QoE modeling method based on cloud native network identifier

Abstract

The invention belongs to the technical field of big data services, and particularly discloses a QoE modeling method based on a cloud native network identifier, which comprises the following steps of: aiming at different service types, adopting network twinborn data agents under a network twinborn cloud native network access architecture, extracting service personalized features corresponding to the service type from historical behavior data of the user; and constructing a user experience QoE model corresponding to the service type based on the extracted service personalized features and a preset service quality index.

Description

Technical Field

[0001] The present invention belongs to the field of big data service technology, and in particular relates to a QoE modeling method based on cloud native network identification. Background Art

[0002] Quality of Service (QoS) is a service metric widely adopted in academia and industry. Typical QoS parameters include bandwidth, rate, packet loss rate, latency, and jitter in communication networks. Currently, communication networks often use QoS as an evaluation metric to schedule network resources. However, QoS metrics reflect performance at the technical and network transmission levels, ignoring user subjective factors and the impact of their environment. Therefore, QoS cannot directly reflect user satisfaction with the service.

[0003] Unlike objectively evaluated technical QoS parameters like rate, latency, and packet loss rate, user experience (QoE) parameters build on these objective technical QoS parameters by comprehensively considering factors affecting the service, network, user, and environment. These parameters directly reflect user satisfaction with the service. Furthermore, for the same QoS metric, different users experience different QoE parameters for the same service. Its design philosophy is to more closely reflect users' real experiences and better meet their personalized needs. Properly modeling user QoE is the first step in achieving personalized service.

[0004] Currently, there are two problems in the research on QoE models:

[0005] 1) Acquisition of personalized user data. Currently, personalized user data is centrally collected by providers or service providers. This data belongs to different providers or service providers, leaving users without control over their personalized service data and unable to establish a truly personalized service QoE model.

[0006] 2) QoE modeling for personalized converged communication services. Existing QoE parameters are constructed by service providers using statistical data collected from a large amount of user behavior to measure the user's subjective experience. For example, the number of users who leave the live broadcast room after a live broadcast freezes for a certain period of time or a certain number of times. The QoE modeled using this method is a statistical parameter and cannot reflect the user's personalized service experience.

[0007] Therefore, it is urgent to propose a QOE modeling method based on cloud native network identification to solve the above technical problems. Summary of the Invention

[0008] The present invention provides a QoE modeling method and system based on cloud native network identification, which are used to solve the problems of being unable to obtain user personalized service data and unable to reflect the user's personalized service experience.

[0009] In a first aspect, a QoE modeling method based on cloud native network identification is provided, the method comprising:

[0010] For different business types, a network twin data agent based on a cloud-native network access architecture based on network twins is used to extract business personalized features corresponding to the business type from the user's historical behavior data;

[0011] Based on the extracted service personalization features and pre-set service quality indicators, a user experience QoE model corresponding to the service type is constructed.

[0012] In a second aspect, a QoE modeling system based on cloud native network identification is provided, the system comprising:

[0013] The extraction module is used to extract the personalized service features corresponding to different service types from the user's historical behavior data using the network twin data agent under the cloud-native network access architecture based on network twins;

[0014] The construction module is used to construct a user experience QoE model corresponding to the service type based on the extracted service personalized features and pre-set service quality indicators.

[0015] An embodiment of the present invention provides a QOE modeling method and system based on cloud-native network identification, which uniformly records users' access data to various services through a network twin data proxy service under a cloud-native network access architecture. In this way, for different service types, the user's personalized characteristics can be extracted from the user's historical behavior data, which are then integrated with QoS indicators and mapped into QoE indicators to obtain a corresponding QoE model. Since in the process of constructing the QoE model, the user's access data to various services is uniformly collected through the network twin proxy service, based on this, corresponding QoE models are constructed for different service types of different users, thereby improving the rationality of network resource adjustment, meeting the personalized needs of users, and improving user experience.

[0016] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 The present invention provides a schematic diagram of the implementation process of a QOE modeling method based on cloud native network identification according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in conjunction with the specific embodiments of this specification and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this specification.

