Heterogeneous network scheduling method and device and computer readable medium

Abstract

The embodiment of the invention provides a heterogeneous network scheduling method and device and a computer readable medium, and the scheme integrates objective evaluation based on index attributes and subjective evaluation based on artificial empowerment through a mode of combining objective evaluation and subjective evaluation, so that a comprehensive score serving as a network scheduling basis is improved, and the network scheduling efficiency is improved. According to the method, the effects of different types of heterogeneous networks for a certain specific target audio-visual service can be reflected more accurately, so that more accurate network scheduling is realized, the user experience is improved, meanwhile, dynamic switching of the networks can be realized, the terminal equipment can be ensured to be always connected with the optimal network in the whole process of executing the audio-visual service, and the user experience is improved. Therefore, the best transmission effect is obtained.

Description

Technical Field

[0001] The present application relates to the field of information technology, and in particular, to a heterogeneous network scheduling method, device, and computer-readable medium for different audio-visual services. Background Art

[0002] With the rapid development of information technology and the continuous popularization of domestic network transmission technology, people have put forward new requirements for traditional audio-visual services. From high-definition to ultra-high-definition, from live broadcast to on-demand and then to real-time audio-video communication, users' demands for audio-visual services have become more diversified, and at the same time, higher requirements have been put forward for network performance.

[0003] However, the current real network environment is complex and changeable. With the continuous development of technology, the networks in some households may have various different network forms such as wired networks, wireless WIFI (Wireless Fidelity) networks, and 5G (5th Generation Mobile Communication Technology) networks. These different networks have their own unique transmission characteristics and limitations during transmission. Therefore, how to allocate a suitable network for the user's terminal device according to different audio-visual service requirements has gradually become an urgent problem to be solved. At present, there is no suitable solution in the industry that can accurately implement the scheduling of heterogeneous networks, enabling the user's terminal device to access a suitable network when performing various audio-visual services, thereby obtaining the best transmission effect and enhancing the user experience. Summary of the Invention

[0004] An object of the present application is to provide a heterogeneous network scheduling method, device, and computer-readable medium.

[0005] To achieve the above object, an embodiment of the present application provides a heterogeneous network scheduling method, the method including:

[0006] Calculating an objective score of each network according to the index data of each network;

[0007] Calculating a subjective score of each network for the target audio-visual service according to the index data and the preset subjective weights of each network for the target audio-visual service;

[0008] Calculating a comprehensive score of each network for the target audio-visual service according to the objective score of each network and the subjective score for the target audio-visual service;

[0009] When the terminal device executing the target audio-visual service accesses the network, determining the network with the highest comprehensive score as the target network accessed by the terminal device.

[0010] Further, after determining the network with the highest comprehensive score as the target network to which the terminal device is connected, the following steps are further included:

[0011] Determine the other networks available for the terminal device except the target network as alternative networks;

[0012] After the terminal device executing the target audio-visual service is connected to the target network, continuously monitor the comprehensive score of each network for the target audio-visual service;

[0013] If the comprehensive score of any alternative network for the target audio-visual service exceeds the comprehensive score of the target network for the target audio-visual service and the switching condition is met, switch the target network to which the terminal device is connected to the alternative network with the highest comprehensive score.

[0014] Further, the switching condition includes:

[0015] Meet and the duration exceeds a preset time length, where represents the comprehensive score of the target network for the target audio-visual service, represents the comprehensive score of the alternative network for the target audio-visual service, and k is a coefficient greater than 1; or

[0016] Meet

[0017] Further, the network includes a wired network, a wireless WIFI network, and a 5G communication network. The terminal device includes a large-screen terminal device, a medium-screen terminal device, and a small-screen terminal device. The networks available for the large-screen terminal device include a wired network and a wireless WIFI network. The networks available for the medium-screen terminal device include a wireless WIFI network and a 5G communication network. The networks available for the small-screen device include a wireless WIFI network and a 5G communication network.

[0018] Further, calculating the comprehensive score of each network for the target audio-visual service according to the objective score and the subjective score of each network for the target audio-visual service includes:

[0019] Calculate the comprehensive score of each network for the target audio-visual service using the following formula:

[0020]

[0021] Where represents the comprehensive score of the i-th network for the target audio-visual service N, R i represents the subjective score of the i-th network for the target audio-visual service N, S i represents the objective score of the i-th network, and t is a constant greater than 0 and less than 1.

