1197 results about "Complete data" patented technology

The invention discloses a report chart automatic generation method based on natural language analysis and data query, which comprises the following steps: acquiring a natural language text, and constructing a slot set and an initial semantic fragment; executing consistency verification and ambiguity identification, and constructing a semantic framework; executing field standardization and mode alignment, generating a data query statement and establishing a traceability chain identifier; querying a target database to obtain an original data set, completing data quality self-correction, and generating a cleaned data set; calling an improved Mamba model to construct a constraint judgment matrix and outputting a target chart subset; generating a chart description grammar and an image annotation template, and executing image rendering, feature point recognition and image sidebar construction; and performing layout optimization and double compilation, and outputting a structured report file. According to the method, the chart generation automation level and the report compiling efficiency are improved, and the accuracy, traceability and specialty of the output content are ensured.

The invention discloses a visual algorithm self-training method based on multi-agent collaborative optimization, and the method comprises the following steps: constructing a multi-agent system architecture which comprises a user interaction layer, an intelligent scheduling layer, an A2A protocol communication layer and a professional agent cluster layer; the user interaction layer analyzes a user task intention and generates an execution plan; the scheduling agent calls the professional agent to complete data processing, model construction, training, testing and deployment; a task process is coordinated through a standardized communication mechanism, and task execution is supported by combining an MCP tool set, a knowledge base module and a memory system; and when the task fails, automatically executing rescheduling operation, and finally outputting a self-training result. According to the method, the development efficiency, the self-adaptability and the intelligent level are remarkably improved, and the method is suitable for computer vision tasks such as industrial detection, intelligent security and protection and automatic driving.

The invention relates to a data query analysis method based on a natural language, which comprises the following steps of: analyzing a natural language query request input by a user into a dynamic semantic intention tensor which comprises an operation type, a comparison relationship, a time constraint and a data role semantic dimension, and dynamically combining according to task semantics to form a complete data query and analysis operation expression; mapping the natural language intention to a controllable data operation space of a database, and generating a preliminary data operation chain; performing side effect perception processing on the operation tensor, predicting a potential execution consequence of the operation, generating a side effect tensor for simulating a side effect of the database operation, and if any index in the side effect tensor exceeds a preset threshold value, performing local correction on the operation tensor; according to the method, a complex natural language query task is disassembled into a plurality of minimum semantic units by adopting a step-by-step semantic resolution mechanism, each unit is mapped into a specific tensor operation, and a dependency relationship between operation units is dynamically reasoned to generate an operation execution chain.

The invention provides a vibration signal space-time reconstruction method based on a multi-modal condition diffusion model, and relates to the technical field of vibration signal reconstruction, and the method comprises the steps: firstly collecting structure vibration response through multiple sensors, constructing a multi-dimensional vibration signal matrix, and automatically recognizing a space continuous missing region and a time random missing region; performing coarse reconstruction on the missing region by adopting self-adaptive multi-scale interpolation so as to recover the basic trend and frequency band characteristics of the signal; a pseudo-missing mask is further applied to complete data, a training sample is constructed through a self-supervision strategy, and the model is guided to learn spatio-temporal correlation features and missing modes; in a training stage, a diffusion model is used as a generation framework, Gaussian noise disturbance is applied to a missing region, four types of condition embedding of time, space, trend and frequency domain are introduced in a denoising inversion process, signal periodicity, multi-sensor space coupling, low-frequency change and a physical frequency spectrum structure are respectively described, and the noise is reduced; and high-fidelity signal reconstruction under multi-modal information joint constraint is realized.

