Automatic media event detection and correction actions for communication sessions

Abstract

Disclosed in some examples are methods, systems, and machine-readable media that provide an automatic communication session assistant that assists participants in planning and performing communication sessions of one or more media customization settings with respect to other participants. A user of a network-based communication service may register one or more media customization settings and store them in a user profile. These media customization settings may be related to one or more rules in a rule data repository. Each rule may specify one or more media events that may affect one or more media customization settings of the participant. The rules may also describe corrective actions, such as prompts to participants, etc.

Description

Technical Field

[0001] Embodiments relate to an automated communication session assistant that, in some examples, detects media-related events in media shared during a network-based communication session (such as a network-based meeting). Some embodiments relate to providing corrective actions in response to detecting those events. Some embodiments relate to providing pre- and post-network-based communication session reports. Background Art

[0002] Modern communication tools allow users to participate in network-based communication sessions. These communication sessions allow for voice, video, application sharing, and content sharing among multiple participants, some of whom may be located far apart from each other. These communication sessions allow users to experience collaborative sessions that are close to and in some respects superior to in-person meetings. Brief Description of the Drawings

[0003] In the drawings, which are not necessarily to scale, like reference numerals may describe similar components in different views. Similar numbers with different letter suffixes may represent different instances of similar components. The drawings generally illustrate, by way of example and not limitation, the various embodiments discussed in this document.

[0004] Figure 1 A block diagram of a communication system is shown in accordance with some examples of the present disclosure.

[0005] Figure 2 A flowchart of a method for taking corrective actions in response to events in a communication session of a communication system is shown in accordance with some examples of the present disclosure.

[0006] Figure 3 A user interface of a communication session is shown in accordance with some examples of the present disclosure.

[0007] Figure 4 A user interface of a communication session is shown in accordance with some examples of the present disclosure.

[0008] Figure 5 is a block diagram of an example of a machine on which one or more embodiments may be implemented. Detailed Description

[0009] While communication sessions provided by web-based communication services offer powerful collaboration tools, the remoteness of these sessions can cause problems for some participants. Certain events during a media session may not present in a form that is conducive to a particular individual's ability to participate in the communication session. Some examples include: a participant referring to visual content shared by stating "as you can see..."; visual elements being presented during a meeting without an audio explanation; a video being shared for a participant with a hearing impairment that does not have appropriate closed captions; and so on. In these examples, for communication sessions where all participants can indeed see and hear what is being discussed, these situations may be okay, but there may be communication sessions where a participant cannot see or hear what is being discussed. That is, while a participant can state "as you can see", there may be situations where a participant cannot actually "see" what is being emphasized. Other events that can affect the experience of participants in web-based communication sessions can include mispronouncing a participant's name, using the incorrect pronoun to refer to a participant, etc. Most often, these events are not the result of an intentional offense, but rather stem from the inherent difficulty of managing or participating in a meeting and also remembering the specific needs of each participant.

[0010] In some examples, methods, systems, and machine-readable media are disclosed that provide an automated communication session assistant that assists participants in planning and conducting a communication session regarding one or more media customization settings for other participants. Users of web-based communication services can register one or more media customization settings and store them in a user profile. For example, the media customization settings can indicate a disability, inclusion, or other media customization settings. These media customization settings can be associated with one or more rules in a rule data repository. Each rule can specify one or more media events that may affect one or more media customization settings of a participant. For example, a media customization setting can indicate that a user is hearing impaired, and the rule corresponding to this customization can be that videos shared during a communication session should include captions. In such an example, a media event can include an instance of a video lacking captions being shared during a communication session. The rules can also describe curative actions, such as prompting a participant, etc.

[0011] As used herein, a media event includes any specified condition that occurs within any media associated with a web-based communication session. Media events can include words or phrases spoken during a meeting, a lack of audio description for a video presentation, a lack of visual content for audio, a shared document, an application or presentation with accessibility or formatting issues, a lack of closed captions, etc. Conditions can include, for example, a specific word or phrase spoken during the communication session, the type of content being shared, the content of the shared content, a lack of description of the shared content, etc. Exemplary words or phrases can include an incorrect description of a participant (e.g., a mispronunciation of their name, use of the wrong pronoun, etc.), an audio cue for viewing a visual element, a visual element without an associated audio interpretation, an audio element without a visual description (e.g., closed captions), etc. Media can include streaming audio (e.g., a conversation), video, chat, shared content, documents, etc.

[0012] As previously described, the communication session assistant can perform pre-session assistance to provide automatic guidance to the organizer to prepare for the communication session. For example, the organizer can be reminded of specific accommodations for one or more participants. A report can be provided to the organizer of the communication session identifying any issues found and reporting one or more media customization settings of the participants. For example, the report can remind the organizer that a participant has a hearing impairment. In other examples, the communication session assistant can scan documents to be shared (if included in the invitation or added later to the agenda or calendar appointment), agenda items, etc. to identify incompatibilities between these items and the media customization settings of each participant. For example, documents can be scanned for issues that may affect specific customization settings of participants. Specific issues in the document that may affect specific media customization settings of participants can be specified within a ruleset. Exemplary issues can include one or more of the following: a lack of alternative text for non-text content; content with a small font size or that is difficult to see; content with a color that does not contrast with the background; a lack of closed captions for audio or video; a lack of text description for visual items; etc. In some examples, documents with identified issues can be automatically fixed. In other examples, the document can be (automatically or with the organizer's permission) sent to an individual within the participant's organization who knows how to fix these issues. In some examples, videos to be shared can be scanned to determine if they are captioned, and in some examples, the videos to be shared can be sent to a designated individual within the organization for inspection to ensure that the closed captions are correct.

[0013] In some examples, issues that do not affect any participant may not be corrected or disclosed to the organizer. For example, if no participant has a custom setting for a media event that maps to a closed caption for a video that is required, a video without closed captions to be shared during a communication session may not trigger a warning or any automated action. In other examples, a base rule set may be mapped to media events that apply to all communication sessions, regardless of the individual media custom settings of the participants. If the closed caption media event is one of the media events mapped to the base rule set, then even if a participant does not have a custom setting mapped to the media event, a plan to share a video without closed captions may trigger a warning and / or an automated action to correct the situation.

