44 results about "Event mining" patented technology

A method and system for detecting an event from a social stream. The method includes the steps of: receiving a social stream from a social network, where the social stream includes at least one object and the object includes a text, sender information of the text, and recipient information of the text; assigning said object to a cluster based on a similarity value between the object and the clusters; monitoring changes in at least one of the clusters; and triggering an alarm when the changes in at least one of the clusters exceed a first threshold value, where at least one of the steps is carried out using a computer device.

The invention discloses a dynamic legal event map construction method oriented to the legal field, and a dynamic legal event map oriented to the legal field is constructed by utilizing a natural language processing technology. In the prior art, the dynamic legal event map construction method does not appear in the legal field, compared with the prior art, the minimum unit of the dynamic legal event map of the present invention is a legal event rather than an entity, and the constructed map is composed of a relationship between the legal event and the legal event. Compared with the traditionalevent extraction, the knowledge in the constructed dynamic legal event map is dynamic, computable and reasonable instead of a simple extraction event. According to the method, the dynamic legal eventmap oriented to the legal field is constructed, the map is constructed by combining a traditional knowledge map knowledge extraction technology and an event mining technology, and then the legal eventmap metering is carried out by modeling the legal event elements in the legal event map and the relations among the legal events respectively.

The invention discloses a method for microblog hot event online detection based on emotion analysis. According to the method for microblog hot event online detection based on emotion analysis, emotion extraction is conducted on online microblog texts according to emotion analysis, the bursting state of emotions and emotion texts is detected according to the improved Kleinberg algorithm, hot topics are extracted according to an affinity propagation clustering algorithm in the bursting period, so that only a small part of texts with a large amount of effective information participate in event extraction, the data volume is reduced, meanwhile a large amount of data noise is filtered out, and therefore the purpose that online real-time detection of the microblog hot events is achieved.

The invention discloses a method and system for mining Chinese event information. The method includes the steps of defining an event sample model based on the mining requirement, instantiating the event sample model to obtain a seed event, taking the seed event as the foundation of an event mined from an original text, conducting preprocessing on the original text to obtain a candidate template set, conducting information labeling on the seed event, processing the seed event on the basis of labeling information to obtain a seed template set, then, processing the candidate template set through an iterative method according to the grade scores of candidate templates and the semantic similarity between the candidate templates and seed templates so that an event mining anchor set can be obtained, and obtaining the event types corresponding to mining event anchors according to the lexical semantic similarity between each event mining anchor in the event mining anchor set and any seed event anchor in the seed event set. The aim of mining the Chinese event information from the original text can be achieved only by labeling a small amount of samples, namely, the seed events, and the mining cost is reduced.

The invention discloses a news event mining method and device, computer equipment and a storage medium, wherein the method comprises the steps of: acquiring a plurality of news texts; for each news text, according to a semantic vector of each vocabulary in the news text, obtaining a semantic vector of the news text, wherein the semantic vector of each vocabulary carries semantic information of corresponding contexts; according to a similarity among the semantic vectors of the plurality of news texts, carrying out clustering on the plurality of news texts to obtain a plurality of clusters; according to release time distribution of the news texts contained in the plurality of clusters, determining a target cluster from the plurality of clusters; and according to a subject of the news texts contained in the target cluster, determining required news events. By the method, contents of the news texts can be effectively understood and shown in a form of the semantic vectors, and by carrying the semantic information of the corresponding contexts in the semantic vectors of the vocabularies and considering correlation of the contexts among the vocabularies, mining accuracy can be improved.

The invention provides a system and a method for recommending a hot spot area in real time. The system for recommending the hot spot area in real time comprises a server and user equipment, wherein the server comprises a GPS (global positioning system) information extraction module, a real-time data stream clustering module, a hot event mining module, a hot event library and a hot spot regional information integration module, wherein the GPS information extraction module is used for extracting GPS information from the user equipment and / or a picture sharing website; the real-time data stream clustering module is used for receiving the extracted GPS information from the GPS information extraction module and performing real-time data stream clustering on the GPS information, so that a clustering center taken as the hot spot area is obtained; the hot event mining module is used for mining a hot discussed event through an information resource sharing platform and reserving a hot event having territoriality; the hot event library is used for storing the reserved hot event having the territoriality; and the hot spot regional information integration module is used for integrating obtained hot event information and hot scenic spot information and providing the integrated hot spot area information for the user equipment.

