US-12627581-B2 - Systems and methods for a proxy model of network quality

US12627581B2US 12627581 B2US12627581 B2US 12627581B2US-12627581-B2

Abstract

A machine learning-based proxy model may be generated to determine quality of user experience in a vehicle-based communication network in the absence of direct feedback from the users regarding the user experience. The machine learning-based proxy model may include supervised and/or unsupervised machine learning models, including for example a k-means clustering algorithm and/or an artificial neural network. Once generated, the proxy model may be applied to observed operational parameters of the vehicle-based communication network to quantify the user experience for any user for any duration of the vehicle-based communication network.

Inventors

Pearl Grey
Jen Pardi-Cusick

Assignees

GOGO BUSINESS AVIATION LLC

Dates

Publication Date: 20260512
Application Date: 20240403

Claims (20)

1 . A computer-implemented method implemented via one or more processors, the computer-implemented method comprising: training, based upon training data, a proxy model to analyze values of a plurality of operational parameters associated with providing a vehicle-based communication network of a vehicle to generate measurements of quality of user experience in the vehicle-based communication network, the training data comprising training sets of operational parameter values associated with uses of the vehicle-based communication network by users; obtaining a first observed set of operational parameter values corresponding to use of the vehicle-based communication network by a first user during a first transit of the vehicle; and obtaining, based at least in part on the first observed set of operational parameter values, an output of the trained proxy model, wherein the output comprises a first measurement of quality of user experience for the first user of the vehicle-based communication network during the first transit of the vehicle.
2 . The computer-implemented method of claim 1 , wherein the vehicle is an aircraft.
3 . The computer-implemented method of claim 1 , wherein the proxy model includes a k-means clustering model, wherein training the proxy model comprises training the k-means clustering model to categorize respective sets of operational parameters for respective users into one of a plurality of clusters associated with different levels of quality of user experience in the vehicle-based communication network.
4 . The computer-implemented method of claim 1 , wherein the proxy model includes one or more artificial neural networks, wherein the training data comprises labeled data comprising a respective labeled user experience measurement for each of the training sets of operational parameter values, and wherein training the proxy model comprises training the one or more artificial neural networks to generate correct measurements of user experience based upon the training data.
5 . The computer-implemented method of claim 1 , wherein the training of the proxy model comprises training one or more ground-based processing elements external to the vehicle.
6 . The computer-implemented method of claim 1 , wherein obtaining the output of the trained proxy model comprises analyzing the first observed set of operational parameter values via the one or more processors disposed within the vehicle.
7 . The computer-implemented method of claim 1 , wherein obtaining the output of the trained proxy model comprises analyzing the first observed set of operational parameter values via one or more second processors of one or ground-based computing devices external to the vehicle.
8 . The computer-implemented method of claim 1 , wherein the plurality of operational parameters comprises one or more parameters indicative of one or more hardware components of the vehicle-based communication network or a configuration of the one or more hardware components of the vehicle-based communication network.
9 . The computer-implemented method of claim 1 , wherein the plurality of operational parameters comprises one or more parameters indicative of a status, availability, or capability of one or more elements of the vehicle-based communication network.
10 . The computer-implemented method of claim 1 , wherein the plurality of operational parameters comprises one or more parameters indicative of usage behavior of the users of the vehicle-based communication network.
11 . The computer-implemented method of claim 1 , wherein the plurality of operational parameters comprises one or more parameters indicative of subscription of a user to one or more service terms for the vehicle-based communication network.
12 . One or more non-transitory computer readable media comprising instructions that, when executed via one or more processors, cause one or more computing devices to: train, based upon training data, a proxy model to analyze values of a plurality of operational parameters associated with providing a vehicle-based communication network of a vehicle to generate measurements of quality of user experience in the vehicle-based communication network, the training data comprising training sets of operational parameter values associated with uses of the vehicle-based communication network by users; obtain a first observed set of operational parameter values corresponding to use of the vehicle-based communication network by a first user during a first transit of the vehicle; and obtain, based at least in part on the first observed set of operational parameter values, an output of the trained proxy model, wherein the output comprises a first measurement of quality of user experience for the first user of the vehicle-based communication network during the first transit of the vehicle.
13 . The one or more non-transitory computer readable media of claim 12 , wherein the vehicle is an aircraft.
14 . The one or more non-transitory computer readable media of claim 12 , wherein the proxy model includes a k-means clustering model, wherein the instructions to train the proxy model comprise instructions to train the k-means clustering model to categorize respective sets of operational parameters for respective users into one of a plurality of clusters associated with different levels of quality of user experience in the vehicle-based communication network.
15 . The one or more non-transitory computer readable media of claim 12 , wherein the proxy model includes one or more artificial neural networks, wherein the training data comprises labeled data comprising a respective labeled user experience measurement for each of the training sets of operational parameter values, and wherein the instructions to train the proxy model comprise instructions to train the one or more artificial neural networks to generate correct measurements of user experience based upon the training data.