[0020] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0021] The technical solutions provided by the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0022] In order to effectively evaluate the degree of user service recognition in different communication service types, an embodiment of the present invention provides a QOE modeling method and system based on cloud native network identification.

[0023] Figure 1 A schematic diagram of the implementation process of a QOE modeling method based on cloud native network identification according to an embodiment of the present invention is provided. Figure 1 , the method comprising:

[0024] S100: For different service types, a network twin data agent based on a cloud-native network access architecture based on network twins is used to extract service personalized features corresponding to the service type from the user's historical behavior data;

[0025] S102: Constructing a user experience QoE model corresponding to the service type based on the extracted service personalized features and pre-set service quality indicators.

[0026] In a specific implementation, the service type includes voice service; and

[0027] Based on the extracted service personalized features and the pre-set service quality indicators, the user experience QoE model corresponding to the service type is constructed according to the following formula:

[0028]

[0029] Where, QoE Y It represents the user experience model indicator parameter of voice services; PEP represents the packet loss rate; α1, β1, and γ1 represent the first variable parameter, the second variable parameter, and the third variable parameter in the user experience model of voice services, respectively. The specific values ​​are obtained by machine learning methods based on the preferences of different users in voice services.

[0030] In a specific implementation manner, the service type further includes data stream service; and

[0031] Based on the extracted service personalized features and the pre-set service quality indicators, the user experience QoE model corresponding to the service type is constructed according to the following formula:

[0032]

[0033] Where, QoE S Indicates the user experience model indicator parameters of data stream services; S represents the file size; T c represents the data stream throughput; α2 and β2 respectively represent the first variable parameter and the second variable parameter in the user experience model of the data stream service. The specific values ​​are obtained by machine learning methods based on the preferences of different users in the data stream service.

[0034] In a specific implementation manner, the service type further includes a high-definition video streaming service; and

[0035] Based on the extracted service personalized features and the pre-set service quality indicators, the user experience QoE model corresponding to the service type is constructed according to the following formula:

[0036]

[0037] Where, QoE G represents the user experience model indicator parameters of the high-definition video streaming service; k represents the video mobility factor; a represents the video spatial characteristic factor; R represents the user's transmission rate; u represents the encoding rate; k, a and α3 respectively represent the first variable parameter, the second variable parameter and the third variable parameter related to the user's personalized preference among users of the high-definition video streaming service.

[0038] In a specific embodiment, the method further comprises:

[0039] Based on the constructed user experience model, the Min-Max deviation standardization method is used to quantify the user experience model indicator parameters corresponding to different business types into normalized continuous values ​​from 0 to 1. The larger the score, the higher the user satisfaction and the better the user experience.

[0040] In a specific embodiment, the method further comprises:

[0041] Determine the target service type currently accessed by the user based on service features extracted from the data stream currently generated by the user;

[0042] According to the determined target service type, network resources are scheduled for the user based on a user experience QoE model corresponding to the target service type.

[0043] In a specific implementation, in addition to adjusting the personalized parameters of the QoE model for different types of services, a deep neural network can also be used to build a personalized QoE model for the user. Specifically, the user's personal data, environment, service type, QoS and other factors in the network twin are used as inputs to the deep neural network, and the user's recognition of the service is used as output. The connection weights, importance weights and aggregation capabilities between nodes in the deep neural network are trained using label data. The trained deep neural network can be directly used to characterize the user's personalized QoE model. The QoE model obtained here can be directly used for on-demand connection and scheduling of resources in future networks, so that resources can guarantee the service quality of the user's personalized services.

[0044] An embodiment of the present invention provides a QOE modeling method based on cloud-native network identification, which uniformly records users' access data to various services through the network twin data proxy service under the cloud-native network access architecture. In this way, for different service types, the user's personalized characteristics can be extracted from the user's historical behavior data, which are integrated with the QoS indicators and mapped into QoE indicators to obtain the corresponding QoE model. Since in the process of constructing the QoE model, the user's access data to various services is uniformly collected through the network twin proxy service, based on this, corresponding QoE models are constructed for different service types of different users, thereby improving the rationality of network resource adjustment, meeting the personalized needs of users, and improving user experience.

