Abstract:
When a second pattern is to be generated by adding an event to a first pattern including events, an extraction program causes a computer to execute the following process based on combinations of events. That is, the extraction program causes the computer to generate the second pattern when the number of occurrence, in the second pattern, of each of the events included in the combinations is not more than a threshold. The extraction program causes the computer to calculate, based on data including a plurality of events, a frequency at which one or more of the generated second patterns occur in the data. The extraction program causes the computer to extract the second pattern having the frequency satisfying a predetermined condition. The extraction program causes the computer to add a new event to the extracted second pattern.
Abstract:
An information processing device including: a storage unit configured to store a first record set including variables of multiple types, and a second record set different from the first record set and including variables of the multiple types; and a processing unit configured to calculate an expected value at which a first variable set representing a combination of variables formed by selecting one variable for each type in the first record set is expected to appear in the second record set, extract the first variable set based on the expected value and the number of records including the first variable set in the second record set, and output at least one of the extracted first variable set and a second variable set, the second variable set representing a combination of variables formed by selecting one or more variables for each type in the second record set.
Abstract:
An extraction program causes a computer to execute a process. The process includes adding an event to a first pattern including the events according to the sequential order, thus generating a second pattern in such a manner that the second pattern is generated by adding the event when a first value is less than a predetermined threshold; when the event is added, adding a predetermined value to the first value, and adding the predetermined value to a second value in a column corresponding to an end of the added event among second values corresponding to respective columns of a table; extracting the second pattern that satisfies a predetermined condition; and when an event in a second or subsequent column in the table is added.
Abstract:
A classification method executed by a computer for classifying a plurality of records into a plurality of groups, the classification method includes: acquiring the plurality of records, the plurality of records including a variable value respectively; tentatively classifying the plurality of records into the plurality of groups; calculating a commonality value indicating a degree of commonality of the variable value among the plurality of groups, based on the variable value included in each of the tentatively classified groups; classifying the plurality of records into the plurality of groups based on the commonality value; and outputting a result of the classifying.
Abstract:
A computing unit obtains a graph including nodes and edges and representing a communication condition at first timing and at second timing and detects an edge that is added between the first and second timing among the edges. The computing unit calculates probabilities of transmitting information from each node to nodes coupled to the added edge, selects a subset of the nodes based on the calculated probabilities, selects nodes included in the subset as the starting points of information, calculates first probabilities of transmitting information from the selected nodes to each node based on the graph obtained at the first timing and second probabilities of transmitting information from the selected nodes to each node based on the graph obtained at the second timing, and detects a change in the communication condition between the first and second timing by comparing the first probabilities with the second probabilities.
Abstract:
According to one aspect, a computer-readable recording medium stores therein an extracting program 330a causing a computer to execute a process. The process includes based on event data obtained by associating a plurality of events stored in a storage unit and an occurrence time of each event, sequentially adding an event to a first pattern obtained by associating the plurality of events and the occurrence order of each event, and sequentially generating a second pattern which includes the first pattern and occurs in the event data; and extracting a pattern which satisfies a predetermined condition from the generated second pattern.
Abstract:
A method for detecting an abnormal transition pattern from a transition pattern includes: first extracting an episode pattern with an appearance frequency greater than or equal to a first frequency from an episode pattern represented with a description form so as to include a first transition pattern and a second transition pattern differing in an order of a part of items from the first transition pattern to have a complementary relation thereto; second extracting a third transition pattern with an appearance frequency greater than or equal to a second frequency from the transition pattern; and specifying a transition pattern other than the third transition pattern from transition patterns included in the extracted episode pattern, and determining an abnormal transition pattern based on the transition pattern specified in the specifying when the third transition pattern includes a fourth transition pattern corresponding to the extracted episode pattern in the first extracting.