78 results about "Reasoning rule" patented technology

The invention provides an alarm root cause analysis method, device and equipment and a storage medium, and relates to the technical field of operation and maintenance. The invention provides a methodfor carrying out alarm root cause analysis based on double correlation, and the method can integrate the time sequence correlation of different alarms and the topological correlation of different alarms to mine root cause alarm information from a large amount of alarms. Time sequence association information based on alarm is obtained. clustering the plurality of alarms; obtaining root cause alarminformation according to the target class conforming to the topology association condition; The alarm root cause analysis method and device can screen out alarms with strong correlation in time sequence and topology at the same time and filter out accidental adjacent noise information in time and accidental adjacent noise information in topology, and therefore interference of the noise informationon alarm root cause analysis can be avoided, and the accuracy of the alarm root cause analysis is improved. Meanwhile, a large amount of business domain knowledge is not needed, and manual definitionof reasoning rules is not needed, so that the cost of alarm root cause analysis is saved.

The invention relates to an ontology library-based tag management method. Media asset tagging is realized through multilayer semantic tag extraction; and semantic tag management is realized based on an ontology reasoning rule. A user uploads a picture to a picture database through a management end; the picture is processed through an ontology-based multilayer semantic tag library generation module to obtain a multilayer semantic tag; and the multilayer semantic tag is stored in an ontology tag library. A new tag submitted by the user is processed through an ontology reasoning rule-based tag library generation module. Firstly the new tag is added to existing tag library contents to obtain a mixed tag library; secondly according to the reasoning rule, the mixed tag library is processed to obtain an optimal ontology; and finally, the optimal ontology is stored and the ontology library is updated. The user submits query information to the tag library for query during use, and if the query is hit, a tag query result is returned to the user; or otherwise, the query information is subjected to similarity calculation through a similarity calculation module to obtain related recommendation information of the query information, and the related recommendation information of the query information is returned to the user.

A system and method for hybrid Rete reasoning based on memory and DBMS are provided. The system for hybrid Rete reasoning based on memory and DBMS includes a reasoning rule type classification means for classifying an input reasoning rule as one of one or more types. A network generation means generates a network depending on the classified reasoning rule type. A network execution means derives extended triples by applying a predetermined triple to the generated network.

The invention discloses a method for constructing an international maritime dangerous goods knowledge map system, wherein, the construction method of the knowledge map system of dangerous goods in international maritime transport comprises the following steps: acquiring knowledge data of dangerous goods in international maritime transport; extracting entities, entity attributes and entity relationships of the knowledge data according to the acquired knowledge data; according to the preset reasoning rules, the entity, entity attributes and entity relations being reasoned, the relationship between entity, entity attributes and entity relations being determined, and the ontology of international maritime dangerous goods being constructed according to the relationship; aiming at the ontology of international maritime dangerous goods, the quality assessment and knowledge updating being carried out, and the knowledge map of international maritime dangerous goods being constructed. The technical proposal provided by the invention expresses the complex international maritime dangerous goods transport rules and the international maritime dangerous goods with ontology knowledge, simplifies the application of the rules, reduces the manpower and time cost, and optimizes the supervision and screening of the international maritime dangerous goods.

The invention discloses a decision support system architecture and method based on a water conservancy knowledge-factorial coupling network. The system comprises an inference mechanism module, a factorial map module, a rule base module and a water conservancy knowledge map module. Firstly, a water conservancy knowledge graph module and a related monitoring database are constructed; the rule base construction module comprises a rule base of an inference rule, an object rule and an attribute rule; the cause map module realizes cause maps associated with an inference rule base, an object rule base and an attribute rule base; the reasoning mechanism module realizes establishment of a reasoning framework running on a coupling network formed by combining a water conservancy knowledge graph and afact graph based on a rule base, reasoning is performed on a reasoning target on the reasoning framework, and finally decision support information pushing is completed; according to the method, causeanalysis and decision support are carried out on the target event in real time, and a real-time, accurate and efficient reasoning effect can be achieved.

