Abstract: An information search method includes: obtaining search words at least including a question to be searched and obtaining an initial text vector representation of the search words; obtaining a video corresponding to the search words, and obtaining multi-modality vector representations of the video; starting from the initial text vector representation, performing N rounds of interaction between the video and the search words based on the multi-modality vector representations and a text vector representation of the search words of a current round, to generate a target fusion vector representation, where N is an integer greater than or equal to 1; and obtaining target video frames matching the question to be searched by annotating the video based on the target fusion vector representation.

Abstract: Provided are a training method for an image generation model, an image generation method, apparatus, and a device. The training method includes extracting reference keypoints of a character from a sample reference image; based on a model to be trained, performing motion estimation using sample audio data and the reference keypoints to obtain predicted keypoints that match the sample audio data; performing parameter estimation using the reference keypoints and the predicted keypoints to obtain motion parameters of the predicted keypoints, and performing prior motion estimation using the motion parameters of the predicted keypoints to obtain optical flow of non-key pixel points; performing image prediction using the sample reference image and dense optical flow to obtain predicted image data that matches the sample audio data; performing model training using the predicted image data and annotated image data to obtain the image generation model.

Abstract: A method of outputting a prompt information, a device, a medium, and a vehicle, which relate to a field of artificial intelligence, in particular to a field of assisted driving, a field of intelligent transportation and a field of computer vision. The method of outputting the prompt information may include: determining a type of an auxiliary prompt information in response to a determination that the auxiliary prompt information is required to be output, wherein the determination that the auxiliary prompt information is required to be output is performed according to a navigation information and an environment information; determining an output time of the auxiliary prompt information according to the type of the auxiliary prompt information; and outputting the auxiliary prompt information in response to the output time being reached.

Abstract: The present disclosure provides a method for training a feature extraction model, a method for classifying an image and related apparatuses, and relates to the field of artificial intelligence technology such as deep learning and image recognition. The scheme comprises: extracting an image feature of each sample image in a sample image set using a basic feature extraction module of an initial feature extraction model, to obtain an initial feature vector set; performing normalization processing on each initial feature vector in the initial feature vector set using a normalization processing module of the initial feature extraction model, to obtain each normalized feature vector; and guiding training for the initial feature extraction model through a preset high discriminative loss function, to obtain a target feature extraction model as a training result.

Abstract: A method and apparatus of constructing a network model for deep learning, a device, and a storage medium, which relate to artificial intelligence, and in particular to a field of deep learning. The method of constructing the network model for deep learning includes: determining an execution mode for executing codes, based on a mode parameter; executing the codes by using a first component, which is executable in a first execution mode, through a syntax element in the codes, in response to determining that the execution mode is the first execution mode; and executing the codes by using a second component, which is executable in a second execution mode, through the syntax element, in response to determining that the execution mode is the second execution mode; wherein the first component and the second component have the same component interface, and the syntax element corresponds to the component interface.

Abstract: The present disclosure provides an image processing method and apparatus, and relates to the field of image processing, and in particular to the field of image annotation. An implementation is: obtaining an image to be processed including a target region to be annotated; in response to a first click on the target region, performing a first operation to expand a predicted region for the target region based on a click position of the first click; in response to a second click in a position where the predicted region exceeds the target region, performing a second operation to reduce the predicted region based on a click position of the second click; and in response to determining that a difference between the predicted region and the target region meets a preset condition, obtaining an outline of the predicted region to annotate the target region.

Abstract: The present disclosure provides a vision processing and model training method, device, storage medium and program product. A specific implementation solution is as follows: establishing an image classification network with the same backbone network as the vision model, performing a self-monitoring training on the image classification network by using an unlabeled first data set; initializing a weight of a backbone network of the vision model according to a weight of a backbone network of the trained image classification network to obtain a pre-training model, the structure of the pre-training model being consistent with that of the vision model, and optimize the weight of the backbone network by using real data set in a current computer vision task scenario, so as to be more suitable for the current computer vision task; then, training the pre-training model by using a labeled second data set to obtain a trained vision model.

Abstract: A system is provided that includes: a first load balancing device cluster, the first load balancing device cluster includes a first load balancing device pool and a second load balancing device pool; at least one first switch respectively coupled with each load balancing device in the first load balancing device pool via a routing protocol link; and at least one second switch respectively coupled with each load balancing device in the second load balancing device pool via a routing protocol link, the at least one first switch and the at least one second switch are configured to be able to be connected with the Internet; and one of the first load balancing device pool and the second load balancing device pool is configured as a standby load balancing device pool of the other.

Abstract: A method for pre-training a language model includes: constructing a pre-training language data set, in which the pre-training language data set comprises unsupervised language data and supervised language data; generating a hierarchical multi-template and multi-task language data set based on the pre-training language data set; and pre-training the language model based on the hierarchical multi-template and multi-task language data set.

