49 results about "Alternating least squares" patented technology

The invention discloses a broadband coherent signal source DOA estimation method based on three orthogonal dipoles. The method comprises the following steps: obtaining an array output matrix by using a single three orthogonal dipole antenna; carrying out FFT (Fast Fourier Transform) on the output matrixes of the three antennas to obtain an array frequency domain output matrix; if the signal is a frequency agility signal, taking out an amplitude-phase peak value, and accumulating frequency domain amplitude-phase peak values of a plurality of frequency points; if the signal is a linear frequency modulation signal, taking an amplitude-phase value in a certain range from a frequency spectrum; rearranging the frequency domain amplitude and phase values of the plurality of frequency points; forming a frequency shift data set; performing surface stacking on the frequency shift data set to obtain a third-order tensor; realizing third-order tensor decomposition by using a trilinear alternating least square method to obtain a steering vector matrix; and calculating an azimuth angle, a pitch angle, a polarization auxiliary angle and a polarization phase difference according to the steering vector matrix. According to the method, a small array aperture, a small number of array elements and low operation complexity are used, DOA estimation of a plurality of coherent signals is realized by using information of a plurality of frequency points, and polarization information estimation is given.

The invention relates to an electric vehicle wireless charging system LPV-Hammerstein model identification method based on an alternating least square iteration strategy, and belongs to the technical field of power electronic system modeling and parameter identification. The method comprises the following steps: firstly, constructing an LPV-Hammerstein model structure based on a WPT system circuit topology and a working mechanism, and then collecting discrete data of a system input control signal U, an output DC voltage Vo and a scheduling variable Req; then, alternately fixing other parameters by adopting an alternate least square iterative algorithm, and converting a to-be-estimated parameter problem into a linear least square sub-problem to be solved; and when a convergence condition is satisfied, a final LPV-Hammerstein model parameter estimation result is obtained. According to the method, the common nonlinear and parameter change coupling characteristics in the wireless charging system of the electric vehicle can be effectively processed, a systematized and efficient way is provided for obtaining a high-precision system dynamic model, and the limitation that the system cannot be accurately described by a traditional linear model or a simple nonlinear model is overcome.

The invention relates to the technical field of servo control, in particular to a servo driving current harmonic compensation method and system for electromagnetic interference suppression. The method comprises the following steps: extracting common-mode and differential-mode interference by using current and voltage sampling and combining differential measurement, and configuring a multi-stage passive filter according to spectrum characteristics to construct a suppression channel; establishing a digital interference cancellation mechanism, generating a reverse compensation signal by adopting self-adaptive trapped wave and a DSP (Digital Signal Processor), and injecting the reverse compensation signal into a control loop to form a software-defined multi-channel suppression architecture; after interference suppression, a high-order tensor model is constructed for the purified three-phase current, and an alternating least square method is adopted for decomposition so as to separate multi-band harmonic waves; a graph neural network is introduced, harmonic coupling is represented, and dominant and residual harmonic decoupling is realized through message passing; according to a grading progressive strategy, dominant harmonic waves are firstly subjected to coarse compensation, then residual harmonic waves are finely adjusted, and a compensation sequence is adaptively optimized through iterative feedback, so that high-robustness closed-loop control of servo driving is realized.

The invention relates to a millimeter wave MIMO-OFDM (Multiple Input Multiple Output-Orthogonal Frequency Division Multiplexing) system channel estimation enhancement method, which mainly solves the problems of unnecessary calculation overhead and precision loss in an estimation process due to the fact that the prior information of a stable path is not effectively utilized in the existing method. The method comprises the following implementation steps: 1) for each subcarrier, a base station (BS) is equipped with different beamforming vectors in continuous time frames, and a user (UE) independently detects a transmission signal in each time subframe; 2) separating known path information from the received signal to obtain a tensor slice combined with prior and unknown information, and constructing the tensor slice into a third-order tensor based on a parallel factor (PARAFAC) model; and 3) estimating three factor matrixes by using a prior information optimization alternative least square (ALS) algorithm, and estimating unknown channel parameters by using maximum likelihood (ML). According to the channel estimation enhancement method provided by the invention, the ALS algorithm can be optimized by using the prior information of a stable path, the estimation error can be reduced, and the system performance can be improved.

