DETAILED ACTION
This communication is in response to the Application No. 18/524,446 filed November 30, 2023
in which Claims 1 - 15 are presented for examination.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim 1-15 are rejected under 35 U.S.C. 101 because these claimed inventions are directed to an
abstract idea without significantly more.
Regarding Claim 1:
Step 1: Claim 1 is a system type claim. Therefore, Claims 1-13 fall within one of the four statutory
categories (i.e., process, machine, manufacture, or composition of matter).
2A Prong 1: If a claim limitation, under its broadest reasonable interpretation, covers performance
of the limitation in the mind but for the recitation of generic computer components, then it falls within
the “Mental Processes” grouping of abstract ideas. If a claim limitation, under its broadest reasonable
interpretation, covers performance of the limitation by mathematical calculation but for the recitation
of generic computer components, then it falls within the “Mathematical Concepts” grouping of abstract
ideas.
to set at least one threshold value for the multilevel signal contained in the operation data, and to convert the multilevel signal into at least one binary signal with using the threshold value (mental process – setting at least one threshold value for the multilevel signal contained in the operation data and converting the multilevel signal into at least one binary may be performed mentally or using pen and paper by a user observing/analyzing the multilevel signal values, selecting a threshold value based on the observed signal values, comparing each multilevel signal value to the threshold value, and accordingly using judgment/evaluation to assign a binary value based said analysis)
to input the converted binary signal to a prediction model which predicts a steady-state signal value of the operation data, and to calculate a prediction value of the converted binary signal as a converted binary signal prediction value (mental process – inputting the converted binary signal to a prediction model and calculating a prediction value may be performed mentally or using pen and paper by a user observing/analyzing the converted binary signal, applying a known prediction rule, lookup table, or mathematical relationship to the converted binary signal, and accordingly using judgment/evaluation to estimate a steady-state signal value as the converted binary signal prediction value)
and to calculate, based on the converted binary signal prediction value and the threshold value, a probability that a signal value of the multilevel signal contained in the operation data exists in a range determined based on the threshold value (mathematical concept/mental process – calculating the probability recites a mathematical concept because it uses numerical prediction values and threshold values to perform a probability/statistical calculation. The calculation may also be performed mentally or using pen and paper by a user observing/analyzing the converted binary signal prediction value and the threshold-defined range, comparing the signal value to the threshold value, and accordingly using judgment/evaluation or a probability rule to estimate whether the signal value exists within the range determined based on the threshold value)
and to determine the steady range of the multilevel signal contained in the operation data, on a basis of the probability (mental process – determining the steady range on a basis of the probability may be performed mentally by a user observing/analyzing the calculated probability for each threshold-defined range, comparing the probability values, and accordingly using judgment/evaluation to select the range having a probability that indicates the signal value is likely to be in a steady state)
Step 2A Prong 2: This judicial exception is not integrated into a practical application.
processing circuitry (recited at a high-level of generality (i.e., a generic processor, computer-readable storage medium, a communication interface, a user interface and memory) such that it amounts to no more than mere instructions to apply the exception using generic computer components)
Step 2B: The claim does not include additional elements considered individually and in combination that
are sufficient to amount to significantly more than the judicial exception.
processing circuitry (recited at a high-level of generality (i.e., a generic processor, computer-readable storage medium, a communication interface, a user interface and memory) such that it amounts to no more than mere instructions to apply the exception using generic computer components)
For the reasons above, Claim 1 is rejected as being directed to an abstract idea without significantly more. This rejection applies equally to dependent claims 1 - 13. The additional limitations of the dependent claims are addressed below.
Regarding Claim 2:
Step 2A Prong 1: See the rejection of Claim 1 above, which Claim 2 depends on.
wherein the processing circuitry displays the signal value of the multilevel signal contained in the operation data by superposing over the range including the steady range and determined based on the threshold value (mental process - displaying the signal value by superposing it over the range including the steady range may be performed mentally or using pen and paper by a user observing/analyzing the signal value, identifying the range determined based on the threshold value, identifying the steady range, and accordingly using judgment/evaluation to mark, plot, or place the signal value over the threshold-defined range including the steady range)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 3:
Step 2A Prong 1: See the rejection of Claim 1 above, which Claim 3 depends on.
wherein the processing circuitry determines, from among ranges each determined based on the threshold value, a range where the probability has a determined value or more, as the steady range (mental process - determining the range where the probability has a determined value or more as the steady range may be performed mentally or using pen and paper by a user observing/analyzing the probability values for the threshold-defined ranges, comparing each probability value to the determined value, and accordingly using judgment/evaluation to select the range having a probability equal to or greater than the determined value as the steady range)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 4:
Step 2A Prong 1: See the rejection of Claim 1 above, which Claim 4 depends on.
wherein the processing circuitry determines, from among ranges each determined based on the threshold value, a range where the probability is maximum, as the steady range (mental process - determining the range where the probability is maximum as the steady range may be performed mentally or using pen and paper by a user observing/analyzing the probability values for the threshold-defined ranges, comparing the probability values with each other, and accordingly using judgment/evaluation to select the range having the highest probability as the steady range)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 5:
Step 2A Prong 1: See the rejection of Claim 4 above, which Claim 5 depends on.
wherein the processing circuitry selects, from among ranges each determined based on the threshold value, ranges in a descending order of probability, and determines ranges selected until the probabilities total up to a determined value or more, each as the steady range (mental process - determining the range where the probability is maximum as the steady range may be performed mentally or using pen and paper by a user observing/analyzing the probability values for the threshold-defined ranges, comparing the probability values with each other, and accordingly using judgment/evaluation to select the range having the highest probability as the steady range)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 6:
Step 2A Prong 1: See the rejection of Claim 4 above, which Claim 6 depends on.
wherein the processing circuitry repeats selecting, from among ranges each determined based on the threshold value, a range where the probability is maximum and selecting, from among ranges adjacent to the selected range, a range where the probability is larger (mental process - repeatedly selecting a maximum-probability range and selecting an adjacent range where the probability is larger may be performed mentally by a user observing/analyzing the probability values for threshold-defined ranges, comparing the probability values, selecting the range having the highest probability, then comparing the probability values of ranges adjacent to the selected range, and accordingly using judgment/evaluation to select an adjacent range having a larger probability)
and determines ranges selected until the probabilities total up to a determined value or more, each as the steady range (mental process - determining selected ranges until the probabilities total up to a determined value or more may be performed mentally or using pen and paper by a user observing/analyzing the probability values for the threshold-defined ranges, adding the probabilities of selected ranges, comparing the total probability to the determined value, and accordingly using judgment/evaluation to identify each selected range as the steady range once the total probability reaches or exceeds the determined value)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 7:
Step 2A Prong 1: See the rejection of Claim 1 above, which Claim 7 depends on.
wherein the processing circuitry determines, from among ranges each determined based on the threshold value, a range where a probability density being a value obtained by dividing the probability by a width of the range has a determined value or more, as the steady range (mental process - determining the range where the probability density has a determined value or more as the steady range may be performed mentally or using pen and paper by a user observing/analyzing the probability and width of each threshold-defined range, dividing the probability by the width of the range to obtain a probability-density value, comparing the probability-density value to the determined value, and accordingly using judgment/evaluation to select the range having a probability density equal to or greater than the determined value as the steady range)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 8:
Step 2A Prong 1: See the rejection of Claim 1 above, which Claim 8 depends on.
wherein the processing circuitry determines, from among ranges each determined based on the threshold value, a range where a probability density being a value obtained by dividing the probability by a width of the range is maximum, as the steady range (mental process - determining the range where the probability density is maximum as the steady range may be performed mentally or using pen and paper by a user observing/analyzing the probability and width of each threshold-defined range, dividing the probability by the width of each range to obtain probability-density values, comparing the probability-density values with each other, and accordingly using judgment/evaluation to select the range having the highest probability-density value as the steady range)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 9:
Step 2A Prong 1: See the rejection of Claim 8 above, which Claim 9 depends on.
wherein the processing circuitry selects, from among ranges each determined based on the threshold value, ranges in a descending order of probability density being a value obtained by dividing the probability by a width of the range, and determines ranges selected until the probability densities total up to a determined value or more, each as the steady range (mental process - selecting ranges in descending order of probability density and determining selected ranges until the probability densities total up to a determined value or more may be performed mentally or using pen and paper by a user observing/analyzing the probability and width of each threshold-defined range, dividing each probability by the corresponding range width to obtain probability-density values, ranking the ranges from highest probability density to lowest probability density, adding the probability-density values in that order, and accordingly using judgment/evaluation to select the ranges until the total probability density reaches or exceeds the determined value)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 10:
Step 2A Prong 1: See the rejection of Claim 8 above, which Claim 10 depends on.
wherein the processing circuitry repeats selecting, from among ranges each determined based on the threshold value, a range where a probability density being a value obtained by dividing the probability by a width of the range is maximum and selecting, from among ranges adjacent to the selected range, a range where the probability density is larger (mental process - repeatedly selecting a maximum-probability-density range and selecting an adjacent range where the probability density is larger may be performed mentally or using pen and paper by a user observing/analyzing the probability and width of each threshold-defined range, dividing each probability by the corresponding range width to obtain probability-density values, comparing the probability-density values to select the range having the highest probability density, then comparing probability-density values of ranges adjacent to the selected range, and accordingly using judgment/evaluation to select an adjacent range having a larger probability density)
and determines ranges selected until the probabilities total up to a determined value or more, each as the steady range (mental process - determining selected ranges until the probabilities total up to a determined value or more may be performed mentally or using pen and paper by a user observing/analyzing the probability values for the threshold-defined ranges, adding the probability values of selected ranges, comparing the total probability to the determined value, and accordingly using judgment/evaluation to identify each selected range as the steady range once the total probability reaches or exceeds the determined value)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 11:
Step 2A Prong 1: See the rejection of Claim 3 above, which Claim 11 depends on.
wherein the processing circuitry determines, regarding the ranges each determined based on the threshold value, an unsteadiness degree of a range that is not steady, according to the probability (mental process - determining an unsteadiness degree of a range that is not steady according to the probability may be performed mentally or using pen and paper by a user observing/analyzing the probability values for the threshold-defined ranges, identifying a range that does not correspond to the steady range, comparing its probability to the probability associated with the steady range, and accordingly using judgment/evaluation to assign an unsteadiness degree based on how strongly the probability indicates that the range is not steady)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 12:
Step 2A Prong 1: See the rejection of Claim 7 above, which Claim 12 depends on.
wherein the processing circuitry determines, regarding the ranges each determined based on the threshold value, an unsteadiness degree of a range that is not steady, according to the probability density being the value obtained by dividing the probability by the width of the range (mental process - determining an unsteadiness degree according to the probability density may be performed mentally or using pen and paper by a user observing/analyzing the probability and width of each threshold-defined range, dividing the probability by the width of the range to obtain a probability-density value, identifying a range that is not steady, and accordingly using judgment/evaluation to assign an unsteadiness degree based on the probability-density value for that non-steady range)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 13:
Step 2A Prong 1: See the rejection of Claim 1 above, which Claim 13 depends on.
wherein the processing circuitry determines, regarding the ranges each determined based on the threshold value, an unsteadiness degree of a range that is not steady, according to a separation degree from the steady range (mental process - determining an unsteadiness degree according to a separation degree from the steady range may be performed mentally or using pen and paper by a user observing/analyzing the threshold-defined ranges, identifying the steady range, identifying a range that is not steady, determining how far the non-steady range is separated from the steady range, and accordingly using judgment/evaluation to assign an unsteadiness degree based on the separation from the steady range)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 14:
Step 1: Claim 14 is a method type claim. Therefore, Claim 14 falls within one of the four statutory
categories (i.e., process, machine, manufacture, or composition of matter).