The invention relates to an AI-based subject education auxiliary method and device and a storage medium, which are applied to the technical field of intelligent teaching, and comprise the steps of: introducing a teaching plan script as a macroscopic framework of teaching, ensuring that an AI teaching process is always carried out around teaching design and core targets of teachers, and improving the teaching efficiency. The problem of teaching content deviation possibly occurring in a pure response type system is avoided, meanwhile, microcosmic dynamic adjustment can be carried out in the framework according to real-time feedback of students, and organic combination of teaching structure and personalized self-adaption is achieved. By constructing and dynamically updating the individual knowledge graph for each student, the system can accurately diagnose the weak knowledge points of the students and provide personalized teaching guidance and after-class homework according to the weak knowledge points, thereby realizing accurate and efficient'apportionality teaching '. According to the invention, the whole process of'teaching-learning-evaluation-diagnosis-mending 'is integrated, a complete data-driven teaching closed loop is formed, and the overall teaching quality is systematically improved.

The invention relates to the technical field of informatization management systems, and particularly discloses an AI-aid decision-making product full-life-cycle informatization management system which comprises a full-link data sensing module, a digital main line construction module, an AI decision-making center module, a service execution interface module and a man-machine collaborative interaction module. The method comprises the following steps: collecting multi-source heterogeneous data of each stage of a full life cycle of a product through a full-link data sensing module to form a full-amount data sequence with a space-time stamp; and in combination with a data fusion engine, an association graph construction unit and a twinborn model driving unit of the digital main line construction module, data cleaning, alignment, semantic fusion and cross-stage association are realized, a dynamically updated product digital twinborn model is constructed, real-time mapping of a physical entity and a virtual model is achieved, and the real-time mapping of the physical entity and the virtual model is realized. Unified and complete data support is provided for full-link decision making, and the problems of data fragmentation and prominent collaborative barriers of a traditional system are thoroughly solved.

The invention provides a data weaving platform-oriented self-service data preparation method, which comprises the following steps of: accessing original data and associated structured metadata of a target data source into a data weaving platform to generate standardized accessed original data and associated structured metadata; based on a semantic model of the data weaving platform, performing classified semantic annotation on the associated structured metadata, and positioning a transfer node of the associated structured metadata to generate a data blood relationship record; performing bidirectional quality verification on the data consanguinity record according to semantics and path continuity, and matching with a federated governance rule of a data weaving platform to generate a metadata governance list; and generating a unified metadata directory based on the metadata governance list, so that a user of the data knitting platform can obtain key segments containing complete data consanguinity records. According to the method, the problem of insufficient accuracy and efficiency in self-service data preparation can be effectively relieved, and the efficient preparation requirement of a data weaving platform for multi-source data is met.

The invention relates to the technical field of data processing, and provides an unmanned aerial vehicle-mounted LiDAR geological modeling and intelligent blasting parameter optimization system, which is characterized in that a laser point cloud and a multispectral image are deeply correlated through a data acquisition module based on a tight coupling algorithm, the sampling quality of a point cloud data set is evaluated, and a supplementary flight instruction is judged and generated; a complete data source is provided for subsequent geological modeling; the geological modeling module divides the point cloud data set through an adaptive threshold algorithm to identify rock mass structural surfaces, analyzes a spatial topological relation of the rock mass structural surfaces based on a graph neural network, performs clustering to form a control structural surface group, and associates the control structural surface group with spectral features through a convolutional neural network to cooperatively discriminate rock mass properties; geological indexes of the three-dimensional geological model are extracted through a parameter optimization module, blasting parameters are generated after genetic algorithm processing, the blasting effect is judged through laser point cloud obtained again after blasting and change characteristics are extracted, the parameters of the genetic algorithm are reversely adjusted, and the three-dimensional geological model is updated.

