35397 results about "Computer program" patented technology

Disclosed in the present application are a multi-modal data processing method and apparatus, an electronic device, and a storage medium. The method comprises: acquiring a reference image and a reference text; extracting a reference visual feature of the reference image; by means of a multi-modal large language model, determining an embedding of the reference text, an embedding of a start mark of the reference visual feature, an embedding of the reference visual feature, and an embedding of an end mark of the reference visual feature; on the basis of the multi-modal large language model, splicing the embedding of the reference text, the embedding of the start mark, the embedding of the reference visual feature, and the embedding of the end mark into a target embedding sequence, performing attention processing on the basis of the embedding of the start mark, the embedding of the end mark, and an embedding selected by a sliding window in the target embedding sequence, and outputting a predicted sequence; and generating a predicted image and a predicted text on the basis of the predicted sequence.

In one embodiment, a computer-implemented method executed using one or more processors of an incident management system comprises receiving a notification of an incident associated with a computer system, and in response to receiving the notification: extracting an error message from the notification; reading a set of computer program code changes that have been implemented in the computer system; matching the error message to the set of computer program code changes and outputting a set of one or more candidate code changes that may correspond to the error message; based on the set of candidate code changes, generating an automatic remediation for the incident; and using the one or more processors of the incident management system, executing the automatic remediation on the computer system.

The invention discloses an urban flood toughness evaluation method, apparatus and device, a medium and a computer program product. The method comprises the steps of obtaining hydro meteorological data of a to-be-evaluated region and geographic information data of an urban spatial form element layer; setting boundary conditions of a plurality of flood scenes according to the hydrometeorological data, constructing a multi-scene urban flood disaster simulation model in combination with geographic information data, and respectively generating flood inundation depth data of urban spatial form element layers of the plurality of flood scenes; and calculating a first toughness index, a second toughness index and a third toughness index of each flood scene so as to calculate a flood toughness comprehensive evaluation result of each flood scene of the to-be-evaluated region. According to the method, an evaluation system of multiple composite flood disaster scenes is established, different disaster factors and interaction thereof are comprehensively considered, and the effect of key space parameters in urban flood toughness is fully considered, so that the capability of coping with flood disasters in cities can be more comprehensively and accurately evaluated.

The present application relates to the technical field of artificial intelligence, and in particular to a question answering method based on a large model, and an electronic device. The electronic device comprises a communication interface, a memory, and a processor, the memory is configured to store a computer instruction, and the processor is configured to execute a computer program to enable the electronic device to: determine, on the basis of each pre-stored text block, a target text block matched with a question to be answered; obtain, if non-text data including a picture and / or a table is pre-stored for the target text block in advance, stored summary text of the non-text data; and input the question to be answered, the target text block, and the summary text into a first large model on the basis of a preset format to obtain answer information. Since the summary text is text that summarizes all content in the non-text data, the first large model does not need to process the picture and / or the table and still can ensure that the content recorded in the picture and / or the table is taken into consideration during generation of the answer information, thereby improving the model-based question answering accuracy.

A computer-implemented method, computer program product and computing system for receiving a message concerning an event within a computer platform, wherein the message concerns a technology type and includes raw data; defining a cipher for the technology type, thus defining an associated cipher; processing the raw data included within the message using the associated cipher to define supplemental data for the technology type; and forming enriched data for the technology type based, at least in part, upon the raw data and the supplemental data.

Disclosed are a second-level optimal control method and apparatus for joint frequency regulation of heterogeneous load resources, and an electronic device, a storage medium, a computer program product and a computer program. The method comprises: establishing a standardized operation model for heterogeneous load resources; on the basis of parameters of the standardized operation model for the resources and historical frequency regulation signal data of a frequency regulation market, predicting frequency regulation signal distribution and price distribution over a future time period; solving an optimal operation model involving the joint participation of multiple heterogeneous resources in energy and frequency regulation markets, in order to determine a baseline energy output and a frequency regulation capacity; constructing an optimal decomposition problem of load resources and performing variable substitution, and calculating the marginal cost and adjustable range of power adjustment for each resource; and in response to receiving a frequency regulation signal sent by a power grid, starting dispatching from the resource having the lowest marginal regulation cost, and updating the power of each load-side resource until power adjustment requirements are met.

