DETAILED ACTION
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 .
Response to Amendment
The amendment filed 05/18/2026 has been entered. As directed, claims 1, 4 and 5 have
been amended, no claim has been added or canceled. Thus claims 1-5 and 7 remain pending in the application.
Response to Arguments
With respect to the Applicant’s argued rejection under 35 U.S.C 101 in “Applicant Arguments/Remarks Made in an Amendment”:
Applicant argues:
…
Applicant respectfully submits that the pending claims recite patent-eligible subject matter. In particular, Applicant respectfully submits that representative amended claim 1 is not directed to an abstract idea, or at least integrates any alleged abstract idea into a practical application under Step 2A, Prong 2 of the eligibility analysis.
The Examiner previously asserted that the claims were recited at a high level of generality and could be performed mentally. Amended claim 1 now explicitly recites the specific technological flow of operations. For model construction, claim 1 recites determining a representative value by "indicating whether a predetermined number or more of pieces of observed data... are in an abnormal state" and processing this data to "determine a conditional probability representing a relationship between the representative observed data and states of apparatuses." For model application, claim 1 recites applying the model to "calculate a posterior probability for each apparatus... and identifying an apparatus... that yields a maximum posterior probability."
Similarly, amended claim 4 recites the technological flow of operations. For model construction, claim 4 recites storing a third causal model combining the first and second causal models "by modifying a conditional probability used for the first causal model based on a conditional probability used for the second causal model." For model application, claim 4 recites estimating the abnormality "by applying one of the first causal model, the second causal model, or the third causal model stored in the memory to the pieces of observed data to calculate a posterior probability for each apparatus of a plurality of apparatuses in the communication network system, and identifying an apparatus in the communication network system that yields a maximum posterior probability."
These steps recite a specific, technological process that grounds the claimed invention in computer technology. A human mind cannot practically ingest pieces of observed data from a communication network system, process representative observed data to determine conditional probabilities representing relationships with states of apparatuses, calculate individual posterior probabilities for each apparatus of a plurality of apparatuses in the communication network system, and identify the specific apparatus that yields a maximum posterior probability to locate a fault. These probabilistic calculations and optimization operations executed across a communication network system operate on a scale and complexity that preclude mental calculation or execution by pen and paper.
Because the amended claims explicitly tie the algorithmic process to a specific, practical application for network diagnostics via specialized probabilistic modeling, they improve the functioning of the diagnostic system itself and impose meaningful limits on the claim scope. For the foregoing reasons, Applicant respectfully requests the withdrawal of the § 101 rejections.
(see Response filed 05/18/2026 [pages 6-7]).
Applicant’s arguments regarding § 101 have been considered but are not persuasive.
Applicant argues that the amended claims recite a specific technological flow of operations and that a human mind cannot practically ingest observed data from a communication network system, determine conditional probabilities, calculate posterior probabilities for each apparatus, and identify the apparatus having the maximum posterior probability. However, the amended claim limitation is not commensurate with Applicant’s argument. The claims do not recite a particular volume of observed data, a particular number of apparatuses, performing dynamic network monitoring, or a specific computer implemented algorithm that would preclude performance of the recited analysis mentally or with the aid of pen and paper.
For claim 1, the steps of dividing observed data into clusters according to types of information, determining whether a predetermined number or more pieces of observed data in a cluster are abnormal, determining a representative value, determining a conditional probability representing a relationship between representative observed data and apparatus states, calculating posterior probability values, comparing the posterior probability values, and identifying the apparatus having the maximum posterior probability value are recited at a high level of generality. Under the broadest reasonable interpretation, these steps encompass observing/reviewing data, classifying data, evaluating whether data satisfies a threshold, assigning representative values, determining probability relationships, calculating posterior probability values, comparing the posterior probability values, identifying apparatus based on the maximum posterior probability value. These are observation, evaluation, judgment, and reasoning processes that can be practically performed by a human mind or using pen and paper for the scope covered by the claim.
Similarly, claim 4 recites estimating the location or cause of the abnormality by applying one of the first causal model, the second causal model, or the third causal model to pieces of observed data, calculating posterior probability values for apparatuses, and identifying the apparatus yielding the maximum posterior probability value are recited at a high level of generality. Under the broadest reasonable interpretation, these steps encompass observing/reviewing data, selecting model, calculating posterior probabilities values, comparing the posterior probabilities values, identifying apparatus having the maximum posterior probabilities value. These are observation, evaluation, judgment, and reasoning processes that can be practically performed by a human mind or using pen and paper for the scope covered by the claim.
Additionally, the claims are not limited to mental processes. The claims also recite mathematical concepts - mathematical relationships, mathematical formulas or equations, mathematical calculations. For example, the limitations of “determine a representative value,” “determine a conditional probability,” and “calculate a posterior probability.” As explained in MPEP § 2106.4(a)(2)(I): “The mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. It is important to note that a mathematical concept need not be expressed in mathematical symbols, because "[w]ords used in a claim operating on data to solve a problem can serve the same purpose as a formula." In re Grams, 888 F.2d 835, 837 and n.1, 12 USPQ2d 1824, 1826 and n.1 (Fed. Cir. 1989). See, e.g., SAP America, Inc. v. InvestPic, LLC, 898 F.3d 1161, 1163, 127 USPQ2d 1597, 1599 (Fed. Cir. 2018) (holding that claims to a “series of mathematical calculations based on selected information” are directed to abstract ideas); Digitech Image Techs., LLC v. Elecs. for Imaging, Inc., 758 F.3d 1344, 1350, 111 USPQ2d 1717, 1721 (Fed. Cir. 2014) (holding that claims to a “process of organizing information through mathematical correlations” are directed to an abstract idea); and Bancorp Servs., LLC v. Sun Life Assurance Co. of Can. (U.S.), 687 F.3d 1266, 1280, 103 USPQ2d 1425, 1434 (Fed. Cir. 2012) (identifying the concept of “managing a stable value protected life insurance policy by performing calculations and manipulating the results” as an abstract idea). MPEP § 2106.04(a)(2)(I)(A): A mathematical relationship is a relationship between variables or numbers. A mathematical relationship may be expressed in words or using mathematical symbols.” MPEP § 2106.04(a)(2)(I)(C) recites: “A claim that recites a mathematical calculation, when the claim is given its broadest reasonable interpretation in light of the specification, will be considered as falling within the "mathematical concepts" grouping … For example, a step of "determining" a variable or number using mathematical methods or "performing" a mathematical operation may also be considered mathematical calculations when the broadest reasonable interpretation of the claim in light of the specification encompasses a mathematical calculation.
Applicant also argues that the claims improve the functioning of the diagnostic system itself and impose meaningful limits on the claim scope is also not persuasive. The additional elements recited in the claims, including the processor, memory, program instruction, and storage medium are recited at a generic functional level and merely provide generic computer implementation of the abstract data analysis and probabilistic reasoning. Further, receiving observed data from the communication network system is data gathering, and the communication network system is used as the source of the data, and storing the causal model in memory is conventional data storage for use in the abstract analysis. The claim do not recite a specific improvement of network operation, networking monitoring hardware, packet processing, data transmission, or fault remediation. Therefore, the additional elements, considered individually and in combination, do not impose a meaningful limit on the judicial exception and do not integrate the judicial exception into a practical application. As explained in MPEP 2106.05(a), II.: "it is important to keep in mind that an improvement in the abstract idea itself (e.g. a recited fundamental economic concept) is not an improvement in technology." (emphasis added).
