4425 results about "User device" patented technology

The present disclosure is directed to enabling asynchronous analytics via an intercept device. The intercept device may intercept a request transmitted by a user device to a host server, the request indicating data of interest to be provided by the host server in a response; transmit the request to the host server; asynchronously extract analytic data from the request; transmit the analytic data to an analytics server for performance of analytics on the analytic data; receive, from the analytics server, a result of performance of the analytics on the analytic data; determine, based at least in part on analyzing the result, whether the response from the host server is to be modified; selectively effect modification of the response based at least in part on determining whether the response from the host server is to be modified; and transmit the response to the user device. Various other aspects are contemplated.

A method for facilitating conversational interaction with users to help the users includes transmitting a conversational interaction interface for conversationally interacting with a user to a user device, receiving a request of the user through the conversational interaction interface from the user device, identifying an information based on the request, generating an input comprising the request and the information for a machine learning model based on the request and the information, processing the input using the machine learning model, generating a response for the request based on the processing of the input, transmitting the response through the conversational interaction interface for conversationally interacting with the user to the user device, and storing the machine learning model, the request, and the response.

Systems and methods for generating industry-specific solutions using collaborative Artificial Intelligence (AI) agents are disclosed. In an aspect, input data corresponding to an industry-specific problem is received. A goal context for the industry-specific problem is then identified. Further, an industry-specific process workflow corresponding to the industry-specific problem is selected based on the goal context. Furthermore, an agentic context, historical intelligence data, group dynamics data for agent compatibility, appropriate agent character data, and historical user feedback data corresponding to the industry-specific workflow are retrieved. Moreover, AI agents and agent compatibility rules to execute user goals are selected and the rules are assigned to each AI agent. An agentic process workflow for the industry-specific problem is then generated. A candidate solution is then generated by executing the generated agentic process workflow. The candidate solution, agentic process workflow and agent compatibility rules are then outputted on a user interface of a user device.

A method of automatic pre-prompt generation includes receiving at least one user preference from a user device, modifying a system prompt for a machine-learning language model based on the received at least one user preference to generate a modified system prompt, providing the modified system prompt as an initial input to the machine-learning language model, receiving a natural-language text prompt provided by the user to a chat application on the user device, receiving a user identifier from the user device, querying a first database with the user identifier to retrieve first information, generating a representation of the first information and the natural-language prompt, querying a second database using the representation to retrieve second information, and generating a modified text prompt based on the natural-language prompt, the first information, and the second information.

Systems and methods are described for enabling asynchronous experience sharing between users visiting the same environment at two different times. First image data is received, captured during a first time period, wherein the first image data comprises data characterizing the environment in three dimensions. Stored second image data is accessed, the stored second image data captured during a second time period earlier than the first time period, the stored second image data characterizing the environment in three dimensions. A display image is caused to be rendered at a user device during the first time period based on the first image data, the display image comprising an object from the second image data.

A first neural network (NN) model may generate labels for training a second NN model. The second NN model may represent instances of a NN model operating on multiple different devices (e.g., decentralized user and / or edge devices). The system may include using a “teacher” model to process data received by one or more of the devices to generate a labeled dataset. The system may use the labeled dataset and a “student” model to calculate gradient data for updating the student model. The student model may be the same or similar to NN model instances operating on the devices. The system may validate the updated student model to determine, for example, whether it exhibits improved performance when processing the newly received data and / or historical data. The system may distribute the validated update to the devices.

A server computer may receive an authentication data packet including authentication data from a relying party computer in communication with an authenticator associated with a user device. The server computer may verify the authentication data in the authentication data packet. The server computer may store the authentication data packet in a database. The server computer may transmit to an authorizing entity computer, a data packet including data relating to the verification of the authentication data.

Disclosed herein, is a method and system for selecting a LLM for response generation to user queries. The method includes receiving a user query from a user device. The method includes determining, for the user query, a query type from a set of query types through a fine-tuned text classification model. The method includes retrieving a plurality of document embeddings based on the user query and the query type from a vector database through a semantic search technique. The method includes preparing a prompt using the user query and the plurality of document embeddings. The method includes inputting the prompt to an LLM selected from a set of LLMs based on the query type. The method includes generating, via the selected LLM, a response to the user query based on the prompt.