The invention discloses a program static automatic analysis method and relates to a method of automatically analyzing program property by using a data flow analysis means and a logic reasoning system.The method includes: using a grammar analysis tool to analyze a source code, and constructing an extension program flow graph on a sentence level; using a recursive function and property thereof to define property of a program to be analyzed, and using a meet semi-lattice to describe a valuing set of the property; customizing a processing procedure when the program property is transmitted and passes a program sentence, performing automatic derivation and analysis by combining a constraint solving tool with logic reasoning rules, and using a data flow analysis algorithm to execute automatic iteration to solve an analysis result; writing the result back onto the program node of the extension flow graph in a formula form for the convenience of analysis personnel to judge whether the code is wrong or not.By using the method, manual analysis operation can be replaced, analysis accuracy and completeness are guaranteed, errors and omissions caused by manual analysis are avoided, and time cost and manpower cost are saved effectively.

The invention provides a Chinese comment emotion classification method and a Chinese comment emotion classification device based on evidence reasoning rules. The method comprises the following steps of: preprocessing the obtained Chinese comment text; Extracting features of the pre-processed Chinese comment text to obtain a vectorized Chinese comment text; Dividing the Chinese comment text into training data and test data, and training a plurality of preset base classifiers using the Chinese comment text; Predicting the emotion tendency of the test data by using the plurality of trained base classifiers to obtain weights of each base classifier; Based on the weight and reliability of each base classifier, the output probabilities of each base classifier are fused by using evidence reasoning rules to obtain the emotion classification results of Chinese comment texts. Thus, the invention uses evidential reasoning rules to fuse the output results of different base classifiers, and considers the weight values and reliability of different classifiers, so that the final fusion result is more reliable and accurate.

The invention relates to a track longitudinal irregularity amplitude value estimation method based on an evidential reasoning rule and belongs to the field of track traffic safe running maintenance. The method includes the steps that frequency domain characteristic signals and a longitudinal irregularity amplitude value of axles and a vehicle body are obtained from a track inspection vehicle; reference values of input characteristics and the irregularity amplitude value are determined, and synthesis similarity distribution of a sample is calculated; a setting point statistical table reflecting the relationship between input and the irregularity amplitude value is established and converted to obtain an evidence matrix table of the input; the reliability of an input information source is confirmed; the evidential reasoning rule is used for fusing evidences activated by the sample input, and the longitudinal irregularity amplitude value is reasoned according to a fusion result; and optimization model training parameters are established, and the track longitudinal irregularity amplitude value of the tested sample can be reasoned on the basis of an optimal parameter set. By the adoption of the method, the track longitudinal irregularity estimated value can be effectively estimated through vibration signals obtained by sensors installed on a common train, cost is low, accuracy is high, and therefore the track longitudinal irregularity amplitude value is monitored in real time.

The invention relates to a parallel system designing and performance optimizing technology of a high-performance computer, in particular to a parallel application performance vulnerability analyzing method and system based on fuzzy rule reasoning. The analyzing method comprises the steps of: firstly, abstracting various conditions causing low efficiency of parallel program performance to obtain a parallel program performance characteristic mode, and constructing a parallel program performance vulnerability characteristic mode reasoning rule base; secondly, extracting trace file characteristics by adopting a reset-based parallel trace analyzing method, and recognizing required characteristics to generate a characteristic file; and finally, introducing a fuzzy mathematical method into production rule definition and reasoning, automatically searching a characteristic mode of an event trace by adopting a fuzzy method-based matching mechanism, realizing matching and finding of the characteristic mode, finding and positioning a parallel program performance vulnerability, and providing aid decision making for the work of further optimizing the performance of the parallel system of the computer. The system mainly comprises a reasoning machine module, a knowledge base, a characteristic extraction module, a synthesis database and a user interface module.

The invention provides an intelligent substation switching operation ticket system. The system comprises a rule base module, a language analysis module, a ticket release safety verification interface, an intelligent reasoning module, an operation ticket production module, a graphic display module and the like. Compared with the existing operation ticket system, the intelligent substation switching operation ticket system provided by the invention has the following characteristics: maintainability: the ticket issue operation process is described by a 'five-prevention' rule descriptive language and is independent of procedures so that the common business personnel can conveniently and dynamically update the 'five-prevention' rule of operation tickets; intellectualization: the 'five-prevention' safety verification rule and the intelligent reasoning rule of the operation tickets can be automatically applied, and the operation tickets can be automatically and intelligently listed according to operation tasks and equipment status before and after ticket issue; and support on off-line operation: the system can support on-off operation ticket tissue operation and meet the requirements of a substation for mobile ticket tissue, ticket tissue in different places and on-off ticket tissue.

