47results about How to "Implement deployment" patented technology

The embodiment of the invention provides a fault alarm self-healing system and method, and the system comprises a micro-service target unit, a management unit, a monitoring collection unit, a data calculation unit, and a plan processing unit, and the management unit is used for determining a to-be-added monitoring collection task and a to-be-deleted monitoring collection task according to the monitoring information carried by each metadata; the monitoring acquisition unit is used for acquiring monitoring index data according to a to-be-added monitoring acquisition task and sending the monitoring index data to the data calculation unit; the data calculation unit is used for detecting the monitoring index data in real time according to a preset index detection rule and generating time sequence index data according to a first detection result; the monitoring index data and the time sequence index data are detected in real time according to a preset anomaly detection rule, and an anomaly event is generated according to a second detection result; and the plan processing unit is used for retrieving a fault self-healing scheme matched with each abnormal event and carrying out fault self-healing processing on the abnormal events according to the fault self-healing scheme.

The invention discloses a large model deployment method and device for a heterogeneous platform, equipment and a program product, and relates to the technical field of artificial intelligence. A large model to be deployed is divided into a plurality of sub-models, and according to the operator type and the operator calculation amount contained in each sub-model, the operator support conditions of various types of chips on the heterogeneous platform are combined, so that the large model deployment efficiency is improved. The method comprises the following steps: determining a target chip to be deployed by each sub-model, determining a quantization strategy of each sub-model according to a quantization support condition of the target chip, quantifying the sub-model according to the quantization strategy, and generating a deployable sub-model from the quantized sub-model and the quantization strategy so as to be deployed into a corresponding target chip on a heterogeneous platform. And automatic deployment of a large model is realized. According to the method, the target chip to be deployed by the sub-model can be automatically selected in the large model deployment process, the quantization strategy can be automatically selected, and compared with a method of manually setting a deployment scheme, the deployment efficiency can be greatly improved, and the end-side deployment difficulty of the large model can be reduced.

The invention discloses an Internet of Things system TAP rule generation method and device based on a large language model, and the method comprises the steps: (1) extracting information from an object model file of equipment, and organizing the information into a proper format; (2) screening out related contents from the equipment information according to user requirements; (3) generating a TAP in a proper format based on the LLM according to the requirements of the user and related equipment information; and (4) converting the TAP format generated by the LLM into a TAP of an actual platform through a Translator component to realize deployment. The core of the method is to define a universal equipment description format and a TAP format, convert user requirements into a universal TAP by means of LLM, and translate the universal TAP into a format required by an actual platform to realize deployment. The method has the advantages that a user can create the TAP in a natural language, manpower and time for realizing simple and repeated work are saved, the method is not limited to a certain specific Internet of Things platform, and the system can be applied to Internet of Things systems needing to create a large number of TAPs in different scenes through proper adjustment and has wide applicability.

The embodiment of the invention provides a base station antenna and a base station. The base station antenna comprises a first antenna array, a metasurface lens and a second antenna array, the metasurface lens is located between the first radiator of the radiation unit of the first antenna array and the second antenna array, and is used for reflecting a radiation signal of the first antenna array and carrying out wavefront phase regulation and transmission on the radiation signal of the second antenna array. Therefore, the radiation signal of the second antenna array penetrating through the metasurface lens is approximately focused into a plane wave. The base station comprises the base station antenna. According to the scheme, a common-caliber array antenna can be realized, the defects of mutual shielding of antennas and mutual interference of antenna performance are avoided, the problem of structural interference can be avoided, and the antenna gain can be improved.

