Network slice selection method and apparatus

Abstract

The application relates to the technical field of slice selection, and provides a network slice selection method and device. The method comprises the following steps: calculating selection parameter values corresponding to a plurality of network slices respectively to obtain a plurality of selection parameter values; determining a maximum selection parameter value from the plurality of selection parameter values, and determining a network slice corresponding to the maximum selection parameter value as a target network slice; wherein the selection parameter value corresponding to any network slice is determined based on a target round-trip delay corresponding to the any network slice and an image control parameter value corresponding to the any network slice. The network slice selection method and device provided by the application can efficiently and accurately select a network slice with optimal network transmission performance and matching actual use demand through a machine automatic process, and based on a target round-trip delay and an image control parameter value corresponding to an actual network slice to obtain a selection parameter value, and determine a target network slice through the selection parameter value.

Description

Technical Field

[0001] This application relates to the field of slice selection technology, specifically to a method and apparatus for selecting network slices. Background Technology

[0002] The development of network technology has brought great convenience to remote operation. In remote operation scenarios, the master control end and the slave control end are connected through the network and exchange media files such as video and pictures of their respective areas so that the other party can understand its own environment and operation, ensuring that the remote operation is carried out accurately.

[0003] The existing network has multiple network slices, each isolated from each other and with varying performance. To ensure accurate remote operation, the network slices used for remote operation need to have good network transmission performance, enabling the master and slave ends to efficiently send and receive media files. However, traditional network slice selection methods include manual estimation or testing, which are inefficient and inaccurate, requiring significant manpower and resources. Other methods use model estimation, but the accuracy can be low due to mismatches between model results and actual usage requirements. Summary of the Invention

[0004] This application provides a network slice selection method and apparatus to solve the technical problems of traditional network slice selection methods, some of which rely on manual estimation or manual testing for network slice selection, resulting in low selection efficiency and accuracy and requiring a lot of manpower and resources, while others rely on model estimation for network slice selection, but the selection accuracy is low due to the mismatch between the model results and actual usage requirements.

[0005] In a first aspect, embodiments of this application provide a network slice selection method, including:

[0006] Calculate the selection parameter values ​​for each of the multiple network slices to obtain multiple selection parameter values;

[0007] The maximum selection parameter value is determined from the plurality of selection parameter values, and the network slice corresponding to the maximum selection parameter value is determined as the target network slice.

[0008] The selection parameter value corresponding to any network slice is determined based on the target round-trip time and the image control parameter value corresponding to any network slice.

[0009] In one embodiment, the selection parameter value corresponding to any network slice is determined based on the following method:

[0010] Calculate the normalized average of the round-trip latency of all users in the network slice at the target time to obtain the target round-trip latency corresponding to the network slice;

[0011] Calculate the neighboring coefficient set of multiple pixels in the transmitted image of the network slice at the target time to obtain the multiple neighboring coefficient sets corresponding to the network slice;

[0012] Based on the multiple adjacent coefficient sets, the image control parameter values ​​corresponding to the network slice are obtained;

[0013] The target round-trip time and the image control parameter value are fused to obtain the selection parameter value corresponding to the network slice.

[0014] In one embodiment, the set of neighboring coefficients for any pixel is determined based on the following method:

[0015] Based on the target coefficient of the pixel and the target coefficients of the pixels adjacent to the pixel in multiple directions, multiple adjacent coefficients corresponding to the pixel in multiple directions are obtained.

[0016] Based on the multiple neighbor coefficients, the neighbor coefficient set of the pixel is obtained.

[0017] In one embodiment, the target coefficient for any pixel is determined based on the following method:

[0018] Calculate the average pixel intensity and standard deviation of the pixel intensity of the transmitted image;

[0019] Based on the average pixel intensity and the standard deviation of pixel intensity, the mean-free normalization coefficient of the pixel intensity value is calculated to obtain the target coefficient of the pixel.

[0020] In one embodiment, obtaining the image control parameter values ​​corresponding to the network slice based on the plurality of adjacent coefficient sets includes:

[0021] Based on the multiple adjacent coefficient sets, parameter fitting is performed to obtain the multi-directional image shape control parameter value and multi-directional image diffusion control parameter value corresponding to the network slice;

[0022] The multi-directional image shape control parameter values ​​are fused to obtain the target shape control parameter values;

[0023] The multi-directional image diffusion control parameter values ​​are fused to obtain the target diffusion control parameter values.

[0024] In one embodiment, fusing the target round-trip time and the image control parameter value to obtain the selection parameter value corresponding to the network slice includes:

[0025] The target round-trip time delay, the target shape control parameters, and the target diffusion control parameters are fused to obtain the selection parameter values ​​corresponding to the network slice.

[0026] Secondly, embodiments of this application provide a network slice selection device, comprising:

[0027] The parameter value calculation module is used to: calculate the selection parameter values ​​corresponding to multiple network slices respectively, and obtain multiple selection parameter values;

[0028] The network slice selection module is used to: determine the maximum selection parameter value from the plurality of selection parameter values, and determine the network slice corresponding to the maximum selection parameter value as the target network slice;

[0029] The selection parameter value corresponding to any network slice is determined based on the target round-trip time and the image control parameter value corresponding to any network slice.