[0014] The communication session assistant can also monitor media during a communication session for media events. At the start of a meeting, the communication session assistant can identify the media custom settings of the participants and any base settings; identify the rule sets corresponding to those media custom settings and base settings; and start scanning for the media events specified in the rule sets. When a media event is detected, the associated corrective action specified in the rule set can be executed. Media events can be scanned by converting speech audio to a language structure and matching the language structure to conditions (such as phrases like "as you can see"). In other examples, an attempt to pronounce a participant's name is detected and compared to an established pronunciation. In other examples, the system can scan shared media to determine the presence of captions, media events, etc. in a document.

[0015] In some examples, event scanning can employ deeper analysis. For example, visual elements such as videos, application sharing, etc. can be displayed. Event scanning can determine that the user has difficulty seeing, and the audio can be scanned to ensure that an audio description of the visual content is provided. For example, the audio can be converted to a transcript. Object recognition algorithms such as region-based convolutional neural networks or other applicable methods can also be used to scan the visual elements. A keyword search of the transcript can be employed to determine if an object identified in the visual elements is discussed in the audio. The keywords can be a pre-specified list of the names or synonyms of the identified objects. In some examples, multiple objects can be shown and discussed, and if a specified threshold or percentage of the shown objects is not discussed, a corrective action can be employed. The threshold can be specified in the media custom settings, the rule set, or can be specified by an administrator.

[0016] In some examples, the data structure identifying media events corresponding to media customization settings can have a severity level for each media event. For example, depending on the rate of other corrective actions being performed for a particular participant, the communication session assistant may not perform a corrective action. That is, to avoid subjecting a particular participant to an excessive number of corrective actions, the system can limit the rate at which corrective actions are performed towards that participant. In some examples, the limiting algorithm can take into account the severity level. Thus, if the frequency of corrective actions previously taken towards a participant is high, corrective actions may not be performed for media events with a low severity rating. Conversely, corrective actions may be performed for media events with a high severity rating even if a high frequency of corrective actions has been previously taken. This ensures that media events that have a high impact on a participant's ability to effectively participate in a communication session will likely have corrective actions taken, while events with less impact may or may not have corrective actions taken. This strikes a balance between not distracting the participant, but at the same time ensuring that action is taken for the most impactful events.

[0017] Corrective actions can include prompts to one or more participants and / or the meeting organizer. For example, a prompt to the participant who initiated the media with the event (e.g., the participant who said a word or phrase). The prompt can include a specific triggering event and one or more ways to fix the problem. For example, if the triggering event is a participant stating "as you can see" and there happens to be a person with a visual impairment, the participant who said the phrase can be prompted that there may be participants who cannot see and be advised to describe what is being shown.

[0018] In other examples, automatic corrective actions can be applied, including automatic transcription (e.g., automatically generating captions for visual elements), automatic color correction (e.g., for participants with color blindness), and other automatic fixes to documents or shared content. The corrective actions can store rules for automatically fixing problems, such as rules for fixing documents in one or more different formats. In some examples, in the case where the corrective action is to change a shared document (e.g., change the colors in a document for a color-blind participant), the corrected document can be presented to all participants, or in some examples, only to participants with a media customization setting indicating that they are color-blind. Other exemplary automatic corrective actions include starting a screen reader service to interpret and describe visual content shared on the screen in the case where the user has a visual impairment.

[0019] In some examples, after a communication session, a communication session assistant can provide a post-session report to one or more participants. The report can be participant-specific and can list media events detected that originated from a particular participant, as well as corrective actions and recommendations for future communication sessions. In some examples, the report can include one or more metrics. Examples include the number of media events detected that originated from the user, the number of corrective actions taken with respect to the user, and the like.

[0020] In some examples, the communication session assistant can provide metrics for all participants of a particular communication session. For example, the number of media events detected for the communication session, the total number of corrective actions taken with respect to the communication session, and the like. The metrics can include breakdowns of media events, corrective actions, which users initiated media events, and corrective actions. These metrics can be aggregated for various components of the organization to provide a health report for those components, or aggregated for the organization as a whole to understand whether media events occur regularly, and if so, which media events.

[0021] In addition to responding to media events and issues throughout the communication session, the communication session assistant can be proactive in that it can provide reminders regarding the various convenience needs of the participants throughout the meeting. These can be provided in the same manner as corrective actions, except that the language can not be specific to media events, but can be general reminders.

[0022] In some examples, since the list of media events scanned by the communication session assistant depends on the particular participant, the system can employ one or more plugins that each look for one or more specific media events. By only loading specific plugins that scan media events indicated by the media customization settings of the meeting participants, rather than having a software module that looks for all possible media events, the system can save computing resources such as memory, processing power, and other resources by not loading code that will not be executed (e.g., code that scans media events that are not relevant to the participants in a web-based communication session).

[0023] Without the assistance of a communication session assistant, users with specific needs may need to waste valuable time asking for clarification or explanation. This takes additional time and thus wastes computing resources because it prolongs the time of the communication session using additional network resources, additional power, and additional computing. Additionally, the disclosed techniques improve the interaction between the computing device and the participants. For example, by providing automatic and helpful feedback to the participants when an event is automatically detected, the system provides a communication session, whereby the participants will not have to directly disclose their obstacles to other participants - something they may not expect to do. This ensures an equal experience for all. For example, the corrected participants will have an automatic and discrete message shown to them by the system, rather than another participant (and not other participants unless they also trigger the event). Thus, the present disclosure teaches the participants. The present disclosure utilizes one or more rule sets based on media customization settings to detect media events within the communication system and performs corrective actions based on the corrective actions in the rule sets, such as modifying the graphical user interface of the participants to enhance the user experience of all participants. The claimed process uses a specific combination order of specific rules, and the specific rules present the information in a specific format, which is then used and applied to create the desired result: an improved communication interface for network-based communication sessions. Additionally, human judgment about what is and is not a media event that needs correction is replaced with neutral rules. Thus, the present disclosure uses a technical solution that detects media events through predefined rule sets and provides corrections to solve the technical problems of inefficient use of computing resources and inefficient user interfaces.

[0024] Figure 1 A block diagram of a communication system 100 according to some examples of the present disclosure is shown. Figure 1 A first participant computing device 105 shown as a laptop computer is shown in the upper left part of the figure. The first participant computing device 105 is shown communicatively coupled to a network 115. The communication coupling is shown as a signal in the form of lightning. The network 115 is symbolically represented by a network cloud and can be a packet-based or circuit-switched network. The network 115 can be a local area network (LAN), a wide area network (WAN), the Internet, etc. A second participant computing device 110 is similarly shown in the lower left corner of the figure. The first participant computing device 105 and the second participant computing device 110 can execute network-based communication applications (not shown for clarity) that communicate with a network-based communication service 120 using the communication coupling to the network 115.

