User plane function equipment selection method and device

Abstract

The invention relates to the technical field of equipment selection, and provides a user plane function equipment selection method and device. The method comprises the following steps: respectively calculating video similarities of video pairs corresponding to a plurality of user plane function devices to obtain a plurality of video similarities corresponding to the plurality of user plane function devices; wherein the video pair corresponding to any user plane function equipment comprises a video before routing and a video after routing of the user plane function equipment based on the same video; and determining the maximum video similarity from the plurality of video similarities, and determining the user plane function equipment corresponding to the maximum video similarity as target user plane function equipment. According to the user plane function equipment selection method and device provided by the invention, the influence of different routing paths on the video transmission quality is fully considered, and the quality of far-end and near-end videos routed by the user plane function equipment can reach the optimal level.

Description

Technical Field

[0001] The present application relates to the technical field of equipment selection, and in particular to a method and apparatus for selecting user plane functional equipment. Background Art

[0002] Teleoperation, also known as remote operation, is a technology that allows an operator to control a device or robot from a location far away. This technology has applications in many fields, including but not limited to medicine, extreme environment exploration (such as deep sea and space), anti-terrorism and explosion prevention, and industrial automation production.

[0003] During the remote operation process, the operator in the remote control area needs to operate and control the proximal device or robot based on the real-time video of the proximal operation area. The learner in the proximal operation area also needs to learn the operation techniques of the remote operator based on the real-time video of the remote control area. The videos of the proximal operation area and the remote control area are routed to the other end based on the user plane functional devices in the network. Selecting different user plane functional devices means selecting different routing paths.

[0004] Since different routing paths may have different transmission distances, transmission bandwidths, transmission packet loss rates, transmission delays, transmission jitters, etc., the network quality of different routing paths will be different, which will in turn lead to different video transmission quality of different routing paths. However, the traditional user plane functional device selection method does not consider the impact of different routing paths on video transmission quality, which can easily cause the far-end and near-end video quality after routing through the user plane functional device to deviate from the optimal level. Summary of the invention

[0005] The embodiments of the present application provide a method and apparatus for selecting a user plane functional device, which are used to solve the technical problem that the traditional method for selecting a user plane functional device does not consider the impact of different routing paths on the quality of video transmission, which easily causes the quality of near- and far-end videos after routing through the user plane functional device to deviate from the optimal level.

[0006] In a first aspect, an embodiment of the present application provides a method for selecting a user plane function device, including: Calculate the video similarities of the video pairs corresponding to the multiple user plane functional devices respectively, and obtain the multiple video similarities corresponding to the multiple user plane functional devices; wherein the video pair corresponding to any user plane functional device includes the pre-routing video and the post-routing video of the user plane functional device based on the same video; A maximum video similarity is determined from the multiple video similarities, and a user plane functional device corresponding to the maximum video similarity is determined as a target user plane functional device.

[0007] In one embodiment, the video similarity of a video pair corresponding to any user plane functional device is determined based on the following method: Calculating image similarities between a plurality of video frames at the same time in a pre-routing video and a post-routing video of the user plane functional device to obtain a plurality of image similarities corresponding to the user plane functional device; The multiple image similarities are merged to obtain the video similarity of the video pair corresponding to the user plane functional device.

[0008] In one embodiment, the image similarity between any video frames at the same time is determined based on the following method: Calculating the brightness similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing; Calculating the contrast similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing; Calculating the structural similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing; The brightness similarity, the contrast similarity and the structure similarity are fused to obtain the image similarity between the video frames at the target moment.

[0009] In one embodiment, calculating the brightness similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing includes: Calculate the grayscale average of the video frame at the target time in the video before routing and the grayscale average of the video frame at the target time in the video after routing respectively, to obtain the grayscale average before routing and the grayscale average after routing; Based on the grayscale average value before routing and the grayscale average value after routing, the brightness similarity between the video frames at the target moment is obtained.

[0010] In one embodiment, calculating the contrast similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing includes: Calculate the grayscale standard deviation of the video frame at the target time in the video before routing and the grayscale standard deviation of the video frame at the target time in the video after routing respectively, and obtain the grayscale standard deviation before routing and the grayscale standard deviation after routing; Based on the grayscale standard deviation before routing and the grayscale standard deviation after routing, the contrast similarity between the video frames at the target moment is obtained.