[0022] Further, calculate the objective score of each network according to the metric data of each network, including:

[0023] Obtain the metric data of each network and perform normalization processing on the values of the metric data;

[0024] According to the metric data after normalization processing in each network, use the entropy weight method to calculate the objective weights of each metric data;

[0025] Based on the objective weights, calculate the objective score of each network.

[0026] Further, calculate the subjective score of each network for the target audio-visual service according to the preset subjective weights of each network for the target audio-visual service, including:

[0027] Obtain the subjective weights of each network for the target audio-visual service through the expert method;

[0028] According to the metric data after normalization processing in each network and the subjective weights, calculate the subjective score of each network for the target audio-visual service.

[0029] Further, the metric data for objective score calculation includes bandwidth, delay, jitter, packet loss rate, and load, and the metric data for objective score calculation includes bandwidth, delay, jitter, packet loss rate, load, and cost.

[0030] Some embodiments of the present application further provide a heterogeneous network scheduling device, wherein the device includes a memory for storing computer program instructions and a processor for executing the computer program instructions. When the computer program instructions are executed by the processor, the device is triggered to execute the foregoing heterogeneous network scheduling method.

[0031] Some other embodiments of the present application further provide a computer-readable medium, on which computer program instructions are stored, and the computer program instructions can be executed by a processor to implement the foregoing heterogeneous network scheduling method.

[0032] Compared with the prior art, an heterogeneous network scheduling scheme provided by an embodiment of the present application can calculate the objective score of each network according to the metric data of each network. At the same time, according to the metric data and the preset subjective weights of each network for the target audio-visual service, calculate the subjective score of each network for the target audio-visual service. After calculating the comprehensive score of each network for the target audio-visual service based on the objective score of each network and the subjective score for the target audio-visual service, when the terminal device executing the target audio-visual service accesses the network, the network with the highest comprehensive score can be determined as the target network accessed by the terminal device. Thus, based on the comprehensive objective evaluation based on metric attributes and the subjective evaluation based on artificial weighting, the comprehensive score used as the basis for network scheduling can more accurately reflect the effects of different types of heterogeneous networks for a specific target audio-visual service, thereby achieving more accurate network scheduling and improving the user experience.

[0033] Further, after the terminal device executing the target audio-visual service accesses the target network, other currently unaccessed networks can be used as alternative networks, and the comprehensive scores of each network including the target network and the alternative networks for the target audio-visual service are monitored in real time. When the comprehensive score of any alternative network for the target audio-visual service exceeds the comprehensive score of the target network for the target audio-visual service and the switching condition is met, the target network accessed by the terminal device is switched to the alternative network with the highest comprehensive score. Thus, dynamic switching of the network can be achieved, ensuring that the terminal device can always be connected to the optimal network throughout the entire process of executing the audio-visual service, thereby obtaining the best transmission effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] By reading the detailed description of the non-limiting embodiments with reference to the following drawings, other features, objects, and advantages of the present application will become more apparent:

[0035] Figure 1 It is a schematic diagram of the processing flow of an heterogeneous network scheduling method provided by an embodiment of the present application;

[0036] The same or similar reference numerals in the drawings represent the same or similar components. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] The present application will be described in further detail below with reference to the drawings.

[0038] In a typical configuration of the present application, the terminal and the device serving the network both include one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0039] The memory may include non - permanent memory in the form of computer - readable media, such as random access memory (RAM) and / or non - volatile memory, such as read - only memory (ROM) or flash RAM. The memory is an example of computer - readable media.

[0040] Computer - readable media includes permanent and non - permanent, removable and non - removable media that can store information by any method or technology. The information can be computer program 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, compact disc read - only memory (CD - ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non - transitory medium that can be used to store information that can be accessed by a computing device.