Systems and methods for performing zero knowledge proofs to prove a user's possession of secret data and / or biometric data without exposing such data. The methods can include receiving a certificate signing request and biometric data associated with a user; creating a stable key based at least in part on the biometric data; creating a private key based at least in part on the stable key; transmitting the private key to the user device for local storage thereon; creating a public key based at least in part on the private key; and forwarding the certificate signing request to an issuer.

An apparatus, including a computer including a database which stores a controllable healthcare record and information contained in a master records file, and a distributed ledger and Blockchain technology system. The apparatus facilitates a video call between a user device and a provider device. The computer, after processing information for updating the controllable healthcare record, processes information for identifying a plurality of electronic records for the individual and a second healthcare provider associated with each electronic record. The computer updates each of the plurality of electronic records, and generates a record update message. The computer transmits the record update message to each of a plurality of second provider devices associated with each second healthcare provider. Information regarding the update to the controllable healthcare record and the update to each of the second records is stored in the distributed ledger and Blockchain technology system.

A method of automatic pre-prompt generation includes receiving, by a user device, an indication of at least one user preference, where the at least one user preference indicative of at least one first characteristic preferred by a user of natural-language outputs generated by a machine-learning language model. The method further includes, by a server, receiving a natural-language text prompt provided by the user, receiving the at least one user preference from the user device, modifying a system prompt based on the received at least one user preference and the at least one first operator preference, providing the modified system prompt as an initial input to the machine-learning language model, providing the natural-language text prompt as an input to the machine-learning language model to generate a natural-language text output after providing the modified system prompt, and transmitting the natural-language text output to the user device.

Determining user types from behavior is described. An artificial intelligence (AI) model is trained to classify user accounts of a payment service into different user types using contextual data associated with processed payments between the user accounts. The AI model is used to analyze additional contextual data associated with additional payments between additional user accounts to classify the additional user accounts, and, if a particular user account of the additional user accounts is associated with a user type of the different user types that requires an action to be performed, an instruction is sent to a user device associated with the particular user account to cause a payment application to present a user interface element prompting a user to perform the action, and, based on whether the action was performed, account data indicating whether the particular user account is an authorized account is stored in a datastore.

Embodiments provide a user device, UE, of a wireless communication network, the wireless communication network using one or more Artificial Intelligence / Machine Learning, AI / ML, models for one or more use cases, wherein the UE is configured or preconfigured with a plurality of AI / ML models for performing one or more certain operations, and wherein, dependent on one or more criteria, for performing the one or more certain operations, the UE is toswitch from a first AI / ML model to a second AI / ML model, ordeactivate one or more of the plurality of AI / ML models, orswitch from a current operation mode to a new operation mode.

A system for micro-segmented networking is provided. A system controller is programmed to a) store a plurality of micro-segmented network accounts and a plurality of subscriber accounts, b) receive a request from a user device to activate a first micro-segmented network associated with a first subscriber account, c) authenticate the first subscriber account based on the subscriber information, d) activate the first micro-segmented network, including a plurality of device slots for a plurality of devices, e) transmit, to the user device, first device slot authentication information for a first device slot of the plurality of device slots; f) receive, from a first device connecting to the wireless network, the first device slot authentication information; g) authenticate the first device slot authentication information; and h) in response to authenticating the first device slot authentication information, connect the first device to the first micro-segmented network.

A method includes receiving, at a server from a user device, a user prompt to a large language model (LLM). The user prompt is segmented to generate a set of user segments. An encoding model generates the set of user segments into a set of user vectors. The method further includes scoring each user vector of the set of user vectors based on a comparison between the user vector and a set of stored vectors in a vector store to generate a set of user vector scores, detecting whether the user prompt is malicious according to the set of user vector scores, and setting a prompt injection signal based on whether the user prompt is detected as malicious according to the set of user vector scores.