[0030] Thirdly, embodiments of this application provide an electronic device, including a processor and a memory storing a computer program, wherein the processor executes the program to implement the steps of the network slice selection method described in the first aspect.

[0031] Fourthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the network slice selection method described in the first aspect.

[0032] Fifthly, embodiments of this application provide a non-transitory computer-readable storage medium, including a computer program, which, when executed by a processor, implements the steps of the network slice selection method described in the first aspect.

[0033] The network slice selection method and apparatus provided in this application calculate selection parameter values ​​corresponding to multiple network slices to obtain multiple selection parameter values, determine the maximum selection parameter value from the multiple selection parameter values, and determine the network slice corresponding to the maximum selection parameter value as the target network slice. The selection parameter value corresponding to any network slice is determined based on the target round-trip time delay and the image control parameter value corresponding to the network slice. On the one hand, this application adopts a fully automated machine process, eliminating the need for manual estimation or testing, thereby effectively improving selection efficiency and accuracy. On the other hand, this application determines the selection parameter value of the network slice based on the target round-trip time and image control parameter value corresponding to the network slice. The target round-trip time can accurately measure the network transmission timeliness of the network slice, and the image control parameter value can accurately measure the impact of the network slice on the image quality during image transmission. Therefore, obtaining the selection parameter value based on the target round-trip time and image control parameter value is to obtain the selection weight of the network slice from both the aspects of network transmission timeliness and network transmission image quality. This selection weight can fully represent the network transmission performance of the corresponding network slice. By selecting the network slice corresponding to the maximum selection weight, the target network slice with the best network transmission performance can be selected. Moreover, since the selection is made from actual network slices, there will be no mismatch with actual usage requirements, further improving the selection accuracy. In summary, this application uses an automated machine process to obtain selection parameter values ​​based on the target round-trip time and image control parameter values ​​corresponding to the actual network slice. By determining the target network slice using these selection parameter values, it can efficiently and accurately select the network slice with the best network transmission performance that matches the actual usage requirements. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This is one of the flowcharts illustrating the network slice selection method provided in the embodiments of this application;

[0036] Figure 2 This is a second schematic flowchart of the network slice selection method provided in the embodiments of this application;

[0037] Figure 3 This is the third flowchart illustrating the network slice selection method provided in the embodiments of this application;

[0038] Figure 4This is a schematic diagram of the internal and external interaction process of the network slice selection device provided in the embodiments of this application;

[0039] Figure 5 This is one of the structural schematic diagrams of the network slice selection system provided in the embodiments of this application;

[0040] Figure 6 This is a second schematic diagram of the network slice selection system provided in the embodiments of this application;

[0041] Figure 7 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0043] Figure 1 This is one of the flowcharts illustrating the network slice selection method provided in this application. (Refer to...) Figure 1 This application provides a network slice selection method, which may include:

[0044] 101. Calculate the selection parameter values ​​for multiple network slices respectively to obtain multiple selection parameter values;

[0045] 102. Determine the maximum selection parameter value from multiple selection parameter values, and determine the network slice corresponding to the maximum selection parameter value as the target network slice.

[0046] The selection parameter value for any network slice is determined based on the target round-trip time and the image control parameter value corresponding to that network slice.

[0047] In step 101, for each network slice, the selection parameter value is determined based on its corresponding target round-trip time and image control parameter value, thereby obtaining the selection parameter values ​​for all network slices.

[0048] The image control parameter values ​​corresponding to different network slices can be control parameter values ​​for the same image or control parameter values ​​for different images. There is no limitation here, but the image control parameter value corresponding to any network slice must be obtained at the same time as its corresponding target round-trip delay.

[0049] The network slice selection method provided in this embodiment calculates selection parameter values ​​corresponding to multiple network slices to obtain multiple selection parameter values. The maximum selection parameter value is determined from the multiple selection parameter values, and the network slice corresponding to the maximum selection parameter value is determined as the target network slice. The selection parameter value corresponding to any network slice is determined based on the target round-trip time and the image control parameter value corresponding to the network slice. On the one hand, this embodiment employs a fully automated machine process, eliminating the need for manual estimation or testing, thereby effectively improving selection efficiency and accuracy. On the other hand, this embodiment determines the selection parameter value of the network slice based on the target round-trip time and image control parameter value corresponding to the network slice. The target round-trip time can accurately measure the network transmission timeliness of the network slice, and the image control parameter value can accurately measure the impact of the network slice on the image quality during image transmission. Therefore, obtaining the selection parameter value based on the target round-trip time and image control parameter value is to obtain the selection weight of the network slice from both the aspects of network transmission timeliness and network transmission image quality. This selection weight can fully represent the network transmission performance of the corresponding network slice. By selecting the network slice corresponding to the maximum selection weight, the target network slice with the best network transmission performance can be selected. Furthermore, since the selection is made from actual network slices, there will be no mismatch with actual usage requirements, further improving selection accuracy. In summary, this embodiment uses an automated machine process to obtain selection parameter values ​​based on the target round-trip latency and image control parameter values ​​corresponding to the actual network slice. By determining the target network slice using these selection parameter values, it is possible to efficiently and accurately select the network slice with the best network transmission performance that matches the actual usage requirements.