2A Prong 1: If a claim limitation, under its broadest reasonable interpretation, covers performance
of the limitation in the mind but for the recitation of generic computer components, then it falls within
the “Mental Processes” grouping of abstract ideas. If a claim limitation, under its broadest reasonable
interpretation, covers performance of the limitation by mathematical calculation but for the recitation
of generic computer components, then it falls within the “Mathematical Concepts” grouping of abstract
ideas.
setting at least one threshold value for the multilevel signal contained in the operation data, and converting the multilevel signal into at least one binary signal with using the threshold value (mental process – setting at least one threshold value for the multilevel signal contained in the operation data and converting the multilevel signal into at least one binary may be performed mentally or using pen and paper by a user observing/analyzing the multilevel signal values, selecting a threshold value based on the observed signal values, comparing each multilevel signal value to the threshold value, and accordingly using judgment/evaluation to assign a binary value based said analysis)
inputting the converted binary signal to a prediction model which predicts a steady-state signal value of the operation data, and calculating a prediction value of the converted binary signal as a converted binary signal prediction value (mental process – inputting the converted binary signal to a prediction model and calculating a prediction value may be performed mentally or using pen and paper by a user observing/analyzing the converted binary signal, applying a known prediction rule, lookup table, or mathematical relationship to the converted binary signal, and accordingly using judgment/evaluation to estimate a steady-state signal value as the converted binary signal prediction value)
and calculating, based on the converted binary signal prediction value and the threshold value, a probability that a signal value of the multilevel signal contained in the operation data exists in a range determined based on the threshold value (mathematical concept/mental process – calculating the probability recites a mathematical concept because it uses numerical prediction values and threshold values to perform a probability/statistical calculation. The calculation may also be performed mentally or using pen and paper by a user observing/analyzing the converted binary signal prediction value and the threshold-defined range, comparing the signal value to the threshold value, and accordingly using judgment/evaluation or a probability rule to estimate whether the signal value exists within the range determined based on the threshold value)
and determining the steady range of the multilevel signal contained in the operation data, on a basis of the probability (mental process – determining the steady range on a basis of the probability may be performed mentally by a user observing/analyzing the calculated probability for each threshold-defined range, comparing the probability values, and accordingly using judgment/evaluation to select the range having a probability that indicates the signal value is likely to be in a steady state)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
For the reasons above, Claim 14 is rejected as being directed to an abstract idea without significantly more.
Regarding Claim 15:
Step 1: Claim 15 is a non-transitory computer readable medium type claim. Therefore, Claim 15 falls within one of the four statutory categories (i.e., process, machine, manufacture, or composition of matter).
2A Prong 1: If a claim limitation, under its broadest reasonable interpretation, covers performance
of the limitation in the mind but for the recitation of generic computer components, then it falls within
the “Mental Processes” grouping of abstract ideas. If a claim limitation, under its broadest reasonable
interpretation, covers performance of the limitation by mathematical calculation but for the recitation
of generic computer components, then it falls within the “Mathematical Concepts” grouping of abstract
ideas.
a conversion process of setting at least one threshold value for the multilevel signal contained in the operation data, and converting the multilevel signal into at least one binary signal with using the threshold value (mental process – setting at least one threshold value for the multilevel signal contained in the operation data and converting the multilevel signal into at least one binary may be performed mentally or using pen and paper by a user observing/analyzing the multilevel signal values, selecting a threshold value based on the observed signal values, comparing each multilevel signal value to the threshold value, and accordingly using judgment/evaluation to assign a binary value based said analysis)
a prediction process of inputting the converted binary signal to a prediction model which predicts a steady-state signal value of the operation data, and calculating a prediction value of the converted binary signal as a converted binary signal prediction value (mental process – inputting the converted binary signal to a prediction model and calculating a prediction value may be performed mentally or using pen and paper by a user observing/analyzing the converted binary signal, applying a known prediction rule, lookup table, or mathematical relationship to the converted binary signal, and accordingly using judgment/evaluation to estimate a steady-state signal value as the converted binary signal prediction value)
a range determination process of calculating, based on the converted binary signal prediction value and the threshold value, a probability that a signal value of the multilevel signal contained in the operation data exists in a range determined based on the threshold value (mathematical concept/mental process – calculating the probability recites a mathematical concept because it uses numerical prediction values and threshold values to perform a probability/statistical calculation. The calculation may also be performed mentally or using pen and paper by a user observing/analyzing the converted binary signal prediction value and the threshold-defined range, comparing the signal value to the threshold value, and accordingly using judgment/evaluation or a probability rule to estimate whether the signal value exists within the range determined based on the threshold value)
and determining the steady range of the multilevel signal contained in the operation data, on a basis of the probability (mental process – determining the steady range on a basis of the probability may be performed mentally by a user observing/analyzing the calculated probability for each threshold-defined range, comparing the probability values, and accordingly using judgment/evaluation to select the range having a probability that indicates the signal value is likely to be in a steady state)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
For the reasons above, Claim 15 is rejected as being directed to an abstract idea without significantly more.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-4, 11, and 13-15 are rejected under 35 U.S.C. 103 as being unpatentable over Aoki et al. (hereafter Aoki) (JP 6790311) in view of Nakahara et al. (hereinafter Nakahara) (US 20200380743).
Regarding Claim 1, Aoki teaches:
processing circuitry (Aoki, Page 11, “The unsteady detection device 100 includes a processing circuit 109”, thus processing circuitry is disclosed)
to set at least one threshold value for the multilevel signal contained in the operation data, and to convert the multilevel signal into at least one binary signal with using the threshold value (Aoki, Page 5, “The threshold group calculation unit 112 calculates a threshold group for each multi-valued signal data included in the operation database 198. The threshold group is one or more thresholds used for converting each multi-value signal value in the multi-value signal data into one or more binary signal values (binary signal value group).”, & Page 7, “The conversion unit 113 converts each multi-valued signal value in the multi-valued signal data into a binary signal value by using the threshold value group for each multi-valued signal data. That is, the conversion unit 113 converts each multi-valued signal data into binary signal data”, thus setting at least one threshold value for the multilevel signal contained in the operation data and converting the multilevel signal into at least one binary signal using the threshold value is disclosed, because Aoki teaches that the threshold group calculation unit calculates a threshold group for each multi-valued signal data included in the operation database, where the threshold group includes one or more thresholds used for converting each multi-value signal value into one or more binary signal values. Aoki further teaches that the conversion unit converts each multi-valued signal value in the multi-valued signal data into a binary signal value by using the threshold value group. Aoki’s multi-valued signal data corresponds to the multilevel signal contained in the operation data, the threshold group corresponds to the at least one threshold value, and the conversion of each multi-valued signal value into a binary signal value corresponds to converting the multilevel signal into at least one binary signal using the threshold value),
to input the converted binary signal to a prediction model which predicts a steady-state signal value of the operation data, and to calculate a prediction value of the converted binary signal as a converted binary signal prediction value (Aoki, Page 10, “The operation database 199 includes a binary signal value of each binary signal before the target time and a binary signal value group of each multivalued signal before the target time. The set of the binary signal value of each binary signal at the target time and the binary signal value group of each multivalued signal at the target time is referred to as a "target signal value group". Each time before the target time is referred to as "past time". The set of the binary signal value of each binary signal at each past time and the binary signal value group of each multivalued signal at each past time is referred to as a "past signal value group", & Page 10, “In step S230, the prediction unit 123 reads the past signal value group from the operation database 199. The prediction unit 123 calculates the prediction model 191 by inputting the past signal value group. As a result, the predicted signal value group of the target time is calculated”, thus inputting the converted binary signal to a prediction model which predicts a steady-state signal value of the operation data, and calculating a prediction value of the converted binary signal as a converted binary signal prediction value is disclosed, because Aoki teaches that the operation database includes binary signal values before the target time and binary signal value groups of multivalued signals before the target time, which are referred to as a past signal value group. Aoki further teaches that the prediction unit reads the past signal value group from the operation database, inputs the past signal value group to the prediction model, and calculates the predicted signal value group of the target time. Aoki’s past signal value group corresponds to the converted binary signal input to the prediction model, and Aoki’s predicted signal value group of the target time corresponds to the converted binary signal prediction value because it is calculated by the prediction model based on the binary signal values of the operation data),
[…], based on the converted binary signal prediction value and the threshold value, […] the multilevel signal contained in the operation data exists in a range determined based on the threshold value (Aoki, Page 8, “In the first binary signal, the binary signal value at each time indicates the magnitude relationship between the target signal value and the first threshold value as binary values. In the second binary signal, the binary signal value at each time indicates the magnitude relationship between the target signal value and the second threshold value as two values. When the target signal value is equal to or higher than the target threshold value, the conversion unit 113 converts the target signal value to “1”. When the target signal value is less than the target threshold value, the conversion unit 113 converts the target signal value to “0””, thus […], based on the converted binary signal prediction value and the threshold value, […] the multilevel signal contained in the operation data exists in a range determined based on the threshold value is disclosed, because Aoki teaches that each binary signal value indicates a magnitude relationship between a target signal value and a threshold value. Aoki further teaches that when the target signal value is equal to or higher than the target threshold value, the conversion unit converts the target signal value to “1,” and when the target signal value is less than the target threshold value, the conversion unit converts the target signal value to “0.” Therefore, Aoki’s threshold values define ranges of signal values, and Aoki’s binary conversion indicates whether the multilevel signal value exists in a range determined based on the threshold value),
and to determine the steady range of the multilevel signal contained in the operation data, […] (Aoki, Page 3, “The multi-valued signal value is a value indicated by the multi-valued signal. For example, the signal output from the robot hand is a multi-valued signal indicating the torque of the robot hand with a value larger than two values”, & Page 2, “Each facility 221 comprises one or more devices. For example, each facility 221 includes a sensor, a robot, and the like. Each facility 221 outputs data indicating the operating status at each time. Data indicating the operating status at each time is referred to as "operating data". The operation data is also referred to as collected data, signal data or status signal data. The operation data includes one or more binary signal values and one or more multi-valued signal values”, thus and to determine the steady range of the multilevel signal contained in the operation data is disclosed, because Aoki teaches that each facility outputs data indicating an operating status at each time, and that such data is referred to as operation data. Aoki further teaches that the operation data includes one or more multi-valued signal values, and that a multi-valued signal value is a value indicated by a multi-valued signal, such as a torque signal output from a robot hand having a value larger than two values. Therefore, Aoki’s multi-valued signal corresponds to the multilevel signal, and Aoki’s operation data corresponds to the operation data containing the multilevel signal)
Aoki does not explicitly teach to calculate […] a probability that a signal value of […a multilevel signal contained in operation data …] and […] on a basis of the probability.
