1. A system for generating a robot genome, the system comprising:
a user preference input unit for receiving user preferences from a user, the user preferences including internal state attribute preferences of internal state attributes according to external stimuli and behavior preferences distinguished according to the internal state attributes;
an initial value generator for generating a robot genome group including a plurality of robot genomes containing initial values of internal state related genes generated by reflecting the internal state attribute preferences, initial values of behavior decision related genes generated by reflecting the behavior preferences, and initial values of essential element related genes determined according to conditions;
a masking unit for performing a masking process of determining internal state related genes and behavior decision related genes manifested with respect to external stimuli and manifested behaviors from among the genes by applying a masking table to each of the plurality of robot genomes, and determining whether manifestation attributes of the genes determined to manifest are positive or negative;
a manifestation unit for manifesting each of the robot genomes according to a stimulus scenario for testing whether the robot genomes are suitable for the input user preferences, and performing processing of manifestation results according to the stimulus scenario;
a suitability determiner for receiving the manifestation results according to the stimulus scenario, determining a reliability value of each robot genome, and determining whether reliability values of according to manifestation results of robot genomes extracted from the robot genome group are suitable for the user preferences;
a modification unit for modifying the input robot genomes according to a modification method when the extracted robot genomes are input; and
a controller for determining according to a determination result of the suitability determiner whether the extracted robot genomes are modified or one of the extracted robot genomes is output, and controlling the modification unit to modify the extracted robot genomes when the extracted robot genomes are determined to be modified, controlling the initial value generator to generate a new robot genome group including a plurality of new robot genomes in which the internal state attribute preferences and the behavior preferences are reflected and the modified robot genomes, controlling the masking unit and the manifestation unit to perform the masking process and the manifestation process for the new robot genome group again, and transmitting robot genomes according to a re-performing result of the manifestation process to the suitability determiner.
2. The system of claim 1, further comprising a stimulus scenario generator for generating a stimulus scenario containing types of stimuli contained according to the selection of the user, a manifestation frequency of each stimulus, and a lasting time of each stimulus.
3. The system of claim 1, wherein the initial value generator calculates the initial values of the internal state related genes by differently applying control constants to the internal state attribute preferences according to a masking table corresponding to each robot genome and calculates the initial values of the behavior decision related genes by applying a control constant to the behavior preferences.
4. The system of claim 3, wherein the initial values of the internal state related genes according to the internal state attribute preferences are determined using equation
x
qk
I
\ue89e
\ue89e
0
=
U
\ue8a0
0
,
I
max
\ue89e
\u03bb
qk
I
\u03bb
qk
I
=
{
\u03c8
qk
l
\u03bb
c
\ue89e
\ue89e
1
l
,
if
\ue89e
\ue89e
m
qk
l
\u2265
0
\u03bb
c
\ue89e
\ue89e
2
I
\u03c8
qk
I
,
if
\ue89e
\ue89e
m
qk
l
<
0
,
where \u03c8qkI denotes a user preference value input with respect to a current internal state attribute, \u03bbc1I and \u03bbc2I denote control constants to a specific external stimulus, mqkI denotes a masking table value corresponding to the specific external stimulus and the internal state attribute, xqkI0 denotes an initial value of an internal state related gene according to the specific external stimulus, and Imax denotes a maximum value of the initial value xqkI0, which can be set.
5. The system of claim 3, wherein the initial values of the behavior decision related genes according to the behavior preferences are determined using equation
x
rk
B
\ue89e
\ue89e
0
=
U
\ue8a0
0
,
B
max
\ue89e
\u03bb
rk
B
,
0
<
\u03bb
rk
B
\u2264
1
\u03bb
rk
B
=
\u03c8
rk
B
\u03bb
c
B
,
where \u03c8rkB denotes a behavior preference value with respect to a current internal state attribute, \u03bbcB denotes a constant to a specifically manifested behavior, xrkB0 denotes an initial value of a behavior decision related gene according to the specifically manifested behavior, and Bmax denotes a maximum value of the initial value xrkB0, which can be set.