[0050] Figure 2 This is the second flowchart illustrating the network slice selection method provided in this application embodiment. (Refer to...) Figure 2 In one embodiment, the selection parameter value corresponding to any network slice can be determined based on the following method:

[0051] 201. Calculate the normalized average of the round-trip delays of all users in the network slice at the target time to obtain the target round-trip delay corresponding to the network slice;

[0052] 202. Calculate the neighboring coefficient set of multiple pixels in the transmitted image of the network slice at the target time, and obtain the multiple neighboring coefficient sets corresponding to the network slice;

[0053] 203. Based on multiple adjacent coefficient sets, obtain the image control parameter values ​​corresponding to the network slices;

[0054] 204. The target round-trip time delay and image control parameter values ​​are fused to obtain the selection parameter values ​​corresponding to the network slice.

[0055] In step 201, "all users" refers to all users using the network slice, including both master and slave users, and there may be multiple master and slave users.

[0056] Assuming there is a total A user, in The round-trip latency for using this network slice at any time is as follows: to The round-trip latency can be the round-trip latency for these users to receive the image. to Normalize them separately to obtain Individual users Normalized round-trip time to ,in, It is the first Individual users The round-trip latency of using the network slice at all times.

[0057] use express Individual users If the average round-trip time of using this network slice is used at any given time, then:

[0058] ;

[0059] The target round-trip time corresponding to this network slice is: .

[0060] It should be noted that it is also possible to... Time and nearby times are obtained The round-trip latency of each user using that network slice is calculated, and then the target round-trip latency for that network slice is calculated similarly based on these round-trip latencyes. Since the round-trip latency of each user is obtained at different times, ... to represent The round-trip time delay at time 1 and before and after 1 is the final result. There exists condition.

[0061] In step 202, each pixel has its own set of neighboring coefficients, and the set of neighboring coefficients for any pixel can be determined based on the following method:

[0062] 202a. Based on the target coefficient of the pixel and the target coefficients of the pixels adjacent to the pixel in multiple directions, obtain multiple adjacent coefficients of the pixel in multiple directions;

[0063] 202b. Based on multiple neighboring coefficients, obtain the set of neighboring coefficients for the pixel.

[0064] In step 202a, the multiple directions can be horizontal, vertical, main diagonal, and secondary diagonal. The target coefficient can be the mean-normalized coefficient of the pixel intensity value. Therefore, for the first pixel in the transmitted image... Line number For column pixels, its target coefficient It can be obtained based on the following formula:

[0065] ;

[0066] in, It is the first Line number The intensity value of the column pixel. It is the average pixel intensity of the transmitted image. It is the standard deviation of pixel intensity of the transmitted image. It is a constant and can be set according to actual needs. It is not limited here. In this embodiment, it can be... Set to 1 to prevent the denominator from being 0.

[0067] Assuming the height of the image after transmission is , width is Then there is , It can be used in the image after transmission. A two-dimensional Gaussian window is used to calculate the average pixel intensity and the standard deviation of pixel intensity, which plays a role in smoothing and reducing noise in the transmitted image. The specific calculation formula is as follows:

[0068] ;

[0069] ;

[0070] in, It is the first in the transmitted image Line number The intensity value of the column pixel. It is the weight of that pixel. and The value can be set according to actual needs, and is not limited here. In this embodiment, .

[0071] Furthermore, the number of pixels in the transmitted image can be calculated using the following formula. Line number Column pixels and multiple adjacent coefficients corresponding to multiple directions:

[0072] ;

[0073] ;

[0074] ;

[0075] ;

[0076] in, It is the first Line number Horizontal adjacency coefficient of column pixels, It is the first Line number Vertical adjacency coefficient of column pixels, It is the first Line number Adjacency coefficient of the main diagonal of column pixels. No. Line number The second diagonal adjacency coefficient of column pixels; It is the first Line number The target coefficients of the horizontally adjacent pixels of a column pixel. It is the first Line number The target coefficients of vertically adjacent pixels in a column. It is the first Line number The target coefficients of the pixels adjacent to each other along the main diagonal of the column pixel. It is the first Line number The target coefficients of the pixels adjacent to the column pixel in the second diagonal direction. , , and It can be based on and It is obtained in the same way, and will not be repeated here.

[0077] In step 202b, it is about to , , and The combination is the first Line number The set of adjacent coefficients for column pixels.

[0078] In step 203, after calculating the neighbor coefficient set of each pixel in the transmitted image, the image control parameter value corresponding to the network slice is obtained based on the neighbor coefficient set of all pixels.

[0079] In practical applications, there is no strict timing relationship between steps 201 and 202; that is, they can be executed simultaneously, or either step can be executed first, depending on the actual needs, which is not limited here. Similarly, there is no strict timing relationship between steps 201 and 203; that is, they can be executed simultaneously, or either step can be executed first, depending on the actual needs, which is not limited here.