However, Nakahara teaches:
to calculate […] a probability that a signal value of […a multilevel signal contained in operation data …] (Nakahara, Par. [0081], “if the normal model is a normal model generated by machine learning, the prediction value calculation unit 314 calculates the probability that the signal value of the prediction value which is a next value of the log data of the control apparatus 2 is 1, by inputting to the normal model, the acquired log data in the past of the control apparatus 2”, thus to calculate […] a probability that a signal value of […a multilevel signal contained in operation data …] is disclosed, because Nakahara teaches that, when the normal model is generated by machine learning, the prediction value calculation unit calculates a probability that the signal value of the prediction value, which is a next value of the log data of the control apparatus, is 1 by inputting past log data to the normal model. Nakahara’s log data corresponds to operation data, and Nakahara’s calculated probability that the next signal value is 1 corresponds to calculating a probability associated with a signal value contained in the operation data)
[…] on a basis of the probability (Nakahara, Par. [0081], the prediction value calculation unit 314 calculates the probability that the signal value of the prediction value which is a next value of the log data of the control apparatus 2 is 1, by inputting to the normal model, the acquired log data in the past of the control apparatus 2. Besides, the probability that the signal value of the prediction value of the log data of the control apparatus 2 is 1 calculated by the prediction value calculation unit 314 is the accuracy degree of the prediction value indicating the accuracy of the prediction value. Here, since the actual measurement value of the log data of the control apparatus 2 is a binary digital signal, a fact that the probability of the signal value of the prediction value of the log data of the control apparatus 2”, thus […] on a basis of the probability is disclosed, because Nakahara teaches that the prediction value calculation unit calculates a probability that the signal value of the prediction value, which is the next value of the log data, is 1 by inputting past log data to the normal model. Nakahara further teaches that the calculated probability is the accuracy degree of the prediction value, indicating the accuracy of the prediction value. Therefore, Nakahara uses the calculated probability as a basis for determining the prediction/normal state information of the log data)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine Aoki’s teaching of setting at least one threshold value for a multilevel signal contained in operation data, converting the multilevel signal into at least one binary signal using the threshold value, inputting the converted binary signal to a prediction model, and calculating a converted binary signal prediction value, with Nakahara’s teaching of calculating a probability that a signal value of log data exists as a predicted signal value and using the probability as an accuracy degree of the prediction value. Aoki teaches using threshold values and a prediction model to process multilevel operation data, while Nakahara teaches determining prediction/normal-state information on a basis of probability. Therefore, a POSITA would have been motivated to incorporate Nakahara’s probability-based prediction teaching into Aoki’s threshold-based prediction system so that the system could calculate, based on the converted binary signal prediction value and the threshold value, a probability that a signal value of the multilevel signal exists in a range determined based on the threshold value, and determine the steady range of the multilevel signal on a basis of the probability (Nakahara, Par. [0003], “there is an increasing demand for anomaly detection for early detection of apparatus anomalies. As a method for achieving this, there is a display method that facilitates detection of the anomaly by a user who uses the apparatus, by displaying log data acquired from the apparatus while separating the log data in a normal state from the log data in an anomalous state”, & Par. [0008], “The present invention aims to realize a display apparatus which displays a display screen targeting log data of a device which is a binary digital signal and is capable of displaying that the log data deviates from a normal state and displaying its degree of deviation, when the log data is in an anomalous state”)
Regarding Claim 2, Aoki combined with Nakahara teaches all the limitations of claim 1 as cited above and Aoki further teaches:
wherein the processing circuitry displays the signal value of the multilevel signal contained in the operation data […] and determined based on the threshold value (Aoki, Page 2, “The operation data includes one or more binary signal values and one or more multi-valued signal values”, & Page 5, “The threshold group calculation unit 112 calculates a threshold group for each multi-valued signal data included in the operation database 198. The threshold group is one or more thresholds used for converting each multi-value signal value in the multi-value signal data into one or more binary signal values (binary signal value group)”, & Page 7, “Specifically, the conversion unit 113 converts the target signal value into a binary signal value indicating the magnitude relationship between the target signal value and the threshold value for each threshold value in the target threshold value group”, thus wherein the processing circuitry displays the signal value of the multilevel signal contained in the operation data […] and determined based on the threshold value is disclosed, because Aoki teaches that the operation data includes one or more multi-valued signal values, and teaches that the threshold group includes one or more thresholds used for converting each multi-value signal value into one or more binary signal values. Aoki further teaches that the conversion unit converts the target signal value into a binary signal value indicating the magnitude relationship between the target signal value and the threshold value for each threshold value. Therefore, Aoki’s multi-valued signal value corresponds to the signal value of the multilevel signal contained in the operation data, and Aoki’s threshold-based conversion indicates that the signal value is processed with respect to a range determined based on the threshold value.)
Nakahara further teaches:
[…] by superposing over [...a range…] including the steady range […] (Nakahara, Par. [0114], “since the prediction value area 7 reflects the accuracy degree of the prediction value, the prediction value area 7 indicates a range of the normal state of the log data of the control apparatus 2”, & Par. [0118], “the display screen generation unit 413 depicts, based on the actual measurement value of the log data of the control apparatus 2 acquired from the collection database 431, an actual measurement value signal 8, which is a signal wavelength of the actual measurement value of the log data of the control apparatus 2, on the prediction screen acquired from the prediction screen generation unit 412 to generate the display screen”, thus […] by superposing over […a range…] including the steady range […] is disclosed, because Nakahara teaches that the prediction value area indicates a range of the normal state of the log data, and further teaches that the display screen generation unit depicts an actual measurement value signal on the prediction screen to generate the display screen. Nakahara’s prediction value area corresponds to the range including the steady range because it indicates the normal-state range of the log data, and Nakahara’s depicting of the actual measurement value signal on the prediction screen corresponds to superposing the signal value over the range including the steady range)
Regarding Claim 3, Aoki combined with Nakahara teaches all the limitations of claim 1 as cited above and Aoki further teaches:
wherein the processing circuitry determines, from among ranges each determined based on the threshold value, […] (Aoki, Page 6, “For example, the threshold group calculation unit 112 generates a frequency distribution graph as shown in FIG. "Section" means the range of signal values”, & Page 6, “the threshold group calculation unit 112 calculates a value between the signal value corresponding to one peak and the signal value corresponding to the other peak for each peak. Each calculated value becomes a threshold value”, thus wherein the processing circuitry determines, from among ranges each determined based on the threshold value, […] is disclosed, because Aoki teaches that the threshold group calculation unit generates a frequency distribution graph and that a section means a range of signal values. Aoki further teaches that the threshold group calculation unit calculates a value between the signal value corresponding to one peak and the signal value corresponding to another peak, and that each calculated value becomes a threshold value. Therefore, Aoki’s sections correspond to ranges, and Aoki’s calculated threshold values define the ranges from among which the processing circuitry makes the determination)
Nakahara further teaches:
[…] a range where the probability has a determined value or more, as the steady range (Nakahara, Par. [0110], “if the normal model is the normal model generated by machine learning, a calculation method of the width W of the actual measurement value area 7 differs depending on whether the probability of the value of the signal value of the prediction value being 1 is 0.5 or more or less than 0.5, the probability being the accuracy degree of the prediction value”, & Par. [0114], “since the prediction value area 7 reflects the accuracy degree of the prediction value, the prediction value area 7 indicates a range of the normal state of the log data of the control apparatus 2”, thus […] a range where the probability has a determined value or more, as the steady range is disclosed, because Nakahara teaches that, when the normal model is generated by machine learning, the width of the prediction value area is calculated depending on whether the probability of the signal value of the prediction value being 1 is 0.5 or more or less than 0.5. Nakahara further teaches that the probability is the accuracy degree of the prediction value and that the prediction value area reflects the accuracy degree of the prediction value. Nakahara’s 0.5 threshold corresponds to the determined value, and Nakahara’s prediction value area corresponds to the steady range because it indicates a range of the normal state of the log data)
Regarding Claim 4, Aoki combined with Nakahara teaches all the limitations of claim 1 as cited above and Aoki further teaches:
wherein the processing circuitry determines, from among ranges each determined based on the threshold value, […] (Aoki, Page 6, “For example, the threshold group calculation unit 112 generates a frequency distribution graph as shown in FIG. "Section" means the range of signal values”, & Page 6, “the threshold group calculation unit 112 calculates a value between the signal value corresponding to one peak and the signal value corresponding to the other peak for each peak. Each calculated value becomes a threshold value”, thus wherein the processing circuitry determines, from among ranges each determined based on the threshold value, […] is disclosed, because Aoki teaches that the threshold group calculation unit generates a frequency distribution graph, and that a section means a range of signal values. Aoki further teaches that the threshold group calculation unit calculates a value between signal values corresponding to peaks, and that each calculated value becomes a threshold value. Therefore, Aoki’s sections correspond to ranges, and Aoki’s calculated threshold values correspond to threshold values that determine the ranges from among which the processing circuitry makes the determination)
Nakahara further teaches:
[…] a range where the probability is maximum, as the steady range (Nakahara, Par. [0081], “a fact that the probability of the signal value of the prediction value of the log data of the control apparatus 2 calculated by the prediction value calculation unit 314 being 1 is 0.5 or more indicates that the signal value of the prediction value of the log data of the control apparatus 2 is likely to be 1. Also, a fact that the calculated probability of the signal value of the prediction value of the log data of the control apparatus 2 being 1 is less than 0.5 indicates that the signal value of the prediction value of the log data of the control apparatus 2 is likely to be 0”, & Par. [0114], “since the prediction value area 7 reflects the accuracy degree of the prediction value, the prediction value area 7 indicates a range of the normal state of the log data of the control apparatus 2”, thus […] a range where the probability is maximum, as the steady range is disclosed, because Nakahara teaches using probability to determine the most likely signal value of log data. Specifically, Nakahara teaches that when the probability that the signal value of the prediction value is 1 is 0.5 or more, the predicted signal value is likely to be 1, and when the probability is less than 0.5, the predicted signal value is likely to be 0. Nakahara further teaches that this probability is the accuracy degree of the prediction value and that the prediction value area reflects the accuracy degree of the prediction value. Because Nakahara’s prediction value area indicates a range of the normal state of the log data, Nakahara uses the probability/accuracy degree to identify the range most likely to represent the normal state. Therefore, when multiple threshold-determined ranges are available, selecting the range having the maximum probability would have been the natural application of Nakahara’s probability-based normal-state determination, because the maximum-probability range represents the range most likely to correspond to the steady/normal state)
