# US 2021/0344737 A1 · Model-based parameter selection for media sessions > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0344737 A1 - Document ID: US20210344737A1 - Status: Published application - Kind: A1 - Application number: 17/379,296 - Filed: 2021-07-19 - Published: 2021-11-04 - Earliest claimed: 2019-09-13 - Assignees: Microsoft Technology Licensing, LLC - Applicants: Microsoft Technology Licensing, LLC - Inventors: Rajesh Gunnalan; Huazhou Liu; Jiannan Zheng; Tin Qian - Web page: https://patentgrep.com/patent/US20210344737A1 ## CPC - H04L 65/1069: Session establishment or de-establishment - G06N 20/00: Machine learning - G06N 20/20: Ensemble learning - H04L 41/145: {involving simulating, designing, planning or modelling of a network} - H04L 41/147: for predicting network behaviour - H04L 41/16: using machine learning or artificial intelligence - H04L 43/0864: Round trip delays - H04L 43/087: Jitter - H04L 65/403: Arrangements for multi-party communication, e.g. for conferences (data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15) - H04L 65/80: Responding to QoS - H04L 67/141: Setup of application sessions (admission control or resource allocation in data switching networks H04L47/70) - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06N 20/10: using kernel methods, e.g. support vector machines [SVM] - H04L 41/5067: Customer-centric QoS measurements - H04L 43/0829: Packet loss - H04L 43/0852: Delays - H04L 43/0894: Packet rate - H04L 67/52: specially adapted for the location of the user terminal - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Techniques for providing improved online communication are provided herein. In one example, a model may be used to predict network parameters of a network connection of a computing device. One or more attributes specifying characteristics of the network connection for the computing device may be received and used by the model to predict the network parameters. The predicted network parameters may be provided to a computing device for initiation of a media session. ## Claims ### Claim 1 A method of initiating an online communication between computing devices, the method comprising: using one or more hardware processors: prior to execution of a media session and prior to receipt of feedback data indicative of one or more metrics of a network connection for the media session: receiving one or more attributes specifying characteristics of the network connection for a computing device for initiating the media session over one or more networks through the network connection, the one or more attributes including a geographic location; accessing a model using the one or more attributes; generating, via the model, one or more startup parameters for the media session using the one or more attributes as input to the model; and applying the one or more startup parameters for initiation of the media session. ### Claim 2 (depends on 1) The method of claim 1, further comprising: receiving data regarding one or more session parameters of the media session while the media session is executing; and updating the model using a machine learning technique, the one or more attributes, and the data regarding the one or more session parameters. ### Claim 3 (depends on 1) The method of claim 1, wherein the model is trained via a machine learning technique using historical data regarding a plurality of previously executed media sessions. ### Claim 4 (depends on 2) The method of claim 2, wherein the one or more session parameters comprise one or more of connectivity protocol, network round-trip time (RTT), loss characteristics, jitter characteristics, bandwidth characteristics, device rating, or connectivity path type. ### Claim 5 (depends on 1) The method of claim 1, wherein the media session is one of a peer-to-peer communication or an online audio and video conference. ### Claim 6 (depends on 1) The method of claim 1, wherein the one or more attributes further comprise one or more of a network provider of the one or more networks, a type of the one or more networks, a type of the computing device, a platform of the computing device, a form factor, a time of day, a day of the week, or a workload of the computing device. ### Claim 7 (depends on 1) The method of claim 1, further comprising: receiving data regarding one or more session parameters of the media session while the media session is executing; generating, by the one or more models, one or more session parameters using one or more of the one or more attributes or data regarding execution of the media session; and updating execution of the media session using the one or more session parameters. ### Claim 8 (depends on 7) The method of claim 7, wherein the one or more startup parameters comprises one or more of a bandwidth, a network connection type, a timeout setting, or a codec. ### Claim 9 (depends on 1) The method of claim 1, wherein the model is selected from a plurality of models using the one or more attributes. ### Claim 10 A system for initiating an online communication between computing devices, the system comprising: one or more hardware processors; one or more memories, storing instructions, which when executed, cause the one or more hardware processors to perform operations comprising: prior to execution of a media session and prior to receipt of feedback data indicative of one or more metrics of a network connection for the media session: receiving one or more attributes specifying characteristics of the network connection for a computing device for initiating the media session over one or more networks through the network connection, the one or more attributes including a geographic location; accessing a model using the one or more attributes; generating, via the model, one or more startup parameters for the media session using the one or more attributes as input to the model; and applying the one or more startup parameters for initiation of the media session. ### Claim 11 (depends on 10) The system of claim 10, the operations further comprising: receiving data regarding one or more session parameters of the media session while the media session is executing; and updating the model using a machine learning technique, the one or more attributes, and the data regarding the one or more session parameters. ### Claim 12 (depends on 10) The system of claim 10, wherein the model is trained via a machine learning technique using historical data regarding a plurality of previously executed media sessions. ### Claim 13 (depends on 11) The system of claim 11, wherein the one or more session parameters comprise one or more of connectivity protocol, network round-trip time (RTT), loss characteristics, jitter characteristics, bandwidth characteristics, device rating, or connectivity path type. ### Claim 14 (depends on 10) The system of claim 10, wherein the media session is one of a peer-to-peer communication or an online audio and video conference. ### Claim 15 (depends on 9) The system of claim 9, wherein the one or more attributes further comprise one or more of a network provider of the one or more networks, a type of the one or more networks, a type of the computing device, a platform of the computing device, a form factor, a time of day, a day of the week, or a workload of the computing device. ### Claim 16 (depends on 10) The system of claim 10, the operations further comprising: receiving data regarding one or more session parameters of the media session while the media session is executing; generating, by the model, one or more session parameters using one or more of the one or more attributes or data regarding execution of the media session; and updating execution of the media session using the one or more session parameters. ### Claim 17 (depends on 16) The system of claim 16, wherein the one or more startup parameters comprises one or more of a bandwidth, a network connection type, a timeout setting, or a codec. ### Claim 18 (depends on 10) The system of claim 10, wherein the model is selected from a plurality of models using the one or more attributes. ### Claim 19 A system of initiating an online communication between computing devices, the system comprising: means for receiving one or more attributes specifying characteristics of a network connection for a computing device for initiating a media session over one or more networks through the network connection, the one or more attributes including a geographic location; means for accessing a model using the one or more attributes; means for generating, via the model, one or more startup parameters for the media session using the one or more attributes as input to the model; and means for applying the one or more startup parameters for initiation of the media session prior to execution of the media session and prior to receipt of feedback data indicative of one or more metrics of the network connection for the media session. ### Claim 20 (depends on 19) The system of claim 19, wherein the one or more attributes further comprise one or more of a network provider of the one or more networks, a type of the one or more networks, a type of the computing device, a platform of the computing device, a form factor, a time of day, a day of the week, or a workload of the computing device.