ≤ 1.2%} was used as the service quality benchmark for "video conferencing application" and stored in the gateway's policy library.

[0083] Subsequently, the gateway repeats the entire process for large file transfer applications on designers' computers and VoIP applications on sales staff's mobile phones, determining a dedicated and optimized QoS benchmark for each "terminal-application" combination. For example, the QoS benchmark for large file transfer applications might be: {latency ≤ 800ms, packet loss rate ≤ 0.5%}. The QoS benchmark for VoIP applications might be: {latency ≤ 50ms, packet loss rate ≤ 1.5%}.

[0084] Phase 2: Benchmark-based dynamic intelligent routing.

[0085] In daily operation, the smart hardware gateway (agent device, hereinafter referred to as the gateway) performs the following operations in real time:

[0086] Real-time line monitoring. The gateway periodically sends probe packets to all three lines (X, Y, Z) to monitor their current actual latency and packet loss rate in real time. Assuming it's 10:00 AM on a weekday, the monitoring results are as follows: Line X: Latency 5ms, Packet Loss Rate 0.01%, High Cost; Line Y: Latency 35ms, Packet Loss Rate 0.4%, Medium Cost; Line Z: Latency 70ms, Packet Loss Rate 1.0%, Low Cost.

[0087] Traffic identification and policy matching. Scenario 1: A video conference is initiated in the conference room. The gateway identifies this as video conferencing application traffic originating from terminal 1. It retrieves the QoS benchmark {latency ≤ 80ms, packet loss rate ≤ 1.2%} from the policy library. Scenario 2: A designer begins uploading a large file. The gateway identifies this as large file transfer traffic originating from terminal 2 and retrieves its QoS benchmark {latency ≤ 800ms, packet loss rate ≤ 0.5%}.

[0088] Decision-making and execution.

[0089] For video conferencing traffic:

[0090] Line X (5ms≤80ms, 0.01%≤1.2%) -> Satisfies.

[0091] Line Y (35ms≤80ms, 0.4%≤1.2%) -> Satisfies the requirements.

[0092] Line Z (70ms≤80ms, 1.0%≤1.2%) -> Satisfies the requirements.

[0093] Decision: Lines X, Y, and Z all meet the QoS benchmark. The gateway selects line Z, which has the lowest cost, to carry the traffic for this video conference.

[0094] For large file upload traffic:

[0095] Line X (5ms≤800ms, 0.01%≤0.5%) -> Satisfies the condition.

[0096] Line Y (35ms≤800ms, 0.4%≤0.5%) -> Satisfies the requirements.

[0097] Line Z (70ms≤800ms, 1.0%>0.5%) -> Does not meet the requirements (packet loss rate exceeds the limit).

[0098] Decision: Lines X and Y meet the QoS benchmark. The gateway selects the lower-cost line Y to handle the file upload task.

[0099] It can also make adaptive adjustments based on time of day. For example, during the peak network period at 2 PM, line Z experiences network quality degradation due to excessive base station load: latency of 120ms and packet loss rate of 2.5%. The gateway's real-time monitoring system detects this change. If a video conference is still in progress in the conference room, the gateway will automatically reassess: line Z (120ms > 80ms) no longer meets the QoS baseline for video conferencing. The gateway will immediately and seamlessly switch the video conference traffic to the currently lowest-cost line (line Y) that meets the baseline, thus ensuring that the user's application experience is not affected.

[0100] Through the above embodiments, the technical solution of this application brings significant advantages:

[0101] Cost optimization means no longer blindly placing all critical business operations on the most expensive, high-quality lines, but intelligently using cheaper lines based on the actual "bottom line" that each application can tolerate, significantly reducing the overall network expenses of the office.

[0102] The user experience is guaranteed, with each application's experience ensured by its own dedicated QoS benchmark based on user satisfaction (MOS score). Even when using lower-cost lines, the user's actual experience will not fall below the preset satisfaction threshold.

[0103] By maximizing resource utilization, the use of multiple communication line resources is refined and differentiated, reserving the highest quality resources for the most sensitive applications and using ordinary quality resources for applications with lower requirements, thereby improving the overall efficiency of network resource utilization.

[0104] Automation and intelligence are combined; the entire process, from baseline determination to dynamic routing, can be executed automatically without human intervention. It can dynamically adapt to changes in the network environment, thus achieving intelligent network management.

[0105] Accordingly, embodiments of this application also provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the various method embodiments of this application. Computer-readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device. As defined herein, computer-readable storage media do not include transient computer-readable media, such as modulated data signals and carrier waves.

[0106] Furthermore, embodiments of this application also provide a proxy device, including a memory for storing computer-executable instructions, and a processor; the processor is used to implement the steps in the above-described method embodiments when executing the computer-executable instructions in the memory. The processor may be a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Digital Signal Processor (DSP), Microcontroller Unit (MCU), Neural Processing Unit (NPU), Application Specific Integrated Circuit (ASIC), Field Programmable Gate Array (FPGA), or other programmable logic devices. The aforementioned memory may be read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or solid-state drive, etc. The steps of the methods disclosed in the embodiments of this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.

[0107] Furthermore, embodiments of this application also provide a computer program product, including computer-executable instructions that, when executed by a processor, implement the steps in the above-described method embodiments.