Regarding Claim 11, Aoki combined with Nakahara teaches all the limitations of claim 3 as cited above and Aoki further teaches:
wherein the processing circuitry determines, regarding the ranges each determined based on the threshold value, […] (Aoki, Page 6, “For example, the threshold group calculation unit 112 generates a frequency distribution graph as shown in FIG. "Section" means the range of signal values”, & Page 6, “the threshold group calculation unit 112 calculates a value between the signal value corresponding to one peak and the signal value corresponding to the other peak for each peak. Each calculated value becomes a threshold value”, thus wherein the processing circuitry determines, regarding the ranges each determined based on the threshold value, […] is disclosed, because Aoki teaches that the threshold group calculation unit generates a frequency distribution graph, and that a section means a range of signal values. Aoki further teaches that the threshold group calculation unit calculates a value between the signal value corresponding to one peak and the signal value corresponding to another peak, and that each calculated value becomes a threshold value. Therefore, Aoki’s sections correspond to ranges, and Aoki’s calculated threshold values correspond to threshold values that determine the ranges regarding which the processing circuitry makes the determination)
Nakahara further teaches:
[…] an unsteadiness degree of a range that is not steady, according to the probability (Nakahara, Par. [0081], “the probability that the signal value of the prediction value of the log data of the control apparatus 2 is 1 calculated by the prediction value calculation unit 314 is the accuracy degree of the prediction value indicating the accuracy of the prediction value”, & Par. [0118], “the display screen generated by the display screen generation unit 413 directly indicates deviation degree that indicates how much the actual measurement value of the log data of the control apparatus 2 deviates from the prediction value area 7 indicating the range of the normal state so that the user can visually recognize on the display screen whether or not the log data of the control apparatus 2 deviates from the normal state and, if deviating, the user can visually recognize the degree of the deviation”, thus […] an unsteadiness degree of a range that is not steady, according to the probability is disclosed, because Nakahara teaches that the probability calculated by the prediction value calculation unit is the accuracy degree of the prediction value, indicating the reliability of the prediction. Nakahara further teaches that the display screen directly indicates a deviation degree showing how much the actual measurement value deviates from the prediction value area indicating the normal-state range. Therefore, Nakahara’s probability/accuracy degree corresponds to the probability used for evaluating the range, and Nakahara’s deviation degree corresponds to the unsteadiness degree of a range that is not steady because it quantifies the extent to which the signal deviates from the normal-state range according to the probability-based prediction)
Regarding Claim 13, Aoki combined with Nakahara teaches all the limitations of claim 1 as cited above and Aoki further teaches:
wherein the processing circuitry determines, regarding the ranges each determined based on the threshold value, […] from the steady range (Aoki, Page 6, “For example, the threshold group calculation unit 112 generates a frequency distribution graph as shown in FIG. "Section" means the range of signal values”, & Page 6, “the threshold group calculation unit 112 calculates a value between the signal value corresponding to one peak and the signal value corresponding to the other peak for each peak. Each calculated value becomes a threshold value”, thus wherein the processing circuitry determines, regarding the ranges each determined based on the threshold value, […] from the steady range is disclosed with respect to the threshold-determined ranges, because Aoki teaches that the threshold group calculation unit generates a frequency distribution graph, and that a section means a range of signal values. Aoki further teaches that the threshold group calculation unit calculates a value between the signal value corresponding to one peak and the signal value corresponding to another peak, and that each calculated value becomes a threshold value. Therefore, Aoki’s sections correspond to ranges, and Aoki’s calculated threshold values correspond to threshold values that determine the ranges regarding which the processing circuitry determines separation from the steady range)
Nakahara further teaches:
[…] an unsteadiness degree of a range that is not steady, according to a separation degree […] (Nakahara, Par. [0081], “the probability that the signal value of the prediction value of the log data of the control apparatus 2 is 1 calculated by the prediction value calculation unit 314 is the accuracy degree of the prediction value indicating the accuracy of the prediction value”, & Par. [0118], “the display screen generated by the display screen generation unit 413 directly indicates deviation degree that indicates how much the actual measurement value of the log data of the control apparatus 2 deviates from the prediction value area 7 indicating the range of the normal state so that the user can visually recognize on the display screen whether or not the log data of the control apparatus 2 deviates from the normal state and, if deviating, the user can visually recognize the degree of the deviation”, thus […] an unsteadiness degree of a range that is not steady, according to a separation degree […] is disclosed, because Nakahara teaches that the probability calculated by the prediction value calculation unit is the accuracy degree of the prediction value, and further teaches that the display screen directly indicates a deviation degree showing how much the actual measurement value deviates from the prediction value area indicating the normal-state range. Nakahara’s prediction value area corresponds to the steady/normal range, Nakahara’s deviation degree corresponds to the separation degree from that steady/normal range, and the indicated degree of deviation corresponds to the unsteadiness degree of a range that is not steady)
Regarding Claim 14, Aoki teaches:
setting at least one threshold value for the multilevel signal contained in the operation data, and converting the multilevel signal into at least one binary signal with using the threshold value (Aoki, Page 5, “The threshold group calculation unit 112 calculates a threshold group for each multi-valued signal data included in the operation database 198. The threshold group is one or more thresholds used for converting each multi-value signal value in the multi-value signal data into one or more binary signal values (binary signal value group).”, & Page 7, “The conversion unit 113 converts each multi-valued signal value in the multi-valued signal data into a binary signal value by using the threshold value group for each multi-valued signal data. That is, the conversion unit 113 converts each multi-valued signal data into binary signal data”, thus setting at least one threshold value for the multilevel signal contained in the operation data and converting the multilevel signal into at least one binary signal using the threshold value is disclosed, because Aoki teaches that the threshold group calculation unit calculates a threshold group for each multi-valued signal data included in the operation database, where the threshold group includes one or more thresholds used for converting each multi-value signal value into one or more binary signal values. Aoki further teaches that the conversion unit converts each multi-valued signal value in the multi-valued signal data into a binary signal value by using the threshold value group. Aoki’s multi-valued signal data corresponds to the multilevel signal contained in the operation data, the threshold group corresponds to the at least one threshold value, and the conversion of each multi-valued signal value into a binary signal value corresponds to converting the multilevel signal into at least one binary signal using the threshold value),
inputting the converted binary signal to a prediction model which predicts a steady-state signal value of the operation data, and calculating a prediction value of the converted binary signal as a converted binary signal prediction value (Aoki, Page 10, “The operation database 199 includes a binary signal value of each binary signal before the target time and a binary signal value group of each multivalued signal before the target time. The set of the binary signal value of each binary signal at the target time and the binary signal value group of each multivalued signal at the target time is referred to as a "target signal value group". Each time before the target time is referred to as "past time". The set of the binary signal value of each binary signal at each past time and the binary signal value group of each multivalued signal at each past time is referred to as a "past signal value group", & Page 10, “In step S230, the prediction unit 123 reads the past signal value group from the operation database 199. The prediction unit 123 calculates the prediction model 191 by inputting the past signal value group. As a result, the predicted signal value group of the target time is calculated”, thus inputting the converted binary signal to a prediction model which predicts a steady-state signal value of the operation data, and calculating a prediction value of the converted binary signal as a converted binary signal prediction value is disclosed, because Aoki teaches that the operation database includes binary signal values before the target time and binary signal value groups of multivalued signals before the target time, which are referred to as a past signal value group. Aoki further teaches that the prediction unit reads the past signal value group from the operation database, inputs the past signal value group to the prediction model, and calculates the predicted signal value group of the target time. Aoki’s past signal value group corresponds to the converted binary signal input to the prediction model, and Aoki’s predicted signal value group of the target time corresponds to the converted binary signal prediction value because it is calculated by the prediction model based on the binary signal values of the operation data),
[…], based on the converted binary signal prediction value and the threshold value, […] the multilevel signal contained in the operation data exists in a range determined based on the threshold value (Aoki, Page 8, “In the first binary signal, the binary signal value at each time indicates the magnitude relationship between the target signal value and the first threshold value as binary values. In the second binary signal, the binary signal value at each time indicates the magnitude relationship between the target signal value and the second threshold value as two values. When the target signal value is equal to or higher than the target threshold value, the conversion unit 113 converts the target signal value to “1”. When the target signal value is less than the target threshold value, the conversion unit 113 converts the target signal value to “0””, thus […], based on the converted binary signal prediction value and the threshold value, […] the multilevel signal contained in the operation data exists in a range determined based on the threshold value is disclosed, because Aoki teaches that each binary signal value indicates a magnitude relationship between a target signal value and a threshold value. Aoki further teaches that when the target signal value is equal to or higher than the target threshold value, the conversion unit converts the target signal value to “1,” and when the target signal value is less than the target threshold value, the conversion unit converts the target signal value to “0.” Therefore, Aoki’s threshold values define ranges of signal values, and Aoki’s binary conversion indicates whether the multilevel signal value exists in a range determined based on the threshold value),
and determining the steady range of the multilevel signal contained in the operation data, […] (Aoki, Page 3, “The multi-valued signal value is a value indicated by the multi-valued signal. For example, the signal output from the robot hand is a multi-valued signal indicating the torque of the robot hand with a value larger than two values”, & Page 2, “Each facility 221 comprises one or more devices. For example, each facility 221 includes a sensor, a robot, and the like. Each facility 221 outputs data indicating the operating status at each time. Data indicating the operating status at each time is referred to as "operating data". The operation data is also referred to as collected data, signal data or status signal data. The operation data includes one or more binary signal values and one or more multi-valued signal values”, thus and to determine the steady range of the multilevel signal contained in the operation data is disclosed, because Aoki teaches that each facility outputs data indicating an operating status at each time, and that such data is referred to as operation data. Aoki further teaches that the operation data includes one or more multi-valued signal values, and that a multi-valued signal value is a value indicated by a multi-valued signal, such as a torque signal output from a robot hand having a value larger than two values. Therefore, Aoki’s multi-valued signal corresponds to the multilevel signal, and Aoki’s operation data corresponds to the operation data containing the multilevel signal)
Aoki does not explicitly teach to calculating […] a probability that a signal value of […a multilevel signal contained in operation data …] and […] on a basis of the probability.