[0011] In one embodiment, calculating the structural similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing includes: Calculate the target grayscale value of the video frame at the target time in the video before routing and the target grayscale value of the video frame at the target time in the video after routing respectively, and obtain the target grayscale value before routing and the target grayscale value after routing; the target grayscale value includes the grayscale mean value and the grayscale standard deviation; Based on the target grayscale value before routing and the target grayscale value after routing, the structural similarity between the video frames at the target time is obtained.

[0012] In a second aspect, an embodiment of the present application provides a user plane function device selection device, including: The video similarity calculation module is used to respectively calculate the video similarities of the video pairs corresponding to the multiple user plane functional devices to obtain the multiple video similarities corresponding to the multiple user plane functional devices; wherein the video pair corresponding to any user plane functional device includes the pre-routing video and the post-routing video of the user plane functional device based on the same video; The instruction arrangement module is used to: determine a maximum video similarity from the multiple video similarities, and determine a user plane function device corresponding to the maximum video similarity as a target user plane function device.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory storing a computer program, wherein when the processor executes the program, the steps of the user plane function device selection method described in the first aspect are implemented.

[0014] In a fourth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the user plane function device selection method described in the first aspect.

[0015] In a fifth aspect, an embodiment of the present application provides a non-transitory computer-readable storage medium, including a computer program, which, when executed by a processor, implements the steps of the user plane function device selection method described in the first aspect.

[0016] The user plane function device selection method and device provided by the present application respectively calculate the video similarity of the video pairs corresponding to the multiple user plane function devices, obtain the multiple video similarities corresponding to the multiple user plane function devices, determine the maximum video similarity from the multiple video similarities, and determine the user plane function device corresponding to the maximum video similarity as the target user plane function device. Since the video pair corresponding to any user plane function device includes the video before routing and the video after routing based on the same video of the user plane function device, therefore, whether for the far-end video or the near-end video, the video similarity before and after routing through the user plane function device can be calculated. The higher the video similarity, the higher the video transmission quality of the routing path corresponding to the user plane function device, and the video transmission quality is the video transmission quality under the comprehensive influence of multiple network factors such as the transmission distance, transmission bandwidth, transmission packet loss rate, transmission delay, and transmission jitter corresponding to the routing path. Therefore, the highest video similarity is determined from the video similarities before and after routing of multiple user plane function devices, and the user plane function device corresponding to the highest video similarity is the target user plane function device that can provide the optimal routing path under the influence of multiple network factors. In summary, the present application fully considers the impact of different routing paths on video transmission quality, and can achieve the optimal level of far-end and near-end video quality after routing through the user plane functional device. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is one of the flow charts of the method for selecting a user plane function device provided in an embodiment of the present application; Figure 2 This is the second flow chart of the method for selecting a user plane function device provided in an embodiment of the present application; Figure 3 This is a third flow chart of the method for selecting a user plane function device provided in an embodiment of the present application; Figure 4 This is a schematic diagram of the internal and external interaction process of the user plane function device selection device provided in an embodiment of the present application; Figure 5 This is one of the structural diagrams of the user plane function device selection system provided in an embodiment of the present application; Figure 6 This is the second structural diagram of the user plane function device selection system provided in the embodiment of the present application; Figure 7It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] Figure 1 This is one of the flow charts of the method for selecting a user plane function device provided in the embodiment of the present application. Figure 1 , the embodiment of the present application provides a method for selecting a user plane function device, which may include: 101. Calculate video similarities of video pairs corresponding to multiple user plane functional devices respectively to obtain multiple video similarities corresponding to the multiple user plane functional devices; The video pair corresponding to any user plane functional device includes a pre-routing video and a post-routing video of the user plane functional device based on the same video; 102. Determine a maximum video similarity from multiple video similarities, and determine a user plane functional device corresponding to the maximum video similarity as a target user plane functional device.

[0021] In step 101, assuming there are three user plane functional devices A, B, and C, the video similarity between video a and video a' routed through user plane functional device A is calculated. , obtain the video similarity corresponding to the user plane functional device A; calculate the video similarity between video b and video b' after routing through the user plane functional device B , get the video similarity corresponding to the user plane functional device B; calculate the video similarity between video c and video c' after routing through the user plane functional device C, and get the video similarity corresponding to the user plane functional device C .

[0022] Among them, video a, video b and video c can be the same video or different videos, which is not limited here.

[0023] In step 102, from , and A maximum value is determined, and a user plane functional device corresponding to the maximum value is determined as a target user plane functional device.

