44 results about "Event mining" patented technology

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 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 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 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.

According to the digital service information processing method applied to big data mining and the server, the first target session description of the smart service session record triggering the hotspot event attention condition is determined, and the first target session description is combined; obtaining a first significant content mining result of the smart service session record triggering the hotspot event attention condition, performing optimization processing on the first target session description in combination with the first significant content mining result to obtain the first target session description after optimization processing, and based on the first target session description after optimization processing, obtaining a second target session description after optimization processing; and obtaining a first hot event mining result of the smart service session record triggering the hot event attention condition, and enhancing the optimization processing of the significant content, so that the accuracy of performing hot event mining on the smart service session record triggering the hot event attention condition can be improved, and the accuracy of performing hot event mining on the smart service session record triggering the hot event attention condition can be improved. The integrity and the distinction degree of the mined hot events are ensured, and repetition or confusion between different hot events is avoided.

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 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.