[0080] This embodiment calculates the target round-trip time of the network slice by taking the normalized average of the round-trip times of all users using the network slice. This allows for a comprehensive evaluation of the transmission timeliness of the network slice based on the timeliness of all users using it, thereby improving the accuracy of the evaluation. Furthermore, normalization ensures that the round-trip times of all users are on the same data scale, thus improving computational efficiency. Simultaneously, the image control parameter values ​​corresponding to the network slice are obtained using the adjacency coefficients of each pixel in multiple directions, including horizontal, vertical, main diagonal, and secondary diagonal. This allows the image control parameter values ​​to evaluate the quality of the transmitted image based on the demeaned normalized coefficients of the intensity values ​​of each pixel and its adjacency pixels in multiple directions, improving the accuracy of the overall quality evaluation of the transmitted image.

[0081] Figure 3 This is the third flowchart illustrating the network slice selection method provided in this application. (Refer to...) Figure 3 In one embodiment, obtaining the image control parameter values ​​corresponding to the network slice based on multiple adjacent coefficient sets may include:

[0082] 301. Based on multiple adjacent coefficient sets, perform parameter fitting to obtain the multi-directional image shape control parameter values ​​and multi-directional image diffusion control parameter values ​​corresponding to the network slices;

[0083] 302. Fuse the shape control parameter values ​​of the multi-directional images to obtain the target shape control parameter values;

[0084] 303. The multi-directional image diffusion control parameter values ​​are fused to obtain the target diffusion control parameter values.

[0085] In step 301, under normal circumstances, these neighboring coefficient sets follow a Gaussian distribution. Therefore, a zero-mean asymmetric generalized Gaussian distribution can be fitted based on these neighboring coefficient sets. Taking the horizontal neighboring coefficients as an example, the fitting equation is as follows:

[0086] (3-1)

[0087] in, , .

[0088] in, It is a zero-mean asymmetric generalized Gaussian distribution function. It is the independent variable of the function. It is the gamma function. The horizontally adjacent coefficients from multiple sets of adjacent coefficients are input into formula (3-1) for fitting, thus obtaining the image's horizontal shape control parameter values. Image left diffusion control parameter values ​​under image horizontal shape control and the image right-side diffusion control parameter values ​​under image horizontal shape control. .

[0089] Similarly, the vertical shape control parameter values ​​of the image can be obtained through fitting. Image left-side diffusion control parameter values ​​under image vertical shape control Image right-side diffusion control parameter values ​​under image vertical shape control Image main diagonal shape control parameter values Image left-side diffusion control parameter value under the control of the image's main diagonal shape Image right-side diffusion control parameter values ​​under image main diagonal shape control Image second diagonal shape control parameter value Image left-side diffusion control parameter value under image second diagonal shape control And the image right-side diffusion control parameter value under the control of the image's second diagonal shape. .

[0090] In step 302, the image horizontal shape control parameter value can be obtained using the following formula. Image vertical shape control parameter values Image main diagonal shape control parameter values and the image second diagonal shape control parameter value By merging, we obtain Target shape control parameter values ​​at any time :

[0091] ;

[0092] In step 303, the image left diffusion control parameter value under the image horizontal shape control can be obtained using the following formula. Image left-side diffusion control parameter values ​​under image vertical shape control Image left-side diffusion control parameter values ​​under image main diagonal shape control and the image left diffusion control parameter value under the control of the image second diagonal shape. By merging, we obtain Target left diffusion control parameter value at time :

[0093] ;

[0094] Similarly, the following formula can be used to calculate the rightward diffusion control parameter value under the horizontal shape control of the image. Image right-side diffusion control parameter values ​​under image vertical shape control Image right-side diffusion control parameter values ​​under image main diagonal shape control And the image right-side diffusion control parameter value under the control of the image's second diagonal shape. By merging, we obtain Target right-side diffusion control parameter value at time :

[0095] ;

[0096] Furthermore, the target round-trip time can be calculated using the following formula. , Target shape control parameter values ​​at any time , Target left diffusion control parameter value at time and the target right-side diffusion control parameter value at time. By merging the data, the selection parameter values ​​corresponding to the network slices are obtained. :

[0097] ;

[0098] in, Indicates the first Network slice selection auxiliary information Corresponding network slices .

[0099] When the image is transmitted stably in this network slice Relatively stable; when the image exhibits pixelation or screen tearing due to excessive round-trip latency, Get smaller If it becomes smaller, then To become smaller, that is The smaller the value, the worse the network transmission performance of the corresponding network slice. Therefore, it is possible to base the network slice on the network slice's performance. Select the maximum value and determine the target network slice with the best network transmission performance by identifying the corresponding network slice.

[0100] In practical applications, there is no strict timing relationship between steps 302 and 303; that is, they can be executed simultaneously, or either step can be executed first, depending on the actual needs, and no restrictions are imposed here.

[0101] This embodiment obtains multi-directional image shape control parameter values, multi-directional left-side diffusion control parameter values, and multi-directional right-side diffusion control parameter values ​​for network slices by fitting multiple adjacent coefficient sets. Then, the multi-directional image shape control parameter values ​​are fused to obtain the target shape control parameter value. Similarly, the multi-directional left-side diffusion control parameter values ​​are fused to obtain the target left-side diffusion control parameter value, and the multi-directional right-side diffusion control parameter values ​​are fused to obtain the target right-side diffusion control parameter value. Finally, these control parameter values ​​are fused with the target round-trip delay to obtain the selection parameter value. This selection parameter value incorporates the network slice's delay information, as well as the network slice's shape control information and diffusion control information for the transmitted image. Based on accurate network timeliness assessment and transmitted image quality assessment, it can select the network slice with the best network transmission performance.