[0025] The network-based communication service 120 is shown as a set of computer servers in the upper central part of the figure. The network-based communication service 120 is also shown as communicatively coupled to the network 115. Next to the computer servers, a logical diagram of the network-based communication service 120 executed on the computer servers is shown as a large box, within which there are multiple boxes that are the logical components of the network-based communication service 120. The logical components included in the network-based communication service 120 shown in the figure include: a media customization settings interface component 125, a network-based communication provider component 130, a participant profile component 135 (shown as a data repository), a rule storage component 137 (also shown as a data repository), and a network-based communication assistant 140. The network-based communication assistant 140 is shown as a large box within which there are additional component boxes. The additional components of the network-based communication assistant 140 include: a media event plugin manager 145, a media event scanner 150, a set of active media scanning plugins 152, a plugin repository 155, and a corrective action component 160. Those of ordinary skill in the art who benefit from this disclosure will understand that the components shown are exemplary, and additional components may be part of the system 100, and some of the components shown may be combined with other components, renamed, or omitted.

[0026] The network-based communication service 120 utilizes instances of network-based communication applications executed on computing devices (such as the first participant computing device 105 and the second participant computing device 110) to provide one or more network-based communication sessions for participants. The network-based communication applications executed on the participant computing devices (such as participant computing devices 105, 110) provide one or more user interfaces for establishing, joining, and participating in communication sessions with one or more other participants. The network-based communication applications transmit voice, video, and other media from their respective computing devices to the network-based communication provider component 130 of the network-based communication service 120. The network-based communication provider component 130 of the network-based communication service 120 can receive media from the participant devices, mix the media with other media received from other participant devices, and then send the media of the communication session to one or more participant devices executing the network-based application. These devices can then output the media.

[0027] The network-based communication provider component 130 and the network-based communication application can implement one or more protocols for establishing communication sessions and receiving and sending media, such as the Hypertext Transfer Protocol (HTTP), the Session Initiation Protocol (SIP), the Real-Time Transport Protocol (RTP), etc. Additionally, the network-based communication provider component 130 can implement one or more media encoders and decoders to encode and decode media. The network-based communication application can be a dedicated communication application or a browser-based communication application for joining and participating in communication sessions via a web browser.

[0028] The media customization settings interface component 125 of the network-based communication service 120 can provide one or more graphical user interfaces (GUIs) that allow users to input various settings (such as media customization settings). The participant profile component 135 saves these settings in the participant's profile. Exemplary media customization settings can include participant media customization settings, such as the identification of one or more impairments, accommodations, inclusion settings, one or more preferred pronouns, information about the correct pronunciation of names, etc. In some examples, the media customization settings can include or be linked to specific rules, such as "Please describe all visual content", etc., rather than identifying specific information about the participant (such as impairments or accommodations).

[0029] In some examples, these media customization settings can then be mapped to media event rules, such as those stored by the rule storage component 137. The rules can include specific media event triggers, such as specific words; specific phrases; the type of shared content; shared content without an audio interpretation; shared content without subtitles; shared content with certain issues that make it difficult for some individuals to see or hear the content; documents or content with poor contrast or colors that may be difficult for color-blind users to see; etc. Each rule can include a corrective action. For example, the corrective action can automatically (with or without the approval of the shared participants) update the document to remove the rule violation. For example, a document with colors that are confusing to a specific participant who may be color-blind can be automatically updated with colors that do not confuse that participant. Confusing colors are color pairs or groups that are typically misinterpreted by color-blind individuals. For example, for red-green color-blind individuals, confusing colors can include: cyan and gray; rose-pink and gray; blue and purple; yellow and neon green; and red, green, orange, and brown.

[0030] In some examples, rather than automatically fixing the document, the document can be sent to an individual within the organization who can fix the document, based on the type of problem. In these examples, the system can initiate an automatic or semi-automatic workflow that assigns corrective actions, tracks the fixes, and so on. In other examples, the corrective action is a message in the GUI of the communication session, such as a pop-up window or other notification. The corrective message can be displayed to everyone, or it can be displayed only to the participant who triggered the event.

[0031] The rules stored in the rule storage component 137 can include default rules corresponding to specific customization options of the participant profile. That is, if the participant indicates a hearing impairment, the default rules can apply default media events and default corrective actions. However, the participant can customize these default rules to create a new set of customized rules.

[0032] In some examples, each rule includes a severity. That is, some media event instances may be less annoying to the participant than other media event instances. In these examples, if many other corrective actions have been performed on a participant who initiated a specific media event with low severity in the past, the web-based communication assistant 140 may not perform a corrective action for that specific media event. This prevents the web-based communication assistant from distracting the participant. However, actions can be taken for some events with a high severity level, and the associated corrective actions can be performed, regardless of the previous frequency of corrective actions on the participant. This ensures that events that are critical for the participant to understand what is happening are delivered.

[0033] The web-based communication assistant 140 can include a media event plug-in manager 145, a media event scanner 150, a plug-in repository 155, an active media scan plug-in 152, and a corrective action component 160. The media event scanner 150 can provide event detection and identification before, during, and after the communication session.

[0034] Before a communication session - for example, after scheduling, or just before the session is scheduled to start, or at some point in between - the media event scanner 150 can determine the participants in the session. The media event scanner 150 can then use the participant profile component 135 to identify the media customization settings of the participants from the participant profiles. Based on the media customization settings of the participants, the media event scanner 150 can determine a set of rules and corrective actions from the rule storage component 137. Based on these rules, information about the meeting - such as the list of invited participants, the media included in the invitation or on the agenda, etc. - can be analyzed to determine any issues before the communication session. Exemplary issues that are discovered and / or fixed can include: fixing issues with documents; providing the organizer with a reminder about the participants' disabilities; automatically inviting assistants associated with the participants (such as interpreters, sign language assistants, vision assistants, etc.). These issues can be automatically fixed with or without the organizer's input.

[0035] During the communication session, the media event scanner 150 uses the rules from the rule storage component 137 to scan for media events. The rules used by the media event scanner 150 can be a subset of all the rules in the rule repository that are selected based on the media customization settings in the participant profiles of the participants in the communication session. As mentioned before, these can be default rules according to the media customization settings of the participants, or they can be custom rules. Scanning during the communication session can include: speech recognition and transcription for comparison with known words and phrases; comparison of word pronunciations; natural language processing and understanding to determine if the presented visual media is being discussed; and so on. These techniques can include machine learning models such as hidden Markov models, dynamic time warping (DTW)-based speech recognition, neural networks, deep feedforward and recurrent neural networks, end-to-end automatic speech recognition, etc.