The embodiment of the invention provides a sound signal processing method and electronic equipment, and the method comprises the steps that a digital signal processor DSP outputs a second sound signal by preprocessing a first sound signal; the DSP transmits the second sound signal to the neural network processor NPU through the central processing unit CPU; receiving a third sound signal output by the NPU, the third sound signal being a sound signal obtained by performing deep neural network processing on the second sound signal by the NPU; and the DSP outputs a target sound signal by post-processing the third sound signal. According to the method and the electronic equipment, the DSP and the NPU in the terminal equipment can establish the transmission channel through the CPU, so that the terminal equipment can utilize computing power resources of the DSP and the NPU, the operation performance of the equipment can be improved, and the processing capacity of the equipment on sound signals can be improved due to the fact that the deep neural network processing capacity of the NPU is called.

The invention discloses an application program deployment method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: acquiring a dependent toolkit of an application program during running, and distributing a classification attribute corresponding to the dependent toolkit for the application program; generating dependency information of the application program based on the dependency toolkit, determining a compiling mode of the application program according to the classification attribute, compiling the application program according to the compiling mode, and generating a compiling package of the application program; and adjusting a deployment environment of the application program according to the dependency information, and deploying a compiling package of the application program in the adjusted deployment environment. According to the embodiment, standard and normalized application program deployment is realized, the influence of factors such as a programming language and an operation framework of the application program on deployment online is shielded, the deployment process is simplified, and the deployment efficiency is improved.

The invention discloses a data deployment method and device based on a dynamic application memory and a storage medium, the data deployment method comprises the following steps: in response to received to-be-deployed data, performing data comparison processing on the to-be-deployed data and deployed data in an image acquisition device to obtain a data comparison result; if the data comparison result represents that data change exists between the to-be-deployed data and the deployed data, applying for a target memory from the image acquisition device based on the to-be-deployed data; and performing deployment processing on the to-be-deployed data based on the target memory. According to the scheme, the flexibility of data deployment can be improved.

The embodiment of the invention provides a model deployment scheme generation method and device, a model processing method and device and electronic equipment, and relates to the technical field of model deployment, large language models and the like. According to the specific implementation scheme, processor parameters of all processors in target equipment are obtained, wherein the target equipment is used for deploying a to-be-deployed model; based on the model information and the processor parameters, a deployment scheme is generated, the deployment scheme comprises first specified information, the to-be-deployed model comprises a plurality of processing layers, and the first specified information is used for specifying processors deployed by model weights of the processing layers. Based on the deployment scheme provided by the embodiment of the invention, reasonable deployment of processor resources in the target equipment can be realized, so that reasonable deployment of the model in the target equipment is realized.

The invention provides an infrared ship identification method and system based on wavelet transform deformable convolution and efficient additional attention, and belongs to the field of deep learning. Creating a model based on a classical target detection algorithm RT-DETR principle, reproducing initialization, and constructing and processing an infrared marine ship data set; an RT-DETR target detection algorithm is improved into a wavelet transform deformable convolution and efficient additional attention network model architecture, an infrared marine ship data set after data processing is used in a model framework, related parameters are debugged to perform iterative training on the wavelet transform deformable convolution and efficient additional attention network model, and an expected test effect is obtained; in order to expand the application range of the algorithm, the model is packaged, stored and deployed to an artificial intelligence development board. According to the method, the problems of low target contrast, large complex sea clutter influence, multi-scale target shielding and the like in the infrared image can be solved, and the ship target detection precision and robustness in the complex marine environment are remarkably improved.

The invention discloses a high-fidelity audio generation method and device and a storage medium, and the method comprises the steps: carrying out the down-sampling interpolation or low-pass filtering of a high-fidelity audio data set, and generating a frequency spectrum missing audio data set; inputting the frequency spectrum missing audio data set into a teacher model for prediction, and generating a predicted high-fidelity data set; performing audio feature extraction on the frequency spectrum missing audio data set; training a student model by taking the audio features as input and taking a real label extracted from the high-fidelity audio data set and a soft label extracted from the predicted high-fidelity data set as training labels to obtain a high-fidelity audio generation model; and extracting the audio features of the collected frequency spectrum missing audio, and inputting the audio features into the high-fidelity audio generation model for prediction to obtain the high-fidelity audio. According to the method, the student model with low time delay and small calculation amount is trained in a knowledge distillation mode, so that deployment at a hardware end is realized, and the technical problems that an existing large model is high in time delay, large in calculation amount and difficult to deploy at the hardware end are solved.

