Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

52 results about "Context variable" patented technology

System and method for dynamically recommending a set of potential courses of actions for a user within a search query

A system and method for dynamically recommending set of potential courses of actions for a user within a search query are disclosed. The system receives search queries from a user and determines dialogue attributes and context variables based on these queries. It identifies query parameters and additional parameters, The system analyzes user preferences, and determines entities and variants based on the user's preferences and the conversation context. The system then determines the types of set of potential courses of actions to generate for the search queries. Further, the system retrieves set of potential courses of, associated applications, and integration parameters from databases based on the determined types. Using large language models (LLMs) in generative AI or conversation AI environments, the system generates responses and clickable elements corresponding to the search queries, incorporating the recommended set of potential courses of actions, applications, and deep integration parameters.
Owner:AI NETOMI INC

Interface generation system based on large language model LLM

The invention relates to interface generation, in particular to an interface generation system based on a large language model (LLM), which comprises a data acquisition layer for performing data extraction and parameterized packaging on interface description data received by a user layer and converting the interface description data into a structured data set; the parameter processing layer is used for classifying the structured data set output by the data acquisition layer according to an input purpose, inserting a corresponding prompt template, automatically generating context variables required by each interface module in an interface generation process by AI, and carrying out association matching on each interface module and parameters thereof; the model processing layer summarizes the operation of each interface module, converts the operation into operation description, inserts the operation description into a corresponding prompt template, and selects the most suitable operation from the operation description according to the description of each interface module; according to the technical scheme, the defect that in the prior art, it is difficult to generate interface codes meeting service requirements on the basis of limited interface description can be effectively overcome.
Owner:NANJING TUANDA TECHNOLOGY CO LTD

Log output method and device, electronic equipment and readable storage medium

The embodiment of the invention provides a log output method and device, electronic equipment and a readable storage medium, and the method comprises the steps: executing a plurality of test cases, and obtaining a first test result of each test case; one test case is associated with one context variable, and the context variable comprises tracking identification information; under the condition that the first test result of the target test case is not matched with a preset test result, determining tracking identification information in a context variable associated with the target test case; the plurality of test cases comprise a target test case; a first log file corresponding to the target test case is generated and output according to the tracking identification information, the first log file comprises first identification information, and the first identification information comprises the tracking identification information associated with the target test case. Through the embodiment of the invention, the test efficiency can be improved.
Owner:BEIJING QIYI CENTURY SCI & TECH CO LTD

User intelligent retrieval platform based on campus service

The invention belongs to the technical field of intelligent user retrieval, and particularly discloses and provides an intelligent user retrieval platform based on campus services, which remarkably improves the joint effect of dynamic user portraits and semantic intention enhancement through retrieval accuracy, can capture user demands and situation changes in real time, and improves user experience. In combination with accurate matching of knowledge graph multi-hop reasoning on resources, the proportion of invalid retrieval results is reduced, and the intention recognition accuracy and the resource matching precision are improved; the environment context variable is greatly optimized through scene adaptability, and the real-time position information is introduced, so that the service recommendation is more suitable for the current scene, and the user requirements under diversified campus situations can be met; the resource position can be visually positioned through the map, and the preference service can be quickly found through personalized sorting, so that the service acquisition path is shortened, the operation complexity is reduced, and the use satisfaction of the user is improved.
Owner:HENAN FENGYUN TECH DEV CO LTD

Defining and Executing Custom Generative Artificial Intelligence Agent Actions on Selected Data Items

Techniques for creating and executing custom AI-driven actions in a data analysis interface are disclosed. One or more embodiments receive user input that defines a custom action by specifying an AI prompt with a natural language query and context variables. This definition is stored for later use. One or more embodiments present a graphical user interface (GUI) displaying data items, allowing users to select a subset. Based on the stored definition of a custom action, an option to execute the custom action appears. When the option is chosen, one or more embodiments assign metadata values from the selected items to the context variables, creating initialized context variables. The complete prompt, including the query and initialized variables, is submitted to an AI agent. The AI's response is displayed in the GUI, providing context-aware insights within the data analysis workflow.
Owner:ORACLE INT CORP