However, Nakahara teaches:
calculating […] a probability that a signal value of […a multilevel signal contained in operation data …] (Nakahara, Par. [0081], “if the normal model is a normal model generated by machine learning, the prediction value calculation unit 314 calculates the probability that the signal value of the prediction value which is a next value of the log data of the control apparatus 2 is 1, by inputting to the normal model, the acquired log data in the past of the control apparatus 2”, thus calculating […] a probability that a signal value of […a multilevel signal contained in operation data …] is disclosed, because Nakahara teaches that, when the normal model is generated by machine learning, the prediction value calculation unit calculates a probability that the signal value of the prediction value, which is a next value of the log data of the control apparatus, is 1 by inputting past log data to the normal model. Nakahara’s log data corresponds to operation data, and Nakahara’s calculated probability that the next signal value is 1 corresponds to calculating a probability associated with a signal value contained in the operation data)
[…] on a basis of the probability (Nakahara, Par. [0081], the prediction value calculation unit 314 calculates the probability that the signal value of the prediction value which is a next value of the log data of the control apparatus 2 is 1, by inputting to the normal model, the acquired log data in the past of the control apparatus 2. Besides, the probability that the signal value of the prediction value of the log data of the control apparatus 2 is 1 calculated by the prediction value calculation unit 314 is the accuracy degree of the prediction value indicating the accuracy of the prediction value. Here, since the actual measurement value of the log data of the control apparatus 2 is a binary digital signal, a fact that the probability of the signal value of the prediction value of the log data of the control apparatus 2”, thus […] on a basis of the probability is disclosed, because Nakahara teaches that the prediction value calculation unit calculates a probability that the signal value of the prediction value, which is the next value of the log data, is 1 by inputting past log data to the normal model. Nakahara further teaches that the calculated probability is the accuracy degree of the prediction value, indicating the accuracy of the prediction value. Therefore, Nakahara uses the calculated probability as a basis for determining the prediction/normal state information of the log data)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine Aoki’s teaching of setting at least one threshold value for a multilevel signal contained in operation data, converting the multilevel signal into at least one binary signal using the threshold value, inputting the converted binary signal to a prediction model, and calculating a converted binary signal prediction value, with Nakahara’s teaching of calculating a probability that a signal value of log data exists as a predicted signal value and using the probability as an accuracy degree of the prediction value. Aoki teaches using threshold values and a prediction model to process multilevel operation data, while Nakahara teaches determining prediction/normal-state information on a basis of probability. Therefore, a POSITA would have been motivated to incorporate Nakahara’s probability-based prediction teaching into Aoki’s threshold-based prediction system so that the system could calculate, based on the converted binary signal prediction value and the threshold value, a probability that a signal value of the multilevel signal exists in a range determined based on the threshold value, and determine the steady range of the multilevel signal on a basis of the probability (Nakahara, Par. [0003], “there is an increasing demand for anomaly detection for early detection of apparatus anomalies. As a method for achieving this, there is a display method that facilitates detection of the anomaly by a user who uses the apparatus, by displaying log data acquired from the apparatus while separating the log data in a normal state from the log data in an anomalous state”, & Par. [0008], “The present invention aims to realize a display apparatus which displays a display screen targeting log data of a device which is a binary digital signal and is capable of displaying that the log data deviates from a normal state and displaying its degree of deviation, when the log data is in an anomalous state”)
Regarding Claim 15, Aoki teaches:
a conversion process of setting at least one threshold value for the multilevel signal contained in the operation data, and converting the multilevel signal into at least one binary signal with using the threshold value (Aoki, Page 5, “The threshold group calculation unit 112 calculates a threshold group for each multi-valued signal data included in the operation database 198. The threshold group is one or more thresholds used for converting each multi-value signal value in the multi-value signal data into one or more binary signal values (binary signal value group).”, & Page 7, “The conversion unit 113 converts each multi-valued signal value in the multi-valued signal data into a binary signal value by using the threshold value group for each multi-valued signal data. That is, the conversion unit 113 converts each multi-valued signal data into binary signal data”, thus a conversion process of setting at least one threshold value for the multilevel signal contained in the operation data and converting the multilevel signal into at least one binary signal using the threshold value is disclosed, because Aoki teaches that the threshold group calculation unit calculates a threshold group for each multi-valued signal data included in the operation database, where the threshold group includes one or more thresholds used for converting each multi-value signal value into one or more binary signal values. Aoki further teaches that the conversion unit converts each multi-valued signal value in the multi-valued signal data into a binary signal value by using the threshold value group. Aoki’s multi-valued signal data corresponds to the multilevel signal contained in the operation data, the threshold group corresponds to the at least one threshold value, and the conversion of each multi-valued signal value into a binary signal value corresponds to converting the multilevel signal into at least one binary signal using the threshold value),
a prediction process of inputting the converted binary signal to a prediction model which predicts a steady-state signal value of the operation data, and calculating a prediction value of the converted binary signal as a converted binary signal prediction value (Aoki, Page 10, “The operation database 199 includes a binary signal value of each binary signal before the target time and a binary signal value group of each multivalued signal before the target time. The set of the binary signal value of each binary signal at the target time and the binary signal value group of each multivalued signal at the target time is referred to as a "target signal value group". Each time before the target time is referred to as "past time". The set of the binary signal value of each binary signal at each past time and the binary signal value group of each multivalued signal at each past time is referred to as a "past signal value group", & Page 10, “In step S230, the prediction unit 123 reads the past signal value group from the operation database 199. The prediction unit 123 calculates the prediction model 191 by inputting the past signal value group. As a result, the predicted signal value group of the target time is calculated”, thus a prediction process of inputting the converted binary signal to a prediction model which predicts a steady-state signal value of the operation data, and calculating a prediction value of the converted binary signal as a converted binary signal prediction value is disclosed, because Aoki teaches that the operation database includes binary signal values before the target time and binary signal value groups of multivalued signals before the target time, which are referred to as a past signal value group. Aoki further teaches that the prediction unit reads the past signal value group from the operation database, inputs the past signal value group to the prediction model, and calculates the predicted signal value group of the target time. Aoki’s past signal value group corresponds to the converted binary signal input to the prediction model, and Aoki’s predicted signal value group of the target time corresponds to the converted binary signal prediction value because it is calculated by the prediction model based on the binary signal values of the operation data),
[…], based on the converted binary signal prediction value and the threshold value, […] the multilevel signal contained in the operation data exists in a range determined based on the threshold value (Aoki, Page 8, “In the first binary signal, the binary signal value at each time indicates the magnitude relationship between the target signal value and the first threshold value as binary values. In the second binary signal, the binary signal value at each time indicates the magnitude relationship between the target signal value and the second threshold value as two values. When the target signal value is equal to or higher than the target threshold value, the conversion unit 113 converts the target signal value to “1”. When the target signal value is less than the target threshold value, the conversion unit 113 converts the target signal value to “0””, thus […], based on the converted binary signal prediction value and the threshold value, […] the multilevel signal contained in the operation data exists in a range determined based on the threshold value is disclosed, because Aoki teaches that each binary signal value indicates a magnitude relationship between a target signal value and a threshold value. Aoki further teaches that when the target signal value is equal to or higher than the target threshold value, the conversion unit converts the target signal value to “1,” and when the target signal value is less than the target threshold value, the conversion unit converts the target signal value to “0.” Therefore, Aoki’s threshold values define ranges of signal values, and Aoki’s binary conversion indicates whether the multilevel signal value exists in a range determined based on the threshold value),
and determining the steady range of the multilevel signal contained in the operation data, […] (Aoki, Page 3, “The multi-valued signal value is a value indicated by the multi-valued signal. For example, the signal output from the robot hand is a multi-valued signal indicating the torque of the robot hand with a value larger than two values”, & Page 2, “Each facility 221 comprises one or more devices. For example, each facility 221 includes a sensor, a robot, and the like. Each facility 221 outputs data indicating the operating status at each time. Data indicating the operating status at each time is referred to as "operating data". The operation data is also referred to as collected data, signal data or status signal data. The operation data includes one or more binary signal values and one or more multi-valued signal values”, thus and to determine the steady range of the multilevel signal contained in the operation data is disclosed, because Aoki teaches that each facility outputs data indicating an operating status at each time, and that such data is referred to as operation data. Aoki further teaches that the operation data includes one or more multi-valued signal values, and that a multi-valued signal value is a value indicated by a multi-valued signal, such as a torque signal output from a robot hand having a value larger than two values. Therefore, Aoki’s multi-valued signal corresponds to the multilevel signal, and Aoki’s operation data corresponds to the operation data containing the multilevel signal)
Aoki does not explicitly teach to a range determination process of calculating […] a probability that a signal value of […a multilevel signal contained in operation data …] and […] on a basis of the probability.
However, Nakahara teaches:
a range determination process of calculating […] a probability that a signal value of […a multilevel signal contained in operation data …] (Nakahara, Par. [0081], “if the normal model is a normal model generated by machine learning, the prediction value calculation unit 314 calculates the probability that the signal value of the prediction value which is a next value of the log data of the control apparatus 2 is 1, by inputting to the normal model, the acquired log data in the past of the control apparatus 2”, thus a range determination process of calculating […] a probability that a signal value of […a multilevel signal contained in operation data …] is disclosed, because Nakahara teaches that, when the normal model is generated by machine learning, the prediction value calculation unit calculates a probability that the signal value of the prediction value, which is a next value of the log data of the control apparatus, is 1 by inputting past log data to the normal model. Nakahara’s log data corresponds to operation data, and Nakahara’s calculated probability that the next signal value is 1 corresponds to calculating a probability associated with a signal value contained in the operation data)
[…] on a basis of the probability (Nakahara, Par. [0081], the prediction value calculation unit 314 calculates the probability that the signal value of the prediction value which is a next value of the log data of the control apparatus 2 is 1, by inputting to the normal model, the acquired log data in the past of the control apparatus 2. Besides, the probability that the signal value of the prediction value of the log data of the control apparatus 2 is 1 calculated by the prediction value calculation unit 314 is the accuracy degree of the prediction value indicating the accuracy of the prediction value. Here, since the actual measurement value of the log data of the control apparatus 2 is a binary digital signal, a fact that the probability of the signal value of the prediction value of the log data of the control apparatus 2”, thus […] on a basis of the probability is disclosed, because Nakahara teaches that the prediction value calculation unit calculates a probability that the signal value of the prediction value, which is the next value of the log data, is 1 by inputting past log data to the normal model. Nakahara further teaches that the calculated probability is the accuracy degree of the prediction value, indicating the accuracy of the prediction value. Therefore, Nakahara uses the calculated probability as a basis for determining the prediction/normal state information of the log data)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine Aoki’s teaching of setting at least one threshold value for a multilevel signal contained in operation data, converting the multilevel signal into at least one binary signal using the threshold value, inputting the converted binary signal to a prediction model, and calculating a converted binary signal prediction value, with Nakahara’s teaching of calculating a probability that a signal value of log data exists as a predicted signal value and using the probability as an accuracy degree of the prediction value. Aoki teaches using threshold values and a prediction model to process multilevel operation data, while Nakahara teaches determining prediction/normal-state information on a basis of probability. Therefore, a POSITA would have been motivated to incorporate Nakahara’s probability-based prediction teaching into Aoki’s threshold-based prediction system so that the system could calculate, based on the converted binary signal prediction value and the threshold value, a probability that a signal value of the multilevel signal exists in a range determined based on the threshold value, and determine the steady range of the multilevel signal on a basis of the probability (Nakahara, Par. [0003], “there is an increasing demand for anomaly detection for early detection of apparatus anomalies. As a method for achieving this, there is a display method that facilitates detection of the anomaly by a user who uses the apparatus, by displaying log data acquired from the apparatus while separating the log data in a normal state from the log data in an anomalous state”, & Par. [0008], “The present invention aims to realize a display apparatus which displays a display screen targeting log data of a device which is a binary digital signal and is capable of displaying that the log data deviates from a normal state and displaying its degree of deviation, when the log data is in an anomalous state”)
Claims 5 is rejected under 35 U.S.C. 103 as being unpatentable over Aoki et al. (hereafter Aoki) (JP 6790311) in view of Nakahara et al. (hereinafter Nakahara) (US 20200380743), and further in view of Wang et al. (hereinafter Wang, a non-patent literature reference titled “A simple new approach to variable selection in regression, with application to genetic fine mapping”).
