133 results about "Target setting" patented technology

The invention discloses a carbon neutralization target setting and tracking system based on big data and an artificial intelligence technology, and relates to the technical field of carbon neutralization. The system comprises a plurality of key modules, a data acquisition module widely collects multi-source data of energy, industry, traffic, building, weather and the like, a satellite remote sensing data acquisition technology is introduced, and the carbon emission condition is comprehensively reflected; the data preprocessing module adopts a transfer learning technology to improve the processing efficiency; the big data storage module is combined with a block chain technology to guarantee data credibility; a reinforcement learning mechanism is integrated into a target setting sub-module of the artificial intelligence analysis module, a knowledge graph technology is introduced into a tracking analysis sub-module, and a carbon neutralization target is accurately set and tracked; the visual display module provides immersive experience by applying VR and A technologies; and the decision support module gives comprehensive decision suggestions in combination with a simulated annealing algorithm and a multi-objective decision theory. The system can scientifically set targets, accurately track the progress and intelligently assist in decision making, and provides powerful technical support for carbon neutralization.

The invention discloses a federal self-supervised learning backdoor attack method and system based on illusion positive example entanglement, and the method comprises the steps: setting a target of an attacker to embed a backdoor into an image encoder during a pre-training period, and guaranteeing that a downstream classifier trained on the image encoder predicts an image with a trigger as a target class; the limited poisoning data is fully utilized, and the feature similarity of the same trigger sample is improved through the illusion enhancement module, so that the malicious client can effectively embed the backdoor into the global encoder. In the training process, a forged positive sample is generated, learning of the model in a feature space is misguided intentionally, poisoning data is utilized to the maximum extent, an entanglement loss function is designed to optimize a target, the attack efficiency is kept in the whole model aggregation process, and the attenuation risk is reduced. According to the invention, a new perspective and important challenge can be provided for the security research of the federated learning system, and the improvement and development of defense capability are promoted.

The embodiment of the invention provides an air supply equipment control method and device, equipment and a medium, the air supply equipment comprises main air supply equipment and auxiliary air supply equipment, the method is applied to the main air supply equipment, and the method comprises the steps that air blowing area information and interference area information associated with the air blowing area information are obtained; wherein the blowing area information is used for indicating a blowing area, and the interference area information is used for indicating an interference area; and according to the blowing area information and the interference area information, target setting information of the auxiliary air supply equipment is determined to recommend to set the auxiliary air supply equipment according to the target setting information, so that the auxiliary air supply equipment is prevented from supplying air to the interference area when supplying air to the blowing area. According to the embodiment of the invention, the auxiliary air supply equipment is arranged according to the interference area and the blowing area, so that the auxiliary air supply equipment assists the main air supply equipment to supply air, the air supply effect is improved, and the demand of avoiding air supply to the interference area when a user supplies air to the blowing area is met.

The invention relates to the field of electric vehicle transverse stability control, and discloses an AFS yaw stability control method based on an improved super-spiral sliding mode algorithm, and the method comprises the steps: a state parameter estimation step: outputting an estimated value of a state quantity based on a Kalman filtering unit; a stability determination step in which the target setting unit outputs an ideal value of the state quantity; the side slip angle judgment unit receives the road adhesion coefficient, the side slip angle and the side slip angle speed and outputs an instability judgment result; the yaw velocity judgment unit receives an ideal value and an actual value of the yaw velocity, and outputs an instability judgment result after judgment of a logic threshold value; an additional front wheel steering angle control output step, wherein a control mode selection unit receives the instability judgment result and outputs a corresponding control mode; and the control quantity calculation unit outputs the sliding mode control quantity according to the selected control mode. According to the method, yaw stability control with high rapidity and robustness can be realized only by using a common vehicle-mounted sensor, and the real-time precision of vehicle state parameter estimation is improved.

An autothrottle for an aircraft that includes a power-control input (PCL) manually movable by a pilot along a travel path to effect a throttle setting that controls engine power of the aircraft. The autothrottle determines a control-target setting for a throttle of the aircraft and dynamically adjusts the throttle according to the control-target setting, including moving the PCL to achieve the control-target setting. A virtual detent is set and dynamically adjusted at positions along a travel path of the PCL corresponding to the control-target setting. The virtual detent is operative, at least when the autothrottle is in a disengaged state for autothrottle control, to indicate the control-target setting to the pilot via a haptic effect that applies a detent force opposing motion of the PCL in response to the PCL achieving the position of the virtual detent.

