An address management method, system, and device to avoid a problem that a same Internet Protocol (IP) address is assigned to different packet data unit (PDU) sessions and to effectively use IP addresses in an address pool. The method includes: obtaining, by a session management network element, an identifier of a user plane function network element serving a terminal and session information of the terminal; determining, by the session management network element based on the identifier of the user plane function network element and the session information, an address pool identifier corresponding to the session; sending, by the session management network element, the address pool identifier to a server, where the address pool identifier is used to assign an IP address to the session; and receiving, by the session management network element from the server, the IP address corresponding to the session.

This application provides methods and apparatuses for communication. In an example method, a first digital reflection (DR) receives a first message, where the first message includes data to be sent to a first terminal device and an identifier of the first terminal device, and the first DR is associated with the first terminal device. The first DR transmits the data to the first terminal device based on a local locator (LLOC) of the first terminal device, where the first DR stores a twin-globally unique temporary identity (TWIN-GUTI) of the first terminal device, the TWIN-GUTI includes the LLOC, the LLOC corresponds to the identifier of the first terminal device, the first DR is deployed on first multi-access edge computing (MEC), and the TWIN-GUTI is generated by the first MEC.

A system, which includes a first device associated with a user, a second device configured to establish a user session and a server, performs storing a default user session setting associated with the user, the default user session setting defining a default user access privilege to functionality or content; determining that the first device is proximate to the second device; receiving a second user input requesting to modify the default user session setting, the second user input including modification data defining a restrictive modification to the default user session setting; modifying, at the server, the default user session setting based on the modification data to create a customized user session setting defining a customized user access privilege to the functionality or content available via the system; and establishing, at the second device, the customized user session for the user based on the customized user setting received from the server.

An approach is disclosed for providing item-to-item recommendations. The approach receives data for an item. The approach generates recommended candidate item data for the data of the received item. The approach generates feature data of the recommended candidate item data and the data of the received item. The feature data may include one or more similarities between the data of the received item and data corresponding to a respective recommended candidate item. The approach generates ranked recommended candidate item data based on the generated feature data and at least one weight determined for candidate test item data. The candidate test item data may include data corresponding to the recommended candidate item data.

Aspects of the present disclosure relate to machine learning techniques for identifying the incremental impact of different past events on the likelihood that a target outcome will occur. The technology can use a recurrent neural network to analyze two different representations of an event sequence—one in which some particular event occurs, and another in which that particular event does not occur. The incremental impact of that particular event can be determined based on the calculated difference between the probabilities of the target outcome occurring after these two sequences.

A user equipment (UE) may transmit, using a first radio access technology (RAT), a service request message including information associated with at least one UE service. Based on the transmitted service request message, a message with information to setup a bearer for a second RAT, wherein the second RAT is a different RAT than the first RAT. The UE may receive multimedia data using the second RAT and simultaneously receive data using the first RAT.

A user equipment (UE) may transmit, using a first radio access technology (RAT), a service request message including information associated with at least one UE service. Based on the transmitted service request message, a message with information to setup a bearer for a second RAT, wherein the second RAT is a different RAT than the first RAT. The UE may receive multimedia data using the second RAT and simultaneously receive data using the first RAT.

Methods for providing enhanced services to users participating in communication sessions (CS), via a virtual assistant, are disclosed. One method receives content that is exchanged by users participating in the CS. The content includes natural language expressions that encode a conversation carried out by users. The method determines content features based on natural language models. The content features indicate intended semantics of the natural language expressions. The method determines a relevance of the content and identifies portions of the content that are likely relevant to the user. Determining the relevance is based on the content features, a context of the CS, a user-interest model, and a content-relevance model of the natural language models. Identifying the likely relevant content is based on the determined relevance of the content and a relevance threshold. A summary of the CS is automatically generated from summarized versions of the likely relevant portions of the content.

Methods for providing enhanced services to users participating in communication sessions (CS), via a virtual assistant, are disclosed. One method receives content that is exchanged by users participating in the CS. The content includes natural language expressions that encode a conversation carried out by users. The method determines content features based on natural language models. The content features indicate intended semantics of the natural language expressions. The method determines a relevance of the content and identifies portions of the content that are likely relevant to the user. Determining the relevance is based on the content features, a context of the CS, a user-interest model, and a content-relevance model of the natural language models. Identifying the likely relevant content is based on the determined relevance of the content and a relevance threshold. A summary of the CS is automatically generated from summarized versions of the likely relevant portions of the content.

The present invention discloses methods and systems for sending and receiving IP packets between network nodes through a tunnel. The tunnel is created according to a session. When the IP packet is a first of the IP packets in sequence of a session, establish a tunnel and send the IP packet through the tunnel of the session. When the IP packet is not the first of the IP packets in sequence of a session, sending the IP packet through the tunnel of the session.