The invention discloses a small sample modeling stability evaluation method and system based on Bootstrap resampling, and particularly relates to the technical field of computers and data intellectualization, the method comprises the following steps: completing data preprocessing and stable stage identification under a unified time base, and forming a segment set; an average block length is used as a decision quantity, an SBB is optimized to construct a sample space, and an optimal block length is determined in combination with variance consistency and nominal coverage rate consistency criteria; carrying out re-sampling training around short / medium / long scales, and collecting layered indexes such as prediction, parameters and features; stability calculation and empirical coverage rate calibration are completed based on intra-scale statistics and inter-scale weighted mixing, and a pseudo-stationary diagnosis score is output; and finally, engineering judgment and backspacing optimization are carried out according to the coverage rate, the correlation maintenance and the risk threshold. The system records random seeds, block metadata and model version generation evidence pointers, has the characteristics of traceability and reverifiability, and is suitable for scenes of production lines, network traffic, finance and the like.

The embodiment of the invention provides a cross-network data exchange method, electronic equipment, a storage medium and a program product, and the method comprises the steps: receiving transmission data, determining the identification information of the transmission data according to the service identification, timestamp and segment sequence number of the transmission data, and determining the verification value according to the performance requirement, the security requirement and the data integrity; the hash algorithm is obtained by performing hash operation on the segmented data; according to the identification information, judging whether the transmission data is duplicated data or not; judging whether the transmission data is complete data or not according to the verification value; whether the transmission data is lost data or not is judged according to the segment serial number, if yes, a retransmission instruction is sent to the sending end equipment, the data segments which are repeatedly transmitted can be accurately recognized through the unique identification information, redundant storage and processing are avoided, the data repetition problem is solved from the source, then the integrity of the data is verified according to the verification value, and the data transmission efficiency is improved. And the lost data end is judged according to the segment sequence number, so that the problem of data loss is solved.

The invention discloses a DCS operation and maintenance method based on fusion dynamic weight distribution and fault chain deduction, and relates to the technical field of operation and maintenance of a distributed control system, and the method comprises the steps: obtaining a plurality of groups of source data of a monitoring region; corresponding monitoring periods are determined according to the multiple groups of source data, and differential monitoring period information is obtained after combination; according to the technical key points, a multi-source data fusion module is utilized to associate data of a DCS system, an associated production system and a cross-plant cooperative system, and fragmented data such as equipment operation data, production load fluctuation and cross-plant interaction information are woven into a complete data network through adjustment of space-time alignment and multi-dimensional verification; the global sensing capability not only solves the one-sidedness of traditional single data judgment, for example, environmental interference is easily misjudged by only depending on equipment temperature data, but also can capture cross-system implicit associated faults; and secondly, when the multi-source data are mutually verified, an evidence chain is formed through logic consistency verification, so that the misjudgment rate of suspected faults is greatly reduced.

The invention discloses a self-adaptive multi-level digital watermarking method based on coding process optimization. The method comprises the following steps: firstly, performing deep preprocessing on an input video stream through a pre-trained multi-modal deep learning model, extracting space complexity, time dynamics and content significance features, and generating a uniform feature vector; and constructing a dynamic decision model based on the feature vectors, adaptively determining the watermark intensity, the embedding position and the type, and realizing accurate matching of watermark parameters and video content characteristics. A multi-level watermark hierarchical embedding mechanism is adopted, a robust invisible watermark, a fragile invisible watermark and a dynamic visible watermark are embedded into a video, and the security is enhanced by combining chaotic encryption or Hash chain encryption. During copyright verification, watermark information of each layer is recovered through an adaptive extraction algorithm, and data verification and infringement traceability are completed in combination with a block chain evidence storage system. According to the method, a full-process copyright protection system of embedding, coding, extraction and verification is constructed.

The invention provides a power transmission line short-circuit fault prediction method and system, and relates to the technical field of data processing, and the method comprises the steps: carrying out the smooth iteration through a gradient optimization strategy based on the initial space risk correction factors of adjacent sub-region units, so as to obtain the space risk correction factors; based on the short-circuit probability predicted value and the spatial risk correction factor, calculating a linkage risk value of the target segmented region in combination with the power grid topological structure data; generating a risk level label and a disposal strategy instruction of the target segmented region based on the linkage risk value; when the output risk level label is a high risk, triggering integrity verification of the multi-dimensional monitoring data; and when the monitoring data is found to be missing through verification, dynamically complementing the multi-dimensional monitoring data of the target segmented region by using the monitoring data and historical data of the adjacent segmented regions, and re-collecting the complemented data. According to the invention, the accuracy and reliability of fault prediction are improved.

