# US 12,113,679 B2 · Training method for application MOS model, device, and system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,113,679 B2 - Document ID: US12113679B2 - Status: Granted - Kind: B2 - Application number: 17/581,935 - Filed: 2022-01-23 - Published: 2022-05-12 - Granted: 2024-10-08 - Earliest claimed: 2019-07-23 - Assignees: Huawei Technologies Co., Ltd. - Applicants: Huawei Technologies Co., Ltd. - Inventors: Shaofeng Kuai - Web page: https://patentgrep.com/patent/US12113679B2 ## CPC - H04L 41/145: {involving simulating, designing, planning or modelling of a network} - H04L 41/147: for predicting network behaviour - H04L 41/5009: Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF] - H04W 24/08: Testing, {supervising or monitoring} using real traffic - H04W 24/10: Scheduling measurement reports {; Arrangements for measurement reports} - H04L 43/08: Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) ## Abstract Embodiments of this application provide a training method for an application MOS model, and related device and system. A central network data analytics function (C-NWDAF) entity sends a first subscription request to an edge network data analytics function (E-NWDAF) entity, where the first subscription request is used to subscribe to a quality of service MOS level of a target service and a corresponding first network performance indicator. The first network performance indicator is a network performance indicator of a transmission network that carries the target service. The C-NWDAF entity receives the quality of service MOS level and the first network performance indicator from the E-NWDAF entity, and establishes a MOS model of the target service based on the received quality of service MOS level and the first network performance indicator. ## Claims ### Claim 1 A training method for an application mean opinion score (MOS) model, wherein the method comprises: sending, by a central network data analytics function (C-NWDAF) entity, a first subscription request to an edge network data analytics function (E-NWDAF) entity, wherein the first subscription request is used to subscribe to a quality of service MOS level of a target service and a corresponding first network performance indicator, and the first network performance indicator is a network performance indicator of a transmission network that carries the target service; receiving, by the C-NWDAF entity, the quality of service MOS level and the first network performance indicator from the E-NWDAF entity; establishing, by the C-NWDAF entity, a MOS model of the target service based on the quality of service MOS level and the first network performance indicator; and obtaining, by the C-NWDAF entity, a second network performance indicator corresponding to the MOS level and/or a first load of a first network function entity corresponding to the MOS level, wherein the second network performance indicator is a performance indicator of a radio network that carries the target service, and the first network function entity is a network data provider function entity; wherein the establishing, by the C-NWDAF entity, a MOS model of the target service based on the quality of service MOS level and the first network performance indicator comprises: excluding, by the C-NWDAF entity, a sample whose quality of service MOS is poor due to an exception of the terminal device and a sample whose quality of service MOS is poor due to an exception of the application function entity based on the quality of service MOS level, the first network performance indicator, and the second network performance indicator and/or the first load of the first network function entity; and establishing the MOS model of the target service. ### Claim 2 (depends on 1) The method according to claim 1, wherein the quality of service MOS level is determined based on service experience data of the target service. ### Claim 3 (depends on 2) The method according to claim 2, wherein when the target service is a video service, the service experience data comprises one or more of the following parameters: an initial buffering delay, playback buffer duration, a bit rate, a service rate, a frame rate, smoothness, and a definition of the video service, and a resolution of a terminal device. ### Claim 4 (depends on 1) The method according to claim 1, wherein the obtaining, by the C-NWDAF entity, a first load of a first network function entity corresponding to the MOS level comprises: sending, by the C-NWDAF entity, a second subscription request to a network repository function entity, wherein the second subscription request is used to subscribe to the first load of the first network function entity; and receiving, by the C-NWDAF entity, the first load of the first network function entity from the network repository function entity. ### Claim 5 (depends on 1) The method according to claim 1, wherein the obtaining, by the C-NWDAF entity, a second network performance indicator corresponding to the MOS level comprises: sending, by the C-NWDAF entity, a second subscription request to an operation administration and maintenance (OAM) entity of a carrier network, wherein the second subscription request is used to subscribe to the second network performance indicator; and receiving, by the C-NWDAF entity, the second network performance indicator from the OAM entity. ### Claim 6 (depends on 1) The method according to claim 1, wherein before the sending, by a C-NWDAF entity, a first subscription request to an E-NWDAF entity, the method further comprises: receiving, by the C-NWDAF entity, a second subscription request from a second network function entity, wherein the second subscription request is used to subscribe to the MOS model of the target service, and the second network function entity is a consumer function entity; and after the establishing, by the C-NWDAF entity, a MOS model of the target service, the method further comprises: sending, by the C-NWDAF entity, the MOS model of the target service to the second network function entity. ### Claim 7 (depends on 1) The method according to claim 1, wherein the method further comprises: receiving, by the C-NWDAF entity, a second subscription request from a policy control entity, wherein the second subscription request is used to request to provide service experience assurance for the target service of the target terminal device, and a