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 .
DETAILED ACTION
1. The amendment filed on 07/22/2026 has been received and considered. Claims 1-20 are presented for examination.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
2. Claims 8-10 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 8-10 recite the limitation "the data points" in line 3. There is insufficient antecedent basis for this limitation in the claim.
Claim 9 recites the limitation "the data points" in line 3. There is insufficient antecedent basis for this limitation in the claim.
Claim 9 recites the limitation "the weights of the data points" in line 3. There is insufficient antecedent basis for this limitation in the claim.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
3. Claims 1-6 and 11-20 are rejected under 35 U.S.C. 103 as being unpatentable over Martinez Canedo (US 20200090085 A1) in view of Stojanovic (US 20190138538 A1) and further in view of Meyerzon (US 20220019908 A1).
As per Claim 1, 11, and 16, Martinez Canedo teaches a method/system/non-transitory computer-readable medium storing instruction for updating digital twins ([0006] “a system for managing a plurality of digital twins using a graph-based structure, the system includes one or more databases storing a DTG comprising a plurality of sub-graphs. Each sub-graph comprises a plurality of nodes associated with a distinct physical object”), the method comprising:
obtaining, by one or more processors, knowledge hierarchy information including digital twin structure information, ontology information, and relationship information; ([0023] "Edges connecting nodes are used to represent the relationships between the DTUs. Edges can be, for example, spatial (e.g., aggregations, hierarchies, dependencies), temporal (e.g., life cycle stages, time-stamped data)"; [0024] "existing general knowledge bases, ontonlogies, and tools are processed to extract data and incorporate it into the DTG via new DTUs or edge connections”);
determining, by the one or more processors, a knowledge graph based on the knowledge hierarchy information, wherein the knowledge graph represents a digital twin of a real world counterpart, ([0021] "the DTG is dynamic in the sense that the graph can continuously morph with the creation and elimination of nodes and edges"; [0022] "FIG. 1 shows how the DTG can be used as the information fabric where real-world objects and their relationships are represented digitally... A real-world object is not represented by a single node, but by a sub-graph in the DTG ": the digital twin graph determined from the graph's structural information represents a digital twin of the real world counterpart), wherein the knowledge graph comprises a plurality of components; ([0022] "A real-world object is not represented by a single node, but by a sub-graph in the DTG": the sub-graphs and their digital twin units are the recited plurality of components of the knowledge graph). In particular, Martinez Canedo teaches a dynamic digital twin graph in which real-world objects are represented as sub-graphs of digital twin units whose nodes and edges are continuously created, eliminated, and updated as data arrives. However, Martinez Canedo fails to teach explicitly performing, by the one or more processors, similarity measurements on the knowledge graph to generate similarity information for one or more components of the plurality of components of the knowledge graph;
performing, by the one or more processors, variable ranking calculations on the similarity information to generate ranked similarity information for the one or more components of the plurality of components of the knowledge graph;
performing, by the one or more processors, variable clustering operations on the ranked similarity information to generate variable cluster information for the one or more components of the plurality of components of the knowledge graph; and
outputting, by the one or more processors, a recommendation for updating the knowledge hierarchy information, the knowledge graph, or both, based on the variable cluster information, wherein the recommendation includes update information for updating a relationship of the knowledge graph, and wherein the update information includes a new relationship between components of the knowledge graph based on clusters identified from the variable cluster information.
Stojanovic teaches performing, by the one or more processors, similarity measurements on the knowledge graph to generate similarity information for one or more components of the plurality of components of the knowledge graph ([0073] “Knowledge service 310 can access one or more knowledge graphs or other knowledge sources 340. The knowledge sources can include publicly available information published by web sites, web services, curated knowledge stores, and other sources”; [0104] "Similarity metric module 314 can implement a method to determine the semantic similarity between two or more datasets. This may also be used to match the user's data to reference data available through the knowledge service 330."; [0107] “Similarity metric module 314 can implement a method to determine the semantic similarity between two or more datasets. ... Similarity metric module 314 may perform similarity metric analysis as described in this disclosure including the descriptions with reference to FIGS. 6-15: the semantic similarity computed over knowledge-graph-backed data sets is the recited similarity information for components of the knowledge graph);
performing, by the one or more processors, variable ranking calculations on the similarity information to generate ranked similarity information for the one or more components of the plurality of components of the knowledge graph ([0170]-[0175] “categories 1404 in curated data 1406 may be determined and ranked based on the similarity metric. The ranked categories 1404 can be assessed to identity the highest ranking category, which can be associated with the data 1402.”; "Based on the similarity metric determined by the comparison, a rank of closeness can be determined based on comparison of data 1502 to curated data. The rank of closeness can be used to identify categories for data 1502.": the rank of closeness determined from the similarity metric is the recited ranked similarity information); and
performing, by the one or more processors, variable clustering operations on the ranked similarity information to generate variable cluster information for the one or more components of the plurality of components of the knowledge graph ([0154], [0159], [0172], [0181] "Using a vector analysis method (e.g., K-means clustering), other words from the word augmentation list that are “close” to the words in the input data set can be identified.": the clustering of similarity-ranked members by the vector analysis method generates the recited variable cluster information).