The present disclosure provides a software deployment method and device, electronic equipment and storage medium, which can be applied to the fields of computer technology, intelligent operation and maintenance, finance or other fields. The method comprises: in response to triggering a deployment task for a target environment, obtaining a target software deployment rule related to the target environment and a to-be-deployed software list; determining target software corresponding to the target software deployment rule from the to-be-deployed software list; creating a first target deployment instance based on the target software deployment rule in the case that a deployment state of the target software meets a preset condition; configuring the first target deployment instance based on a version number of the target software and an identifier of the target environment to obtain a second target deployment instance; and deploying the target software in the target environment based on the second target deployment instance.

The application belongs to the technical field of integrated circuits, and discloses a circuit structure for one-step solution of linear equations based on a memristor array, wherein the linear equations are Ax=b, and in the circuit, a first memristor array matrix operation core realizes mapping of the matrix A, takes a negative value of a first operation voltage vector as a bit line voltage, performs a matrix multiplication operation, reads a word line current as a first operation current vector after the operation, a bias mapping module maps b into a bias current vector, a current superposition module superimposes the first operation current vector and the bias current vector to generate a superimposed current vector, and converts the superimposed current vector into a second operation voltage vector through a transimpedance amplifier module, a second memristor array matrix operation core realizes mapping of the matrix A, takes the second operation voltage vector as a bit line voltage, performs a matrix multiplication operation, reads a word line current, and performs an integral operation on the word line current through an integrator module to obtain an updated first operation voltage vector. T The above hardware circuit can realize solution of the linear equations.

The utility model discloses a kind of semitrailer tarpaulin devices, comprising: semitrailer floor, the top of the semitrailer floor is fixedly connected with vertical plate, the top of the vertical plate is fixedly connected with top plate, the top of the semitrailer floor is fixedly connected with the side of head baffle;Top shielding component, the top of the head baffle is fixedly connected with the side of top shielding component, side shielding component, the side of the vertical plate is fixedly connected with the side of side shielding component, the tail shielding component is used to adopt tarpaulin shielding to the tail of semitrailer, the utility model relates to tarpaulin device technical field.The semitrailer tarpaulin device, by the setting of top shielding component, by driving motor directly driving threaded block drives the rotation axis of far end to move outward, first tarpaulin is spread over the top of entire semitrailer, and first tarpaulin is carried by multiple rotation axes, can evenly share tarpaulin quality, avoid causing equipment overload in moving process.

This invention provides a flexible production line control method and system based on a large vertical domain model. The method includes: constructing a pruning index combining temporal stability and spatial similarity for the original large vertical domain model to evaluate the redundancy of the activation tensors in the intermediate layers, and performing structured pruning accordingly to obtain a sparse structure model; performing mixed-precision quantization on the pruned model: allocating quantization bits according to the sensitivity of each network layer weight to task loss, and calculating scaling factors and zeros based on the range of non-zero weights to represent sparse weights; calculating the output deviation between the quantized pruned model and the original model under the same input, and training a feedforward network with the former's output as input to fit and compensate for the output deviation; combining the quantized pruned model and the feedforward network to form a composite control model; after deployment, adding the output command of the quantized pruned model to the compensation vector during inference to generate control commands.

The present invention discloses a device for mitigating application software vulnerabilities in a container without any sense and a mitigation method thereof, the device comprising: a container initiator additional process unit, used to modify the dynamic linking order of the application software vulnerability mitigation strategy loading unit and the application software vulnerability mitigation strategy execution unit to take precedence over the dynamic linking order of the dynamic link library in the container; an application software vulnerability mitigation strategy loading unit, used to load and initialize the application software vulnerability mitigation strategy; an application software vulnerability mitigation strategy execution unit, including copies for different dynamic link library calls, each copy is used to execute the corresponding application software vulnerability mitigation strategy according to the call of the corresponding dynamic link library. By implementing the present invention, after the application software vulnerability mitigation strategy is loaded and executed, matching and filtering of known vulnerability exploitation programs is achieved, so that users are free from targeted known vulnerability exploitation attacks.

