112 results about "Sparse vector" patented technology

The invention belongs to the field of natural language processing, particularly relates to a multi-modal document generation method and device based on multi-agent collaboration, and aims to solve the problems that an existing method is low in intention recognition accuracy, limited in retrieval range and not professional enough in content generation. The method comprises the following steps: generating a structured template; analyzing the text input by the user to identify a writing intention, and determining a target template; vectorizing each candidate resource feature to obtain a corresponding sparse vector, a dense vector and a knowledge vector, and performing semantic alignment; extracting context features of the input text, respectively performing multi-path retrieval recall, evaluating and sorting recall results, and screening out target features; and constructing a thinking chain in combination with the knowledge graph, and generating a multi-modal document according to the target template. According to the method, the outline structure can be extracted, the picture / table style can be recognized, the templates adaptive to different document types can be dynamically generated, and full-process automation from user input to document output is achieved.

The invention provides a highway intelligent operation and maintenance question-answering system based on a large language model, and belongs to the technical field of natural language processing. The system takes a large language model as a core reasoning engine and combines a domain knowledge base and an RAG technology to realize accurate question and answer of highway operation and maintenance; the method comprises the following steps: based on original knowledge data cutting, generating a title through a large language model, and customizing a knowledge base; receiving query, analyzing an intention by using a large language model, and matching to generate a function; the query is rewritten by using a large language model, dense and sparse vector query is generated, and a double-layer retrieval mechanism is formed; a two-step recall mode is utilized, coarse-grained recall is firstly carried out, then a recall result is subjected to fine-grained optimization through a screening mechanism, and a reasoning text is generated; and finally, inputting the query and reasoning text into the large language model, and generating an optimal answer through single-round and multi-round questions and answers. According to the method, the professionality and reliability of answers are enhanced, and the technical problem that answers are incomplete and inaccurate in an existing question and answer system is solved.

The invention relates to the technical field of information retrieval, and provides a multi-dimensional heterogeneous knowledge recall enhanced hybrid retrieval method and system.The method comprises the steps that texts recalled through keyword retrieval, sparse vector retrieval and dense vector retrieval are screened through a reciprocal sorting fusion algorithm, and a text type candidate knowledge list is obtained; based on user query, generating and checking a query statement through a large language model, and retrieving an entity-relationship-attribute triple from the knowledge graph library; based on user query, generating enhanced knowledge through a knowledge graph enhanced retrieval method fusing keyword retrieval, vector retrieval and community retrieval; and carrying out format alignment and duplicate removal on the text type candidate knowledge list, the triple result and the enhanced knowledge to form a multi-modal candidate pool, and carrying out reordering score calculation and ordering on each piece of recall knowledge in the multi-modal candidate pool through a reordering model and a business rule to obtain a final retrieval result. And the coverage blind area of single retrieval on heterogeneous knowledge is solved.

The invention discloses a data scarcity industrial vertical field-oriented knowledge-guided retrieval enhancement generation method, belongs to the technical field of natural language processing and industrial intelligence crossing, and can improve the retrieval accuracy and generation reliability of a large language model in an industrial scene. According to the method, a'sparse vector + dense vector 'mixed knowledge base is constructed, and general knowledge and industrial field texts are fused; after the model generates an initial text, judging whether external retrieval is needed or not through multi-dimensional evaluation token confidence; extracting attention weights for the low-confidence tokens, and screening key tokens to generate a retrieval query; dynamically adjusting the weight of a retriever based on a BGE-M3 model, and optimizing a retrieval result through reordering; the retrieval knowledge is converted into a context with an index, and a prompt template is constructed to generate a correction value iteration calibration text; and finally, optimizing the text format, and generating a structured response meeting industrial requirements. The method solves the problems of lack of professional knowledge of large language models in the industrial field, shallow retrieval and generation fusion, lack of knowledge calibration mechanisms and the like.

