Classification apparatus, classification method, and classification program
A classification apparatus that classifies sequential data, in which input communication destinations in a plurality of communications are recorded in order of occurrence of the communications, into a class that has a similar feature. There is a numerical vector calculation unit-configured to calculate numerical vectors that represent characteristics of communication destinations for each of the communication destinations, on the basis of sequential data in which the communication destinations in a plurality of communications are recorded in order of occurrence of the communications, and a classification unit-configured to classify the sequential data into a class that has a similar feature, on the basis of order relation of the communication destinations of the numerical vectors.
1. A classification apparatus comprising:
a memory; and
a processor coupled to the memory and programmed to execute a process comprising:
calculating numerical vectors that represent characteristics of communication destinations for each of the communication destinations, on the basis of sequential data in which the communication destinations in a plurality of communications are recorded in order of occurrence of the communications; and
classifying the sequential data into a class that has a similar feature, on the basis of order relation of the communication destinations of the numerical vectors,
wherein the classifying includes classifying after combining a plurality of the calculated numerical vectors and obtaining a small number of new numerical vectors.
2. The classification apparatus according to claim 1 , wherein the processor is further programmed to execute:
extracting, as the sequential data, the communication destinations of a plurality of successive communications from a log in which the communication destinations and order relation of the communication destinations are recorded.
3. The classification apparatus according to claim 1 , wherein the classifying repeats calculation of new numerical vectors by integrating the plurality of numerical vectors in the sequential data and creation of the small number of numerical vectors by calculating a new value for each of dimensions of the numerical vectors from the plurality of newly-calculated numerical vectors.
4. The classification apparatus according to claim 3 , wherein the classifying selects two numerical vectors from among a plurality of numerical vectors that are included in a predetermined range of the sequential data, and calculates a new numerical vector by integrating the selected two numerical vectors.
5. A classification method implemented by a classification apparatus that classifies sequential data into a class that has a similar feature, the sequential data being data in which input communication destinations in a plurality of communications are recorded in order of occurrence of the communications, the classification method comprising:
a numerical vector calculation step of calculating numerical vectors that represent characteristics of the communication destinations for each of the communication destinations, on the basis of the sequential data; and
a classification step of classifying the sequential data into a class that has a similar feature, on the basis of order relation of the communication destinations of the numerical vectors,
wherein the classification step includes classifying after combining a plurality of the calculated numerical vectors and obtaining a small number of new numerical vectors.
6. A non-transitory computer-readable recording medium having stored therein a classification program for causing a computer to execute a process comprising:
a numerical vector calculation step of calculating numerical vectors that represent characteristics of the communication destinations for each of the communication destinations, on the basis of sequential data in which input communication destinations in a plurality of communications are recorded in order of occurrence of the communications; and
a classification step of classifying the sequential data into a class that has a similar feature, on the basis of order relation of the communication destinations of the numerical vectors,
wherein the classification step includes classifying after combining a plurality of the calculated numerical vectors and obtaining a small number of new numerical vectors.