122 results about "Composite index" patented technology

A block chain double-chain cold chain traceability management system for meat quality fluctuation belongs to the technical field of traceability management systems and comprises a data acquisition and preprocessing module, a composite index module, a security verification module, a federated learning and AI resource management module, a fragmentation and verification architecture module and an automatic error correction module. According to the method, data chain storage environment data hash and transaction chain record operation logs are innovatively separated through a block chain double-chain architecture, hash fingerprints are synchronized in combination with an anchoring technology, cross-chain consistency is ensured, long-term non-tampering of data is realized through an anti-quantum hash algorithm, resource allocation is optimized through hierarchical storage design, and the method is suitable for large-scale popularization and application. The composite index technology is fused with hypergraph dynamic index to trace production batches, vehicles, warehouses and space-time quadtree dynamic subdivision areas, complex query response time is remarkably compressed, path deviation real-time alarm is achieved, the edge node cache hit rate is increased, and full-link data safety and query efficiency are remarkably improved.

The invention discloses a charging station operation maintenance method based on a multi-dimensional data system, and relates to the field of intelligent optimization, and the method comprises the steps: collecting the operation, environment, user and power grid data of a charging pile, preprocessing the data into JSON, carrying out the real-time analysis and classification through Kafka-Flume, storing the data into a distributed database, building a composite index, and carrying out the retrieval through Presto; after cleaning, combining GraphQL and a graph query language to construct a space-time atlas, and extracting a multi-dimensional feature vector; a digital twinborn model is generated, multi-source data are fused through virtual-real mapping, and residual correction and reinforcement learning optimization are combined; fusing multi-modal data by using a hypergraph neural network, and optimizing topology in combination with an entropy regularization multi-target strategy and meta-learning; power is dynamically distributed, LSTM-GAN predicts and positions faults, and PID regulates and controls output; and the block chain contract automatically triggers equipment freezing and power limiting, and on-chain data feedback optimizes scheduling and load balancing. According to the invention, through multi-dimensional data fusion and a dynamic optimization mechanism, the operation and maintenance accuracy and response efficiency of the charging station are significantly improved.

Devices and techniques are generally described for key-value store having improved support for indexing and querying. The proposed system can expand query functionality by adding compound indexing. In some implementations, compound index may allow multiple simple key-value store queries (e.g., for multiple event types) to be replaced with a single query. In some implementations, compound index may allow for query filtering otherwise unavailable for the key-value store. The system may return results from the compound query in timestamp order and with appropriate pagination. Indexing may be updated dynamically; for example, manually via a self-service portal and / or automatically in response to frequent query combinations. The expanded query functionality can improve the efficiency and usability of, for example, an event timeline system.

The invention provides a large model lightweight reasoning deployment method under limited hardware resources, and the method comprises the steps: quantifying the weight importance of a large model through a composite index of gradient sensitivity and activation frequency, and carrying out pruning operation in combination with an improved index weighted moving average strategy, thereby obtaining a structured sparse model; the sparse model is divided into sub-networks by adopting double rules, a routing decision network is trained, and an adaptive feature shunting architecture model is constructed; a multi-precision weight set is generated through a nested quantization technology, quantization bit width is dynamically adjusted, and edge equipment hardware parameters are adapted to complete reasoning environment initialization; after a reasoning request is received, an optimal sub-network is selected based on the trained routing decision network, corresponding weights are loaded in parallel, and a reasoning result is fused and output; and converting a reasoning result format, and dynamically optimizing a scheduling strategy based on a system real-time monitoring index. The method is compatible with a mainstream large model and a hardware platform, and an efficient and universal deployment scheme is provided for end-side AI engineering landing.

The invention belongs to the field of pollution prevention and control data processing, and particularly relates to a laboratory instrument data automatic acquisition and quality tracing system and a laboratory instrument data automatic acquisition and quality tracing method. A distributed search traceability mapping space is constructed through the storage mapping module to realize space-time-semantic composite indexing and classification detection of data, and a causal reasoning model of the quality judgment module is used for performing anomaly judgment; a reverse Hash traceability mechanism is innovatively designed, an index-traceability node graph and a segmented Hash heterogeneous node anchoring strategy are combined, Hash head, body and tail fragments are stored in three types of nodes of acquisition, storage and detection, and tamper-proof traceability of abnormal data and dynamic optimization of acquisition parameters are realized through cross-node aggregation verification; according to the invention, the problems of low data credibility and poor abnormal traceability efficiency in ecological environment monitoring are solved, and full-chain closed-loop management of data acquisition-analysis-traceability-acquisition configuration adjustment is supported.