[0041] An embodiment of this application provides a heterogeneous network scheduling method. This method can calculate the objective score of each network according to the metric data of each network, and at the same time, according to the metric data and the preset subjective weights of each network for the target audio - visual service, calculate the subjective score of each network for the target audio - visual service. After calculating the comprehensive score of each network for the target audio - visual service based on the objective score and the subjective score of each network for the target audio - visual service, when the terminal device accessing the network for the target audio - visual service, the network with the highest comprehensive score can be determined as the target network accessed by the terminal device. Thus, by comprehensively considering the objective evaluation based on metric attributes and the subjective evaluation based on artificial weighting, the comprehensive score used as the basis for network scheduling can more accurately reflect the effects of different types of heterogeneous networks for a specific target audio - visual service, thereby achieving more accurate network scheduling and improving the user experience.

[0042] In an actual scenario, the execution entity of this method can be a user device, a network device, or a device formed by integrating a user device and a network device through a network, or it can also be an application program running on the above - mentioned devices. The user device includes, but is not limited to, various terminal devices such as computers, mobile phones, and tablets; the network device includes, but is not limited to, network hosts, single network servers, multiple network server sets, or computer collections based on cloud computing. Here, the cloud consists of a large number of hosts or network servers based on cloud computing. Cloud computing is a type of distributed computing, consisting of a virtual computer formed by a group of loosely coupled computers.

[0043] A heterogeneous network scheduling method provided by an embodiment of this application comprehensively considers the characteristics of various different networks and the requirements of different audio-visual services, combines the objective and subjective evaluation results, determines a comprehensive score as the basis for scheduling, and selects a suitable network for the terminal device when needed.

[0044] Among them, the heterogeneous network in the solution of this application refers to an architecture including multiple different types of networks. For example, the solution in this embodiment may include a wired network, a wireless WIFI network, a 5G network, etc. These networks have different characteristics, so their applicability to different audio-visual services is also different. In the embodiment of this application, taking the above three networks as examples, the solution will be described:

[0045] Among them, the characteristics of the wired network are as follows: For the application scenario of the radio and television industry, the wired network refers to the cable television network, which is a network system that uses physical media such as coaxial cables or optical fibers to specifically transmit television signals and other multimedia content. It originated in the mid-20th century. With the continuous progress of technology, it has developed from traditional analog signal transmission to modern digital signal transmission. This network not only provides high-quality TV programs, but also covers Internet access, telephone services, and various interactive multimedia applications. With its excellent bandwidth capacity, stable transmission performance, and low latency characteristics, the wired network plays a crucial role in building an efficient and high-speed data transmission system, which enables it to transmit high-definition, even 4K / 8K ultra-high-definition TV signals, providing users with an excellent audio-visual experience. In addition, through digital encryption technology, the cable television network can effectively ensure the secure transmission of signals and prevent illegal theft and copying. Due to the above characteristics, in the heterogeneous network architecture, the wired network, as an important part of the infrastructure, usually undertakes a large number of core data transmission tasks, including high-definition video streams, large-scale file sharing, and real-time interactive data, etc. They connect each node through physical lines, avoiding the interference and attenuation problems that wireless signals may suffer, and ensuring the consistency and reliability of data transmission.

[0046] However, the limitations of the wired network cannot be ignored. First, the wiring process is complex and costly, especially in large-scale deployments, which requires careful planning and construction of infrastructure. Second, due to the fixed lines, the wired network is unable to meet the requirements when facing user mobility and convenience. At the same time, it cannot provide access services for users' mobile terminal devices (such as small and medium-sized screen terminal devices like mobile phones and tablets), nor can it flexibly adapt to the connection requirements of different locations like the wireless WIFI network.

[0047] The characteristics of the wireless WIFI network are as follows: The wireless WIFI network has occupied a place in the modern communication field with its unique advantages. Its coverage is extensive, allowing users to seamlessly access the network at any location and at any time, greatly enhancing convenience and flexibility. At the same time, the deployment of the wireless WIFI network is relatively simple and fast, without the need for large-scale wiring projects, and is especially suitable for network coverage in temporary venues, hotspots, or remote areas. In a heterogeneous network environment, the wireless WIFI network plays a complementary and extended role. Especially for mobile users, it provides the possibility of seamless docking of wired and wireless services.