The invention relates to the field of computer vision, in particular to a human face deep forgery detection method based on StreamLit and a multiple attention deep forgery detection network. On the basis of an OfficientNetv2s network in combination with a Haar feature algorithm and a face-recovery method in dlib, real-time face detection can be carried out on embedded equipment through a 3D depth camera, and multi-terminal deployment is supported. The feature extraction capability of the model is enhanced by adopting an attention mechanism, and deep counterfeiting detection is performed through an MAD method, so that an excellent effect is achieved. Experimental results show that the detection performance of the system on data sets such as WIDER FACE, Celeb-DF, DFDC and the like is remarkably superior to that of other existing methods, and meanwhile the system has high robustness and real-time performance. The technology can be effectively applied to face video forgery detection and identity verification, and is suitable for mobile terminal and embedded equipment scenes.

The invention discloses an IRS-assisted active node deployment and channel estimation method for a communication-inductance integrated system, and belongs to the technical field of wireless communication. The method comprises the following steps: establishing a channel model based on the antenna array response and channel characteristics of the IRS-assisted communication and inductance integrated system; an active node is arranged on the surface of the IRS in the IRS-assisted communication-inductance integrated system to collect and observe a channel value of a channel model, and an IRS receiving signal model after a base station sends a pilot frequency to the IRS is established based on the channel value; establishing a channel graph topological structure matrix; the channel graph topological structure matrix is subjected to graph segmentation based on spectral clustering clustering, the most smooth node of each cluster is selected for sampling, and deployment of active nodes is carried out; and introducing graph smoothing constraint according to the local smoothing characteristic of the channel graph topological structure matrix, obtaining a linear objective function based on atomic norm minimization, solving to obtain a channel estimation result, and completing channel estimation. According to the method, the accuracy and the stability of channel estimation in different scenes can be ensured.

The invention provides a software development environment construction method and system, electronic equipment and a medium. The software development environment construction method comprises the following steps: generating a script file required by a software development environment, wherein the script file is used for constructing a development environment consistent with a basic environment template; making a mirror image based on the script file, and deploying the mirror image to different development links of the software development environment; in the mirror image, compiling and packaging the to-be-published source code which is checked to be correct to obtain a to-be-published software package; and under the condition that the to-be-released software package is matched with the environment of the application server, pushing the to-be-released software package to the application server.

The invention provides an attention mechanism improvement-based lightweight Taijiquan scoring method and related equipment, and the method comprises the steps: carrying out the preprocessing of a Taijiquan video, inputting the preprocessed Taijiquan video into a skeleton point extraction network, extracting the skeleton point features in each frame image, and obtaining a skeleton point sequence file; inputting the skeleton point sequence file into a long short-term memory network, identifying a Tai Chi style, distributing a weight for each skeleton point, and generating a weighted skeleton point sequence; obtaining a standard shadowboxing video, and calculating the score of the shadowboxing video based on the standard shadowboxing video; with the adoption of the method, the time sequence dependence in the shadowboxing type can be captured by utilizing the long-short-term memory network, and the weight is distributed to each skeleton point by utilizing the attention mechanism, so that the system can dynamically adjust the focus point according to the characteristics of different actions, and the accuracy of action recognition and analysis is improved; and the accuracy and objectivity of shadowboxing scoring are improved.