[0036] Exemplary techniques for determining if visual elements are described can include both applying speech recognition to produce an automatic transcription and applying image recognition to determine one or more themes of the visual content shared by the participants. The transcription is then searched to determine if the theme or a synonym is mentioned and how frequently it is mentioned. If the theme or a synonym is not mentioned at all, or not mentioned at the specified frequency (which can be specified in the rule set), then a corrective action can be triggered.

[0037] The correction action component 160 may perform correction actions. In some examples, this may include initiating a thread or process to transform a document from a first form to a second form, converting a document, changing the color of a document, etc. This may include sending prompts to one or more participants, etc. The correction action component 160 may initiate one or more workflows, such as a workflow to update one or more issues in one or more documents. The correction action component 160 may track the frequency of applying correction actions to each participant. In some examples, depending on the frequency of past correction actions applied to a participant and the severity of the media event, the correction action component 160 may not perform the associated correction action.

[0038] In some examples, the media event plugin manager 145 may manage one or more plugins. In some examples, the media event scanner 150 may utilize plugins (such as the active media scan plugin 152) to scan for issues. The media event plugin manager 145 may load the active media scan plugin 152 from the plugin repository 155 based on the rules scanned by the media event scanner 150 given the rules associated with a participant and their media customization settings. Each plugin may scan for one or more different media events. Thus, the media event plugin manager 145 scans the list of participants, determines the media customization settings of those participants, determines the associated rule sets, and based on those rule sets, selects from the plugin repository 155 one or more plugins that include executable instructions that will scan for the media events described in each rule based on the input media. By using plugins, in some examples, this makes the media event scanner 150 more suitable for scanning for future media events that may arise later and may also keep the execution size of the media event scanner 150 low, thus saving computing resources.

[0039] After a communication session, the media event scanner 150 may provide one or more reports to one or more participants that record the types of media events detected from the media originating from that participant, what corrective actions were taken, etc. The media event scanner 150 may provide a comprehensive report of all media events that occurred to the organizer of the communication session.

[0040] Figure 2 A flowchart of a method 200 for taking corrective actions in response to events in a communication session of a communication system according to some examples of the present disclosure is shown. The flowchart of method 200 is organized into a series of blocks, where the operations in each block are described in text and are connected by arrows showing the flow of the method. The figure is not shown, but optionally may include and as already described, provide a pre-session report that provides information about the media customization settings of the participants, fix issues in the documents or other media to be shared or discussed, etc. Additionally, the flow is not shown, but optionally may include providing a post-session report.

[0041] At operation 210, as shown in the first box at the top, the system identifies, in a participant profile data structure corresponding to a participant in the communication system, a first media customization setting for the participant who is using a first device in the communication session. Exemplary first settings include media customization settings as described herein. The system can identify the participants in the communication session, load their participant profiles, and determine a set of media customization settings applicable to all participants. In some examples, a set of default settings is also determined.

[0042] The process then proceeds to the next box, which is operation 215, where the system selects, based on the first settings, a data structure that includes a description of a first media event, an associated first corrective action to be taken in response to detecting the media event, and, in some examples, a severity level. For example, based on the setting information obtained in operation 210, the system can identify one or more rules from a rule repository that apply to the setting. In some examples, the media event includes one or more of the following: an audio cue for viewing a visual element, a visual element without an associated audio interpretation, an audio element without an associated visual description, or a specific description of a participant.

[0043] The process then proceeds to operation 220 shown in the next box, where the system scans the media of the communication session for the event during the communication session, which media is the audio, video, or shared content of the communication session. As previously described, the system can utilize one or more algorithms, machine learning models, etc.

[0044] At operation 225, the diamond box represents a decision as to whether the event has been detected. The box has two branches, where the first branch where no event has been detected directs the method flow back to the box containing operation 220 that is immediately above the diamond box of operation 225, where the media is scanned. If the event is detected, the process proceeds downward to the next box at operation 230, where the system identifies a second device based on an analysis of the media of the communication session, indicating that the media of the event originated from the second device, which device is one of the multiple devices participating in the communication session and is different from the first device.

[0045] The process proceeds downward from operation 230 to operation 235 at the next box, where the system determines the frequency of corrective actions that have been taken for the second device during the communication session. For example, the frequency can be the number of corrective actions within a predetermined time period. The process then proceeds from operation 235 to a decision box at operation 240, where it is decided whether to execute a corrective action based on the frequency and the severity level of the first settings.

[0046] If the decision is not to take a corrective action, the process returns to operation 220 where the media session is scanned. If a corrective action is to be taken, the process proceeds to the next box where, at operation 245, in response to determining to perform a corrective action, the system performs a corrective action for the second device. In some examples, the corrective action is for the second device but not for other devices among the multiple devices participating in the communication session. In some examples, the form of the corrective action may depend on the media customization settings of the target of the corrective action in the participant profile. For example, if the user has impaired vision, the notification may be delivered as an electronically created voice. After the corrective action is performed at operation 245, the process may return to operation 220 where the media is scanned for additional events until the communication session ends.

[0047] Figure 3 A user interface 300 for a communication session is shown in accordance with some examples of the present disclosure. The user interface includes a first window 310 having a title for the communication session, which in this case is "Monday Status Meeting". The user interface includes a row of icons 312 across the top that, when clicked, perform various functions such as inviting other users, opening a chat window, raising a hand, minimizing the window, disabling or enabling video, muting or unmuting the microphone, sharing content, and leaving the meeting. In the illustrated user interface, the main area (stage) 302 below the icons shows the names of two users present and their associated avatars. In Figure 3 the example, there are two users, "John Jones" and "Susan Smith". On the right, there is a meeting chat box 320 that shows a chat message 330 that says "Check out this file!" and has a file 340 named "Project X.docx" attached, which is represented by a file icon in the user interface and, when clicked, allows the user to download and / or open the file.

[0048] In Figure 3 the example, a web-based communication assistant has identified a media event as a result of a chat message. The media event includes the identification of a file having formatting or other issues. Accordingly, the web-based communication assistant provides a corrective action, which in this case is a prompt - shown as a box 345 below the message that states "Note *Project X.docx has formatting issues that may prevent all participants from viewing all elements of the file. Click here to fix." Box 345 has a user interface control in the form of a button 350 that allows the user to consent to fixing the file. In some examples, the fix may be automatically completed without the user having to click a fix button. In some examples, once the file is fixed, the originally posted copy is replaced with the fixed copy.