The invention discloses a model-free state estimation method and system for a power distribution network based on canonical multi-linear decomposition and a storage medium in the field of state estimation of a power system, and aims to solve the technical problem that the power distribution network cannot execute state estimation under the condition that real-time topological information of the power distribution network is lost. The method comprises the following steps: acquiring historical measurement data of a power distribution network and preprocessing the historical measurement data, constructing a three-dimensional tensor according to a time dimension, a node dimension and a measurement type dimension, and performing tensor decomposition on the three-dimensional tensor through an alternating least square algorithm to obtain an optimal decomposition factor matrix, and reconstructing a measurement tensor by using an optimal decomposition factor matrix to realize filtering of historical measurement data in an original three-dimensional tensor and complementation of missing measurement data, and finally extracting a voltage sub-tensor in the reconstructed measurement tensor and performing reverse normalization processing to obtain a voltage amplitude estimated value. The method is applied to state estimation of the power distribution network, and stable and accurate state estimation calculation can be achieved under the condition that topological information is not used.

The invention provides a three-dimensional fluorescence spectrum analysis method based on unsupervised contribution modeling. The method comprises the following steps: acquiring an original three-dimensional fluorescence spectrum of a sample; carrying out independent component analysis on the three-dimensional fluorescence spectrum, and reconstructing the spectrum by utilizing an analysis result; and carrying out modeling on the reconstructed spectrum by using a multivariate curve resolution-alternating least square algorithm to obtain an analysis report. According to the method, interference signals such as scattering in an original three-dimensional fluorescence spectrum are automatically removed through combination of two two-dimensional unsupervised modeling algorithms, then modeling is carried out on a reconstructed spectrum, dependence of three-dimensional fluorescence spectrum analysis on data, tools, platforms and personnel is reduced, good fault tolerance and accuracy are guaranteed while flexibility is improved, and the method is suitable for popularization and application. And reliable technical support is provided for water quality monitoring.

The invention provides a direction-of-arrival estimation method based on an unmanned aerial vehicle group-borne electromagnetic vector sensor array multi-input multi-output radar. The method is suitable for air and space target detection of an unmanned aerial vehicle cluster and a small reconnaissance aircraft cluster. One same electromagnetic vector sensor is installed on each unmanned aerial vehicle in a cluster to form an electromagnetic vector sensor array with any array element position, attitude error compensation is performed on a data receiving model of a single sensor, so that all airborne sensors reach a zero attitude, and the unmanned aerial vehicle is in a zero attitude state. An array transmitting data model and an array receiving data model are arranged according to a parallel factor model to obtain three-dimensional tensor data, a bearing matrix is obtained by using a trilinear alternating least square method, and finally DOA estimation is realized by using vector cross multiplication. According to the invention, multi-target DOA estimation of blind array element positions and blind polarization information is realized.

The invention relates to the technical field of power distribution network data processing, and discloses a power distribution network topology and line parameter identification method based on an intelligent electric meter, which comprises the following steps of: configuring the intelligent electric meter at a node of a power distribution network system, obtaining injection active power, reactive power and voltage amplitude of all nodes in a set sampling time period, and performing denoising processing to obtain a power distribution network topology and line parameter identification result; obtaining a denoised measurement data set; establishing a voltage power relation equation between the denoised measurement data and the impedance information, converting the voltage power relation equation into a matrix form, and normalizing the data; reactance information matrixes and resistance information matrixes of all the nodes are obtained, an alternating least square regression method is adopted for iterative solution, and optimal reactance information matrixes and resistance information matrixes of all the nodes are obtained; performing clustering analysis based on the optimal resistance information matrix of all nodes to obtain a node level array; based on the node level array, constructing a graph topological structure of the nodes to obtain line parameters; according to the method, the calculation precision of the line parameters in the topological structure of the power distribution network is improved.

The invention belongs to the technical field of radar parameter processing, and discloses a polarization MIMO multi-parameter estimation method and system based on emission polarization modulation. The polarized multiple-input multiple-output high-frequency ground wave radar array structure is composed of a transmitting end and a receiving end; the transmitting end performs transmitting polarization modulation on a target signal transmitted by the transmitting array element through the polarization phase controller; a receiving end receives the echo data of the target after emission polarization modulation, and echo data reconstruction is carried out after pulse pressure processing is carried out on the echo data; constructing a three-order tensor form, and performing tensor decomposition on the three-order tensor form through an alternating least square method; polarization parameter joint estimation is carried out by using a multi-parameter joint estimation signal processing method. The invention aims at designing a novel high-frequency ground wave radar transmitting and receiving array structure and a P-MIMO-HFSWR signal processing method, and multi-parameter high-precision estimation of a sea surface target is realized.

