4015 results about "Equipment computers" patented technology

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.

A control method for a support robot, the method comprising: in response to recognizing that a target object has an intent to require support, controlling a support robot to move toward the target object, and when the support robot moves to a target movement position, controlling a robot arm to move to a target joint position, wherein the target movement position and the target joint position are both determined on the basis of the relative position between the target object and a target sensor; and in the process of the robot arm moving to the target joint position or after the robot arm moves to the target joint position, when it is detected by means of a tactile sensor that an external force is applied to the robot arm, performing compliance control on the support robot. Further provided are a support robot, an electronic device, a computer storage medium, and a computer program.

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.

The invention discloses an eye movement tracking method, an eye movement tracking device, eye movement tracking equipment, computer equipment and a storage medium. The method comprises the following steps: calculating calibration gaze information and a calibration pupil position according to first event data collected by an event camera; determining a region of interest based on the calibrated pupil position; processing second event data collected by the event camera according to the region of interest to generate region of interest data, the collection time of the second event data being later than the collection time of the first event data; according to the region-of-interest data, calculating a current fixation position offset; according to the calibration gaze information and the current gaze position offset, the current gaze information is determined, the calibrated pupil position is updated based on the current gaze position offset, the gaze direction, the moving direction and the moving distance of the pupil are accurately captured in real time by utilizing the characteristics of high time resolution and the like of the event camera, and the eye movement tracking effect is effectively improved.

Embodiments of the present invention provide a method and apparatus for suppressing transient current of a grid-forming converter, a computing device, a computer-readable storage medium, and a computer program product. The suppressing method comprises: calculating first virtual impedance on the basis of an actual voltage instantaneous value of a point of common coupling; calculating second virtual impedance on the basis of an actual current maximum amplitude of the point of common coupling; and suppressing the transient current of the grid-forming converter on the basis of the first virtual impedance and the second virtual impedance. In this way, by combining the actual voltage instantaneous value of the point of common coupling and the actual current maximum amplitude of the point of common coupling, transient current can be suppressed at the moment when a fault occurs in a grid-forming converter, thereby avoiding misoperation triggering of a protection apparatus, and ensuring that the grid-forming converter can restore stable operation once the fault is removed.

A robot control method, comprising: acquiring the current state parameters of a robot to be controlled at the current moment; calling a state regulator to determine, on the basis of a preset dynamics model and the current state parameters, basic control parameters for each joint of said robot; performing parameter filtering processing on the basic control parameters to obtain safety control parameters for each joint of said robot; on the basis of the safety control parameters for each joint, determining motion control parameters for each joint of said robot; and on the basis of the motion control parameters for each joint, controlling each joint of said robot at the current moment. Further provided is a robot control apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

Computer vision techniques for configuring a robot having a robotic arm to interface with equipment to perform a task. The techniques include: capturing at least one image of the equipment: determining a position of a first alignment feature in the at least one captured image: determining, using the position of the first alignment feature in the at least one captured image, an alignment difference between a current alignment of the robot and the equipment with respect to a prior alignment of the robot and the equipment; and configuring the robot to interface with the equipment based on the alignment difference.

The invention relates to the technical field of unmanned aerial vehicle positioning, discloses an unmanned aerial vehicle accurate positioning method and device fusing multi-source positioning data, electronic equipment, a computer readable storage medium and a computer program product, and is used for solving the technical problem that accurate and stable positioning of an unmanned aerial vehicle cannot be realized in an indoor weak texture scene in the prior art. The method comprises the following steps: acquiring initial positioning data of an unmanned aerial vehicle in real time, the initial positioning data being at least from two information sources; constructing a positioning fusion algorithm based on an unscented Kalman filtering algorithm, evaluating the credibility of initial positioning data from each information source in real time, and calculating a positioning covariance matrix; and adjusting the fusion weight of each initial positioning data based on the positioning covariance matrix, and calling a positioning fusion algorithm to perform weighted fusion on the initial positioning data of each information source to obtain fusion positioning data of the unmanned aerial vehicle. According to the method, the positioning accuracy and stability of the unmanned aerial vehicle in a scene in which GPS signals are lacked and environment textures are weak can be improved.