[0045] Based on the same inventive concept, the present invention also provides a QoE modeling system based on cloud native network identification, the system comprising:

[0046] The extraction module is used to extract the personalized service features corresponding to different service types from the user's historical behavior data using the network twin data agent under the cloud-native network access architecture based on network twins;

[0047] The construction module is used to construct a user experience QoE model corresponding to the service type based on the extracted service personalized features and pre-set service quality indicators.

[0048] In a specific implementation, the service type includes voice service; and

[0049] The construction module is specifically used to construct a user experience QoE model corresponding to the service type according to the following formula based on the extracted service personalized features and the pre-set service quality indicators:

[0050]

[0051] Where, QoE Y It represents the user experience model indicator parameter of voice services; PEP represents the packet loss rate; α1, β1, and γ1 represent the first variable parameter, the second variable parameter, and the third variable parameter in the user experience model of voice services, respectively. The specific values ​​are obtained by machine learning methods based on the preferences of different users in voice services.

[0052] In a specific implementation manner, the service type further includes data stream service; and

[0053] The construction module is further specifically configured to construct a user experience QoE model corresponding to the service type according to the following formula based on the extracted service personalized features and the pre-set service quality indicators:

[0054]

[0055] Where, QoE S Indicates the user experience model indicator parameters of data stream services; S represents the file size; T c represents the data stream throughput; α2 and β2 respectively represent the first variable parameter and the second variable parameter in the user experience model of the data stream service. The specific values ​​are obtained by machine learning methods based on the preferences of different users in the data stream service.

[0056] In a specific implementation manner, the service type further includes a high-definition video streaming service; and

[0057] The construction module is further specifically configured to construct a user experience QoE model corresponding to the service type according to the following formula based on the extracted service personalized features and the pre-set service quality indicators:

[0058]

[0059] Where, QoE G represents the user experience model indicator parameters of the high-definition video streaming service; k represents the video mobility factor; a represents the video spatial characteristic factor; R represents the user's transmission rate; u represents the encoding rate; k, a and α3 respectively represent the first variable parameter, the second variable parameter and the third variable parameter related to the user's personalized preference among users of the high-definition video streaming service.

[0060] In a specific embodiment, it also includes:

[0061] Based on the constructed user experience model, the Min-Max deviation standardization method is used to quantify the user experience model indicator parameters corresponding to different business types into normalized continuous values ​​from 0 to 1. The larger the score, the higher the user satisfaction and the better the user experience.

[0062] In a specific embodiment, it also includes:

[0063] Determine the target service type currently accessed by the user based on service features extracted from the data stream currently generated by the user;

[0064] According to the determined target service type, network resources are scheduled for the user based on a user experience QoE model corresponding to the target service type.

[0065] An embodiment of the present invention provides a QOE modeling system based on cloud-native network identification, which uniformly records users' access data to various services through the network twin data proxy service under the cloud-native network access architecture. In this way, for different service types, the user's personalized characteristics can be extracted from the user's historical behavior data, which are integrated with the QoS indicators and mapped into QoE indicators to obtain the corresponding QoE model. Since in the process of constructing the QoE model, the user's access data to various services is uniformly collected through the network twin proxy service, based on this, corresponding QoE models are constructed for different service types of different users, thereby improving the rationality of network resource adjustment, meeting the personalized needs of users, and improving user experience.

[0066] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0067] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A QoE modeling method based on cloud native network identification, characterized in that: The method comprises: For different business types, a network twin data agent based on a cloud-native network access architecture based on network twins is used to extract business personalized features corresponding to the business type from the user's historical behavior data; Based on the extracted service personalization features and pre-set service quality indicators, a user experience QoE model corresponding to the service type is constructed.