The invention discloses a multi-sensor fusion sensing precision self-adaptive system, and relates to the technical field of radio positioning and multi-sensor fusion sensing, the system integrates multi-source sensing units such as a laser radar and a GPS, establishes a unified reference by means of a space-time synchronization module to complete data alignment, and optimizes data quality through preprocessing means such as filtering and denoising; a dynamic weight fusion module allocates weights according to the real-time quality scores, and a unified sensing result is output by fusing the positioning and speed measuring results; through multi-dimensional index evaluation precision grade, self-adaptive adjustment of sensor parameters and fusion strategies, and balance of precision and energy consumption, a result is output in a standardized format, an operation state is fed back, and an external system is linked. According to the invention, through multi-sensing fusion and dynamic adaptive adjustment, the sensing precision and stability are significantly improved; the method can intelligently adapt to multiple scenes, resists interference, has fault-tolerant capability, adapts to new requirements through self-learning evolution, and provides reliable perception support for automatic driving, unmanned aerial vehicle surveying and mapping and the like.

The invention relates to an industrial Internet of Things secure communication method and system based on OpenHarmony, and the method comprises the following steps: collecting node features of to-be-communicated equipment, carrying out the routing selection through combining network performance parameters, and generating a main and standby transmission path combination. And performing fragmentation encryption on the industrial production data sent by the source equipment to form encrypted fragmentation data. And sending the encrypted fragmented data through the main transmission path, and synchronously executing integrity verification to obtain a verification result. Whether transmission abnormity occurs in the main path or not is judged according to the integrity verification result, if yes, switching to the standby transmission path is triggered, encrypted fragmented data corresponding to the abnormity is retransmitted, it is ensured that the data are complete and reliable, and finally the data are recombined into complete industrial production data at a receiving end. The technical problems that a rapid detection and response mechanism for abnormal behaviors is lacked in the data transmission stage, and it is difficult to switch a standby path in time and complete data retransmission when transmission abnormity occurs are solved.

The invention belongs to the technical field of intelligent soil monitoring, and particularly relates to a multi-sensor networking soil parameter high-precision detection device and method.The device adopts sensing, transmission and data processing, a four-layer architecture is applied, a sensing layer collects soil texture, temperature and salinity parameters, an environment interference factor matrix is constructed, and a data processing layer is constructed; outputting non-interference data through a layered interference calibration model; the transmission layer completes data transmission through wired and wireless dual modes; the data processing layer extracts spatial-temporal characteristics after preprocessing, and obtains a soil parameter fusion value through dynamic weight fusion; and the application layer matches the fusion value with a preset template to realize scene generation and visual rendering. According to the invention, the problems that the precision of the existing multi-sensor networking system is easily influenced by the outside and the intelligent level is insufficient can be solved.

The invention discloses an association mapping method and system based on an API and a database sensitive field. Comprising the following steps: generating a tracking identifier for a current HTTP request through a global interceptor, and storing the tracking identifier and request context information into a thread context; intercepting an SQL (Structured Query Language) statement sent to a database by the application program, and analyzing the SQL statement to extract a data table name and a field name set accessed by a current HTTP (Hyper Text Transport Protocol) request; identifying sensitive fields in all access fields in the field name set; generating an associated log record based on the accessed sensitive field set, the SQL statement, the tracking identifier and the request context information; and analyzing the API response data to obtain a response field set, and establishing an association mapping relationship between the accessed sensitive field set and the response field set, so as to create complete data flow link information based on the association mapping relationship and the association log record. The data security of the sensitive data can be improved.