[0048] However, the wireless WIFI network has certain disadvantages compared to the wired network. First of all, due to the characteristics of wireless signal propagation, its transmission process is easily affected by external environmental factors such as buildings, obstacles, and electromagnetic interference, which may lead to a decline in signal quality, bandwidth fluctuations, or even service interruptions. Secondly, the wireless WIFI network usually faces a greater risk of latency. Especially when the number of users surges, the problem of network congestion will become more prominent, which is a significant challenge for audio-visual services that require low-latency guarantees.

[0049] The characteristics of the 5G network are as follows: As the fifth-generation mobile communication technology, the 5G network mainly has good transmission performance and a large bandwidth. The ultra-high data transmission rate means that more data content can be quickly transmitted in the same time. Whether it is a high-definition movie, a 3D model, or a 4K / 8K ultra-high-definition video, it can be quickly downloaded and shared; the extremely low latency characteristic is crucial for real-time interactive applications. For example, in business scenarios such as remote medical surgery, virtual reality experiences, and online games, the 5G network can ensure the immediacy of information transmission; the large-scale connection ability enables the 5G network to support a large number of devices to be online simultaneously without interference, which is of great significance for the collaborative work of devices in smart cities, smart factories, and Internet of Things applications.

[0050] However, the construction and operation costs of the 5G network are relatively high, and the technical complexity is also relatively high. In practical applications, problems such as limited coverage, limited battery life, and network security also need to be solved.

[0051] Therefore, the characteristics of the above three different types of networks can be summarized as the content in Table 1:

[0052]

[0053] Table 1

[0054] In the radio and television industry, the current mainstream audio-visual services can mainly be classified into the following three types: live broadcast services, on-demand services, and audio-video communication services. For these different types of audio-visual services, the network requirements are also different. In the embodiments of this application, the above audio-visual services are taken as examples to illustrate the solution:

[0055] Among them, the requirements for the live broadcast service are as follows: The live broadcast service is a multimedia service in the modern Internet industry with requirements for real-time, high definition, and smooth audio quality. To meet such service requirements, the network scheduling scheme needs to have excellent response speed and adaptability. During the live broadcast, the transmission of content needs to be low-latency, ensuring that viewers can instantly watch the real-time dynamics of the anchor. At the same time, the picture resolution should be high, the color restoration should be accurate, and the audio quality should be clear and lossless, bringing an immersive experience to the viewers.

[0056] The requirements for the on-demand service are as follows: Compared with the live broadcast, the on-demand service focuses more on the user's personalized content selection and interactive experience. In this business model, the network scheduling scheme not only needs to quickly and accurately respond to each user's on-demand request but also needs to flexibly schedule and allocate network resources according to the specific network environment where the user is located and the real-time network conditions, select the optimal transmission path and encoding format, and ensure that the content can be smoothly delivered to the user terminal in the shortest time.

[0057] The requirements for the audio and video communication service are as follows: Audio and video communication services, such as online meetings, distance education, and real-time games, emphasize two-way communication and seamless transmission between users. Such services have extremely high requirements for the network. Any slight delay or jitter may affect the call quality and even cause poor experiences such as disconnection and reconnection. Therefore, in such service scenarios, the network scheduling scheme needs to have powerful real-time monitoring capabilities, be able to accurately capture and analyze the changing trends of the network status, and accordingly quickly make decisions, adjust the transmission strategy, and ensure the stability and smoothness of audio and video communication.

[0058] Thus, the requirements for the above three different types of audio-visual services can be summarized as the content in Table 2:

[0059]

[0060] Table 2

[0061] Figure 1 shows the processing flow of a heterogeneous network scheduling method provided by an embodiment of the present application, including at least the following processing steps:

[0062] Step S1, calculate the objective score of each network according to the index data of each network.

[0063] In the embodiments of the present application, the metric data may include bandwidth, latency, jitter, packet loss rate, and load, so as to quantitatively represent the characteristics of different networks. Among the above-mentioned metric data, bandwidth is a positive metric, that is, the larger the value of the bandwidth metric data, the better the performance of the network in this aspect. While latency, jitter, packet loss rate, and load are negative metrics, that is, the larger the values of these metric data such as latency, jitter, packet loss rate, and load, the worse the performance of the network in these aspects.

