111 results about "Knowledge mining" patented technology

The invention relates to the field of heterogeneous information retrieval, in particular to an intelligent retrieval and analyzing method based on domain ontology and information mining and a visual analyzing system comprising the method. The system mainly comprises a field data acquisition subsystem, a corpus resource processing subsystem, an information mining subsystem and a visual analyzing subsystem, wherein the field data acquisition subsystem is used for acquiring data by network capturing and local uploading, the field data acquisition subsystem is used for pre-processing field related data, the field data acquisition subsystem is used for analyzing and mining related information in corpus, and the visual analyzing subsystem is used for dynamically displaying and counting and analyzing retrieval results. Concepts in a domain ontology base and mutual relations of the concepts are fully used by the system for heterogeneous information mining and visual analysis, requirements of users can be correctly understood to automatically cluster hierarchical structural information of a certain field so as to support the users to inquire key words, phrases and simple sentences and optimize retrieval results, relevant concepts and extension concepts can be found by ontological reasoning to support graphic display preview of each information meaning in the inquiry results, and the professional-field information retrieval performance can be remarkably improved to realize dynamic information display.

The invention discloses an object-level information excavation system, which comprises a data collection module, a data cleaning module, a content pretreatment module and an object correlation search module, wherein, the data collection module used to collect data comprises a WEB grabber, the data cleaning module used to process structured data comprises a data verification module and a repeat-ridding process module, the content pretreatment module used to pretreat unstructured data comprises a metadata management module and a content analyzer, and the object correlation search module used to analyze the correlation degree of the processed content of the content pretreatment module comprises a correlation degree analyzer. The invention also discloses an object-level information excavation method, which comprises the following steps that: information is collected from web pages; the data cleaning process is carried out to the structured data collected; the content pretreatment operation is carried out to the unstructured data collected; the object correlation search operation is carried out to the content obtained after the pretreatment.

The invention discloses a knowledge graph construction method and device for power grid main equipment, and belongs to the technical field of power grid operation and inspection. Through continuous exploration and test, basic information, operation data and operation content of power grid main equipment are subjected to structured processing, knowledge triple extraction, ontology construction and knowledge graph completion and reasoning of the power grid main equipment are achieved through a system tool, and then a knowledge graph of the power grid main equipment is constructed; the method is suitable for the power grid equipment, can be applied to a power grid operation and maintenance management and control platform, can provide an auxiliary decision for operation and maintenance commanders, effectively improves the processing capability of personnel and equipment abnormality and faults, improves the quality and efficiency of knowledge analysis and processing of the power grid equipment, reduces the operation and maintenance cost of the power grid equipment, and improves the power transformation operation and maintenance efficiency. According to the invention, the knowledge mining capability and the intelligent analysis service capability of the equipment management business can be effectively improved, and the informatization and intelligence level project range of power grid operation and maintenance is comprehensively improved.

The invention relates to a computer assistant reporting and knowledge-base generation method including the following steps: a server system receives requests of information search from users and searches all structured and unstructured web pages and websites matching the search requirements of users on the internet and a third-party database and also feeds the search results back to a client digital terminal system after classification, de-emphasis and compilation while matching the third-party database; the server system records the search behavior of a user and detects the updating of information resource and catches and classifies the updated information in real time so as to remind the user of the updating of the information resource when the user goes on line; the user selects the required information from the search results and collects the information into the system and the knowledge mining method is adopted to generate reports and derive files. The invention has the beneficial effects that the efficiency of searching, collecting and classifying the information is enhanced for the user, and the unstructured information can be converted into structured information and the semantic relevance between information can be preserved by human-computer interaction.

The embodiment of the invention provides an information analysis method based on big data and artificial intelligence and a cloud service information platform. In the pushing process of the information pushing index content data, considering of operation metadata of a field name association structure or a keyword association structure is added; therefore, the operation node information of the field names and the keywords associated according to the logic relationship in each knowledge mining element of the user operation behavior big data can be reflected; therefore, knowledge mining elementsare screened and then knowledge graph mining is carried out, so that the pertinence and the accuracy of a subsequent interest pushing index strategy updating process can be improved under the condition of complex data contents, particularly more noise data, and the accuracy of index pushing contents is improved.