Accordingly, as discussed above, the amended claims remain directed to an abstract idea including mental processes and mathematical/probabilistic concepts. The additional elements, considered individually and in combination, do not integrate the abstract idea into a practical application and do not amount to significantly more than the abstract idea. Therefore, the rejection under 35 U.S.C. 101 for claims 1-5, and 7 is maintained.
Applicant’s arguments with respect to claim(s) 1 and 4 have been considered but are moot because
the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. The newly applied reference Surdulescu (US7523016B1) teaches grouping or clustering observed/network data and using an abnormality indication based on whether a predetermined number or threshold number of abnormal values or anomalous annotations is preset in the grouped or clustered data. The newly applied reference Ferguson (US20170230391A1) teaches processing grouped or representative observed data in a Bayesian models, where metrics representative of data associated with grouped entities are used in conditional probability terms involving groups, device type, activity, and network traffic data, thereby determining conditional probability information representing relationship between grouped/representative observed data and apparatus related states, and Ferguson further teaches data-driven Bayesian modeling and updating conditional probability terms using corresponding conditional probability terms from another model. The newly applied reference Mosleh (US20070011113A1) teaches a hybrid causal modeling framework including a first causal model, a second casual model, and a computational or hybrid causal model constructed from the first and second causal models.
For at least the reasons discussed above, the combined teachings of Cinato (US20090292948A1) in view of Surdulescu and Ferguson teach or suggest the amended limitations of claim 1, and the combined teachings of Cinato in view of Mosleh and Ferguson teach or suggest the amended limitations of claim 4. Therefore, the rejection of claims 1, 4, 5 and 7, and the claims dependent thereon, under 35 U.S.C. 103 is maintained.
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.
The claim(s) 1-5 and 7 are rejected under 35 USC § 101 because the claimed invention is
directed to judicial exception an abstract idea, it has not been integrated into practical application and the claims further do not recite significantly more than the judicial exception. Examiner has evaluated the claims under the framework provided in the 2019 Revised Patent Subject Matter Eligibility Guidance published in the Federal Register 01/07/2019, as well as subsequent USPTO eligibility guidance updates, and has provided such analysis below.
Step 1: Are the claims to a process, machine, manufacture or composition of matter?"
Yes, Claims 1-3 are directed to model construction apparatus and fall within the statutory category of machine;
Yes, Claims 4 is directed to estimation apparatus and fall within the statutory category of machine;
Yes, Claims 5 is directed to method and fall within the statutory category of process;
Yes, Claims 7 is directed to non-transitory computer-readable storage medium and fall within the statutory category of article of manufacture.
In order to evaluate the Step 2A inquiry "Is the claim directed to a law of nature, a natural phenomenon or an abstract idea?" we must determine, at Step 2A Prong 1, whether the claim recites a law of nature, a natural phenomenon or an abstract idea and further whether the claim recites additional elements that integrate the judicial exception into a practical application.
Step 2A Prong 1:
Claim 1: The limitations of “divide the received pieces of observed data into a plurality of clusters according to types of information represented by the respective pieces of observed data,” as drafted, are processes that, but for the recitation of generic computing components, under the broadest reasonable interpretation (BRI) in light of the specification, cover performance of the limitation in the human mind. For example, a person is capable of observing or reviewing pieces of observed data, determining the type of information represented by each piece of observed data, and classifying the pieces of observed data into corresponding groups based on the type of information. The steps include observation, evaluation, judgment, and reasoning processes that can be performed mentally or with the aid of pen and paper (The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011)) – MPEP 2106.04(a)(2)(III).
Claim 1: The limitations of “determine, for each location or each cause of an abnormality, a representative value as representative observed data for each of the plurality of clusters, the representative value for each of the plurality of clusters being a value indicating whether a predetermined number or more of pieces of observed data belonging to a corresponding cluster among the plurality of clusters are in an abnormal state,” as drafted, are processes that, but for the recitation of generic computing components, under the broadest reasonable interpretation (BRI) in light of the specification, cover performance of the limitation in the human mind. For example, a person is capable of observing or reviewing the pieces of observed data in a corresponding group, determining whether individual pieces of observed data in the group are normal or abnormal, determining whether a predetermined number or more pieces of observed data in the group are abnormal, and assigning a representative value as representative observed data for the group to indicate whether the predetermined number has been met. The steps include observation, evaluation, judgment, and reasoning processes that can be performed mentally or with the aid of pen and paper (The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011)) – MPEP 2106.04(a)(2)(III).
Claim 1: The limitations of “process the representative observed data to determine a conditional probability representing a relationship between the representative observed data and states of apparatuses in the communication network system, and construct a first causal model for estimating the location or the cause of the abnormality using the conditional probability,” as drafted, are processes that, but for the recitation of generic computing components, under the broadest reasonable interpretation (BRI) in light of the specification, cover performance of the limitation in the human mind. For example, a person is capable of reviewing representative observed data and apparatus states, determining or assigning conditional probability values that represent relationships between the representative observed data and the apparatus states, and arranging the determined conditional probability values in a probability table, causal diagram, or graph for use in estimating the location or cause of the abnormality. The steps include observation, evaluation, judgment, and reasoning processes that can be performed mentally or with the aid of pen and paper (The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011)) – MPEP 2106.04(a)(2)(III).
Claim 1: The limitations of “apply the constructed first causal model to the pieces of observed data to calculate a posterior probability for each apparatus in the communication network system, and estimate the location or the cause of the abnormality by identifying an apparatus in the communication network system that yields a maximum posterior probability,” as drafted, are processes that, but for the recitation of generic computing components, under the broadest reasonable interpretation (BRI) in light of the specification, cover performance of the limitation in the human mind. For example, a person is capable of using the pieces of observed data to the constructed probability table, causal diagram or graph to determine posterior probability values for each apparatus, comparing the posterior probability values, and identifying the apparatus having the largest posterior probability as the estimated location or cause of the abnormality. The steps include observation, evaluation, judgment, and reasoning processes that can be performed mentally or with the aid of pen and paper (The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011)) – MPEP 2106.04(a)(2)(III).
Claim 4: The limitations of “estimate the location or the cause of the abnormality in the communication network system by applying one of the first causal model, the second causal model, or the third causal model stored in the memory to the pieces of observed data to calculate a posterior probability for each apparatus of a plurality of apparatuses in the communication network system, and identifying an apparatus in the communication network system that yields a maximum posterior probability,” as drafted, are processes that, but for the recitation of generic computing components, under the broadest reasonable interpretation (BRI) in light of the specification, cover performance of the limitation in the human mind. For example, a person is capable of selecting one of constructed probability tables, causal diagrams or graphs, using pieces of observed data to determining posterior probability values for a plurality of apparatus, comparing the posterior probability values, and identifying the apparatus having the greatest posterior probability as the estimated location or cause of the abnormality. The steps include observation, evaluation, judgment, and reasoning processes that can be performed mentally or with the aid of pen and paper (The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011)) – MPEP 2106.04(a)(2)(III).