Disclosed embodiments include a computational memory system. The computational memory system includes at least one computational memory chip including one or more processor subunits and one or more memory banks formed on a common substrate. The at least one computational memory chip is configured to store one or more portions of an embedding table in the one or more memory banks, the embedding table including one or more feature vectors. The one or more processor subunits are configured to receive a sparse vector indicator from a host external to the at least one computational memory chip and, based on the received sparse vector indicator and the one or more portions of the embedding table, generate one or more vector sums.

Conventional Orthogonal frequency division multiplexing (OFDM) is unable to retain its orthogonality and suffers loss in performance in high Doppler circumstances. The present disclosure converts a signal received in delay-time domain into delay-Doppler domain and extracts a guard band region from the received converted signal. A 2-dimensional fast Fourier transform is performed on guard band region extracted from received converted signal. A 2-dimensional fast Fourier transform of the received converted signal is divided with the 2-dimensional fast Fourier transform of transmitted signal to extract phase information. A dictionary is created using a pre-defined set of values of delay and Doppler. A sparse recovery problem is formed for received converted signal using an orthogonal matching pursuit algorithm. One or more parameters are estimated by identifying one or more locations pertaining to the one or more columns corresponding to L significant non-zero locations comprised in sparse vector of sparse recovery problem.

The invention discloses an electric power equipment safety long text knowledge retrieval method based on sparse and dense joint enhancement, which comprises the following steps of: encoding an electric power equipment safety long text and retrieval query by utilizing a pre-training language model for performing supervision and fine tuning on an electric power equipment safety field label data set, and generating a semantic word vector; a weighted sparse vector fusing semantic information and a dense semantic vector enhanced through nonlinear transformation are generated through fine-grained semantic enhancement branches; respectively calculating sparse similarity based on a common item weight product and dense similarity adopting a double-distance weighted fusion strategy combining a cosine distance and an Euclidean distance; and carrying out weighted summation on the two similarity scores through the learnable weight to obtain a final similarity, and realizing accurate sorting retrieval of the long text knowledge. The method gets rid of dependence on global features of sentence vectors, can accurately capture local key information in a long text, and has high retrieval precision and semantic robustness.

This invention belongs to the field of wireless communications technology and discloses a large-scale multiple access method based on adaptive matching pursuit. First, some active users in a large-scale user terminal send spread-spectrum signals to a base station to perform uplink access transmission. Next, the base station receives the uplink signals of multiple users and models them as block-sparse vectors, using these vectors to reconstruct a new uplink receive signal equation. The base station then uses an adaptive matching pursuit algorithm based on the block-sparse model to detect active users and reconstruct the user-sent data. This invention is suitable for scenarios where large-scale terminals have sporadic burst uplink transmissions. It can achieve unauthorized random access for large-scale terminals while reducing user terminal overhead, thereby improving the uplink throughput of cellular networks.

The invention belongs to the technical field of robot control, and particularly discloses a wire harness assembly robot control method and system based on machine learning, and the method comprises the steps: firstly collecting the joint torque, the position error of an end effector, the posture change and other multi-dimensional sensor data in real time when a robot wire harness is plugged; intercepting and constructing a multi-channel contact event tensor by a sliding time window; inputting the effective contact event into a pre-training sparse auto-encoder, encoding to obtain a sparse vector, reconstructing a reconstructed tensor, and decomposing a sparse component of the effective contact event and a residual component of interference noise; identifying an effective contact event by judging whether the norm of the sparse vector L1 exceeds a first threshold value or not; and finally, calling a predefined fine tuning control strategy to execute an action response. Weak contact event recognition precision and action response accuracy are improved, assembly quality and safety are guaranteed, and the method is suitable for efficient control of the wire harness assembly robot.

The invention relates to the technical field of wireless communication, and discloses a robust semantic communication method, device and equipment based on sparse vector coding, and the method comprises the steps: extracting continuous semantic features of original data through a semantic encoder model; discretizing the continuous semantic features into index bits through a vector quantization method by using a learnable feature dictionary; the index bit is mapped into a sparse vector by adopting sparse vector coding, and the sparse vector is sent after being expanded by a codebook; and a receiving end identifies the index through a multipath matching pursuit algorithm and reconstructs the original data. According to the method, a semantic feature extraction model, a vector quantization technology and sparse vector coding are fused, and gradient approximation, joint loss function optimization and a transmission parameter dynamic adjustment mechanism are designed, so that the problems of poor digital transmission compatibility and weak channel adaptability of traditional semantic communication are effectively solved; and the semantic transmission reliability and the system resource utilization efficiency under the dynamic channel condition are improved.