16 . The one or more non-transitory computer readable media of claim 12 , wherein the instructions to train the proxy model comprise instructions to train one or more ground-based processing elements external to the vehicle.
17 . The one or more non-transitory computer readable media of claim 12 , wherein the instructions to obtain the output of the trained proxy model comprise instructions to analyze the first observed set of operational parameter values via the one or more processors disposed within the vehicle.
18 . The one or more non-transitory computer readable media of claim 12 , wherein the instructions to obtain the output of the trained proxy model comprise instructions to analyze the first observed set of operational parameter values via one or more second processors of one or ground-based computing devices external to the vehicle.
19 . The one or more non-transitory computer readable media of claim 12 , wherein the plurality of operational parameters comprises one or more parameters indicative of one or more hardware components of the vehicle-based communication network or a configuration of the one or more hardware components of the vehicle-based communication network.
20 . The one or more non-transitory computer readable media of claim 12 , wherein the plurality of operational parameters comprises one or more parameters indicative of a status, availability, or capability of one or more elements of the vehicle-based communication network.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to, and the benefit of the filing date of, U.S. Provisional Patent Application No. 63/493,982, filed Apr. 3, 2023 and entitled “Systems and Methods for a Proxy Model of Network Quality,” the entirety of the disclosure of which is incorporated by reference herein. FIELD The present disclosure relates to communication systems, and more particularly, to techniques for measuring quality of experience at user devices over a duration of use of a communication network. BACKGROUND Vehicles, including but not limited to aircraft, may establish one or more satellite-based and/or terrestrial communication links to receive information to, and/or transmit information from the vehicle. A vehicle-based communication system is typically enabled via various communication components aboard the vehicle, including for example one or more aircraft-mounted antennas and further components which may be implemented, for example, as a Line Replaceable Unit (LRU) on-board the vehicle. Operation of the vehicle-based communication system enables an on-board communication network which may, for example, allow devices of passengers to receive live media content (e.g., web browsing, sporting events, live news) at the passenger electronic devices, or enable live bidirectional communications to and from the passenger devices (e.g., internet browsing, cellular calling, etc.) using the on-board communication network. Additionally or alternatively, such communications links may enable the vehicle to communicate with the ground to support the necessary operations of vehicle instruments and/or crew (e.g., aircraft navigation systems or crew communications). A fundamental goal for any vehicle-based communication system is to operate to the satisfaction of users of the system, i.e., to provide a satisfactory on-board network experience from the perspective of the users over a duration of use of the network (e.g., over a flight in an aircraft). Various technological factors may affect the provision of a satisfactory network experience by a communication system provider. These factors may include, for example, the availability and/or performance of components of the communication system by which the network is provided, and/or the resilience of software/hardware/firmware elements to mitigate or account for issues encountered in real-time. Other technological limitations of the communication system may also play a role in user experience, such limitations not always being under the control of the provider of the on-board system. Such limitations may include for example limited bandwidth of an air-to-ground (ATG) or satellite link (and/or of the greater communication network relied upon by the on-board network, e.g., for cell towers in a greater ATG network), or latency associated with components in the greater communication network. Moreover, regardless of the level of technological resources available, and even when the system provider operates an on-board network in a manner that the system provider believes to provide a best possible experience to users (e.g., by considering tradeoffs of application/feature availability, bandwidth, latency, etc., such that the network performs “well” from the perspective of the system provider), the service parameters considered the system provider may not match the service parameters that a given user(s) most strongly correlates to their own assessment of user experience. In consideration of these factors and limitations, vehicle communication system providers have sought models for evaluate the satisfaction of users with the network experience provided to the users (or “user experience”) during any given transit, or across multiple transits. Models established by vehicle communication system providers to evaluate user experience in typically rely upon direct, explicit feedback from the users, e.g., to rate their own experience and/or identify particular factors observed to affect their own experience. To that end, system providers may provide users with surveys, e.g., delivered to respective devices of users during or immediately upon the conclusion of use of the on-board network. The present disclosure identifies, though, that feedback rate for user surveys is often low, or nonexistent for certain types of transit routes and service. Moreover, survey-based feedback, even when received, may not particularly identify the factors positively and/or negatively affecting the user experience. SUMMARY The present disclosure describes systems and methods for generating and applying a proxy model to evaluate user experience in a vehicle-based communication network, to be used in the absence of direct feedback from network users. The proxy model, operating as a proxy for the direct user feedback, may identify and model the relationship(s) between user experience and each of a plurality of parameters associated with operation of the on-board communica