13 results about "Domestic environment" patented technology

The invention discloses an AI-based localized environment application offline deployment method and device and a medium. The method comprises the steps that a localized environment is pre-detected based on probe service, a system layer configuration list is generated, heterogeneous features are extracted through a dual-channel deep learning model based on the system layer configuration list, and adaptive priority labels of the heterogeneous features are generated; the method comprises the following steps: analyzing an application program through static analysis and dynamic scanning technologies, constructing a dependency list, and constructing a version compatibility atlas based on metadata of a domestic operating system warehouse; generating a minimum-cost replacement path by using a graph attention network, performing hash check on each dependency packet, and generating an incremental update packet through a differential packaging algorithm; the resource occupation condition of the system is monitored in real time through a reinforcement learning model so as to dynamically optimize a deployment sequence and a resource allocation strategy, a deployment log is analyzed based on a natural language processing model, an error type is recognized, a repair operation is triggered, and application offline deployment is achieved.

The invention relates to a domestic environment-oriented power application performance anomaly detection method and system, and the method comprises the following steps: S1, obtaining a domestic basic environment, power real-time data, an application system performance index and a business operation log, and carrying out the preprocessing, and obtaining a multi-dimensional time series data matrix; s2, performing feature engineering and feature optimization based on the multi-dimensional time sequence data matrix to obtain an optimized feature matrix; s3, constructing a multi-level AI anomaly detection model based on the optimized feature matrix in combination with historically labeled anomaly samples; s4, according to the multi-level AI anomaly detection model and the preprocessed real-time data, obtaining an anomaly detection result; and S5, according to an anomaly detection result, obtaining an alarm strategy and a disposal white list, and converting the anomaly detection result into operable alarm and disposal. According to the method, the operation and maintenance pressure and the response risk are powerfully reduced, and the whole-process intelligent and refined management from anomaly detection to alarm disposal is realized.

The invention relates to a distributed performance testing method and device oriented to a domestic environment, and the method comprises the following steps: defining a data model, defining a Mock generation function of each field, generating a basic Mock value for each field according to the Mock generation function, and enabling the basic Mock value to serve as a final field value or an intermediate value, performing rule calculation or splicing to obtain final field values, and combining the final field values to obtain simulation data; the main control mechanism constructs a time sequence vector of each node, forms a whole network performance matrix by using a plurality of node data, calculates a performance score and identifies a bottleneck, and completes a performance test; and setting an early warning value for the monitoring parameter, and meanwhile, analyzing a parameter value at the next moment through an intelligent analysis model, and carrying out pre-judgment. The method has the advantages that 1) the dynamic configuration capability of the structured data pool and the Mock engine is utilized to realize a data constructor close to a real scene, and 2) the main control computer synchronously integrates multiple test results to realize second-level bottleneck positioning.

The invention relates to a liquid level measuring device for process automation in an industrial or domestic environment, comprising a control circuit configured to selectively perform a liquid level measuring operation of the liquid level measuring device in a first operating mode or a second operating mode, wherein the second working mode has interference echo suppression different from that of the first working mode.

The invention relates to an adaptive model evaluation and optimization method based on a domestic operating system, and belongs to the technical field of deployment and optimization of AI models. According to the method, resource management characteristics of a domestic operating system are deeply integrated, an adaptive model evaluation and optimization framework is provided, and the core contradiction between resource limitation and model efficiency imbalance in a domestic environment is solved.

The utility model relates to a dust collector of convenient folding storage belongs to dust collector technical field, including dust collector main part and positioning frame, the dust collector main part top is provided with the storage subassembly of convenient folding storage, the storage subassembly includes the rotary frame fixed mounting at the dust collector main part top, the inboard rotation of rotary frame is connected with the push -hand, the front of push -hand is fixedly connected with fixed frame, the inboard fixed connection of fixed frame has spring and sliding rod, the middle part fixed connection of lifter plate has pull rod, the top fixed connection of pull rod has pull frame, the top fixed connection of dust collector main part has fixed cover, the inboard of positioning frame is provided with the adsorption fixed component for dust collector main part spacing, the dust collector of convenient folding storage, through setting up storage subassembly, has realized folding storage function, has carried out folding storage, avoided the domestic environment to appear disorderly, effectively reduced the burden of user.

The utility model discloses a pull-out type washing device which comprises a shell, a pull-out type washing device and a washing device body. The rear plate comprises a rear back plate and a rear connecting plate located on the lower side of the rear back plate. The rear connecting plate is provided with a plate body and a concave mounting groove formed in the inner side of the plate body, and a waterway connecting piece is arranged in the mounting groove; the shell is provided with a stretching-in opening for an outer water pipe to stretch in, the outer water pipe is a water supply pipe and / or a water drainage pipe, and the stretching-in end of the outer water pipe is connected with an outer end opening of the water way connecting piece. The concave mounting groove is formed in the rear connecting plate, the waterway connecting piece is arranged on the mounting groove, the original protruding part of the waterway connecting piece can be contained in the concave space of the mounting groove, the size of the equipment in the depth direction can be reduced, and the whole equipment is more compact in the depth direction; and the device is more suitable for being placed in a home environment with limited space. The outer water pipe extends into the shell, so that the outer water pipe does not occupy the space in the front-back direction.