2. The method according to claim 1, characterized in that The service type includes voice service; and Based on the extracted service personalized features and the pre-set service quality indicators, the user experience QoE model corresponding to the service type is constructed according to the following formula: Where, QoE Y It represents the user experience model indicator parameter of voice services; PEP represents the packet loss rate; α1, β1, and γ1 represent the first variable parameter, the second variable parameter, and the third variable parameter in the user experience model of voice services, respectively. The specific values ​​are obtained by machine learning methods based on the preferences of different users in voice services.

3. The method according to claim 2, characterized in that The service type also includes data flow service; and Based on the extracted service personalized features and the pre-set service quality indicators, the user experience QoE model corresponding to the service type is constructed according to the following formula: Where, QoE S Indicates the user experience model indicator parameters of data stream services; S represents the file size; T c represents the data stream throughput; α2 and β2 respectively represent the first variable parameter and the second variable parameter in the user experience model of the data stream service. The specific values ​​are obtained by machine learning methods based on the preferences of different users in the data stream service.

4. The method according to claim 3, characterized in that The service type also includes high-definition video streaming service; and Based on the extracted service personalized features and the pre-set service quality indicators, the user experience QoE model corresponding to the service type is constructed according to the following formula: Where, QoE G represents the user experience model indicator parameters of the high-definition video streaming service; k represents the video mobility factor; a represents the video spatial characteristic factor; R represents the user's transmission rate; u represents the encoding rate; k, a and α3 respectively represent the first variable parameter, the second variable parameter and the third variable parameter related to the user's personalized preference among users of the high-definition video streaming service.

5. The method according to claim 1, characterized in that The method further comprises: Based on the constructed user experience model, the Min-Max deviation standardization method is used to quantify the user experience model indicator parameters corresponding to different business types into normalized continuous values ​​from 0 to 1. The larger the score, the higher the user satisfaction and the better the user experience.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Determine the target service type currently accessed by the user based on service features extracted from the data stream currently generated by the user; According to the determined target service type, network resources are scheduled for the user based on a user experience QoE model corresponding to the target service type.

7. A QoE modeling system based on cloud native network identification, characterized in that: The system comprises: The extraction module is used to extract the personalized service features corresponding to different service types from the user's historical behavior data using the network twin data agent under the cloud-native network access architecture based on network twins; The construction module is used to construct a user experience QoE model corresponding to the service type based on the extracted service personalized features and pre-set service quality indicators.

8. The system according to claim 7, characterized in that The service type includes voice service; and The construction module is specifically used to construct a user experience QoE model corresponding to the service type according to the following formula based on the extracted service personalized features and the pre-set service quality indicators: Where, QoE Y It represents the user experience model indicator parameter of voice services; PEP represents the packet loss rate; α1, β1, and γ1 represent the first variable parameter, the second variable parameter, and the third variable parameter in the user experience model of voice services, respectively. The specific values ​​are obtained by machine learning methods based on the preferences of different users in voice services.

9. The system according to claim 8, characterized in that The service type also includes data flow service; and The construction module is further specifically configured to construct a user experience QoE model corresponding to the service type according to the following formula based on the extracted service personalized features and the pre-set service quality indicators: Where, QoE S Indicates the user experience model indicator parameters of data stream services; S represents the file size; T c represents the data stream throughput; α2 and β2 respectively represent the first variable parameter and the second variable parameter in the user experience model of the data stream service. The specific values ​​are obtained by machine learning methods based on the preferences of different users in the data stream service.

10. The system according to claim 9, characterized in that The service type also includes high-definition video streaming service; and The construction module is further specifically configured to construct a user experience QoE model corresponding to the service type according to the following formula based on the extracted service personalized features and the pre-set service quality indicators: Where, QoE G represents the user experience model indicator parameters of the high-definition video streaming service; k represents the video mobility factor; a represents the video spatial characteristic factor; R represents the user's transmission rate; u represents the encoding rate; k, a and α3 respectively represent the first variable parameter, the second variable parameter and the third variable parameter related to the user's personalized preference among users of the high-definition video streaming service.

Images