A computer-implemented method for detecting attribute value pairs from corpus data using a computer comprising a processor and a computer readable medium comprising instructions executable by the processor to at least: receive the corpus data comprising at least one pair; detect a layout template of the at least one pair; measure the merit of the layout template by determining at least one of (a) relative magnitudes of content probabilities based on a probability of the contents of an attribute cell and a probability of a corresponding value cell, (b) the validity of a name-value pair, or (c) the pointwise mutual information of a frequency matrix M corresponding to a sparse vector capturing context information of a word; and output detected attribute value pairs.

The invention discloses an article recommendation method based on RAG and knowledge graph guidance. The method specifically comprises the following steps: preprocessing and warehousing a structured abstract based on a large language model, adopting an offline processing mode of first abstracting and then warehousing, and utilizing the large language model LLM to obtain a structured abstract document through a two-stage prompt project; performing deep normalization on user input by utilizing the knowledge graph, converting all non-standard input into standardized entity names, and complementing the association relationship of the non-standard input and the standardized entity names; acquiring an article by adopting a sparse vector and dense vector mixed recall strategy; independent reordering and scoring links driven by a Qwen3 32B large model are introduced, a context-aware paired comparison task is designed for the large language model LLM, and a final recommendation result is ensured. The method has the advantages that it is ensured that recommended content is highly consistent with user requirements; professional recommendation services far beyond general schemes are provided; and the quality of recommendation results is greatly improved.

The invention provides a time-space structured sparse optical coding deepwater heterogeneous network data synchronization method and system, and the method comprises the steps: carrying out the sparse decomposition of the time sequence clock deviation data of each current underwater node at a transmitting end device of a deepwater heterogeneous network based on a trained over-complete dictionary, and obtaining an original sparse vector; converting the dynamic compression observation data corresponding to the original sparse vector into an optical signal, and transmitting the optical signal to a receiving end device of the deepwater heterogeneous network by a transmitting end device through an umbilical cable; demodulating the optical signal into an observation vector through receiving end equipment, inputting the observation vector into the trained deep expansion network model, and outputting a reconstructed sparse vector by the deep expansion network model; and recovering the reconstructed sparse vector into a clock skew signal through the over-complete dictionary, and generating a clock synchronization calibration instruction to realize data synchronization of the corresponding underwater node. According to the invention, the problems of high bandwidth occupation, low signal ratio and poor reconstruction time efficiency existing in the underwater network time synchronization technology can be solved.

The invention provides a radar channel and communication channel estimation method and device of a communication and inductance integrated system, and belongs to the technical field of wireless communication. The method comprises the following steps: determining a joint sparse vector of a radar channel and a communication channel based on a sparse vector of the radar channel and a sparse vector of the communication channel; determining a channel dynamic sparsity probability expression based on the joint sparse vector and a space-time Markov model; solving the channel dynamic sparsity probability expression based on a three-layer Bayesian reasoning framework to obtain a channel dynamic sparsity probability; substituting the dynamic sparsity probability of the channel into a maximum likelihood estimation problem of the environmental perception parameters, and solving the maximum likelihood estimation problem to obtain the environmental perception parameters; and estimating a radar channel and a communication channel based on the environment perception parameters. According to the radar channel and communication channel estimation method and device of the communication and inductance integrated system, the estimation precision of the radar channel and the communication channel can be effectively improved.

The invention relates to a verification code processing method. The method comprises the following steps: in response to a verification code acquisition request sent by a client, generating a first verification code for the verification code acquisition request; converting the first verification code into a first sparse vector based on a preset mapping rule; performing encryption processing on the first sparse vector to obtain an encrypted vector; and sending the encryption vector to the client to enable the client to reconstruct a first sparse vector based on the encryption vector, and converting the first sparse vector into a first verification code based on a preset mapping rule. By adopting the method, the security of verification code transmission and verification can be improved.