Examiner note: The claims recite the limitations at high level of generality and does not require a particular computer implementation, specialized data structure, packet processing technique, networking monitoring hardware, dynamically processing requirements, or specific technical algorithm for performing the recited determining, representing, calculating, comparing and identifying steps. Under broadest reasonable interpretation, the recited causal model and probability relationships can be represented in a probability table, casual diagram or graph, and the recited posterior probability determination and maximum probability identification can be performed for a finite set pf apparatuses by a human using mental evaluation or pen and paper. Therefore, the recited operations remain observation, evaluation, judgment, comparison, and probabilistic reasoning processes that can be performed in the human mind or with the aid of pen and paper.
If a claim limitation, under its broadest reasonable interpretation in light of specification, covers performance of the limitation in the human mind, but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong One, step 2A. See MPEP § 2106.04(a)(2)(III).
In MPEP § 2106.04(II)(B): A claim may recite multiple judicial exceptions. For example, claim 4 at issue in Bilski v. Kappos, 561 U.S. 593, 95 USPQ2d 1001 (2010) recited two abstract ideas, and the claims at issue in Mayo Collaborative Servs. v. Prometheus Labs. Inc., 566 U.S. 66, 101 USPQ2d 1961 (2012) recited two laws of nature. However, these claims were analyzed by the Supreme Court in the same manner as claims reciting a single judicial exception, such as those in Alice Corp., 573 U.S. 208, 110 USPQ2d 1976.
The claim 1 does recite a mathematical concept.
As explained in MPEP § 2106.4(a)(2)(I): “The mathematical concepts grouping is defined as mathematical relationships, mathematical formulas or equations, and mathematical calculations. It is important to note that a mathematical concept need not be expressed in mathematical symbols, because "[w]ords used in a claim operating on data to solve a problem can serve the same purpose as a formula." In re Grams, 888 F.2d 835, 837 and n.1, 12 USPQ2d 1824, 1826 and n.1 (Fed. Cir. 1989). See, e.g., SAP America, Inc. v. InvestPic, LLC, 898 F.3d 1161, 1163, 127 USPQ2d 1597, 1599 (Fed. Cir. 2018) (holding that claims to a “series of mathematical calculations based on selected information” are directed to abstract ideas); Digitech Image Techs., LLC v. Elecs. for Imaging, Inc., 758 F.3d 1344, 1350, 111 USPQ2d 1717, 1721 (Fed. Cir. 2014) (holding that claims to a “process of organizing information through mathematical correlations” are directed to an abstract idea); and Bancorp Servs., LLC v. Sun Life Assurance Co. of Can. (U.S.), 687 F.3d 1266, 1280, 103 USPQ2d 1425, 1434 (Fed. Cir. 2012) (identifying the concept of “managing a stable value protected life insurance policy by performing calculations and manipulating the results” as an abstract idea).
MPEP § 2106.04(a)(2)(I)(A): A mathematical relationship is a relationship between variables or numbers. A mathematical relationship may be expressed in words or using mathematical symbols.”
Further, MPEP § 2106.04(a)(2)(I)(C) recites: ““A claim that recites a mathematical calculation, when the claim is given its broadest reasonable interpretation in light of the specification, will be considered as falling within the "mathematical concepts" grouping … For example, a step of "determining" a variable or number using mathematical methods or "performing" a mathematical operation may also be considered mathematical calculations when the broadest reasonable interpretation of the claim in light of the specification encompasses a mathematical calculation.
Claim 1, The limitations of “determine, for each location or each cause of an abnormality, a representative value as representative observed data for each of the plurality of clusters, the representative value for each of the plurality of clusters being a value indicating whether a predetermined number or more of pieces of observed data belonging to a corresponding cluster among the plurality of clusters are in an abnormal state; process the representative observed data to determine a conditional probability representing a relationship between the representative observed data and states of apparatuses in the communication network system; apply the constructed first causal model to the pieces of observed data to calculate a posterior probability for each apparatus in the communication network system, and estimate the location or the cause of the abnormality by identifying an apparatus in the communication network system that yields a maximum posterior probability,” as drafted, under its broadest reasonable interpretation (BRI) in light of specification, can be reasonably considered to represent mathematical concept, expressed in words including mathematical relationships, mathematical formulas or equations, and mathematical calculations. As recites in specification: for example, [0021]-[0030]. See MPEP § 2106.04(a)(2)(I).
Claim 4, The limitations of “estimate the location or the cause of the abnormality in the communication network system by applying one of the first causal model, the second causal model, or the third causal model stored in the memory to the pieces of observed data to calculate a posterior probability for each apparatus of a plurality of apparatuses in the communication network system, and identifying an apparatus in the communication network system that yields a maximum posterior probability” The limitation with the broadest reasonable interpretation (BRI) in light of specification that can be considered to represent mathematical concepts expressed in words including mathematical relationships, mathematical formulas or equations, and mathematical calculations. As recites in specification: for example, [0030], [0036] - [0046], [0050], [0052] and [0054]. See MPEP § 2106.04(a)(2)(I).
Claims 5 and 7 recites substantially the same elements as claim 1, and are rejected for the
same reasons under 35 U.S.C. 101.
Therefore, claims 1, 4, 5 and 7 recite judicial exceptions. The claims have been identified to recite judicial exceptions, Step 2A Prong 2 will evaluate whether the claims as a whole integrates the exception into a practical application of that exception.
Step 2A Prong 2: Claims 1, 4, 5 and 7: The judicial exception is not integrated into a practical application.
In particular, the claims recite the following additional elements - "A model construction apparatus comprising: a processor; and a memory storing program instructions that cause the processor to:” and “An estimation apparatus comprising: a processor; and a memory storing program instructions that cause the processor to:” and “A model construction method comprising the following executed by a computer:” and “A non-transitory computer-readable storage medium that stores therein a program for causing a computer to execute the model construction method,” which are merely recitations of instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to implement the judicial exception, which does not integrate judicial exception into a practical application (see MPEP §2106.05(f)).
Further, the following additional elements – “receive pieces of observed data from a communication network system that is a target for estimation of a location or a cause of an abnormality” and “store, into the memory, a causal model for estimating the location or the cause of the abnormality, the causal model including a first causal model constructed based on a rule-based method, a second causal model constructed based on a data-driven method, and a third causal model combining the first causal model and the second causal model by modifying a conditional probability used for the first causal model based on a conditional probability used for the second causal model,” are merely recitations of insignificant extra-solution activity as data gathering (i.e., data transmission and storage), which does not integrate a judicial exception into practical application (see MPEP § 2106.05(g)).
Additionally, adding the steps of receive pieces of observed data and store causal models to a process that only recites dividing data, determining value, constructing mathematical model (abstract idea) does not add a meaningful limitation to the process of dividing data, determining value, constructing mathematical model and estimating a location or a cause of an abnormality. Therefore, the receiving limitations function only as generic data gathering and do not meaningfully limit or integrate the judicial exception into a practical application. Although the stored third causal model is described in terms of modifying a conditional probability used for the first causal model based on a conditional probability used for the second causal model, the claim recites a characteristic of the stored causal model. Thus, the limitation merely recite a generic storage of mathematical/probability model in memory, rather than as an additional technical operation.