6. The system of claim 1, wherein in the masking table, each internal state attribute of the robot genome has a masking value of 0 when the internal state attribute is not manifested according to specific external stimuli and specifically manifested behaviors, or +1 or \u22121 when the internal state attribute is manifested according to any of specific external stimuli and specifically manifested behaviors.
7. The system of claim 6, wherein the masking values are experientially set according to customary values generally acknowledged by social members.
8. The system of claim 6, wherein the masking values can be arbitrarily modified according to the user’s selection.
9. The system of claim 1, wherein the suitability determiner calculates an internal state attribute occupancy ratio, which is a ratio of an integral value of each internal state attribute to a sum of integral values of all internal state attributes, and an internal state attribute-based behavior manifestation count occupancy ratio, which is a ratio of a number of behavior manifestations classified for each internal state attribute to a sum of numbers of behavior manifestations classified for all internal state attributes, during the stimulus scenario with respect to a manifestation result of each robot genome,
calculates an internal state attribute preference gain, which is a ratio of an internal state attribute preference according to a specific internal state attribute to a sum of the internal state attribute preferences, for each internal state attribute,
calculates a behavior preference gain, which is a ratio of a behavior preference according to a specific internal state attribute to a sum of the behavior preferences, for each internal state attribute,
calculates an absolute value of a difference between an internal state attribute preference gain and an internal state attribute occupancy ratio corresponding to the internal state attribute preference gain, for each internal state attribute,
calculates an absolute value of a difference between a behavior preference gain and an internal state attribute-based behavior manifestation count occupancy ratio corresponding to the behavior preference gain, for each internal state attribute,
calculates a sum of all the absolute values as the reliability value, and determines based on the reliability value whether the robot genome is suitable for the user preferences.
10. The system of claim 9, wherein the internal state attribute preference gain is determined using equation
\u03d5
k
I
=
\u03c8
k
I
\u2211
l
=
1
14
\ue89e
\u03c8
l
I
,
where \u03c6kI denotes an internal state attribute preference gain of a kth internal state, \u03c8kI denotes an internal state attribute preference of the kth internal state, and
\u2211
l
=
1
14
\ue89e
\u03c8
l
I
denotes a sum of all internal state attribute preferences.
11. The system of claim 9, wherein the behavior preference gain is determined using equation
\u03d5
k
B
=
\u03c8
k
B
\u2211
l
=
1
14
\ue89e
\u03c8
l
B
,
where \u03c6kB denotes a behavior preference gain of a kth internal state, \u03c8kB denotes a behavior preference of the kth internal state, and
\u2211
l
=
1
14
\ue89e
\u03c8
l
B
denotes a sum of all behavior preferences.
12. The system of claim 9, wherein the suitability determiner classifies the internal state attributes according to types, calculates a sum of absolute values of a difference between an internal state attribute preference gain and an internal state attribute occupancy ratio of each of state attributes for each type of the internal state attributes, calculates a sum of absolute values of a difference between a behavior preference gain and an internal state attribute-based behavior manifestation count occupancy ratio for each internal state attribute, calculates a reliability value using the sums, and determines whether the extracted robot genomes are suitable for the user preferences.