Embodiments of the present disclosure relate to multimodal AI-based search for digital assets via an indexing and / or search pipeline. With respect to the indexing pipeline, some embodiments obtain first data and second data associated with a first digital asset. Such data represents different data types or modalities of the same digital asset. After obtaining the first and second data, some embodiments then generate a composite index. After the composite index is built such index can then be used to execute a query via the search pipeline. To execute the query some embodiments compute a relevance score for each digital asset, of multiple digital assets, based at least in part on a measure in which each digital asset satisfies one or more parameters or conditions for two or more data types of the query. Various embodiments then rank each digital asset and present one or more associated indicators.

The invention discloses a dam safety monitoring data effective information extraction method and system based on adaptive time sequence decomposition. The method comprises the following steps: firstly, obtaining a dam single-measuring-point monitoring time sequence; adopting a multi-population Jaya algorithm to adaptively optimize control parameters of variational mode decomposition (VMD); performing non-recursive decomposition on a data sequence by using the optimized VMD, and screening high-frequency and medium-and-low-frequency sub-modals through a correlation coefficient-energy entropy composite index; superposing the high-frequency sub-modes to form a high-frequency sequence, constructing a composite threshold in combination with kernel density estimation and a box graph method, and eliminating local singular values in the high-frequency sequence to generate a residual sequence; and finally, superposing and reconstructing the low and medium frequency sub-modes and the residual high-frequency sequence to realize effective information extraction of the monitoring data. According to the method, the feature extraction precision of dam monitoring data is remarkably improved through parameter adaptive optimization and composite criteria.

The invention discloses an integrated management system for safety responsibility insurance information, and particularly relates to the field of risk prevention and control, which comprises a multi-source data acquisition layer, a composite index calculation engine, a progressive analysis model library, an intelligent decision center and a management cockpit. According to the method, insurance services, enterprise production and geographic risk data are integrated through a multi-source heterogeneous data fusion architecture, information islands are eliminated by adopting a streaming cleaning verification mechanism, a panoramic dynamic risk feature library is constructed, the integrity and timeliness of assessment elements are improved, a composite index calculation engine innovatively fuses a Shannon entropy theory and a nonlinear coupling algorithm, and the risk assessment efficiency is improved. Risk density adaptive measurement and calculation are realized through dynamic industry coefficients and seasonal factors, a risk evolution law and compensation association relationship are accurately described, prediction perspectiveness and strategy scientificity are enhanced, and an intelligent decision center is linked with a block chain evidence storage system based on a progressive analysis model, automatically generates an underwriting strategy optimization instruction and issues the instruction in real time.

The invention, which relates to the technical field of power grid stability testing, discloses a stability boundary evaluation method for a network-following type and network-constructing type hybrid wind power plant, comprising the following steps: S1, collecting system data of the network-following type and network-constructing type hybrid wind power plant in real time, and calculating a composite index by using the collected data; s2, setting a critical threshold value, performing preliminary evaluation on the overall stability of the system by using the critical threshold value and the composite index, and if the preliminary evaluation result is stable, entering the step S3; s3, outputting fast, medium and slow scale index characteristics in real time by using a multi-time scale monitoring module, and calculating multi-scale indexes by using the fast, medium and slow scale index characteristics and a dynamic weight distribution mechanism; and S4, performing secondary judgment on the stability of the system by using a multi-scale index. According to the method, a collaborative decision-making mechanism based on a composite stability index and multi-time scale monitoring is adopted, namely, a double-layer criterion system is adopted, the dimension limitation of a single criterion is broken through, and the identification precision of the instability critical point of the hybrid wind power plant is remarkably improved.

The invention belongs to the technical field of data processing, and discloses a book personalized recommendation method based on big data analysis. The recommendation method comprises the following specific steps: S1: data integration and cleaning; S2: data storage and index optimization; S3: personalized recommendation algorithm design; S4: keyword interaction mechanism; according to the invention, through deep cooperation of data storage optimization and recommendation algorithm design, double breakthrough of performance and precision is realized; a B + tree joint index of MySQL enables a collaborative filtering algorithm to obtain a user borrowing sequence at a millisecond level and support time decay weighted calculation, and a MongoDB composite index compresses response time of community theme extension recommendation, so that recommendation generation time consumption is reduced through cooperation of the B + tree joint index and the MongoDB composite index, and a concurrence scene of thousands of people can be easily coped with.