[0049] Figure 4 FIG. 400 shows a user interface of a communication session according to some examples of the present disclosure. The user interface 400 is very similar to Figure 3 the user interface shown in FIG., except that the chat window has been closed, thus revealing the name and avatar of the third participant. In this example, the network-based communication assistant has identified a media event in the audio spoken by the participant. The network-based communication assistant has taken a corrective action and uses the prompt 410 to prompt the participant. The content of the prompt 410 is "Note *You said a phrase suggesting that you can see the shared item, and one or more participants may not be able to see the item. Consider describing the item." The button 412 at the bottom of the prompt allows the user to dismiss the prompt.

[0050] Figure 5 FIG. 500 shows a block diagram of an exemplary machine 500 on which any one or more of the techniques (e.g., methods) discussed herein can be performed. In alternative embodiments, the machine 500 can act as a stand-alone device or can be connected (e.g., networked) to other machines. In a networked deployment, the machine 500 can operate in a server-client network environment as a server machine, a client machine, or both. In an example, the machine 500 can act as a peer machine in a peer-to-peer (P2P) (or other distributed) network environment. The machine 500 can be in the form of a server computer, a personal computer (PC), a tablet PC, a set-top box (STB), a personal digital assistant (PDA), a mobile phone, a smartphone, a web device, a network router, a switch, or a bridge, or any machine capable of executing instructions (sequentially or otherwise) that specify actions to be taken by that machine. Additionally, although only a single machine is shown, the term "machine" should also be regarded as including any collection of machines that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methods discussed herein, such as cloud computing, software as a service (SaaS), other computer cluster configurations. The machine 500 can be configured to implement Figure 1 any device and component of Figure 2 the method of Figure 3 and Figure 4 the user interface of

[0051] Examples as described herein may include one or more logical units, components, or mechanisms (hereinafter referred to as "components"), or may operate on them. A component is a tangible entity (such as hardware) capable of performing a specified operation and can be configured or arranged in a certain way. In an example, a circuit can be arranged as a component in a specified way (such as internally or relative to an external entity such as other circuits). In an example, all or part of one or more computer systems (such as stand-alone, client, or server computer systems) or one or more hardware processors can be configured by firmware or software (such as instructions, an application part, or an application) to operate as a component that performs a specified operation. In an example, the software can reside on a machine-readable medium. In an example, when executed by the underlying hardware of a component, the software causes the hardware to perform the specified operation of the component.

[0052] Accordingly, the term "component" is understood to encompass tangible entities that are physically constructed, specifically configured (such as hardwired), or temporarily (such as transiently) configured (such as programmed) to operate in a specified manner or to perform any of the operations described herein, in whole or in part. Considering examples where components are transiently configured, each component need not be instantiated at any given moment. For example, in the case where a component includes a general-purpose hardware processor configured with software, the general-purpose hardware processor can be configured as a corresponding different component at different times. The software can configure the hardware processor accordingly, such as to constitute a particular module at one moment and different components at different moments.

[0053] A machine (such as a computer system) 500 may include one or more hardware processors, such as processor 502. Processor 502 can be a central processing unit (CPU), a graphics processing unit (GPU), a hardware processor core, or any combination thereof. Machine 500 may include main memory 504 and static memory 506, some or all of which may communicate with each other via an interlink (such as a bus) 508. An example of main memory 504 may include synchronous dynamic random access memory (SDRAM), such as double data rate memory, such as DDR4 or DDR5. Interlink 508 can be one or more different types of interlinks such that one or more components can be connected using a first type of interlink and one or more components can be connected using a second type of interlink. Exemplary interlinks may include a memory bus, a peripheral component interconnect (PCI), a peripheral component express (PCIe) bus, a universal serial bus (USB), etc.

[0054] The machine 500 may also include a display unit 510, an alphanumeric input device 512 (such as a keyboard), and a user interface (UI) navigation device 514 (such as a mouse). In an example, the display unit 510, the input device 512, and the UI navigation device 514 may be a touch screen display. The machine 500 may additionally include a storage device (such as a drive unit) 516, a signal generation device 518 (such as a speaker), a network interface device 520, and one or more sensors 521, such as a Global Positioning System (GPS) sensor, a compass, an accelerometer, or other sensors. The machine 500 may include an output controller 528, such as a serial (such as Universal Serial Bus (USB), parallel, or other wired or wireless (such as infrared (IR), Near Field Communication (NFC), etc.) connection, to communicate with or control one or more peripheral devices (such as a printer, a card reader, etc.).

[0055] The storage device 516 may include a machine-readable medium 522 on which is stored a set or sets of data structures or instructions 524 (such as software) that embody or are utilized by any one or more of the techniques or functions described herein. The instructions 524 may also reside, completely or at least partially, within the main memory 504, within the static memory 506, or within the hardware processor 502 during execution by the machine 500. In an example, one or any combination of the hardware processor 502, the main memory 504, the static memory 506, or the storage device 516 may constitute a machine-readable medium.

[0056] Although the machine-readable medium 522 is shown as a single medium, the term "machine-readable medium" may include a single medium or multiple media (such as a centralized or distributed database and / or associated caches and servers) configured to store one or more instructions 524.

[0057] The term "machine-readable medium" may include any medium that is capable of storing, encoding, or carrying instructions for execution by the machine 500 and that causes the machine 500 to perform any one or more of the techniques of the present disclosure, or any medium that is capable of storing, encoding, or carrying data structures used by or associated with such instructions. Non-limiting examples of machine-readable media may include solid-state memory and optical and magnetic media. Specific examples of machine-readable media may include: non-volatile memory, such as semiconductor memory devices (such as Electrically Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM)), and flash memory devices; magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; Random Access Memory (RAM); Solid State Drives (SSD); and CD-ROM and DVD-ROM disks. In some examples, the machine-readable medium may include a non-transitory machine-readable medium. In some examples, the machine-readable medium may include a machine-readable medium that is not a transitory propagated signal.

