589results about How to "Avoid dependence" patented technology

The invention provides a crop yield prediction method and system based on artificial intelligence, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining continuous historical meteorological data, soil data, crop planting data and remote sensing image data of a designated region for many years, and carrying out the alignment according to a time sequence, and constructing a multi-dimensional spatio-temporal data cube; a fusion prediction model is trained, the fusion prediction model is used for extracting growth feature vectors in the crop growth and development process and carrying out yield prediction, and model parameters of the fusion prediction model are dynamically adjusted through an adaptive learning rate optimization algorithm; the method comprises the following steps: acquiring real-time meteorological data, soil data and remote sensing image data of a specified area, inputting the data into a pre-constructed fusion prediction model, introducing an agricultural knowledge graph into the fusion prediction model to restrain and correct a prediction result of the fusion prediction model, and reasoning to obtain crop growth and estimated yield of each grid of the specified area. And performing spatial interpolation on the estimated yield of each grid to generate a yield distribution diagram of the specified area.

The invention relates to the technical field of wastewater treatment, in particular to a generation method for a chemical production wastewater treatment system control model. The method comprises the following steps: collecting chemical wastewater data by using an online monitoring instrument, wherein the chemical wastewater data comprises tin-containing wastewater data and etching liquid waste liquid data; determining a wastewater recovery control stage according to the chemical wastewater data; constructing a wastewater control model by utilizing chemical engineering simulation software based on the wastewater recovery control stage; inputting the chemical wastewater data into a wastewater control model, simulating a wastewater recovery control process by using simulation software to obtain wastewater recovery control data, and performing control abnormality judgment on the wastewater recovery control data to obtain abnormal wastewater data; the high-definition industrial camera is used for collecting images of the waste water sedimentation tank, and a centrifugal pump image is recognized and obtained from the images of the waste water sedimentation tank. According to the method, wastewater recovery control is optimized based on a wastewater treatment technology, and the wastewater recovery efficiency and the anomaly detection rate are remarkably improved.

The invention belongs to the field of computer graphics, and discloses a fast parallel multi-scale smooth symbol distance curved surface reconstruction method and system, and the method comprises the steps: carrying out the local fitting of point cloud data through employing a moving least square method, and calculating the Gaussian curvature of a point cloud; constructing a curvature adaptive octree based on Gaussian curvature, wherein the octree is used for dynamically adjusting local resolution and capturing geometric details to improve curved surface reconstruction precision; global fitting is carried out through an implicit function, and a zero contour surface is obtained through an octree contour surface extraction algorithm; and multiple threads are introduced in the process of iteratively solving the linear system to carry out parallel computing. The adaptive octree based on Gaussian curvature can effectively capture complex geometric details, and the algorithm realizes high-precision curved surface reconstruction under different scales. In addition, the local and overall calculation efficiency is remarkably improved through parallel calculation, and the high efficiency of the algorithm in large-scale data processing is ensured. The method provided by the invention provides an efficient and accurate solution for complex curved surface reconstruction.

The invention discloses a multi-source traffic data information extraction and intelligent responsibility judgment method, system and device, and relates to the technical field of traffic accident data processing and analysis, and the method comprises the steps: inputting traffic accident related data into a pre-constructed multi-modal large model, and generating a brief description text of traffic accident passing; retrieving legal provisions related to the traffic accident from a pre-constructed legal knowledge base according to the brief description text; and inputting the brief description text and the legal provisions into a pre-constructed Traffic-T5 model, and automatically generating a responsibility affirmation result. According to the method, unified modeling and processing are performed on the text and image data by adopting the multi-modal large model, the efficiency and accuracy of accident information extraction are improved, the multi-modal large model is optimized, the understanding and analysis ability of the multi-modal large model on incomplete traffic accident data is enhanced, and a legal knowledge base is combined, so that the method is suitable for popularization and application. Dynamic retrieval and application of traffic laws and regulations are realized, and the responsibility division result is ensured to have a basis.

The invention discloses a building point cloud data high-precision three-dimensional model generation method, and belongs to the technical field of point cloud deep learning modeling, and the method comprises the following steps: S1, collecting multi-source building point cloud data; s2, carrying out deep learning point cloud registration; s3, performing deep learning point cloud completion; s4, carrying out deep learning point cloud segmentation; s5, slicing the point cloud and extracting building parameters; and S6, building a BIM model according to the extracted parameters. According to the method, the steps of point cloud registration, completion, segmentation and parameter extraction are optimized through a deep learning method, an efficient method from point cloud data to BIM model automatic generation is provided, and the method has the advantages of high precision, high robustness and adaptation to multi-source data.