Therefore, "Do the claims recite additional elements that integrate the judicial exception into a practical application? No, these additional elements do not integrate the abstract idea into a practical application and they do not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
After having evaluated the inquires set forth in Steps 2A Prong One and Two, it has been concluded that claims 1, 4, 5 and 7 recite a judicial exception and are directed to the judicial exception as the judicial exception is not integrated into a practical application.
Step 2B: Claims 1, 4, 5 and 7: The claims do not include additional elements, alone or in combination, that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements amount to no more than generic computing components which do not amount to significantly more than the abstract idea. Limitations that the courts have found not to be enough to qualify as "significantly more" when recited in a claim with a judicial exception include:
i. Adding the words "apply it" (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, e.g., a limitation indicating that a particular function such as creating and maintaining electronic records is performed by a computer, as discussed in Alice Corp., 573 U.S. at 225-26, 110 USPQ2d at 1984 (see MPEP § 2106.05(f));
ii. Simply appending well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception, e.g., a claim to an abstract idea requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known to the industry, as discussed in Alice Corp., 573 U.S. at 225, 110 USPQ2d at 1984 (see MPEP § 2106.05(d));
iii. Adding insignificant extra-solution activity to the judicial exception, e.g., mere data gathering in conjunction with a law of nature or abstract idea such as a step of obtaining information about credit card transactions so that the information can be analyzed by an abstract mental process, as discussed in CyberSource v. Retail Decisions, Inc., 654 F.3d 1366, 1375, 99 USPQ2d 1690, 1694 (Fed. Cir. 2011) (see MPEP § 2106.05(g)); or
iv. Generally linking the use of the judicial exception to a particular technological environment or field of use, e.g., a claim describing how the abstract idea of hedging could be used in the commodities and energy markets, as discussed in Bilski v. Kappos, 561 U.S. 593, 595, 95 USPQ2d 1001, 1010 (2010) or a claim limiting the use of a mathematical formula to the petrochemical and oil-refining fields, as discussed in Parker v. Flook, 437 U.S. 584, 588-90, 198 USPQ 193, 197-98 (1978) (MPEP § 2106.05(h)).
As explained in MPEP 210.05(d)(II): The courts have recognized the following computer functions as well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity.
i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); …
ii. Performing repetitive calculations, Flook, 437 U.S. at 594, 198 USPQ2d at 199 (recomputing or readjusting alarm limit values); …
iii. Electronic recordkeeping, Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 573 U.S. 208, 225, 110 USPQ2d 1984 (2014) (creating and maintaining "shadow accounts"); Ultramercial, 772 F.3d at 716, 112 USPQ2d at 1755 (updating an activity log);
iv. Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93; …
Therefore, the additional elements, when considered individually and in combination, merely apply the judicial exception using conventional computing components and do not provide significantly more than the judicial exception.
Accordingly, "Do the claims recite additional elements that amount to significantly more than the judicial exception? No, these additional elements, alone or in combination, do not amount to significantly more than the judicial exception. Having concluded analysis within the provided framework, claims 1, 4, 5 and 7 do not recite patent eligible subject matter under 35 U.S.C. § 101.
Dependent claims 2-3 are also similar rejected under same rationale as cited above wherein these claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. These claims are merely further elaborate the mental process itself (and/or mathematical operations) or providing additional definition of process which does not impose any meaningful limits on practicing the abstract idea. Claims 2-3 are also rejected for incorporating the deficiency of their independent claims 1.
Claim 2 recites “The model construction apparatus according to claim 1, wherein the program instructions further cause the processor to: calculate a value representing a relationship between pieces of observed data when the communication network system is in a normal state among the received pieces of observed data; calculate, using the value representing the relationship, a first conditional probability representing a relationship between a location or a cause of an abnormality in the communication network system and the pieces of observed data when the communication network system is in the normal state; calculate, using pieces of observed data when the communication network system is in an abnormal state, a second conditional probability representing a relationship between the location or the cause of the abnormality and the pieces of observed data when the communication network system is in the abnormal state, based on a data-driven method; and construct a second causal model for estimating the location or the cause of the abnormality from the pieces of observed data, using the first conditional probability and the second conditional probability.”
The limitation merely defines constructing a second causal model using the first and second conditional probabilities, which involves mathematical relationships and probabilistic calculations to model relationships between variables (see specification, [0033]-[0040]). Accordingly, the limitation recites a mathematical concept. Therefore, the claim 2 does not recite patent-eligible subject matter under 35 U.S.C. § 101.
Claim 3 recites “The model construction apparatus according to claim 2, wherein the program instructions further cause the processor to construct a third causal model by modifying the first causal model based on the second causal model.”
The limitation merely defines constructing a third causal model by modifying the first causal model based on the second causal model, which involves evaluating and making a judgement for relationships between models that can be performed mentally or with pen and paper. Accordingly, the limitation recites an extension of mental process. Therefore, the claim 3 does not recite patent eligible subject matter under 35 U.S.C. § 101.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and
103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
Claim(s) 1-2, 5 and 7 are rejected under 35 U.S.C. 103 as being unpatentable over Cinato
US20090292948A1 in view of Surdulescu US7523016B1 and Ferguson US20170230391A1.