[0024] The user plane function device selection method provided in this embodiment calculates the video similarities of the video pairs corresponding to the multiple user plane function devices respectively, obtains the multiple video similarities corresponding to the multiple user plane function devices, determines the maximum video similarity from the multiple video similarities, and determines the user plane function device corresponding to the maximum video similarity as the target user plane function device. Since the video pair corresponding to any user plane function device includes the video before routing and the video after routing based on the same video of the user plane function device, therefore, whether for the far-end video or the near-end video, the video similarity before and after routing through the user plane function device can be calculated. The higher the video similarity, the higher the video transmission quality of the routing path corresponding to the user plane function device, and the video transmission quality is the video transmission quality under the comprehensive influence of multiple network factors such as the transmission distance, transmission bandwidth, transmission packet loss rate, transmission delay, and transmission jitter corresponding to the routing path. Therefore, the highest video similarity is determined from the video similarities before and after routing of the multiple user plane function devices, and the user plane function device corresponding to the highest video similarity is the target user plane function device that can provide the optimal routing path under the influence of multiple network factors. In summary, this embodiment fully considers the influence of different routing paths on the video transmission quality, and can make the far-end and near-end video quality reach the optimal level after routing through the user plane functional device.

[0025] Figure 2 This is the second flow chart of the method for selecting a user plane functional device provided in the embodiment of the present application. Figure 2 In one embodiment, the video similarity of a video pair corresponding to any user plane functional device may be determined based on the following method: 201. Calculate image similarities between multiple video frames at the same time in the pre-routing video and the post-routing video of the user plane functional device to obtain multiple image similarities corresponding to the user plane functional device; 202. Fuse multiple image similarities to obtain video similarity of the video pair corresponding to the user plane functional device.

[0026] In step 201, assuming that there are video frames at N moments in both the pre-routing video a and the post-routing video a' of the user plane functional device A, the image similarity between the video frame at the first moment in the pre-routing video a and the video frame at the first moment in the post-routing video a' is calculated to obtain the first image similarity; the image similarity between the video frame at the second moment in the pre-routing video a and the video frame at the second moment in the post-routing video a' is calculated to obtain the second image similarity; and so on, until the image similarity between the video frame at the Nth moment in the pre-routing video a and the video frame at the Nth moment in the post-routing video a' is calculated to obtain the Nth image similarity, thereby obtaining N image similarities corresponding to the user plane functional device A.

[0027] In step 202, the N image similarities may be multiplied to obtain the video similarity of the video pair corresponding to the user plane functional device A.

[0028] For any user plane functional device, this embodiment calculates the image similarity between the video frames at the same time in the video before and after routing, obtains the similarity of the video before and after routing at the video frame level, and then merges all the similarities at the video frame level to obtain the similarity at the video level. The similarity at the video level merges all the similarity details at the video frame level, and is therefore more comprehensive and accurate.

[0029] Figure 3 This is the third flow chart of the method for selecting a user plane functional device provided in the embodiment of the present application. Figure 3 In one embodiment, the image similarity between any video frames at the same time can be determined based on the following method: 301. Calculate the brightness similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing; 302. Calculate the contrast similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing; 303. Calculate the structural similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing; 304. The brightness similarity, the contrast similarity and the structure similarity are integrated to obtain the image similarity between the video frames at the target moment.

[0030] In step 301, the brightness of the video frame is a description of the grayscale value of the video frame pixels. For any pixel, the larger the grayscale value, the closer the pixel is to white, that is, the greater the brightness of the pixel. For a video frame at any moment, the larger the average value of the grayscale values ​​of all pixels, the closer the video frame is to white, that is, the greater the brightness of the video frame. Therefore, the brightness similarity can be specifically calculated as follows: 301a, respectively calculating the grayscale average of the video frame at the target time in the video before routing and the grayscale average of the video frame at the target time in the video after routing, to obtain the grayscale average before routing and the grayscale average after routing; 301b. Based on the grayscale average before routing and the grayscale average after routing, the brightness similarity between the video frames at the target time is obtained.

[0031] In step 301a, the video before routing The video frame at the moment is digitally discretized OK Column gray value matrix , and the video after routing The video frame at the moment is digitally discretized OK Column gray value matrix They can be expressed as follows: ; ; Among them, the video before routing The video frame at the moment and the video after routing The video frames at each moment include pixels, so and Included The gray value of a pixel.

[0032] Then route the previous video The average grayscale value of the video frame before routing at time for: ; in, for The Line Grayscale value of the column.

[0033] Similarly, after routing, the video The average grayscale value of the video frame after routing at time for: ; in, for The Line Grayscale value of the column.