The present invention belongs to the technical field of large-scale data mining, and specifically relates to a knowledge graph construction system. The knowledge graph construction system comprises a crawler cluster, a Hadoop distributed storage cluster, a natural language processing cluster, a Mahout knowledge mining module and a knowledge database. The crawler cluster is used for crawling webpage data according to seed addresses and storing the webpage data into a webpage HBase table. The natural language processing cluster is used for obtaining the webpage HBase table from the Hadoop distributed storage cluster, generating original knowledge information, and storing the original knowledge information in an original knowledge HBase table. The Mahout knowledge mining module is used for performing knowledge mining on the original knowledge information, generating unstructured data, and storing the unstructured data in an unstructured data HBase table. The knowledge database is used for constructing a knowledge graph according to the manually reviewed unstructured data.

The invention provides a data mining system used for an enterprise innovation system. The data mining system comprises a science and technology innovation system decision assisting and supporting subsystem, a science and technology enterprise innovation knowledge mining subsystem, a science and technology innovation service subsystem and an innovation resource catalogue service subsystem. The science and technology innovation system decision assisting and supporting subsystem comprises an information collection module, an analytical prediction module, a decision making module and a decision execution module, wherein the information collection module is used for finding mass data on a knowledge base or a network and comprehensively and accurately obtaining all types of basic data related to items where decision making is to be conducted. The data mining system has the advantages of being comprehensive in function and high in intelligent degree, the effect of conducting deep mining on enterprises is achieved, and enterprises are scientifically guided to conduct technical innovation.

The invention discloses a pipeline safety event identification and knowledge mining method based on an HMM model, belonging to the pipeline safety event monitoring field. The method comprises the following steps: (1) extracting the multi-domain features of signals collected by each space point and obtaining the feature vector sequence of the signals; 2, inputting a feature vector sequence into anHMM model for off-line training to complete that construction of a typical event HMM model library; 3, after obtaining that current feature vector sequence of the signal to be identified through the step 1, inputting the signal to be identified into a typical event HMM model library for identification and outputting an event judgment type, and calculate an optimal hidden state sequence as the information of the evolution process of the event state sequence for output, and completing knowledge mining; The HMM model of the invention is analyzed and identified based on the characteristic timing sequence, and the event identification rate is effectively improved. At the same time, knowledge mining is realized in the evolution process of event state series, which can be used for short-term prediction.

The invention relates to an interval value fuzzy set method for aging state evaluation of insulation paper of a transformer, and belongs to the fields of a power system and automation thereof. To solve the problem that big data related to insulation state evaluation of the distribution transformer is diversified, large in amount and complex in mutual relation, knowledge mining and inference principles are used on the basis of establishment of a big data library to process and analyze the big data; and aimed at random and fuzzy nondeterminant parameters related to insulation state evaluation ofthe distribution transformer, an interval value fuzzy set theory is used for processing and analysis, and the aging state of the insulation paper of the transformer is evaluated accurately.

The invention discloses a data analysis platform and method for an electric power system. The platform stores data to be processed by virtue of a cloud distributed database, performs instant inquiry and / or multidimensional analysis and / or machine learning and the like on the data to be processed according to a received operation instruction of analyzing the data to be processed and carries out the knowledge mining on the data to be processed through the machine learning algorithm analysis. The data analysis platform and method for the electric power system disclosed by the invention can be used for extracting unknown and valuable data through a machine learning algorithm, thereby proving a powerful support for enterprise decision making.

The invention discloses a large-scale medical data knowledge mining and treatment scheme recommendation system. The system comprises a data set preprocessing module which is used for obtaining real electronic medical record data and carrying out preprocessing on the electronic medical record data composed of a plurality of types of heterogeneous data sources; a disease severity prediction module which is used for obtaining disease severity scores of each patient in the treatment process; a treatment effectiveness measurement module which is used for obtaining effective treatment measurement information; a patient similarity measurement module which is used for constructing a similarity measurement relationship of patients; and a drug therapy scheme recommendation module which is used for obtaining drug therapy scheme recommendation of the next stage. According to the invention, the severity degree of the illness state of the patient is judged and predicted through the multitask bidirectional heterogeneous LSTM, the effectiveness measure of treatment is defined, the fine grit similarity of the patient is calculated, and the treatment scheme of the next stage is recommended accordingto the historical treatment records of the patient and the effective treatment schemes of other patients with high pathology similarity.