Context-aware action execution system for conversational ai

Techniques for executing system actions during conversations between a human user and an autonomous conversational system are disclosed. A first generative language model processes user messages to determine user intent, while a dialog management model analyzes the intent and conversation context to identify required system actions. The system executes actions by retrieving parameters from context, performing database queries or API calls to obtain response data, and storing results in conversation context variables. A second generative language model generates natural language responses using the action results. The system maintains conversation context including message history, action results, and state information, validates action execution, and initiates human agent handoff when needed. The system improves over time by detecting poor performance, gathering problematic conversations, and retraining using updated configurations.
Owner:GICRM AI LLC

Entropy decoding processing method and device, computer equipment, readable storage medium and program product

The invention relates to an entropy decoding processing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: for a context model of each intra-frame coding strip, if a current syntax element is a first type syntax element, initializing the current context model, and determining a context variable in the current context model; the first type syntax element comprises a first syntax element of a first coding tree unit of a slice, slice or coding tree unit row; analyzing the current syntax element through the initialized current context model; and storing the context variables in each current context model until the current syntax element is the second type syntax element. By adopting the method, the data volume processed in the entropy decoding process can be reduced, the processing time is shortened, and the processing efficiency is improved.
Owner:GLENFLY TECH CO LTD

Transform coefficient adaptive entropy coding in video coding systems

PendingCN123036838AAlgorithmContext variable
An entropy coding method based on a subset selection of context variables of transform coefficient positions and adaptive thresholds is provided herein. A video codec can code data of a certain transform block in a current block as transform coefficients generated by a transform operation. The video codec utilizes context modeling to entropy encode or decode the transform coefficients in the transform block. The video codec determines a threshold for the context modeling based on coding information of the current block. For each transform coefficient in the transform block, the video codec compares a position value of the transform coefficient in the transform block with the determined threshold, and selects a set of context variables for the context modeling. The video codec can reconstruct the current block based on entropy-decoded transform coefficients generated by an inverse transform operation, or transmit the entropy-encoded transform coefficients as a bitstream.
Owner:MEDIATEK INC

INFORMATION PROCESSING DEVICE, PROGRAM AND INFORMATION PROCESSING METHOD

An information processing device (100) comprises: an attention mechanism unit (113) that calculates a context variable by weighting and adding a plurality of time series variables using an attention mechanism learning model that is a learning model of an attention mechanism; a decision unit (114) that determines a decision included in a plurality of decisions based on confidence levels of the plurality of decisions calculated from the context variable and a last variable included in the plurality of variables; a storage unit (101) that stores result information correlating the context variable and the one decision; and an evaluation unit (115) that evaluates a training state of at least the attention mechanism learning model based on the result information.
Owner:MITSUBISHI ELECTRIC CORP

Electric vehicle powertrain calibration

A method includes generating, for an electric vehicle powertrain, a calibration map providing a mapping from values of a set of context variables to mapped values of a set of decision variables. The c
Owner:SECONDMIND LTD

Encoding method, decoding method, encoder, decoder, and storage medium

The invention relates to an encoding method, a decoding method, an encoder, a decoder, and a storage medium. The invention also relates to signaling affine modes in the encoded video stream; specifically, a list of merge candidates corresponding to adjacent blocks of a current block is determined; and signaling an affine mode of the current block; wherein signaling the affine mode comprises decoding a context coded flag from the data stream, and wherein a context variable of the flag is determined based on whether the neighboring block uses the affine mode. Related encoding and decoding methods and apparatuses are also disclosed.
Owner:CANON KK

A test case automatic generation system based on probability extended finite state machine

