Abstract: Artificial intelligence (AI) based technologies for improving patient intake are disclosed herein. An example method includes receiving a patient intake request from a user; initiating, based on the patient intake request, a patient intake data stream including verbal responses from the user regarding patient intake of the user; applying, while simultaneously receiving the patient intake data stream, a natural language processing (NLP) model to the verbal responses from the user to output (i) textual transcriptions and (ii) intent interpretations; generating, by a care plan generation module, a recommended care plan based on the textual transcriptions and the intent interpretations; identifying, by an intent interpretation fulfillment module, one or more recipient entities to receive the textual transcriptions and the recommended care plan; and transferring the textual transcriptions and the recommended care plan to one or more recipient entity devices of the one or more recipient entities.

Abstract: Artificial intelligence (AI) based technologies for improving patient appointment scheduling and inventory management are disclosed herein. An example method includes receiving, at a server including a natural language processing (NLP) model, an appointment request from a user. The example method further includes initiating, based on the appointment request, a patient appointment data stream including verbal responses from the user regarding an appointment of the user. The example method further includes applying, while simultaneously receiving the patient appointment data stream, the NLP model to the verbal responses from the user to output (i) textual transcriptions and (ii) intent interpretations. The example method further includes querying a scheduling database to determine a matching appointment that satisfies a distance threshold, a date threshold, a service threshold, and an inventory threshold.

Abstract: A system may include a network communication interface configured to receive network traffic, a processing unit, and a memory unit storing instructions for various engines that are executable by the processing unit. The various engines include a data policy enforcement engine that includes an intent detection engine configured to receive context data and content data relating to the network traffic and generate an intent indexer for the network traffic based on the context data and the content data. The intent indexer documents an operation request and a subject of the operation request that are connected to the network traffic. The various engines also include an intent policy control engine configured to administer aspects of the network traffic based on the intent indexer and the context data.

Abstract: A System may include various engines that are executable by a processing unit. An interception engine is configured to intercept outbound network traffic from a client device. A policy engine is configured to receive the outbound network traffic, parse the outbound network traffic to determine an intended network service, select an approved network service based on the intended network service and contents of the outbound network traffic, generate a destination specific dataset based on the contents of the outbound network traffic and a first data processing schema, transmit the destination specific dataset to the approved network service via a network communication interface, and store network session data in the data storage system. The network session data documents the client device, the approved network service, the intended network service, an indication of the contents of the outbound network traffic, and the destination specific dataset.

Abstract: System and methods use a network service registry to differentiate risks associated with use of respective network services, e.g., artificial intelligence (AI) and/or machine learning (ML) network services that may pose risks to use in an enterprise context based for example upon training, data retention, and/or content moderation policies of the respective network services. Upon a request (e.g., outbound network traffic) to an intended network service, systems and methods may intercept the request, reference the request to the service registry to identify risk identifiers of the intended network service, and select an approved network service(s) for the request (e.g., the same intended network service, and/or a different service). Thus, the systems and methods may mitigate or prevent potentially hazardous use of AI and/or ML network services in an enterprise.

Abstract: Data loss prevention systems and methods in an enterprise data management and monitoring system may intercept a request to a network service, e.g., a service using an artificial intelligence and/or machine learning model. The systems and methods may represent contents of the request via one or more vector embeddings, which may be compared to vector embeddings corresponding to respective ones of a plurality of sensitive data elements in the enterprise. The data loss prevention system and methods may apply various data sensitivity policies based on determinations of whether sensitive data of the enterprise is included in the request to the network service, e.g., by blocking or redacting the request to prevent exposure of the sensitive data to the network service.

Abstract: Techniques for improved prompt engineering are disclosed herein. An example computer-implemented method includes receiving an initial input from a user; determining an intent corresponding to the initial input; providing a set of input requests to the user based on the intent or the initial input; receiving one or more subsequent inputs from the user in response to the set of input requests; applying a prompt generation engine to (i) the intent, (ii) the initial input, and (iii) the one or more subsequent inputs to output an input prompt; transmitting the input prompt to a machine learning model that is configured to output a response to the input prompt; and causing the response to be displayed for viewing by the user.

Abstract: Artificial intelligence (AI) based technologies for improving patient intake are disclosed herein. An example method includes receiving a patient intake request from a user; initiating, based on the patient intake request, a patient intake data stream including verbal responses from the user regarding patient intake of the user; applying, while simultaneously receiving the patient intake data stream, a natural language processing (NLP) model to the verbal responses from the user to output (i) textual transcriptions and (ii) intent interpretations; generating, by a care plan generation module, a recommended care plan based on the textual transcriptions and the intent interpretations; identifying, by an intent interpretation fulfillment module, one or more recipient entities to receive the textual transcriptions and the recommended care plan; and transferring the textual transcriptions and the recommended care plan to one or more recipient entity devices of the one or more recipient entities.