The invention relates to the technical field of artificial intelligence, and discloses a self-adaptive indoor positioning and path optimization method based on artificial intelligence, which comprises the following steps: S1, collecting visual positioning data, deploying the position and angle of a camera to cover an indoor area, then collecting image data of an indoor environment in real time, and setting the position and angle of the camera to be the same as the position and angle of the camera; calculating and determining the positions of the target object and other obstacles in the image through visual artificial intelligence; s2, collecting wireless Bluetooth positioning data; s3, positioning data fusion and evaluation; s4, target setting and path planning; s5, executing and monitoring a path; and S6, dynamic path optimization. Visual artificial intelligence and wireless Bluetooth positioning are combined to improve positioning accuracy and stability, visual positioning provides abundant image information, wireless Bluetooth positioning ensures coverage and stability, and matching of the visual positioning and the wireless Bluetooth positioning can correct errors, adapt to different environment changes and provide an accurate position basis for path optimization. The robot navigation efficiency and the task execution success rate are improved.

The invention, which relates to the technical field of temperature control, discloses a temperature regulation and control system comprising a target making module, a comprehensive monitoring module, a central decision module, an optimization control module and a temperature control execution module. The target formulating module generates a real-time target temperature table by considering the environmental parameters based on the environmental correction strategy; the comprehensive monitoring module obtains and feeds back a real-time monitoring parameter table; the central decision-making module considers the environmental parameter change and the real-time temperature change of each key component based on a progressive change perception strategy to decide whether to update a target thermometer or carry out temperature regulation and control; the optimization control module adopts a grey wolf optimization fuzzy PID algorithm to optimize a control factor, and obtains a real-time optimal temperature control power adjustment scale; and the temperature control execution module starts temperature control equipment through a conventional temperature control power meter, receives an adjustment execution instruction and updates real-time temperature control power, so that multi-component cooperative temperature regulation and control which dynamically cope with the environment and adjust the total power to be minimum is realized.

Embodiments of the present description provide a focusing assistance device, method and system, and a storage medium. The focusing assistance device is used for: acquiring a calibration image pair which is obtained by a camera apparatus and a distance measurement apparatus separately performing image acquisition on a calibration pattern; determining a mapping relationship between a lens of the camera apparatus and the distance measurement apparatus on the basis of a matched feature point pair in the calibration image pair, and storing the mapping relationship; and acquiring a scene image of a photography scene acquired by the camera apparatus and a depth image of the photography scene acquired by the distance measurement apparatus, determining depth information of an object in the scene image on the basis of the mapping relationship and the depth image, determining a current depth-of-field range of the lens on the basis of the movement of the lens fed back by a focus adjustment apparatus, and displaying the depth information and the depth-of-field range on a display interface. Thus, users can conveniently know the real-time focusing status and perform focus adjustment or focusing target setting on the basis of the information, thereby improving the focusing efficiency of the users.

The invention discloses a smart city monitoring system, and relates to the technical field of monitoring identification, and the system comprises an image acquisition module, a preliminary image analysis module, a target setting module, a depth image analysis module, a judgment execution module, and a tracking module. The image acquisition module is connected with the monitoring camera and is used for acquiring an image shot by the monitoring camera to obtain a first image; according to the smart city monitoring system, by arranging the image acquisition module and the preliminary image analysis module, a shot image can be preliminarily judged, temporary storage is carried out when a moving object appears, then judgment is carried out, the early-stage data processing amount is reduced, the shooting reaction speed is increased, missed shooting of a high-speed target is prevented, and the shooting efficiency is improved. Therefore, the probability of shooting effective information is improved, secondary judgment can be carried out on the temporarily stored image, whether the shot image contains the target or not is judged, otherwise, the temporarily stored image is deleted, and if yes, the temporarily stored image is stored, so that the shooting accuracy is ensured.