The application provides a test case automatic generation system based on a probability extended finite state machine, which can improve the efficiency and quality of test case generation, and finally generates test cases through probability selection on the processed PEFSM model. The system comprises a PEFSM model construction module, a removing unfeasible path module and a test case probability generation module. The PEFSM model construction module obtains relevant data for constructing a model from a user historical operation record database according to the requirement specification and interface design of a system under test, and outputs a PEFSM model describing the behavior of the system under test. The removing unfeasible path module takes the PEFSM model as input, adopts an evaluation path feasibility measurement method to identify and remove unfeasible paths in the PEFSM model, and outputs a reliable test path set formed by a transition path set. The test case probability generation module takes the reliable test path set as input, initializes context variables, and instantiates test paths in the path set to obtain test cases of the system under test.
Owner:BEIJING INST OF TECH

Methods, apparatuses and computer program products for mental model aware explainable artificial intelligence for intelligent user interfaces

PCT designated stage expiredWO2025081181A1Input/output for user-computer interactionGraph readingIntelligent user interfaceContext variable
A system and method for determining content to recommend to a user interface are provided. The system may determine contexts of users within environments. The system may implement a machine learning model including training data pre-trained, or trained in real-time based on historical interactions of users with data, or determined interactions with content by the users in real time. The system may analyze an item(s) of context information associated with the contexts to determine content relevant to a user associated with the system capturing content items within an environment. The system may analyze the item(s) of context information or other items of context information to determine contextual variables, of the environments, determined as relevant to the system. The system may utilize the determined content relevant to the user and the contextual variables determined as relevant to the system to determine a recommendation(s) or action(s) to present to a user interface.
Owner:META PLATFORMS INC

Method and apparatus for entropy coding transform coefficients in an image or video coding system

Methods and apparatus of decoding for transform coefficients of residual data are disclosed. According to one method, one or more high-level syntax elements indicating whether to enable a controlling scheme are parsed. In response to said one or more high-level syntax elements indicating the controlling scheme being enabled: a value for a target syntax flag related to representation of the transform coefficients is inferred as an inferred value for the target syntax flag when a target probability for a selected context variable associated with the target syntax flag corresponds to a specified high / low probability range. According to another method, one or more high-level syntax elements indicating whether the current bitstream represents a coded input video data by lossless compression are parsed. According to yet another method, a pre-defined parameter setting for lossless compression is determined, wherein all coding tools that cause coding artefacts are disabled.
Owner:MEDIATEK INC

Method for decoding video from video bitstream, method for encoding video, video decoder, and video encoder

A method for decoding a video from a video bitstream is provided and at least includes: accessing a binary string representing a partition of the video, the partition comprising a plurality of coding tree units (CTUs) forming one or more CTU rows; for each CTU of the plurality of CTUs in the partition, determining whether the CTU is the first CTU in a slice or a tile; in response to determining that the CTU is the first CTU in a slice or a tile, initializing context variables for context-adaptive binary arithmetic coding (CABAC) according to a first context variable initialization process; in response to determining that the CTU is not the first CTU in a slice or a tile, determining whether parallel decoding is enabled and the CTU is the first CTU in a CTU row of a tile.
Owner:GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD

Method for decoding video from video bitstream, method for encoding video, video decoder, and video encoder

A method for decoding a video from a video bitstream is provided and includes: accessing a binary string representing a partition of the video, the partition comprising a plurality of coding tree units (CTUs) forming one or more CTU rows; for each CTU of the plurality of CTUs in the partition, determining whether the CTU is the first CTU in a slice or a tile; in response to determining that the CTU is the first CTU in a slice or a tile, initializing context variables for context-adaptive binary arithmetic coding (CABAC) according to a first context variable initialization process; in response to determining that the CTU is not the first CTU in a slice or a tile, determining whether parallel decoding is enabled and the CTU is the first CTU in a CTU row of a tile.
Owner:GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD

Initialization process for video encoding

ActiveCN121151567BPredictor variableAlgorithm
In some embodiments, a video decoder decodes a video from a bitstream. The video decoder accesses a bin string representing a partition of the video and processes each coding tree unit (CTU) in the partition to generate decoded values in the CTU. The process includes initializing context variables for context adaptive binary arithmetic coding (CABAC), Rice parameter variables, and palette predictor variables only when the CTU is the first CTU in a tile, or the CTU is the first CTU in a slice, or parallel coding is enabled and the CTU is the first CTU in a CTU row of a tile. No other initialization is performed for these variables. The video decoder decodes the CTU based on the initialized context variables, Rice parameter variables, and palette predictor variables.
Owner:GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD

Information processing device, program, and information processing method

An information processing device (100) is provided with: an attention mechanism unit (113) that calculates a context variable by weighting and adding a plurality of variables, which are time series, using an attention mechanism training model, which is an attention mechanism training model; a determination unit (114) that estimates one determination included in a plurality of determinations on the basis of the reliability of the plurality of determinations calculated on the basis of the context variable and the latest one variable included in the plurality of variables; a storage unit (101) that stores result information in which the context variable is associated with the one determination; and an evaluation unit (115) that evaluates at least the training state of the attention mechanism training model on the basis of the result information.
Owner:MITSUBISHI ELECTRIC CORP

Entropy coding transform coefficients in video coding system

A method for entropy coding transform coefficients is provided. A video coder receives data for a block of pixels to be encoded or decoded as a current block of a current picture. The video coder may encode the received data of a transform block of the current block into transform coefficients generated by transform operations. The video coder entropy encodes or decodes the transform coefficients of the transform block according to a diagonal scan order with context modeling. The video coder selects context variables for the context modeling, such that for each transform coefficient currently coded, a set of context variables is selected according to a position of the transform coefficient in the diagonal scan order. The video coder may reconstruct the current block based on the entropy decoded transform coefficients generated by inverse transform operations, or transmit the entropy encoded transform coefficients as a bitstream.
Owner:MEDIATEK INC

Encoding method, decoding method, encoder, decoder, and storage medium

The invention relates to an encoding method, a decoding method, an encoder, a decoder, and a storage medium. The invention also relates to signaling affine modes in the encoded video stream; specifically, a list of merge candidates corresponding to adjacent blocks of a current block is determined; and signaling an affine mode of the current block; wherein signaling the affine mode comprises decoding a context coded flag from the data stream, and wherein a context variable of the flag is determined based on whether the neighboring block uses the affine mode. Related encoding and decoding methods and apparatuses are also disclosed.
Owner:CANON KK

Methods, apparatuses and computer program products for mental model aware explainable artificial intelligence for intelligent user interfaces

PendingUS20250123860A1Execution for user interfacesOptical elementsIntelligent user interfaceContext variable
A system and method for determining content to recommend to a user interface are provided. The system may determine contexts of users within environments. The system may implement a machine learning model including training data pre-trained, or trained in real-time based on historical interactions of users with data, or determined interactions with content by the users in real time. The system may analyze an item(s) of context information associated with the contexts to determine content relevant to a user associated with the system capturing content items within an environment. The system may analyze the item(s) of context information or other items of context information to determine contextual variables, of the environments, determined as relevant to the system. The system may utilize the determined content relevant to the user and the contextual variables determined as relevant to the system to determine a recommendation(s) or action(s) to present to a user interface.
Owner:META PLATFORMS INC

Information processing device, non-transitory computer-readable storage medium, and information processing method

An information processing device includes: an attention mechanism unit that calculates a context variable by weighting and adding a plurality of time-series variables by using an attention-mechanism learning model that is a learning model of an attention mechanism; a decision unit that estimates one decision included in a plurality of decisions based on confidence levels of the plurality of decisions calculated from the context variable and a latest variable included in the plurality of variables; a storage unit that stores result information correlating the context variable and the one decision; and an evaluating unit that evaluates a training state of at least the attention-mechanism learning model from the result information.
Owner:MITSUBISHI ELECTRIC CORP