13. The system of claim 12, wherein the suitability determiner calculates a reliability value and determines whether the extracted robot genomes are suitable for the user preferences using equation
\u03a6
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
=
C
–
\u03c1
\u2211
k
=
1
6
\ue89e
(
1
\u03d5
k
I
)
\ue89e
\uf603
\u03d5
k
I
–
\u03a6
pk
M
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
+
\u2211
k
=
7
9
\ue89e
(
1
\u03d5
k
I
)
\ue89e
\uf603
\u03d5
k
I
–
\u03a6
pk
H
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
+
\u2211
k
=
10
14
\ue89e
(
1
\u03d5
k
I
)
\ue89e
\uf603
\u03d5
k
I
–
\u03a6
pk
E
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
+
\u2211
k
=
1
14
\ue89e
(
1
\u03d5
k
B
)
\ue89e
\uf603
\u03d5
k
B
–
\u03a6
fk
BG
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
,
where 1\u03c6kI denotes a weight of a kth internal state and a value to expedite the convergence of an occupancy ratio of a kth internal state integral value, C denotes a suitability constant, \u03c1 denotes a scaling factor for a percentage calculation,
\u2211
k
=
1
6
\ue89e
(
1
\u03d5
k
I
)
\ue89e
\uf603
\u03d5
k
I
–
\u03a6
p
\ue89e
\ue89e
k
M
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
is used to obtain a sum of absolute values of a difference between an internal state attribute preference gain and an internal state attribute occupancy ratio of each of internal states corresponding to \u2018motivation\u2019 among all internal state attributes, \u2003kI denotes an internal state attribute preference gain of a kth internal state attribute among the internal state attributes belonging to \u2018motivation\u2019, \u03a6pkM(j\u0394T,g) denotes an internal state attribute occupancy ratio of a kth internal state among the internal state attributes belonging to \u2018motivation\u2019,
\u2211
k
=
7
9
\ue89e
(
1
\u03d5
k
I
)
\ue89e
\uf603
\u03d5
k
I
–
\u03a6
pk
H
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
is used to obtain a sum of absolute values of a difference between an internal state attribute preference gain and an internal state attribute occupancy ratio of each of internal states corresponding to \u2018homeostasis\u2019 among all internal state attributes, \u03c6kI denotes an internal state attribute preference gain of a kth internal state attribute among the internal state attributes belonging to \u2018homeostasis\u2019, \u03a6pkH(j\u0394T,g) denotes an internal state attribute occupancy ratio of the kth internal state among the internal state attributes belonging to \u2018homeostasis\u2019,
\u2211
k
=
10
14
\ue89e
(
1
\u03d5
k
I
)
\ue89e
\uf603
\u03d5
k
I
–
\u03a6
p
\ue89e
\ue89e
k
E
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
is used to obtain a sum of absolute values of a difference between an internal state attribute preference gain and an internal state attribute occupancy ratio of each of internal states corresponding to \u2018emotion\u2019 among all internal state attributes, \u03c6kI denotes an internal state attribute preference gain of a kth internal state attribute among the internal state attributes belonging to \u2018emotion\u2019, \u03a6pkE(j\u0394T,g) denotes an internal state attribute occupancy ratio of the kth internal state among the internal state attributes belonging to \u2018emotion\u2019,
\u2211
k
=
1
14
\ue89e
(
1
\u03d5
k
B
)
\ue89e
\uf603
\u03d5
k
B
–
\u03a6
fk
BG
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
is used to obtain a sum of absolute values of a difference between a behavior preference gain and an internal state attribute-based behavior manifestation count occupancy ratio, for each internal state attribute, \u03c6kB denotes a behavior preference gain classified for a kth internal state attribute among the internal state attributes, and \u03a6fkBG(j\u0394T,g) denotes an internal state attribute-based behavior manifestation count occupancy ratio of the kth internal state among the internal state attributes.
14. The system of claim 1, wherein the suitability determiner extracts a pre-number of robot genomes from among the robot genomes according to reliability values and determines whether the extracted robot genomes are suitable for the user preferences according to whether reliability values of the extracted robot genomes are within a reliable range.
15. The system of claim 14, wherein the suitability determiner determines whether all the reliability values of the extracted robot genomes are within the reliable range or whether a representative value of the reliability values of the extracted robot genomes is within the reliable range.
16. The system of claim 1, wherein the modification unit modifies the input robot genomes are modified using an arbitrary learning algorithm.
17. The system of claim 16, wherein the learning algorithm includes one of mutation calculation, general crossover calculation, independent crossover calculation, uniform crossover calculation, and building crossover calculation.