The invention relates to the technical field of semantic search and provides a semantic search system for automobile information analysis and service to solve the problems of loss, dislocation and blurring of an original latent semantic meaning in the conventional semantic processing mode. The system comprises an automobile industry ontology base, a demand intelligent matching module, a non-structure and content analyzer, a behavioral semantic meaning preprocessing module, a demand semantic processor, an index processing module and a retrieving module, wherein the automobile industry ontology base is used for supplying automobile industry domain knowledge to the demand intelligent matching module and the demand semantic processor; the demand intelligent matching module is used for matching and recombining data which is in accordance with a standard describing way according to the automobile industry domain knowledge supplied by the ontology base; the non-structure and content analyzer is used for eliminating labels of non-structures and contents to generate an abstract; the behavioral semantic meaning preprocessing module is used for preprocessing semantic information; the demand semantic processor is used for converting data into a relational data format (RDF) and finding a latent relationship between data information by using a reasoning rule; the index processing module is used for collecting, sorting and indexing information resources; and the retrieving module comprises a user interface and a searcher.

An intelligent spatial reasoning method receives a plurality of object sets. A spatial mapping feature learning method uses the plurality of object sets to create at least one salient spatial mapping feature output. It performs spatial reasoning rule learning using the at least one spatial mapping feature to create at least one spatial reasoning rule output. The spatial mapping feature learning method performs a spatial mapping feature set generation step followed by a feature learning step. The spatial mapping feature set is generated by repeated application of spatial correlation between two object sets. The feature learning method consists of a feature selection step and a feature transformation step and the spatial reasoning rule learning method uses the supervised learning method.The spatial reasoning approach of this invention automatically characterizes spatial relations of multiple sets of objects by comprehensive collections of spatial mapping features. Some of the features have clearly understandable physical, structural, or geometrical meanings. Others are statistical characterizations, which may not have clear physical, structural or geometrical meanings when considered individually. A combination of these features, however, could characterize subtle physical, structural or geometrical conditions under practical situations. One key advantage of this invention is the ability to characterize subtle differences numerically using a comprehensive feature set.

The invention discloses a method for realizing a fuzzy PID (Proportion Integration Differentiation) ActiveX control. The method comprises the following steps of: 1, setting a variable, a membership function of the variable, a fuzzy reasoning method and a de-fuzziness method; 2, setting a reasoning rule, determining the fuzzy values of e and ec to obtain accurate values kp, ki and kd after de-fuzzing a PID output variable, and establishing a fuzzy control decision polling list; and 3, compiling a fuzzy PID algorithm through VB (Visual Basic), and creating an ActiveX control. Due to the adoption of the control realizing method disclosed by the invention, the logical operation program of a fuzzy reasoning process is not required to be compiled any more during development, the output values deltaKP, deltaKI and deltakd of the fuzzy adjustment amount of a PID parameter which corresponds to a basic discourse domain are not required to be calculated according to a weighted average method, a program structure is simplified, the program executing period is shortened greatly, and the response speed of a system is increased.

The invention discloses a knowledge discovery device based on path migration of an RDF (Resource Description Framework) picture. The device comprises an input module, a link data RDF module, a reasoning module and an output module. The link data RDF module can perform modeling for link data with multiple conceptions and complicated relationships to construct the RDF picture, migrates by steps inside sub pictures and skip among the sub pictures to find a new path and is combined with the reasoning module to reason new knowledge so as to find more hidden knowledge in mass and complicated link data. The device provided by the invention has wide value in actual application. The invention further discloses a method based on path migration of the RDF picture. The method comprises the steps of: performing RDF modeling for the link data; controlling steps of an intelligent agent in sub pictures and skip among sub pictures while finding new knowledge and updating new RDF pictures according to a knowledge reasoning rule dynamically. Therefore, the method provided by the invention has stronger flexibility and variability.