The application discloses a deep learning driven target parameter estimation method, and relates to the cross field of radar signal processing and artificial intelligence. The application embeds the maximum correlation entropy criterion into an alternating least square process, expands the alternating least square process into a differentiable network layer containing weight updating and a damped weighted least square, realizes end-to-end optimization under a unified criterion by combining a deep initialization network, introduces a sigma-Net based on a teacher-student framework, dynamically predicts an optimal kernel width based on three types of characteristic features, namely, a residual tail ratio, a peak ratio and an estimated GSNR, and synchronously optimizes initialization quality and kernel width strategies through double-path gradient back propagation, so that the synergistic gain of high-quality initialization, robust updating and adaptive parameter adjustment is realized.

The invention provides a PARAFAC decomposition measurement method for platform attitude tracking of a reference wave structure, and the method comprises the steps: building an array steering vector of an airborne electromagnetic vector sensor according to a change rule between the attitude position of the airborne electromagnetic vector sensor and a received signal; according to a three-dimensional information structure and attitude relation of signal time, polarization and space-frequency phase delay, all electromagnetic vector sensors are arranged to receive signal data, and a parallel factor trilinear data model can be obtained. An observation matrix is windowed, a tracking algorithm is used for replacing tradition, and complexity is prevented from being increased along with time. By popularizing a traditional parallel factor alternating least square algorithm, platform attitude data of a reference wave structure is tracked under the orthogonal constraint condition, and then the platform attitude is calculated.

The present invention provides a method for accelerating the calculation of a recommendation system based on an analog in-memory computing circuit, and belongs to the fields of semiconductor, analog computing, and integrated circuit technology. Based on the iterative calculation of the alternating least squares method, the method of the present invention designs a block matrix method, utilizes a variable resistor array to solve large-scale matrix decomposition problems, and uses analog computing to accelerate the large number of ridge regression calculations contained in the block matrix method, thereby realizing analog computing acceleration of the recommendation system. The method of the present invention can achieve high-speed and energy-efficient matrix decomposition of the recommendation system, providing a new solution for hardware acceleration of the recommendation system training process in the context of big data, and has broad application prospects.

The invention relates to a railway communication interference elimination algorithm, and aims to realize interference elimination and symbol extraction. The algorithm comprises the following steps of: 1, randomly initializing # imgabs0 #; 2, performing tensor decomposition by using a multivariate decomposition interference elimination algorithm; 3, solving a rank-one matrix decomposition factor {h1, a1, s1} through a regular multivariate alternating least square algorithm of blind decomposition; and 4, estimating user information by using a singular value decomposition algorithm. The multivariate decomposition interference elimination algorithm comprises the following steps: step 1, obtaining a signal tensor # imgabs1 # through interference cancellation; step 2, decomposing a rank-one matrix factor {h1, a1, s1} by using a regular multivariate alternating least square algorithm of blind decomposition; step 3, reconstructing a signal # imgabs2 # and calculating a residual error # imgabs3 #; step 4, combining a rank 1 matrix factor of # imgabs4 # and a rank 1 matrix factor of # imgabs5 # to obtain a rank 2 initialization matrix factor H * = [h1, h '] and A * = [a1, a'], and # imgabs6 #; step 5, decomposing the rank matrix factors {Hr, Ar, Sr} by adopting a regular multiple alternating least square algorithm of blind decomposition, and finally reconstructing the signal and extracting information.

The invention discloses a recommendation method based on interpretable generalized logic transformation matrix decomposition. The recommendation method comprises the following steps: converting an original scoring matrix into normal distribution data through a generalized logic transformation function; constructing indexes based on similarity and indexes based on ranking; calculating probability distribution and expected scores of scores of the recommended items by the similar users, and generating interpretability indexes in combination with the similarity indexes; integrating the interpretability index into a matrix decomposition objective function for optimization; solving a user feature matrix and a project feature matrix through an alternating least square method or stochastic gradient descent; calculating a prediction score and mapping the prediction score back to an original score interval through generalized logic inverse transformation; generating a recommendation list; the method provided by the invention has wider applicability and higher performance in practical application.