The invention provides a method adaptive to fast calculation of big data indexes. The method comprises the following steps: synchronizing data needing to be treated into a hive cluster; converting the configuration of the page into an SQL statement through an SQL converter; the atomic indexes, the derived indexes, the composite indexes and the user-defined indexes are converted into SQL statements through an SQL converter; and calculating the index data by using a manner of integrating trino with hive. According to the scheme, the method capable of being adaptive to fast calculation of the big data indexes is provided, the problem that performance is insufficient when an existing index calculation method executes complex index calculation is solved, index calculation efficiency is improved, and the calculation efficiency is improved through step description in the embodiment. Rapid calculation can be achieved in index calculation, and friendly interaction experience is improved. The calculation method completely depends on memory operation, the performance is effectively improved, the problem of large disk I / O consumption caused by shuffle of a hive bottom layer is solved, and server resource consumption is reduced.

The invention discloses a port disaster risk grading method, which relates to the technical field of risk grading, and further considers comprehensive correlation coefficients among all consequences in each disaster type in a data-driven manner on the basis of the prior art, so as to ensure that correlation factors among different consequences can be comprehensively considered, and improve the risk grading efficiency. Meanwhile, a first composite index and a second composite index of each disaster type are analyzed and calculated, and a third composite index is obtained on the basis of combining the first composite index and the second composite index so as to ensure that complexity factors of consequences of each disaster type are effectively considered, and finally the obtained result is incorporated into an existing calculation formula of an expected loss value, so that the calculation accuracy of the expected loss value is improved. According to the method and the device, the probability of occurrence of risk level misjudgment can be effectively reduced to the greatest extent even if the risk level of disaster types with the same coordinates is judged subsequently, so that the expected loss value which is more accurate, more comprehensive and more scientific is ensured to be obtained, and the probability of occurrence of risk level misjudgment can be effectively reduced to the greatest extent.

The embodiment of the invention relates to a method for determining the performance of a pump unit, computing equipment and a storage medium. The method comprises the following steps: constructing an index network for pump performance evaluation, wherein the index network comprises a plurality of performance indexes related to the pump and a relationship among the performance indexes; on the basis of the constructed index network, atomic indexes of the pump unit and all single pumps in the pump unit are collected in real time, and values of derived indexes and composite indexes are predicted on the basis of the collected atomic indexes; feature extraction is carried out on each performance index, so that features of multiple performance indexes in deviation value features, deviation time sequence features, performance features, energy consumption features and fault features of the pump unit and single pumps in the pump unit are obtained; and evaluating the performance of the pump unit and each single pump in the pump unit based on the obtained characteristics of the plurality of performance indexes. Therefore, deep evaluation can be carried out on the pump unit and each single pump in the unit, and traceability and root cause analysis can be directly carried out on equipment performance degradation.

The invention discloses a composite index-driven urban water body health measurement method, which belongs to the field of environmental sciences, and constructs a new index system comprising 12 composite indexes such as algae apparent turbidity, water body algae primary productivity, oxygen dynamic equilibrium index, multi-element spectrum blotting and the like; aiming at the complexity of the urban water body, the invention provides the urban water body health measurement method driven by the composite indexes by taking the composite indexes and the key water quality indexes as elements, taking the water body nutrition level, the water body cleanliness degree and the ecosystem elasticity as key dimensions and taking self-adaption and quick response as cores. According to the method, the limitations of water quality and biological index separation, evaluation and early warning separation, lack of pertinence of an index system, incapability of feeding back internal optimization, neglect of an advanced monitoring technology and the like of a traditional urban water environment evaluation method are broken through, and a theoretical foundation is laid for water ecology monitoring and evaluation system research; the method is applied to urban water to realize rapid grading quantitative evaluation of the water ecological health state.

Systems and methods of determining composite indices such as, e.g., health, safety, and performance indices, of an enclosure from weighted values of contributing metrics including sensor data and / or controlling one or more building systems based on the composite indices.