The invention discloses a stacking-based steel hot-rolled product mechanical property prediction method, and relates to the technical field of steel product quality prediction. The method comprises the following steps: constructing a steel hot rolling actual production data set and carrying out missing value interpolation on the data set; performing normalization processing on the complete data set, and dividing a part of data from the normalized data set as a training set; establishing a stacking ensemble learning model based on a regression chain; taking the yield strength, the tensile strength and the elongation in the training set as training labels, taking other data types as training features, and training the learning model by using the training set to obtain a steel hot-rolled product mechanical property prediction model; and the steel hot-rolled product mechanical property prediction model is practically applied to perform real-time prediction on the mechanical property of the steel hot-rolled product. According to the method, the coupling relation among the multiple target variables can be effectively processed, and the accuracy and stability of mechanical property prediction of the steel hot-rolled product can be effectively improved.

The invention relates to the technical field of intelligent education, and discloses an innovation ability dynamic evaluation system and method based on multi-dimensional data fusion analysis, and the system comprises a process data collection module, a literacy feature extraction module, a dynamic evaluation engine and a teaching intervention engine. The method corresponds to the system. According to the method, multi-dimensional, dynamic and accurate evaluation of the innovation ability of the students is realized by constructing a complete data processing and evaluation closed loop, and specifically, performance characteristics of the students in innovation practice can be comprehensively captured by fusing and analyzing online and offline multi-modal process data; by means of a multi-mode cross-domain time sequence fusion model, dynamic tracking of the innovation ability development trajectory is achieved; finally, a personalized teaching intervention strategy is generated based on an evaluation result, a complete teaching closed loop of evaluation-diagnosis-intervention is formed, and the accuracy and teaching efficiency of innovative talent training are improved.

The invention belongs to the technical field of data security and block chains, and discloses a physical infrastructure node continuous data chaining and traceability method and system, and the method comprises the steps: generating a unique asymmetric key pair for each node; continuously collecting physical sensing data and generating a unique data identifier; performing digital signature on the current physical sensing data to form a continuous signature chain; storing the original physical perception data, the corresponding digital signature and the continuous signature chain in an off-chain service platform database; uploading the data identifier, the digital signature and the hash value of the original physical sensing data to a block chain network based on a dynamic anchoring strategy; and comparing the calculated hash value with the hash value of the corresponding original physical sensing data in the block chain network, and backtracking the continuous signature chain. According to the invention, a safe, efficient and traceable complete data guarantee scheme can be provided for a decentralized physical infrastructure network.

The invention discloses a dynamic optimization method and system for a boron diffusion process of a photovoltaic cell and electronic equipment. Comprising the following steps: collecting process parameters and sheet resistance data, and associating the process parameters and the sheet resistance data to form a process parameter set; optimizing a process parameter set, removing noise data and incomplete data, and extracting an available feature data set; dividing the feature data set into a training set and a verification set, and training to obtain a nonlinear regression model for predicting resistance data under different feature data; carrying out validity verification on the nonlinear regression model, and constructing an optimization function to reduce a difference value between a predicted value and an actual value; and deploying a nonlinear regression model in the diffusion process, adjusting the process parameters of the diffusion process in real time according to the predicted value, and optimizing the obtained sheet resistance data. The problem that the boron diffusion process is difficult to accurately adjust by a traditional process control method can be solved.

The invention belongs to the technical field of chip design, and discloses a three-dimensional stacked heterogeneous in-memory computing system and a data interaction processing method thereof.The three-dimensional stacked heterogeneous in-memory computing system comprises a storage chip layer and an AI processing chip layer located below the storage chip layer, the storage chip layer is electrically connected with the AI processing chip layer, and the AI processing chip layer is electrically connected with the storage chip layer. The AI processing chip layer is of a heterogeneous storage and calculation integrated structure integrating an RRAM storage and calculation array and an SRAM storage and calculation array, and the RRAM storage and calculation array is used for storing system configuration data; and the SRAM memory array is used for writing read-write data of the memory chip layer and completing data processing in the array. According to the three-dimensional stacking heterogeneous storage and calculation integrated device, through heterogeneous cooperation of the RRAM and the SRAM storage and calculation integrated array, key problems existing in the prior art are fully balanced and considered, finally, the optimal design of a system architecture level is achieved, and core obstacles are cleared away for large-scale application of the three-dimensional stacking technology in the field of AI chips.