Regarding Claim 5, Aoki combined with Nakahara teaches all the limitations of claim 4 as cited above and Aoki further teaches:
wherein the processing circuitry selects, from among ranges each determined based on the threshold value, […] , each as the steady range (Aoki, Page 6, “For example, the threshold group calculation unit 112 generates a frequency distribution graph as shown in FIG. "Section" means the range of signal values”, & Page 6, “the threshold group calculation unit 112 calculates a value between the signal value corresponding to one peak and the signal value corresponding to the other peak for each peak. Each calculated value becomes a threshold value”, thus wherein the processing circuitry selects, from among ranges each determined based on the threshold value, […] , each as the steady range is disclosed, because Aoki teaches that the threshold group calculation unit generates a frequency distribution graph, and that a section means a range of signal values. Aoki further teaches that the threshold group calculation unit calculates values between peaks, and that each calculated value becomes a threshold value. Therefore, Aoki’s sections correspond to ranges, and Aoki’s threshold values determine the ranges from among which the processing circuitry selects)
Aoki combined with Nakahara does not explicitly teach […] ranges in a descending order of probability, and determines ranges selected until the probabilities total up to a determined value or more […].
However, Wang teaches:
[…] ranges in a descending order of probability, and determines ranges selected until the probabilities total up to a determined value or more […] (Wang, Page 6- Section 3.2, “In brief, this involves sorting variables by decreasing αj, then including variables in the CS until their cumulative probability exceeds ρ”, thus […] ranges in a descending order of probability, and determines ranges selected until the probabilities total up to a determined value or more […] is disclosed, because Wang teaches sorting variables by decreasing αj and including variables until their cumulative probability exceeds ρ. Wang’s decreasing αj corresponds to descending order of probability, and Wang’s cumulative probability exceeding ρ corresponds to selecting items until the probabilities total up to a determined value or more)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to further combine Aoki and Nakahara with Wang’s teaching of sorting candidates in decreasing probability order and selecting candidates until their cumulative probability exceeds a determined value. Aoki and Nakahara teach determining steady/normal ranges of operation data using threshold-determined ranges and probability information, while Wang teaches a simple and computationally scalable probability-based selection technique that captures uncertainty, identifies high-probability credible sets, and prioritizes candidates within each set. Therefore, a POSITA would have been motivated to apply Wang’s descending-order and cumulative-probability selection technique to the probability values associated with the threshold-determined ranges in the Aoki-Nakahara system, thereby improving the system by providing a simple and reliable rule for selecting high-probability steady ranges until the selected probabilities satisfy a desired confidence level (Wang, Page 2 – Introduction, “Here we develop a new approach to this problem that has several attractive features: it is simple, computationally scaleable, and it provides new, more effective, ways to capture uncertainty in which variables should be selected. Our new approach is particularly helpful in situations involving highly correlated variables, where it may be impossible to confidently select any individual variable, but it may nonetheless be possible to confidently draw useful conclusions such as “either variable A or B is relevant”. More generally it may be possible to confidently identify “Credible Sets” of (cor related) variables, that each, with high probability, contain a relevant variable. Our new approach can quickly, simply and reliably identify such sets, as well as prioritize the variables within each set”)
Claims 6 is rejected under 35 U.S.C. 103 as being unpatentable over Aoki et al. (hereafter Aoki) (JP 6790311) in view of Nakahara et al. (hereinafter Nakahara) (US 20200380743) in view of Michael et al. (hereinafter Michael) (WO 2020173740), and further in view of. Wang et al. (hereinafter Wang, a non-patent literature reference titled “A simple new approach to variable selection in regression, with application to genetic fine mapping”).
Regarding Claim 6, Aoki combined with Nakahara teaches all the limitations of claim 4 as cited above and Aoki further teaches:
wherein the processing circuitry [….] selecting, from among ranges each determined based on the threshold value, […] (Aoki, Page 6, “For example, the threshold group calculation unit 112 generates a frequency distribution graph as shown in FIG. "Section" means the range of signal values.”, & Page 6, “the threshold group calculation unit 112 calculates a value between the signal value corresponding to one peak and the signal value corresponding to the other peak for each peak. Each calculated value becomes a threshold value”, thus wherein the processing circuitry [….] selecting, from among ranges each determined based on the threshold value, […] is disclosed, because Aoki teaches that the threshold group calculation unit generates a frequency distribution graph and that a section means a range of signal values. Aoki further teaches that the threshold group calculation unit calculates a value between signal values corresponding to peaks, and that each calculated value becomes a threshold value. Therefore, Aoki’s sections correspond to ranges, and Aoki’s calculated threshold values determine the ranges from among which the processing circuitry selects)
Aoki combined with Nakahara does not explicitly teach […] repeats […] a range where the probability is maximum and selecting, from among ranges adjacent to the selected range, a range where the probability is larger and determines ranges selected until the probabilities total up to a determined value or more, each as the steady range.
However, Michael teaches:
[…] repeats […] a range where the probability is maximum and selecting, from among ranges adjacent to the selected range, a range where the probability is larger (Michael, Page 2, “determine a first probabilistic model describing dynamics of the time series data inside the first time window;- determine a second probabilistic model describing dynamics of the time series data adjacent to the first time window”, & Page 5, “This first and second probabilistic model 225, 235 may each be provided in the form of a function which, for a certain data point or time interval of the time series data 20 , out puts a probability of observing this data point time interval”, & Page 5, “the first probabilistic model 225 and the second probabilistic model 235 may thus allow for deciding whether a certain time interval of the time series data 20 better matches the dynamic of the time series data 20 inside the time window 21 or the dynamic of the time series data 20 outside the time window 21”, & Page 6, “the analysis tool 200 may operate in an iterative manner . That is to say, the time se ries data 20 with the updated label may be fed back to the memory 210 and the above-described processes repeated, with the refined time window 21 ' then taking the place of a new initial time window . Such iterations may be repeated until a certain stopping criterion is met”, thus […] repeats […] a range where the probability is maximum and selecting, from among ranges adjacent to the selected range, a range where the probability is larger is disclosed, because Michael teaches determining a first probabilistic model for time-series data inside a first time window and a second probabilistic model for time-series data adjacent to the first time window. Michael further teaches that each probabilistic model outputs a probability for a data point or time interval, and that the probabilistic models allow deciding whether a time interval better matches the dynamics inside or outside the time window. Michael also teaches that the analysis tool operates iteratively, where the updated time-series data is fed back and the above-described processes are repeated with the refined time window taking the place of a new initial time window. Therefore, Michael teaches repeatedly selecting or refining a range based on probability and selecting adjacent ranges based on larger probability-based matching)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to further combine Aoki and Nakahara with Michael’s teaching of iteratively refining time-series ranges using adjacent probabilistic models. Aoki and Nakahara teach threshold-determined ranges and probability-based steady/normal range determination, while Michael teaches determining probabilistic models for data inside a time window and data adjacent to the time window, using those models to determine which parts of the time-series data match each probabilistic model, and repeating the refinement process. Michael further teaches that iterating the refinement of the time window multiple times successively improves the preciseness of the time-window setting. Therefore, a POSITA would have been motivated to apply Michael’s iterative adjacent-range probability refinement to the threshold-determined ranges in the Aoki-Nakahara system, thereby improving the system by repeatedly selecting/refining ranges based on probability and adjacent-range comparison until the selected ranges satisfy the cumulative probability requirement (Michael, Page 3, “determine a fourth probabilistic model describing dynamics of the time series data adjacent to the second time window;- based on the third probabilistic model and the fourth prob abilistic model , determining a third part of the time series data that is estimated to match the third probabilistic model and a fourth part of the time series data that is estimated to match the fourth probabilistic model ; and- determine third label information indicating a third time window which includes the third part of the time series data and excludes the fourth part of the time series data . Accordingly, the device may operate in an iterative manner by iterating the refinement of the time window multiple times , thereby successively further improving preciseness the set ting of the time window”)
Aoki and Nakahara combined with Michael does not explicitly teach and determines ranges selected until the probabilities total up to a determined value or more, each as […].
However, Wang teaches:
and determines ranges selected until the probabilities total up to a determined value or more, each as […](Wang, Page 6 – Section 2.3, “In brief, this involves sorting variables by decreasing αj, then including variables in the CS until their cumulative probability exceeds ρ”, thus and determines ranges selected until the probabilities total up to a determined value or more, each as [….] is disclosed, because Wang teaches including variables in a credible set until their cumulative probability exceeds ρ. Wang’s cumulative probability exceeding ρ corresponds to the probabilities total up to a determined value or more, and Wang’s included variables correspond to selected ranges)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to further combine Aoki, Nakahara, and Michael with Wang’s teaching of selecting items in descending order of probability and including selected items until their cumulative probability exceeds a determined value. Aoki and Nakahara teach threshold-determined ranges and probability-based steady/normal range determination, and Michael teaches repeatedly refining adjacent time-series ranges using probabilistic models. Wang teaches a simple and computationally scalable probability-based selection technique that captures uncertainty, identifies high-probability credible sets, and prioritizes variables within each set. Therefore, a POSITA would have been motivated to apply Wang’s cumulative-probability selection technique to the ranges selected in the Aoki/Nakahara/Michael system, thereby improving the system by providing a simple and reliable rule for determining selected ranges as steady ranges until the probabilities total up to a determined value or more (Wang, Page 2 – Introduction, “Here we develop a new approach to this problem that has several attractive features: it is simple, computationally scaleable, and it provides new, more effective, ways to capture uncertainty in which variables should be selected. Our new approach is particularly helpful in situations involving highly correlated variables, where it may be impossible to confidently select any individual variable, but it may nonetheless be possible to confidently draw useful conclusions such as “either variable A or B is relevant”. More generally it may be possible to confidently identify “Credible Sets” of (correlated) variables, that each, with high probability, contain a relevant variable. Our new approach can quickly, simply and reliably identify such sets, as well as prioritize the variables within each set”)
Claims 7-8 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Aoki et al. (hereafter Aoki) (JP 6790311) in view of Nakahara et al. (hereinafter Nakahara) (US 20200380743), and further in view of Ryota et al. (hereinafter Ryota) (WO 2019111435).
Regarding Claim 7, Aoki combined with Nakahara teaches all the limitations of claim 1 as cited above and Aoki further teaches:
wherein the processing circuitry determines, from among ranges each determined based on the threshold value, […] as the steady range (Aoki, Page 6, “For example, the threshold group calculation unit 112 generates a frequency distribution graph as shown in FIG. "Section" means the range of signal values”, & Page 6, “the threshold group calculation unit 112 calculates a value between the signal value corresponding to one peak and the signal value corresponding to the other peak for each peak. Each calculated value becomes a threshold value”, thus wherein the processing circuitry determines, from among ranges each determined based on the threshold value, […] as the steady range is disclosed, because Aoki teaches that the threshold group calculation unit generates a frequency distribution graph, and that a section means a range of signal values. Aoki further teaches that the threshold group calculation unit calculates a value between the signal value corresponding to one peak and the signal value corresponding to another peak, and that each calculated value becomes a threshold value. Therefore, Aoki’s sections correspond to ranges, and Aoki’s calculated threshold values determine the ranges from among which the processing circuitry determines the steady range)
Aoki combined with Nakahara does not explicitly teach […] a range where a probability density being a value obtained by dividing the probability by a width of the range has a determined value or more, […].