[0034] In step 301b, the video number before routing can be calculated based on the following formula: The video frame at the moment and the video after routing The brightness similarity between video frames at the same time : ; (3-1)

[0035] in, is a constant, and its function is to prevent the denominator from being 0 in the above formula. The constant can be set according to actual needs and is not limited here. In this embodiment, Set to 0.01. From the above formula, we can see that when hour, .

[0036] In step 302, the contrast of the video frame is a description of the distribution of the pixel grayscale values ​​of the video frame in the entire dynamic range. The wider the distribution of the pixel grayscale values ​​of the video frame at any moment in the dynamic range, the greater the contrast of the video frame, that is, for the video frame at any moment, the greater the standard deviation of the grayscale values ​​of all pixels, the greater the contrast of the video frame. Therefore, the contrast similarity can be specifically calculated as follows: 302a, respectively calculating the grayscale standard deviation of the video frame at the target time in the video before routing and the grayscale standard deviation of the video frame at the target time in the video after routing, to obtain the grayscale standard deviation before routing and the grayscale standard deviation after routing; 302b. Based on the grayscale standard deviation before routing and the grayscale standard deviation after routing, the contrast similarity between the video frames at the target time is obtained.

[0037] In step 302a, the video before routing The grayscale standard deviation of the video frame before routing at time , and the video after routing The standard deviation of the grayscale of the video frame after routing at time They can be expressed as follows: ; ; In step 302b, the video number before routing can be calculated based on the following formula: The video frame at the moment and the video after routing Contrast similarity between video frames at time : ; (3-2)

[0038] in, is a constant, and its function is to prevent the denominator from being 0 in the above formula. The constant can be set according to actual needs and is not limited here. In this embodiment, Set to 0.03. From the above formula, we can see that when hour, .

[0039] In step 303, the structure of the video frame is a description of the relative position and proportional relationship between the pixels of the video frame, which can be regarded as the direction of the video frame in the vector space. The structural similarity can be specifically calculated as follows: 303a, respectively calculating the target grayscale value of the video frame at the target time in the video before routing and the target grayscale value of the video frame at the target time in the video after routing, to obtain the target grayscale value before routing and the target grayscale value after routing; The target grayscale value includes the grayscale mean value and grayscale standard deviation; 303b. Based on the target grayscale value before routing and the target grayscale value after routing, the structural similarity between the video frames at the target time is obtained.

[0040] In step 303a, the first The target grayscale value of the video frame before routing at time is and , the video after routing The target grayscale value of the video frame after routing at time is and .

[0041] In step 303b, the first video before routing can be calculated based on the following formula: The video frame at the moment and the video after routing The similarity to be processed between video frames at time :

[0042] ; (3-3)

[0043] in, This is the video before and after routing The vector modulus of the video frame at time, yes The standardized gray value matrix, yes Normalized gray value matrix.

[0044] because and The covariance of for: ; (3-4)

[0045] Substituting formula (3-4) into formula (3-3) yields: ; (3-5)

[0046] Process formula (3-5) to get the video before routing The video frame at the moment and the video after routing The structural similarity between video frames at the moment : ; (3-6)

[0047] in, is a constant, and its function is to prevent the denominator from being 0 in the above formula. The constant can be set according to actual needs and is not limited here. In this embodiment, Set to From the above formula, we can see that when hour, .

[0048] In step 304, the following formula can be used to calculate , and Fusion is performed to obtain the video before routing. The video frame at the moment and the video after routing Image similarity between video frames at time : ; (3-7)

[0049] Substitute formulas (3-1), (3-2) and (3-6) into formula (3-7), and When you get: ; in, The value range is , When , it means the video before and after routing The video frames at the same time have no similarity at all. When , it means the video before and after routing The video frames at each moment are exactly the same. In practical applications, due to the problem of retransmission and packet loss of data packets after long-distance transmission, The possibility is very low.

[0050] Based on the above method, the image similarity between the video frames at the same time before and after routing is calculated. Assuming that there are N video frames at each time in the video before and after routing, N image similarities based on the video frames at these N times can be obtained between the video before routing and the video after routing. These N image similarities are fused according to the following formula to obtain the video similarity corresponding to the user plane functional device providing routing: ; in, is based on a (DN Access Identifier, Data Network Access Identifier) ​​The video similarity corresponding to the user plane functional device selected, The value range is The higher the value, the better the video transmission quality of the routing path of the corresponding user plane functional device. If the value is 100%, it means that the video before and after routing is exactly the same, and the corresponding user plane functional device is the best.