[0102] The network slice selection device provided in the embodiments of this application is described below. The network slice selection device described below can be referred to in correspondence with the network slice selection method described above.

[0103] Figure 4 This is a schematic diagram of the internal and external interaction process of the network slice selection device provided in this application embodiment. (Refer to...) Figure 4 This application provides a network slice selection device, which may include:

[0104] The parameter value calculation module is used to: calculate the selection parameter values ​​corresponding to multiple network slices respectively, and obtain multiple selection parameter values;

[0105] The network slice selection module is used to: determine the maximum selection parameter value from the plurality of selection parameter values, and determine the network slice corresponding to the maximum selection parameter value as the target network slice;

[0106] The selection parameter value corresponding to any network slice is determined based on the target round-trip time and the image control parameter value corresponding to any network slice.

[0107] The network slice selection device provided in this embodiment calculates selection parameter values ​​corresponding to multiple network slices to obtain multiple selection parameter values, determines the maximum selection parameter value from the multiple selection parameter values, and determines the network slice corresponding to the maximum selection parameter value as the target network slice. The selection parameter value corresponding to any network slice is determined based on the target round-trip time of the network slice and the image control parameter value of the network slice. On the one hand, this embodiment employs a fully automated machine process, eliminating the need for manual estimation or testing, thereby effectively improving selection efficiency and accuracy. On the other hand, this embodiment determines the selection parameter value of the network slice based on the target round-trip time and image control parameter value corresponding to the network slice. The target round-trip time can accurately measure the network transmission timeliness of the network slice, and the image control parameter value can accurately measure the impact of the network slice on the image quality during image transmission. Therefore, obtaining the selection parameter value based on the target round-trip time and image control parameter value is to obtain the selection weight of the network slice from both the aspects of network transmission timeliness and network transmission image quality. This selection weight can fully represent the network transmission performance of the corresponding network slice. By selecting the network slice corresponding to the maximum selection weight, the target network slice with the best network transmission performance can be selected. Furthermore, since the selection is made from actual network slices, there will be no mismatch with actual usage requirements, further improving selection accuracy. In summary, this embodiment uses an automated machine process to obtain selection parameter values ​​based on the target round-trip latency and image control parameter values ​​corresponding to the actual network slice. By determining the target network slice using these selection parameter values, it is possible to efficiently and accurately select the network slice with the best network transmission performance that matches the actual usage requirements.

[0108] In one embodiment, the parameter value calculation module includes:

[0109] The latency calculation module is used to: calculate the normalized average of the round-trip latency of all users in the network slice at the target time, and obtain the target round-trip latency corresponding to the network slice;

[0110] The adjacent coefficient calculation module is used to: calculate the adjacent coefficient set of multiple pixels in the transmitted image of the network slice at the target time, and obtain multiple adjacent coefficient sets corresponding to the network slice;

[0111] The fitting calculation module is used to: obtain the image control parameter values ​​corresponding to the network slice based on the multiple adjacent coefficient sets;

[0112] The algorithm fusion module is used to fuse the target round-trip time delay and the image control parameter value to obtain the selection parameter value corresponding to the network slice.

[0113] In one embodiment, the adjacency coefficient calculation module is specifically used for:

[0114] Based on the target coefficient of the pixel and the target coefficients of the pixels adjacent to the pixel in multiple directions, multiple adjacent coefficients corresponding to the pixel in multiple directions are obtained.

[0115] Based on the multiple neighbor coefficients, the neighbor coefficient set of the pixel is obtained.

[0116] In one embodiment, the adjacency coefficient calculation module is specifically used for:

[0117] Calculate the average pixel intensity and standard deviation of the pixel intensity of the transmitted image;

[0118] Based on the average pixel intensity and the standard deviation of pixel intensity, the mean-free normalization coefficient of the pixel intensity value is calculated to obtain the target coefficient of the pixel.

[0119] In one embodiment, the fitting calculation module is specifically used for:

[0120] Based on the multiple adjacent coefficient sets, parameter fitting is performed to obtain the multi-directional image shape control parameter value and multi-directional image diffusion control parameter value corresponding to the network slice;

[0121] The multi-directional image shape control parameter values ​​are fused to obtain the target shape control parameter values;

[0122] The multi-directional image diffusion control parameter values ​​are fused to obtain the target diffusion control parameter values.

[0123] In one embodiment, the algorithm fusion module is specifically used for:

[0124] The target round-trip time delay, the target shape control parameters, and the target diffusion control parameters are fused to obtain the selection parameter values ​​corresponding to the network slice.