The present application relates to a kind of millimeter wave MIMO-OFDM system channel estimation enhancement method, focus on solving the prior information of stable path that existing method cannot effectively utilize, leading to unnecessary calculation overhead and precision loss problem in estimation process.Its implementation steps are:1) for each subcarrier, base station (BS) is equipped with different beamforming vector in continuous time frame, user (UE) independently detects transmission signal in each time subframe;2) separate known path information from received signal, obtain the tensor slice of prior and unknown information joint, based on parallel factor (PARAFAC) model it is constructed as three-order tensor;3) using prior information optimization alternating least squares (ALS) algorithm, estimate three factor matrices, then use maximum likelihood (ML) estimation to obtain unknown channel parameters.The channel estimation enhancement method proposed in the present application can optimize ALS algorithm using the prior information of stable path, can reduce estimation error, improve system performance.

The present application relates to resource recommendation technical field, especially to a kind of learning resource recommendation method and system based on user portrait, including establishing user portrait matrix and learning resource feature matrix, and using factor decomposition machine and collaborative filtering algorithm to build the implicit semantic matching model of user and learning resource;The parameter of implicit semantic matching model is learned by alternating least squares method, and user-learning resource implicit semantic association feature is generated;User-learning resource implicit semantic association feature is used as individual code, and the Pareto optimal recommendation solution set of multi-objective learning resource recommendation optimization model is searched using non-dominated sorting genetic algorithm, and learning resource recommendation scheme is generated in combination with optimal recommendation decision model.The present application dynamically adjusts recommendation strategy by combining multi-objective optimization and deep reinforcement learning etc., improves the accuracy of recommendation, while it can balance the diversity and personalization of recommended content, improve the dynamic adaptability and robustness of recommendation system.

The application discloses a spatial weighted pooling shift invariant rank-(L, L, 1, 1) block term decomposition algorithm suitable for multi-subject fMRI data, and belongs to the field of medical signal processing. On the basis of an alternating least squares (ALS) method, a spatial weighted pooling processing method is proposed to preprocess multi-subject fMRI data, down-sample and smooth fMRI data images, and significantly reduce the fMRI data volume and remove most of the noise. In addition, considering the high space-time difference between subjects, the method combines spatial orthogonalization constraints and time shift invariance, relaxes and compresses the rank-(L, L, 1, 1) BTD model of the fMRI data, and improves the separation performance of the algorithm.

The present invention provides a WIFI parameter estimation and positioning method assisted by multiple RISs. Aiming at the indoor scenario with complex multipath effects, the present invention first constructs the received signal assisted by multiple RISs into a fourth-order parallel factor model based on tensors; secondly, utilizes subcarrier resources and adopts virtual antenna array technology to rearrange the model to meet the uniqueness of tensor decomposition; subsequently, uses the four-linear alternating least squares algorithm to decompose the rearranged tensor model, and extracts multipath channel parameters by using subspace methods; finally, adopts a search-free positioning method to achieve accurate positioning of users and multiple RIS nodes. Therefore, the indoor joint estimation and positioning based on the rearranged tensor assisted by multiple RISs proposed by the present invention has the advantage of high accuracy, and at the same time has stronger robustness compared with existing competing methods, thus better meeting the requirements of actual communication systems.

Embodiments of the present disclosure relate to online training and updating of factorization machines using alternating least squares optimization. Techniques for training a factorization machine (FM) using streaming alternating least squares (ALS) optimization are disclosed. A method of implementing the techniques according to an embodiment includes receiving a data point including a feature vector and an associated target value. The feature vector includes a user identifier, a topic identifier, and a context. The target value identifies the user's opinion of the topic. The method also includes applying the FM to the feature vector to generate an estimate of the target value, and updating the parameters of the FM for training of the FM. The parameter update is based on the application of streaming ALS optimization to the following: the data point; the estimate of the target value; and an updated sum of intermediate calculation terms generated by applying the streaming ALS optimization to previously received data points associated with a previous parameter update of the FM.

The invention discloses a method for measuring the attitude of a separated electromagnetic vector sensor array platform of a reference wave structure, belongs to the technical field of navigation, and is suitable for measuring the attitude of an aircraft-borne array aerospace platform. The electromagnetic vector sensor is separated in space, engineering realization is facilitated, cross polarization is avoided, and attitude measurement precision is improved. And according to the change rule between the attitude position of the airborne electromagnetic vector sensor and the received signal, an array steering vector of the airborne electromagnetic vector sensor is established. According to a relationship between a three-dimensional information structure of signal time, polarization and space-frequency phase delay and an attitude, signal data is received by arranging all electromagnetic vector sensors, and a parallel factor (PARAFAC) trilinear data model can be obtained. By popularizing the traditional parallel factor alternating least square algorithm, the platform attitude is calculated with high precision under the orthogonal constraint condition when the separated electromagnetic vector sensor is possibly incomplete.