The present application provides a data processing method and apparatus, an electronic device, a computer readable storage medium and a computer program product. The method comprises: acquiring historical interaction information and a predicted interaction text corresponding to the historical interaction information; extracting a first acoustic feature and a first semantic feature of the historical interaction information, and extracting a second semantic feature of the predicted interaction text; performing fusion mapping on the basis of the first acoustic feature, the first semantic feature and the second semantic feature to obtain a first paralanguage feature; denoising initial noise on the basis of the second semantic feature and the first paralanguage feature to obtain a second acoustic feature of the predicted interaction text; and on the basis of the second acoustic feature, generating a voice signal corresponding to the predicted interaction text.

The invention relates to a data processing method for iterative sensor fusion. The method comprises receiving sensor data from a first data source type and a second data source type. The first data source type is adapted for providing sensor data for exclusively determining an entity and the second data source type is adapted for providing sensor data of a tracked entity. The method further comprises generating a data source identifier for each of the sensor data. The data source identifier comprises a data source type identifier corresponding to a data source type from which the sensor data is received. A first data source type identifier corresponds to the first data source type and a second data source type identifier corresponds to the second data source type. The method further comprises compiling a dataset that comprises newest sensor data received, and iteratively performing a data association step on the dataset.

The present application provides training and speech generation methods and apparatuses for a speech generation model, an electronic device, a computer-readable storage medium, and a computer program product. The method comprises: obtaining a first speech generation model; obtaining sample data of a plurality of modalities; on the basis of a prompt image sequence and speech text, respectively calling a plurality of encoders to perform encoding, so as to obtain a multi-modal encoding vector sequence; on the basis of the multi-modal encoding vector sequence, calling a decoder to perform decoding, so as to obtain decoded text; determining a probability distribution for the decoded text and the sample data of the plurality of modalities, and determining a target loss on the basis of the probability distribution; and on the basis of the target loss, updating parameters of the decoder and at least one of the encoders, wherein the updated decoder and the plurality of updated encoders are configured to form a second speech generation model, and the second speech generation model is used to generate target speech text corresponding to a prompt image sequence of a target object.

Embodiments include methods, electronic device, storage medium, and computer program to implement a dedicated queue based on a user request. In one embodiment, a method comprises: receiving a first message to optimize one or more data flows based on a quality-of-service request for an end user; enabling a first queue dedicated to the one or more data flows sourced for the end user in the network node based on the first message; and upon a determination of congestion in the network, marking packets in the one or more data flows stored in the first queue as candidates to drop based on a queue size of the first queue, wherein the marking is to set explicit congestion notification bits of the packets.

An intelligent task-type dialogue method based on a large language model, comprising: acquiring a dialogue with a user; identifying and parsing input information of the user to obtain an identification and parsing result; on the basis of the identification and parsing result, synchronously updating the state of a dialogue state tracker; on the basis of the intelligent guidance of the tracker, entering a proper dialogue scene node; executing a preset Action to complete a specific task; and on the basis of the current dialogue node context and dialogue historical data, generating a feedback message of a robot. In the method, by combining the large language model, rapid adaptation and efficient configuration of a scene can be achieved, and by dynamically loading the configuration information of a specific scene, a round of dialogue process can be efficiently pushed on the basis of preset process logic. Also disclosed are an intelligent task-type dialogue system based on a large language model, an electronic device, and a computer program product.

Methods, systems, and computer programs are presented to perform semantic analysis of video data for event detection and validation. One method includes an operation for training a machine-learning model with text-image pairs to create a semantic model. The semantic model generates text embeddings based on text describing events and image embeddings from video frames. The system calculates similarity values between text and image embeddings to determine event occurrences when the similarity exceeds a predetermined threshold. The system enables precise event detection by analyzing object relationships and attributes within video frames, reducing false alarms and enhancing monitoring efficiency. Further, these techniques can be used to detect any event describable by human text or by some image examples.