[0058] Instructions 524 may also be sent or received over communication network 526 via network interface device 520 using a transmission medium. Machine 500 may communicate, wired or wirelessly, with one or more other machines using any of a variety of transmission protocols such as Frame Relay, Internet Protocol (IP), Transmission Control Protocol (TCP), User Datagram Protocol (UDP), Hypertext Transfer Protocol (HTTP), etc. Exemplary communication networks may include local area networks (LANs), wide area networks (WANs), packet data networks (e.g., the Internet), mobile telephone networks (e.g., cellular networks), plain old telephone (POTS) networks, and wireless data networks such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard family, known as Wi-Fi, the IEEE 802.15.4 standard family, the 5G New Radio (NR) standard family, the Long Term Evolution (LTE) standard family, the Universal Mobile Telecommunications System (UMTS) standard family, peer-to-peer (P2P) networks, etc. In an example, network interface device 520 may include one or more physical jacks (e.g., Ethernet, coaxial, or phone jacks) or one or more antennas to connect to communication network 526. In an example, network interface device 520 may include multiple antennas to communicate wirelessly using at least one of single-input multiple-output (SIMO), multiple-input multiple-output (MIMO), or multiple-input single-output (MISO) techniques. In some examples, network interface device 520 may communicate wirelessly using multi-user MIMO techniques.

[0059] Other Notes and Examples

[0060] Example 1 is a method of taking corrective actions in response to events in a communication session of a communication system, the method comprising: using a hardware processor: identifying a first setting of a participant in a participant profile data structure corresponding to the participant in the communication system, the participant using a first device in the communication session; selecting, based on the first setting, a data structure that includes a description of a first media event, an associated first corrective action to be taken in response to detecting the first media event, and a severity level, the first media event including one or more of: an audio cue for viewing a visual element, a visual element without an associated audio interpretation, an audio element without an associated visual description, or a specific description of the participant; scanning the media of the communication session for the first media event during the communication session, the media of the communication session being the audio, video, or shared content of the communication session; identifying the first media event in the media of the communication session; and in response to identifying the first media event: identifying a second device based on an analysis of the media of the communication session, indicating that the media of the event originated from the second device, the second device being one of a plurality of devices participating in the communication session, the first device and the second device being different; identifying the frequency of corrective actions that have been taken for the second device during the communication session; determining whether to perform the first corrective action based on the frequency and the severity level of the first setting; and in response to determining to perform the first corrective action, performing the first corrective action for the second device but not performing the first corrective action with respect to other devices of the plurality of devices participating in the communication session.

[0061] In Example 2, the subject matter of Example 1 includes, after the communication session, presenting, on the second device, a prompt indicating a plurality of events triggered due to media originating from the second device, the plurality of events including at least one event regarding a second corrective action not being performed due to the frequency of the corrective actions taken during the communication session.

[0062] In Example 3, the subject matter of Examples 1-2 includes, before the communication session, providing a report identifying the settings of the plurality of participants in the communication session.

[0063] In Example 4, the subject matter of Example 3 includes, before the communication session, scanning a document, included in an invitation to the communication session, for compatibility issues between the media in the document and the settings of the plurality of participants in the communication session.

[0064] In Example 5, the subject matter of Examples 1 - 4 includes identifying second settings of a second participant in a second participant profile data structure corresponding to the second participant in the communication system, the second participant using a third device in the communication session; selecting a second data structure based on the second settings, the second data structure including a description of a second media event and an associated second corrective action to be taken in response to detecting the second media event, the second media event including an audio element without subtitles; wherein scanning the media of the communication session during the communication session includes scanning both the first media event and the second media event; identifying the second media event in the media of the communication session; and in response to identifying the second media event: performing the second associated corrective action by automatically creating subtitles.

[0065] In Example 6, the subject matter of Examples 1 - 5 includes providing a reminder to a participant of the communication session during the communication session of the first settings.

[0066] In Example 7, the subject matter of Examples 1 - 6 includes calculating the number of media events detected during a plurality of communication sessions of an organization over a specified time period; and providing a report to a computing device describing the number of media events detected during the plurality of communication sessions of the organization.

[0067] Example 8 is a computing device for taking corrective actions in response to events in a communication session of a communication system. The computing device includes: a hardware processor; a memory that stores instructions that, when executed by the hardware processor, cause the device to perform operations, the operations including: identifying a first setting of a participant in a participant profile data structure corresponding to a participant in the communication system, the participant using a first device in the communication session; selecting a data structure based on the first setting, the data structure including a description of a first media event, an associated first corrective action to be taken in response to detecting the first media event, and a severity level, the first media event including one or more of the following: an audio cue for viewing a visual element, a visual element without an associated audio interpretation, an audio element without an associated visual description, or a specific description of the participant; scanning the media of the communication session for the first media event during the communication session, the media of the communication session being the audio, video, or shared content of the communication session; identifying the first media event in the media of the communication session; and in response to identifying the first media event: identifying a second device based on an analysis of the media of the communication session, indicating that the media of the event originated from the second device, the second device being one of a plurality of devices participating in the communication session, the first device and the second device being different; identifying the frequency of corrective actions that have been taken for the second device during the communication session; determining whether to perform the first corrective action based on the frequency and the severity level of the first setting; and in response to determining to perform the first corrective action, performing the first corrective action for the second device, but not performing the first corrective action with respect to other devices of the plurality of devices participating in the communication session.

[0068] In Example 9, the subject matter of Example 8 includes, wherein the operations further include: after the communication session, presenting, on the second device, a prompt indicating a plurality of events triggered by media originating from the second device, the plurality of events including at least one event regarding a second corrective action not being performed due to the frequency of corrective actions taken during the communication session.

[0069] In Example 10, the subject matter of Examples 8-9 includes, wherein the operations further include: before the communication session, providing a report identifying the settings of a plurality of participants in the communication session.

[0070] In Example 11, the subject matter of Example 10 includes, wherein the operations further include: prior to the communication session, scanning a document included in an invitation to the communication session for compatibility issues between media in the document and the settings of the multiple participants in the communication session.

[0071] In Example 12, the subject matter of Examples 8-11 includes, wherein the operations further include: identifying second settings of a second participant in a second participant profile data structure corresponding to the second participant in the communication system, the second participant using a third device in the communication session; selecting a second data structure based on the second settings, the second data structure including a description of a second media event and an associated second corrective action to be taken in response to detecting the second media event, the second media event including an audio element without subtitles; wherein scanning the media of the communication session during the communication session includes scanning both the first media event and the second media event; identifying the second media event in the media of the communication session; and in response to identifying the second media event: performing the second associated corrective action by automatically creating subtitles.

[0072] In Example 13, the subject matter of Examples 8-12 includes, wherein the operations further include: providing a reminder to participants in the communication session during the communication session with the first settings.