18. The system of claim 17, wherein the mutation calculation is a modification method in which at least one of the genes of a currently selected robot genome is modified to an arbitrary value.
19. The system of claim 17, wherein the general crossover calculation is a modification method in which a currently selected robot genome is modified by exchanging essential element related genes, internal state related genes, and behavior decision related genes according to a specific internal state with another robot genome.
20. The system of claim 17, wherein the independent crossover calculation is a modification method in which a currently selected robot genome is modified by independently exchanging essential element related genes, internal state related genes, and behavior decision related genes according to a specific internal state with another robot genome.
21. The system of claim 17, wherein the uniform crossover calculation is a modification method in which a currently selected robot genome is modified by independently exchanging specific essential element related genes, specific internal state related genes, and specific behavior decision related genes with another robot genome regardless of internal states.
22. The system of claim 17, wherein the building crossover calculation is a modification method in which a currently selected robot genome is modified by exchanging specific essential element related genes, specific internal state related genes, and specific behavior decision related genes with another robot genome in an aggregate manner according to a plurality of internal states.
23. The system of claim 17, wherein the modification unit iteratively modifies at least one of the input robot genomes using the evolution calculation or the neural network calculation a number of times.
24. A method of generating robot genome, the method comprising:
a user preference receiving process, wherein user preferences are received from a user, the user preferences including internal state attribute preferences of internal state attributes according to external stimuli and behavior preferences distinguished according to the internal state attributes;
a robot genome group generating process, wherein a robot genome group is generated, the robot genome group including a plurality of robot genomes containing initial values of internal state related genes generated by reflecting the internal state attribute preferences, initial values of behavior decision related genes generated by reflecting the behavior preferences, and initial values of essential element related genes determined according to conditions;
a masking process, wherein internal state related genes and behavior decision related genes manifested with respect to external stimuli and manifested behaviors are determined from among the genes by applying a masking table to each of the plurality of robot genomes, and a determination is made whether manifestation attributes of the genes determined to manifest are positive or negative;
a manifesting process, wherein each of the robot genomes is manifested according to a stimulus scenario for testing whether the robot genomes are suitable for the input user preferences, and manifestation results of the robot genomes according to the stimulus scenario are output;
a suitability determining process, wherein a reliability value of each robot genome is determined by receiving the manifestation results according to the stimulus scenario and the robot genomes, and a determination is made whether reliability values of robot genomes extracted from the robot genome group are suitable for the user preferences;
a modifying process, wherein the extracted robot genomes are modified according to a modification method when the reliability values of the extracted robot genomes are not suitable for the user preferences according to a determination result in the suitability determining process;
a secondary robot genome group generating process, wherein a new robot genome group is generated, which includes a plurality of new robot genomes in which the internal state attribute preferences and the behavior preferences are reflected and the modified robot genomes; and
an iterating process, wherein the masking process, the manifesting process, and the suitability determining process are iteratively performed for the secondary robot genome group, and the modifying process and the secondary robot genome group generating process are iteratively performed according to a result in the suitability determining process.
25. The method of claim 24, wherein the user preference receiving process comprises:
generating a Graphic User Interface (GUI) containing an input menu for receiving the internal state attribute preferences and an input menu for receiving the behavior preferences; and
receiving the internal state attribute preferences and the behavior preferences using the GUI.
26. The method of claim 24, wherein the robot genome group generating process comprises:
an initial value setting process, wherein the initial values of the internal state related genes, which are parameters of internal state attributes with respect to external stimuli, and the initial values of the behavior decision related genes, which are parameters of internal state attributes with respect to manifested behaviors, are set according to the internal state attribute preferences and the behavior preferences;
an essential element related gene generating process, wherein the initial values of the essential element related genes, which are parameters of essential elements related to the internal state attributes, are set;
a robot genome generating process, wherein a robot genome containing the internal state related genes, the behavior decision related genes, and the essential element related genes is generated; and
an iterative robot genome generating process, wherein a determination is made whether the number of currently generated robot genomes is a particular number, and the initial value setting process, the essential element related gene generating process, and the robot genome generating process are iteratively performed when the number of currently generated robot genomes is less than the particular number.