The invention discloses a decision classification method for fusion reasoning and learning of liquid-based cytological examination, which comprises the following steps: 1) data and ontology preparation: constructing a data set for a decision target and an ontology related to the data, extracting a plurality of associated data features between the data set and the ontology, and taking the associated data features as sub-features of target features; 2) neural network and rule construction: training a neural network set comprising a target feature clustering device and a plurality of sub-featureclassifiers, and constructing an inference rule related to a decision target; and 3) knowledge reasoning and neural network fusion: fusing knowledge reasoning and machine learning to realize knowledgerule reasoning supporting a machine learning result, combining a reasoning result with an evolution method of the machine learning result, and analyzing a processing result. According to the method,two ways of knowledge reasoning and machine learning are fused, the classification accuracy is improved, meanwhile, the result has interpretability through an evolution method, and the reliability ofthe result is gradually improved.

Embodiments of the invention disclose a context distributed reasoning method and device. The method comprises the following steps: obtaining mass of context data in various types from a plurality of computing nodes, and carrying out modeling processing on the obtained context data to obtain a reasoned context set, wherein the expression forms of various contexts in the reasoned context set are uniform and the mass indicates that the scale of the context data achieves a specific data amount; obtaining a reasoning rule which is used for carrying out distributed reasoning on the reasoned context set; analyzing the reasoning rule to generate a reasoning plan of the reasoning rule; carrying out distributed reasoning on the reasoned context set according to the reasoning plan and a pre-configured context reasoning algorithm for the reasoning rule so as to generate a reasoning result of the reasoning plan. According to the method and device disclosed in the invention, the context reasoning efficiency can be improved.

The embodiment of the invention relates to the technical field of image processing, and discloses a verification method and device based on a picture verification code and a computer readable storagemedium. The verification method comprises the following steps: generating and displaying a verification code, wherein the verification code comprises a plurality of verification code pictures respectively representing one number or one letter string, and reasoning rules for reasoning a verification result according to the number or the letter string; wherein each verification code picture comprises a plurality of picture areas arranged according to a position arrangement rule, each picture area represents a number or a letter, and combining the numbers or the letters represented by the pictureareas according to the arrangement rule to obtain a number or a letter string represented by the verification code picture; receiving a verification result input by the user according to the verification code picture and the reasoning rule; and verifying the verification result input by the user. According to the verification method provided by the invention, the complexity and calculation difficulty of the verification code are improved, the verification code is prevented from being identified by a machine, and malicious behaviors such as automatic batch registration are effectively prevented.

The embodiment of the invention provides an information recommendation method and device, electronic equipment and a computer storage medium, and the method comprises the steps: obtaining a first typeof user information for indicating a real-time behavior of a user and a second type of user information for indicating a user demand scene; according to at least one first reasoning rule corresponding to the first type of user information, obtaining at least one piece of corresponding first theme information, and according to at least one second reasoning rule corresponding to the second type ofuser information, obtaining at least one piece of corresponding second theme information; and determining to-be-recommended theme information from the first theme information and the second theme information, and performing information recommendation operation according to the determined theme information. Through the embodiment of the invention, the information recommendation efficiency is improved, and the use experience of the user is also improved.

The invention discloses a building method of an alarm reasoning knowledge base of an intelligent transformer substation. The method comprises the following steps that (1), a protection logic diagram is built according to a matching relation between action signals generated by a protection device and a breaker respectively, the important grade of actions of the protection device, the relation between main protected devices related to the effective protection actions generated by the protection device, and the time sequence relation and time interval relation between the action signals; (2), an intelligent alarm knowledge object is built in an integrated alarm monitoring system, and the protection logic diagram obtained in the step (1) is converted to be the intelligent alarm reasoning knowledge base by adding a reasoning condition object and a reasoning rule object into the intelligent alarm knowledge object. By combining the time sequence relation and the time interval relation generated by the fault phenomenon, different fault reasons finally generating multiple same fault phenomena are distinguished, and the reliability of the fault reasons obtained by reasoning analysis is improved greatly.

The invention relates to establishing a general model of a spatial problem solver by using a constraint satisfaction method. In order to adopt technologies and methods in prior art to better realize spatial constraint problem solving in schema reasoning, the technical scheme adopted by the invention is as follows: a spatial problem solving method based on a constraint satisfaction framework comprises the following steps of: establishing a schema reasoning system structure which includes the following steps that: 1. a schematic sketch is formed by inputted strokes after recognition and normalization, and each pixel of the schematic sketch and spatial relations between each pixel are saved; and 2. for a specific problem, initialization on the schematic sketch is performed according to known conditions, namely, a corresponding valuation operation is performed, and then, a process of reasoning is completed according to reasoning rules, namely a spatial problem is solved, and finally, a solution or a schematic for the problem is acquired; and adopting a specification language to describe space constraint relationships between each pixel. The method in the invention is mainly applied to establishment of a spatial problem solver.