The present invention discloses a model development system, which specifically includes: multiple Dockers, which are used to execute multiple task steps in the model development process; a scheduling module, which is used to configure the startup sequence and startup parameters of each Docker, and start each Docker in sequence according to the startup sequence of each Docker, and execute the task steps corresponding to the Docker in the model development process until all task steps are completed to obtain a developed model; a training log generation module, which is used to record the relevant computing task information of each Docker when executing the corresponding task steps, and form a training log file; a model deployment module, which is used to deploy the developed model to an application system. In the solution provided by the embodiment of the present invention, the development process is unified, and the algorithm environment is managed in a unified standard; and monitoring and backtracking of the entire model development process, as well as multiple model deployment methods, are provided.

The present invention discloses a method and system for constructing a virtualized security component of an electric power Internet of Things, the method comprising: obtaining a core basic image corresponding to the current application environment, current security requirements, and the minimum operating environment of the security component of the location to be deployed; based on the current application environment and the current security requirements, screening security component images from a preset security component image library to form a security component image set, the preset security component image library is used to store the application environment, security requirements, and mapping rules between security components; constructing a virtualized security component based on the core basic image and the security component image set. The present invention presets the application environment, security requirements, and mapping rules between security components, and can quickly find the required security component image based on the mapping relationship based on the security requirements and the application environment, thereby quickly realizing the deployment of the security component, ensuring the timely response of security protection, and this construction method is conducive to the rapid change of security components.

The invention discloses a psychological stress machine learning combination model classification method and device, equipment and a medium, and belongs to the technical field of psychological stress recognition. The method comprises the following steps: acquiring original ECG data, and acquiring HRV data according to the original ECG data; constructing a plurality of different classification models, and training each classification model by adopting the obtained HRV data; forming a combined model by the plurality of trained classification models, and obtaining a final classification result through a voting mechanism; wherein in the process of training the classification models, the HRV data and the multiple classification models are distributed to the multiple calculation units in a parallel calculation mode, so that each calculation unit independently trains one classification model. According to the method, various machine learning method models are combined, the advantages of various machine learning methods and deep learning methods can be combined, the generalization ability of model prediction classification is improved, and the prediction accuracy of the model is effectively improved.

The invention discloses a network equipment management system and method based on an SNMP (Simple Network Management Protocol). The network equipment management system comprises a central server, a network channel, a plurality of distributed proxy nodes and a plurality of network equipment, the distributed proxy node is connected with network equipment through an SNMP protocol; and the central server is used for interacting with the distributed agent nodes, realizing front-end and rear-end interaction, performing identity verification, decrypting the equipment encrypted data and displaying the equipment encrypted data. According to the invention, cross-platform access and deployment are realized, complete network management is supported, and all network devices in the system are comprehensively managed; operation is performed through the user interface, the operation mode is simple, the working efficiency of a network administrator is improved, the working quality is ensured, and the management cost is saved; and the security and the reliability of information between the network devices are improved through the encryption algorithm unit.

This application provides an image contrast enhancement method, system, electronic device, and storage medium. The method includes: separating luminance and chrominance components from the YUV data of an input image; training the luminance component for contrast enhancement using an enhancement network model to obtain an enhancement coefficient grid for the luminance component and compensation coefficients for the chrominance component; enhancing the luminance component using the enhancement coefficient grid and enhancing the chrominance component using the compensation coefficients; and obtaining an enhanced image based on the enhanced luminance and chrominance components. This application can significantly reduce computational complexity while maintaining contrast enhancement effects, and can also suppress noise and eliminate video flicker.

Provided in an embodiment of the present application are a core network spaceborne deployment method, apparatus, device and storage medium, the method comprising: for a first cell, based on a service parameter of the first cell, determining a target type corresponding to the first cell, the first cell being a cell whose network element demand or network element deployment changes, and the target type corresponding to the first cell being a cell whose network element deployment changes; the target type is the type of the network element required by the service of the first cell; for each target type, if there is no network element of the target type in the deployed network elements in the available satellites corresponding to the first cell, deploying the network elements of the target type in the available satellites based on the remaining resources of the available satellites; and otherwise, based on the service parameters corresponding to the target type and the available network element resources of the target type, determining whether to deploy a new network element of the target type in the available satellite. By creating and using the on-satellite core network resources as required, the use efficiency of the on-satellite resources is improved, and the service requirements of different cells are met.