27. The method of claim 24, wherein the masking process comprises each gene of each of the robot genomes included in the robot genome group is multiplied by a corresponding value of a masking table.
28. The method of claim 27, wherein in the masking table, each internal state attribute of the robot genome has a masking value of 0 when the internal state attribute is not manifested according to specific external stimuli and specifically manifested behaviors, or +1 or \u22121 when the internal state attribute is manifested according to any of specific external stimuli and specifically manifested behaviors.
29. The method of claim 28, wherein the masking values are experientially set according to customary values generally acknowledged by social members.
30. The method of claim 24, wherein the manifesting process comprises:
a stimulus scenario setting loading process, wherein one of stimulus scenarios is loaded; and
a robot genome manifesting process, wherein each of the robot genomes included in the robot genome group is manifested according to settings of the loaded stimulus scenario.
31. The method of claim 30, wherein the stimulus scenario setting loading process comprises:
a stimulus scenario generation window displaying process, wherein when the user selects generation of a stimulus scenario, displaying a stimulus scenario generation window;
a stimulus scenario setting process, wherein settings of the stimulus scenario are modified according to setting values input by the user by means of the stimulus scenario generation window; and
a loading process, wherein the stimulus scenario modified by the user is loaded.
32. The method of claim 31, wherein the stimulus scenario generation window contains a menu for setting types of stimuli contained in the stimulus scenario, a manifestation frequency of each stimulus, and a lasting time of each stimulus.
33. The method of claim 24, wherein the suitability determining process further comprises an outputting process, wherein one of the extracted robot genomes is output when the reliability values of the extracted robot genomes are suitable for the user preferences.
34. The method of claim 24, wherein the suitability determining process comprises:
an internal state attribute occupancy ratio calculating process, wherein an internal state attribute occupancy ratio, which is a ratio of an integral value of each internal state attribute to a sum of integral values of all internal state attributes during the stimulus scenario, is calculated with respect to a manifestation result of each robot genome;
a behavior manifestation count occupancy ratio calculating process, wherein an internal state attribute-based behavior manifestation count occupancy ratio, which is a ratio of a number of behavior manifestations classified for each internal state attribute to a sum of numbers of behavior manifestations classified for all internal state attributes during the stimulus scenario, is calculated with respect to a manifestation result of each robot genome;
an internal state attribute preference gain calculating process, wherein an internal state attribute preference gain, which is a ratio of an internal state attribute preference according to a specific internal state attribute to a sum of the internal state attribute preferences, is calculated for each internal state attribute;
a behavior preference gain calculating process, wherein a behavior preference gain, which is a ratio of a behavior preference according to a specific internal state attribute to a sum of the behavior preferences, is calculated for each internal state attribute;
a reliability value calculating process, wherein an absolute value of a difference between an internal state attribute preference gain and an internal state attribute occupancy ratio corresponding to the internal state attribute preference gain, is calculated for each internal state attribute, an absolute value of a difference between a behavior preference gain and an internal state attribute-based behavior manifestation count occupancy ratio corresponding to the behavior preference gain, is calculated for each internal state attribute, and a reliability value of each robot genome is calculated by adding all the absolute values;
a robot genome extracting process, wherein a number of robot genomes are extracted using the calculated reliability values; and
a determining process, wherein a determination is made whether reliability values of the extracted robot genomes are suitable for the user preferences.
35. The method of claim 34, wherein the internal state attribute preference gain is determined by the equation
\u03d5
k
I
=
\u03c8
k
I
\u2211
l
=
1
14
\ue89e
\u03c8
l
I
,
where \u03c6kI denotes an internal state attribute preference gain of a kth internal state, \u03c8kI denotes an internal state attribute preference of the kth internal state, and
\u2211
l
=
1
14
\ue89e
\u03c8
l
I
denotes a sum of all internal state attribute preferences.