[0108] It should be noted that in this application, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. In this application, if it refers to performing an action according to an element, it means performing the action at least according to that element, including two cases: performing the action only according to that element, and performing the action according to that element and other elements. Expressions such as "multiple," "repeatedly," and "various" include two, two times, two kinds, and more than two, more than two times, and more than two kinds.

[0109] The numbering used in describing the steps of a method does not inherently impose any restrictions on the order of these steps. For example, a step with a higher number does not necessarily have to be executed after a step with a lower number; it can be executed first and then second, or even in parallel, as long as such an execution order is reasonable to a person skilled in the art. Furthermore, having multiple steps with consecutively numbered sequences (e.g., step A, step B, step C, etc.) does not restrict other steps from being executed in between; for example, there can be other steps between step A and step B.

[0110] This specification includes combinations of various embodiments described herein. Individual references to embodiments are made (e.g., "one embodiment," "some embodiments," or "preferred embodiments"); however, these embodiments are not mutually exclusive unless indicated to be mutually exclusive or are readily apparent to those skilled in the art. It should be noted that the word "or" is used in a non-exclusive sense throughout this specification unless the context explicitly indicates or requires it.

[0111] Furthermore, it should be understood that the above description is merely a preferred embodiment of this specification and is not intended to limit the scope of protection of this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of this specification should be included within the scope of protection of one or more embodiments of this specification.

[0112] In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for determining a communication service quality benchmark, wherein a terminal communicates with a server through a proxy device, the proxy device forwarding data packets between the terminal and the server, characterized in that, The method includes the following steps: Step A: Measure the basic latency and basic packet loss rate of data packet transmission between the terminal and the server, provided that the proxy device does not actively introduce additional latency and additional packet loss. Step B: In the proxy device, based on a preset set of additional delay duration and additional packet loss rate parameters, the forwarded data packets are subjected to additional delay and additional packet loss. Step C: Add the base latency duration to the additional latency duration to determine the actual latency duration; combine the base packet loss rate with the additional packet loss rate to determine the actual packet loss rate; Step D: Obtain a satisfaction score representing the application running experience on the terminal, under the conditions of the actual latency and the actual packet loss rate. Step E involves changing the additional delay duration and additional packet loss rate parameters and repeating steps B to D until the satisfaction score is lower than the preset satisfaction threshold, to obtain multiple sets of results. Each set of results includes the actual delay duration, the actual packet loss rate, and the corresponding satisfaction score. Step F: From the multiple sets of results, determine the combination of the maximum acceptable actual delay time and the maximum acceptable actual packet loss rate that ensures the satisfaction score is not lower than the preset satisfaction threshold. Step G: For each terminal in the local area network: run one or more applications on the terminal, and repeat steps A to F for each application, thereby determining a maximum acceptable combination of actual latency and actual packet loss rate for each combination of terminal and application, as a benchmark for selecting the service quality of the communication line. When the proxy device processes a data packet originating from a specific application on a specific terminal, it dynamically selects the communication line that meets the service quality benchmark and has the lowest cost from multiple currently available communication lines based on the service quality benchmark determined for the combination of the terminal and the application, and uses it to forward the data packet.

2. The method for determining a communication service quality benchmark according to claim 1, characterized in that, Step D specifically includes: Each time a new set of additional latency and additional packet loss is introduced into the data packets in the proxy device, the user interface of the terminal is refreshed; The user interface displays a preset prompt message to request the user to input a satisfaction rating for the current application's running experience; The user-inputted satisfaction score, corresponding to the current actual latency and actual packet loss rate, is obtained from the user interface.

3. The method for determining a communication service quality benchmark according to claim 1, characterized in that, In step E, the additional delay duration and additional packet loss rate parameters are changed in an increasing or decreasing order according to preset gradient values.

4. The method for determining a communication service quality benchmark according to claim 1, characterized in that, The satisfaction rating is based on the MOS standard, which follows telecommunications industry standards and uses a numerical rating scale from 1 to 5.

5. The method for determining a communication service quality benchmark according to claim 1, characterized in that, The proxy device is one of the following two: Software agent integrated within the terminal operating system or application; A hardware gateway device deployed in the local network accessed by the terminal.

6. The method for determining a communication service quality benchmark according to claim 1, characterized in that, Steps A to G are executed separately in at least two preset different time periods, thereby determining a corresponding maximum acceptable combination of actual delay duration and actual packet loss rate for each of the different time periods, which serves as the benchmark for selecting the service quality of communication lines within that time period. At any given time period, based on the combination of the maximum acceptable actual latency and the actual packet loss rate determined for that time period, the proxy device selects from multiple available communication lines the communication line that meets its corresponding quality of service benchmark and has the lowest cost within that time period.

7. The method for determining a communication service quality benchmark according to claim 1, characterized in that, Step D is performed automatically by measuring one or more key performance indicators of the application through an automated script running on the terminal. Based on the measured values ​​of the key performance indicators, they are automatically converted into the satisfaction score through a preset mapping relationship; The key performance indicators include the application's frame rate, loading time, or response latency.

8. The method for determining a communication service quality benchmark according to claim 1, characterized in that, In step C, the actual packet loss rate = 1 - (1 - additional packet loss rate) * (1 - base packet loss rate).

Images