[0064] When calculating the objective score, first, the metric data of each network can be obtained, and the values of the metric data are standardized. Then, based on the standardized metric data in each network, the objective weights of each metric data are calculated using the entropy weight method. Finally, based on the objective weights, the objective score of each network is calculated.

[0065] Among them, the entropy weight method is an objective evaluation method that can be used for multi-object and multi-metric problems. When dealing with the problem of multi-metric weighting, it can effectively eliminate the result deviation caused by subjective human assignment, avoid the influence of subjective factors, and improve the objectivity and accuracy of the evaluation results. The specific calculation steps are as follows:

[0066] Step S101, data standardization.

[0067] The entropy weight method requires data standardization to ensure fair and effective comparison between different metrics. Since different metrics may have different dimensions and value ranges, directly comparing them will lead to inaccurate results. Therefore, it is necessary to standardize the metric data.

[0068] First, a metric data matrix can be constructed based on the metric data of each network. Taking the 3 networks and 5 metric data in the above scenario as an example, a 3×5 metric data matrix X can be constructed:

[0069]

[0070] In this embodiment, m = 3, n = 5, and the element X in the metric data matrix X ij represents the value of the j-th metric data of the i-th network, corresponding to the data in Table 3:

[0071]

[0072]

[0073] Table 3

[0074] For example, in this embodiment, if the order of the three types of networks is set to be a wired network, a wireless WIFI network, and a 5G network in sequence, and the order of the five types of index data is bandwidth, delay, jitter, packet loss rate, and load in sequence, then the element X in the index data matrix X 23 represents the value of the jitter index of the wireless WIFI network.

[0075] When performing the normalization process, since the bandwidth is a positive index, the following formula can be used for normalization:

[0076]

[0077] where Z ij is the normalized value of the element X in the index data matrix X ij after normalization, max(X 1j ,…, X mj ) represents taking the maximum value among the elements in the j-th column, and min(X 1j ,…, X mj ) represents the minimum value among the elements in the j-th column.

[0078] For negative indexes such as delay, jitter, packet loss rate, and load, the following formula can be used for normalization:

[0079]

[0080] For the 3×5 index data matrix X in the embodiment of the present application, the elements in the first column are subjected to positive normalization, and the elements in the second to fifth columns are subjected to positive normalization.

[0081] After the index data matrix X undergoes the above normalization process, a standard data matrix Z can be obtained:

[0082]

[0083] Step S102, calculate the numerical proportion.

[0084] For the numerical proportion P corresponding to the element in the i-th row and j-th column of the matrix ij it can be calculated using the following formula:

[0085]

[0086] Step S103, calculate the entropy value.

[0087] Taking the elements in the j-th column of the matrix as an example, the entropy value e of the corresponding index data j can be calculated using the following formula:

[0088]

[0089] Step S104, calculate the coefficient of variation.

[0090] The coefficient of variation is D j It can be obtained by subtracting the entropy value of the corresponding index data from 1, and the specific calculation formula is as follows:

[0091] D j = 1 - e j

[0092] Step S105, calculate the objective weights of each index data.

[0093] Taking the weight w of the jth index data as an example, its calculation formula is as follows: j For example, its calculation formula is as follows:

[0094]

[0095] Step S106, calculate the objective scores of the objective weight calculation network of each index data.

[0096] Taking the ith network as an example, its objective score S i The calculation formula is as follows:

[0097]

[0098] Thus, the objective scores of each network are accurately calculated by the entropy weight method for subsequent processing.

[0099] Step S2, calculate the subjective scores of each network for the target audiovisual service according to the index data and the preset subjective weights of each network for the target audiovisual service.

[0100] In the actual scenario, considering the differences in the requirements of various audiovisual services for each network index during the actual development of audiovisual services, subjective weights can be assigned to the index data of the network, and appropriate subjective weights can be preset to calculate the subjective scores of each network for the target audiovisual service, so as to make up for the one-sidedness of the objective scores and make the comprehensive scores used for actual evaluation more comprehensive and accurate.

[0101] In some embodiments of the present application, in order to obtain more accurate subjective weights, the subjective weights of each network for the target audiovisual service obtained by the expert method can be used, and then according to the index data and the subjective weights after standardized processing in each network, calculate the subjective scores of each network for the target audiovisual service.