The invention belongs to the technical field of marine surveying and mapping, and discloses an unmanned aerial vehicle laser / shipborne multi-beam data land and water topographic mapping method, which comprises the following steps of: coarsely extracting a data overlapping region through a virtual grid, finely extracting the overlapping region by using an alpha-shape algorithm, and obtaining boundary points; removing edge triangles in an irregular triangulation network constructed by the unmanned aerial vehicle laser sounding data and the shipborne multi-beam sounding data; calculating a vertex normal vector, taking a vertex tangent plane of the multi-beam triangular irregular network as a registration element, carrying out weight distribution according to the distance from a point to the vertex, and carrying out coarse registration through a point-to-plane ICP registration algorithm; and constructing a precise registration model based on a point-surface distance, and eliminating the elevation difference of the overlapping region by minimizing the normal distance from the unmanned aerial vehicle laser sounding point to the multi-beam sounding triangular surface element. By adopting the point cloud fusion model for processing, the phenomenon that different source point cloud elevations in the overlapping area are inconsistent is effectively improved, and underwater topographic data fusion is realized.

The invention provides an elevator door abnormal sound detection and identification method based on a variational auto-encoder (VAE) and a Transform network. The method comprises the steps of data acquisition and preprocessing, model construction and training, abnormal sound detection and identification, method performance evaluation and the like. The method specifically comprises the following steps: acquiring sound signals in the operation process of an elevator door by installing an audio sensor, continuously recording to form time sequence data, and cleaning and normalizing the time sequence data; then, feature reconstruction is carried out through a VAE-Transform network, a reconstruction error is calculated to obtain an abnormal score, abnormal feature vectors are continuously marked, finally, abnormal segments are input into a classifier, and the abnormal sound types are judged according to the confidence score of each abnormal sound type. According to the method, unsupervised network training is introduced to complete abnormal sound detection, and then the detected abnormal sound is further classified and identified, so that the calculation amount of data can be significantly reduced, the efficiency is greatly improved, the specific fault type is rapidly identified, and accurate maintenance suggestions are provided, thereby improving the fault processing efficiency and accuracy, and improving the fault processing efficiency and accuracy. The problem that abnormal sound fault data are scarce is effectively solved, and the method is suitable for abnormal sound fault monitoring of the elevator door in a complex environment.

The invention discloses a universal self-supervised learning Raman spectrum noise reduction method, which comprises the following steps of: 1, acquiring Raman data; step 2, preprocessing the Raman data, removing a baseline from the Raman data by using an adaptive iterative reweighted penalty least square method, and standardizing a spectrum after baseline removal to obtain preprocessed spectrum data; step 3, processing the preprocessed spectral data by using a down-sampling strategy H (.) to obtain two sub-spectrum sets h1 (.) and h2 (.) with independent noise, each sub-spectrum set comprising 10 sub-spectrums; and step 4, inputting the preprocessed spectrum data and the corresponding two sub-spectrum sets into a U-Net network f theta (.) to obtain a spectrum after noise reduction processing. The noise reduction method can carry out good noise reduction processing on various Raman data, and the self-supervised learning method does not need a complex long-time learning process.

The invention relates to a method and a device for tracking a dynamic resource dependency relationship and terminal equipment. The method comprises the following steps: acquiring cloud resource dependency data of a cloud service platform and / or a data center in real time; constructing a cloud resource dynamic dependency graph according to the cloud resource dependency data; detecting the cyclic dependence of the cloud resource dynamic dependence graph by adopting a depth-first search algorithm to obtain a cyclic dependence detection result; and using a TGCN algorithm to predict the future cyclic dependence of the cloud resource dynamic dependence graph to obtain a cyclic dependence prediction result. According to the method, a real-time cloud resource dynamic dependency graph is constructed, a depth-first search algorithm and a TGCN algorithm are adopted to process the cloud resource dynamic dependency graph to obtain a cyclic dependency detection result and a cyclic dependency prediction result, and a basis is provided for determining corresponding resource cyclic dependency prevention measures and processing strategies. And data is provided for effective cloud resource management and optimization, so that problems and risks caused by cyclic dependence are reduced, and the reliability of cloud services is improved.