The invention relates to the technical field of computers, and provides an application deployment method, device and equipment and a storage medium, and the method comprises the steps: obtaining a service package of each target service of a to-be-deployed application, and deployment parameters configured by each target service; obtaining available resources in the computing power resource pool, and determining deployment resources corresponding to the target services according to the deployment parameters and the available resources; the deployment resources comprise at least one of local resources, private cloud resources and public cloud resources, and the computing power resource pool is obtained by carrying out computing power fusion on the local resources, the private cloud resources and the public cloud resources; and distributing the service package of the target service to the corresponding deployment resource for deployment. By integrating the resources, hybrid deployment of the applications is achieved, unified planning and deployment of the computing power resources are achieved, the deployment requirements of rapid iteration and continuous delivery of the applications under multiple types of computing power resources are met, the flexibility of application deployment is improved, and resource configuration is optimized.

The invention relates to the technical field of cluster deployment, and provides a big data cluster dynamic deployment method and device, equipment, a product and a storage medium. The method comprises the steps of obtaining a resource demand template based on a prediction type of a calculation task; generating a trigger event based on the monitoring signals in the sub-clusters of the plurality of calculation modes; generating a deployment rule based on the trigger event; based on a calculation mode required by the calculation task, constructing a big data cluster deployment model; and dynamically deploying the big data cluster based on the big data cluster deployment model and the deployment rule. Changes of computing resource requirements of big data in different computing modes can be sensed in real time and are sequentially associated with the trigger event, the deployment rule and the big data cluster deployment model, overall deployment of the big data cluster is achieved, the utilization rate of cluster resources is effectively increased, and the deployment efficiency is improved. And resource dynamic deployment requirements for different calculation modes in big data processing are met.

The invention relates to a software deployment method and device in an offline environment, computer equipment and a medium, and the method comprises the steps: obtaining an input software demand version and target environment key elements; searching for target deployment medium detailed information in a preset deployment medium library according to the input software demand version and the target environment key elements, wherein the deployment medium library stores deployment medium detailed information corresponding to different software versions and different target environment key elements; pulling a dependent medium from the plurality of medium sources according to the detailed information of the target deployment medium; packaging the pulled dependent medium and a preset script to generate a deployment package, wherein the preset script is used for executing automatic software deployment operation; and transmitting the deployment packet to the deployment object in an offline mode. According to the whole scheme, efficient and accurate software deployment in an offline environment can be realized.

The application provides a task processing method and device based on a multi-cloud server and a server, relates to computer technology, and the method comprises the following steps: acquiring test plan information; if it is determined that the preset configuration information of the cloud server for the corresponding task is successfully deployed and the current time reaches the start time, then the multiple cloud servers are controlled to run the task corresponding to each cloud server, the resource utilization of each cloud server is monitored, and monitoring result information of each cloud server is obtained; if it is determined that the monitoring result information represents that the resource utilization of the cloud server is lower than a preset threshold, then the task running in the cloud server with the resource utilization lower than the preset threshold is called according to a task calling strategy, and test result information of each cloud server based on the running of the corresponding task is obtained. The application realizes server management and deployment, test plan and real-time calling management of UI automation testing, and solves the problem of low task test efficiency.

The application relates to a pressure test method, system, device, computer equipment and storage medium, the method comprising: in response to a pressure test request for a test object, determining a pressure test parameter corresponding to the pressure test request; based on a test script file stored in a pressure test platform, obtaining a test instruction corresponding to the pressure test parameter; calling a target execution device from a plurality of pressure test execution devices preset in the pressure test platform, and sending the test instruction to the target execution device to instruct the target execution device to perform pressure test on the test object based on the test instruction, thereby realizing automatic application and deployment of the pressure test execution device and effectively improving the allocation and use efficiency of pressure test resources.