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.

Embodiments of the present application relate to speech processing technology. The embodiments of the present application provide a data processing method and apparatus based on artificial intelligence, an electronic device, a computer program product, and a computer readable storage medium. The method comprises: acquiring speech, and acquiring emotion data corresponding to the speech; performing first speech content feature extraction processing on the speech to obtain a first speech content feature corresponding to the speech, and performing emotion feature extraction processing on the emotion data to obtain emotion features corresponding to the speech; performing fusion processing on the first speech content feature and the emotion features to obtain a fusion feature corresponding to the speech; and performing animation parameter mapping processing on the fusion feature to obtain controller parameters corresponding to the speech, wherein the controller parameters are used for controlling a virtual object model to be presented in a target image, and the target image matches the content of the speech and the emotion data.

The invention relates to an application method of a GPU (Graphics Processing Unit) in design rule inspection in the field of integrated circuits, in particular to a layout design rule inspection method, system and equipment, a medium and a product. The layout design rule checking method comprises the following steps: inputting initial layout data, analyzing a design rule checking task to be executed, and marking the priority and complexity level of the task; the method comprises the following steps: dividing layout data into a plurality of data blocks according to regions on the basis of regional characteristics of the layout data, distributing tasks and corresponding data blocks to a GPU computing core according to task priorities and complexity levels, and distributing new data blocks according to the overall load condition of the GPU computing core after the GPU computing core completes data block processing, and repeating the steps until all tasks are executed, and outputting a layout design rule check result. The system, the computer equipment, the computer readable storage medium and the computer program product have the same beneficial effects as the layout design rule checking method.

Provided in the embodiments of the present disclosure are an optimal control method and system for a distribution network with a high penetration of distributed generators, and an electronic device, a computer-readable storage medium and a computer program product. The optimal control method is applied to a centralized control platform. The method comprises: on the basis of an association relationship between power outputs of distributed generators at various levels, performing multi-level forecasting on historical power generation data of each distributed generator, so as to obtain a day-ahead forecasted output value of each distributed generator; for each distributed generator, determining a day-ahead output adjustment value on the basis of historical power flow data and an optimal power flow optimization model; and sending to the corresponding distributed generator the output adjustment value and forecasted output value of each distributed generator as centralized control instructions, so that the distributed generator controls an output value during each control period within the day ahead on the basis of an acquired real-time output measurement value, the acquired output adjustment value and the acquired forecasted output value.

The invention relates to a memory management method and device applied to a server-free data center, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: in response to a virtual memory application instruction, performing virtual memory allocation in a local computing resource pool to obtain a virtual address space; in response to the virtual address access instruction, acquiring cache information of the computing resource pool, and triggering missing page interruption under the condition that data corresponding to the virtual address is not hit in the cache information; the cache information comprises locally cached cache data and page table information; acquiring physical memory resources in a memory resource pool according to the virtual address and the page table information under the condition of triggering missing page interruption of the anonymous page; and updating the page table information and the cache information according to the physical memory resources. By adopting the method, the processing delay of the data center can be reduced while the decoupled memory management logic is used for improving the resource utilization rate.

The invention provides a hot upgrade method for a virtual machine monitor (VMM), which comprises the following steps of: pausing the operation of a virtual machine, storing state information of an original VMM, and reserving a kernel-based virtual machine KVM extension page table and a memory management structure of the original VMM; reserving a page global directory and a virtual memory area VMA corresponding to a virtual machine RAM area according to the memory management structure, and refreshing a process address space described by the memory management structure into a new VMM execution program so as to complete switching of the original VMM into the new VMM; and executing the new VMM, recovering the state information to the new VMM, and inheriting the KVM extension page table by the new VMM to recover the operation of the virtual machine. The invention further provides computer equipment, a computer readable medium and a computer program product.