[0073] In Example 14, the subject matter of Examples 8-13 includes, wherein the operations further include: calculating the number of media events detected during a plurality of communication sessions of an organization over a specified time period; and providing a report to a computing device describing the number of media events detected during the plurality of communication sessions of the organization.

[0074] Example 15 is a machine-readable medium storing instructions for taking corrective actions in response to events in a communication session of a communication system. The instructions, when executed by a computing device, cause the computing device to perform operations including: identifying a first setting of a participant corresponding to a participant in the communication system, the participant using a first device in the communication session; selecting, based on the first setting, a data structure that includes a description of a first media event, an associated first corrective action to be taken in response to detecting the first media event, and a severity level, the first media event including one or more of: an audio cue for viewing a visual element, a visual element without an associated audio explanation, an audio element without an associated visual description, or a specific description of the participant; scanning the media of the communication session for the first media event during the communication session, the media of the communication session being the audio, video, or shared content of the communication session; identifying the first media event in the media of the communication session; and in response to identifying the first media event: identifying a second device based on an analysis of the media of the communication session, indicating that the media of the event originated from the second device, the second device being one of a plurality of devices participating in the communication session, the first device and the second device being different; identifying the frequency of corrective actions that have been taken for the second device during the communication session; determining whether to perform the first corrective action based on the frequency and the severity level of the first setting; and in response to determining to perform the first corrective action, performing the first corrective action for the second device but not performing the first corrective action with respect to other devices of the plurality of devices participating in the communication session.

[0075] In example 16, the subject matter of example 15 includes, wherein the operations further include: after the communication session, presenting, on the second device, a prompt indicating a plurality of events triggered by media originating from the second device, the plurality of events including at least one event regarding a second corrective action not being performed due to the frequency of the corrective actions taken during the communication session.

[0076] In example 17, the subject matter of examples 15 - 16 includes, wherein the operations further include: before the communication session, providing a report identifying the settings of the plurality of participants in the communication session.

[0077] In example 18, the subject matter of example 17 includes, wherein the operations further include: before the communication session, scanning a document included in an invitation to the communication session for compatibility issues between the media in the document and the settings of the plurality of participants in the communication session.

[0078] In Example 19, the subject matter of Examples 15 - 18 includes, wherein the operations further include: identifying second settings of the second participant in a second participant profile data structure corresponding to the second participant in the communication system, the second participant using a third device in the communication session; selecting a second data structure based on the second settings, the second data structure including a description of a second media event and an associated second corrective action to be taken in response to detecting the second media event, the second media event including an audio element without subtitles; wherein scanning the media of the communication session during the communication session includes scanning both the first media event and the second media event; identifying the second media event in the media of the communication session; and in response to identifying the second media event: performing the second associated corrective action by automatically creating subtitles.

[0079] In Example 20, the subject matter of Examples 15 - 19 includes, wherein the operations further include: providing a reminder to a participant of the communication session during the communication session of the first settings.

[0080] In Example 21, the subject matter of Examples 15 - 20 includes, wherein the operations further include: calculating a number of media events detected during a plurality of communication sessions of an organization over a specified time period; and providing a report to a computing device describing the number of media events detected during the plurality of communication sessions of the organization.

[0081] Example 22 is a device for taking corrective actions in response to events in a communication session of a communication system. The device includes: a unit for identifying a first setting of the participant in a participant profile data structure corresponding to a participant in the communication system, where the participant uses a first device in the communication session; a unit for selecting a data structure based on the first setting, the data structure including a description of a first media event, an associated first corrective action to be taken in response to detecting the first media event, and a severity level, where the first media event includes one or more of the following: an audio cue for viewing a visual element, a visual element without an associated audio explanation, an audio element without an associated visual description, or a specific description of the participant; a unit for scanning the media of the communication session for the first media event during the communication session, where the media of the communication session is the audio, video, or shared content of the communication session; a unit for identifying the first media event in the media of the communication session; and in response to identifying the first media event: a unit for identifying a second device based on an analysis of the media of the communication session, indicating that the media of the event originated from the second device, where the second device is one of a plurality of devices participating in the communication session and is different from the first device; a unit for identifying the frequency of corrective actions taken for the second device during the communication session; a unit for determining whether to execute the first corrective action based on the frequency and the severity level of the first setting; and in response to determining to execute the first corrective action, a unit for executing the first corrective action for the second device but not for other devices among the plurality of devices participating in the communication session.

[0082] In Example 23, the subject matter of Example 22 includes, after the communication session, a unit for presenting a prompt on the second device indicating a plurality of events triggered by media originating from the second device, where the plurality of events includes at least one event regarding a second corrective action not being executed due to the frequency of the corrective actions taken during the communication session.

[0083] In Example 24, the subject matter of Examples 22 - 23 includes a unit for providing a report identifying the settings of a plurality of participants in the communication session before the communication session.

[0084] In Example 25, the subject matter of Example 24 includes, before the communication session, a unit for scanning a document included in an invitation to the communication session for compatibility issues between the media in the document and the settings of the plurality of participants in the communication session.

[0085] In Example 26, the subject matter of Examples 22-25 includes a unit for identifying a second setting of a second participant in a second participant profile data structure corresponding to the second participant in the communication system, the second participant using a third device in the communication session; a unit for selecting a second data structure based on the second setting, the second data structure including a description of a second media event and an associated second corrective action to be taken in response to detecting the second media event, the second media event including an audio element without subtitles; wherein the unit for scanning the media of the communication session during the communication session includes a unit for scanning both the first media event and the second media event; a unit for identifying the second media event in the media of the communication session; and in response to identifying the second media event: a unit for performing the second associated corrective action by automatically creating subtitles.

[0086] In Example 27, the subject matter of Examples 22-26 includes a unit for providing a reminder to a participant in the communication session during the communication session of the first setting.

[0087] In Example 28, the subject matter of Examples 22-27 includes a unit for calculating the number of media events detected during a plurality of communication sessions of an organization over a specified time period; and a unit for providing a report to a computing device describing the number of media events detected during the plurality of communication sessions of the organization.

[0088] Example 29 is at least one machine-readable medium including instructions that, when executed by a processing circuit, cause the processing circuit to perform operations to implement any one of Examples 1-28.

[0089] Example 30 is a device including units for implementing any one of Examples 1-28.

[0090] Example 31 is a system for implementing any one of Examples 1-28.

[0091] Example 32 is a method for implementing any one of Examples 1-28.