The invention provides a method and a device for establishing an event repository. The method comprises the following steps of recognizing a text to make out an event excavation candidate statement; segmenting the recognized event excavation candidate statement to obtain a syntax fragment; generating event knowledge instances according to the syntax fragment and the pre-defined event knowledge structure, wherein the quantity of the event knowledge instances is identical to that of verb-object fragments and subject-predicate fragments contained in the syntax fragment; obtaining the corresponding event excavation target statement according to the verb-object fragments and the subject-predicate fragments contained in the syntax fragment, classifying the components of the obtained event excavation target statement, and writing the classified component into the event knowledge instance so as to complete the establishment of the repository. The event repository can be established through the pre-defined event knowledge structure, an accurate search result can be provided for the users on the basis of the event repository, and the search experience of the user can be improved.

The embodiment of the invention discloses an event generation method based on text information, and the method comprises the steps: obtaining a to-be-processed text information set, and enabling the to-be-processed text information set to comprise N pieces of to-be-processed text information; grouping each piece of to-be-processed text information in the to-be-processed text information set to obtain M text groups, the to-be-processed text information in each text group corresponding to the same word type; carrying out clustering processing on the target text group to obtain a text result cluster, the target text group being any one text group in the M text groups, and each text result cluster comprising at least one keyword; and generating a corresponding first event according to the textresult cluster. The embodiment of the invention further provides an event generation device. According to the embodiment of the invention, on one hand, processing resources and computing resources are saved, the event mining efficiency is improved, and on the other hand, the grouped to-be-processed text information is clustered, so that the event generation accuracy can be effectively enhanced.

The invention discloses an automatic mining system and method of news events in large-scale data. The automatic mining system comprises a receiving module, a clustering processing module, an event merging module and a cache processing module, wherein the receiving module is used for receiving news data pushed to the event mining system in a time slice, and sending the news data accumulated in the previous time slice to the clustering processing module, and the clustering processing module is used for carrying out hierarchical clustering processing of the received news data according to titles of news or the degree of similarity of body texts in order to mine the news group with the same event attribute; and the event merging module is used for the merging processing of new events formed by clustering processing and old news formed in history according to the degree of similarity between the events, and the newly formed events and the modified historical events are sent to the catch module for cache processing. With the system and the method, the massive news data can be automatically mined, and the timeliness and accuracy requirements are met.

The invention relates to an enterprise hot event mining method based on incremental clustering, comprising the following steps: acquiring enterprise network news through a network crawler; de-noisingthe crawled enterprise network news and storing it in the database; reading enterprise news from database for preprocessing; cluster analysis of the preprocessed enterprise news; the centroid news being extracted from the cluster of hot events and stored in the database; obtaning the required enterprise hot spots from the database and exhibit them in chronological order. The present invention canprovide enterprises or individuals with hot events that have occurred in the past.

A method and system for detecting an event from a social stream. The method includes the steps of: receiving a social stream from a social network, where the social stream includes at least one object and the object includes a text, sender information of the text, and recipient information of the text; assigning said object to a cluster based on a similarity value between the object and the clusters; monitoring changes in at least one of the clusters; and triggering an alarm when the changes in at least one of the clusters exceed a first threshold value, where at least one of the steps is carried out using a computer device.

The invention discloses an electric power information system health assessment method and system based on fuzzy reasoning. The method comprises the steps: collecting logs generated in an operation process of an electric power information system, and carrying out preprocessing on the log data; carrying out log information screening and multi-source log fusion by adopting a fuzzy reasoning theory, and analyzing and processing log information generated by different heterogeneous devices; collecting vulnerability log information and operation log information of the electric power information system, and carrying out importance evaluation to acquire a high-risk security event; converting structured log data and unstructured log data based on a log event mining technology; and by constructing ahierarchical structure, determining the membership relationship of element arrows of a hierarchical layer, carrying out consistency check on single criterion sorting of each layer, formulating a system health assessment index value, and carrying out health assessment of the electric power information system.