Disclosed in the present application are a data processing method based on a large language model, and a large language model, an electronic device, a computer-readable storage medium and a computer program product. The method is applied to a user terminal, wherein a large language model is deployed on the user terminal, and weight parameters of linear calculation layers of the large language model are pre-quantized into format data of an integer data type. The method comprises: acquiring input data; performing vector conversion on the input data by means of an embedding layer of a large language model, so as to obtain a floating-point query vector of a floating-point data type corresponding to the input data; converting the floating-point query vector into an integer query vector of an integer data type; and performing an operation by means of weight parameters of linear calculation layers and the integer query vector, so as to obtain a query result corresponding to the input data. By means of the solution provided in the present application, a large language model can be smoothly run on a user terminal, such that the user terminal can provide services for users without needing network connectivity, and can better ensure the privacy of the users.

The invention relates to a security authentication method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: receiving a key generation request sent by target equipment; if it is determined that the key generation request is legal, generating a trust identifier and a security certificate of the target device, obtaining an identifier verification request through the trust identifier, and sending the identifier verification request to an authentication server, so that the authentication server verifies the trust identifier to obtain an access token corresponding to the target device; receiving a message returned by the authentication server, and processing an access token carried by the message to obtain a trust identifier; and writing the security certificate into the target protection area, and sending the trust identifier and the security certificate to the target equipment, so that the target equipment is registered in the authentication server. By adopting the method, the identity verification of the equipment and the control of an encryption communication mechanism are realized, and the safety protection performance in a communication system is further improved.

The embodiment of the invention discloses a video generation method and device, electronic equipment, a computer readable storage medium and a computer program product, and the method comprises the steps: generating a rough three-dimensional world of a target scene formed by a three-dimensional Gaussian ball set, and automatically searching a multi-angle offset view angle at the same coordinate position as a new view angle. According to the method, a multi-view-angle combined repairing mechanism is realized, geometric and semantic consistency of image data among different view angles is ensured, consistency of scene structures, textures and semantic information at different observation angles is realized, and a continuous, coherent and high-quality three-dimensional world is constructed. According to the method, the problem of multi-view inconsistency in a traditional method is solved, the new view image quality under large view conversion is improved, the image quality problems of floating objects, artifacts, structural distortion and the like in the image are eliminated, the generated image is more stable and real, the spatial continuity is improved, and the immersion and exploration experience of a user are enhanced.

The embodiment of the invention provides a content display method and device, equipment, a computer readable storage medium and a product, and the method comprises the steps: responding to a first operation triggered by a user for a first theme, and displaying a first display interface associated with the first theme; first content is displayed in the first display interface, the first content comprises media content associated with the first theme and multiple pieces of third content associated with second content, and the second content is generated based on the first theme; and in response to a second operation of the user in the first display interface, displaying a second display interface associated with the first theme, the second display interface being used for displaying the second content. Therefore, the display content in the first display interface can be enriched, so that a user can check more abundant related content of the first theme in the first display interface. In addition, the second user can check the second content in the second display interface more visually.

The invention provides a construction method of a digital twin system, the method is applied to at least one agent, and the method comprises the following steps: obtaining mapping information associated with a physical system; analyzing the mapping information, and generating a resource configuration strategy meeting twin requirements; and generating the digital twin system in response to the resource configuration strategy. The mapping information of the physical system is analyzed through the intelligent agent, the resource configuration strategy adaptive to the twinborn demand is automatically generated, and the consistency of the digital twinborn system and the physical system is further ensured. The invention further provides electronic equipment, a computer program product and a construction device of the digital twin system.

The present disclosure relates to the technical field of high-voltage direct-current power transmission, and provides a surge protection method and apparatus for a fully controlled valve in a controllable line-commuted converter, a computer device, a computer readable storage medium and a computer program product. The method comprises: monitoring a terminal voltage of a fully controlled valve in real time; when a wave turn-off voltage per cycle of a primary IGBT valve exceeds an operating voltage of a surge arrester, subtracting 1 from an available action count of the surge arrester of the primary IGBT valve, and when a wave turn-off voltage per cycle of a secondary IGBT valve exceeds an operating voltage of a surge arrester, subtracting 1 from an available action count of the surge arrester of the secondary IGBT valve; when the available action count of the surge arrester of the primary IGBT valve is less than a second preset count, or when the available action count of the surge arrester of the secondary IGBT valve is less than the second preset count, controlling a converter to return to a power grid line-commutation operation mode; and when the available action count of the surge arrester of the primary IGBT valve is greater than a third preset count, or when the available count of the surge arrester of the secondary IGBT valve is greater than the third preset count, controlling the converter to enter a controllable line-commutation operation mode.

