Abstract: The present disclosure relates generally to facilitating two-way communications. One example involves receiving input data as part of a two-way communication session associated with a plurality of bots, accessing confidence scores from the bots. Mapped scores are then generated for the plurality of bots from the confidence scores using a bot score mapper. A selected bot is identified using the mapped scores, and the two-way communication session is facilitated using the selected bot. Further, techniques are provided to track performance of the selected bot and dynamically updated mapping adjustments in the bot score mapper using feedback and machine learning systems.

Abstract: Disclosed embodiments provide a framework to assist bot managers and builders in identifying particular friction points between bots and customers to allow for real-time identification of bot conversation issues and to train bots to improve conversation flows. Conversation data is processed using machine learning models to detect bot states within conversations and calculate a Meaningful Automated Connection Score (MACS) for these conversations. The MACS for a conversation is provided to bot builders to allow the bot builders to identify friction points and update bots accordingly.

Abstract: The present disclosure relates generally to systems and methods for analyzing intent. Intents may be analyzed to determine to which device or agent to route a communication. The analyzed intent information can also be used to formulate reports and analyze the accuracy of the identified intents with respect to the received communication.

Abstract: A cyber defense system using models that are trained on a normal behavior of email activity and user activity associated with an email system. A cyber-threat module may reference the models that are trained on the normal behavior of email activity and user activity. A determination is made of a threat risk parameter that factors in the likelihood that a chain of one or more unusual behaviors of the email activity and user activity under analysis fall outside of a derived normal benign behavior. An autonomous response module can be used, rather than a human taking an action, to cause one or more autonomous rapid actions to be taken to contain the cyber-threat when the threat risk parameter from the cyber-threat module is equal to or above an actionable threshold.

Abstract: A cyber-threat defense system for a network including its email domain protects this network from cyber threats. Modules utilize machine learning models as well communicate with a cyber threat module. Modules analyze the wide range of metadata from the observed email communications. The cyber threat module analyzes with the machine learning models trained on a normal behavior of email activity and user activity associated with the network and in its email domain in order to determine when a deviation from the normal behavior of email activity and user activity is occurring. A mass email association detector determines a similarity between highly similar emails being i) sent from or ii) received by a collection of two or more individual users in the email domain in a substantially simultaneous time frame. Mathematical models can be used to determine similarity weighing in order to derive a similarity score between compared emails.

Abstract: In accordance with one embodiment of the invention, a method coordinates experiences of a realm for a group of users, including at least an administrative user and at least one participating user. The method includes transmitting, from the server to an administrative user, a session identifier associated with the realm. The method also includes receiving, by the server, a user acceptance to join a session using the session identifier so that the at least one participating user can experience the realm. In response to receiving the acceptance, the method also includes transmitting to a computing device of the participating user, by the server, executable code including data describing a series of locations in the realm. The series of locations comprises at least a first location and a second location, and the first location is associated with a first panoramic image and the second location is associated with a second panoramic image.

Abstract: Systems, methods, devices, instructions, and other examples are described for natural language processing. One example includes accessing natural language processing general encoder data, where the encoder data is generated from a general-domain dataset that is not domain specific. A domain specific dataset is accessed and filtered encoder data using a subset of the encoder data is generated. The filtered encoder data is trained using the domain specific dataset to generate distilled encoder data, and tuning values for the distilled encoder data are generated to configure task outputs associated with the domain specific dataset.

Abstract: A cyber security appliance has modules that utilize probes to interact with entities in a cloud infrastructure environment (CIE). A cloud module can 1) use the information about relevant changes in the CIE fed from the probes, and 2) use machine learning models that are trained on a normal behavior of at least a first entity associated with the CIE; and thus, indicate when a behavior of the first entity falls outside of being a normal pattern of life. A cyber threat module can use machine learning models trained on cyber threats in the CIE and examine at least the behaviors of the first entity falling outside of the normal pattern of life to determine what is a likelihood of ‘a chain of unusual behaviors under analysis that fall outside of being the normal behavior’ is a cyber threat. An autonomous response module can cause actions to contain the cyber threat.

Abstract: A cyber-threat coordinator-component identifies devices and/or users that are in a breach state of a benchmark of parameters, utilized by AI models, that correspond to the normal pattern of life for the network. The cyber-threat coordinator-component sends an external communication to selected network devices in order to initiate actions with that network device in order to change a behavior of a detected threat of at least one a user and/or a device acting abnormal to the normal pattern of life on the network. The initiated actions are also targeted to minimize an impact on other network devices and users that are i) currently active in the network and ii) that are not in breach of being outside the normal behavior benchmark.

