Apparatus and method for analyzing characteristic of game player in real time

1. An apparatus for analyzing a characteristic of a game player in real time, comprising:

at least one individual action determiner for calculating a player characteristic value indicating a level or tendency of a game player by giving a first weight to game play data values resulting from game play of the game player;

an accuracy determiner for comparing the player characteristic value and a value set by an administrator, and calculating an accuracy value of the individual action determiner;

a comprehensive level determiner for calculating a final characteristic value indicating a level or tendency of the game player by giving a second weight to the player characteristic values calculated by the individual action determiners when the accuracy value does not exceed a reference value; and

a characteristic value output unit for outputting the final characteristic value.

2. The apparatus of claim 1 , wherein the characteristic value output unit outputs the player characteristic value calculated by the individual action determiner when the accuracy value calculated by the accuracy determiner exceeds the reference value.

3. The apparatus of claim 1 , further comprising a learning processor for inputting a simulation data value to the individual action determiner, controlling the individual action determiner to calculate a result value by giving the first weight to the simulation data value, controlling the accuracy, determiner to compare the result value and a simulation result value and calculate an accuracy value, and setting the individual action determiner to use the first weight when the calculated accuracy value exceeds a previously set value.

4. The apparatus of claim 3 , wherein the learning processor inputs a simulation data value to the comprehensive level determiner, controls the comprehensive level determiner to calculate a result value by giving the second weight to the simulation data value, controls the accuracy determiner to compare the result value and a simulation result value and calculate an accuracy value, and sets the individual action determiner to use the second weight when the calculated accuracy value exceeds a previously set value.

5. The apparatus of claim 1 , wherein the individual action determiner calculates the player characteristic value by normalizing the game play data values or preprocessing the game play data values into an average value.

6. The apparatus of claim 1 , wherein the play data values are at least one of response time values, selected action values, and game environment values of the game player, and

each of the player characteristic value and the final characteristic value of the game player is at least one of a level value indicating a level of the game player and a tendency value indicating a tendency of the game player.

7. The apparatus of claim 1 , wherein the at least one of the individual action determiner and the comprehensive level determiner calculates the player characteristic value or the final characteristic value on the basis of at least one of a neural network, a multilayer perceptron (MLP), a genetic algorithm, a hidden Markov model (HMM), a Markov random field (MRF), a distributed system object model (DSOM), a fuzzy method, an evolution method, and a reinforcement method.

8. A method of analyzing a characteristic of a game player in real time, comprising:

calculating a player characteristic value indicating a level or tendency of a game player by giving a first weight to game play data values resulting from game play of the game player;

comparing the player characteristic value and a value set by an administrator, and calculating an accuracy value;

calculating a final characteristic value indicating a level or tendency of the game player by giving a second weight to the player characteristic values when the accuracy value does not exceed a reference value; and

outputting the final characteristic value.

9. The method of claim 8 , further comprising, before calculating a player characteristic value, setting the first weight or the second weight to be used when a result value calculated by giving the first weight or the second weight to a simulation data value exceeds a previously set value.