An end-cloud cooperative data mining method, comprising: determining a target text and a task configuration file according to a business requirement by a cloud end; encoding the target text by a text encoder to obtain a text feature; placing the text feature in the task configuration file and issuing it to a vehicle end together; encoding image data by a first picture encoder to obtain an image feature by the vehicle end; calculating a value of a similarity of the text feature and the image feature; determining a target picture according to the value of the similarity and the task configuration file; and uploading the target picture to the cloud end; wherein the first picture encoder is obtained by compressing and optimizing a second picture encoder; and the text encoder and the second picture encoder are two modules of a picture-text multimodal large model. The application is applied to an automatic driving shadow mode, can complete data mining of any interesting target text by using one large model, and does not need to design and develop detection rules for each type of interesting target. The picture encoder of the vehicle end can be continuously updated and optimized, and the model iteration efficiency is improved.

The invention discloses a lock-free single-memory data sharing method and device for an embedded real-time system. The method comprises the following steps: statically distributing a unique memory space for each message type; when a publisher task needs to update shared data, new data is written into a memory space of a corresponding message type, it is ensured that data writing is completed and is visible to other tasks, the atomic version number of the memory space is progressively increased, and data publishing is completed; and when the subscriber task needs to read the shared data, firstly reading the atomic version number of the memory space, then copying the content in the memory space to the local buffer area, reading the atomic version number again, and if the two version numbers are consistent, confirming that the read data is complete, otherwise, executing the reading process again. According to the method, the use of a lock can be avoided, dynamic memory allocation is avoided, copying of multiple memories is avoided, and efficient, strong-determinacy, extremely-low-memory-overhead, safe and reliable inter-task data communication is realized.

The invention discloses an advertisement putting ROI dynamic optimization method and system based on real-time data driving. The method comprises the steps of collecting advertising data such as advertisement display quantity, click quantity, conversion quantity and consumption cost in a minute-level period through a multi-platform data interface; based on historical and real-time data, utilizing a machine learning model to predict the rate of return on investment (ROI) of each advertisement platform in a future time period; constructing an optimization problem with the overall ROI maximization as a target under the constraint of the total budget, and solving an optimal budget allocation strategy of each platform in each time period through an optimization algorithm; and synchronizing the budget allocation strategy to an advertisement platform for execution through an automatic control module, and recording ROI changes before and after optimization by a monitoring module to realize iterative updating of the model. Compared with the prior art, data acquisition, prediction and optimization can be completed in a minute-level period, dynamic allocation and rolling optimization of advertisement budget are realized, the overall ROI is effectively improved, putting waste is reduced, and the method is suitable for a multi-platform advertisement scene.

The invention discloses a PLC-based optical cable sheath bump on-line detection alarm method and system, and the method comprises the steps: presetting a permissible outer diameter error, enabling an optical cable sheath to enter a bump test device center through a cable stabilizing device after the optical cable sheath is extruded and cooled, resetting the optical cable through a meter length reset button when the optical cable is normal and meets the requirements, and providing a trigger signal to obtain a standard size, effective optical cable detection is started, the defect detector feeds back data of the detected cable diameter to the field PLC in real time, the data is compared with a permitted error range limit value for calculation, a bulge alarm pulse is sent out when the data exceed an upper limit, a narrow-neck alarm pulse signal is sent out when the data is smaller than a lower limit, then the data are transmitted to the main control PLC through the field PLC, the meter counting length is locked, and the defect position is determined; and complete data of the whole optical cable is reserved. Through the mode, the instantaneous defects on the surface of the optical cable can be captured in real time, missing detection caused by response lag or overlarge sampling interval is avoided, accurate synchronization of defect positions and meter counting information is achieved, and accurate and comprehensive quality monitoring under high-speed production is guaranteed.