The invention relates to the technical field of computer vision, and particularly discloses a target detection optimization method and system, electronic equipment and a storage medium, and the method comprises the steps: inputting a to-be-detected image into a trained target detection model, and obtaining a target detection frame of the to-be-detected image and a first confidence coefficient of the target detection frame; generating a background description text of the to-be-detected image by using a CO-STAR framework, and inputting the target detection frame and the background description text into a trained multi-modal large language model to obtain a second confidence coefficient of the target detection frame; and carrying out confidence coefficient fusion on the first confidence coefficient and the second confidence coefficient of the target detection frame to obtain a target confidence coefficient of the target detection frame. According to the method, the target detection result is rechecked by using the multi-modal large language model, new confidence judgment is given in a high-interpretability mode, the precision of an existing detection framework is remarkably improved, and thus optimization of the target detection result is realized.

The application discloses an energy equipment intelligent control method and system, and belongs to the technical field of electric energy storage systems. The method comprises the following steps: acquiring environmental parameter information of an energy equipment according to a preset period, and determining demand load change information of the energy equipment based on the environmental parameter information; acquiring a target efficiency cost factor, and determining a target control parameter group based on the demand load change information and the target efficiency cost factor; determining a target controller coefficient corresponding to each control parameter based on a target setting value of each control parameter in the target control parameter group and the target efficiency cost factor; and generating a power adjustment instruction corresponding to each control parameter based on the target setting value and the target controller coefficient. According to the technical scheme, the real-time change of the demand load of the energy equipment is dynamically matched, global adaptive control of the energy equipment is realized, and the energy consumption cost and the equipment control efficiency are accurately balanced, so that the long-term operation economy and stability of the energy equipment under a complex environment are improved.

The invention discloses a method for improving generalization of binocular cameras in mass production based on random optical axis offset, and the method comprises the steps: carrying out the random sampling of the binocular cameras, and carrying out the quantitative analysis of the optical axis offset angle of the batch of products after the binocular calibration; according to a statistical result of the camera deviation angle, calculating a mean value and a variance of the deviation angle, and constructing a rotation matrix meeting normal distribution through the mean value and the variance; remapping the right image according to the rotation matrix to obtain a left image and a right image which conform to real distribution and have optical axis offset; the model is trained on the data set which simulates the optical axis deviation, and the trained model is deployed in a binocular camera. According to the method, the angle of the optical axis deviation of the mass-production binocular camera in the actual working scene is counted, the data set is remapped, the data distribution when the optical axis deviation occurs in the real scene is simulated, the generalization of the model is improved, and the good reasoning effect can still be kept when the camera structure is slightly disturbed.

According to one aspect of the present invention, a radiation measurement system is provided, comprising: an irradiation unit, a target setting unit, a detection unit, and a candidate setting unit. The irradiation unit is configured to irradiate a target with radiation. The target setting unit is configured to place the target within the irradiation range of the radiation. The detection unit is configured to detect radiation after passing through the target. The candidate setting unit is configured to set a candidate of the target and includes a shaft, a first support, and a second support. The shaft extends axially and is configured to rotate about a rotation axis along the axial direction. The first support is configured to rotate with the shaft and includes a plurality of first support regions, each supporting a candidate of the target and arranged along the outer periphery of the first support. The second support is configured to rotate with the shaft and includes a plurality of second support regions, each supporting a candidate of the target and arranged along the outer periphery of the shaft. The first support and the second support are arranged at positions spaced apart from each other in the axial direction.

The invention provides a setting calculation method and system based on different tenses, equipment and a storage medium, and belongs to the field of electric power systems.The method comprises the steps that first order reduction is conducted on a multi-tense model, and a first calculation model and a second calculation model are obtained, the first calculation model comprises a common model of a past tense model, a current tense model and a future tense model, and the second calculation model comprises a difference model of the past tense model, a difference model of the current tense model and a difference model of the future tense model; performing double order reduction on the first calculation model to obtain a plurality of common calculation units; and performing triple order reduction on the plurality of common calculation units and the second calculation model based on the target setting demand to obtain a target model corresponding to the target demand, and determining a setting strategy corresponding to the target demand according to the target model. According to the invention, rapid conversion calculation of the power grid setting constant value in different time states can be realized.