quality of service MOS level requirement for the service experience assurance is a first quality of service MOS level; sending, by the C-NWDAF entity, a third subscription request to the E-NWDAF entity, wherein the third subscription request is used to subscribe to a trigger event for using the target service by the target terminal device, a second quality of service MOS level of the target service, and a corresponding first network performance indicator; after the trigger event is triggered, receiving, by the C-NWDAF entity, the second quality of service MOS level and the corresponding first network performance indicator from the E-NWDAF entity; when the second quality of service MOS level is different from the first quality of service MOS level, matching, by the C-NWDAF entity, the first network performance indicator corresponding to the second quality of service MOS level with a first network performance indicator corresponding to the first quality of service MOS level in the MOS model of the target service, to obtain a network analysis result; and sending, by the C-NWDAF entity, the network analysis result to the policy control entity, wherein the network analysis result is used for network optimization. ### Claim 8 (depends on 1) The method according to claim 1, wherein the method further comprises: receiving, by the C-NWDAF entity, a second subscription request from a policy control entity, wherein the second subscription request is used to request to provide service experience assurance for the target service of the target terminal device, and a quality of service MOS level requirement for the service experience assurance is a first quality of service MOS level; determining, by the C-NWDAF entity based on a movement track of the target terminal device, that the target terminal device is to move from a service range of a first access network device to a movement range of a second access network device; sending, by the C-NWDAF entity, a third subscription request to the E-NWDAF entity, wherein the third subscription request is used to subscribe to a trigger event for using the target service by a first terminal device and a first network performance indicator associated with the second access network device; after the trigger event is triggered, receiving, by the C-NWDAF entity, the first network performance indicator associated with the second access network device from the E-NWDAF entity; matching, by the C-NWDAF entity, the first network performance indicator associated with the second access network device with the MOS model of the target service, to determine a third quality of service MOS level of the target service corresponding to the first network performance indicator associated with the second access network device; when the third quality of service MOS level is different from the first quality of service MOS level, matching, by the C-NWDAF entity, the first network performance indicator corresponding to the third quality of service MOS level with a first network performance indicator corresponding to the first quality of service MOS level in the MOS model of the target service, to obtain a network prediction result; and sending, by the C-NWDAF entity, the network prediction result to the policy control entity, wherein the network prediction result is used for network optimization. ### Claim 9 A training method for an application mean opinion score (MOS) model, wherein the method comprises: receiving, by an edge network data analytics function (E-NWDAF) entity, a first subscription request from a central network data analytics function (C-NWDAF) entity, wherein the first subscription request is used to subscribe to a quality of service MOS level of a target service and a corresponding first network performance indicator, and the first network performance indicator is a network performance indicator of a transmission network that carries the target service; obtaining, by the E-NWDAF entity, the quality of service MOS level and the first network performance indicator; and sending, by the E-NWDAF entity, the quality of service MOS level and the first network performance indicator to the C-NWDAF entity; receiving, by the E-NWDAF entity, a second subscription request from the C-NWDAF entity, wherein the second subscription request is used to subscribe to a trigger event for using the target service, a second quality of service MOS level of the target service, and a corresponding first network performance indicator; after the trigger event is triggered, sending, by the E-NWDAF entity, the second quality of service MOS level and the corresponding first network performance indicator to the C-NWDAF entity: wherein when the second quality of service MOS level is different from the first quality of service MOS level, the first network performance indicator corresponding to the second quality of service MOS level is matched with a first network performance indicator corresponding to the first quality of service MOS level in the MOS model of the target service, to obtain a network analysis result. ### Claim 10 (depends on 9) The method according to claim 9, wherein the obtaining, by the E-NWDAF entity, the quality of service MOS level comprises: obtaining, by the E-NWDAF entity, service experience data of the target service; and determining, by the E-NWDAF entity, the quality of service MOS level based on the service experience data of the target service. ### Claim 11 (depends on 10) The method according to claim 10, wherein when the target service is a video service, the service experience data comprises one or more of the following parameters: an initial buffering delay, playback buffer duration, a bit rate, a service rate, a frame rate, smoothness, and a definition of the video service, and a resolution of a terminal device. ### Claim 12 (depends on 1) A chip, comprising a processor and an interface port, wherein the processor is coupled to a memory through the interface port; and when the processor executes a computer programs or instructions stored in the memory, the method according to claim 1 is performed. ### Claim 13 (depends on 9) A chip, comprising a processor and an interface port, wherein the processor is coupled to a memory through the interface port; and when the processor executes a computer programs or instructions stored in the memory, the method according to claim 9 is performed.