The invention discloses a system and method for mining hot words and events in social network, and relates to the field of social network. The method comprises counting candidate words to obtain a corresponding candidate words sequence; calculating the state parameter of the candidate words at different time points according to the candidate words sequence; providing an alternative state sequence, and calculating the state generate cost of the candidate words according to the candidate words sequence, the state parameter and the alternative state sequence; calculating the state transfer cost of the candidate words according to the alternative state sequence; and screening the alternative state sequence according to the candidate words sequence, the state parameter, the state generation cost and the state transfer cost to obtain a state sequence with the lowest total cost. The system and method provided by the invention can improve the hot words mining accuracy.

The embodiment of the invention provides a method and system for ship affiliation event mining based on port multi-layer areas. The method comprises: obtaining first position information of a port to be mined, creating an index mapping table according to the first position information, wherein the port to be mined comprises multi-layer areas; obtaining second position information of ships in a preset time period, and constructing the area arrival and departure event set of the multi-layer areas according to the second position information and the index mapping table; and according to the area arrival and departure event set, employing the greedy algorithm to calculate and obtain the ship affiliation information at the multi-layer areas. The system is applied to the method. According to the embodiment of the invention, the index mapping table is created according to the first position information, the area arrival and departure event set of the multi-layer areas is constructed according to the second position information and the index mapping table, the ship affiliation information at the multi-layer areas is obtained through adoption of the greedy algorithm according to the area arrival and departure event set so as to calculate the work time and the navigation details of ships in the port.

The invention discloses indexed security measurement system and device based on power information network security event mining. The method and device are characterized in that the power information network heterogeneous security events are acquired on real time and normalized through a pre-defined template; the real-time data of index parameters Vk of the normalized standard safety events are acquired on real time, and the measurement value Ei of the dimension parameter Di and the whole network security measurement index H can be obtained according to the data. According to the method and device, the pre-defined security measurement strategy can be performed for adapting to complex network demand; an automatic, indexed and intelligent security measurement system is created based on the real-time characteristic and comprehensiveness of the security event data, and therefore, network security state and effectiveness can be accurately evaluated.

The invention discloses a relational network construction method and device and a computer readable storage medium. The method comprises the steps of obtaining data required for constructing a relational network; mapping the data to at least one of the following spaces: an absolute space, an administrative division space and a point location space, the absolute space comprising latitude and longitude position information corresponding to the data, the administrative division space comprising administrative region position information corresponding to the data, and the point location space comprising position information of a relatively preset reference object corresponding to the data; and extracting an operator according to a preset relationship, and extracting a relationship in the mapped spatial data. Data is mapped to at least one of the following spaces: space of at least one of data and space of at least one of the following spaces. Compared with the prior art, the method has theadvantages that multi-source data processing is effectively realized through the basic event mining, the joint query of multiple event relations can be provided, the relation construction efficiencyis improved, and the method is convenient for constructing a large-scale relation rule system suitable for a multi-source scene.

The invention discloses an event mining method and an event mining device for an interest point. The method comprises the steps that a plurality of pieces of information are acquired, the informationis screened according to a preset event verb set, and the preset event verb set comprises a plurality of event verbs. Interest point event sentences are extracted from the screened information, and interest points and events corresponding to the interest points are extracted from the interest point event sentences. Therefore, the interest points and the events corresponding to the interest pointsare captured from the information, the efficiency and accuracy of event mining are improved, and the technical problems that in the prior art, the accuracy of event mining is low, and events cannot bemined in mass information are solved.

The present invention discloses a topic mining based event cluster acquisition method. The method comprises the following steps: S1, collecting a text data set C; S2, preprocessing the text data set C, and removing meaningless words from the text data set; S3: setting the number n of topics and a parameter, running CTM to obtain a CTM model; S4, in a covariance matrix sigma indicating an association degree between topics of the CTM model, searching for all maximum clusters by using a backtracking algorithm, wherein the maximum clusters are topic clusters; and S5, for each topic comprised in each topic cluster, selecting a most corresponding article from the text data set C, and clustering events corresponding to the most corresponding article to form an event cluster. The method provided by the present invention has the following advantages: association degree information at the topic level is used during association degree analysis, and compared with the traditional technology in which association degree information is mined and used at the word level, the method provided by the present invention can better improve rationality in calculating an event association degree.