[0051] The target user plane functional device can be selected according to the following formula: ; in, In many Chinese Envoy The largest , then it can be based on A corresponding user plane functional device is selected, and the user plane functional device is the target user plane functional device.

[0052] It should be noted that, in actual applications, there is no strict timing relationship between step 301, step 302 and step 303; that is, they can be executed simultaneously, or any step can be executed first, depending on actual needs and is not limited here.

[0053] This embodiment calculates the brightness similarity, contrast similarity and structural similarity between the video frames at the same time in the pre-routing video and the post-routing video of the user plane functional device, and can obtain the similarity between each pair of video frames from the three key image features of brightness, contrast and structure, and then fuses the similarities of these three aspects to obtain the similarity of the videos before and after routing based on the video frame level. The similarity at the video frame level fuses the similarity details in brightness, contrast and structure, and is therefore more comprehensive and accurate.

[0054] The user plane function device selection apparatus provided in an embodiment of the present application is described below. The user plane function device selection apparatus described below and the user plane function device selection method described above can refer to each other.

[0055] Figure 4 Schematic diagram of the internal and external interaction flow of the user plane function device selection device provided in the embodiment of the present application. Figure 4 , the embodiment of the present application provides a user plane function device selection device, which may include: The video similarity calculation module is used to respectively calculate the video similarities of the video pairs corresponding to the multiple user plane functional devices to obtain the multiple video similarities corresponding to the multiple user plane functional devices; wherein the video pair corresponding to any user plane functional device includes the pre-routing video and the post-routing video of the user plane functional device based on the same video; The instruction arrangement module is used to: determine a maximum video similarity from the multiple video similarities, and determine a user plane function device corresponding to the maximum video similarity as a target user plane function device.

[0056] The user plane function device selection device provided in this embodiment calculates the video similarity of the video pairs corresponding to the multiple user plane function devices respectively, obtains the multiple video similarities corresponding to the multiple user plane function devices, determines the maximum video similarity from the multiple video similarities, and determines the user plane function device corresponding to the maximum video similarity as the target user plane function device. Since the video pair corresponding to any user plane function device includes the video before routing and the video after routing based on the same video of the user plane function device, therefore, whether for the far-end video or the near-end video, the video similarity before and after routing through the user plane function device can be calculated. The higher the video similarity, the higher the video transmission quality of the routing path corresponding to the user plane function device, and the video transmission quality is the video transmission quality under the comprehensive influence of multiple network factors such as the transmission distance, transmission bandwidth, transmission packet loss rate, transmission delay, and transmission jitter corresponding to the routing path. Therefore, the highest video similarity is determined from the video similarities before and after routing of the multiple user plane function devices, and the user plane function device corresponding to the highest video similarity is the target user plane function device that can provide the optimal routing path under the influence of multiple network factors. In summary, this embodiment fully considers the influence of different routing paths on the video transmission quality, and can make the far-end and near-end video quality reach the optimal level after routing through the user plane functional device.

[0057] In one embodiment, the video similarity calculation module includes: An image similarity calculation module is used to calculate the image similarity between multiple video frames at the same time in the pre-routing video and the post-routing video of the user plane functional device to obtain multiple image similarities corresponding to the user plane functional device; The image similarity fusion module is used to: fuse the multiple image similarities to obtain the video similarity of the video pair corresponding to the user plane functional device.

[0058] In one embodiment, the image similarity calculation module includes: A brightness comparison module, used to calculate the brightness similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing; A contrast comparison module, used to calculate the contrast similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing; A structure comparison module, used to calculate the structure similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing; The feature similarity fusion module is used to fuse the brightness similarity, the contrast similarity and the structure similarity to obtain the image similarity between the video frames at the target moment.

[0059] In one embodiment, the brightness contrast module is specifically used to: Calculate the grayscale average of the video frame at the target time in the video before routing and the grayscale average of the video frame at the target time in the video after routing respectively, to obtain the grayscale average before routing and the grayscale average after routing; Based on the grayscale average value before routing and the grayscale average value after routing, the brightness similarity between the video frames at the target moment is obtained.

[0060] In one embodiment, the contrast comparison module is specifically used to: Calculate the grayscale standard deviation of the video frame at the target time in the video before routing and the grayscale standard deviation of the video frame at the target time in the video after routing respectively, and obtain the grayscale standard deviation before routing and the grayscale standard deviation after routing; Based on the grayscale standard deviation before routing and the grayscale standard deviation after routing, the contrast similarity between the video frames at the target moment is obtained.