The invention discloses a method, a device and a system for protein knowledge mining and discovery in a Chinese bibliographic database and can achieve mining and discovery of protein knowledge in the Chinese life-science bibliographic database. The technical scheme includes that the method comprises constructing the Chinese bibliographic database and a scientific data type database, performing translation and compiling of a protein-relevant text mining tool dictionary on the basis of a standard control vocabulary of the scientific data type database and with protein nouns in the Chinese bibliographic database as mining and discovery objects; converting identification number into hyperlink information according to protocols provided by the scientific data type database, and generating the Chinese bibliographic database facing to themes and application; and removing false-positive protein mining results in data mining and information integration results and modifying Chinese bibliographic text mining results.

The invention discloses a knowledge mining method for an intelligent IETM fault maintenance record text. The knowledge mining method comprises the steps of 1, collecting equipment fault maintenance record text data; 2, establishing an equipment fault word bank; 3, obtaining a lexical item document matrix; 4, generating a theme document matrix; 5, training a label feature matrix; 6, constructing aneural network; and 7, classifying the equipment fault maintenance record texts. According to the method, the LDA topic model is used for extracting lexical item document matrix features; obtaining label feature matrix, providing a classification label of the fault maintenance record text; equipment fault maintenance record texts can be quickly classified; in addition, a pooling layer in the convolutional neural network is replaced with a circulating layer, the convolutional layer in the convolutional neural network has the advantage of weight sharing, the circulating layer has the advantage of solving the problem of long-term dependency of texts, and sufficient knowledge data is provided for a fault maintenance auxiliary system in an intelligent IETM platform.

The invention discloses a map visualization system and method for knowledge mining based on spatial big data. The method comprises the following steps: drawing a visualization area space-time basic map: drawing the determined visualization area space-time basic map according to a GIS geographic information system; realizing a spatio-temporal data acquisition step: according to the geographic position information of the determined area range, acquiring spatio-temporal data with geographic attributes and time attributes in the area range based on a GIS geographic information system; realziing adata analyzing and processing step: analyzing and processing the obtained space-time data; and realzing a visualization model display step: inputting the output result of the data analysis processingstep and the space-time basic map into a visualization model to realize visualization display of the determined area map. The space-time basic map for determining the urban area and the collected space-time data are imported into the visual model to be processed, and finally visual display of the map is achieved through the space-time visual display terminal, so that map representation is more visual.

The invention discloses a vulnerability knowledge mining method and system based on a graph, and the method comprises the steps: S1, collecting vulnerability data disclosed in the field of network space safety, importing vulnerability data into a database, and constructing a vulnerability knowledge graph; S2, performing vulnerability knowledge mining and the like based on the constructed knowledge graph; fusing multi-source heterogeneous public vulnerability information to form a unified knowledge representation form; obtaining closed-loop knowledge from the product manufacturer to the vulnerability information to the attack method through associated query and derivation of the knowledge graph; and mining more vulnerability-related knowledge based on an algorithm of the knowledge graph.

The invention relates to a knowledge base construction method and device. The knowledge base construction method includes the steps that text linguistic data are obtained, and whether the text linguistic data contain first information is judged according to a preset attribute description mode, wherein the first information includes attribute information of entities in a preset entity set; when it is determined that the text linguistic data contain the first information, the first information is extracted, and a knowledge base is constructed according to the first information and entities corresponding to the first information. According to the embodiment of the knowledge base construction method and device, in the process of constructing the knowledge base, it is unnecessary to perform knowledge mining in a manual mode, in this way, labor is saved, and the construction speed of the knowledge base is increased.

The invention discloses an enterprise quality credit data acquiring method. The method comprises the following steps: S1, preprocessing data which are associated with enterprise quality credits to obtain corpus data; S2, carrying out knowledge mining on the corpus data to obtain template data; and S3, extracting key data which correspond to the template data from the corpus data, and taking the key data as the enterprise quality credit data. By the enterprise quality credit data acquiring method, consistency, accuracy and comprehensiveness of data acquisition are ensured.

