18 results about "Random mapping" patented technology

The invention discloses a class incremental learning method for edge scene image recognition and electronic equipment, and the method comprises the steps: collecting real-time data, and taking the real-time data as an input sample; performing feature dimension raising on an input sample through a random mapping module of width learning, and mapping features to feature representation with higher dimensions; judging whether the input sample belongs to a new class sample or an old class sample according to the Grubrum matrix, and if the input sample belongs to the new class sample, performing amplification processing on a sample label; feature fusion is carried out on the Gramer matrix of the new-class sample and the Gramer matrix of the previous sample; and performing fine adjustment on the weight of an output layer of the width learning model by using the feature-fused Gramer matrix to obtain an edge scene image recognition model after class incremental learning. According to the method, feature fusion of new and old class samples after width mapping is realized by introducing the Grubrum matrix operation, and the incremental learning performance of a model class can be greatly improved. The method can be widely applied to the technical field of edge scene image recognition.

The invention provides a multi-dimensional engineering cost analysis and comparison method, which comprises the following steps of: obtaining an engineering construction plan, and constructing a time sequence according to construction time nodes in the engineering construction plan; acquiring spatial data and resource data according to the engineering construction plan; randomly mapping the spatial data and the resource data to a time period formed by construction time nodes in a time sequence according to different time nodes to obtain a construction sequence; calculating the viscosity of adjacent time periods in the construction sequence, and adding the viscosity into the construction sequence; a sparrow search algorithm is adopted to analyze and compare the construction sequence based on the lowest cost, and an optimal construction sequence is obtained; a time dimension, a space dimension and a resource dimension are combined together to construct a time sequence, and after the viscosity between a logistics supplier and a resource provider is considered, a sparrow search algorithm is adopted for optimization, so that an optimal construction sequence with the lowest construction cost evaluated from multiple dimensions can be obtained.

Provided is a method for authenticating identity. The method includes: generating a target random mapping function in response to an identity verification instruction, wherein a random mapping function is a function defined to randomly map characters into gestures; displaying a virtual keyboard based on the target random mapping function, wherein password conversion prompt information corresponding to the target random mapping function is displayed in the virtual keyboard and is defined to prompt to convert password characters in an original password into gestures; acquiring facial feature data by performing facial feature extraction on identity verification images collected by a camera; acquiring a gesture sequence by performing activity detection on the identity verification images; acquiring the original password by performing password conversion on the gesture sequence based on the target random mapping function; and performing identity authentication based on the original password and the facial feature data.

The invention discloses a body fat prediction system and method based on a multi-band impedance signal, and relates to the technical field of big data analys.The method comprises the steps that impedance data of different segments under different frequency bands, the body fat amount, the lean body weight and the human body weight are collected; integrity verification is carried out on the impedance data, missing values are filled with mean values, abnormal values are removed and corrected, and meanwhile timestamp alignment is carried out; extracting features to construct an original impedance vector, and mapping the original impedance vector to a high-dimensional space through a random matrix to generate a random mapping function; constructing a time sequence regression model, taking the embedding dimension as an input layer, taking the body fat amount and the lean body mass as an output layer, and using mean square error calibration and back propagation updating; and through a mean square error weighting evaluation model, outputting a performance standard result. The system comprises a data acquisition module, a data preprocessing module, a random distribution embedding module, a time sequence model training module and a display module. The method can adapt to impedance characteristics of different crowds, is suitable for portable terminal or smart home body measurement, and can be used at high frequency in daily life.

The application discloses a differential privacy data desensitization method based on time sequence random mapping and related devices, comprising: obtaining various target time sequence data that needs to be desensitized in a power transaction center, and clustering the target time sequence data by using a k-medoids clustering algorithm based on dynamic time warping distance measurement to obtain time sequence data sets of different clusters; based on the maximum compression ratio of the target time sequence data, the window value size corresponding to different target time sequence data in the same cluster is calculated, and the average compression ratio of all target time sequence data is determined, and the average compression ratio is taken as the target window size set during desensitization; based on the pre-determined security protection requirement level of the target time sequence data, the privacy budget required by differential privacy is determined, and the target time sequence data is processed according to the target window value size and the differential privacy desensitization mode of time sequence random mapping to obtain power market subject data after time sequence desensitization.