[0061] In one embodiment, the structure comparison module is specifically used to: Calculate the target grayscale value of the video frame at the target time in the video before routing and the target grayscale value of the video frame at the target time in the video after routing respectively, and obtain the target grayscale value before routing and the target grayscale value after routing; the target grayscale value includes the grayscale mean value and the grayscale standard deviation; Based on the target grayscale value before routing and the target grayscale value after routing, the structural similarity between the video frames at the target time is obtained.

[0062] Reference Figure 4 The user plane function device selection device also includes a digital image module and a user plane function UPF device selection instruction module. The UPF device selection device can be set in a UPF device selection platform based on a 5G network, and interacts with devices outside the platform with the data transceiver gateway in the platform to achieve the selection of UPF devices. The device is applied to the remote operation scenario of the surgical robot, and the near-end video before and after routing is taken as an example to explain the specific selection process of the UPF device as follows: 1. The UPF device selection instruction module sends DNAI to the 5G core network session management function SMF device through the data transceiver gateway to select a UPF device. After the UPF device executes successfully, the core network SMF device feeds back the message of successful execution of the instruction to the UPF device selection instruction module; 2. The UPF device selection instruction module sends the surgical robot image test instruction to the instruction arrangement module, and the instruction arrangement module feeds back a message of successful instruction execution to the UPF device selection instruction module; 3. The instruction arrangement module sends the surgical robot image test instruction to the surgical robot console in the surgical robot control area through the data transceiver gateway, and the surgical robot console feeds back the successful execution of the instruction to the instruction arrangement module through the data transceiver gateway; 4. The instruction arrangement module sends the surgical robot image collection instruction to the digital image module, and the digital image module feeds back a message that the instruction is successfully executed to the instruction arrangement module; 5. The digital image module collects the video of the proximal operation area received by it from the proximal surgical display system in the surgical robot control area through the data transceiver gateway, that is, the proximal video after routing by the UPF device; It should be noted that, in addition to displaying the video received from the proximal operation area, the proximal surgery display system also displays the video received from the remote control area where it is located, that is, the remote video before the UPF device routing; 6. The digital image module collects the video of its own proximal operation area through the data transceiver gateway to the remote surgical display system in the surgical robot operation area, that is, the proximal video before the UPF device routing; It should be noted that, in addition to displaying the video received by the remote operation display system in its own proximal operation area, it also displays the video received by the remote control area, that is, the remote video after routing by the UPF device; 7. The digital image module discretizes the collected near-end videos before and after routing, and sends them to the brightness comparison module, contrast comparison module and structure comparison module for processing respectively; 8. The brightness comparison module, the contrast comparison module and the structure comparison module send the processed brightness similarity, contrast similarity and structure similarity to the feature similarity fusion module for fusion, and obtain the image similarity between the video frames of the near-end video at the same time before and after routing; 9. The feature similarity fusion module sends the similarities of each image to the image similarity fusion module for fusion to obtain the video similarity of the videos before and after routing; 10. The image similarity fusion module sends the video similarity corresponding to the UPF device selected based on DNAI to the instruction arrangement module for recording; 11. After the instruction arrangement module sends the instruction to re-issue DNAI to the UPF device selection instruction module, the cycle from step 1 to step 11 is performed until the instruction arrangement module completes the recording of the video similarities corresponding to all UPF devices; Finally, the instruction arrangement module sorts the videos according to their similarity. , the UPF device it selects is optimal, and the UPF device selection instruction module will It is sent down to the core network SMF to complete the adaptive selection of the optimal UPF device. In this case, the near-end video maintains the best quality after being transmitted through the routing path of the optimal UPF device.

[0063] Figure 5 This is one of the structural diagrams of the user plane function device selection system provided in an embodiment of the present application; Figure 6 This is the second structural diagram of the user plane function device selection system provided in the embodiment of the present application.

[0064] Reference Figure 5 In the remote operation scenario of the surgical robot, the system includes a UPF equipment selection platform based on the 5G network, a mobile communication 5G network system, a surgical robot control area with a master-slave architecture, and a surgical robot operation area with a master-slave mechanism.

[0065] Among them, the 5G network system includes core network SMF equipment, UPF equipment, data communication equipment and wireless network equipment; 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.