The application provides a whole vehicle sound source noise target setting method, system, device and medium, relates to the NVH technical field, and the method comprises the following steps: firstly, obtaining the sound pressure level noise data of a test vehicle under a target working condition through a first bench test; then, respectively determining the sound transmission functions of the test vehicle and a target vehicle through a second bench test; then, performing frequency spectrum analysis on the sound pressure level noise of the test vehicle to obtain target sound pressure level noise in a specific frequency range. Combined with the sound pressure level noise of the test vehicle and the sound transmission function thereof, the sound source noise of the test vehicle is calculated; further, the target sound pressure level noise and the sound transmission function of the target vehicle are utilized to determine the sound source noise of the target vehicle; finally, according to the sound source noises of the test vehicle and the target vehicle, the sound source noise target value of the target vehicle is set. The application can effectively solve the problem that the bench test is inconsistent with the actual performance of the whole vehicle, and improve the accuracy and rationality of the sound source noise target setting.

The invention discloses an engineering consultation value list comprehensive evaluation system based on target data analysis, and belongs to the technical field of engineering evaluation, and the system comprises a target setting module which is configured to set target data; the data collection module is configured to collect engineering project multi-source data and perform preprocessing; the feature extraction module is configured to perform feature extraction on the engineering project multi-source data; the model construction module is configured to construct an engineering consultation value list comprehensive evaluation model; and the result output module is configured to output a comprehensive evaluation result of the project consultation value list. The problem that the comprehensive evaluation efficiency of the project consultation value list is low because the project consultation value list cannot be comprehensively evaluated based on target data analysis in the prior art is solved. According to the method, the engineering consultation value list can be comprehensively evaluated based on the target data analysis, the comprehensiveness of the evaluation result is ensured, the automation and intelligence of the evaluation process are realized, and the comprehensive evaluation efficiency of the engineering consultation value list is improved.

The invention relates to a PID (Proportion Integration Differentiation) control-based output regulation method and system for an activation coal feeder of an European silo, and solves the problems that the manual output regulation stability is poor and the operation depends on experience in the prior art. According to the method, the target coal flow is preset to serve as reference input, the electronic scale is used for collecting the actual flow in real time, deviation is calculated, the controlled quantity is generated through proportional, integral and differential adjustment of the PID controller, the air pressure of an oscillation motor of the activated coal feeder is automatically adjusted, and the closed-loop control process of measurement, deviation calculation and automatic adjustment is formed. The system comprises a target setting unit, a flow acquisition unit, a PID control unit and an execution unit. According to the method, the working pressure of operators can be reduced, the coal flow control precision and the bunker adding process stability can be improved, the bunker adding amount and time can be accurately estimated, technical support is provided for a subsequent automatic bunker adding system, and the method has the advantages of economy and intelligence.

The invention belongs to the technical field of artificial intelligence image processing, and particularly relates to an artificial intelligence image processing method and system, and the method comprises the steps: S1, question definition and target setting, S2, data preparation and preprocessing, S3, model selection and design, S4, model training, and S5, subsequent monitoring and maintenance, and saves labor time and energy. According to the method and the system, the AI is used as a model, real-time or near-real-time image analysis is realized by means of an efficient deep learning algorithm and hardware acceleration, meanwhile, through continuous training and feedback, the AI can gradually optimize own performance, incremental learning or transfer learning is used, the AI can adapt to new data and new environmental conditions, and the capability of solving unknown problems is improved.

The invention belongs to the technical field of talent management development, and relates to a staged progressive talent growth path planning method and system, and the system collects and integrates the static and dynamic data of talents through a talent portrait construction module to generate an initial talent portrait; the growth stage division module divides progressive growth stages and sets capability thresholds based on the initial talent portraits and the organization development objectives; the stage target setting module is used for disassembling a stage target into quantifiable sub-target schemes with time limit; the resource matching and pushing module is used for matching resources according to the target and the portrait and automatically pushing the resources to the talent end; the capability evaluation feedback module is used for evaluating a stage target achievement condition and generating an evaluation report; the path dynamic adjustment module progressively or triggers path adjustment based on the evaluation report judgment stage; and the data storage and analysis module is used for storing the whole-process data, carrying out multi-dimensional analysis and optimizing parameters. According to the invention, personalized planning, dynamic adjustment and whole-process closed-loop management of talent growth paths can be realized.