The invention discloses an amphiphilic carbon dot, a clean fracturing fluid and application of the clean fracturing fluid. The amphiphilic carbon dot is prepared by performing solvothermal reaction on organic acid and a hydrophobic aliphatic compound. According to the amphiphilic carbon dots provided by the invention, simple preparation of the amphiphilic carbon dots with different structures and properties can be realized by changing the types of the hydrophobic aliphatic compounds, and the clean fracturing fluid prepared by utilizing the amphiphilic carbon dots not only has high temperature resistance and is suitable for reservoirs with relatively high temperature, but also has high salt resistance, so that the clean fracturing fluid can be used for preparing the clean fracturing fluid. And the fracturing fluid has a good fracturing effect in hydrofracture operation of low-permeability and high-salinity oil reservoirs.

The invention relates to the technical field of hyperspectral imaging, in particular to a single-pixel hyperspectral imaging method and device based on time domain stretching. The method comprises the following steps: broadband signal light passes through a sample to be detected to obtain two-dimensional image information and one-dimensional spectral information, a mask pattern is generated by using a spatial light modulation module, and spatial coding modulation is performed on the signal light carrying the sample information; the broadband signal light subjected to space coding is effectively collected through a multimode optical fiber, different space frequency components are homogenized, then time stretching is conducted through a time stretching module to achieve separation of different wavelengths in the time domain, and time domain information of signal pulses is recorded through a single-pixel detector; time is mapped back to a frequency spectrum through the accurate corresponding relation between the signal light frequency and the time delay amount, and a hyperspectral image is obtained according to the known mask sequence and the signal intensity corresponding to different wavelengths in combination with an association algorithm. According to the technical scheme, high-spectral imaging with high speed, high spectral resolution and high sensitivity can be realized.

The invention provides a battery state prediction method and system, computer equipment and a storage medium, and the method comprises the steps: randomly selecting a preset proportion of batteries from a target batch of batteries as a test sample set; performing current switching cycle life test on each battery sample to obtain a plurality of groups of current sudden change data comprising current time sequence data, voltage time sequence data and battery health state corresponding to the preset charge state segment point sequence; obtaining a current abrupt change point battery impedance spectrum according to the current time sequence data and the voltage time sequence data in each group of current abrupt change data, and constructing a battery state prediction model according to all the current abrupt change point battery impedance spectrums and the corresponding battery health states; and obtaining a battery state prediction value according to the obtained current mutation battery impedance spectrum of the to-be-evaluated battery and the battery state prediction model. According to the invention, the high efficiency, accuracy and operation convenience of online monitoring of the health state of the battery can be effectively improved under the low-cost condition of not additionally adding measuring equipment.

The invention belongs to the technical field of road engineering materials, and discloses a wide-temperature-range crack pouring adhesive based on rubber modified asphalt and a preparation method thereof.The wide-temperature-range crack pouring adhesive is prepared by taking the rubber modified asphalt as a matrix through a response surface method and adding SBS, basalt fibers and a modifier. The performance of the material is tested through a conventional test, and meanwhile, a test with more characteristics in northeast regions is provided, and the performance of the material is detected through injection depth, viscosity, low-temperature stretching after aging and freeze-thaw cycle stretching. Results show that a test designed by a response surface method has very strong reliability, and the modified heating type crack pouring adhesive added with the basalt fiber can significantly improve the high and low temperature performance of the crack pouring adhesive, and also has good anti-aging performance and freeze-thaw cycle resistance. And the filling depth and the viscosity of the sealant are not obviously lower than those of the same type of sealant.

The invention discloses binder spraying 3D printing equipment and a printing method for low-fluidity powder, and relates to the technical field of 3D printing. The printing method comprises the steps that the powder forming module is controlled to reach an initial position; the powder forming module comprises a powder falling module and a powder spreading module which move synchronously; powder is added into the powder falling module through the powder supplementing module; the powder forming module is moved to the initial powder laying position, and powder is controlled to be scattered on a vibration plate from a powder supplementing bearing plate of the powder falling module; vibration of a vibration plate is controlled, so that the powder is transferred to the front of the powder spreading module and is spread and compacted; laying of single-layer powder is completed; the steps are repeated to complete laying of the bottom powder layer; and laying of the slice layers is completed repeatedly on the bottom powder layer, the ink jetting module is controlled to move along with the powder forming module, a binder is jetted to each slice layer, and a 3D printing product is obtained through curing. A matching scheme of layer-by-layer powder supply, independent powder spreading and independent compaction is adopted, so that high density and high uniformity of a low-fluidity powder printing breadth are ensured.