[0125] Reference Figure 4 The network slice selection device also includes a network slice information collection module, an orchestration module, and a display module. This device can be installed in a low-latency slice selection platform based on a 5G network, interacting with external devices via a transceiver gateway within the platform to select network slices. Applying this device to a remote operation scenario of a surgical robot, and using the proximal surgical display system in the surgical robot control area, which receives the image of the surgical robot's operating area after network slice transmission, as the transmitted image, the specific network slice selection process is described below:

[0126] 1. The network slice information collection module sends an instruction to the transceiver gateway to collect all network slice information;

[0127] 2. The transceiver gateway forwards the instruction to the Communication Service Management Function (CSMF);

[0128] 3. CSMF queries the network slice management function NSMF for information on all currently configured network slices, and NSMF returns the queried information to CSMF;

[0129] 4. CSMF will return the full network slice information obtained from NSMF to the transceiver gateway;

[0130] 5. The transceiver gateway returns all network slice information to the network slice information collection module;

[0131] 6. The network slice information collection module feeds back all network slice information to the orchestration module. The orchestration module selects auxiliary information NSSAI from the collected n network slices, sorts and assigns values, and generates a slice orchestration list.

[0132] 7. The arrangement module, based on the arrangement list... The sorting module sends auxiliary information for selecting the nth network slice. Corresponding network slices Configuration;

[0133] 8. The network slice information collection module sends this configuration to the transceiver gateway;

[0134] 9. The transceiver gateway sends this configuration to CSMF;

[0135] 10. CSMF sends this configuration to NSMF;

[0136] 11. The NSMF will distribute this configuration to the NSMF (Network Subslice Management Function) of the transmission network, the NSMF of the core network, and the NSMF of the wireless network.

[0137] 12. The NSSMF of the transmission network distributes the configuration to the SPN (Slice Packet Network) equipment, the NSSMF of the core network distributes the configuration to the AMF (Access and Mobility Management Function) equipment, the SMF (Session Management Function) equipment, and the UPF (User Plane Function) equipment, and the NSSMF of the radio network distributes the configuration to the 5G base station equipment.

[0138] 13. The latency calculation module sends a full user latency information query command to the transceiver gateway;

[0139] 14. The transceiver gateway sends this instruction to the signaling analysis system;

[0140] 15. The signaling analysis system sends this instruction to the signaling aggregation gateway;

[0141] 16. The signaling aggregation gateway collects full user latency information from the AMF device, SMF device, and UPF device respectively;

[0142] 17. The AMF, SMF, and UPF devices will feed back all collected user latency information to the signaling aggregation gateway;

[0143] 18. The signaling aggregation gateway feeds back all collected user latency information to the signaling analysis system;

[0144] 19. The signaling analysis system will collect all user latency information and feed it back to the transceiver gateway;

[0145] 20. The transceiver gateway feeds back the collected latency information of all users to the latency calculation module, which then calculates the network slice based on the latency information of all users. The corresponding target round-trip time;

[0146] 21. The adjacent coefficient calculation module sends the remote-operated surgical robot operation instructions to the transceiver gateway;

[0147] 22. The transceiver gateway forwards the instruction to the surgical robot control console;

[0148] 23. The adjacency coefficient calculation module sends an image collection command from the proximal surgical display system to the transceiver gateway;

[0149] 24. The transceiver gateway sends this instruction to the proximal surgical display system;

[0150] 25. The proximal surgical display system returns image information of the proximal surgical display system within the statistical period to the transceiver gateway;

[0151] 26. The transceiver gateway returns the image information to the adjacency coefficient calculation module, which then calculates the network slice based on the image information. This corresponds to multiple sets of adjacent coefficients. After long-distance transmission via user data protocols, images may exhibit pixelation, distortion, or other issues due to packet loss. This can be understood as image degradation, which causes changes in the data within the adjacent coefficient sets before and after image transmission.

[0152] 27. The adjacent coefficient calculation module pushes multiple adjacent coefficient sets within the statistical period to the fitting calculation module. The fitting calculation module performs zero-mean asymmetric generalized Gaussian fitting based on the multiple adjacent coefficient sets to obtain network slices. The corresponding image control parameter values;

[0153] 28. The fitting calculation module sends the image control parameter values ​​to the algorithm fusion module;

[0154] 29. The algorithm fusion module sends a request to the delay calculation module to obtain the target round-trip delay obtained in step 20;

[0155] 30. The delay calculation module feeds back the target round-trip time to the algorithm fusion module. The algorithm fusion module fuses the target round-trip time and the image control parameter values ​​to obtain a network slice. The corresponding selection parameter value;

[0156] 31. The algorithm fusion module sends the selected parameter value to the orchestration module for sorting;

[0157] 32. The orchestration module slices the network. The number and selected parameter value are sent to the display module for display;

[0158] 33. The display module sends an instruction to the network slice information collection module to collect and calculate the data for the next network slice. Repeat steps 1 to 32 until the selection parameter values ​​of all network slices are obtained. Sort all selection parameter values ​​and the one with the highest value is the target network slice of the teleoperated surgical robot. This target network slice has the best network transmission performance.

[0159] Figure 5 This is one of the structural schematic diagrams of the network slice selection system provided in the embodiments of this application;

[0160] Figure 6 This is the second schematic diagram of the network slice selection system provided in the embodiments of this application.

[0161] Reference Figure 5 In the remote operation scenario of surgical robots, the system includes a network slice selection platform based on a 5G network, a 5G mobile communication network system, a master-slave architecture surgical robot control area, and a master-slave mechanism surgical robot operation area.