The invention discloses a formal semantic reasoning and deep learning-based natural language knowledge mining method. The method comprises the following steps: a machine learning step used for combining a formal semantic reasoning method with a machine learning method and performing machine learning including semanteme, an intention learning step used for learning a descriptive intention of a to-be-mined natural language, a text topic extraction step used for analyzing a text topic content and paragraph content descriptive intention according to an LDA model, and a document structure classification model building step used for performing model training according to a deep convolutional neural network, automatically modifying and perfecting the neural network in a training process and building an automatic document structure classifier. According to the method, a non-structured data group represented by literatures, voices and the like is directly processed and the intention is reasoned by depending on the combination of automated semantic reasoning, a deep learning technology and natural language processing, thereby obtaining a real intention of text description; and mined and retrieved knowledge is used for analysis and construction of a new knowledge structure, so that knowledge mining and retrieval can be performed in an efficient, intelligent, learnable and self-evolution manner.

The invention discloses a big data mining system for traditional Chinese medicine clinical case information. The system comprises a medical record management module, a data source module and a data mining module, wherein the medical record management module allows a doctor to input a medical record and retrieve the medical record information, and provides the data to the data source module; the data source module is responsible for storing the data submitted by the medical record management module and other external data and carrying out standardized processing; and the data mining module is responsible for performing data preprocessing, knowledge mining and knowledge analysis processing on the data transmitted by the data source module.

The invention discloses a matrix dynamic attribute reduction method in which objects and attributes are simultaneously added, which relates to the technical field of rough set and granular computing theory in data mining. Firstly, the minimum attribute reduction REDU of a decision table before change is calculated. When objects and attributes are added to the decision table at the same time, whether the relative knowledge granularity of the minimal attribute reduction of the decision table is equal to the relative knowledge granularity of the changed decision table is calculated, If so, REDU is the minimum attribute reduction after the change, otherwise, the matrix method and incremental mechanism are used to calculate the external importance of all attributes of the changed decision tableexcept REDU, Select the largest attribute to add to the minimum attribute reduction, calculate the relative knowledge granularity until it is equal to the relative knowledge granularity of the changed decision table, delete the redundant attributes, and obtain the minimum attribute reduction of the changed decision table. The invention effectively solves the problem that the minimum attribute reduction can be quickly calculated when the objects and the attributes in the decision table are simultaneously increased, and contributes to improving the efficiency of the dynamic data knowledge mining.

The invention discloses a knowledge mining method and a system for structured data. The method collects structured data to be mined and cleans the collected structured data. According to the characteristics of the target data, the structured data after data cleaning is analyzed, and the knowledge mining model is constructed according to the analysis results. Using the knowledge mining model, the corresponding target information is extracted from the structured data. It has the beneficial effect of constructing the corresponding knowledge mining model according to the specific knowledge miningrequirements, thus improving the pertinence of knowledge mining and the accuracy of knowledge mining.

The invention relates to an intelligent managing cockpit for a power supply system. The intelligent managing cockpit is a one-stop decision support system with the cockpit as a form. The key indication state of electric power system operation is shown through various visualization technologies such as a speedometer, a volume column, early warning radar and a radar ball, a decision maker and a manager are helped to orderly tease the mass information of an electric power system, and the real-time states of the electric power system are easily and visually monitored and sensed; by means of the state sensing means, the abnormal key index is sensed in time; by means of the knowledge finding and other advanced computing technologies, tendency preconceiving, knowledge mining and situation early warning are achieved, and the managing cockpit suitable for the characteristics of a power supply system is manufactured.

The invention discloses a clinical medicine entity identification method and a clinical test knowledge mining method, and the clinical test knowledge mining method comprises the steps of clinical medicine entity identification, clinical test argument mining and clinical test result reasoning. According to the method, on the basis of a BERT pre-model, further pre-training of abstract literatures of RCT is added, a text model in the clinical test field is obtained, entity category information is fused into model prediction, and the effect of a clinical test entity mining task is improved; in the information extraction stage, while a PICO entity is recognized, IC and an evidence sentence containing O are matched, then the logic relation of the IC and the O is judged, and the mask language model architecture of BERT is fully utilized for prediction.

A method for construction of a construction project risk knowledge base is characterized by comprising the steps of first performing combing, statistics and analysis according to collected project risk events and accident cases, establishing knowledge expressions of environment factors and engineering factors of the project risk events and the accident cases, classifying risk knowledge, and constructing a risk knowledge map; designing and establishing the risk knowledge base of engineering project construction of factors such as comprehensive scheduling, investment, safety, quality and environmental influence, enabling the risk knowledge base to comprise attribute establishment of the environment factors and the engineering factors; and finally updating data of the knowledge base through data collection and handing of projects in construction. According to the method, by utilizing disasters occurring in the engineering projects under construction or having been constructed, performing knowledge mining on the disasters and combining a computer-assisted construction risk knowledge base to analyze risks of projects to be constructed, project risk prediction and early warning on the projects to be constructed are performed, repeated occurrence of safety accidents to the projects to be constructed is avoided, and safety of the construction project is improved.