An apparatus, computing device, computer program product, and a computer-implemented method for delivering financial services within a secure, authenticated network environment, and more particularly, for facilitating a quick and efficient manner of performing a mobile deposit of a financial instrument using a distinctive two-dimensional, machine-readable barcode displayed on a surface of the financial instrument. The two-dimensional, machine-readable barcode contains mobile deposit data that includes client PII, and financial data.

The invention discloses a micro burst traffic detection method, network element equipment, a computer readable storage medium and a computer program product, and relates to the technical field of communication, the method is applied to the network element equipment, the network element equipment is provided with a microsecond-level timer, and the method comprises the following steps: counting the number of forwarding message bytes of each sub-time window in a sliding time window; performing mean value calculation on the forwarding message byte numbers of all the sub-time windows in the sliding time window to obtain a sub-window byte number mean value of the sliding time window; determining a sub-window byte number threshold value of the sliding time window based on the sub-window byte number mean value; and determining the state of the sub-time window of which the forwarding message byte number is greater than the byte number threshold value of the sub-window as a flow micro-burst state. According to the invention, the size of the micro-burst flow and the corresponding time delay can be accurately detected in a fine-grained manner, and the detection precision of the micro-burst flow is effectively improved.

The invention provides a robot interaction processing method and device, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: in response to a character configuration operation for a robot, configuring the character of the robot as a target character; in response to interaction operation for the robot, the robot is controlled to interact in a multi-modal mode matched with the target character, and the multi-modal mode comprises at least two of voice, expression and action; in the interaction process of the robot, the target character is updated based on interaction feedback data, and the robot is controlled to interact in a multi-mode mode matched with the updated target character. By means of the robot interaction method and device, the naturalness and vividness of the robot interaction process can be improved.

The invention relates to a KV cache optimization method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: calculating a key vector and a value vector corresponding to each element in a text input sequence input into a large language model; through a multi-head potential attention mechanism, performing low-rank joint compression on the key vector and the value vector to obtain a potential vector, and storing the potential vector in a KV cache space; based on a scaling law, determining an optimal compression dimension, regenerating an adaptive potential vector and updating a KV cache space; for the same text input sequence, generating corresponding query vectors, and grouping the query vectors according to a preset grouping rule; calculating a semantic association weight between each group and the correspondingly called potential vector, and taking the semantic association weight as a group attention calculation result; in the reasoning process, potential vectors and grouping attention calculation results are calculated to calculate attention weights. By adopting the method, the storage requirement of the KV cache can be further reduced.

The invention relates to the technical field of artificial intelligence, discloses a data differential privacy protection method and device for large language model service, electronic equipment, a computer readable storage medium and a computer program product, and is used for solving the problems that in the prior art, a data privacy protection method can reduce the reasoning ability of a large language model, and the data privacy protection efficiency is high. And the privacy protection effect is not good. The method comprises the following steps: acquiring user data and user query, and extracting context content related to the user query from the user data; constructing an undesensitized original orchestration prompt based on the user query and the contextual content; identifying sensitive entities contained in the original arrangement prompt which is not desensitized, and performing differential privacy processing on the sensitive entities to obtain a desensitized anonymized arrangement prompt; sending the anonymization arrangement prompt to the large language model to obtain an anonymization response result generated by the large language model; and performing reverse reduction on the anonymization response result to obtain a de-anonymization model response result.