Claim 1, Cinato teaches (Previously Presented) A model construction apparatus (Fig.1, fault management system 1. [0001] The present invention relates in general to telecommunications networks, and more particularly to fault location in telecommunications networks with distributed-agent or centralized fault management system by using Bayesian networks.” [0012] This objective is achieved by the present invention in that it relates to a method, a system and a software product for locating faults in a communication network [0025] constructing a probabilistic model relating possible faults and status information in the identified limited region.) comprising:
a processor; and
a memory storing program instructions that cause the processor ([0084] The present invention further relates to a software product which can be loaded into the memory of a fault locating system in a communication network and includes software-code portions for performing, when the computer program product is run on the fault processing system, the method previously described. See also [0098], [0100] and [0102]. Examiner note: A POSITA would understand that the software product loaded into memory and run on the fault locating system includes executable program instructions executed by a processor or computing component) to:
receive pieces of observed data from a communication network system that is a target for estimation of a location or a cause of an abnormality ([0023] receiving status information relating to at least an alarm, an event, a polled status or a test result in the communication network. [0024] identifying a limited region of the communication network in which the fault has occurred based on the received status information; [0025] constructing a probabilistic model relating possible faults and status information in the identified limited region; and [0026] locating the fault based on the constructed probabilistic model and on the received status information. [0104] Initially, each Autonomous Agent collects all the reports sent by the network apparatus it manages, including alarms spontaneously generated by the network apparatus or status changes detected by the polling system, which constantly checks the value of certain indicators on the network apparatus and generates and sends reports to the Autonomous Agent (block 10).);
divide the received pieces of observed data into a plurality of clusters according to types of information represented by the respective pieces of observed data ([0105], “… each Autonomous Agent groups the collected alarms or status changes based on information about the network apparatus that has sent the alarm or changed the status, the type of fault, and the time when the alarm was generated or the status change was notified.”);
determine, for each location or each cause of an abnormality, ([0067] for each individual possible fault in the accountable network resource, in the contiguous network resource and in the interconnection resource, determining a first probability that a status information is generated when the individual fault occurs (effect/cause probability); [0068] for each status information that may be generated by the network resource managed by the agent, determining a second probability that the status information is generated when no fault occurs in the network resource managed by the agent (effect/no_cause probability). Examiner note: the reference teaches determining probabilities for possible fault locations or causes based on statues information);
process ([0031] for each possible fault in the identified limited region, determining a first probability that a status information is generated when the fault occurs (effect/cause probability); [0032] for each possible status information in the identified limited region, determining a second probability that the status information is generated when no fault occurs in the identified limited region (effect/no_cause probability); and [0033] constructing the probabilistic model relating faults and status information in the identified limited region based on the determined first and second probabilities. [0154] … Probability Tables associated to the effect states are then computed … using the effect/cause conditional probabilities and the effect/no_cause conditional probabilities in the Useful Probability Group. [0157] The existence of an effect/cause conditional probability implies a dependency between the CauseResource-Cause pair and the EffectResource-Effect pair in question. [0129] Finally, the Accountable Agent performs an inference process on the complete Bayesian Network (of the considered limited network region) using the information of those alarms that have been received by, and/or status changes that have been notified to, the Accountable Agent and the Contiguous Agent(s) as input data to the Inference Bayesian Network (block 100) … the inference process allows computing the probability of each possible cause. Examiner note: the status information/effects correspond to observed data used in the fault location model, and the possible faults, CauseResource-Cause pairs, and cause states correspond to apparatus/resource fault states in the communication network. The reference teaches effect/cause conditional probabilities and effect/no-cause conditional probabilities, and explains that the effect/cause conditional probability defines a dependency between a CauseResouce-Cause pair and an effectResouce-Effect pair. Thus, the reference teaches determining a conditional probability representing a relationship between observed data/effects and apparatus/resource fault states. The reference further teaches constructing probability tables and a probabilistic model using those conditional probabilities, and using alarm or status changes as input data to compute probabilities of possible causes. Accordingly, the reference teaches the conditional probability and causal/probabilistic model portions of the limitation); and
apply the constructed first causal model to the pieces of observed data to calculate a posterior probability for each apparatus in the communication network system, and estimate the location or the cause of the abnormality by identifying an apparatus in the communication network system that yields a maximum posterior probability ([0015] Bayesian networks allow computation of the probability that, based on a set of alarms collected by the management system, the cause is to be associated with a certain fault in a resource, leading to the identification of the cause, intended as that with the greatest probability to have generated the alarm and derived from statistical inference. [0128] Then the Accountable Agent constructs a complete Bayesian Network, hereinafter referred to as Inference Bayesian Network, … which Inference Bayesian Network is maintained by the Accountable Agent and regards faults on the network apparatus managed by the Accountable Agent, on the Silent Resource, and on the network apparatuses managed by the Contiguous Agents, and alarms collected by, and/or status changes notified to, the Accountable and the Contiguous Agents. [0129] Finally, the Accountable Agent performs an inference process on the complete Bayesian Network … using the information of those alarms that have been received by, and/or status changes that have been notified to, the Accountable Agent and the Contiguous Agent(s) as input data to the Inference Bayesian Network (block 100), thus identifying the fault (block 110) … the inference process allows computing the probability of each possible cause. [0181] In particular, inference is a process for assessing the probability of each state of a node of the Bayesian Network when information (evidence) on other variables is known. … To (a posteriori) update the distribution of the probability of one or more variables in the domain based on known observation values (evidences) … [0182] Appropriately applying the Bayes' theorem, the probability that alarm A1 is a consequence of the fault G1, i.e., that G1=P, is: … [0183] The same applies to the fault G2, and hence the probability that G2=P is: … Examiner note: the complete “inference Bayesian Network” corresponds to the constructed causal/probabilistic model, and the alarms and status changes correspond to the observed data applied to the model as evidence. The reference teaches performing inference on the Inference Bayesian Network using the received alarms or status changes as input data, thereby computing the probability of each possible causes. The reference further teaches identifying the cause with the greatest probability as the cause associated with the fault. Thus, the reference teaches applying the constructed causal/probabilistic model to the observed data to calculate posterior probabilities for possible apparatus/resource fault states and estimating the location or cause of the abnormality by identifying the apparatus/resource fault state having the maximum probability).
However, Cinato fails to teach determining a representative value as representative observed data for each of the plurality of clusters, the representative value for each of the plurality of clusters being a value indicating whether a predetermined number or more of pieces of observed data belonging to a corresponding cluster among the plurality of clusters are in an abnormal state.
Surdulescu teaches determining a representative value as representative observed data for each of the plurality of clusters, the representative value for each of the plurality of clusters being a value indicating whether a predetermined number or more of pieces of observed data belonging to a corresponding cluster among the plurality of clusters are in an abnormal state (Col.1, lines 42-46, “… identifying the sampled data associated with the one or more transaction components as unusual if a predetermined number of values for the monitored characteristics of the sampled data are determined to be unusual.” Col.1, lines 48-55, “aggregating network data into entries including network activity for network transaction components during a period of time, annotating each entry with statistically derived measures of how anomalous the entry is relative to other entries, and identifying annotated entries that have annotations specifying that the entry is anomalous if a number of the annotations exceeds a predetermined threshold.” Col.9, lines 63-67, “The cluster list can display clusters of characteristics that have substantially similar abnormal values. A cluster list, such as the cluster list 822, can include a cluster id used to identify a cluster of similar entries, a number of “hot bits,” which indicates how many abnormal characteristics are included in the entries of the cluster …” Examiner note: the sampled data and network data correspond to observed data, and its entries, cells, groups, or clusters correspond to grouped observed data. The reference teaches identifying the sampled data as unusual when a predetermined number of monitored characteristic values re unusual, and identifying aggregated network data entries as anomalous when the number of anomaly annotations exceeds a predetermined threshold. The reference further teaches clusters of characteristics having substantially similar abnormal values and a number of “hot bits” indicating how many abnormal characteristics are included in the entries of the cluster. Thus the anomalous/unusual indication for the entry or cluster corresponds to the claimed representative value as representative observed data, because it is a single abnormality indication represent the grouped observed data and indicates whether a threshold number of observed data characteristics in the corresponding group or cluster are abnormal).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Cinato to incorporate the teachings of Surdulescu and to apply determining a representative abnormality value for grouped or clustered network data based on whether a predetermined number of monitored values or abnormal characteristics in the group or cluster are unusual or abnormal in order to provide a compact representative observed data value for each cluster of Cinato’s grouped observed data. The combination of teachings would predictably provide a single representative abnormality indication for each cluster, reduce multiple observed data abnormality indications in a cluster into a compact representative value, and improve efficient organization and use of abnormal status information in the communication network.
However, Cinato and Surdulescu fail to teach process the representative observed data to determine a conditional probability representing a relationship between the representative observed data and states of apparatuses in the communication network system.