Abstract: An intent confusion evaluation engine receives conversation data corresponding to conversations between customers and agents. The engine evaluates annotations in the conversation data corresponding to intents identified from messages exchanged between customers and agents to determine levels of confusion amongst different intents. Based on these levels of confusion, the engine creates a graphical representation that illustrates the various intents and the level of confusion between different pairings of intents for the set of conversations. If an update is provided to the annotations, the graphical representation is updated dynamically and in real-time to provide updated levels of confusion amongst the various intents in accordance with the update.

Abstract: Disclosed embodiments provide a framework for intent discovery based on user input and execution of processes based on the discovered intents. An intent processing system provides, via an interface, a graphical representation of different intent clusters corresponding to different intents. An intent cluster includes a set of intent terms and/or phrases that can be used to submit a request or issue that is associated with an intent. As a user selects intent terms and/or phrases from an intent cluster via the interface, the intent processing system can identify actions that can be performed to address the user's request or issue.

Abstract: Disclosed embodiments provide a framework to assist bot managers and builders in identifying particular friction points between bots and customers to allow for real-time identification of bot conversation issues and to train bots to improve conversation flows. Conversation data is processed using machine learning models to detect bot states within conversations and calculate a Meaningful Automated Connection Score (MACS) for these conversations. The MACS for a conversation is provided to bot builders to allow the bot builders to identify friction points and update bots accordingly.

Abstract: The present disclosure relates generally to facilitating two-way communications. One example involves receiving input data as part of a two-way communication session associated with a plurality of bots, accessing confidence scores from the bots. Mapped scores are then generated for the plurality of bots from the confidence scores using a bot score mapper. A selected bot is identified using the mapped scores, and the two-way communication session is facilitated using the selected bot. Further, techniques are provided to track performance of the selected bot and dynamically updated mapping adjustments in the bot score mapper using feedback and machine learning systems.

Abstract: A cyber-threat defense system for a network including its email domain protects this network from cyber threats. Modules utilize machine learning models as well communicate with a cyber threat module. Modules analyze the wide range of metadata from the observed email communications. The cyber threat module analyzes with the machine learning models trained on a normal behavior of email activity and user activity associated with the network and in its email domain in order to determine when a deviation from the normal behavior of email activity and user activity is occurring. A mass email association detector determines a similarity between highly similar emails being i) sent from or ii) received by a collection of two or more individual users in the email domain in a substantially simultaneous time frame. Mathematical models can be used to determine similarity weighing in order to derive a similarity score between compared emails.

Abstract: The present disclosure relates generally to systems and methods for analyzing intent. Intents may be analyzed to determine to which device or agent to route a communication. The analyzed intent information can also be used to formulate reports and analyze the accuracy of the identified intents with respect to the received communication.

Abstract: Systems, methods, devices, instructions, and other examples are described for natural language processing. One example includes accessing natural language processing general encoder data, where the encoder data is generated from a general-domain dataset that is not domain specific. A domain specific dataset is accessed and filtered encoder data using a subset of the encoder data is generated. The filtered encoder data is trained using the domain specific dataset to generate distilled encoder data, and tuning values for the distilled encoder data are generated to configure task outputs associated with the domain specific dataset.

Abstract: The present disclosure relates generally to facilitating two-way communications. One example involves receiving input data as part of a two-way communication session associated with a plurality of bots, accessing confidence scores from the bots. Mapped scores are then generated for the plurality of bots from the confidence scores using a bot score mapper. A selected bot is identified using the mapped scores, and the two-way communication session is facilitated using the selected bot. Further, techniques are provided to track performance of the selected bot and dynamically updated mapping adjustments in the bot score mapper using feedback and machine learning systems.

Abstract: Disclosed embodiments provide a framework to assist bot managers and builders in identifying particular friction points between bots and customers to allow for real-time identification of bot conversation issues and to train bots to improve conversation flows. Conversation data is processed using machine learning models to detect bot states within conversations and calculate a Meaningful Automated Connection Score (MACS) for these conversations. The MACS for a conversation is provided to bot builders to allow the bot builders to identify friction points and update bots accordingly.

Abstract: A tracking system passively tracks and records searches conducted by actual search engine users. The recorded data for each search event preferably includes the search query submitted, the search engine used, the search result item (e.g., web page) selected, the position (e.g., page number) of this item, and the user's IP address. The collected data is aggregated and analyzed to generate data regarding the search queries used to locate and access particular destinations (e.g., web pages and sites). This data may be used for various purposes, such as (1) to generate reports showing, e.g., how users reach a particular destination from different search engines and geographic locations, (2) to select content to display on a destination page, such that the content is relevant to search queries commonly used to locate that page, and (3) to update the database of one search engine to reflect searches conducted on other search engines.

Abstract: The present disclosure relates generally to providing an intent-driven contact center. The contact center according to some embodiments analyzes intents to determine to which device or agent to route a communication. The analyzed intent information can also be used to formulate reports and analyze the accuracy of the identified intents with respect to the received communication.