A computer-implemented method for computational textual search to find and display search identified information in documents. Search queries are processed over one or more documents either at a server or user device using match schemes that produce both binary (match or no match) and non-binary (i.e. multiple matching values) results and have relative fuzziness relationships. A fuzzier match scheme implies more results and fewer false negatives and a less fuzzy match scheme implies fewer results and fewer false positives. This fuzziness relationship allows, without changing a search string, for users to quickly change from a match scheme to a fuzzier or less fuzzy match scheme depending on user evaluation of results as containing too many false negatives or too many false positives—without becoming a programmer of complex search string metadata or an expert user of advanced search capabilities.

Systems and methods involving various registration and authentication workflows are disclosed herein. A user may be authenticated without the use of static usernames or passwords. In some embodiments, an authentication identifier may be generated that is associated with an authentication request for a user to access a protected resource (e.g., a web app). An authentication code may be generated based on the authentication identifier. The authentication code may be sent to a computing device to be provided to the user, who may provide the authentication code to an application on their mobile device. The mobile device may send a payload containing the authentication identifier, credentials saved on the user device from a previous registration step, and a digital signature. The digital signature may be authenticated using contents of the payload before validating the authentication identifier.

Systems and methods described herein provide a document processing service using customizable schemas. First user input includes a document and second user input identifies a classification schema. The classification schema is retrieved to obtain first prompt content. Prompt data is generated. The prompt data includes the first prompt content and second prompt content that includes a document classification instruction. The prompt data and document content of the document are processed by a large language model to obtain a classification result for the document. The classification result is presented via a user interface at a user device.

Described is a system for a generative model XR Experience using open prompt by receiving a first prompt of a first user via a user interface of a user device indicating a user's intent, processing the first prompt using a first machine learning model to generate a second prompt that is applied to a second machine learning model, the second prompt indicative of attributes associated with the first prompt, capturing an image of the first user via a camera feed of the user device, processing a combination of the image of the first user with the second prompt using the second machine learning model to generate a plurality of images, and applying the plurality of images to the live camera feed of the user device.

The present disclosure relates to a method of enrolling an individual at a secure server and subsequently authenticating and identifying the individual at an authenticating party using an authentication token created during the enrolment and a secure server performing the method. The method comprises engaging, via a user device, in an enrolment process with the individual, registering the user device by receiving a public key, the public key being created by the user device along with a private key corresponding to the public key, acquiring a trusted identifier of the individual, associating the acquired trusted identifier of the individual with at least one database index to create an authentication token, the database index being utilized for look-up at the secure server, signing the authentication token, and sending the signed authentication token to the user device, while deleting the acquired trusted identifier at the secure server.

An apparatus comprises a memory communicatively coupled to a processor. The memory is configured to store network interchange parameters and user profiles. The processor is configured to receive a data exchange request triggered by a user device. Further, the processor is configured to request, to a decentralized network, a token indicating that a user profile associated with the user device is entitled to access an entitlement, determine whether a data exchange network is available to exchange data in accordance with the network interchange parameters, identify a second data exchange network that is available in accordance with second network interchange parameters in response to determine that the data exchange network is unavailable, and request a data exchange output from the second data exchange network via the token. The processor is configured to receive the data exchange output from the second data exchange network.

Methods, systems and apparatus, for an unmanned aerial vehicle electromagnetic avoidance and utilization system. One of the methods includes obtaining a flight package indicating a flight pattern associated with inspecting a structure, the flight pattern causing the UAV to remain at a standoff distance from the structure, wherein the standoff distance is based on an electromagnetic field associated with the structure, and wherein the flight pattern is laterally constrained according to a property geofence associated with a right of way of the structure. The UAV is navigated according to the flight pattern, and the UAV captures images of the structure. For an initial portion of the flight pattern, the UAV navigates at an altitude based on the standoff distance and the property geofence towards the structure. The UAV determines a location at which to capture images of the structure, and the UAV provides the captured images to a user device.