36. The method of claim 34, wherein the behavior preference gain is determined by the equation
\u03d5
k
B
=
\u03c8
k
B
\u2211
l
=
1
14
\ue89e
\u03c8
l
B
,
where \u03c6kB denotes a behavior preference gain of a kth internal state, \u03c8kB denotes a behavior preference of the kth internal state, and
\u2211
l
=
1
14
\ue89e
\u03c8
l
B
denotes a sum of all behavior preferences.
37. The method of claim 34, wherein the suitability determining process comprises:
an internal state type classifying process, wherein the internal state attributes are classified according to types;
an internal state attribute type adding process, wherein a sum of absolute values of a difference between an internal state attribute preference gain and an internal state attribute occupancy ratio of each of state attributes is calculated for each type of the internal state attributes;
a behavior manifestation adding process, wherein a sum of absolute values of a difference between a behavior preference gain and an internal state attribute-based behavior manifestation count occupancy ratio is calculated for each internal state attribute; and
a calculating process, wherein a reliability value is calculated by adding the addition result of the internal state attribute type adding process and the addition result of the behavior manifestation adding process.
38. The method of claim 37, wherein the suitability determining process comprises calculating a reliability value and determining whether the extracted robot genomes are suitable for the user preferences using equation
\u03a6
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
=
C
–
\u03c1
\u2211
k
=
1
6
\ue89e
(
1
\u03d5
k
I
)
\ue89e
\uf603
\u03d5
k
I
–
\u03a6
pk
M
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
+
\u2211
k
=
7
9
\ue89e
(
1
\u03d5
k
I
)
\ue89e
\uf603
\u03d5
k
I
–
\u03a6
pk
H
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
+
\u2211
k
=
10
14
\ue89e
(
1
\u03d5
k
I
)
\ue89e
\uf603
\u03d5
k
I
–
\u03a6
pk
E
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
+
\u2211
k
=
1
14
\ue89e
(
1
\u03d5
k
B
)
\ue89e
\uf603
\u03d5
k
B
–
\u03a6
fk
BG
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
,
where 1\u03c6kI denotes a weight of a kth internal state and a value to expedite the convergence of an occupancy ratio of a kth internal state integral value, C denotes the suitability constant, \u03c1 denotes a scaling factor for a percentage calculation,
\u2211
k
=
1
6
\ue89e
(
1
\u03d5
k
I
)
\ue89e
\uf603
\u03d5
k
I
–
\u03a6
pk
M
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
is used to obtain a sum of absolute values of a difference between an internal state attribute preference gain and an internal state attribute occupancy ratio of each of internal states corresponding to \u2018motivation\u2019 among all internal state attributes, \u03c6kI denotes an internal state attribute preference gain of a kth internal state attribute among the internal state attributes belonging to \u2018motivation\u2019, \u03a6pkM(j\u0394T,g) denotes an internal state attribute occupancy ratio of a kth internal state among the internal state attributes belonging to \u2018motivation\u2019,
\u2211
k
=
7
9
\ue89e
(
1
\u03d5
k
I
)
\ue89e
\uf603
\u03d5
k
I
–
\u03a6
pk
H
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
is used to obtain a sum of absolute values of a difference between an internal state attribute preference gain and an internal state attribute occupancy ratio of each of internal states corresponding to \u2018homeostasis\u2019 among all internal state attributes, \u03c6kI denotes an internal state attribute preference gain of a kth internal state attribute among the internal state attributes belonging to \u2018homeostasis\u2019, \u03a6pkH(j\u0394T, g) denotes an internal state attribute occupancy ratio of the kth internal state among the internal state attributes belonging to \u2018homeostasis\u2019,
\u2211
k
=
10
14
\ue89e
(
1
\u03d5
k
I
)
\ue89e
\uf603
\u03d5
k
I
–
\u03a6
pk
E
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
is used to obtain a sum of absolute values of a difference between an internal state attribute preference gain and an internal state attribute occupancy ratio of each of internal states corresponding to \u2018emotion\u2019 among all internal state attributes, \u03c6kI denotes an internal state attribute preference gain of a kth internal state attribute among the internal state attributes belonging to \u2018emotion\u2019, \u03a6pkE(j\u0394T,g) denotes an internal state attribute occupancy ratio of the kth internal state among the internal state attributes belonging to \u2018emotion\u2019,
\u2211
k
=
1
14
\ue89e
(
1
\u03d5
k
B
)
\ue89e
\uf603
\u03d5
k
B
–
\u03a6
fk
BG
\ue8a0
(
j\u0394
\ue89e
\ue89e
T
,
g
)
\uf604
is used to obtain a sum of absolute values of a difference between a behavior preference gain and an internal state attribute-based behavior manifestation count occupancy ratio, for each internal state attribute, \u03c6kB denotes a behavior preference gain classified for a kth internal state attribute among the internal state attributes, and \u03a6fkBG(j\u0394T,g) denotes an internal state attribute-based behavior manifestation count occupancy ratio of the kth internal state among the internal state attributes.