The invention relates to a micro-blog hot event mining method, belonging to the technical field of data processing. Firstly, the micro-blog data is crawled and the micro-blog database is established.Then preprocessing the crawled micro-blog data; Then the pre-processed micro-blog data is identified by named entity recognition. Then, according to the results of preprocessing and named entity recognition, the entities and event triggers of micro-blog data are extracted to determine the events expressed by each micro-blog, and finally, similarity between micro-blogs is calculated, similarity results are analyzed, publisher information and publishing time are obtained, and micro-blog hot events are obtained. As compare with that prior art, This method mainly solves the problem of lacking a large number of complete training corpus in the pre-processing process of micro-blog and the non-standardization of the naming entity recognition link, which will lead to a large error in the process ofentity recognition, so that the accuracy of micro-blog event extraction is low, in order to improve the efficiency of micro-blog hotspot event mining.

The invention relates to the field of natural language processing, in particular to a public opinion event mining method and system. The method comprises the following steps of constructing an event ontology corresponding to each preset event type in at least one preset event type; analyzing each event ontology to generate a rule representation corresponding to each event ontology; and obtaining ato-be-mined text, and mining the to-be-mined text according to the rule representation corresponding to each event ontology to obtain at least one target preset event type contained in the to-be-mined text. The tagging of massive data is avoided; the influence of word segmentation on event mining is avoided; and the spreading of automatic word segmentation errors is prevented. A user can maintainthe event ontology as needed, so that the applicability, mining efficiency and mining accuracy of the public opinion event mining method are improved.

The present invention discloses a method for constructing a dynamic legal event map oriented to the legal field. The present invention uses natural language processing technology to construct a dynamic legal event map oriented to the legal field. The method for constructing a dynamic legal event map has not yet appeared in the legal field; and Compared with the prior art, the smallest unit of the dynamic legal event map in the present invention is a legal event rather than an entity, and the constructed map is composed of legal events and the relationship between legal events; compared with traditional event extraction, the present invention The knowledge in the constructed dynamic legal event graph is dynamic, computable, and deducible, rather than simply extracting events. The present invention constructs a dynamic legal event map oriented to the legal field, combines the traditional knowledge map knowledge extraction technology and event mining technology to construct the map, and then models the legal event elements and the relationship between legal events in the legal event map Perform legal event graph measurement.

The invention discloses a public security event-based mobile cloud data mining method. The method comprises the steps of S1: selecting a mobile network cloud public social application platform, namely, according to a usage amount of a user, selecting the mobile network cloud public social application platform; S2: massively mining public security hot events, setting a time point based on data of the selected mobile network cloud public social application platform, and extracting data of three dimensions of a forwarding amount (T), a concerning amount (G) and a rating amount (C) of public security event information before the time point; S3: calculating popularity attenuation factors of the public security hot events, and by reference to and based on a Newton cooling law, generating the popularity attenuation factors of the three dimensions of each time period of the events; S4: cleaning the public security hot events, performing sigma 1, sigma 2 and sigma 3 setting on investigated weights of the data of the three dimensions, and obtaining current popularity factors of the event information; and S5: fusing public security hot event mining data, constructing or updating a database bythe events with the popularity factors higher than a threshold, and additionally attaching event keyword fields in a data storage process to serve as data mining results for the user to use. The public security event-based mobile cloud event hot data information mining is realized; an interface can be provided for a public security management related application; and the security event identification acuity is improved.

The invention provides a network node semantic information mining method and device, a storage medium and electronic equipment, and relates to the technical field of network node semantic information mining. According to the technical scheme, the weighted undirected network between the enterprises is constructed based on the enterprise text data, and the negative event mapping function is constructed by using the rule-based event mining algorithm and the time decay function, so that the enterprise negative event information is mined, and mining node semantic information of the weighted undirected network by using an improved PageRank algorithm and negative event information. According to the method, the influence of human subjectivity on a network node semantic information mining process is avoided, manual operation is replaced by a computer and a corresponding algorithm, the problems of low efficiency and high cost during data processing are avoided, and a network node semantic information mining result is more objective, accurate, real and effective.