Certain aspects of the present disclosure provide techniques and apparatus for wireless channel estimation using machine learning. A sensing matrix is processed using a set of one or more layers of a machine learning model, based on a learned sparsifying dictionary, to generate a set of associated sparse vector representations. A channel estimation is determined based on output of a final layer of the set of one or more layers of the machine learning model.

The invention relates to the technical field of bearing fault detection, in particular to a bearing fault sparse feature extraction method based on local feature online learning, and the method comprises the steps: collecting a bearing vibration original signal of warehouse logistics equipment, and carrying out the normalization processing; performing sliding window segmentation on the processed bearing vibration signal based on a kurtosis index, and selecting a preset number of signal segments with the maximum kurtosis as an initial atom set; carrying out orthogonalization operation on atoms in the initial atom set in sequence to form an online learning dictionary based on local feature learning; carrying out convolution operation on atoms in the online learning dictionary and the normalized bearing vibration signal to obtain a sparse coefficient matrix, and executing soft threshold operation; kurtosis values of sparse coefficient vectors in the sparse coefficient matrix are calculated respectively, the sparse vector with the maximum kurtosis value is selected as a target feature vector for envelope spectrum analysis, and finally whether the bearing of the warehouse logistics equipment breaks down or not is judged through an envelope spectrum.

The application relates to the technical field of medical treatment and discloses a liver chronic disease screening method, a device and a storage medium.The method comprises the following steps: a liver detection system collects liver stiffness data and liver fat attenuation parameters of a target object; a mobile terminal system receives the liver stiffness data and the liver fat attenuation parameters, combines the liver stiffness data and the liver fat attenuation parameters with basic information of a preset target object, generates acquisition characteristic data, carries out label marking matrix processing on pretreatment integrated data of the cloud service system, generates a label marking matrix, carries out fitting residual processing on the label marking matrix, obtains extended decision tree data, carries out discrete sampling processing on the extended decision tree data, obtains a sparse vector, carries out classification calculation processing on the sparse vector, obtains a classification result, and generates a disease screening report based on the classification result.In the embodiment of the application, through system architecture and cloud service system data processing, the early warning timeliness and accuracy of liver chronic disease screening are improved.

Techniques for generating and managing sparse vector representations in a database system are provided. In one technique, an embedding that was generated by an embedding model is accessed. Based on one or more characteristics associated with the embedding, a particular storage format is selected from among multiple storage formats in which to store the embedding. A sparse vector representation is generated based on the embedding and the particular storage format. The sparse vector representation is stored. The sparse vector representation may be stored in the same VECTOR type column that stores sparse vector representations that are in different storage formats and / or dense vector representations.

The application relates to the technical field of wireless communication, and discloses a robust semantic communication method, device and equipment based on sparse vector coding, which comprises the following steps: extracting continuous semantic features of original data through a semantic encoder model; discretizing the continuous semantic features into index bits through a vector quantization method by using a learnable feature dictionary; mapping the index bits into sparse vectors by using sparse vector coding, and transmitting the sparse vectors after codebook extension; and identifying the index and reconstructing the original data by using a multi-path matching tracking algorithm at a receiving end. By fusing a semantic feature extraction model, a vector quantization technology and sparse vector coding, and by designing a gradient approximation, a joint loss function optimization and a transmission parameter dynamic adjustment mechanism, the application effectively solves the problems of poor compatibility and weak channel adaptability of traditional semantic communication digital transmission, and improves the semantic transmission reliability and system resource utilization efficiency under dynamic channel conditions.

The invention belongs to the cross technical field of artificial intelligence and synthetic biology, and discloses an intelligent retrieval reasoning method and system oriented to strain development, and the method comprises the steps: collecting a document in a portable document format from an open acquisition database, carrying out document analysis processing to generate a lightweight markup language file, carrying out semantic splitting to obtain text paragraphs, and storing the text paragraphs in the open acquisition database; forming a data set; taking the split text paragraphs as input, generating a sparse vector and a dense vector for each text paragraph by utilizing a retrieval plug-in, establishing a vector mixed index framework, and respectively storing the vector mixed index framework in a database; an application interface layer is built, and a data interface used for full-text retrieval and paragraph precise reading is provided. According to the method, a general technology and a synthetic biological strain development whole process are deeply fused, and strain development key information such as gene modification, metabolism regulation and control, culture medium setting and fermentation conditions is accurately matched; and the DBTL whole-process operation efficiency of a biological manufacturing enterprise and an invention mechanism in strain development is obviously optimized.