The invention discloses a carbon footprint tracking method and device, a storage medium and a computer program product, and relates to the technical field of carbon emission accounting, and the method comprises the steps: obtaining a carbon footprint evaluation target inputted by a user, and screening a to-be-tracked core product according to the carbon footprint evaluation target; drawing a life cycle boundary diagram according to the supply chain hierarchy diagram of the to-be-tracked core product, and marking high-emission key nodes in the life cycle boundary diagram; collecting carbon emission activity data and emission factors of each node in the life cycle boundary diagram; and performing carbon footprint calculation according to the carbon emission activity data and the emission factor to obtain a carbon footprint calculation result, and generating a carbon footprint tracking report according to the carbon footprint calculation result and the high-emission key node. The accuracy of carbon footprint tracking is improved by drawing the life cycle boundary diagram, so that emission reduction can be performed in a targeted manner according to the carbon footprint tracking report.

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for generating structured query language using machine learning. In some implementations, a system provides an interface configured to receive input comprising data processing criteria expressed in natural language text. The system receives natural language input through the interface, where the natural language input specifies one or more criteria for retrieving or generating data from a data set. The system obtains a structured query language (SQL) statement generated by an artificial intelligence or machine learning (AI / ML) model based on the natural language input, and the system provides the SQL statement through the interface.

The invention relates to the technical field of building risk monitoring, in particular to an urban building safety evaluation method, device and equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a synthetic aperture radar image, an optical remote sensing image, a hyperspectral image, topographic data and building contour data of a to-be-evaluated region; based on the optical remote sensing image and the building contour data, identifying spatial form change information of each target building, and generating change parameters used for describing structure adjustment features; generating an interferogram based on the synthetic aperture radar image, extracting a corresponding deformation monitoring point, and generating a settlement parameter reflecting the displacement change of the building; based on the hyperspectral image and the topographic data, identifying spatial relationship information of the target building and the surrounding environment risk body, and generating external influence parameters; and based on the change parameter, the settlement parameter, the external influence parameter and the preset evaluation model, generating a safety evaluation result of each target building, thereby improving the efficiency of urban building safety evaluation.

Provided in the present disclosure are a task scheduling method applicable to a large language model (LLM), and a computing device, a storage medium and a computer program product. The method comprises: when determining that a target task processing node currently executing a target task meets a resource reporting condition, a target second task scheduler sending a target running resource of the target task processing node to a first task scheduler; when determining that the target running resource meets a task migration condition, the first task scheduler determining a migration task processing node from among a plurality of task processing nodes, and sending node information of the migration task processing node to the target second task scheduler; and the target second task scheduler determining the migration task processing node on the basis of the node information, determining the target task currently executed by the target task processing node, as well as task data of the target task, and migrating the target task and the task data in batches to the migration task processing node for execution, so as to obtain a task processing result of the target task.

Techniques for visual deep learning for inline phishing detection are disclosed. In some embodiments, a system / process / computer program product for visual deep learning for inline phishing detection includes extracting a logo from a screenshot of a web page; detecting phishing based on a match to at least one of a plurality of reference logos using a visual deep learning model and that a domain associated with the web page is not associated with an entity that matches the logo extracted from the web page; and performing a remedial action in response to determining that the web page is associated with phishing.

The invention relates to the technical field of monitoring management, in particular to an intelligent water affair monitoring management system based on the Internet of Things, the system comprises a processor and a memory, and the processor executes a computer program stored in the memory to realize the following steps: acquiring data correlation coefficients and differential correlation coefficients corresponding to different monitoring moments, obtaining a target abnormal coefficient of the first clustering cluster and a target abnormal coefficient of the second clustering cluster according to a data volume ratio and a variable coefficient in the first clustering cluster and the second clustering cluster obtained by clustering the data correlation coefficient and the difference correlation coefficient corresponding to the monitoring moment; and obtaining a target abnormal index value corresponding to the current monitoring moment according to the data correlation coefficient corresponding to the current monitoring moment and the target abnormal coefficient of the cluster to which the differential correlation coefficient belongs, and monitoring the water affair system according to the target abnormal index value. And the timeliness and the reliability of abnormal monitoring and early warning of the water affair system can be improved.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for content generation are provided. One of the methods includes receiving one or more user input identifying information associated with one or more media elements and one or more characteristics of the video to be generated; and generating video content based on the received one or more user inputs, the generating comprising: identifying assets to include in the video, the assets including an avatar, generating a script for the video, and assembling a video layout.

