Abstract: Techniques are disclosed to generate relevant responses for requests received in a connected environment. A user communicating with the connected environment may request, in natural language, an operation to be performed. The request may be augmented with the information related to the requesting user to generate an augmented query. The augmented query may be processed by a large language model to generate a response to the augmented query. The response is returned in natural language.

Abstract: Systems, devices, and methods for blockchain abstraction are provided. Via use of the exemplary systems and methods, transactions between one or more blockchains and one or more off-chain systems are made faster and simpler.

Abstract: A method for associating a meeting invitation with a team includes receiving a meeting invitation from an email system comprising names of invitees and receiving team information from a team system comprising names of team members and team topics. Using a trained machine learning model, a match metric representing similarity between teams and the meeting invitation is calculated. Calculating the match metric includes determining an attendee score based on invitees who are team members and a topic score based on comparison between a meeting topic and team topics. The match metric is based on the attendee score and topic score. The trained machine learning model uses names of invitees, names of team members, and team topics. The method further includes adding to the meeting invitation a link to the team with the highest match metric.

Abstract: Techniques are disclosed to generate relevant responses for requests received in a connected environment. A user communicating with the connected environment may request, in natural language, an operation to be performed. The request may be augmented with the information related to the requesting user to generate an augmented query. The augmented query may be processed by a large language model to generate a response to the augmented query. The response is returned in natural language.

Abstract: Techniques are disclosed to generate relevant responses for requests received in a connected environment. A user communicating with the connected environment may request, in natural language, an operation to be performed. The request may be augmented with the information related to the requesting user to generate an augmented query. The augmented query may be processed by a large language model to generate a response to the augmented query. The response is returned in natural language.

Abstract: The present disclosure is directed techniques for executing a task or service using a virtual agent. A method includes: executing, using a virtual agent, one or more tiers of a plurality of tiers of machine learning analysis to identify a desired action to be performed based on a user command, the user command being received from an external computing device; responsive to the one or more tiers of the plurality of tiers of machine learning analysis identifying a plurality of actions associated with the user command, determining a series of inquiries to present via the external computing device, wherein each inquiry of the series of inquiries is selected based on a number of actions associated with each inquiry, and wherein each subsequent inquiry in the series of inquires is based on a user response to a preceding inquiry; identifying, based on responses to the series of inquiries, the desired action to be performed; and executing the desired action to be performed.

Abstract: A multi-tenant system performs custom configuration of a tenant-specific chatbot to process and act upon natural language requests. The multi-tenant system configures the tenant-specific chatbots without requiring tenant-specific training. The multi-tenant system providing a user interface for configuring a tenant-specific set of permitted actions. The multi-tenant system determines a set of example phrases for each of the selected permitted actions. The multi-tenant system receives a natural language request from a user and identifies the action that the user wants to perform. The multi-tenant system uses a neural network to compare the natural language request with example phrases to identify an example phrase that matches the natural language request. The multi-tenant system performs the action corresponding to the matching example phrase.

Abstract: A method for associating a team with a meeting for prospective meeting attendees includes training a machine-learning algorithm to determine a match metric between a group of meeting attendees and a plurality of teams; in response to receiving a meeting invitation for a meeting, determining, by the processor, using the trained machine-learning algorithm, a match metric for each of the plurality of teams in a team system; in response to determining that the match metric for each of the plurality of teams is below a threshold value, creating, by the processor, a new team; associating, by the processor, the new team with the meeting for prospective meeting attendees; and sending, to the prospective meeting attendees, a link to the new team.

Abstract: A method for associating a team with a meeting for prospective meeting includes receiving a meeting invitation comprising first information, wherein the first information comprises data identifying the prospective meeting attendees, receiving second information for a plurality of teams, wherein the second information comprises data identifying members for each one of the plurality of teams, comparing the first information with the second information to determine a match metric for each one of the plurality of teams, and determining a matching team from the plurality of teams for which the match metric is above a match threshold value. The method further includes, in response to determining that the match metric is below the match threshold value computed for each one of the plurality of teams, creating a new team, and associating one of the matching team or the new team with the meeting for prospective meeting attendees.

Abstract: Approaches to using unstructured input to update heterogeneous data stores include receiving unstructured text input, receiving a template for interpreting the unstructured text input, identifying, using an entity classifier, entities in the unstructured text input, identifying one or more potential parent entities from the identified entities based on the template, receiving a selection of a parent entity from the one or more potential parent entities, identifying one or more potential child entities from the identified entities based on the template and the selected parent entity, receiving a selection of a child entity from the one or more potential child entities, identifying an action item in the unstructured text input based on the identified entities and the template, determining, using an intent classifier, an intent of the action item, and updating a data store based on the determined intent, the identified entities, and the selected child entity.