The application discloses a Chinese herbal medicine composition quality information processing method and device. It relates to the field of artificial intelligence technology. The method comprises the following steps: obtaining target data information corresponding to a target Chinese herbal medicine composition to be predicted, wherein the target data information at least comprises medicine name information of multiple medicinal materials contained in the target Chinese herbal medicine composition and medicinal material weight information corresponding to each medicinal material; performing feature conversion on the target data information through a first feature converter or a second feature converter in a target model to obtain a target sparse vector; and processing the target sparse vector through at least one multi-classification layer in the target model to obtain target quality information corresponding to the target Chinese herbal medicine composition. Through the application, the technical problem that the quality information prediction accuracy is relatively low in the related art due to the quality information prediction of Chinese herbal medicine compositions based on an electronic tongue is solved.

The invention discloses a frame conversion DCSK system based on pulse position modulation and a communication method, the system comprises a modulator and a demodulator, and the modulator and the demodulator transmit signals through a channel; the modulator is used for generating a chaotic signal and applying dynamic frame transformation to the chaotic signal to construct a frame structure with time slot variability; and the demodulator is used for receiving the modulation signal sent by the modulator to obtain a received signal, and carrying out dynamic frame structure adjustment and multi-path delay alignment processing on the received signal. Compared with the prior art, the method has the advantages that a frame transformation mechanism and a pulse position modulation technology are introduced, so that the reconstruction of a chaos signal frame structure and the optimization of an information mapping mode are realized. Partial information bits are used for pulse position mapping, and only a single pulse is excited in a sparse vector, so that a modulation signal has stronger anti-interference capability, and the robustness of a system in a low signal-to-noise ratio environment is effectively improved.

The embodiment of the invention provides a model training method in a network target range, a network security judgment method and device, equipment and a medium, and relates to the technical field of network security. Obtaining a local reference parameter according to the reference parameter and a learnable sparse vector mask, and obtaining a first adaptive parameter and a second adaptive parameter according to other adaptive parameters and adaptive parameters, obtaining a model parameter of a network security discrimination model in the target client at least according to the local reference parameter, the adaptive parameter, the first adaptive parameter and the second adaptive parameter; adjusting the model parameter at least based on the task loss function to obtain a target reference parameter, a target vector mask and a target adaptive parameter, and obtaining a trained network security discrimination model; and at least sending the target reference parameter and the target vector mask to a server side, so that the server side updates the global parameter. And the model parameters are split, so that the prediction accuracy is improved, and meanwhile, the multi-task disastrous forgetting is effectively relieved.

This application discloses a data processing method and apparatus, electronic device, and computer program product. It relates to the field of artificial intelligence technology. The method includes: performing a multi-path knowledge retrieval operation in a target knowledge base based on target question information to obtain multiple initial response information, wherein the multi-path knowledge retrieval operation includes at least: a sparse vector-based knowledge retrieval operation and a dense vector-based knowledge retrieval operation; sorting the multiple initial response information if they meet preset conditions to obtain processed initial response information; and determining the target response information corresponding to the target question information based on the processed initial response information. This application solves the technical problem that retrieving response information for related questions through keyword matching results in relatively low accuracy of the response information.