39. The method of claim 34, wherein the determining process comprises determining whether the extracted robot genomes are suitable for the user preferences according to whether reliability values of the extracted robot genomes are within a reliable range.
40. The method of claim 39, wherein the determining process comprises determining whether all the reliability values of the extracted robot genomes are within the reliable range or whether a representative value of the reliability values of the extracted robot genomes is within the reliable range.
41. The method of claim 34, wherein the suitability determining process further comprises an outputting process, wherein one of the extracted robot genomes is output when the reliability values of the extracted robot genomes are suitable for the user preferences.
42. The method of claim 24, wherein the modifying process comprises:
a robot genome selecting process, wherein one of the robot genomes is selected;
a modification method selecting process, wherein one of evolution calculation or neural network calculation is selected; and
a robot genome modifying process, wherein the selected robot genome is modified using the selected modification method.
43. The method of claim 42, wherein the evolution calculation is one or an aggregation of mutation calculation, general crossover calculation, independent crossover calculation, uniform crossover calculation, and building crossover calculation.
44. The method of claim 42, wherein the modification method selecting process comprises selecting one of the mutation calculation, the general crossover calculation, the independent crossover calculation, the uniform crossover calculation, the building crossover calculation, and the neural network calculation.
45. The method of claim 42, wherein the modifying process further comprises an iterative modifying process, wherein the robot genome selecting process, the modification method selecting process, and the robot genome modifying process are iteratively performed a number of times when the modification of all the input robot genomes is completed, the robot genome selecting process.
46. The method of claim 24, wherein the secondary robot genome group generating process comprises;
a robot genome regenerating process, wherein robot genomes in which the internal state attribute preferences and the behavior preferences are reflected are regenerated;
a secondary robot genome number checking process, wherein a determination is made whether a sum of a number of regenerated robot genomes and a number of robot genomes modified in the modifying process is less than a particular number;
a robot genome regenerating iteration process, wherein the robot genome regenerating process is repeated when a determination is made that the sum is less than the particular number; and
a generating process, wherein these robot genomes are generated as a secondary robot genome group when the sum is determined to be equal to the particular number.
47. The system of claim 1, wherein the modification unit modifies the input robot genomes are modified using an arbitrary learning algorithm, such as evolution calculation or neural network calculation.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. A method of promoting an entity, comprising the steps of:
(a) receiving descriptive information about the entity;
(b) receiving a video segment of the entity;
(c) assigning a common unique identifier to both the descriptive information and video segment;
(d) incorporating the unique identifier into the video segment;
(e) broadcasting the video segment;
(f) making the descriptive information available to viewers of the video segment in an information portal in which the descriptive information is indexed by the unique identifier.
2. The method according to claim 1, wherein the entity is selected from the group consisting of an individual, an object, and real property.