The application belongs to the technical field of radar parameter processing, and discloses a polarization MIMO multi-parameter estimation method and system based on transmission polarization modulation. A polarization multi-input multi-output high-frequency ground wave radar array structure is formed by a transmission end and a receiving end. The transmission end performs transmission polarization modulation on the target signal transmitted by the transmission array element through a polarization phase controller. The receiving end receives the echo data of the target after the transmission polarization modulation, performs pulse compression processing on the echo data, and then reconstructs the echo data. The form of a third-order tensor is constructed, and then the tensor decomposition of the third-order tensor form is performed through an alternating least square method. The polarization parameter joint estimation is performed through a multi-parameter joint estimation signal processing method. The application aims to design a novel high-frequency ground wave radar transmission-receiving array structure and a P-MIMO-HFSWR signal processing method, and realize the multi-parameter high-precision estimation of the sea surface target.

The invention relates to the technical field of computer data processing, provides a business-driven data asset unified management method and system, and solves the technical problems of lagging data asset discovery and low management efficiency. The method comprises the following steps: acquiring a database access log and business metadata; analyzing the database access log, and constructing a sparse tensor according to the screened triple; carrying out dimension reduction decomposition operation on the sparse tensor by utilizing an alternating least square method to obtain a user potential vector, a data potential vector and a time potential vector; taking a data potential vector corresponding to the unaccessed data in the vectors as an input vector, and inputting the input vector into the trained neural collaborative filtering model to obtain a prediction preference value of the unaccessed data; according to the method, the unaccessed data are arranged in a descending order according to the predicted preference values, and potential target data are identified based on the predicted preference values, so that unified management of the data assets is realized, and intelligent active discovery and efficient unified management of the data assets are realized.

The embodiment of the application discloses a structural color design method and device based on a tensor completion algorithm, which comprises the following steps: obtaining spectral data and geometric data of a dielectric array constituting a structural color, and combining the spectral data and the geometric data into multi-dimensional tensor data, wherein the tensor data comprises a to-be-completed tensor and a complete tensor containing all known entries; applying an alternating least squares method to Tucker decomposition of the to-be-completed tensor according to the tensor data, so as to obtain a minimum rank tensor after tensor completion, which is the same as known entries in the to-be-completed tensor; and converting the minimum rank tensor into spectral data and geometric data to obtain corresponding structural color. Through the above method, the embodiment of the application can quickly and accurately design structural color, avoids complex electromagnetic theory, and improves the device design efficiency of a small number of features.

The invention relates to the technical field of resource recommendation, in particular to a learning resource recommendation method and system based on a user portrait, and the method comprises the steps: building a user portrait matrix and a learning resource feature matrix, and constructing a latent semantic matching model of a user and a learning resource through a factorization machine and a collaborative filtering algorithm; learning parameters of the latent semantic matching model through an alternating least square method, and generating user-learning resource latent semantic association features; and taking the user-learning resource latent semantic association features as individual codes, searching a Pareto optimal recommendation solution set of the multi-target learning resource recommendation optimization model by using a non-dominated sorting genetic algorithm, and generating a learning resource recommendation scheme in combination with an optimal recommendation decision model. According to the method, the recommendation strategy is dynamically adjusted by combining technologies such as multi-objective optimization and deep reinforcement learning, the recommendation accuracy is improved, meanwhile, the diversity and personalization of recommended contents can be balanced, and the dynamic adaptability and robustness of a recommendation system are improved.

The invention relates to a smoked mural pigment spectral unmixing method, and belongs to the field of hyperspectral unmixing. The method comprises the following steps: S1, establishing a pure pigment spectrum library and a smoking spectrum library as a data basis, S2, constructing a sparse unmixing model based on end member linear combination of the smoking spectrum library, S3, introducing a spatial self-adaptive mechanism based on spectrum similarity measurement, and dynamically adjusting regularization weight through abundance gradient analysis to optimize an objective function. And S4, implementing layered iterative optimization by adopting an alternating least square method in combination with spectral smoothing constraint, and finally realizing accurate unmixing of smoke pigment components. According to the method, smoke layer interference and a mixed pixel nonlinear effect are effectively overcome through dynamic weight adjustment, and spectrum similarity analysis and abundance space distribution characteristics are fused. The method is mainly applied to quantitative analysis of original pigment components under a smoked covering layer in ancient murals, and provides accurate material composition data support for cultural relic restoration.