The disclosed embodiments describe systems and methods for approving a transfer. User information may be accessed for a plurality of users in a group. Account information for a plurality of disparate electronic accounts associated with the group may be accessed. The disparate electronic accounts may be integrated and managed through a central entitlements engine. Permissions information associated with the user information and the account information may be accessed. A transfer request for an account in the plurality of disparate electronic accounts may be received from a first user device associated with a first user of the plurality of users. The transfer request may be sent to a second user device associated with a second user of the plurality of users. An electronic indication of an approval of the transfer request may be received. The permissions information may be modifiable by input from the second user device.

Mechanisms are provided for dynamically implementing reactive actions in edge nodes of a network in response to user equipment (UE) behaviors. Data of UE events are collected to infer UE movements and UE behavior within the network. A machine learning computer model is executed on the collected data of UE events to predict UE movements and UE behavior and their impact on edge node conditions within the network with regard to quality of service (QoS) metrics. An accuracy of the precited impacts of the predicted UE movements and UE behavior is evaluated and, based on the accuracy, reactive action(s) to execute to reduce the predicted impact of inaccurate predictions on edge node conditions with regard to the QoS metrics are determined and recommended to a control plane of the network for implementation of at least one of the one or more reactive actions on edge node(s) of the network.

Disclosed is a system and method for grounded query generation over heterogeneous data sources. The method includes receiving a user input corresponding to a user requirement from at least one user, extracting a plurality of sub-models corresponding to the received user input, creating a context of the received user input based on the extracted plurality of sub-models, generating an executable query in a specific query language based on the context using a Large Language Model (LLM) by processing the context and the user input within a structured prompt, validating the generated executable query using a multi-stage validation process, generating an LLM response for the received user input based on results of the validation, and outputting the generated LLM response on a user interface of a user device.

A system and a method for responding to an outage of a computing system use a sidecar computing system and an event manager. The computing system is operatively connected to multiple user devices by a first network. The sidecar computing system includes a processor, a non-transitory storage device and multiple virtual machines, wherein computer-readable instructions are stored in the storage device. A second network operatively connected to the sidecar computing system and the sidecar computing system is deactivated when the computing system is operating. The event manager communicates with the computing system through the first network and the sidecar computing system through the second computer network, wherein the event manager activates the sidecar computing system to operate in an outage mode when the computing system has an outage.

Systems and methods for processing artificial intelligence user requests including receiving a user input from a user device, performing a routing analysis on the user input on multiple characteristics, making a routing decision based on the routing analysis to send the user input to one or both of an experiential reasoning agent model and an analytical reasoning model, routing the user input to at least one of the experiential reasoning agent model and the analytical reasoning model responsive to the routing decision, receiving one or more outputs from at least one of the experiential reasoning agent model and the analytical reasoning model, generating a final result by performing a result validation procedure on the one or more outputs, and transmitting the final result to the user device.

A user device renders content tiles in cache, where the content tiles represent a segment of a shared content provided on a canvas. The user device receives collaborator change data over one or more networks, where the collaborator change data represents a change made to the shared content by a second user device. The user device determines which content tiles in cache are affected by the collaborator change data. For each affected content tile, the user device implements a time-slicing process to render a replacement content tile, and after completing rendering of the replacement tile, the user device updates the cache by replacing the affected content tile with the replacement tile. The user device displays the segment of the shared content using the updated cache.

A method for enabling users to conversationally interact with a data table comprises receiving by a virtual assistant server from a user device, a natural language query targeted at a data table. The virtual assistant server determines one or more table intents or one or more table sub-intents of the natural language query. The virtual assistant server determines one or more table operations to execute on the data table based on the determined table intents or table sub-intents. The virtual assistant server iteratively executes each of the determined table operations on the data table, where a final version of the data table results after completion of one or more of the iteratively executed determined table operations. Subsequently, the virtual assistant server determines a response to the natural language query based on the final version of the data table and outputs the determined response to the natural language query to the user device.

An apparatus includes at least one processor; and at least one memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to: receive as input to a machine learning model a sequence of past serving locations of a user equipment; determine, using the machine learning model, a vector of confidences for predicted next locations of the user equipment; create at least one fork for at least one predicted next location of the predicted next locations having a confidence that exceeds a forking threshold; and determine iteratively a plurality of next locations of the user equipment, using as input the at least one predicted next location having the confidence that exceeds the forking threshold.