3. The method according to claim 1, wherein the entity is an individual.
4. The method according to claim 3, and further including the steps of:
(a) establishing participation standards for the promotional method;
(b) receiving background information about the individual; and
(c) based on the background information, excluding the individual from the promotional method if the individual does not meet the participation standards.
5. The method according to claim 1, and further including the step of incorporating narration into the video segment.
6. The method according to claim 1, and further including the step of incorporating directions for accessing the information portal into the video segment.
7. The method according to claim 1, and further including the steps of:
(a) establishing participation standards for the promotional method;
(b) prior to providing access to the information portal, receiving background information about the viewer; and
(c) based on the background information, excluding the viewer from access to the information portal if the viewer does not meet the participation standards.
8. The method according to claim 1, wherein the information portal allows individuals to communicate with each other through services selected from the group consisting of electronic bulletin boards, newsgroups, electronic mail, instant messaging, video casting, and telephone.
9. The method according to claim 1, wherein the information portal is selected from the group consisting of a website and a telephone service.
10. A method of promoting an entity, comprising the steps of:
(a) receiving descriptive information about a plurality of entities;
(b) receiving a video segment of each of the entities;
(c) assigning a common unique identifier to both of the descriptive information and the video segment for each of the entities;
(d) incorporating the unique identifiers into the respective video segments;
(e) editing each of the video segments into a television show;
(f) broadcasting the television show;
(g) making the descriptive information available to viewers of the video segments in an information portal indexed by the unique identifiers.
11. The method according to claim 10, and further including the step of:
(a) establishing participation standards for the promotional method;
(b) receiving background information for each of the entities; and
(c) based on the background information, excluding the entities from the promotional method if the entity does not meet the participation standards.
12. The method according to claim 10, and further including the step of incorporating narration into the video segment.
13. The method according to claim 10, and further including the steps of:
(a) establishing participation standards for the promotional method;
(b) prior to providing access to the information portal, receiving background information about the viewer; and
(c) based on the background information, excluding the viewer from access to the information portal if the viewer does not meet the participation standards.
14. The method according to claim 10, wherein the information portal allows individuals to communicate with each other through services selected from the group consisting of electronic bulletin boards, newsgroups, electronic mail, instant messaging, video casting, and telephone.
15. The method according to claim 10, and further including the step of advertising the television show, the step of advertising comprising the steps of:
(a) identifying a service provider which concurrently distributes a plurality of television programs to viewers;
(b) obtaining a common time slot from the service provider associated with the plurality of programs; and
(c) broadcasting a commercial during the time slot, the commercial directing viewers to the television show.
16. A method of facilitating interpersonal relationships, comprising the steps of:
(a) providing a promotional platform, comprising:
(i) a television show; and
(ii) an information portal;
(b) receiving personal descriptive information about a plurality of participants;
(c) receiving a video segment of each of the participants;
(d) assigning a common unique identifier to both of the descriptive information and video segment for each of the participants;
(e) incorporating the unique identifier into the respective video segments;
(f) broadcasting the video segments on the television show; and
(g) making the descriptive information available to viewers of the television show through the information portal, wherein the descriptive information is indexed by the unique identifiers.
17. The method according to claim 16, and further including the step of incorporating narration into the television show.
18. The method according to claim 16, and further including the steps of:
(a) establishing participation standards for the facilitation of interpersonal relationships;
(b) prior to providing access to the information portal, receiving background information about the viewer; and
(c) based on the background information, excluding the viewer from access to the information portal if the viewer does not meet the participation standards.
19. The method according to claim 16, wherein the information portal allows participants to communicate with each other through services selected from the group consisting of electronic bulletin boards, newsgroups, electronic mail, instant messaging, video casting, and telephone.
20. The method according to claim 16, and further including the step of advertising the television show, the step of advertising comprising the steps of:
(a) identifying a service provider which concurrently distributes a plurality of television programs to viewers;
(b) obtaining a common time slot from the service provider associated with the plurality of programs; and
(c) broadcasting a commercial during the time slot, the commercial directing viewers to the television show.