[0066] The main functions of each part of the system are described as follows: 1. UPF device selection platform: collects the operation control information of the surgical robot console, the video information received by the proximal surgical display system, the video information received by the distal surgical display system, etc. through the data transceiver gateway of the platform, and interacts with the core network SMF device through the data transceiver gateway to complete the issuance of DANI to select the corresponding UPF device; 2. Surgical robot console: provides the surgeon with joysticks, pedals, buttons, etc. to perform remote-operated surgery; 3. Proximal surgery display system: displays the video of the proximal operation area received by the surgeon to provide a high-definition field of view for the surgical operation, in which the patient's wound, organs, blood vessels, and the robotic arm and end effector of the surgical robot are presented; 4. Data communication equipment: It consists of routers and servers, providing a dedicated line access environment for the surgical robot control area; 5. Core network SMF equipment: Select the corresponding UPF equipment based on DANI issued by the UPF equipment selection platform; 6. UPF equipment: provides contract control and video message routing for surgical services; 7. Wireless network equipment: composed of 5G wireless base stations, providing dedicated line access environment for the surgical robot operation area; 8. Surgical robot operating table: It is a remote operating environment for surgeons, providing the surgeons with the robotic arm and end effector of the surgical robot for surgical operations; 9. Remote surgery display system: displays the video of the remote control area received by the surgical learner, so as to provide the operation video of the surgical doctor, so as to facilitate remote consultation and learning for the surgical learner.

[0067] The main functions of each interface in the system are described as follows: 1. C1 interface: It is the interface between the UPF device selection platform and the surgical robot console. Its function is to collect the control instructions sent by the surgical robot console to the surgical robot operating table and determine the video startup and update status at the surgical robot console; 2. C2 interface: It is the interface between the UPF device selection platform and the proximal surgical display system. Its function is to collect the video information received by the proximal surgical display system. 3. API interface: It is the interface between the UPF device selection platform and the core network SMF device, which is used to instruct the core network SMF device to select different UPF devices according to the different DNAIs issued, so as to realize the change of teleoperation surgery service control and video message forwarding path; 4. P1 interface: It is the interface between the UPF device selection platform and the remote surgical display system. Its function is to collect the video information received by the remote surgical display system. 5. N4 interface: 5G core network standard interface between core network SMF equipment and UPF equipment, used by the core network SMF equipment to issue forwarding routing strategies to the selected UPF equipment; 6. N6 interface and N3 interface: 5G core network standard interface between data communication equipment and UPF equipment, and 5G core network standard interface between wireless network equipment and UPF equipment, used for control and video information forwarding between the surgical robot control area and the surgical robot operation area.

[0068] Reference Figure 6 Considering the wide application of the system, the UPF device selection platform can be deployed on a cloud x86 virtual machine based on Ubuntu 16.04.1LTS Xenial Xerus and ROSKinetic Kame framework. The surgical robot control area and the surgical robot operation area both use IP bearer mode. By pre-configuring relevant data, the IP network between the UPF device selection platform and the 5G core network, the surgical robot control area and the surgical robot operation area in the 5G network system is connected. In addition to SMF devices and UPF devices, the 5G core network also includes unified data management function UDM devices and access and mobility management function AMF devices, and the 5G core network reuses the existing network N2, N3, N4, N6, N8, N10, and N11 interfaces.

[0069] In addition, 5G NR and the packet slice network SPN / packet transport network PTN, as well as SPN / PTN and 5G core network are interconnected through IP dedicated lines. The feedback signal of the end effector of the surgical robot's robotic arm is routed to the surgical robot console through 5G NR, SPN / PTN and the UPF device of the 5G core network.

[0070] FIG. 7 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. 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 through the communication bus 740. The processor 710 may call a computer program in the memory 730 to execute the steps of the user plane function device selection method, for example including: Calculate the video similarities of the video pairs corresponding to the multiple user plane functional devices respectively, and obtain the multiple video similarities corresponding to the multiple user plane functional devices; wherein the video pair corresponding to any user plane functional device includes the pre-routing video and the post-routing video of the user plane functional device based on the same video; A maximum video similarity is determined from the multiple video similarities, and a user plane functional device corresponding to the maximum video similarity is determined as a target user plane functional device.

[0071] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0072] On the other hand, an embodiment of the present application further provides a computer program product, the computer program product including a computer program, the computer program may be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can perform the steps of the user plane function device selection method provided in the above embodiments, for example, including: Calculate the video similarities of the video pairs corresponding to the multiple user plane functional devices respectively, and obtain the multiple video similarities corresponding to the multiple user plane functional devices; wherein the video pair corresponding to any user plane functional device includes the pre-routing video and the post-routing video of the user plane functional device based on the same video; A maximum video similarity is determined from the multiple video similarities, and a user plane functional device corresponding to the maximum video similarity is determined as a target user plane functional device.