The invention discloses a flue gas emission continuous monitoring device and a monitoring method, and relates to the technical field of flue gas emission, the device realizes gas inlet detection and multidirectional gas inlet and gas exhaust of cleaning pipelines and parts through a U-shaped gas inlet pipe, a preheating pipe, a first gas return pipe, a first gas inlet pipe, a gas collection chamber, a condensation pipe, a liquid collection chamber and a second gas return pipe; preheating and heat preservation are achieved through air inlet and air outlet, heat preservation measurement is achieved in the heat preservation shell, pipelines and parts, interference of temperature, oil and particulate matter is effectively reduced, and the monitoring precision is improved; the laser scattering sensor is used for measuring the concentration and the particle size of particulate matters, the optical fiber measuring unit is used for monitoring other components in flue gas, and real-time monitoring and emission component analysis of the flue gas are realized by collecting released liquid and measuring substances dissolved in the liquid; the problems that smoke monitoring is easy to interfere, detection data are easy to fluctuate, and a multi-operation-mode switching technology of a detection device is lacked, so that the smoke monitoring precision is low are solved.

According to the fan model prediction control method and system based on Gaussian process error compensation, a complex mechanism model does not need to be depended on, the model output compensation amount is predicted in real time through the Gaussian model, dynamic correction is conducted on the model according to the model output compensation amount, the high dependence of a traditional method on the model precision is effectively overcome, and the accuracy of the model is improved. And the modeling process is simplified. The Gaussian model is used for predicting the future wind speed and the output compensation amount, the Gaussian model has the excellent nonlinear approximation capability, the future complex and changeable working conditions and system states can be accurately predicted, the effectiveness of the MPC control strategy is remarkably improved, and more accurate fan control is achieved.

The invention discloses a sewage treatment fault diagnosis method and system based on data analysis, and the method comprises the steps: continuously optimizing a diagnosis strategy in the input and training process of a large amount of data through introducing a fault diagnosis model, and improving the accurate recognition capability of a fault under a complex working condition; therefore, the system not only has strong learning ability, but also can perform self-optimization through a reward mechanism, thereby reducing the occurrence rate of false report and missing report. An adaptive weight adjustment mechanism is introduced, so that the model can automatically adjust weight distribution and increase response to a new fault when the system has a novel fault or few faults; by dynamically adjusting the weight vector, the diagnosis model of the invention has strong self-learning ability and can continuously adapt to new fault modes and working condition changes, and the weight adjustment mechanism greatly improves the generalization ability and adaptability of the model, and especially has significant advantages in the face of fault scenes with strong uncertainty.

The invention discloses a federated learning privacy protection method based on a generative adversarial network and knowledge distillation, and relates to the technical field of privacy protection. Comprising the following steps: S1, local model training; s2, generative adversarial network training; s3, communication in an initialization stage; s4, carrying out distillation training; s5, communication at a distillation stage; and S6, updating the client. According to the method, the generative adversarial network and the knowledge distillation technology are creatively combined, the generative adversarial network model is locally trained at the client, the synthetic data conforming to private data distribution is generated, dependence on a public data set is avoided, knowledge distillation is performed by using the generated synthetic data, and the knowledge distillation efficiency is improved. Knowledge migration without selecting a public data set is realized, and direct exposure of private data distribution is effectively avoided, so that the risk of privacy disclosure is remarkably reduced.

The invention discloses a text duplicate checking method based on audit risks, a storage medium and an electronic device, and belongs to the technical field of text duplicate checking, and the method comprises the following steps: S1, segmenting an audit document to be subjected to duplicate checking into first text fragments according to slice characters, inputting the first text fragments into a word vector model, and obtaining a first word vector library, generating a vector pair according to the first word vector library and a second word vector library of a historical document in the word vector model, and obtaining a first document based on the vector pair; s2, presetting a keyword based on the first text fragment, inputting the first document and the keyword into a mixed model for analysis to obtain second documents, and calculating semantic similarity between each second document and the keyword; and S3, obtaining a third document based on the semantic similarity between each second document and the keyword, and obtaining a final duplicate checking result based on the third document. The problem that due to the fact that the semantic similarity between the text and the keyword is not obtained and the semantic similarity depends on the target feature statement, the duplicate checking result is missed and misreported is solved.