The invention relates to the technical field of medical data mining, and particularly discloses an elderly sepsis index model, a prediction model construction method and a prediction system.The method comprises the steps that a development queue data set and an independent verification queue data set of elderly sepsis patients at the age larger than or equal to 60 years old are determined according to an intensive care database; performing sepsis death and prognosis importance sorting on candidate inflammation-immune composite indexes of the development queue data set according to a total correlation feature selection algorithm; superposing and combining preset basic indexes, each index in the importance inflammation marker indexes and a preset importance scoring standard; comparing the scoring results of the multiple groups of joint optimization index models, and evaluating the scoring results; and determining the joint optimization index model with the optimal evaluation result as the senile sepsis index model. According to the construction method of the senile sepsis index model provided by the invention, the index model suitable for senile sepsis can be obtained based on the existing index database.

The embodiment of the invention provides a big data index management method and system based on a weak model, and the method comprises the steps: selecting a data source based on a business scene, writing an SQL statement, recognizing dimension information and index information based on the SQL statement, and writing the dimension information and the index information into an index table, correspondingly writing the SQL statement and the index table into a distributed column database; receiving a query request of the user-defined index, querying SQL statements based on parameter key information of the query request in combination with basic information of the user-defined index, assembling the SQL statements, generating user-defined SQL statements, and performing statement optimization on the user-defined SQL statements; index codes are created according to the dimension information and the index information, detail indexes are generated based on the index codes, synchronization parameters of the detail indexes are set, and the detail indexes comprise basic indexes, derivative indexes and composite indexes.

The invention discloses a cracking zone tunnel blasting construction safety risk grading evaluation method and system, and belongs to the technical field of tunnel engineering safety monitoring. According to the method, dimensionality reduction and conflict resolution are performed on the original indexes by adopting the PCA-EWM method, and the mutually independent composite indexes among the indexes are obtained, so that the independence and effectiveness of the indexes are improved, and the problem that the final evaluation result is inaccurate due to the fact that the information among the original indexes is overlapped and the weight distribution is inevitably caused by repeated distribution is avoided; the weight is dynamically adjusted through the offset of the criterion layer so as to adapt to the complex engineering environment, and it is ensured that the evaluation result can reflect the current risk state; due to the fact that the composite index of tunnel blasting and the construction risk degree are in a nonlinear relation, a normal cloud model is adopted to reconstruct a membership function and process nonlinear risk evolution of the index so as to better adapt to nonlinear characteristics of the tunnel blasting construction data of the cracked zone, the accuracy of risk assessment is improved, and the safety of construction is guaranteed.

The invention provides a reservoir sediment modeling method based on multi-time-sequence multi-beam sounding point cloud data, and relates to the field of reservoir sediment monitoring and modeling, and the method comprises the steps: constructing a reservoir area space grid skeleton model, and collecting multi-time-sequence multi-beam point cloud data and corresponding hydrological auxiliary data; performing space division by adopting an adaptive tile subdivision method, generating multi-level point cloud tiles by adopting a feature point downsampling method, and establishing a three-dimensional composite index; the indexed multi-level point cloud tile set is processed through an anisotropic ICP registration method, and a point cloud tile set of multi-time-sequence registration is obtained; establishing an initial triangulated irregular network sediment model, carrying out differentiated partitioning by utilizing historical hydrological auxiliary data, and carrying out dynamic updating based on a partitioning state to obtain a dynamic reservoir sediment model; and S5, calculating to obtain deposition parameters, and mapping the deposition by adopting a three-dimensional engine to obtain an interactive three-dimensional dynamic deposition situation map. According to the invention, high-precision dynamic visualization of the reservoir sediment deposition process is realized.

The invention discloses a dynamic SQL (Structured Query Language) optimization method based on consanguinity dependency, and relates to the technical field of database query optimization. The method comprises the following steps: analyzing all indexes in a database, and dividing the indexes into atomic indexes and composite indexes; a blood relationship dependency tree is constructed according to the mathematical relationship between the indexes, each node represents one index, and each directed edge represents the dependency relationship; receiving a to-be-queried index set, and recursively searching all dependent target atomic indexes based on the graph structure; grouping the target atomic indexes according to data sources, and generating corresponding SQL query statements; and executing the SQL statement, and calculating a final query index result after obtaining an atomic index value. According to the invention, through unified management of the index dependence structure, repeated calculation across indexes is eliminated, the query performance is improved, the resource consumption is reduced, and the index development and maintenance efficiency is improved.