However, Ryota teaches:
[…] a range where a probability density being a value obtained by dividing the probability by a width of the range has a determined value or more, […] (Ryota, Page 3, “the degree of abnormality may be an amount (likelihood function (probability density function) or the like) that represents the likelihood of occurrence of the signal. That is, the abnormality degree may be the likelihood of a signal”, & Page 3, “the abnormality determination unit 104 determines the presence or absence of an abnormality using the conversion result by the conversion unit 103 and the threshold value”, thus […] a range where a probability density being a value obtained by dividing the probability by a width of the range has a determined value or more, […] is disclosed or rendered obvious, because Ryota teaches using a likelihood function, such as a probability density function, as a degree of abnormality representing the likelihood of occurrence of a signal. Ryota further teaches determining abnormality using a conversion result and a threshold value. In the combined Aoki-Ryota system, Aoki’s threshold values define ranges of signal values, and applying Ryota’s probability-density teaching to those threshold-defined ranges would result in evaluating the likelihood per unit range width. Therefore, dividing the probability of a threshold-defined range by the width of that range is an obvious way to obtain a probability-density value for comparing the ranges)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to further combine Aoki and Nakahara with Ryota’s teaching of using a probability density function as an abnormality/likelihood measure for determining whether a signal is abnormal. Aoki and Nakahara teach determining steady/normal ranges of operation data using threshold-determined ranges and probability information, while Ryota teaches that it is important to determine whether a device or system is operating normally and teaches converting an abnormality-degree value according to a predetermined probability distribution so that abnormality determination can be made without depending on the distribution of the signal. Therefore, a POSITA would have been motivated to apply Ryota’s probability density based abnormality determination to the threshold-determined ranges in the Aoki-Nakahara system, thereby improving the system by allowing the steady range to be determined using a normalized probability-density value for each threshold-defined range (Ryota, Page 2, “It is important to determine whether a device or system performing a predetermined process is operating normally, that is, to determine whether or not an abnormality has occurred in a signal obtained from the device or system”, & Page 3, “According to the abnormality determination device 1, the conversion unit 2 converts the value indicating the abnormality degree of the signal into a random variable value according to a predetermined probability distribution (specific probability distribution). That is, the value indicating the degree of abnormality of the signal is converted into a random variable value whose range and distribution are specified in advance. Therefore, the determination as to the presence or absence of abnormality can be made without depending on the distribution of the signal”)
Regarding Claim 8, Aoki combined with Nakahara teaches all the limitations of claim 1 as cited above and Aoki further teaches:
wherein the processing circuitry determines, from among ranges each determined based on the threshold value, […] as the steady range (Aoki, Page 6, “For example, the threshold group calculation unit 112 generates a frequency distribution graph as shown in FIG. "Section" means the range of signal values”, & Page 6, “the threshold group calculation unit 112 calculates a value between the signal value corresponding to one peak and the signal value corresponding to the other peak for each peak. Each calculated value becomes a threshold value”, thus wherein the processing circuitry determines, from among ranges each determined based on the threshold value, […] as the steady range is disclosed, because Aoki teaches that the threshold group calculation unit generates a frequency distribution graph, and that a section means a range of signal values. Aoki further teaches that the threshold group calculation unit calculates a value between the signal value corresponding to one peak and the signal value corresponding to another peak, and that each calculated value becomes a threshold value. Therefore, Aoki’s sections correspond to ranges, and Aoki’s calculated threshold values determine the ranges from among which the processing circuitry determines the steady range)
Aoki combined with Nakahara does not explicitly teach […] a range where a probability density being a value obtained by dividing the probability by a width of the range is maximum, […].
However, Ryota teaches:
[…] a range where a probability density being a value obtained by dividing the probability by a width of the range is maximum, […] (Ryota, Page 3, “the degree of abnormality may be an amount (likelihood function (probability density function) or the like) that represents the likelihood of occurrence of the signal. That is, the abnormality degree may be the likelihood of a signal”, & Page 2, “The monitoring method performs network validation by using a threshold criterion for estimates of joint probability density functions”, & Page 15, “Therefore, the value of the transformation function f .sub.4 (x) takes the minimum value f .sub.4 (x) = 0 when x ≦ 0, and when x is greater than or equal to the maximum value of the likelihood function p .sub.0 (z) It is a monotonically increasing function that takes the maximum value f .sub.4 (x) = 1”, thus […] a range where a probability density being a value obtained by dividing the probability by a width of the range is maximum, […] is disclosed, because Ryota teaches using a likelihood function, such as a probability density function, as a degree of abnormality representing the likelihood of occurrence of a signal. Ryota further teaches network validation using a threshold criterion for estimates of joint probability density functions and teaches a maximum value of a likelihood function. Therefore, Ryota’s probability density function corresponds to the probability-density-based value, and Ryota’s maximum likelihood function supports selecting the range having the maximum probability-density-based value. In the combined Aoki-Ryota system, Aoki’s threshold values define ranges of signal values, and applying Ryota’s probability-density teaching to those threshold-defined ranges would result in determining the range having the maximum probability density)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to further combine Aoki and Nakahara with Ryota’s teaching of using a probability density function as an abnormality/likelihood measure for determining whether a signal is abnormal. Aoki and Nakahara teach determining steady/normal ranges of operation data using threshold-determined ranges and probability information, while Ryota teaches that it is important to determine whether a device or system is operating normally and teaches converting an abnormality-degree value according to a predetermined probability distribution so that abnormality determination can be made without depending on the distribution of the signal. Therefore, a POSITA would have been motivated to apply Ryota’s probability density based abnormality determination to the threshold-determined ranges in the Aoki-Nakahara system, thereby improving the system by allowing the steady range to be determined using a normalized probability-density value for each threshold-defined range (Ryota, Page 2, “It is important to determine whether a device or system performing a predetermined process is operating normally, that is, to determine whether or not an abnormality has occurred in a signal obtained from the device or system”, & Page 3, “According to the abnormality determination device 1, the conversion unit 2 converts the value indicating the abnormality degree of the signal into a random variable value according to a predetermined probability distribution (specific probability distribution). That is, the value indicating the degree of abnormality of the signal is converted into a random variable value whose range and distribution are specified in advance. Therefore, the determination as to the presence or absence of abnormality can be made without depending on the distribution of the signal”)
Regarding Claim 12, Aoki and Nakahara combined with Ryota teaches all the limitations of claim 7 as cited above and Aoki further teaches:
wherein the processing circuitry determines, regarding the ranges each determined based on the threshold value, […] (Aoki, Page 6, “For example, the threshold group calculation unit 112 generates a frequency distribution graph as shown in FIG. "Section" means the range of signal values”, & Page 6, “the threshold group calculation unit 112 calculates a value between the signal value corresponding to one peak and the signal value corresponding to the other peak for each peak. Each calculated value becomes a threshold value”, thus wherein the processing circuitry determines, regarding the ranges each determined based on the threshold value, […] is disclosed, because Aoki teaches that the threshold group calculation unit generates a frequency distribution graph, and that a section means a range of signal values. Aoki further teaches that the threshold group calculation unit calculates a value between signal values corresponding to peaks, and that each calculated value becomes a threshold value. Therefore, Aoki’s sections correspond to ranges, and Aoki’s calculated threshold values correspond to threshold values that determine the ranges regarding which the processing circuitry makes the determination)
Nakahara teaches:
[…] an unsteadiness degree of a range that is not steady, […] (Nakahara, Par. [0081], “the probability that the signal value of the prediction value of the log data of the control apparatus 2 is 1 calculated by the prediction value calculation unit 314 is the accuracy degree of the prediction value indicating the accuracy of the prediction value”, & Par. [0118], “the display screen generated by the display screen generation unit 413 directly indicates deviation degree that indicates how much the actual measurement value of the log data of the control apparatus 2 deviates from the prediction value area 7 indicating the range of the normal state so that the user can visually recognize on the display screen whether or not the log data of the control apparatus 2 deviates from the normal state and, if deviating, the user can visually recognize the degree of the deviation”, thus […] an unsteadiness degree of a range that is not steady, […] is disclosed, because Nakahara teaches that the calculated probability is the accuracy degree of the prediction value and teaches that the display screen directly indicates a deviation degree showing how much the actual measurement value deviates from the prediction value area indicating the normal-state range. Nakahara’s prediction value area corresponds to the steady/normal range, and Nakahara’s deviation degree corresponds to the unsteadiness degree because it indicates the extent to which the actual measurement value departs from the normal-state range)
Ryota teaches:
[…] according to the probability density being the value obtained by dividing the probability by the width of the range (Ryota, Page 3, “the degree of abnormality may be an amount (likelihood function (probability density function) or the like) that represents the likelihood of occurrence of the signal. That is, the abnormality degree may be the likelihood of a signal”, & Page 14, “Here, the degree of abnormality may be the value of the likelihood function (probability density function) of the distribution of the signal”, thus […] according to the probability density being the value obtained by dividing the probability by the width of the range is disclosed, because Ryota teaches that the degree of abnormality may be a likelihood function, such as a probability density function, representing the likelihood of occurrence of a signal. Ryota further teaches that the degree of abnormality may be the value of the likelihood function/probability density function of the signal distribution. Therefore, Ryota’s probability density function corresponds to the probability-density-based value used to determine the unsteadiness degree, and applying that probability-density teaching to Aoki’s threshold-defined ranges would result in evaluating probability per unit range width)
Claims 9 is rejected under 35 U.S.C. 103 as being unpatentable over Aoki et al. (hereafter Aoki) (JP 6790311) in view of Nakahara et al. (hereinafter Nakahara) (US 20200380743) in view of Ryota et al. (hereinafter Ryota) (WO 2019111435), and further in view of Wang et al. (hereinafter Wang, a non-patent literature reference titled “A simple new approach to variable selection in regression, with application to genetic fine mapping”).
Regarding Claim 9, Aoki and Nakahara combined with Ryota teaches all the limitations of claim 8 as cited above and Aoki further teaches:
wherein the processing circuitry selects, from among ranges each determined based on the threshold value, […], each as the steady range (Aoki, Page 6, “For example, the threshold group calculation unit 112 generates a frequency distribution graph as shown in FIG. "Section" means the range of signal values”, & Page 6, “the threshold group calculation unit 112 calculates a value between the signal value corresponding to one peak and the signal value corresponding to the other peak for each peak. Each calculated value becomes a threshold value”, thus wherein the processing circuitry selects, from among ranges each determined based on the threshold value, […], each as the steady range is disclosed, because Aoki teaches that the threshold group calculation unit generates a frequency distribution graph, and that a section means a range of signal values. Aoki further teaches that the threshold group calculation unit calculates a value between signal values corresponding to peaks, and that each calculated value becomes a threshold value. Therefore, Aoki’s sections correspond to ranges, and Aoki’s calculated threshold values determine the ranges from among which the processing circuitry selects)
Ryota further teaches:
[…] probability density being a value obtained by dividing the probability by a width of the range, […] the probability densities […] (Ryota, Page 3, “the degree of abnormality may be an amount (likelihood function (probability density function) or the like) that represents the likelihood of occurrence of the signal. That is, the abnormality degree may be the likelihood of a signal”, & Page 6, “When using a probability density function (likelihood function) or Mahalanobis distance as the degree of abnormality, even if the value of the degree of abnormality changes due to changes in the signal distribution (probability density function) or the Mahalanobis space”, thus […] probability density being a value obtained by dividing the probability by a width of the range, […] the probability densities […] is disclosed, because Ryota teaches that the degree of abnormality may be a likelihood function, such as a probability density function, representing the likelihood of occurrence of a signal. Ryota further teaches using a probability density function as the degree of abnormality and recognizes that the value of the degree of abnormality changes due to changes in the signal distribution. Therefore, Ryota’s probability density function corresponds to the probability-density-based value, and in the combined Aoki-Ryota system, applying Ryota’s probability-density teaching to Aoki’s threshold-defined ranges would result in determining probability densities for the respective ranges)
Aoki and Nakahara combined with Ryota does not explicitly teach [...] ranges in a descending order of [….] and determines ranges selected until […probabilities. …] total up to a determined value or more […].