The application discloses a college performance evaluation management system and method based on multi-source data fusion, and relates to the technical field of college performance evaluation management.The system comprises a target setting and disassembly module, a disassembly rationality evaluation module, a target progress early warning module and a performance accounting and improvement module.The application assigns initial indexes to corresponding executors, then performs weight distribution on the initial indexes of each target management level to obtain corresponding initial weights, performs multi-level index disassembly rationality evaluation, judges whether to perform index disassembly optimization, then performs performance accounting, judges whether to push early warning information to a preset person in charge, finally performs performance accounting update evaluation after performance accounting, and judges whether there is a demand to generate a performance accounting update scheme, thereby improving the effectiveness of college performance evaluation management and solving the problem of low effectiveness of college performance evaluation management in the prior art.

This application relates to the field of equipment testing, providing a method, device, and storage medium for configuring parameters of a simulated load. The method obtains the desired test parameters of the power supply device under test, performs a load test on the device based on these parameters, obtains measured data, and adjusts the resistance value of the simulated load device to determine the target setting parameters if the difference between the actual output power and the desired power value is greater than a preset threshold. Similarly, if the difference between the desired power value and the actual output power is greater than a preset threshold, the load power of the simulated load device is adjusted to determine the target setting parameters. This method, through code scripts, enables automated parameter setting of the simulated load device, avoiding human error and improving the efficiency of determining the target setting parameters.

The invention provides an intelligent self-adaptive tensioning system and method for a belt conveyor under a mine. The system comprises a belt assembly, a tension detection unit, an intelligent control unit and an execution mechanism which form a closed-loop control system. The tension detection unit monitors the belt tension in real time and outputs a signal; the intelligent control unit receives the processing signal, calculates an adjustment amount according to a self-adaptive control algorithm and generates an instruction; and the execution mechanism receives the instruction to adjust the belt tension. A fuzzy PID (Proportion Integration Differentiation) control algorithm is adopted, a tension prediction model is included, and a tension adjusting assembly can be accurately adjusted. The method comprises the steps of tension detection, data transmission, preprocessing, working condition recognition and target setting, tension prediction, control quantity calculation, instruction generation and execution, closed-loop feedback, safety monitoring and the like. Real-time accurate automatic adjustment is achieved, frequent manual intervention is not needed, complex working conditions can be dealt with, the belt problem is avoided, the production efficiency is improved, the service life of equipment is prolonged, and the operation performance is optimized.

The invention provides an information processing method and device in a game, electronic equipment and a storage medium, and the method comprises the steps: displaying a deposit target setting interface in a game interface through responding to a setting triggering operation; in response to a setting operation for the deposit target setting interface, determining a target deposit amount; displaying a deposit prompt identifier in the game interface, wherein the deposit prompt identifier is used for indicating the target deposit amount; according to the comparison result of the current holding amount and the target deposit amount, the visual state and / or the available state of a transaction control displayed in the game interface are / is adjusted, and the transaction control is used for triggering a game amount consumption item. According to the embodiment, the economic state of a user is monitored in real time through the deposit prompt identifier, and the understanding and operation complexity of the user is effectively reduced. Not only is the interaction experience improved, but also the depth of the game strategy level is enriched.

To provide a power system capable of performing control considering demand values in power control using induction command values.SOLUTION: A power system S1 includes a processing device A1 including a target setting unit 13 that sets a system target value and a command value calculation unit 14 that calculates an induced command value, and a plurality of power control devices B1 that controls the output power of power equipment X on the basis of a common induced command value calculated by the processing device A1. The target setting unit 13 includes a storage unit 131 storing set target values, a demand prediction unit 132 that estimates predicted demand, a demand difference determination unit 133 that determines whether a demand difference prediction exists where a demand difference exists between the predicted demand and the target demand, and a target change unit 134 that changes the system target value in a direction that reduces the demand difference when a demand difference prediction exists. The command value calculation unit 14 calculates the guidance command value using the modified target value changed by the target change unit 134 when a demand discrepancy prediction occurs.SELECTED DRAWING: Figure 2

The invention discloses a flight path mature management method based on 4D millimeter wave radar and visual fusion, which considers that a historical frame association cluster source is radar point cloud and the frame number of a visual network detection frame, and designs a mature frame value according to the ratio of the network frame number to the total detection frame number, and compared with single frame information, the utilization of historical frame number information is more reliable. According to a specific scene and a target motion state, the number of mature frames of different target tracks is designed, the number of basic mature frames is set to be three, and the number of additional frames of the mature frames is increased according to different conditions, so that the purpose of setting different number of mature frames of the tracks for different targets in different scenes so as to regenerate a more reliable track is achieved; the problem that the track is immature due to the fact that different confidence coefficients possibly existing in each target are not considered in the prior art is solved.