The embodiment of the invention provides a rail transit 3D data defect detection method and system based on spatial indexing, and the method comprises the steps: collecting rail 3D original data, carrying out the preprocessing, and unifying the data into a unified rail coordinate system; dividing the preprocessed track 3D data into a plurality of regular grid units as space units according to spatial positions, extracting multi-dimensional features of data in each space unit, establishing a composite index for each space unit, and storing the composite index in a space-time database; after the acquired 3D data of the current track are subjected to identical processing, spatial position areas corresponding to the 3D data of the current track and historical data are quickly matched through a composite index, and a difference value of multi-dimensional features is calculated; dynamically adjusting the defect judgment threshold of each dimension according to the statistical distribution of the difference values, judging the defect type and severity of the region meeting the threshold, and generating a detection report. The problems that traditional 3D data processing is low in efficiency and long in comparison time consumption are solved.

The invention relates to the technical field of industrial data management, in particular to a supply chain data real-time integration processing method and system based on multi-source heterogeneous data, and the method comprises the steps: obtaining an external compliance data document, calling a document layout analysis model based on a multi-modal converter, extracting a text semantic vector, fusing the text semantic vector with a two-dimensional space coordinate feature to generate a composite index key, and carrying out the real-time integration processing of the supply chain data. Executing clustering analysis to recognize the text blocks and generating structured metadata; carrying out discretization processing on the business transaction data flow, and constructing an associated database with production environment and logistics data as attributes; executing cross-modal entity alignment by using the structured metadata, and establishing a bidirectional pointer link between the unstructured document index and the associated database; receiving a query vector, executing a recursive traversal algorithm based on a bidirectional pointer link, calculating a cascade influence probability as a correlation sorting score, and outputting a retrieval result; through multi-modal feature fusion and cross-modal entity alignment, deep integration and risk linkage retrieval of supply chain heterogeneous data are realized.

The invention discloses a foreign language teaching effect evaluation method and system based on artificial intelligence. The method comprises the steps of data acquisition, voice feature extraction, multi-modal fusion evaluation modeling and teaching effect evaluation. The invention relates to the technical field of teaching effect intelligent evaluation, in particular to a foreign language teaching effect evaluation method and system based on artificial intelligence. According to the scheme, a pronunciation definition composite index is constructed through formant difference analysis, the acoustic semantic coupling degree is calculated, and the phoneme transfer stability is evaluated; the definition, the accuracy and the continuity of the voice can be accurately quantified in a multi-noise environment; according to the scheme, modal attention is introduced, full-interconnection cross-modal cross attention is utilized to realize multi-modal information bidirectional interaction, a complementary gating mechanism is innovatively introduced to adaptively adjust a modal fusion proportion, a light quantum network is combined to generate a local score, a meta-decision network dynamically distributes weight, and finally end-to-end optimization is carried out through a differential weighting strategy. And teaching effect evaluation of fineness and accuracy is realized.

The invention discloses an efficiency monitoring system for a large model training cluster. The efficiency monitoring system comprises a training data acquisition module, a back-end processing module and a client, the training data acquisition module comprises a monitoring hook submodule and a database; the monitoring hook submodule intercepts an import request of a core module of a training task by rewriting a Python module finder, and installs a monitoring hook in a target training process; the monitoring hook collects corresponding data in real time and stores the data into a database; the back-end processing module acquires various monitoring data acquired by the data acquisition module through the data acquisition module interface access layer, and calculates various composite indexes related to training efficiency based on the preprocessed monitoring data through a high-order index calculation engine. According to the invention, real-time monitoring and non-intrusive deployment can be realized, and data integrity can be ensured.

The invention discloses an urban credit monitoring analysis method and device and a medium, and the method comprises the steps: carrying out the analysis of collected standard urban credit monitoring data according to a preset assessment index specification, and determining a basic index of urban credit monitoring; according to the basic indexes, constructing a monitoring index library of urban credit, and determining to-be-optimized indexes in the monitoring index library through data comparison; combining the indexes to be optimized through a combination number combination algorithm to generate a composite index; and analyzing the composite index through a pre-trained neural network model, generating urban credit monitoring knowledge, and accessing the urban credit monitoring knowledge to a knowledge base through a knowledge base API to construct an urban credit monitoring knowledge base. According to the method, the urban credit monitoring knowledge base is constructed, so that the difficulty of acquiring the urban credit monitoring data by the user is greatly simplified, the accuracy and efficiency of urban credit monitoring analysis are effectively improved, and the actual demand and benefit of the customer are met to the maximum extent.