[0102] Among them, when calculating the subjective weight, in addition to the index data used in the calculation of the objective score, the index data of cost can be further added. For example, the index data used for objective score calculation includes 5 items: bandwidth, delay, jitter, packet loss rate, and load, while the index data used for objective score calculation includes 6 items: bandwidth, delay, jitter, packet loss rate, load, and cost. Thus, for this scenario, when calculating the subjective score, both the index data matrix X and the standard data matrix Z will be expanded into 3×6 matrices.

[0103] Taking the above three networks as an example, the cost of the 5G network is the highest, the cost of the wired network is the second, and the cost of the wireless WIFI network is the lowest. In this embodiment, the cost index data of the above three networks can be set to the following values according to this principle: the cost of the 5G network is 10, the cost of the wired network is 5, and the cost of the wireless WIFI network is 1. Since cost is a negative index, the standardized value of the cost can be calculated by the method of standardizing negative indexes described above, and combined with the subjective weight to calculate the subjective score of each network for the target audiovisual service.

[0104] This embodiment gives a calculation formula for the subjective score, which is specifically as follows:

[0105]

[0106] Among them, represents the subjective score of the i-th network for the target audiovisual service N, and Z ij is the standardized value of the element X ij in the index data matrix X after being standardized, represents the subjective weight of the j-th index data of the i-th network for the audiovisual service N. The specific form of the subjective weight can be as shown in Table 4 below:

[0107]

[0108]

[0109] Table 4

[0110] Step S3, calculate the comprehensive score of each network for the target audiovisual service according to the objective score and the subjective score of each network for the target audiovisual service.

[0111] When calculating the comprehensive score of each network for the target audiovisual service according to the objective score and the subjective score of each network for the target audiovisual service, the following formula can be specifically used for calculation:

[0112]

[0113] Among them, represents the comprehensive score of the i-th network regarding the target audiovisual service N, and R i represents the subjective score of the i-th network regarding the target audiovisual service N, and S i represents the objective score of the i-th network. t is a constant greater than 0 and less than 1, such that t can be adjusted between 0 and 1 according to the needs of the actual scenario to facilitate optimizing the results of the algorithm. When t is set larger, it means that the subjective score has a greater impact on the comprehensive evaluation. Conversely, if t is set smaller, it means that the objective score has a greater impact on the comprehensive evaluation.

[0114] Furthermore, after substituting the calculation formulas of and S i disclosed in the foregoing content, the following comprehensive score calculation formula can be obtained:

[0115]

[0116] Step S4, when the terminal device for executing the target audiovisual service accesses the network, determine the network with the highest comprehensive score as the target network for the terminal device to access.

[0117] When the terminal device for executing the target audiovisual service accesses the network, in order to obtain a better transmission effect and improve the user experience, the comprehensive scores of each network available to the terminal device regarding the target audiovisual service can be calculated in real time, select the network with the highest comprehensive score, and determine the network with the highest comprehensive score as the target network for the terminal device to access. Thus, it can be ensured that the terminal device can connect to the network with the highest comprehensive score to execute the target audiovisual service, and ensure that the target network accessed by the terminal device is a network suitable for executing the target audiovisual service.

[0118] In some embodiments of the present application, after determining the network with the highest comprehensive score as the target network for the terminal device to access, other networks available to the terminal device except the target network can also be determined as alternative networks. For example, taking the three networks in the foregoing scenario as an example, if a certain terminal device can use three networks simultaneously, after determining the 5G network with the highest comprehensive score as the target network for the terminal device to access, the other two available networks, namely the wired network and the wireless WIFI network, can be determined as alternative networks.

[0119] After the terminal device performing the target audio-visual service accesses the target network, the comprehensive score of each network regarding the target audio-visual service can be monitored in real time. If the comprehensive score of any alternative network regarding the target audio-visual service exceeds the comprehensive score of the target network regarding the target audio-visual service and the switching condition is satisfied, the target network to which the terminal device is connected is switched to the alternative network with the highest comprehensive score.