The invention provides a switch cabinet partial discharge detection method and system and a storage medium, and belongs to the technical field of partial discharge detection.The method specifically comprises the steps that when a setting processing strategy of a harmonic monitoring device in a combination does not belong to a target setting strategy, an abnormal switch cabinet is determined according to partial discharge detection data of the switch cabinet in the combination, according to the distribution data of the partial discharge detection time period of the abnormal switch cabinet, when it is determined that optimization processing of the setting processing strategy of the harmonic monitoring device in the combination needs to be carried out, according to the change coincidence condition of the partial discharge detection data of different switch cabinets in the combination and the setting processing strategy of the harmonic monitoring device, optimization processing is carried out. The partial discharge detection method of the combined switch cabinet is determined, and the reliability of partial discharge detection processing is improved.

A braking control device 70 comprises: a target setting unit 115 that, when stopping a vehicle 10, performs an at-vehicle-stop target setting process which includes decreasing a target regenerative braking force and increasing a target frictional braking force; a correction unit 117 that corrects the target frictional braking force so that a deviation between a target value and an actual value of deceleration of the vehicle 10 is reduced; and a stop control unit 119 that, when the at-vehicle-stop target setting process is being performed, stops the vehicle 10 by operating a regenerative braking unit 20 on the basis of the target regenerative braking force and operating a friction braking unit 40 on the basis of a corrected target frictional braking force.

An object of the system according to the embodiment is to realize equal corporate planning by learning the work and experience value of the manager.SOLUTION: A system according to an embodiment includes a manager work learning unit, an objective setting unit, a task management unit, an evaluation unit, a feedback unit, a compliance monitoring unit, an indication unit, and a consultation handling unit. A manager work learning part learns the work and experience value of a manager. The target setting unit sets a target. The task management unit performs task management. The evaluation unit performs business evaluation. The feedback unit provides feedback. The compliance monitor monitors compliance compliance. The pointing out unit points out to a subordinate. The consultation handling unit acts for the consultation with the superior.SELECTED DRAWING: Figure 1

The present invention provides a control method for an air conditioner based on an intelligent treadmill and the intelligent treadmill. The intelligent treadmill is connected to the air conditioner by signal. The control method includes: obtaining a startup instruction of the intelligent treadmill; in response to the startup instruction, obtaining the real-time operating speed of the intelligent treadmill; matching the real-time operating speed with a preset historical speed parameter comparison table to obtain a historical operating speed that is the same as the real-time operating speed as a target historical speed; wherein the historical speed parameter comparison table includes at least the historical operating speeds of the intelligent treadmill after each startup and the corresponding historical air conditioner operating parameters; selecting the historical air conditioner operating parameters corresponding to the target historical speed as target setting parameters; and operating the air conditioner according to the target setting parameters, thereby achieving automatic control of the air conditioner based on the historical operating speeds of the intelligent treadmill and the historical air conditioner operating parameters corresponding to the historical operating speeds, thereby providing a comfortable environment for the user during exercise.

The application discloses an intelligent decision-making method and system for satellite intelligence support based on machine learning, and the method comprises the following steps: acquiring a satellite remote sensing image in satellite intelligence, inputting the satellite remote sensing image into a CNN neural network, and finding an identified target in the satellite remote sensing image; setting a shape feature extraction function, extracting the shape feature of the identified target, and setting a texture feature extraction function, extracting the texture feature of the identified target, wherein the shape feature of the identified target is extracted by performing a rotational symmetry operation on the identified target and calculating the height index of the identified target; combining the extracted shape feature and the texture feature, determining the morphology of the identified target, comparing the morphology with a preset object classification dictionary, thereby determining the object classification of the identified target, and making a decision according to the object classification of the identified target.