A semantically secure identification and communication method based on classical quantum channels comprises the following steps: constructing a classical quantum channel, selecting the input signal distribution and dividing the codeword, constructing an encoder, joint decoding, verification and identification, reliability analysis, and information leakage analysis. This invention divides the communication codeword into a main block and an auxiliary block. The main block uses an output statistical approximation of the transmission codebook, making it impossible for eavesdroppers to distinguish the communication signal from background noise. The auxiliary block uses a hash function for random mapping, preventing eavesdroppers from extracting valid information, thus achieving semantic security. Mapping the identification message to a combination of seed and hash value reduces the probability of confusion between different identification messages, improves identification accuracy, and provides a coding basis for analyzing false alarms, missed alarms, and information leakage. This invention has advantages such as strong confidentiality, strong concealment, high identification accuracy, and the ability to achieve identification communication while satisfying semantically secure requirements. It can be used for classical quantum secure communication.

This invention provides a bearing fault diagnosis method and system based on multi-information fusion. Step 1: Acquire time-varying vibration signals from the bearing. Calculate the number of sample points collected per revolution of the bearing based on the bearing speed and sampling frequency. Divide the acquired time-varying vibration signals into multiple samples according to the calculated number of sample points. Divide the samples into training and test datasets according to a certain ratio and add corresponding category labels. Step 2: Construct a signal feature extraction layer that includes extracted data features, impact features, time-domain features, and frequency-domain features. Step 3: Use an ELM classifier model to randomly map the data features from the experience pool and output the results. Step 4: Train the output weights of the bearing fault diagnosis model using the training dataset and use the trained weights for fault diagnosis on the test dataset. This invention can extract and effectively fuse signal features with multiple different attributes, facilitating bearing fault diagnosis.

According to various embodiments, a method executed by a processor is described, comprising: providing an electronic file that has a representable content of the electronic file in a first content description layer, wherein the representable content of the electronic file is described at a respective position within the first content description layer by means of an index, and generating a digital copy of the electronic file having several content description layers by performing the following for each index of at least a part of the representable content of the first content description layer of the electronic file: • For each index, a corresponding additional index is generated, wherein the additional index is set up in such a way that it is not visible to a human viewer when displaying the content of the electronic file using a file display program, wherein the additional index is generated using a random image; • The index is stored in one of the multiple content description layers, • The additional index is stored in a different content description layer among the multiple content description layers.

The present invention discloses an image texture classification method and system, comprising the following steps: extracting image texture features from an original image to form a feature vector of the original image; using a Gaussian kernel function to map the feature vector of the original image to a high-dimensional feature space to obtain a feature expression of the high-dimensional space; mapping the feature vector of the original image to a low-dimensional space by a random mapping method to obtain a feature expression of the low-dimensional space; fusing the feature expression of the high-dimensional space with the feature expression of the low-dimensional space to form a comprehensive feature representation; based on the comprehensive feature representation, using a classifier to classify the image texture. The present invention comprehensively applies high-dimensional space expression and low-dimensional space expression, fully utilizes the advantages of features of different dimensions, and improves the accuracy and efficiency of texture classification. At the same time, the present invention also has strong versatility and scalability, and can adapt to texture classification needs in different industries and scenarios.

The present application discloses a model training optimization method, an electronic device, and a computer-readable storage medium, which are applied to the field of artificial intelligence technology, including: randomly mapping the original data to obtain the mapping data of the original data; sending the predicted class label corresponding to the original data and the mapping data to the server communicating with the client, wherein the predicted class label is a label for training the model to be trained, so that the server can calculate the mapping feature matrix based on the mapping data, and calculate the model parameters corresponding to the model to be trained according to the mapping feature matrix and the predicted class label, and iteratively optimize the model to be trained based on the model parameters. The present application solves the technical problem of low security of model training.

The invention provides an order-preserving encryption method, a data query method and a data storage method. The order-preserving encryption method comprises the following steps: acquiring plaintext data, and performing order-preserving random mapping on the plaintext data to obtain first order-preserving coded data; carrying out decryptable encryption processing on the plaintext data to obtain decryptable ciphertext data; and splicing the first order-preserving coded data and the decryptable ciphertext data to obtain order-preserving ciphertext data. And according to the size sequence relationship of the first order-preserving codes, operations such as sequence-related comparison sorting query and the like in the secret state database can be quickly completed, and a plaintext form result corresponding to query is obtained. Compared with a common order-preserving encryption algorithm, the order-preserving coding encryption method and device can realize an efficient and safe order-preserving coding encryption function with a controllable ciphertext length.

The invention relates to a 3D point cloud target detection method and system based on random mapping, and the method comprises the steps: compressing a point cloud implicit vector of a 3D point cloud target detection image into a low-dimensional vector through a lower projection matrix, carrying out the L2 norm normalization processing, and obtaining a normalized vector; projecting the normalized vector to k one-dimensional axes through k independent random linear mapping functions to generate k projection value sequences, screening out the projection value sequence with the maximum variance as an optimal sequence, and calculating a vector difference value between the normalized query vector and the normalized key vector based on the optimal sequence so as to realize approximate nearest neighbor search. And the trained Transform target detection model carries out target detection on the 3D point cloud target detection image according to the sparse attention operator to obtain a target detection result. Therefore, the detection efficiency and the detection accuracy are improved.