The embodiment of the invention provides an attack traceability path determination method and device, equipment, a storage medium and a product, and the method comprises the steps: obtaining communication behavior data of lost equipment in a lost time range; for the communication behavior data of each network device, if the communication behavior data exceeds the standard range of the communication behavior baseline, the probability that each network device is an attack address is calculated, and if the probability that any network device is an attack address exceeds a malicious probability threshold, according to the communication behavior data, the malicious probability is determined; constructing a communication behavior graph and iteratively executing the following steps: calculating the probability that each IP address of communication is an attack address according to historical communication data of any network equipment; if the malicious probability exceeds the malicious probability threshold, adding any IP address into the communication behavior graph; if the probabilities that all the IP addresses communicating with any network device are attack addresses are not exceeded, ending the iteration process; and determining an attack traceability path based on the determined communication behavior graph. The method is used for achieving the effect of restoring the multi-level attack path.

The invention discloses a low signal-to-noise ratio conditional modulation identification method based on wavelet transform and channel attention. The method comprises the following steps: acquiring a received signal; and inputting the received signal into an identification model of a pre-trained neural network, and outputting a classification identification result and classification accuracy. In the recognition model based on signal reconstruction and the neural network, a wavelet threshold estimation module and a wavelet reconstruction module form a signal reconstruction path, a multi-scale feature extraction module and a prediction classification module form a recognition path, and the two paths are mutually enhanced, so that the combination of the advantages of a digital signal processing technology and the neural network is realized; a wavelet threshold estimation module is introduced to predict a denoising threshold through a neural network, and network parameters of the wavelet threshold estimation module are updated according to back propagation; a signal reconstruction path is combined with a recognition path, the interpretability of the network is enhanced, and the accuracy of modulation recognition in a low signal-to-noise ratio scene is remarkably improved by using multi-scale modulation characteristics.

The invention belongs to the technical field of agricultural food detection, and particularly relates to a method for rapidly detecting the fatty acid content of Beijing ducks based on a near infrared spectrum technology, which comprises the following steps: selecting a sample and pre-treating the sample; collecting sample data by using a standardized collection method; removing abnormal samples; performing spectral data correction; standard normal variable transformation is used to eliminate baseline drift and random errors in the spectral data; dividing the data set into a training set and a test set according to a proportion of 7: 3 by using a sample set division method based on a joint X-Y distance; constructing an optimized extreme learning machine model, and training the optimized extreme learning machine model based on the training set; constructing an evaluation model, and verifying the detection effect of the optimized extreme learning machine model based on the test set; rapid detection of the fatty acid content of the Beijing duck is realized. The defects that an existing method is long in consumed time and lagged in detection result, and dangerous solvents need to be used are effectively overcome.

The invention provides a shock wave generating method. The shock wave generating method comprises the following steps that a boosting module charges an energy storage capacitor; when the voltage of the energy storage capacitor reaches a set value, the boosting module stops charging the energy storage capacitor, and the energy storage capacitor charges the energy relay capacitor and the shock wave electrode; when the voltage at the two ends of the shock wave electrode reaches the breakdown voltage of the shock wave electrode, the energy relay capacitor stops charging and discharges to the shock wave electrode, the energy storage capacitor continues to discharge to the shock wave electrode, and the shock wave electrode discharges, breaks down and releases shock waves. The invention further provides a shock wave system for implementing the shock wave generation method. The peak value and the pulse width of the pulse current formed by the circuit where the shock wave electrode is located when the shock wave electrode releases shock waves are improved, namely, the pulse energy of the pulse current is improved, so that the shock wave energy released by the shock waves released by the shock wave electrode is effectively improved, and dependence of the shock wave energy on an electrode structure is avoided.

The invention discloses a gene identification method based on a mask graph auto-encoder. The method comprises the following steps: 1, acquiring gene interaction data and omics characteristic data and preprocessing the data; 2, masking the processed data, specifically comprising two branches, a node masking module and an edge masking module; 3, inputting the masked network into a graph automatic encoder for training, wherein the graph automatic encoder learns embedded representation of the network by reconstructing nodes and edges of the network; and 4, obtaining low-dimensional embedding of the features through the trained encoder, and finally performing gene classification by using a logic regression classifier. According to the method, the node information and the structure information of the graph are concerned at the same time by respectively masking the nodes and the edges in the network, and the dependence of the feature training model on the label information is reduced in a self-supervised learning mode, so that the genes can be accurately classified.