The invention relates to a retrieval method and device based on static word embedding, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of performing word segmentation on an original text to obtain a first word segmentation result, training a static word embedding model by utilizing the first word segmentation result to obtain word vectors, and generating a synonym word library; the method comprises the following steps: establishing a full-text inverted index by utilizing an original text, and expanding query words by utilizing a synonym library in a retrieval stage; encoding the original text into a semantic vector by using a semantic generation model, and constructing a vector index based on the semantic vector; based on a to-be-queried text in a user query request, performing retrieval by using the full-text inverted index to obtain a first candidate document, and performing retrieval by using the vector index to obtain a second candidate document; performing fusion processing on the first candidate document and the second candidate document to obtain a target candidate document; and inputting the target candidate document into the text generation model to obtain a retrieval result. By adopting the method, the accuracy of text retrieval can be improved.

The invention relates to the technical field of intelligent traffic and energy-saving illumination, in particular to an intelligent management and control method and system for energy-saving illumination of a highway tunnel and a computer program, and is suitable for an intelligent illumination control system for improving tunnel driving safety and energy efficiency of an illumination system. Dynamic response and fine energy consumption adjustment of tunnel lighting are realized through out-of-tunnel brightness multi-source fusion prediction, entrance section feedforward, closed-loop dimming control, a segmented intelligent lighting strategy based on vehicle detection and an in-tunnel brightness closed-loop and stepless dimming mechanism. The system has a multi-sensor redundancy mechanism and can automatically return to a safety mode when equipment fails, so that the continuity and the safety of illumination are guaranteed; and meanwhile, data summarization and energy-saving statistics are combined, control parameters are optimized in cooperation with a digital twinning or self-learning algorithm, the energy-saving effect and the operation and maintenance efficiency are further improved, and the purposes of traffic safety and low-carbon operation are considered.

Methods, apparatuses, system, devices, and computer program products for evaluating tokenized entities using an AI model are disclosed. In a particular embodiment, a controller generates a profile for a digitally traded asset and generates, using an AI model, one or more entity profiles corresponding respectively to one or more entities that back the digitally traded asset. The controller stores the profile for a digitally traded asset and the one or more entity profiles in a database comprising a plurality of entity profiles corresponding to different entities. The controller augments the AI model based on the plurality of entity profiles. The controller generates using the augmented AI model, a rating for the digitally traded asset based on an AI-driven analysis of the plurality of entity profiles.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a 3D representation of a scene. In particular, one of the methods includes obtaining a plurality of training images of a scene; initializing a three-dimensional (3D) representation of the scene, the 3D representation comprising a set of Gaussian distributions; and generating a final 3D representation of the scene, comprising, at each of a plurality of update steps, updating, using rendered images rendered using the set of Gaussians and corresponding training images, the set of Gaussian distributions. As part of the updating, gradient-based pruning, semantically-aware optimization, or both can be performed.

The invention relates to an incidence relation determination method and device, computer equipment, a storage medium and a computer program product. Relates to the technical field of software engineering. The method comprises the following steps: constructing a code knowledge graph based on a source code of a to-be-processed project, and constructing a demand knowledge graph based on a demand document of the to-be-processed project; mining historical data of the to-be-processed project, establishing a tracking link between the code knowledge graph and the demand knowledge graph, and generating a unified knowledge graph; receiving a query request of a user, and performing retrieval in the unified knowledge graph based on the query request to obtain structured context information; and obtaining enhanced prompt information based on the structured context information and a preset prompt template, sending the enhanced prompt information to the large language model, and outputting target result information corresponding to the query request based on the large language model. By adopting the method, the efficiency of determining the incidence relation between the software requirement and the source code can be improved.

Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for training a denoising neural network and, once the denoising neural network is trained, generating new images using the denoising neural network. In particular, the described techniques include obtaining data specifying a trained initial denoising neural network, obtaining training data, and training, using the training data and on a denoising objective, a target denoising neural network. The target denoising neural network includes the core-subnetwork of the trained initial denoising neural network, but also includes a target encoder and decoder neural networks that are not included in the trained initial denoising neural network. By training a target neural network that includes the core-subnetwork of a trained initial denoising neural network, the system achieves stable training of a large-scale target denoising neural networks that can be used to generate high resolution images.

The invention relates to a multi-agent cooperative recruitment method, system and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining a target recruitment demand, and generating a task tree for the target recruitment demand through a preset dynamic decision-making mechanism in a main agent; determining a time sequence relationship and logic constraint information of each sub-task in the task tree, and calling target sub-agents in the sub-agents in sequence based on the time sequence relationship and the logic constraint information; the target sub-agent is used for executing the sub-task in the task tree; and generating a target recruitment task result until task execution results of the sub-tasks are obtained. By adopting the method, the recruitment efficiency can be improved.

A method, computer program product, and computing system for generating a plurality of chunks for a plurality of text portions of a document, wherein the document includes the plurality of text portions and a plurality of images. Each chunk is indexed using a word embedding. Each of the plurality of images is indexed based upon, at least in part, a position of a respective image relative to a corresponding chunk. An image placeholder is generated for each of the plurality of images. A plurality of image-enhanced embeddings is generated by inserting the image placeholder for each of the plurality of images into a respective word embedding for the corresponding chunk. The plurality of image-enhanced embeddings are provided for processing a query using a generative artificial intelligence (AI) model.

Systems, methods, apparatuses, and computer program products for enhancing dynamic CORESET adaptation with limited or no control channel overhead. One method may include receiving, by a UE, a plurality of PDCCH CORESET configurations associated with at least one SS; determining, by the UE, at least one of the PDCCH CORESET configurations is associated with a symbol or slot format from a corresponding set of symbols; and performing, by the UE, PDCCH monitoring on an active control resource set configuration associated with the set of determined slots or symbols.

The invention discloses a zero-carbon park planning method and device, a storage medium and a computer program product, and relates to the technical field of carbon emission management, and the method comprises the steps: collecting the original space data of a target park, and obtaining the environment parameters of the target park, constructing a park three-dimensional digital twinborn model according to the original spatial data of the target park and the environmental parameters of the target park; dividing the park three-dimensional digital twinborn model into a plurality of grid units, respectively calculating the photovoltaic theoretical generating capacity of the plurality of grid units, and generating a plurality of candidate zero-carbon park planning schemes according to the photovoltaic theoretical generating capacity; performing economic cost measurement and calculation and carbon efficiency income measurement and calculation on each candidate zero-carbon park planning scheme to obtain an economic carbon efficiency measurement and calculation result; and selecting an optimal zero-carbon park planning scheme from the candidate zero-carbon park planning schemes according to an economic carbon effect measurement result. Zero-carbon park quantitative simulation is carried out in the planning stage, high cost of later modification of the park is avoided, and the economic carbon-efficiency ratio of the zero-carbon park is increased.

Provided in the present application are a balanced charging method and apparatus for a battery pack, and a computer program product. Charging current control consists of two stages, i.e., a "pulse square-wave excitation" stage and a "multi-stage current-reduction charging" stage. During the pulse square-wave excitation stage, the parameter identification of an equivalent circuit model and the joint estimation of state variables are realized, thereby providing reliable battery parameters for a subsequent balancing process. During the multi-stage current-reduction charging stage, a flyback converter is used to control a balanced current of each battery cell, and the battery cells remain in a charging state throughout a balancing process, thereby effectively mitigating the impact of a hysteresis voltage.