Ferguson teaches process the representative observed data to determine a conditional probability representing a relationship between the representative observed data and states of apparatuses in the communication network system ([0034] The model of normal behavior of the group of entities may be based on metrics representative of data associated with the plurality of entities of the computer system. [0152] These dependencies define the conditional probability terms for the Bayesian model, where a conditional probability is the probability of an event, given that another has already occurred. [0170] The conditional probability terms involving user groups and device types are as below: [0174] P(N/A,Y,G,T): The network traffic data due to a user performing a certain type of work on a particular device given the time of the day. [0175] These conditional probabilities are calculated accumulating over the users within the group. Examiner note: the “metrics representative of data associated with the plurality of entities” correspond to representative observed data associated with grouped entities in a computer or communication network system. The reference further teaches conditional probability terms involving user groups and device types, including a conditional probability term for network traffic data based on activity, device type , group, and time. The reference explains that the dependencies define the conditional probability terms, and that the conditional probabilities are calculated by accumulating over users within the group. Thus, the reference teaches processing representative or grouped observed data to determine conditional probability information representing a relationship between the representative observed data and apparatus related states in the communication network system).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Cinato and Surdulescu to incorporate the teachings of Ferguson and to apply using metrics representative of data associated with grouped entities in a Bayesian framework, wherein dependencies among group, device type, activity, time, and network traffic data define conditional probability terms and the conditional probabilities are calculated by accumulating over users within the group in order to determine conditional probability information from representative grouped observed data that represents relationships between observed network data and apparatus related states in the communication network system. In this case, Cinato teaches processing observed status information to determine conditional probability information associated with possible fault location or causes. Surdulescu teaches representative abnormality values for grouped observed data. Ferguson teaches using representative grouped data in a Bayesian conditional probability framework. The combination of teachings would predictably allow the representative observed data taught by Surdulescu to be used in determining conditional probability information, reduce the amount and variability of raw observed data used for probability determination, and improve reliable determination of relationships between observed network data and apparatus related states in the communication network system.
Claim 2, Cinato teaches (Previously Presented) The model construction apparatus according to claim 1, wherein the program instructions further cause the processor to:
calculate a value representing a relationship between pieces of observed data when the communication network system is in a normal state among the received pieces of observed data ([0190] … the statistics of operation cases in which, after receiving alarms, events, polled statuses and test results, no fault has been found in the field. Examiner note: the statistics of operation cases correspond to calculated quantitative relationships among the received pieces of observed data (e.g., alarms, events, statuses, and test results) observed when no fault is present (i.e., when the communication network system is in normal state). Therefore, these statistical correlations constitute a value representing a relationship between pieces of observed data in a normal state.);
calculate, using the value representing the relationship, a first conditional probability representing a relationship between a location or a cause of an abnormality in the communication network system and the pieces of observed data when the communication network system is in the normal state ([0032] for each possible status information in the identified limited region, determining a second probability that the status information is generated when no fault occurs in the identified limited region (effect/no_cause probability). [0190] effect/no_cause conditional probabilities are updated using the statistics of operation cases in which, after receiving alarms, events, polled statuses and test results, no fault has been found in the field. Examiner note: the identified limited region corresponds to a location in the communication network, and the absence of a fault corresponds to a normal state of the communication network system. The probability that status information is generated when no fault occurs represents a conditional probabilistic relationship between the location or cause of an abnormality and received pieces of observed data (e.g., alarms, events, statuses, and test results) when the communication network is in the normal state. Further, these conditional probabilities are calculated and updated using statistics derived from observed operation cases ([0190]), which corresponds to the calculated value representing relationships among pieces of observed data in the normal state.);
calculate, using pieces of observed data when the communication network system is in an abnormal state, a second conditional probability representing a relationship between the location or the cause of the abnormality and the pieces of observed data when the communication network system is in the abnormal state, based on a data-driven method ([0031] for each possible fault in the identified limited region, determining a first probability that a status information is generated when the fault occurs (effect/cause probability). [0189] effects/cause conditional probabilities are updated using statistics of the cases of alarms, events, polled statuses and test results received in association with a single fault detected in the field. Examiner note: the occurrence of a fault corresponds to an abnormal state of the communication network system, and the identified limited region corresponds to a location in the communication network. The probabilities updated using statistics of operation cases in which faults have been observed to represent probabilistic relationships between the location or cause of the abnormality and the received pieces of observed data (e.g., alarms, events, statuses, and test results) when the communication network system is in an abnormal state. Further, deriving conditional probabilities from historical operation data constitutes a data-driven method because the probabilistic relationships are learned from empirical observed data rather than predefined rules.); and
construct a second causal model for estimating the location or the cause of the abnormality from the pieces of observed data, using the first conditional probability and the second conditional probability ([0168] In particular, FIGS. 5a, 5b and 5c show, respectively, examples … of a partial Bayesian Network constructed by the Contiguous Agent … [0062] constructing by the contiguous agent a partial probabilistic model relating status information received by the contiguous agent and faults occurred in the accountable network resource, in the contiguous network resource and in the interconnection resource. [0069] constructing the partial probabilistic model based on the determined first and second probabilities. [0126] … each Contiguous Agent that has received the request sent by the Accountable Agent constructs its own partial Bayesian Network (block 70). [0047] inferring the fault location based on the probabilistic model and on status information received from the identified limited region of the communication network. [0181] In particular, inference is a process for assessing the probability of each state of a node … Examiner note: the reference teaches constructing the partial Bayesian Network constructed by the Contiguous Agent based on the determined first and second conditional probabilities, and inferring the fault location using the probabilistic model. Additionally, the complete inference Bayesian Network relied upon in claim 1 corresponds to the construed causal/probabilistic model applied by the Accountable Agent. Separately, the reference teaches that each Contiguous Agent constructs its own partial Bayesian Network or partial probabilistic model, which relates received status information to faults occurring in the accountable network resource, the contiguous network resource, and the interconnection resource. The reference further teaches constructing the partial probabilistic model based on the determined first and second probabilities. Thus, the Contiguous Agent’s partial Bayesian Network or partial probabilistic model corresponds to a second causal/probabilistic model constructed using the first conditional probability and the second conditional probability for estimating the location or cause of the abnormality).
The elements of claims 5 and 7 are substantially the same as those of claim 1. Therefore, the elements of claims 5 and 7 are rejected due to the same reasons as outlined above for claim 1.
Claim(s) 3 is rejected under 35 U.S.C. 103 as being unpatentable over Cinato and Surdulescu and
Ferguson as applied to claim 2 above, and further in view of Mosleh US20070011113A1.
Claim 3, Cinato and Surdulescu and Ferguson fail to teach, but Mosleh teaches (Previously Presented) The model construction apparatus according to claim 2, wherein the program instructions further cause the processor to construct a third causal model by modifying the first causal model based on the second causal model ([0010] The causal scenario is modeled by a first causal model characterized by a plurality of first nodes interconnected one with another to define a termination of the causal scenario in the end state via Boolean states of a variable at each of said first nodes. Factors affecting the Boolean state of at least one variable at a corresponding one of the first nodes are modeled by a second causal model characterized by a plurality of second nodes … A computational model is constructed from the first causal model and the second causal model. Examiner note: The reference teaches that the first causal model includes variables or events represented by first nodes, and that factors affecting the state of tat least one variable of the first causal model are modeled by a second causal model. The reference further teaches that the second causal model includes at least one node corresponding to the variable of the first causal model, and that a computational model is constructed from the first causal model and the second causal model. Thus, the first causal model is not used alone, but is modified or supplemented by causal /probabilistic information from the second causal model through the corresponding variable to form the computational model as claimed third model).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Cinato and Surdulescu and Ferguson to incorporate the teachings of Mosleh and to apply constructing a computational model from a first causal model and a second casual model, where the second causal model provides probability information affecting a variable or event in the first causal model in order to provide a more comprehensive causal modeling framework for estimating fault locations or causes in a communication network. The combination of teachings would predictably allow Cinato’s fault location model to construct a further causal/probabilistic model by incorporating causal information from another causal/probabilistic model, thereby improving the ability to model relationships among possible causes and compute probabilities for fault estimation.