Abstract: A method for natural language processing includes receiving, by one or more processors, an unstructured text input. An entity classifier is used to identify entities in the unstructured text input. The identifying the entities includes generating, using a plurality of sub-classifiers of a hierarchical neural network classifier of the entity classifier, a plurality of lower-level entity identifications associated with the unstructured text input. The identifying the entities further includes generating, using a combiner of the hierarchical neural network classifier, a plurality of higher-level entity identifications associated with the unstructured text input based on the plurality of lower-level entity identifications. Identified entities are provided based on the plurality of higher-level entity identifications.

Abstract: The present disclosure is directed techniques for executing a task or service using a virtual agent.

Abstract: The present disclosure is directed techniques for executing a task or service using a virtual agent. A method includes: defining a plurality of intents; conducting a first tier of machine learning analysis to compare a received input string with a first subset of training phrases associated with the plurality of intents to extract one or more parameters of the received input string; conducting a second tier of machine learning analysis to compare an output of the first tier of machine learning analysis with a second subset of training phrases associated with the plurality of intents, wherein the comparison is used to generate respective similarity scores indicating whether the received input string matches one or more of the second subset of training phrases; selecting an intent from among the plurality of intents based on the respective similarity scores; and executing an action associated with the selected intent.

Abstract: A method for associating a team with a meeting for prospective meeting includes receiving a meeting invitation comprising first information, wherein the first information comprises data identifying the prospective meeting attendees, receiving second information for a plurality of teams, wherein the second information comprises data identifying members for each one of the plurality of teams, comparing the first information with the second information to determine a match metric for each one of the plurality of teams, and determining a matching team from the plurality of teams for which the match metric is above a match threshold value. The method further includes, in response to determining that the match metric is below the match threshold value computed for each one of the plurality of teams, creating a new team, and associating one of the matching team or the new team with the meeting for prospective meeting attendees.

Abstract: Described herein is a method, system, and non-transitory computer readable medium for updating fields in records. Initially, fields are displayed according to how frequently the fields are updated. One of the fields is selected and then records of a record type including the selected field are displayed. One of the records is selected and a form is displayed that enables a user to update the value stored in the selected field of the selected record.

Abstract: Approaches to using unstructured input to update heterogeneous data stores include receiving unstructured text input, receiving a template for interpreting the unstructured text input, identifying, using an entity classifier, entities in the unstructured text input, identifying one or more potential parent entities from the identified entities based on the template, receiving a selection of a parent entity from the one or more potential parent entities, identifying one or more potential child entities from the identified entities based on the template and the selected parent entity, receiving a selection of a child entity from the one or more potential child entities, identifying an action item in the unstructured text input based on the identified entities and the template, determining, using an intent classifier, an intent of the action item, and updating a data store based on the determined intent, the identified entities, and the selected child entity.

Abstract: A multi-tenant system performs custom configuration of a tenant-specific chatbot to process and act upon natural language requests. The multi-tenant system configures the tenant-specific chatbots without requiring tenant-specific training. The multi-tenant system providing a user interface for configuring a tenant-specific set of permitted actions. The multi-tenant system determines a set of example phrases for each of the selected permitted actions. The multi-tenant system receives a natural language request from a user and identifies the action that the user wants to perform. The multi-tenant system uses a neural network to compare the natural language request with example phrases to identify an example phrase that matches the natural language request. The multi-tenant system performs the action corresponding to the matching example phrase.

Abstract: Approaches to using unstructured input to update heterogeneous data stores include receiving unstructured text input, receiving a template for interpreting the unstructured text input, identifying, using an entity classifier, entities in the unstructured text input, identifying one or more potential parent entities from the identified entities based on the template, receiving a selection of a parent entity from the one or more potential parent entities, identifying one or more potential child entities from the identified entities based on the template and the selected parent entity, receiving a selection of a child entity from the one or more potential child entities, identifying an action item in the unstructured text input based on the identified entities and the template, determining, using an intent classifier, an intent of the action item, and updating a data store based on the determined intent, the identified entities, and the selected child entity.

Abstract: A method for natural language processing includes receiving, by one or more processors, an unstructured text input. An entity classifier is used to identify entities in the unstructured text input. The identifying the entities includes generating, using a plurality of sub-classifiers of a hierarchical neural network classifier of the entity classifier, a plurality of lower-level entity identifications associated with the unstructured text input. The identifying the entities further includes generating, using a combiner of the hierarchical neural network classifier, a plurality of higher-level entity identifications associated with the unstructured text input based on the plurality of lower-level entity identifications. Identified entities are provided based on the plurality of higher-level entity identifications.

Abstract: Approaches to using unstructured input to update heterogeneous data stores include receiving unstructured text input, receiving a template for interpreting the unstructured text input, identifying, using an entity classifier, entities in the unstructured text input, identifying one or more potential parent entities from the identified entities based on the template, receiving a selection of a parent entity from the one or more potential parent entities, identifying one or more potential child entities from the identified entities based on the template and the selected parent entity, receiving a selection of a child entity from the one or more potential child entities, identifying an action item in the unstructured text input based on the identified entities and the template, determining, using an intent classifier, an intent of the action item, and updating a data store based on the determined intent, the identified entities, and the selected child entity.