The embodiment of the invention provides a knowledge reasoning method and device based on a knowledge base and electronic equipment, and relates to the technical field of knowledge bases. The knowledge reasoning method based on the knowledge base generates a constraint set serving as a basic unit of the knowledge base according to the obtained conditional probability among multiple event information. As the basic unit in the knowledge base comprises the first event and the second event in the plurality of event information and the conditional probability between the first event and the secondevent, on the premise that the conditional probability corresponding to the basic unit meets the preset requirement, the preset reasoning rule is matched for processing, and from the perspective of information flow logic, the measurability and interpretability of the knowledge reasoning process are higher, so that endless loop is avoided, and the problems of long reasoning time and low efficiencyare avoided.

The invention discloses a vehicle-mounted composite power supply power distribution optimization method. The method comprises the following steps: acquiring the states of charge of a storage battery and a supercapacitor and the required power of a load of an electric vehicle in the running process in real time; determining a value range of a weighting factor of the storage battery power and the supercapacitor power in the power distribution process according to a multiple reasoning rule; establishing a target function, and setting constraint conditions; searching a search space formed by the value range by adopting a double chaotic algorithm to obtain an initial value of the weighting factor; adopting a harmony optimization algorithm to obtain an optimal solution of the weighting factor inthe value range; determining the power required to be provided by the storage battery and the supercapacitor in the current running state; judging whether energy loss exists in the storage battery orthe supercapacitor or not, and if yes, conducting energy exchange according to an energy sharing mechanism, so that the composite power supply can meet the dual requirements of the electric vehicle for energy and power.

The application provides a decision result determining method, device and equipment and a readable storage medium. The method includes the following steps: acquiring at least two candidate answers corresponding to a target question in a target scene; retrieving evidence corpus related to the combination of each candidate answer and the target question in a corpus corresponding to the target scene;acquiring the matching features of the candidate answers and the target problem according to the inclusion of the words of the candidate answers and the target problem in the evidence corpus; and determining a matching answer to the target question from the candidate answers according to the matching features of each candidate answer and the target problem. According to the scheme of the invention, a decision is made directly based on a corpus corresponding to the target scene from the perspective of natural language understanding and reasoning, there is no need for experts to construct and update the relationship between questions and answers in the knowledge base or to summarize reasoning rules. The cost is saved. Moreover, it is ensured that there is no rule conflict in the decision-making process, and the determined decision result is more reliable.

The invention belongs to the technical field of assembly tolerance specification design and computer-aided tolerance design (CAT), and particularly relates to an assembly tolerance specification intelligent design method based on Ontology. The method specifically comprises the following steps: (1) constructing a body of an assembly tolerance specification; (2) establishing an SWRL reasoning rule of an assembly tolerance specification; (3) extracting related tolerance information of the assembly tolerance specification; (4) constructing an assembly tolerance specification instantiation ontologymodel; and (5) combining the Jess inference machine with the SWRL rule, inferring the assembly tolerance specification, and outputting a result inference result. An ontology reasoning knowledge framework for the assembly tolerance specification domain knowledge is constructed by utilizing an ontology, and an assembly tolerance specification knowledge base is expanded according to dominant domainknowledge reasoning implicit knowledge. In combination with a semantic network rule language rule base, reasoning design parameters of assembly tolerance specifications for specific design of geometric products and using environmental conditions. The consistency knowledge description framework of the assembly tolerance specification can be provided, so that a computer can automatically select appropriate tolerance principles, tolerance types, size parameters and the like according to shape and size parameters of geometric products, and a quick and effective method is provided for intelligent design of the assembly tolerance specification.