The application relates to a power application performance anomaly detection method and system facing a domestic environment, which comprises the following steps: S1: obtaining a domestication basic environment, power real-time data, application system performance indexes and business operation logs, and preprocessing to obtain a multi-dimensional time sequence data matrix; S2: based on the multi-dimensional time sequence data matrix, performing feature engineering and feature optimization to obtain an optimized feature matrix; S3: based on the optimized feature matrix, combining historical labeled abnormal samples, and constructing a multi-level AI anomaly detection model; S4: according to the multi-level AI anomaly detection model, according to the preprocessed real-time data, obtaining an abnormal detection result; S5: according to the abnormal detection result, obtaining an alarm strategy and a disposal whitelist, and converting the abnormal detection result into an operable alarm and disposal. The application effectively reduces operation and maintenance pressure and response risk, realizes intelligentization and fine management of the whole process from abnormal detection to alarm disposal.

The invention discloses a core and cable material reclassification method and system based on a domestic environment, and belongs to the technical field of cable quality detection.The implementation of the method comprises the following steps that picture information is obtained, and pictures are preprocessed; the processed picture information is transmitted to a server through tcp, and the server sends data to a domestic reasoning board card for reasoning; a wire core area frame is calculated through post-processing, then the area frame is cut into square areas with the same size through a cutting algorithm, and a coordinate point set of each square area is stored; cutting the original picture through the obtained coordinate point set, and preprocessing the target picture; and the server side returns the identification information, and stores the coordinate point set of the suspected material caking area for use after classification pretreatment. According to the invention, the problem of low detection accuracy of the caking defect in the surface defects of the cable core and cable in the cable industry can be solved, the accuracy of defect detection is improved, the defects are classified, and the probability of caking false detection is reduced.

The invention discloses a localized adaptation test method, device and equipment and a storage medium, and relates to the technical field of data test.The method comprises the steps that a safety penetration test is conducted on a tested system through a penetration test tool, and safety penetration test data are obtained; performing functional test on the tested system based on the functional test case to obtain functional test data; when the safety penetration test and the functional test are completed, accessing the tested system into a localized environment to carry out a credential test to obtain credential test data; and generating an adaptive test result of the tested system based on the security penetration test data, the functional test data and the credential test data. By applying the technical scheme, the technical problems that in the prior art, in the adaptation testing process of domestic software and hardware in the domestic environment, adaptation testing work is usually conducted in an offline manual mode, the testing process is tedious, and the testing efficiency is not high are solved.

The invention relates to the technical field of computers, and provides an eye movement tracking method and device based on a domestic platform terminal, equipment and a medium, and the method comprises the steps: collecting eye video data and environment scene data of a user, and transmitting the data to the domestic platform terminal; determining the sight line direction of the user according to the eye video data through a domestic platform terminal, and calibrating the sight line direction based on the environment scene data to establish a mapping relationship between the sight line direction and the spatial position; according to the calibrated sight line direction and the mapping relation, the fixation point of the user in the environment scene is obtained through calculation. According to the scheme, on the premise of not depending on specific expensive hardware, the general computing power of a domestic platform terminal is fully utilized, a set of eye movement tracking scheme which is high in compatibility, low in cost, reliable in processing flow and standard in data output is achieved, and popularization and deep application of the technology in a domestic environment are powerfully promoted.

The utility model relates to the technical field of direct drinking machines, and discloses a table type small cold and hot direct drinking machine which comprises a shell, a touch screen is arranged at the top end of the front end of the shell, a water tank is vertically embedded into the rear end of the shell, a water inlet is correspondingly formed in an end cover of the shell above the water tank, and a filtering and purifying core is installed at the bottom end in the water tank. The water dispenser can be directly placed on a table top to be used through the shell, the shell can be directly hung on a wall to be used through the connecting assembly by means of matching of the rotating butt strap and the connecting assembly, and due to the fact that the limiting supporting plate, the U-shaped block and the like are vertically inserted and connected in a lap joint mode, installation operation is simpler and more convenient, and use is more convenient. And meanwhile, the external structure of the shell cannot be damaged when the shell is disassembled and assembled, so that various placement and use modes of the shell are realized, and the shell can be more suitable for being used in various family environments.

The utility model provides a wearable bracelet for formaldehyde gas detection, and belongs to the technical field of detection. The flexible formaldehyde gas sensor comprises a semiconductor sensing chip, a flexible electrode, a copper foil circuit, a binding post, a flexible printed circuit board, a resistor, a signal amplification unit, a microcontroller, a crystal oscillation circuit, a power supply, an LED indicating lamp and a substrate layer, the binding posts are connected with a circuit on the flexible printed circuit board; the resistor, the signal amplification unit, the microcontroller, the crystal oscillation circuit, the power supply and the LED indicating lamp are connected through a circuit on the flexible printed circuit board; the flexible printed circuit board covers the substrate layer; the wrist strap comprises a lock catch, a lock ring and a lock hole. The wearable bracelet disclosed by the utility model is quick in response and simple to operate, and can be used for detecting the formaldehyde content in a daily family environment and monitoring the formaldehyde content in a factory environment in real time.