The application provides a deep rock mass multi-field coupling test data-driven intelligent grading method, relates to the technical field of deep rock mass grading, and constructs a multi-field coupling mechanism database through deep rock mass multi-field coupling test data, refines intelligent characteristic indexes representing multi-field coupling effects from the database, the intelligent characteristic indexes include traditional indexes and composite indexes, the composite indexes are determined based on geological environment parameters of the deep rock mass, the intelligent characteristic indexes are taken as inputs, corresponding deep rock mass grades are taken as outputs, a machine learning model is trained, a deep rock mass intelligent grading model under different geological environment parameters is obtained, intelligent characteristic indexes of deep rock mass to be graded in an engineering site and geological environment parameters thereof are acquired, grading is performed through the deep rock mass intelligent grading model matched with the geological environment parameters, and the grade of the deep rock mass is obtained, so that the problem of low accuracy of existing deep rock mass grading is solved, and the application is suitable for deep rock mass grading.

The invention discloses a virtual measurement method and device, equipment, a storage medium and a product, and relates to the technical field of computers, and the virtual measurement method comprises the steps that multi-time-scale abstract processing is conducted on process parameters and production data sequences obtained online, and a multi-scale time sequence group is obtained; based on a preset virtual measurement model, virtual measurement is carried out on the multi-scale time sequence group, a key parameter measurement result is obtained, and the virtual measurement model is obtained by adopting a reinforcement learning mode to carry out virtual measurement training on a preset time sequence data sample. According to the method, the multi-scale time sequence group of the online time sequence characteristics is extracted, virtual measurement is performed on the online time sequence characteristics by using the trained virtual measurement model, the key parameter measurement result of the composite index is obtained, accurate prediction of the composite index is realized, and the accuracy of the prediction result is improved. Therefore, the problem that comprehensive monitoring of the composite indexes is difficult to achieve in precise laser cutting through a traditional method is solved, and the prediction accuracy is improved.

The invention discloses a time series data analysis method and device, a storage medium and electronic equipment, and relates to the technical field of the Internet of Things. By establishing a composite index structure combining a time index and an equipment index, under the composite index structure, corresponding index entries are dynamically created for a target data flow, the framework of the composite index structure is not changed, and the time series data analysis efficiency is improved. The content is dynamically filled along with the data, and finally a complete composite index result capable of being efficiently retrieved is formed. And the time index adopts a B-Tree structure, so that data in a specific time range can be quickly positioned. Equipment indexing is realized based on a hash table, data generated by specific equipment can be efficiently retrieved, the throughput bottleneck of mass data storage is broken through, and second-level writing and aggregation query of ten millions of data are realized. And in combination with artificial intelligence AI, distributed time series data management and an Internet of Things multi-source data fusion technology, in the face of massive time series data, the analysis processing capability of the time series data is improved to meet the demand of time series data analysis.

The invention discloses a method and equipment for processing meteorological grid point data based on a database, and the method comprises the steps: analyzing original meteorological grid point data, and extracting metadata information; the metadata information is grouped and coded according to at least two dimensions, and binary bit streams corresponding to coded values obtained after information of each dimension is coded serve as input data; starting from the most significant bit of the binary bit stream, sequentially extracting one bit from each dimension according to a preset sequence for interlacing, and generating a primary key corresponding to the original meteorological grid point data; the main keys are written into a database for storage, and the database sorts the main keys according to the sizes of the main keys. According to the method provided by the invention, through a multi-dimensional joint index construction method, efficient and flexible support for multi-dimensional range query of the type is realized, complex multi-dimensional range query is converted into efficient one-dimensional continuous interval scanning of a data storage engine, and the meteorological service data retrieval performance is improved.

The application provides a multi-source Parkinson's disease database integration method based on LEDD-UPDRS composite index alignment, and is applied to the technical field of data processing. In view of the heterogeneous problems of multi-source Parkinson's disease databases, the application integrates heterogeneous data of PPMI, PDBP and local queues, disassembles characteristics according to four modes of heredity and clinic, introduces a standardized term library and a BERT-BiLSTM-CRF model unified term adjusted in combination with medical corpus, generates a cross-library feature table; a storage architecture is constructed based on FlashROM mode to realize data storage and retrieval; a composite observation system is built with LEDD and UPDRS-III, consistency is verified by multiple methods, data is standardized, missing data is filled in combination with multiple models to generate an integrated data set; a double prediction model is built relying on the data set, and the advantages of the data are realized by a Cohen's d value verification method; finally, cross-library joint analysis is carried out, phenotype-genotype correlation modeling and causal inference are completed, and data support is provided for Parkinson's disease research and clinical prediction.