Abstract: A method for obtaining browser running data, includes: receiving a trigger request of event, in which the trigger request includes an event to be executed and a first time point corresponding to the trigger request; in a case that the event to be executed is bound with a callback function, binding the event to be executed with a preset event monitoring function; obtaining a second time point for executing the event monitoring function; and determining a response duration of a browser under the event to be executed based on a time interval between the second time point and the first time point.

Abstract: A positioning method includes: receiving detection data sent by a positioning device, in which the detection data includes first satellite data of multiple satellites; determining prediction noise of each satellite based on the first satellite data, and determining a weight of each satellite based on the prediction noise; and determining a position of the positioning device based on the weight and observation equations.

Abstract: A method for determining a risk level of an instance on a cloud server. The method includes: obtaining one or more monitoring items of an instance to be monitored and a rule base of each monitoring item; obtaining monitoring data corresponding to each monitoring item of the instance to be monitored; and determining a risk level of the instance to be monitored under each monitoring item based on the rule base and the monitoring data of each monitoring item.

Abstract: A method for processing a question is performed by an electronic device. The method includes: receiving a question to be processed from a user input; determining a first similarity between the question to be processed and each candidate question in at least one reference question-answer (Q&A) pair; determining a second similarity between the question to be processed and the at least one reference Q&A pair based on the first similarity; determining a target Q&A pair from the at least one reference Q&A pair based on the second similarity; and replying to the user for the question to be processed based on a target answer in the target Q&A pair.

Abstract: Provided are an image processing method and apparatus, a device, a medium and a program product. The image processing method includes: performing image augmentation on an original image to obtain at least one augmented image; performing subject detection on the original image and the at least one augmented image to obtain an original detection frame in the original image and an augmented detection frame in the at least one augmented image; determining whether the original detection frame and the augmented detection frame belong to the same subject; and in response to the original detection frame and the augmented detection frame belonging to the same subject, determining a target subject frame in the original image according to the augmented detection frame.

Abstract: A method of protecting a model, which relates to a field of computer, a field of artificial intelligence, and may be applied to an AI model protection scenarios. The method includes: generating a WASM file for providing a runtime environment for a target model, the WASM file containing a corresponding model inference algorithm and security verification algorithm, wherein the security verification algorithm is configured to perform at least one security verification operation to protect the target model, the at least one security verification operation is selected from: a verification of a host environment; a verification of an integrity of the WASM file; a verification of an integrity of the model file generated corresponding to an original model file of the target model; a timeout verification of a specified inference process during a model inference process; or a timeout verification of an entire inference process during the model inference process.

Abstract: A large model-based video processing method, device and storage medium in the field of artificial intelligence technology, particularly in the fields of deep learning and large models are disclosed. The specific solution includes: collecting an imitation video made by a user based on a target video; extracting three-dimensional postures of the imitation video using a pre-trained large model based on the imitation video; and performing posture assessment on the imitation video using the pre-trained large model based on the three-dimensional postures of the imitation video and pre-obtained three-dimensional postures of the target video to obtain an assessment result.

Abstract: A method, electronic device and computer-readable storage medium for extracting entity relationships, which relates to artificial intelligence technologies such as natural language processing, knowledge graphs, deep learning, and large language models. The method for extracting entity relationships includes: inputting a target long text into a target large language model to obtain a target keyword list based on an output result of the target large language model; inputting the target keyword list into multiple target relationship agents respectively to obtain multiple target regular expressions corresponding to different entity relationships based on output results of the multiple target relationship agents; and processing texts in a preset text set using the multiple target regular expressions to obtain entity relationship extraction results.

Abstract: The present disclosure provides a method and an apparatus for intent recognition based on a large language model (LLM), an electronic device, and a storage medium, relating to a field of computer technology, specifically to a field of artificial intelligence technology, such as natural language processing and an LLM. A specific implementation solution is as follows: obtaining a query statement, a preset intent, and descriptive information of the preset intent; obtaining a first candidate intent corresponding to the query statement by matching the query statement with the preset intent and the descriptive information of the preset intent; generating first prompt information based on the query statement, the first candidate intent, and descriptive information of the first candidate intent; and determining a first target intent corresponding to the query statement from the first candidate intent by inputting the first prompt information into the LLM.

Abstract: Provided are a joint perception model training method, a joint perception method, a device, and a storage medium. The joint perception model training method includes: acquiring sample images and perception tags of the sample images; acquiring a preset joint perception model, where the joint perception model includes a feature extraction network and a joint perception network; performing feature extraction on the sample images through the feature extraction network to obtain target sample features; performing joint perception through the joint perception network according to the target sample features to obtain perception prediction results; and training the preset joint perception model according to the perception prediction results and the perception tags, where the joint perception includes executing at least two perception tasks.