[0162] The 5G network system includes wireless network equipment, core network equipment, transmission network equipment, signaling analysis system, signaling aggregation gateway, CSMF, NSMF, transmission network NSSMF, core network NSSMF, and wireless network NSSMF; the surgical robot control area includes a surgical robot console and a proximal surgical display system; the surgical robot operation area includes a surgical robot operating table and a remote surgical display system.

[0163] The main functions of each part of the system are described below:

[0164] 1. Network Slice Selection Platform: Collects user-level latency information from the signaling analysis system and post-transmission image information from the near-end surgical display system through the transceiver gateway. Calculates the target round-trip latency corresponding to the network slice based on the collected user latency information. Calculates the image control parameter value corresponding to the network slice based on the collected post-transmission image information. Obtain the selection parameter value corresponding to the network slice based on the target round-trip latency and the image control parameter value. Select the target network slice based on the selection parameter value and send the configuration of the target network slice to CSMF through the transceiver gateway.

[0165] 2. 5G Network System: The transmission network equipment provides the physical connection between the 5G network and the surgical robot control area; the core network equipment provides a protocol data unit session path for messages between the surgical robot control area and the operating area, and provides policy control for this path; the radio network equipment provides a radio access environment for the surgical robot operating area; the transmission network NSSMF, radio network NSSMF, core network NSSMF, NSMF, and CSMF provide a network slice distribution path for the network slice selection platform; the signaling aggregation gateway and signaling analysis system collect user latency data for calculation by the network slice selection platform.

[0166] 3. Surgical robot control area and surgical robot operation area: The two areas are connected via a 5G network system. The control area provides the surgeon with a remote control and a surgical image field of view, while the operation area provides the end effector and local surgical image acquisition and local display.

[0167] The main functions of each interface in this system are described below:

[0168] 1. n1 interface: The interface between the surgical robot console and the proximal surgical display system. It is used to acquire surgical image information in the control area, send end effector control commands and surgical image information in the control area to the operating area, and receive surgical image information in the operating area sent by the operating area.

[0169] 2. n2 interface: The interface between the surgical robot operating table and the remote surgical display system, used to acquire surgical image information in the operating area, send surgical image information in the operating area to the control area, and receive and execute end effector control commands sent by the control area;

[0170] 3. Interface A: The interface between the network slicing selection platform and the surgical robot control console, used to collect control command information issued by the surgical robot control console;

[0171] 4. Interface B: The interface between the network slice selection platform and the proximal surgical display system, used to collect surgical image information acquired in the control area;

[0172] 5. C Interface: The interface between the network slice selection platform and CSMF, used to collect executable network slice information from the 5G network system and issue network slice information to be executed;

[0173] 6. D Interface: The interface between the network slicing selection platform and the signaling analysis system, used to collect user latency information within the 5G network system;

[0174] 7. N9 Interface: The interface between the control area and the transmission network equipment, used to transmit control information and image information between the control area and the operation area;

[0175] 8. G interface: The interface between CSMF and NSMF, providing wireless access capability for the surgical robot;

[0176] 9. Uu Interface: The interface between the operating area and the wireless network device, providing wireless access capability for the surgical robot;

[0177] 10. E1 Interface: The interface between NSMF and NSMMF of the transport network, used by NSMF to issue configuration instructions for a network slice to the transport network;

[0178] 11. E2 interface: The interface between NSMF and NSMMF in the core network, used by NSMF to issue configuration instructions for a network slice to the core network;

[0179] 12. E3 interface: The interface between NSMF and NSMMF of the wireless network, used by NSMF to issue configuration commands for a certain network slice to the wireless network;

[0180] 13. E4 Interface: The interface between the signaling analysis system and the signaling aggregation gateway, used by the signaling aggregation gateway to report the collected user latency information to the signaling analysis system;

[0181] 14. F1 Interface: The interface between the NSSMF and the transmission network equipment, used by the NSSMF to issue network slice configuration commands to the transmission network equipment;

[0182] 15. F2 Interface: The interface between the core network NSMF and the core network equipment, used by the core network NSMF to issue network slice configuration commands to the core network equipment;

[0183] 16. F3 Interface: The interface between the NSSMF and the wireless network device, used by the NSSMF to send network slicing configuration commands to the wireless network device;

[0184] 17. F4 Interface: The interface between the core network equipment and the signaling aggregation gateway, used by the core network equipment to provide user round-trip delay information to the signaling aggregation gateway.

[0185] Reference Figure 6Considering the wide applicability of the system, the network slicing selection platform can be deployed on a cloud-based x86 virtual machine based on Ubuntu 16.04.1LTS Enial Xerus, using an all-IP bearer approach. By pre-configuring relevant data, the IP network between the network slicing selection platform and the 5G network system (including the 5G core network and 5G transmission network), the surgical robot control area, and the surgical robot operating area is established. In addition to SMF, UPF, AMF, signaling aggregation gateway, and core network NSSMF, this 5G core network also includes Unified Data Management (UDM) and Policy Control (PCF).

[0186] In this system, interfaces A, B, C, and D are carried on a private IP network and isolated using different VPN technologies. The system also reuses existing network interfaces N2, N3, N4, N6, N7, N8, N10, N11, E1, E2, E3, E4, F1, F2, F3, and F4.