The invention provides a false face image detection method based on misleading learning, and the method comprises the steps: S1, constructing a priori knowledge obtaining module, and constructing a basic counterfeit artifact discrimination capability for a counterfeit feature extractor and a detector; s2, establishing a misleading learning knowledge flow and a bias data knowledge flow; s3, introducing a single-channel attention fusion network, and enabling the model to adaptively select required multi-scale counterfeit latent layer features and multi-scale real picture latent layer features; s4, constructing a high-pass filter specially used for misleading learning, and carrying out preprocessing operation on the forged image; s5, misleading learning loss is introduced, and training constraint is carried out on the forged feature extractor; and S6, performing fine adjustment on the forged feature extractor and an adaptive device. According to the method, the model gets rid of feature dependence bias generated by interference of irrelevant semantic features in the picture on the model as far as possible, the method has excellent detection capability for forged pictures of different race statistical tags, and the optimal performance is achieved under intra-domain and cross-domain tests.

The invention discloses a multi-modal text travel knowledge base response method and system based on a large language model. The method comprises the following steps: acquiring a text and an image input by a user; performing retrieval through an image similarity retrieval technology and a text knowledge base; and returning tourism information related to user input. According to the system architecture, a large language model, image similarity retrieval and text knowledge base construction are integrated, multi-modal input can be efficiently processed, and personalized and accurate tourism information services are achieved. The system further comprises a set of Web user interface which supports the user to interact through multi-mode query of images and texts. According to the method, the response speed and accuracy of the system can be effectively improved, and the expansibility of supporting voice interaction, multi-modal data processing and knowledge base content automatic updating is achieved. The method and the system are suitable for scenes needing to provide personalized tourism information services, and have relatively high practicability and innovativeness.

The invention belongs to the field of big data processing, and discloses a crowd travel mode identification method and system for multi-view subspace learning based on dynamic and static feature fusion, and the method comprises the steps: carrying out the preprocessing of original signaling data, and cleaning invalid data; extracting a travel track of each user, and processing possible abnormal conditions of ping-pong data and drift data; after track data of a single user in a sample time period is obtained, segmenting the track data, and extracting a single trip chain track; extracting static characteristics such as travel behaviors and travel traffic of a travel chain in combination with multi-source data such as mobile phone signaling data, an OSM road network and public traffic data; extracting time sequence features by using an LSTM model, and modeling dynamic features of a travel track; static and dynamic features are fused, and travel modes are captured from multiple views. According to the method, the complex travel mode can be more accurately captured, data redundancy and noise are reduced, and the accuracy of travel mode identification is remarkably improved.

The invention belongs to the field of image text segmentation in the field of computer vision, and discloses an image text segmentation method based on frequency separation. Firstly, a CNN and a Transform are used to construct a local feature coding branch and a global feature coding branch respectively, and local features and global features from an image are extracted preliminarily. In the frequency feature enhancement module, wavelet transform is used to decompose the frequency of the input feature. And then enhancing the obtained high-frequency component and low-frequency component by using different strategies. And finally, low-frequency information is utilized to guide the network to pay attention to local features near the text region, the influence of irrelevant background noise on a segmentation result is reduced, and finally an accurate segmentation result is obtained. According to the method, the problem of dependence on a text detection model in an image text segmentation task is solved, and a result output by the method has high integrity and accuracy.

The invention provides a mechanical arm reward-free reinforcement learning method based on expert state learning, belongs to the technical field of automation, particularly focuses on operation control of a robot arm, and comprises two core modules: an expected state prediction network and a reward-free strategy network. The expected state prediction network is used for predicting state transition, and the non-reward strategy network optimizes action through an error between a prediction state of the expected state prediction network and a target state provided by an expert under the condition of no reward signal; according to the method, the mechanical arm can directly learn an effective grabbing strategy from state data observed by experts, complex reward function design is avoided, dependence on expert action data is not needed, and therefore understanding of dynamic characteristics of grabbing tasks is improved, and accuracy of action prediction is enhanced.

The invention relates to the technical field of biology, in particular to an oligo A-tailed DNA-nanogold material with high modification density and a preparation method of the oligo A-tailed DNA-nanogold material. The oligo A-tag DNA-nanogold material is prepared from AuNPs (AuNPs), and / or AuNRs (AuNPs) and modified oligo A-tag DNA (Deoxyribose Nucleic Acid), wherein the AuNRs are AuNPs, AuNRs and the modified oligo A-tag DNA; and an oligo A-tag DNA (Deoxyribose Nucleic Acid) sequence is as shown in SEQ ID No 1. The preparation method is low in cost and easy to operate, high-density oligoA-tailed DNA modification on the surfaces of the nanogold with different morphologies can be achieved, and stability is high.