The invention discloses a subject selection method aiming at scientific research project application, and aims at providing an optimized subject selection method which is simple, and easy to execute and meanwhile, is supported by theories for science researchers interested in applying for various national provincial scientific research projects. The subject selection disclosed by the invention concretely comprises the following steps of calculating relevancy among individual research directions, research contents and all subjects listed in a project application guide; performing statistic analysis on data that department employees apply for each subject in recent years, and calculating data characteristic values; performing fusion calculation on relevancy data and the data characteristic values according to the Bayesian reasoning rule to obtain a recommend weight of each subject; applying for the subject with the maximum recommend weight. The invention provides the effective subject selection method for a scientific research project application process, which can be used for individual project application, or can be used for scientific research management departments to put forward planning and suggestions for department project application.

The invention discloses a multi-entry medical question template device and a method thereof. The multi-entry medical template device is a medical question conversion mechanism based on medical concepts and medical relations, and is characterized in that reasoning rules in a main template structure, a synonymous template structure and a multi-entry combined structure are bound with a reasoning function, so as to realize that multiple synonymous user questions are converted into a multi-entry medical question template, and corresponding answers are extracted from a UMLS medical knowledge base according to the multi-entry medical question template obtained through conversion. The method is designed for solving the problems that in an intelligent information retrieval and automatic question answering system in the medical industry, knowledge and relations are complex, and one question semantic needs to be explained through multiple semantic relations; and meanwhile template design efficiency is improved, and the scale of a template library is reduced, and the question asking intention of the user is met to the maximum extent.

A context aware apparatus is provided. The context aware apparatus includes an extracting unit configured to extract a terminological-box (T-box) from a semantic model, a first generating unit configured to generate a reasoning rule based on the extracted T-box, a second generating unit configured to generate a first assertion-box (A-box) based on sensing information, and a reasoning unit configured to infer a user context based on the reasoning rule and the first A-box.

The invention relates to a track longitudinal irregularity amplitude value estimation method based on an evidential reasoning rule and belongs to the field of track traffic safe running maintenance. The method includes the steps that frequency domain characteristic signals and a longitudinal irregularity amplitude value of axles and a vehicle body are obtained from a track inspection vehicle; reference values of input characteristics and the irregularity amplitude value are determined, and synthesis similarity distribution of a sample is calculated; a setting point statistical table reflecting the relationship between input and the irregularity amplitude value is established and converted to obtain an evidence matrix table of the input; the reliability of an input information source is confirmed; the evidential reasoning rule is used for fusing evidences activated by the sample input, and the longitudinal irregularity amplitude value is reasoned according to a fusion result; and optimization model training parameters are established, and the track longitudinal irregularity amplitude value of the tested sample can be reasoned on the basis of an optimal parameter set. By the adoption of the method, the track longitudinal irregularity estimated value can be effectively estimated through vibration signals obtained by sensors installed on a common train, cost is low, accuracy is high, and therefore the track longitudinal irregularity amplitude value is monitored in real time.

The invention provides a classification device based on machine learning knowledge, and the device comprises a classification rule module used for collecting a classification behavior of a user and deriving a classification reasoning rule; an acquisition module used for acquiring knowledge to be classified; an extraction module used for extracting keyword words in the knowledge content according to a word segmentation method, wherein keyword words comprise keywords and word groups; a calculation processing module used for calculating the occurrence frequency and position of the keyword words and a detection output module used for detecting the keyword words meeting the preset frequency and the preset positions and outputting the keyword words as classification results. Keyword words are extracted in the knowledge contents by adopting a word segmentation method. The nearest neighbor set is established according to the classification behaviors of the user. Comprehensive analysis is carried out in combination with keyword weighting, transformation, mixture, characteristics and meta-level. Keywords of the optimal combination are obtained, accuracy of label classification of knowledge is improved, the retrieval accuracy is improved, and information recommendation and information filtering are facilitated.

The invention provides a gene similarity intrusion detection method based on an electric power network IEC protocol. The method comprises the following steps of carrying out information collection onkey nodes of an electric power monitoring system, performing protocol analysis on the acquired IEC message; establishing three levels of mapping models of behavior, events and relations; solving the relationship aggregation between events through automatic discovery of reasoning rules and depth relationship mining; merging of events, carrying out multi-dimensional relationship association, establishing a power network abnormal behavior gene feature library, discovery hidden attacks through gene similarity comparison based on a mean value and deviation model, achieving active defense of security events through multi-mode combination alarm, and blocking network attacks in real time. Local monitoring system paralysis and out-of-control are prevented, hazard spreading is prevented, and situation development is avoided.