Claim(s) 4 is rejected under 35 U.S.C. 103 as being unpatentable over Cinato
US20090292948A1 in view of Mosleh US20070011113A1 and Ferguson US20170230391A1.
Claim 4, Cinato teaches (Previously Presented) An estimation apparatus (Fig.1, fault management system 1. [0001] The present invention relates in general to telecommunications networks, and more particularly to fault location in telecommunications networks with distributed-agent or centralized fault management system by using Bayesian networks.” [0025] constructing a probabilistic model relating possible faults and status information in the identified limited region.) comprising:
a processor; and
a memory storing program instructions that cause the processor ([0084] The present invention further relates to a software product which can be loaded into the memory of a fault locating system in a communication network and includes software-code portions for performing, when the computer program product is run on the fault processing system, the method previously described. See also [0098], [0100] and [0102]. Examiner note: A POSITA would understand that the software product loaded into memory and run on the fault locating system includes executable program instructions executed by a processor or computing component) to:
receive pieces of observed data from a communication network system that is a target for estimation of a location or a cause of an abnormality ([0023] receiving status information relating to at least an alarm, an event, a polled status or a test result in the communication network. [0024] identifying a limited region of the communication network in which the fault has occurred based on the received status information; [0025] constructing a probabilistic model relating possible faults and status information in the identified limited region; and [0026] locating the fault based on the constructed probabilistic model and on the received status information. [0104] Initially, each Autonomous Agent collects all the reports sent by the network apparatus it manages, including alarms spontaneously generated by the network apparatus or status changes detected by the polling system, which constantly checks the value of certain indicators on the network apparatus and generates and sends reports to the Autonomous Agent (block 10).);
divide the received pieces of observed data into a plurality of clusters according to types of information represented by the respective pieces of observed data ([0105], “… each Autonomous Agent groups the collected alarms or status changes based on information about the network apparatus that has sent the alarm or changed the status, the type of fault, and the time when the alarm was generated or the status change was notified.”);
store, into the memory, a causal model for estimating the location or the cause of the abnormality, the causal model including ([0025] constructing a probabilistic model relating possible faults and status information in the identified limited region; and [0026] locating the fault based on the constructed probabilistic model and on the received status information. [0027] The probabilistic model is advantageously represented by a Bayesian Network. [0139] Information concerning the above probabilities are stored in database 5 in FIG. 1, hereinafter referred to as Probability Database (PD), which can be maintained on an Application Agent and managed in a centralized manner or on the Autonomous Agents and managed in a distributed manner. [0140] The Accountable Agent, as well as each Contiguous Agent … constructs its own partial Bayesian Network based on the above probabilities … [0128] … the Accountable Agent constructs a complete Bayesian Network, hereinafter referred to as Inference Bayesian Network, based on, and in particular by combining, its own partial Bayesian Network and the partial Bayesian Networks received from the Contiguous Agents, as described in detail further on (block 90), which Inference Bayesian Network is maintained by the Accountable Agent and regards faults on the network apparatus managed by the Accountable Agent, … and alarms collected by, and/or status changes notified to, the Accountable and the Contiguous Agents. Examiner note: the reference teaches a probabilistic/Bayesian model used for estimating or locating a fault in a communication network, and further teaches storing probability information used for constructing the Bayesian Network in a Probability Database, constructing partial Bayesian Networks based on the stored probabilities, and maintaining a complete Inference Bayesian Network by the Accountable Agent. Thus, the reference teaches storing model/probability information corresponding to a causal/probabilistic model for estimating the location or cause of an abnormality.); and
estimate the location or the cause of the abnormality in the communication network system by applying one of the first causal model, the second causal model, or the third causal model stored in the memory to the pieces of observed data to calculate a posterior probability for each apparatus of a plurality of apparatuses in the communication network system, and identifying an apparatus in the communication network system that yields a maximum posterior probability ([0015] Bayesian networks allow computation of the probability that, based on a set of alarms collected by the management system, the cause is to be associated with a certain fault in a resource, leading to the identification of the cause, intended as that with the greatest probability to have generated the alarm and derived from statistical inference. [0128] Then the Accountable Agent constructs a complete Bayesian Network, hereinafter referred to as Inference Bayesian Network, … which Inference Bayesian Network is maintained by the Accountable Agent and regards faults on the network apparatus managed by the Accountable Agent, on the Silent Resource, and on the network apparatuses managed by the Contiguous Agents, and alarms collected by, and/or status changes notified to, the Accountable and the Contiguous Agents. [0129] Finally, the Accountable Agent performs an inference process on the complete Bayesian Network … using the information of those alarms that have been received by, and/or status changes that have been notified to, the Accountable Agent and the Contiguous Agent(s) as input data to the Inference Bayesian Network (block 100), thus identifying the fault (block 110) … the inference process allows computing the probability of each possible cause. [0181] In particular, inference is a process for assessing the probability of each state of a node of the Bayesian Network when information (evidence) on other variables is known. … To (a posteriori) update the distribution of the probability of one or more variables in the domain based on known observation values (evidences) … [0182] Appropriately applying the Bayes' theorem, the probability that alarm A1 is a consequence of the fault G1, i.e., that G1=P, is: … [0183] The same applies to the fault G2, and hence the probability that G2=P is: … Examiner note: the complete “Inference Bayesian Network” corresponds to the corresponding stored causal/probabilistic model, and the alarms and status changes correspond to the observed data applied to the model as evidence. The reference teaches performing inference on the Inference Bayesian Network using the received alarms or status changes as input data, thereby computing the probability of each possible causes. The reference further teaches identifying the cause with the greatest probability as the cause associated with the fault. Thus, the reference teaches applying corresponding stored causal/probabilistic model to the observed data to calculate posterior probabilities for possible apparatus/resource fault states and estimating the location or cause of the abnormality by identifying the apparatus/resource fault state having the maximum probability).
However, Cinato fails to teach a first causal model constructed based on a rule-based method, a second causal model constructed based on a data-driven method, and a third causal model combining the first causal model and the second causal model by modifying a conditional probability used for the first causal model based on a conditional probability used for the second causal model.