[0120] Among them, the purpose of setting the switching condition is to avoid the problem of performance degradation caused by frequent network switching, thereby implementing a ping-pong switching suppression mechanism. This mechanism controls and manages the switching process by setting specific switching conditions, so as to reduce unnecessary switching and improve the stability and efficiency of the system. Among them, the switching condition may include the following specific content:

[0121] Satisfy and the duration exceeds the preset duration, where represents the comprehensive score of the target network regarding the target audio-visual service, represents the comprehensive score of the alternative network regarding the target audio-visual service, k is a coefficient greater than 1, which can be dynamically adjusted according to the needs of the actual scenario, and its value range can be set to be greater than 1 and less than 1.5; or satisfy

[0122] For example, in the solution of the embodiment of the present application, when the terminal device performing the target audio-visual service accesses the network, if the calculated comprehensive scores of three networks regarding the audio-visual service N are the wired network wireless WIFI network 5G network At this time, the wireless WIFI network with the highest comprehensive score regarding the audio-visual service N can be determined as the target network. At this time If all three networks are networks that the terminal device can use, then at this time There are two, which are respectively and

[0123] After the terminal device performing the target audio-visual service accesses the target network, the comprehensive score of each network regarding the target audio-visual service is monitored in real time. If at a certain moment, it is monitored that the wired network wireless WIFI network 5G network If t in this solution is set to 1.4, at this time it satisfies At this time, it can enter the pre-switching preparation state and further judge that it satisfies Whether the duration exceeds a preset duration, such as 10 minutes, 20 minutes, 30 minutes, etc. If it exceeds the preset duration, it means that the switching condition is met. At this time, a switching instruction is sent to perform network switching, and the target network (wireless WIFI network) to which the terminal device is connected is switched to the alternative network with the highest comprehensive score (5G network).

[0124] In addition, another situation that satisfies the switching condition is This situation corresponds to a scenario where the comprehensive score of the alternative network is significantly higher than that of the current target network. At a certain moment, a wired network Wireless WIFI network 5G network At this time, since the advantage of the alternative network is significantly better than that of the current target network, the performance improvement brought by this will far exceed the performance overhead caused by switching. Therefore, there is no need to wait for the preset duration, and network switching can be directly performed to switch the target network (wireless WIFI network) to which the terminal device is connected to the alternative network with the highest comprehensive score (5G network).

[0125] In some embodiments of the present application, for the audio-visual service scenario of a conventional family, the types of terminal devices can be mainly divided into the following three types, including large-screen terminal devices (such as set-top boxes, smart TVs, etc.), medium-screen terminal devices (tablet computers), and small-screen terminal devices (mobile phones). The network types that these terminal devices can use are shown in Table 5 below:

[0126] Wired network Wireless WIFI network 5G network Large screen terminal device √ √ × Medium screen terminal device × √ √ Small screen terminal device × √ √

[0127] Table 5

[0128] As can be seen from Table 5 above, the networks that the large-screen terminal devices in the embodiments of the present application can use include wired networks and wireless WIFI networks. The networks that the medium-screen terminal devices can use include wireless WIFI networks and 5G communication networks. The networks that the small-screen devices can use include wireless WIFI networks and 5G communication networks. Therefore, when judging the switching condition, it is necessary to compare the values to determine whether to switch to the alternative network.

[0129] In addition, the embodiments of the present application also provide a heterogeneous network scheduling device, which includes a memory for storing computer program instructions and a processor for executing the computer program instructions. When the computer program instructions are executed by the processor, the device is triggered to execute the foregoing heterogeneous network scheduling method.

[0130] In particular, the method and / or embodiments in the embodiments of the present application can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. When the computer program is executed by a processing unit, the above functions defined in the method of the present application are executed.

[0131] It should be noted that the computer-readable medium described in the present application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0132] In the present application, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0133] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., by connecting through the Internet using an Internet service provider).

[0134] The flowcharts or block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of devices, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of the code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks can occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0135] As another aspect, this application also provides a computer-readable medium, which can be included in the devices described in the above embodiments; or it can exist separately without being assembled into the device. The above computer-readable medium carries one or more computer program instructions, and the computer program instructions can be executed by a processor to implement the methods and / or technical solutions of the foregoing multiple embodiments of this application.