Abstract: Techniques for providing natural language understanding (NLU) services to contact centers are disclosed herein. An example method includes receiving, at a cloud NLU connector, a data stream from a contact center that includes an audio stream, extracting the audio stream from the data stream, and transmitting the audio stream through a secure network to a cloud-based NLU hub. The cloud-based NLU hub is communicatively coupled to a plurality of cloud-based NLU service providers and stores a plurality of user NLU profiles that each designate one or more cloud-based NLU service providers to provide NLU services. The example method further includes determining one or more designated cloud-based NLU service providers to provide at least one NLU service corresponding to the audio stream, and causing the one or more designated cloud-based NLU service providers to process the audio stream in accordance with the at least one NLU service.

Abstract: Artificial intelligence (AI) based technologies for improving patient intake are disclosed herein. An example method includes receiving a patient intake request from a user; initiating, based on the patient intake request, a patient intake data stream including verbal responses from the user regarding patient intake of the user; applying, while simultaneously receiving the patient intake data stream, a natural language processing (NLP) model to the verbal responses from the user to output (i) textual transcriptions and (ii) intent interpretations; generating, by a care plan generation module, a recommended care plan based on the textual transcriptions and the intent interpretations; identifying, by an intent interpretation fulfillment module, one or more recipient entities to receive the textual transcriptions and the recommended care plan; and transferring the textual transcriptions and the recommended care plan to one or more recipient entity devices of the one or more recipient entities.

Abstract: Artificial intelligence (AI) based technologies for improving patient appointment scheduling and inventory management are disclosed herein. An example method includes receiving, at a server including a natural language processing (NLP) model, an appointment request from a user. The example method further includes initiating, based on the appointment request, a patient appointment data stream including verbal responses from the user regarding an appointment of the user. The example method further includes applying, while simultaneously receiving the patient appointment data stream, the NLP model to the verbal responses from the user to output (i) textual transcriptions and (ii) intent interpretations. The example method further includes querying a scheduling database to determine a matching appointment that satisfies a distance threshold, a date threshold, a service threshold, and an inventory threshold.

Abstract: Artificial intelligence (AI) based technologies for improving patient appointment scheduling and inventory management are disclosed herein. An example method includes receiving, at a server including a natural language processing (NLP) model, an appointment request from a user. The example method further includes initiating, based on the appointment request, a patient appointment data stream including verbal responses from the user regarding an appointment of the user. The example method further includes applying, while simultaneously receiving the patient appointment data stream, the NLP model to the verbal responses from the user to output (i) textual transcriptions and (ii) intent interpretations. The example method further includes querying a scheduling database to determine a matching appointment that satisfies a distance threshold, a date threshold, a service threshold, and an inventory threshold.

Abstract: Techniques for providing natural language understanding (NLU) services to contact centers are disclosed herein. An example method includes receiving, at a cloud NLU connector, a data stream from a contact center that includes an audio stream, extracting the audio stream from the data stream, and transmitting the audio stream through a secure network to a cloud-based NLU hub. The cloud-based NLU hub is communicatively coupled to a plurality of cloud-based NLU service providers and stores a plurality of user NLU profiles that each designate one or more cloud-based NLU service providers to provide NLU services. The example method further includes determining one or more designated cloud-based NLU service providers to provide at least one NLU service corresponding to the audio stream, and causing the one or more designated cloud-based NLU service providers to process the audio stream in accordance with the at least one NLU service.

Abstract: Artificial intelligence (Al) based technologies for improving patient appointment scheduling and inventory management are disclosed herein. An example method includes receiving, at a server including a natural language processing (NLP) model, an appointment request from a user. The example method further includes initiating, based on the appointment request, a patient appointment data stream including verbal responses from the user regarding an appointment of the user. The example method further includes applying, while simultaneously receiving the patient appointment data stream, the NLP model to the verbal responses from the user to output (i) textual transcriptions and (ii) intent interpretations. The example method further includes querying a scheduling database to determine a matching appointment that satisfies a distance threshold, a date threshold, a service threshold, and an inventory threshold.

Abstract: Artificial intelligence (AI) based technologies for improving patient intake are disclosed herein. An example method includes receiving a patient intake request from a user; initiating, based on the patient intake request, a patient intake data stream including verbal responses from the user regarding patient intake of the user; applying, while simultaneously receiving the patient intake data stream, a natural language processing (NLP) model to the verbal responses from the user to output (i) textual transcriptions and (ii) intent interpretations; generating, by a care plan generation module, a recommended care plan based on the textual transcriptions and the intent interpretations; identifying, by an intent interpretation fulfillment module, one or more recipient entities to receive the textual transcriptions and the recommended care plan; and transferring the textual transcriptions and the recommended care plan to one or more recipient entity devices of the one or more recipient entities.