However, Wang teaches:
[...] ranges in a descending order of [….] and determines ranges selected until […probabilities. …] total up to a determined value or more […] (Wang, Page 6 – Section 2.3, “this involves sorting variables by decreasing αj, then including variables in the CS until their cumulative probability exceeds ρ”, thus [...] ranges in a descending order of [….] and determines ranges selected until […probabilities…] total up to a determined value or more […] is disclosed, because Wang teaches sorting variables by decreasing αj and including variables in the credible set until their cumulative probability exceeds ρ. Wang’s sorting by decreasing αj corresponds to selecting in descending order of probability, and Wang’s cumulative probability exceeding ρ corresponds to selecting until the probabilities total up to a determined value or more)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to further combine Aoki, Nakahara, and Ryota with Wang’s teaching of sorting candidates in decreasing probability order and including selected candidates until their cumulative probability exceeds a determined value. Aoki and Nakahara teach threshold-determined ranges and probability-based steady/normal range determination, and Ryota teaches using probability density as a likelihood/abnormality measure for signals. Wang teaches a simple and computationally scalable selection approach that captures uncertainty, identifies high-probability credible sets, and prioritizes variables within each set. Therefore, a POSITA would have been motivated to apply Wang’s descending-order and cumulative-selection technique to the probability-density values associated with the threshold-determined ranges in the Aoki-Nakahara-Ryota system, thereby improving the system by allowing it to prioritize ranges by probability density and select ranges until the selected probability-density values total up to a determined value or more (Wang, Page 2 – Introduction, “Here we develop a new approach to this problem that has several attractive features: it is simple, computationally scaleable, and it provides new, more effective, ways to capture uncertainty in which variables should be selected. Our new approach is particularly helpful in situations involving highly correlated variables, where it may be impossible to confidently select any individual variable, but it may nonetheless be possible to confidently draw useful conclusions such as “either variable A or B is relevant”. More generally it may be possible to confidently identify “Credible Sets” of (correlated) variables, that each, with high probability, contain a relevant variable. Our new approach can quickly, simply and reliably identify such sets, as well as prioritize the variables within each set”)
Claims 10 is rejected under 35 U.S.C. 103 as being unpatentable over Aoki et al. (hereafter Aoki) (JP 6790311) in view of Nakahara et al. (hereinafter Nakahara) (US 20200380743) in view of Wang et al. (hereinafter Wang, a non-patent literature reference titled “A simple new approach to variable selection in regression, with application to genetic fine mapping”) in view of Ryota et al. (hereinafter Ryota) (WO 2019111435), and further in view of Michael et al. (hereinafter Michael) (WO 2020173740).
Regarding Claim 10, Aoki and Nakahara combined with Ryota teaches all the limitations of claim 7 as cited above and Aoki further teaches:
wherein the processing circuitry […] selecting, from among ranges each determined based on the threshold value, […] (Aoki, Page 6, “For example, the threshold group calculation unit 112 generates a frequency distribution graph as shown in FIG. "Section" means the range of signal values.”, & Page 6, “the threshold group calculation unit 112 calculates a value between the signal value corresponding to one peak and the signal value corresponding to the other peak for each peak. Each calculated value becomes a threshold value”, thus wherein the processing circuitry [….] selecting, from among ranges each determined based on the threshold value, […] is disclosed, because Aoki teaches that the threshold group calculation unit generates a frequency distribution graph and that a section means a range of signal values. Aoki further teaches that the threshold group calculation unit calculates a value between signal values corresponding to peaks, and that each calculated value becomes a threshold value. Therefore, Aoki’s sections correspond to ranges, and Aoki’s calculated threshold values determine the ranges from among which the processing circuitry selects)
Ryota further teaches:
[…] a range where a probability density being a value obtained by dividing the probability by a width of the range is maximum and […] probability density […] (Ryota, Page 3, “the degree of abnormality may be an amount (likelihood function (probability density function) or the like) that represents the likelihood of occurrence of the signal. That is, the abnormality degree may be the likelihood of a signal”, & Page 14, “Here, the degree of abnormality may be the value of the likelihood function (probability density function) of the distribution of the signal”, & Page 15, “when x is greater than or equal to the maximum value of the likelihood function p .sub.0 (z) It is a monotonically increasing function that takes the maximum value f .sub.4 (x) = 1”, thus […] a range where a probability density being a value obtained by dividing the probability by a width of the range is maximum and […] probability density […] is disclosed, because Ryota teaches that the degree of abnormality may be a likelihood function, such as a probability density function, representing the likelihood of occurrence of a signal. Ryota further teaches that the degree of abnormality may be the value of the likelihood function/probability density function of the signal distribution, and teaches a maximum value of the likelihood function. Therefore, Ryota’s likelihood function/probability density function corresponds to the probability-density-based value, and Ryota’s maximum likelihood-function teaching supports selecting a range having the maximum probability-density-based value)
Aoki and Nakahara combined with Ryota does not explicitly teach […] repeats […] selecting, from among ranges adjacent to the selected range, a range where the […probability…] is larger and determines ranges selected until the probabilities total up to a determined value or more, […].
However, Michael teaches:
[…] repeats […] selecting, from among ranges adjacent to the selected range, a range where the […probability…] is larger (Michael, Page 7, “At block 540, the device determines a second probabilistic model describing dynamics of the time series data adjacent to the first time window”, & Page 7, “At block 550 , the device determines , based on the first probabilistic model and the second probabilistic model , a first part of the time series data that is estimated to match the first probabilistic model and a second part of the time series data that is estimated to match the second probabilistic model”, & Page 7, “In the HMM, state transitions between the hidden states of adjacent time intervals are determined based on the first probabilistic model and the second probabilistic model”, thus […] repeats […] selecting, from among ranges adjacent to the selected range, a range where the […probability…] is larger is disclosed, because Michael teaches determining a second probabilistic model describing dynamics of time-series data adjacent to a first time window. Michael further teaches determining, based on the first probabilistic model and the second probabilistic model, portions of the time-series data that are estimated to match the respective probabilistic models. Michael also teaches that state transitions between hidden states of adjacent time intervals are determined based on the probabilistic models. Therefore, Michael’s adjacent time intervals correspond to ranges adjacent to the selected range, and Michael’s probability-based matching of adjacent time intervals supports selecting an adjacent range where the probability-based match is larger)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to further combine Aoki, Nakahara, and Ryota with Michael’s teaching of using adjacent probabilistic models to iteratively refine time-series ranges. Aoki and Nakahara teach threshold-determined ranges and probability-based steady/normal range determination, and Ryota teaches using probability density as a likelihood/abnormality measure for selecting a maximum probability-density-based range. Michael teaches determining probabilistic models for data adjacent to a selected time window, determining which portions of the time-series data match the respective probabilistic models, and iterating the refinement of the time window multiple times. Therefore, a POSITA would have been motivated to apply Michael’s adjacent-range probabilistic refinement to the Aoki-Nakahara-Ryota system, thereby improving the system by allowing adjacent threshold-determined ranges to be repeatedly evaluated and selected based on probability based matching (Michael, Page 3, “determine a fourth probabilistic model describing dynamics of the time series data adjacent to the second time window;- based on the third probabilistic model and the fourth probabilistic model , determining a third part of the time series data that is estimated to match the third probabilistic model and a fourth part of the time series data that is estimated to match the fourth probabilistic model ; and- determine third label information indicating a third time window which includes the third part of the time series data and excludes the fourth part of the time series data . Accordingly, the device may operate in an iterative manner by iterating the refinement of the time window multiple times, thereby successively further improving preciseness the set ting of the time window”)
Aoki, Nakahara, and Ryota combined with Michael does not explicitly teach determines ranges selected until the probabilities total up to a determined value or more, […].
However, Wang teaches:
determines ranges selected until the probabilities total up to a determined value or more, […] (Wang, Page 6 – Section 2.3, “In brief, this involves sorting variables by decreasing αj, then including variables in the CS until their cumulative probability exceeds ρ”, thus determines ranges selected until the probabilities total up to a determined value or more, […] is disclosed, because Wang teaches sorting variables by decreasing αj and including variables in the credible set until their cumulative probability exceeds ρ. Wang’s cumulative probability exceeding ρ corresponds to the selected probabilities totaling up to a determined value or more)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to further combine Aoki, Nakahara, Ryota, and Michael with Wang’s teaching of sorting candidates in decreasing probability order and including selected candidates until their cumulative probability exceeds a determined value. Aoki and Nakahara teach threshold-determined ranges and probability-based steady/normal range determination, Ryota teaches using probability density as a likelihood measure for selecting a maximum probability-density-based range, and Michael teaches iteratively evaluating adjacent ranges using probabilistic models. Wang teaches a simple and computationally scalable selection approach that captures uncertainty, identifies high-probability credible sets, and prioritizes candidates within each set. Therefore, a POSITA would have been motivated to apply Wang’s cumulative-probability selection technique to the ranges selected in the Aoki-Nakahara-Ryota-Michael system, thereby improving the system by providing a simple and reliable stopping rule for selecting ranges until the selected probabilities total up to a determined value or more (Wang, Page 2 – Introduction, “Here we develop a new approach to this problem that has several attractive features: it is simple, computationally scaleable, and it provides new, more effective, ways to capture uncertainty in which variables should be selected. Our new approach is particularly helpful in situations involving highly correlated variables, where it may be impossible to confidently select any individual variable, but it may nonetheless be possible to confidently draw useful conclusions such as “either variable A or B is relevant”. More generally it may be possible to confidently identify “Credible Sets” of (correlated) variables, that each, with high probability, contain a relevant variable. Our new approach can quickly, simply and reliably identify such sets, as well as prioritize the variables within each set”)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. WO 2020049615 is pertinent because it teaches a signal display control device that receives observation signals from a monitored target, calculates probability information indicating whether the signal is normal, detects steady or unsteady periods based on probability/threshold information, and displays signal and probability graphs to help determine whether the signal is abnormal or normal. Because applicant’s disclosure similarly concerns signal processing, probability-based steady/unsteady determination, threshold-based evaluation, and displaying signal state information, the reference is relevant to the invention but is not relied upon in the rejection.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MAHLIET ADMASU whose telephone number is (571)272-0034. The examiner can normally be reached Mon-Fri, 8am-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Alexey Shmatov can be reached at (571)270-3428. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/M.T.A./Examiner, Art Unit 2123
/ALEXEY SHMATOV/Supervisory Patent Examiner, Art Unit 2123
Prosecution Insights