[0136] It should be noted that the present application can be implemented in software and / or a combination of software and hardware. For example, it can be implemented using an application specific integrated circuit (ASIC), a general purpose computer, or any other similar hardware device. In some embodiments, the software program of the present application can be executed by a processor to implement the above steps or functions. Similarly, the software program of the present application (including related data structures) can be stored in a computer-readable recording medium, such as a RAM memory, a magnetic or optical drive, or a floppy disk and the like. In addition, some steps or functions of the present application can be implemented using hardware, for example, as a circuit that cooperates with the processor to execute each step or function.

[0137] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or basic characteristics of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present application is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be encompassed in the present application. Any reference signs in the claims should not be construed as limiting the claimed rights. In addition, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. The multiple elements or devices recited in the apparatus claims can also be implemented by one element or device through software or hardware. First, second, etc. are used to denote names and do not denote any particular order.

Claims

1. A heterogeneous network scheduling method, characterized in that, The method includes: Calculating the objective score of each network according to the metric data of each network; Calculating the subjective score of each network for the target audio-visual service according to the metric data and the preset subjective weights of each network for the target audio-visual service; Calculating the comprehensive score of each network for the target audio-visual service according to the objective score of each network and the subjective score for the target audio-visual service; When the terminal device executing the target audio-visual service accesses the network, determining the network with the highest comprehensive score as the target network accessed by the terminal device.

2. The method according to claim 1, wherein After determining the network with the highest comprehensive score as the target network accessed by the terminal device, it further includes: Determining the other networks available to the terminal device except the target network as alternative networks; After the terminal device executing the target audio-visual service accesses the target network, real-time monitoring the comprehensive scores of each network for the target audio-visual service; If the comprehensive score of any alternative network for the target audio-visual service exceeds the comprehensive score of the target network for the target audio-visual service and the switching condition is satisfied, switching the target network accessed by the terminal device to the alternative network with the highest comprehensive score.

3. The method according to claim 2, wherein The switching condition includes: Meet and the duration exceeds a preset duration, where represents the comprehensive score of the target network for the target audio-visual service, represents the comprehensive score of the alternative network for the target audio-visual service, and k is a coefficient greater than 1; or Meet 4. The method according to claim 2, characterized in that The network includes a wired network, a wireless WIFI network, and a 5G communication network. The terminal device includes a large-screen terminal device, a medium-screen terminal device, and a small-screen terminal device. The networks available to the large-screen terminal device include a wired network and a wireless WIFI network. The networks available to the medium-screen terminal device include a wireless WIFI network and a 5G communication network. The networks available to the small-screen device include a wireless WIFI network and a 5G communication network.

5. The method according to claim 1, wherein Calculating the comprehensive score of each network for the target audio-visual service according to the objective score of each network and the subjective score for the target audio-visual service includes: Calculating the comprehensive score of each network for the target audio-visual service using the following formula: Among them, represents the comprehensive score of the i-th network regarding the target audiovisual service N, and R i represents the subjective score of the i-th network regarding the target audiovisual service N, and S i represents the objective score of the i-th network, and t is a constant greater than 0 and less than 1.

6. The method according to claim 5, characterized in that Calculating the objective score of each network according to the metric data of each network includes: Obtaining the metric data of each network and performing normalization processing on the numerical values of the metric data; Calculating the objective weights of each metric data using the entropy weight method according to the metric data of each network after normalization processing; Calculating the objective score of each network based on the objective weights.

7. The method according to claim 5, wherein Calculating the subjective score of each network for the target audio-visual service according to the preset subjective weights of each network for the target audio-visual service includes: Obtaining the subjective weights of each network for the target audio-visual service through the expert method; Calculating the subjective score of each network for the target audio-visual service according to the metric data of each network after normalization processing and the subjective weights.

8. The method according to claim 1, characterized in that, The metric data for calculating the objective score includes bandwidth, delay, jitter, packet loss rate, and load. The metric data for calculating the objective score includes bandwidth, delay, jitter, packet loss rate, load, and cost.

9. An heterogeneous network scheduling device, wherein, The device includes a memory for storing computer program instructions and a processor for executing the computer program instructions, wherein when the computer program instructions are executed by the processor, the device is triggered to execute the method according to any one of claims 1 to 7.

10. A computer-readable medium having computer program instructions stored thereon, the computer program instructions being executable by a processor to implement the method according to any one of claims 1 to 7.

Images