[0073] On the other hand, an embodiment of the present application further provides a non-transitory computer-readable storage medium on which a computer program is stored, wherein the computer program is used to enable a processor to perform the steps of the user plane function device selection method provided in the above embodiments, for example, including: Calculate the video similarities of the video pairs corresponding to the multiple user plane functional devices respectively, and obtain the multiple video similarities corresponding to the multiple user plane functional devices; wherein the video pair corresponding to any user plane functional device includes the pre-routing video and the post-routing video of the user plane functional device based on the same video; A maximum video similarity is determined from the multiple video similarities, and a user plane functional device corresponding to the maximum video similarity is determined as a target user plane functional device.

[0074] The non-transitory computer-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)), etc.

[0075] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0076] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for selecting a user plane functional device, characterized in that: include: Calculate the video similarities of the video pairs corresponding to the multiple user plane functional devices respectively, and obtain the multiple video similarities corresponding to the multiple user plane functional devices; wherein the video pair corresponding to any user plane functional device includes the pre-routing video and the post-routing video of the user plane functional device based on the same video; A maximum video similarity is determined from the multiple video similarities, and a user plane functional device corresponding to the maximum video similarity is determined as a target user plane functional device.

2. The method for selecting a user plane functional device according to claim 1, characterized in that: The video similarity of a video pair corresponding to any user plane functional device is determined based on the following method: Calculating image similarities between a plurality of video frames at the same time in a pre-routing video and a post-routing video of the user plane functional device to obtain a plurality of image similarities corresponding to the user plane functional device; The multiple image similarities are merged to obtain the video similarity of the video pair corresponding to the user plane functional device.

3. The method for selecting a user plane functional device according to claim 2, characterized in that: The image similarity between any video frames at the same time is determined based on the following method: Calculating the brightness similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing; Calculating the contrast similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing; Calculating the structural similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing; The brightness similarity, the contrast similarity and the structure similarity are fused to obtain the image similarity between the video frames at the target moment.

4. The method for selecting a user plane functional device according to claim 3, characterized in that: The calculating of the brightness similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing includes: Calculate the grayscale average of the video frame at the target time in the video before routing and the grayscale average of the video frame at the target time in the video after routing respectively, to obtain the grayscale average before routing and the grayscale average after routing; Based on the grayscale average value before routing and the grayscale average value after routing, the brightness similarity between the video frames at the target moment is obtained.

5. The method for selecting a user plane functional device according to claim 3, characterized in that: The calculating the contrast similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing includes: Calculate the grayscale standard deviation of the video frame at the target time in the video before routing and the grayscale standard deviation of the video frame at the target time in the video after routing respectively, and obtain the grayscale standard deviation before routing and the grayscale standard deviation after routing; Based on the grayscale standard deviation before routing and the grayscale standard deviation after routing, the contrast similarity between the video frames at the target moment is obtained.

6. The method for selecting a user plane functional device according to claim 3, characterized in that: The calculating the structural similarity between the video frame at the target time in the video before routing and the video frame at the target time in the video after routing includes: Calculate the target grayscale value of the video frame at the target time in the video before routing and the target grayscale value of the video frame at the target time in the video after routing respectively, and obtain the target grayscale value before routing and the target grayscale value after routing; the target grayscale value includes the grayscale mean value and the grayscale standard deviation; Based on the target grayscale value before routing and the target grayscale value after routing, the structural similarity between the video frames at the target time is obtained.

7. A user plane function device selection device, characterized in that: include: The video similarity calculation module is used to respectively calculate the video similarities of the video pairs corresponding to the multiple user plane functional devices to obtain the multiple video similarities corresponding to the multiple user plane functional devices; wherein the video pair corresponding to any user plane functional device includes the pre-routing video and the post-routing video of the user plane functional device based on the same video; The instruction arrangement module is used to: determine a maximum video similarity from the multiple video similarities, and determine a user plane function device corresponding to the maximum video similarity as a target user plane function device.

8. An electronic device comprising a processor and a memory storing a computer program, characterized in that: When the processor executes the computer program, the steps of the user plane function device selection method according to any one of claims 1 to 6 are implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the user plane function device selection method according to any one of claims 1 to 6 are implemented.

10. 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, the steps of the user plane function device selection method according to any one of claims 1 to 6 are implemented.

Images