Martinez Canedo and Stojanovic are analogous art because they are both from the same field of endeavor, knowledge-graph-based management and analysis of digital data representing real-world systems.
It would have obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of cited references. Thus, one of ordinary skill in the art before the effective filling date of the claimed invention would have been motivated to incorporate Stojanovic into Martinez Canedo’s invention for purpose of or managing a plurality of digital twins using a graph-based structure. In particular, Stojanovic teaches data enrichment system with similarity metric module is designed to identify datasets based on their metadata attributes and data values enabling easier indexing and high performance retrieval of data values (Stojanovic: [0016], [0018]) so that downstream processing can prioritize the highest-ranking variable groupings rather than treating all similar variables as equally salient.
However, Martinez Canedo as modified by Stojanovic fails to teach explicitly outputting, by the one or more processors, a recommendation for updating the knowledge hierarchy information, the knowledge graph, or both, based on the variable cluster information; and wherein the recommendation includes update information for updating a relationship of the knowledge graph, and wherein the update information includes a new relationship between components of the knowledge graph based on clusters identified from the variable cluster information.
On the other hand, Meyerzon teaches outputting, by the one or more processors, a recommendation for updating the knowledge hierarchy information, the knowledge graph, or both, based on the variable cluster information ([0158] "A knowledge graph merge/link process 550 updates the knowledge graph 310 based on the output of the clustering process 546"; [0159] "The knowledge graph 310 provides suggestions for the topic page 342 based on the attributes of the entity record and linked entities": the merge/link update driven by the output of the clustering process, surfaced as suggestions, is the recited recommendation based on the variable cluster information), wherein the recommendation includes update information for updating a relationship of the knowledge graph, and wherein the update information includes a new relationship between components of the knowledge graph based on clusters identified from the variable cluster information ([0184] "A link by clustering process 1040 is similar to the clustering process 1020, except the link by clustering process 1040 operates on the potential entity names and the set of candidate entity records"; [0103] "The incremental clustering may include linking the potential entity names with at least partial matching ones of the set of candidate entity records… The disclosed mining systems may update the knowledge graph with the updated matching candidate entity records "; [0185] "An update process 1050 stores the merged entity records, updated entity records, or new entity records in the knowledge graph 1060": the link created by the link-by-clustering process between entities of the knowledge graph, stored into the graph by the update process, is the recited new relationship between components based on the identified clusters).
Martinez Canedo, Stojanovic, and Meyerzon are analogous art because they are all from the same field of endeavor, knowledge-graph-based management and analysis of digital data representing real-world systems.
Therefore, it would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to further incorporate Meyerzon into Canedo as modified by Stojanovic’s invention for purpose of for managing a plurality of digital twins using a graph-based structure. In particular, Meyerzon teaches cluster-driven recommendation-to-update step which accurately mine information (Meyerzon: [0001], [0026]).
As per Claim 2, Martinez Canedo teaches updating, by the one or more processors, the knowledge hierarchy information, the knowledge graph, or both based on the recommendation to generate updated knowledge information; ([0022] "This update by the OEM, also updates the DTG. Interactions like these are continuously updating the DTG": the update pushed on the basis of the graph's information updates the digital twin graph and generates the recited updated knowledge information).
However, Martinez Canedo fails to teach explicitly running, by the one or more processors, a query against the updated knowledge information to obtain a query result, wherein the query corresponds to a software development query and the query result indicates an outcome or optimization of one or more variables of knowledge graph.
Stojanovic teaches running, by the one or more processors, a query against the updated knowledge information to obtain a query result, wherein the query corresponds to a software development query and the query result indicates an outcome or optimization of one or more variables of knowledge graph ([0100] "A transform script may be generated based on a chosen recommendation or requested by a user interactively through a graphical user interface"; [0098] "A linear transformation may be implemented through use of an API (e.g., Spark API). The transform actions may be performed by operations invoked using the API. A transform script may be configured based on transform operations defined using the API.": a user request that generates a transform script through the API is a query corresponding to a software development query (i.e., the "software development query" as claimed), and the generated script's transform operations over the data indicate the recited outcome or optimization of the variables).
As per Claim 3, Martinez Canedo teaches wherein updating the knowledge hierarchy information, the knowledge graph, or both further includes:
merging the knowledge graph with at least one other knowledge graph to generate an updated knowledge graph, the updated knowledge graph representing a heterogenous digital twin system;
generating the updated knowledge graph and modifying a knowledge model hierarchy indicated by the knowledge hierarchy information based on the updated knowledge graph ([0024] "existing general knowledge bases, ontonlogies, and tools are processed to extract data and incorporate it into the DTG via new DTUs or edge connections";
modifying a component or relationship of the knowledge model hierarchy ([0006] "modify the sub-graphs and edge connections between the sub-graphs based on the data received via the one or more sensor interfaces"); or
modifying the knowledge model hierarchy and updating one or more knowledge models representing multiple digital twins based on the modified knowledge model hierarchy.