The invention belongs to the technical field of artificial intelligence and data analysis, and discloses a data analysis method and system based on multi-layer intention recognition and multiple agents, which remarkably improves the accuracy and robustness of natural language understanding through an innovative multi-layer intention recognition technology and improves the accuracy and robustness of natural language understanding. A common user can perform complex data analysis without mastering professional skills; through a multi-agent cooperative working mechanism, specialized division of labor of different agents is realized, the problem of capability dispersion of a single agent is avoided, and the analysis efficiency and the result quality are remarkably improved; through a real-time streaming processing technology and intelligent visual matching, complete transparency of a code execution process and intelligent recommendation of chart types are realized, and the user experience and the professionality of an analysis result are greatly improved; through an end-to-end integration solution, full-link intelligent processing from data input to visual large screen generation is realized, and a complete data analysis platform is provided for enterprise decision support.

The invention discloses a 3D printing aluminum alloy mechanical property prediction method based on machine learning, and belongs to the field of metal 3D printing, and the method comprises the steps that input feature data of 3D printing aluminum alloy are collected, and the input feature data comprise mechanical property data, printing parameter data, special processing data and aluminum alloy wire physical attribute data; preprocessing the input feature data, including performing standardization processing on numeric features and performing numerical coding on category features to obtain a data set; filling missing values in the data set by using a mean value filling method to obtain a complete data set; and training a machine learning model by using the complete data set, and predicting the mechanical properties of the aluminum alloy. According to the method, the efficiency and precision of the aluminum alloy 3D printing process are improved, and prediction of the mechanical property of the 3D printing aluminum alloy is simpler, more convenient and more efficient.

The invention relates to the technical field of data interpolation, in particular to a wind speed time series data interpolation method and system based on a deep convolutional generative adversarial network, a medium and equipment, and the interpolation method comprises the steps: constructing a data matrix and a mask matrix; performing data preprocessing on the data matrix and the mask matrix to generate a dual-channel two-dimensional feature map containing a data feature map and a mask feature map; constructing a generative adversarial network; adversarial training is carried out on the generative adversarial network to obtain a data interpolation model with data interpolation capability; inputting the two-channel two-dimensional feature map into a data interpolation model to obtain a complete reconstruction data matrix containing an interpolation value; and fusing a part corresponding to a missing value in the complete reconstruction data matrix with an observation value part in the data matrix according to the mask matrix to obtain a wind speed time sequence data matrix which is completely interpolated. According to the technical scheme, training of a complete data set is not needed, the interpolation precision and robustness are effectively improved, and the stability of model training is enhanced.

The invention discloses a BIM and block chain-based construction whole process quality tracing method and system, and relates to the technical field of building construction quality management. In a material entering stage, material information is collected through the Internet of Things and is associated with a BIM component identifier, and an initial block is generated by using an intelligent contract; in the process execution stage, BIM 4D / 5D simulation data is associated with a construction log, and a Hash chain algorithm is adopted to generate a process block containing IPFS Hash; in the acceptance inspection stage, the consistency of detection results is verified through zero-knowledge proof, and a new block is generated; checking the block data through a consensus mechanism to obtain a complete data set; constructing a graph database index based on the BIM component tree, and generating a chain path graph; responding to a query request, traversing path diagram nodes, comparing hash values and outputting a tracing result; trusted communication, tamper-proof evidence storage and intelligent tracing of data in the whole construction process are achieved, and the accuracy and reliability of project quality management are remarkably improved.