The embodiment of the invention provides a model optimization method and device, computer equipment, a computer readable storage medium and a computer program product, and relates to the technical field of computers. The method comprises the following steps: acquiring a target initial frame picture and a target text prompt; taking the target initial frame picture and the target text prompt as model input, and outputting a plurality of training videos through a preset video generation model; scoring the plurality of training videos to obtain a reward score corresponding to each training video; according to the reward score corresponding to each training video, determining a reward score difference between the highest reward score and the lowest reward score; and according to the reward score difference, adjusting a preset video generation model to obtain a target video generation model. According to the technical scheme of the embodiment of the invention, the speed and effect of the model optimization process can be improved, and the quality of the video generated by the optimized target video generation model is improved.

The invention relates to a lithium battery health state prediction method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: collecting multi-dimensional time sequence data generated by a lithium battery charging and discharging experiment, and processing the multi-dimensional time sequence data to generate a model input sequence; inputting the model input sequence into a deep neural network to obtain a time derivative of the state of health of the lithium battery at the current moment, and pre-training the deep neural network; inputting the model input sequence into a Bayesian LSTM network, outputting a predicted value of the lithium battery health state at the next moment, pre-training the Bayesian LSTM network, and performing uncertainty estimation on the predicted value of the lithium battery health state at the next moment; and constructing a total loss function, jointly training the deep neural network and the Bayesian LSTM network by using the total loss function to obtain a target prediction model, and predicting the state of health of the lithium battery. By adopting the method, the health state of the lithium battery can be predicted in a high-precision, high-reliability and high-adaptability manner.

The invention relates to a large model energy consumption optimization method and device, computer equipment, a computer readable storage medium and a computer program product. Comprising the steps of collecting hardware state data and task data of a large model; performing stage identification according to the task data, and determining a current stage; performing state prediction according to the hardware state data and the task data through a prediction model corresponding to the current stage to obtain target state information; generating optimization parameters of the current stage through a joint optimizer according to the target state information; and adjusting the resources of the large model according to the optimization parameters. In combination with stage perception and dynamic resource adjustment, a differentiated resource adjustment strategy based on different stages is realized, specific energy consumption pain points in an AI scene are solved, high power consumption of large model training, instantaneous fluctuation of reasoning requests and the like are reduced, sustainable and efficient operation of an AI system is ensured, the computing power demand and resource consumption of a large model are balanced, and the system performance is improved. And wide landing and development of a large model in various scenes are facilitated.

The invention relates to a data processing method and device, computer equipment, a computer readable storage medium and a computer program product. After first matrix data is obtained, tensor data to be processed are obtained, and the tensor data are distributed to a plurality of calculation units; calculating a local feature value corresponding to the target calculation unit according to the local tensor data allocated to the target calculation unit; dividing the target calculation unit into data blocks corresponding to the number of the plurality of calculation units; according to the serial number of the data block, mapping the local feature value recorded in each data block to a target storage block of a target memory until the local feature value in each calculation unit is distributed to the corresponding storage block in the target memory, and obtaining a global feature value table; according to the global feature value table, feature value calculation is carried out to determine the target feature value, conflict-free parallel calculation is achieved, the utilization rate of calculation resources is increased, and the data processing efficiency is improved.

The invention discloses a cerebral hemorrhage image recognition method, and aims to solve the problems that different cerebral hemorrhage focuses have significant differences in form, size and position, and cerebral anatomical structures of different individuals also have significant differences, so that the features of cerebral hemorrhage images are complex and changeable, and the recognition accuracy is high. Therefore, a traditional image processing method is difficult to accurately identify the key information of the focus in the cerebral hemorrhage image. The method comprises the steps of obtaining a cerebral hemorrhage image; the cerebral hemorrhage image is input into the trained cerebral hemorrhage image recognition model to obtain a recognition result output by the model, and the recognition result comprises the lesion type, position and size of the lesion in the cerebral hemorrhage image; wherein the cerebral hemorrhage image recognition model is obtained by training an enhanced cerebral hemorrhage image sample obtained by performing elastic deformation processing on a cerebral hemorrhage image sample. The invention further discloses a cerebral hemorrhage image recognition device, electronic equipment, a computer readable storage medium and a computer program product.