The present invention discloses a method for direct positioning of coherent distributed information sources based on parallel factors, comprising the following steps: S1, constructing a coherent distributed information source positioning model using angle and delay information to obtain the received signal of each array in the frequency domain; S2, extracting useful frequency points to obtain a known inverse Fourier transform matrix, and constructing a parallel factor model; S3, obtaining a position information matrix using a trilinear alternating least squares method; S4, constructing a direct positioning cost function related to the position information matrix, performing a three-dimensional search on the direct positioning cost function, and obtaining the grid point position with the smallest Euclidean distance to the position information matrix as the estimated position of the coherent information source. The present invention is applicable to antenna arrays with arbitrary spacing, and has application prospects in multipath environments such as dense urban areas.

This invention relates to a method for simultaneous localization and mapping (SLAM) assisted by a UAV equipped with a reconfigurable smart surface (UAV-RIS), addressing the problems of parameter decoupling difficulties caused by cascaded channels and large amplitude-based localization and mapping errors due to signal strength distortion. The method includes: 1) constructing a nested parallel factor model of the received signal and performing tensor decomposition using a bilinear alternating least squares method to achieve joint channel parameter estimation and signal detection; 2) initializing and removing outliers using an amplitude-independent geometric inference method based on the estimated geometric parameters; and 3) optimizing the model using a weighted least squares method to determine user state and environmental characteristic parameters. This method reduces the impact of amplitude model mismatch and improves parameter estimation accuracy in complex channel environments, making it suitable for autonomous localization and mapping in low-altitude wireless networks.

The application discloses a kind of intelligent reflecting surface auxiliary cascading surface array channel nested tensor decomposition estimation methods, first constructs cascading channel model, initialization each end guiding matrix and channel matrix in turn;Zero intelligent reflecting surface phase shift is first placed, respectively constructs the tensor model of transceiver end parallel factor decomposition, combined with three linear alternating least square method and least square method, completes two-dimensional angle estimation of transceiver end;Again control phase shift, through two linear alternating least square method, Khatri-Rao decomposition, complete intelligent reflecting surface two-way angle estimation, finally rely on Kronecker product and Khatri-Rao product model solves beam gain.The application relies on nested parallel factor decomposition, realizes four angles automatic pairing, adapts single, multi-beam scene, reduces high-dimensional calculation amount, suppresses off-grid energy leakage, without signal autocorrelation matrix and complex angle pairing, adapts super large scale surface array, improves channel estimation applicability, supports sensing integration system design.

The application discloses a recommendation method based on an interpretable generalized logistic transformation matrix decomposition, and comprises the following steps: converting an original score matrix into normally distributed data through a generalized logistic transformation function; constructing a similarity-based index and a ranking-based index; calculating a probability distribution of a similar user's score on a recommended item and an expected score, and combining the similarity index to generate an interpretability index; integrating the interpretability index into a matrix decomposition target function for optimization; solving a user feature matrix and an item feature matrix through an alternating least squares method or a stochastic gradient descent; calculating a predicted score and mapping back to an original score interval through a generalized logistic inverse transformation; and generating a recommendation list; the application has wider applicability and higher performance in practical application.

This invention provides a deep denoising-based multi-RIS indoor positioning method. For indoor scenarios with multipath interference and noise, this invention first constructs a fourth-order tensor model from the channel state information reflected from multiple indoor RIS points and scattering points to the receiver. Second, it uses antenna rearrangement technology to rearrange the tensor model to satisfy the decomposition uniqueness condition. Then, it utilizes the denoising capabilities of a deep learning architecture to suppress noise in the received signal. Further, it employs an optimized quadlinear alternating least squares algorithm to estimate the factor matrix and extract channel parameters. Finally, it uses a geometrically based search-free spatial positioning method to estimate the user's location and azimuth angle, and map the indoor environment. Therefore, the deep denoising-based multi-RIS indoor positioning method proposed in this invention has higher accuracy and robustness compared to comparative algorithms, and is more in line with the needs of practical communication scenarios.