The AIOT PaaS Internet of Things operation platform comprises an application layer, a platform layer, a trusted layer, a network layer, an edge layer and a device layer, wherein the device layer comprises all Internet of Things devices provided with intelligent chips; the edge layer constructs a data basis of the Internet of Things operation platform by performing large-range and deep-level data acquisition on Internet of Things devices included in the device layer and performing protocol conversion and edge processing on heterogeneous data; the network layer is used for transparent data transmission between the edge layer and the trusted layer; the trusted layer is used for providing trusted infrastructure as a service (IaaS); the platform layer provides development, operation and management and control environment, namely middleware functions, for the application layer by utilizing the capability of the trusted layer; the application layer carries out calculation, processing and knowledge mining on data collected and transmitted by the edge layer, so that implementation control, accurate management and scientific decision making of the Internet of Things operation platform are realized.

The invention relates to the field of data release, in particular to a multi-source data fusion privacy protection method for multi-privacy policy combination optimization. A multi-party data fusion framework based on the over-anonymity is provided, and the situation of privacy disclosure of fused data is prevented. Furthermore, the practical significance of data fusion is to provide a more comprehensive data basis for the user, so that extensive knowledge mining can be carried out on the basis. Therefore, a multi-privacy protection strategy combination optimization scheme is designed, and the availability of fused data is improved to the greatest extent while privacy constraints of all parties are met. According to the strategy, multi-source multi-privacy constraint data are fused and mapped into a hypergraph, hyperedges are selected, solved and eliminated on the hypergraph one by one by using a heuristic rule, the hyperedges are eliminated, the privacy constraints are realized one by one, and a data fusion scheme is formulated.

The invention provides a poison-target literature knowledge mining method and system based on network crawling. The poison-target literature knowledge mining method comprises the steps of: acquiring poison and target data information, and processing the poison and target data information, so as to establish a comprehensive data set; developing a web crawler tool; crawling poison and target literature text information by utilizing the web crawler tool based on the comprehensive data set, and processing the poison and target literature text information to establish a literature text database; based on the literature text database, determining a poison-target potential action relationship by utilizing a natural language processing technology to form a poison-target relationship knowledge base; and performing poison-target literature knowledge mining by utilizing the literature text database and the poison-target relationship knowledge base. The poison-target literature knowledge mining method and the system based on network crawling are high in efficiency, good in accuracy and high in intelligent degree.

The invention discloses a cam shaft intelligent grinding process software database system based on a numerical control system. The system comprises a technological problem definition module, a technological integrated database module, an expert knowledge base, a decision optimization module, an automatic programmable module and a grinding application module. The technological problem definition module is used for storing a plurality of pieces of process case information according to generalized technological problem definition information model normalization requirements and building other modules with data and knowledge mining and rule-knowledge self-learning ability. A complete set of software is integrated and embedded by the aid of Siemens (original equipment manufacturer) system development communication interface programs. The system solves the problems of complicated and changeable current cam shaft grinding environments, process parameter optimization and decision-making difficulty, complex numerical control programs, low similar part decision-making and programming efficiency and the like. Cam shaft part decision-making processing time can be remarkably shortened, processing efficiency is improved, and the performance of a numerical control machine tool is brought into full play.

The invention discloses a knowledge graph construction system and method based on a graph database, and the method comprises the steps: recognizing the types of graph data in the graph database, and loading the different types of graph data into a CPU memory in batches; identifying the graph data loaded into the CPU memory one by one, marking a result attribute association field to obtain a fieldof a knowledge graph, and extracting an information field; establishing a data dimension inner-layer model for the information fields according to the proportion, and establishing a data dimension outer-layer model based on the data dimension inner-layer model; according to the data dimension inner-layer model and the data dimension outer-layer model, data in the models being subjected to persistence, and obtaining a knowledge graph database; and establishing a knowledge query Web interface, analyzing the query command, and returning to the knowledge graph database to retrieve result data. According to the invention, one-key query and millisecond response are realized, the difficulty of knowledge mining of graph data is reduced as much as possible, and the efficiency of knowledge graph construction is greatly improved.