The present application discloses a prediction method, device, equipment and medium based on a multi-modal extreme learning machine. The method includes: obtaining training data and neuron weight parameters under a probability distribution, and constructing a label vector corresponding to the training data; constructing a number of intermediate neurons under each probability distribution according to each neuron weight parameter; constructing a composite feature of the training data under each probability distribution according to each number of intermediate neurons; calculating a second-order sample feature corresponding to the composite feature, and constructing a kernel matrix corresponding to the second-order sample feature; obtaining a sample to be predicted, and predicting the sample to be predicted according to an extreme learning machine model jointly constructed by the kernel matrix and the label vector to obtain a prediction result. The present invention can be applied to solve data-driven modeling problems, such as image classification, sequence prediction, geophysics, credit evaluation, etc. The present application solves the technical problem of unstable accuracy of the extreme learning machine model caused by random mapping in the prior art.

The application discloses a data sharing method and device, equipment, a storage medium and a program product. The method comprises the following steps: performing first random mapping on a plurality of first original data to obtain a position index in a first sequence corresponding to each first original data; performing second random mapping on each first original data to obtain a second sequence corresponding to each first original data; performing third mapping on each second sequence according to the position index to obtain an encoding matrix, performing pseudo-random operation on the plurality of first original data based on the encoding matrix to obtain a first operation result; receiving a second operation result corresponding to a plurality of second original data sent by a second object, determining to-be-shared data according to the first operation result and the second operation result, and sending the to-be-shared data to the first object and / or the second object. By using the method, the leakage of data other than the to-be-shared data in local data can be avoided, and the privacy and security of data sharing are ensured.

The invention provides a width learning gradient stabilization method based on a generative adversarial network, and the method comprises the steps: obtaining and cleaning data information from a database through a data collection and preparation module, so as to obtain the needed information; the feature construction and width expansion module introduces a width learning structure, and constructs a wide feature space with strong nonlinear representation capability through multiple groups of random mapping nodes and enhanced nodes; the model construction and training module adopts a width network structure and realizes final output through a trainable linear projection weight; according to the recommendation result generation and output module, the system performs prediction scoring on candidate items according to the output of the trained generator; and the model evaluation and updating module is used for evaluating a model effect through an offline evaluation index and continuously monitoring recommendation performance in an online stage.

A method and system for hiding a secret into a digital information and for recovering it are proposed. The method comprises, by a hiding module: obtaining a digital information and a secret that a user wants to hide into the digital information; generating an invariant information using the digital information; generating a hiding information by implementing a random data processing comprising randomly mapping bits of the secret with bits of the invariant information; generating a secret identifier unique for the secret using the invariant information and / or a value provided by the user; generating a custodian hiding information using the generated secret identifier and an encrypted hiding information; sending the custodian hiding information and an identity proof of the user to a custodian module; and receiving a notification of whether the custodian hiding information has been stored. The method also recovers the hidden secret using a recovering module and the custodian module.

The present invention belongs to the field of recommendation technology, and specifically relates to a project recommendation method and device based on an attribute-expanded dual message propagation graph. The method includes obtaining user data, project data, and attribute data to construct a user-project-attribute tripartite graph structure; obtaining initial user, project, and attribute embedding vectors through random mapping technology; inputting them into a preference information graph neural network to obtain user and project preference embedding vectors; inputting them into a similarity information graph neural network to obtain user and project similarity embedding vectors; calculating the user's predicted attribute score for the project based on the inner product of the fused user final embedding vector and the project final embedding vector; inputting the predicted score into a user-project-attribute matrix, finding the project and attribute corresponding to the highest predicted score, forming a recommended explanation list, and taking the top-ranked attributes as explanations for the recommended project. The present invention improves the accuracy and interpretability of the recommendation system.

The application discloses a kind of for edge scene image recognition class incremental learning method and electronic equipment, wherein method includes: collecting real-time data as input sample;By the random mapping module of width learning to input sample is carried out feature dimension, feature is mapped to higher-dimensional feature representation;According to gram matrix, judge whether input sample belongs to new class sample or old class sample, if it is new class sample, sample label is amplified processing;Gram matrix of new class sample and gram matrix of previous sample are carried out feature fusion;The output layer weight of width learning model is fine-tuned using gram matrix after feature fusion, obtains the edge scene image recognition model after class incremental learning.The application is introduced gram matrix operation, realizes the feature fusion of new and old class samples after width mapping, can greatly improve the model class incremental learning performance.The application can be widely applied to edge scene image recognition technical field.