The application belongs to the field of bridge health monitoring and rapid detection, and discloses a bridge bending stiffness identification method based on multi-point deflection influence line input, and steps are as follows: firstly, a linear model for solving bending stiffness is established by using measured deflection influence lines at multiple positions of a bridge and linear elasticity theory; then, a redundant dictionary composed of multiple types of global basis functions is used for sparse representation of the bending stiffness distribution curve, and the bending stiffness reconstruction problem is converted into a sparse vector solving problem; finally, a sparse vector solution model with 1-norm regularization constraint is established, and the optimal bending stiffness distribution is obtained by solving the model. l The application can realize continuous bending stiffness curve solving by using multi-point measured deflection influence lines only, is suitable for stiffness evaluation of statically indeterminate in-service bridges such as continuous girder bridges, and has the advantages of strong applicability, high solving efficiency and strong robustness.

The application provides a kind of spatio-temporal structure sparse light coding deep water heterogeneous network data synchronization method and system, including based on the overcomplete dictionary trained, the time sequence clock deviation data of each underwater node in the sending terminal equipment of deep water heterogeneous network is sparsely decomposed, and the original sparse vector is obtained;After the dynamic compressed observation data corresponding to the original sparse vector is converted into optical signal, it is transmitted to the receiving terminal equipment of deep water heterogeneous network by umbilical cable by sending terminal equipment;After the optical signal is demodulated into observation vector by receiving terminal equipment, it is input into the trained deep unfolding network model, and the reconstructed sparse vector is output by deep unfolding network model;The reconstructed sparse vector is recovered into clock deviation signal by overcomplete dictionary, and clock synchronization calibration instruction is generated, to realize the data synchronization of corresponding underwater node.The application can solve the problems of high bandwidth occupation, low signal ratio and poor reconstruction timeliness in underwater network time synchronization technology.

The present application relates to the technical field of mechanical fault diagnosis, and discloses a gearbox fault diagnosis method and system based on light-weight variational Bayesian learning, which comprises the following steps: collecting a vibration signal to be diagnosed of a gearbox, preprocessing the vibration signal to be diagnosed to obtain an original vibration signal and a fault characteristic frequency thereof; determining an amplitude-frequency modulation sparse combination representation of the original vibration signal according to the fault characteristic frequency of the original vibration signal, and constructing a joint probability model according to a classification distribution containing a sparse vector and the amplitude-frequency modulation sparse combination representation of the original vibration signal; performing variational Bayesian inference solving on the joint probability model by using a non-overlapping subsequence of the original vibration signal and a natural gradient optimization to obtain a posterior probability estimation of a sparse coefficient; determining an active component according to the posterior probability estimation of the sparse coefficient and a sparse precision parameter, and matching the active component with a pre-established multi-scale amplitude-frequency modulation sparse dictionary to obtain a fault type and a confidence thereof.

The invention belongs to the technical field of data processing, and discloses a hybrid vector-based normative file intelligent question-answering system, which comprises a structure analysis module for splitting a university normative file into a plurality of atomic fragments by extracting natural hierarchical information; for each clause atomic fragment, generating a corresponding hierarchical path identifier and an original position index, and constructing a clause atomic fragment set through association packaging; the knowledge base construction module is used for carrying out multi-dimensional semantic modeling on the clause atom fragment set and respectively generating dense vector representation and sparse vector representation; constructing a hybrid vector index based on dense vector representation and sparse vector representation; refined structure modeling of university normative files is achieved, and clause retrieval accuracy is improved.

The invention discloses a folding clutter suppression method based on a frequency agility radar, and the method comprises the steps: setting the pulse number of a frequency agility pulse sequence, a frequency hopping interval and a frequency hopping coefficient of each frequency agility pulse signal, and transmitting a plurality of frequency agility pulse signals; calculating the carrier frequency of the echo signal received by the frequency agility radar according to the frequency hopping interval and the frequency hopping coefficient; filtering the echo signal by using a frequency domain filter corresponding to the echo signal carrier frequency, and outputting the filtered echo signal; respectively performing impulse response and convolution processing on the time domain and the frequency domain of the filtered echo signal by using a matched filter, and outputting the echo signal after matched filtering; and sparse reconstruction is carried out on observation signals in the sparse reconstruction model by using an orthogonal matching pursuit algorithm or an alternating direction multiplier method to obtain sparse vectors, so that target signal energy is enhanced, non-matching interference components are suppressed, significant enhancement of weak and small targets is realized, and folding clutters and noise are suppressed.