Mosleh teaches a first causal model constructed based on a rule-based method, a second causal model ([0010] The causal scenario is modeled by a first causal model characterized by a plurality of first nodes interconnected one with another to define a termination of the causal scenario in the end state via Boolean states of a variable at each of said first nodes. Factors affecting the Boolean state of at least one variable at a corresponding one of the first nodes are modeled by a second causal model characterized by a plurality of second nodes … A computational model is constructed from the first causal model and the second causal model. [0012] The apparatus also includes fault logic coupled to the sequential logic for providing the condition to each of the decision units … Also included in the apparatus is a probabilistic network coupled to the fault logic for characterizing uncertain relationships between the causal factors of the system … The apparatus includes also a hybrid causal model operable to determine a probability of the risk scenarios … as determined from the joint probability distribution between variables representing the corresponding causal factors of the probabilistic network. Examiner note: the reference teaches a first causal model based on Boolean/sequential/fault logic, a second causal model based on a probabilistic network, and a computational/hybrid causal model constructed from the first and second causal models. Thus, the reference teaches that a causal model may include a first causal model, a second causal model, and a third combined causal model).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Cinato to incorporate the teachings of Mosleh and to apply constructing a hybrid causal model including a first causal model based on Boolean, sequential, or fault logic, a second casual model based on a probabilistic network, and a computational model constructed from the first causal model and the second causal model in order to provide a more comprehensive causal modeling framework for estimating fault locations or causes in a communication network. In this case, Cinato teaches using a Bayesian/probabilistic model to estimate the location or cause of a fault in a communication network based on alarms or status changes. Mosleh teaches a hybrid causal model that combines logic based causal modeling with probabilistic network modeling. The combination of teachings would predictably allow Cinato’s fault location model to incorporate both logic based causal relationships in a unified causal model, thereby improving the ability to model relationships among possible causes and compute probabilities for fault estimation.
However, Cinato and Mosleh fail to teach a second causal model constructed based on a data-driven method and modifying a conditional probability used for the first causal model based on a conditional probability used for the second causal model.
Ferguson teaches a second causal model constructed based on a data-driven method and modifying a conditional probability used for the first causal model based on a conditional probability used for the second causal model ([0029] a method for use in detection of abnormal behavior of a group of a plurality of entities of a computer system is disclosed … comprising: creating a model of normal behavior of the group of entities … [0031] … grouping the plurality of entities of the computer system to generate the group of entities based on data associated with the plurality of entities of the computer system. [0034] The model of normal behavior of the group of entities may be based on metrics representative of data associated with the plurality of entities of the computer system. [0035] The model of normal behavior of the group of entities may be based on a Bayesian model. The Bayesian model may be such that it comprises one of the conditional probability terms: P(G/T); P(Y/G,T); P(A/Y,G,T); and P(N/A,Y,G,T). [0048]The conditional probability terms may be updated with an interpolation term with an interpolation weight w. [0049]The conditional probability terms may be updated with an interpolation term with an interpolation weight w, wherein: P(U/T)→wP(U/T)+(1-w)P(G/T) P(D/U,T)→wP(D/U,T)+(1-w)P(Y/G,T) P(A/D,U,T)→wP(A/D,U,T)+(1-w)P(A/Y,G,T) P(N/A,D,U,T)→wP(N/A,D,U,T)+(1-w)P(N/A,Y,G,T) [0177] The interpolation formula is a seamless way of starting with the group model for the new user and gradually transitioning to the specific user model over time as data builds up. [0178] Combining the group behavior model with the user model can reduce false alerts. Examiner note: the reference teaches constructing a Bayesian model based on data associated with entities of a computer system and metrics representative of the data. Thus, the reference teaches a causal/probabilistic model constructed based on a data-driven method. The reference also teaches conditional probability terms for the Bayesian model and updating conditional probability terms using interpolation, where a conditional probability term of one model is modified based on a corresponding conditional probability term of another model, for example modifying P(U/T) based on P(G/T), modifying P(D/U,T) based on P(Y/G,T), modifying P(A/D,U,T) based on P(A/Y,G,T), and modifying P(N/A,D,U,T) based on P(N/A,Y,G,T). The reference further explains that this interpolation combines the group behavior model with the user model. Thus, the reference teaches using a data-driven Bayesian model and combing model information by modifying conditional probabilities based on corresponding conditional probabilities form another model).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Cinato and Mosleh to incorporate the teachings of Ferguson and to apply constructing a Bayesian model based on data and metrics associated with entities of a computer system and updating conditional probability terms using an interpolation term based on corresponding conditional probability terms from another Bayesian model in order to provide a data-driven probability model and combine probability information from different Bayesian models for abnormality estimation. In this case, Cinato teaches using a Bayesian/probabilistic model to estimate the location or cause of a fault in a communication network based on alarms or status changes. Mosleh teaches a hybrid causal model including a first causal model, a second causal model, and a computational model constructed from the first causal model and the second causal model. Ferguson teaches constructing Bayesian models from observed data and metrics and updating conditional probability terms using corresponding conditional probability terms from another model. The combination of teachings would predictably allow the hybrid causal model framework applied to Cinato’s communication network fault estimation to use data-derived probability information and to combine conditional probability information from different Bayesian models, thereby improving the accuracy and reliability of abnormality estimation as observed data becomes available.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Khanduja US20110055138A1, discloses a method of processing network activity data, includes
receiving network activity data and generating an event based on the network activity data. The method also includes generating a probability based at least in part on Bayesian statistics, the probability corresponding to a likelihood that the event caused or was caused by another event. The method also includes generating an event message corresponding to the event based on the probability.
Skaanning US20010011260A1, discloses an automated diagnostic system uses Bayesian networks to
diagnose a system. Knowledge acquisition is performed in preparation to diagnose the system. An issue to diagnose is identified. Causes of the issue are identified. Subcauses of the causes are identified. Diagnostic steps are identified. Diagnostic steps are matched to causes and subcauses. Probabilities for the causes and the subcauses identified are estimated. Probabilities for actions and questions set are estimated. Costs for actions and questions are estimated.
Yemini US20050137832A1, discloses determining the source of a problem in a complex system of
managed components based upon symptoms. The problem source identification process is split into different activities. Explicit configuration non-specific representations of types of managed components, their problems, symptoms and the relations along which the problems or symptoms propagate are created that can be manipulated by executable computer code. A data structure is produced for determining the source of a problem by combining one or more of the representations based on information of specific instances of managed components in the system. Computer code is then executed which uses the data structure to determine the source of the problem from one or more symptoms.
Lakshmanan US20140006871A1, discloses techniques are provided for gathering network
information, analyzing the gathered information to identify correlations, and for diagnosing a problem based upon the correlations. The diagnosis may identify a root cause of the problem. In certain embodiments, a computing device may be configurable to determine a first event from information, allocate a first event to a first cluster, the first cluster is from one or more clusters of events, based on a set of attributes for the first event, and determine a set of attributes for the first cluster, and rank the first cluster against the other clusters from the one or more clusters of events based on the set of attributes for the first cluster. The set of attributes may be indicative of the relationship between events in the cluster. In some embodiments, one or more recommendations may be provided for taking preventative or corrective actions for the problem.
M. Julia Flores et al., “Incorporating expert knowledge when learning Bayesian network structure: A medical case study,” Published in 2011, discloses a methodology for incorporating expert knowledge as structural priors when learning BNs … We also presented novel visualisations of the learned networks, which support the interactive development process by allowing the knowledge engineers to assess intermediate results and revise experimental parameters. These visualisations could also assist comparisons of BN learning algorithms (e.g., [12]) …
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37
CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to whose telephone number is (571)270-1303. The examiner can normally be reached Monday - Friday.
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, Emerson Puente can be reached at (571)272-3652. 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.
/YI . HAO/
Examiner, Art Unit 2187
/EMERSON C PUENTE/Supervisory Patent Examiner, Art Unit 2187
Prosecution Insights