Video coding and decoding

The invention relates to signalling affine mode in an encoded video stream; in particular determining a list of merge candidates corresponding to blocks neighbouring a current block; and signalling affine mode for said current block; wherein signalling said affine mode comprises decoding a context encoded flag from the data stream, and wherein the context variable for said flag is determined based on whether or not said neighbouring blocks use affine mode. Related encoding and decoding methods and devices are also disclosed.
Owner:CANON KK

Adaptive workflow and creative automation system

An adaptive workflow and creative automation system is disclosed that dynamically generates personalized outputs by integrating contextual variables based on a user’s personality traits, philosophical perspectives, and cognitive biases. The system comprises at least one computing device in operable communication with an application program, a user interface module for receiving user inputs, and a server configured to process those inputs and generate workflow automation tasks and creative content. An adaptive algorithm analyzes user data and adjusts system behavior in real time to produce contextually relevant outputs, while one or more data stores preserve user information and historical interactions for continuous optimization. Unlike traditional rule-based systems, the disclosed invention personalizes automation through behavioral modeling, enabling real-time adaptation of tasks and outputs aligned with the user’s evolving needs, beliefs, and decision-making tendencies. The system improves efficiency, creativity, and user alignment across both operational and creative workflows.
Owner:TUNACAT LLC

Image processing apparatus and method

The invention relates to an image processing apparatus and method. The image processing apparatus includes circuitry configured to assign a context variable to a first bin in a sequence of bins based on a parameter regarding a tree type, the sequence of bins being obtained by binarizing a quadratic orthogonal transformation identifier indicating a pattern of quadratic orthogonal transformation in image coding, and performing context coding for a first bin in the sequence of bins.
Owner:SONY GROUP CORP

Initialization processing for video coding

In some embodiments, a video decoder decodes video from a bitstream. A video decoder accesses a binary string representing a partition of the video and processes each coding tree unit (CTU) in the partition to generate decoded values in the CTUs. The process includes initializing a context variable, a Rice parameter variable, and a palette predictor variable for context adaptive binary arithmetic coding (CABAC) only when the CTU is a first CTU in a tile, or the CTU is a first CTU in a slice, or parallel coding is enabled and the CTU is a first CTU in a CTU row of the tile. Other initializations are not performed on these variables. The video decoder decodes the CTU based on the initialized context variable, the Rice parameter variable, and the palette predictor variable.
Owner:GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD

Generating suggested communications by simulating interactions using language model neural networks

To provide methods, systems and recording mediums for generating suggested communications during a multi-agent interaction using a language model neural network.SOLUTION: A method comprises: identifying multiple first and second strategies for selecting between parameterizations for communications for first and second actors; parametrizing a set of context variables for the communications of the actors during an interaction; for each of multiple pairs including respective first and second strategies: generating simulations of the interaction using a language model neural network; determining, from the simulations, a score for the pair that indicates a degree to which the first and second actors satisfy objectives for the interaction; selecting, using the scores for the multiple pairs, a parametrization for the first actor; and generating, by processing an input that conditions the language model neural network on the selected parameterization, a suggested communication for the first actor.SELECTED DRAWING: Figure 2
Owner:ジーディーエム·ホールディング·エルエルシー

Signaling for Wavefront Parallel Processing

Methods, apparatus, and systems for video coding and encoding are described, including constraints, restrictions, and signaling for sub-pictures, slices, and slices. An example video processing method includes performing conversion between a picture of a video and a bitstream of the video, wherein the bitstream conforms to a format rule, wherein the format rule specifies a first syntax element that enables (a) synchronization of context variables before decoding a codec tree unit (CTU) in the picture and (b) storage of the context variables after decoding the CTU, wherein the first syntax element is signaled in a sequence parameter set (SPS) associated with the picture.
Owner:DOUYIN CO LTD