The invention discloses an event mining method and device. According to the method, a plurality of reference texts can be extracted from a text data set; event classification is carried out on the reference texts to obtain an event text set, wherein the event text set comprises reference texts associated with a target event; clustering processing is carried out on reference texts in the event textset to obtain a clustered text set corresponding to sub-events, wherein the sub-events belong to the target event; a mapping relationship between the text quantity of a target text in the text data set and the search time of the target text is analyzed to obtain an analysis result, wherein the target text is a text belonging to the sub-event in the text data set; and periodic discrimination is performed on the sub-events based on the analysis result, and a periodic discrimination result is output. According to the method, automatic mining of periodic events can be realized, the accuracy of event mining results is improved, and the mining efficiency can also be improved.

The invention discloses a hot event mining method based on a large-scale knowledge base. The method is characterized by including the steps of based on data acquired through the internet, automatically establishing a text-understanding-oriented large-scale knowledge base, and allowing for automatic optimization and knowledge updating of the base; based on the large-scale knowledge base, performing structural information extraction on short texts to be detected, sorting the short texts to be detected, according to extracted structural information, and screening out corresponding event texts; based on the large-scale knowledge base, clustering the screened event texts to screen out hot events. The method has the advantages that structural knowledge representation is automatically extracted from the internet, structural tuple representation is established for semantic relation between instances and concepts, a knowledge back-tracking mode is provided, and accuracy in extraction of structural information from short texts is improved.

The embodiment of the invention provides a method and system for ship affiliation event mining based on port multi-layer areas. The method comprises: obtaining first position information of a port to be mined, creating an index mapping table according to the first position information, wherein the port to be mined comprises multi-layer areas; obtaining second position information of ships in a preset time period, and constructing the area arrival and departure event set of the multi-layer areas according to the second position information and the index mapping table; and according to the area arrival and departure event set, employing the greedy algorithm to calculate and obtain the ship affiliation information at the multi-layer areas. The system is applied to the method. According to the embodiment of the invention, the index mapping table is created according to the first position information, the area arrival and departure event set of the multi-layer areas is constructed according to the second position information and the index mapping table, the ship affiliation information at the multi-layer areas is obtained through adoption of the greedy algorithm according to the area arrival and departure event set so as to calculate the work time and the navigation details of ships in the port.

The invention provides a hot event mining method and device, equipment and a medium, and relates to the technical field of data processing, in particular to the technical field of big data and artificial intelligence. According to the implementation scheme, a plurality of original documents are obtained; for each original document, obtaining at least one keyword included in the original document; obtaining at least one keyword frequent item set based on a plurality of keywords respectively included in the plurality of original documents; determining a plurality of primarily screened documents from the plurality of original documents based on at least one keyword frequent item set; constructing an event graph at least based on a plurality of keywords included in each of the plurality of primarily screened documents; obtaining at least one event cluster based on the event graph; and determining a hot event list based on the at least one event cluster.

The invention provides a system and a method for recommending a hot spot area in real time. The system for recommending the hot spot area in real time comprises a server and user equipment, wherein the server comprises a GPS (global positioning system) information extraction module, a real-time data stream clustering module, a hot event mining module, a hot event library and a hot spot regional information integration module, wherein the GPS information extraction module is used for extracting GPS information from the user equipment and / or a picture sharing website; the real-time data stream clustering module is used for receiving the extracted GPS information from the GPS information extraction module and performing real-time data stream clustering on the GPS information, so that a clustering center taken as the hot spot area is obtained; the hot event mining module is used for mining a hot discussed event through an information resource sharing platform and reserving a hot event having territoriality; the hot event library is used for storing the reserved hot event having the territoriality; and the hot spot regional information integration module is used for integrating obtained hot event information and hot scenic spot information and providing the integrated hot spot area information for the user equipment.

The invention discloses a system and method for mining hot words and events in social network, and relates to the field of social network. The method comprises counting candidate words to obtain a corresponding candidate words sequence; calculating the state parameter of the candidate words at different time points according to the candidate words sequence; providing an alternative state sequence, and calculating the state generate cost of the candidate words according to the candidate words sequence, the state parameter and the alternative state sequence; calculating the state transfer cost of the candidate words according to the alternative state sequence; and screening the alternative state sequence according to the candidate words sequence, the state parameter, the state generation cost and the state transfer cost to obtain a state sequence with the lowest total cost. The system and method provided by the invention can improve the hot words mining accuracy.