[0187] Figure 7 is a schematic diagram of the structure of the electronic device provided in an embodiment of this application, as shown below. Figure 7 As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730, and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 communicate with each other via the communication bus 740. The processor 710 can call a computer program in the memory 730 to execute steps of the network slice selection method, such as:

[0188] Calculate the selection parameter values ​​for each of the multiple network slices to obtain multiple selection parameter values;

[0189] The maximum selection parameter value is determined from the plurality of selection parameter values, and the network slice corresponding to the maximum selection parameter value is determined as the target network slice.

[0190] The selection parameter value corresponding to any network slice is determined based on the target round-trip time and the image control parameter value corresponding to any network slice.

[0191] Furthermore, the logical instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0192] On the other hand, embodiments of this application also provide a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the steps of the network slice selection method provided in the above embodiments, such as including:

[0193] Calculate the selection parameter values ​​for each of the multiple network slices to obtain multiple selection parameter values;

[0194] The maximum selection parameter value is determined from the plurality of selection parameter values, and the network slice corresponding to the maximum selection parameter value is determined as the target network slice.

[0195] The selection parameter value corresponding to any network slice is determined based on the target round-trip time and the image control parameter value corresponding to any network slice.

[0196] On the other hand, embodiments of this application also provide a non-transitory computer-readable storage medium storing a computer program thereon, the computer program being used to cause a processor to execute the steps of the network slice selection method provided in the above embodiments, for example including:

[0197] Calculate the selection parameter values ​​for each of the multiple network slices to obtain multiple selection parameter values;

[0198] The maximum selection parameter value is determined from the plurality of selection parameter values, and the network slice corresponding to the maximum selection parameter value is determined as the target network slice.

[0199] The selection parameter value corresponding to any network slice is determined based on the target round-trip time and the image control parameter value corresponding to any network slice.

[0200] The non-transitory computer-readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic memory (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO)), optical memory (e.g., CD, DVD, BD, HVD), and semiconductor memory (e.g., ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)).

[0201] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0202] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0203] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for selecting network slices, characterized in that, include: Calculate the selection parameter values ​​for each of the multiple network slices to obtain multiple selection parameter values; The maximum selection parameter value is determined from the plurality of selection parameter values, and the network slice corresponding to the maximum selection parameter value is determined as the target network slice. The selection parameter value corresponding to any network slice is determined based on the target round-trip time and the image control parameter value corresponding to any network slice, including: Calculate the normalized average of the round-trip latency of all users in the network slice at the target time to obtain the target round-trip latency corresponding to the network slice; Calculate the neighboring coefficient set of multiple pixels in the transmitted image of the network slice at the target time to obtain the multiple neighboring coefficient sets corresponding to the network slice; Based on the multiple adjacent coefficient sets, the image control parameter values ​​corresponding to the network slice are obtained; The target round-trip time and the image control parameter value are fused to obtain the selection parameter value corresponding to the network slice.

2. The network slice selection method according to claim 1, characterized in that, The set of neighboring coefficients for any pixel is determined based on the following method: Based on the target coefficient of the pixel and the target coefficients of the pixels adjacent to the pixel in multiple directions, multiple adjacent coefficients corresponding to the pixel in multiple directions are obtained. Based on the multiple neighbor coefficients, the neighbor coefficient set of the pixel is obtained.

3. The network slice selection method according to claim 2, characterized in that, The target coefficient for any pixel is determined based on the following method: Calculate the average pixel intensity and standard deviation of the pixel intensity of the transmitted image; Based on the average pixel intensity and the standard deviation of pixel intensity, the mean-free normalization coefficient of the pixel intensity value is calculated to obtain the target coefficient of the pixel.

4. The network slice selection method according to claim 2, characterized in that, The process of obtaining the image control parameter values ​​corresponding to the network slice based on the multiple adjacent coefficient sets includes: Based on the multiple adjacent coefficient sets, parameter fitting is performed to obtain the multi-directional image shape control parameter value and multi-directional image diffusion control parameter value corresponding to the network slice; The multi-directional image shape control parameter values ​​are fused to obtain the target shape control parameter values; The multi-directional image diffusion control parameter values ​​are fused to obtain the target diffusion control parameter values.

5. The network slice selection method according to claim 4, characterized in that, The step of fusing the target round-trip time and the image control parameter value to obtain the selection parameter value corresponding to the network slice includes: The target round-trip time delay, the target shape control parameters, and the target diffusion control parameters are fused to obtain the selection parameter values ​​corresponding to the network slice.

6. A network slicing selection device, characterized in that, For performing the network slice selection method of claim 1, comprising: The parameter value calculation module is used to: calculate the selection parameter values ​​corresponding to multiple network slices respectively, and obtain multiple selection parameter values; The network slice selection module is used to: determine the maximum selection parameter value from the plurality of selection parameter values, and determine the network slice corresponding to the maximum selection parameter value as the target network slice; The selection parameter value corresponding to any network slice is determined based on the target round-trip time and the image control parameter value corresponding to any network slice.

7. An electronic device comprising a processor and a memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the network slice selection method according to any one of claims 1 to 5.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the network slice selection method according to any one of claims 1 to 5.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the network slice selection method according to any one of claims 1 to 5.

Images