Claims

1. A method for taking corrective actions in response to events in a communication session of a communication system, the method comprising: using a hardware processor: identifying a first setting of a participant in a participant profile data structure corresponding to the participant in the communication system, the participant using a first device in the communication session; selecting a data structure based on the first setting, the data structure including a description of a first media event, an associated first corrective action to be taken in response to detecting the first media event, and a severity level, the first media event including one or more of the following: an audio cue for viewing a visual element, a visual element without an associated audio interpretation, an audio element without an associated visual description, or a specific description of the participant; scanning the media of the communication session for the first media event during the communication session, the media of the communication session being the audio, video, or shared content of the communication session; identifying the first media event in the media of the communication session; and in response to identifying the first media event: identifying a second device based on an analysis of the media of the communication session, indicating that the media of the event originated from the second device, the second device being one of a plurality of devices participating in the communication session, the first device and the second device being different; identifying the frequency of corrective actions taken for the second device during the communication session; determining whether to execute the first corrective action based on the frequency and the severity level of the first setting; and in response to determining to execute the first corrective action, executing the first corrective action for the second device, but not executing the first corrective action for other devices among the plurality of devices participating in the communication session.

2. The method according to claim 1, further comprising: after the communication session, presenting a prompt on the second device indicating a plurality of events triggered by the media originating from the second device, the plurality of events including at least one event regarding a second corrective action not being executed due to the frequency of the corrective actions taken during the communication session.

3. The method according to claim 1, further comprising: before the communication session, providing a report identifying the settings of a plurality of participants in the communication session.

4. The method according to claim 3, further comprising: before the communication session, scanning a document included in an invitation to the communication session for compatibility issues between the media in the document and the settings of the plurality of participants in the communication session.

5. The method according to claim 1, further comprising: identifying a second setting of a second participant in a second participant profile data structure corresponding to the second participant in the communication system, the second participant using a third device in the communication session; Select a second data structure based on the second setting, the second data structure including a description of a second media event and an associated second corrective action to be taken in response to detecting the second media event, the second media event including an audio element without subtitles; wherein scanning the media of the communication session during the communication session includes scanning both the first media event and the second media event; identifying the second media event in the media of the communication session; and in response to identifying the second media event: perform the second associated corrective action by automatically creating subtitles.

6. The method according to claim 1, further comprising: providing a reminder to the participants of the communication session during the communication session with the first setting.

7. The method according to claim 1, further comprising: calculating the number of media events detected during a plurality of communication sessions of an organization within a specified time period; and providing a report to a computing device describing the number of media events detected during the plurality of communication sessions of the organization.

8. A computing device for taking corrective actions in response to events in a communication session of a communication system, the computing device comprising: a hardware processor; a memory storing instructions that, when executed by the hardware processor, cause the device to perform operations, the operations including: identifying a first setting of a participant in a participant profile data structure corresponding to a participant in the communication system, the participant using a first device in the communication session; selecting a data structure based on the first setting, the data structure including a description of a first media event, an associated first corrective action to be taken in response to detecting the first media event, and a severity level, the first media event including one or more of: an audio cue for viewing a visual element, a visual element without an associated audio explanation, an audio element without an associated visual description, or a specific description of the participant; scanning the media of the communication session for the first media event during the communication session, the media of the communication session being the audio, video, or shared content of the communication session; identifying the first media event in the media of the communication session; and in response to identifying the first media event: identifying a second device based on an analysis of the media of the communication session, indicating that the media of the event originated from the second device, the second device being one of a plurality of devices participating in the communication session, the first device and the second device being different; identifying the frequency of corrective actions taken for the second device during the communication session; determining whether to perform the first corrective action based on the frequency and the severity level of the first setting; and in response to determining to perform the first corrective action, performing the first corrective action for the second device but not performing the first corrective action with respect to other devices among the plurality of devices participating in the communication session.

9. The computing device according to claim 8, wherein, The operations further include: After the communication session, a prompt indicating a plurality of events triggered due to media originating from the second device is presented on the second device, the plurality of events including at least one event regarding non-execution of a second corrective action due to the frequency of corrective actions taken during the communication session.

10. The computing device according to claim 8, wherein, The operation further includes: Before the communication session, providing a report identifying settings of a plurality of participants in the communication session.

11. The computing device according to claim 10, wherein, The operation further includes: Before the communication session, scanning a document included in an invitation to the communication session for compatibility issues between media in the document and the settings of the plurality of participants in the communication session.

12. The computing device according to claim 8, wherein, The operation further includes: Identifying second settings of a second participant corresponding to a second participant in the communication system, the second participant using a third device in the communication session; Selecting a second data structure based on the second settings, the second data structure including a description of a second media event and an associated second corrective action taken in response to detection of the second media event, the second media event including an audio element without subtitles; wherein scanning the media of the communication session during the communication session includes scanning both the first media event and the second media event; Identifying the second media event in the media of the communication session; and In response to identifying the second media event: Performing the second associated corrective action by automatically creating subtitles.

13. The computing device according to claim 8, wherein, The operation further includes: During the communication session with the first settings, providing a reminder to participants in the communication session.

14. The computing device according to claim 8, wherein, The operation further includes: Calculating the number of media events detected during a plurality of communication sessions of an organization over a specified period of time; and Providing a report to a computing device describing the number of media events detected during the plurality of communication sessions of the organization.

15. A device for taking corrective actions in response to events in a communication session of a communication system, the device comprising: A unit for identifying first settings of a participant in a participant profile data structure corresponding to a participant in the communication system, the participant using a first device in the communication session; A unit for selecting a data structure based on the first settings, the data structure including a description of a first media event, an associated first corrective action taken in response to detection of the first media event, and a severity level, the first media event including one or more of the following: an audio cue for viewing a visual element, a visual element without an associated audio explanation, an audio element without an associated visual description, or a specific description of a participant; A unit for scanning the media of the communication session for the first media event during the communication session, the media of the communication session being the audio, video, or shared content of the communication session; A unit for identifying the first media event in the media of the communication session; and And In response to identifying the first media event: A unit for identifying a second device based on an analysis of the media of the communication session, indicating that the media of the event originates from the second device, the second device being one of a plurality of devices participating in the communication session, the first device and the second device being different; A unit for identifying the frequency of corrective actions taken for the second device during the communication session; A unit for determining whether to perform the first corrective action based on the frequency and the severity level of the first setting; And A unit for, in response to determining to perform the first corrective action, performing the first corrective action for the second device but not performing the first corrective action for other devices among the plurality of devices participating in the communication session.

Images