As per Claim 4, Martinez Canedo teaches wherein obtaining the knowledge hierarchy information includes:
generating, by the one or more processors, the knowledge hierarchy information based on the ontology information and domain data corresponding to a domain associated with the ontology information ([0024] "a mixed-driven approach may be used that incorporates scenario information, engineering knowledge, and general knowledge"); or
receiving, by the one or more processors, the knowledge hierarchy information from a knowledge hierarchy instantiator or database. ([0006] "the system includes one or more databases storing a DTG comprising a plurality of sub-graphs"; [0024] "To bootstrap the DTG, a mixed-driven approach may be used that incorporates scenario information, engineering knowledge, and general knowledge”).
As per Claim 5, Martinez Canedo teaches wherein determining the knowledge graph includes:
generating, by the one or more processors, the knowledge graph based on ontology data and domain data corresponding to a domain associated with the ontology information ([0021] "the DTG is dynamic in the sense that the graph can continuously morph with the creation and elimination of nodes and edges. This morphing is the result of updates by data, queries, simulation, models, new providers, new consumers", “existing databases (e.g., GraphX, Linked Data) and algorithms (e.g., Pregel, MapReduce) running in cloud platforms”); or
receiving, by the one or more processors, the knowledge graph from a knowledge graph instantiator or database. ([0021] "the DTG is dynamic in the sense that the graph can continuously morph with the creation and elimination of nodes and edges. This morphing is the result of updates by data, queries, simulation, models, new providers, new consumers", “existing databases (e.g., GraphX, Linked Data) and algorithms (e.g., Pregel, MapReduce) running in cloud platforms”).
As per Claim 6, Martinez Canedo teaches wherein generating the knowledge graph includes: analyzing, by the one or more processors, data source information, and the knowledge hierarchy information, to generate analyzed data source information ([0023]- [0024] "Edges connecting nodes are used to represent the relationships between the DTUs", "The data source engineering knowledge is processed by one or more extractors to extract relevant information for the DTG");
analyzing, by the one or more processors, twin architecture artifact information to generate twin architecture information ([0023]- [0024] "Edges connecting nodes are used to represent the relationships between the DTUs", "The data source engineering knowledge is processed by one or more extractors to extract relevant information for the DTG"’ "Engineering knowledge is then incorporated including, for example, engineering principles (books, manuals, patents), models, time series data, system telemetry");
extracting, by the one or more processors, the plurality of components from the data source information and the twin architecture information as candidate nodes for the knowledge graph ([0023]- [0024] "Edges connecting nodes are used to represent the relationships between the DTUs", "The data source engineering knowledge is processed by one or more extractors to extract relevant information for the DTG); and
querying, by the one or more processors, the knowledge hierarchy information to determine relationships among the plurality of components and label the plurality of components to generate nodes for the knowledge graph. ( [0022] "The DTUs in the sub-graph may represent, for example, the CAD design, the service records, its current state (where it is, its speed, etc.)"; [0023]- [0024] "Edges connecting nodes are used to represent the relationships between the DTUs", "The data source engineering knowledge is processed by one or more extractors to extract relevant information for the DTG”).
As per Claim 12, Martinez Canedo fails to teach explicitly wherein the one or more processors are further configured to: provide an application programming interface (API) that provides recommendation or query building functionality; receive a user input indicating one or more query parameters; and generate the recommendation or a query based on the user input.
Stojanovic teaches provide an application programming interface (API) that provides recommendation or query building functionality ([0098] “A linear transformation may be implemented through use of an API (e.g., Spark API). The transform actions may be performed by operations invoked using the API. A transform script may be configured based on transform operations defined using the API”);
receive a user input indicating one or more query parameters ([0100] “a transform script may be generated based on a chosen recommendation or requested by a user interactively through a graphical user interface…. Based on the transform operations specified by a user through the graphical user interface, the transform engine 322 performs transform operations according to those operations”); and
generate the recommendation or a query based on the user input ([0100] “a transform script may be generated based on a chosen recommendation or requested by a user interactively through a graphical user interface…. Based on the transform operations specified by a user through the graphical user interface, the transform engine 322 performs transform operations according to those operations”).
As per Claim 13, Martinez Canedo fails to teach explicitly wherein the one or more processors are further configured to: display a graphical user interface that includes the recommendation or a query result.
Stojanovic teaches display a graphical user interface that includes the recommendation or a query result ([0100] “a transform script may be generated based on a chosen recommendation or requested by a user interactively through a graphical user interface.”).
As per Claim 14, Martinez Canedo teaches wherein the one or more processors are further configured to:
generate a control signal based on the recommendation or a query result ([0022] "we can, for example, predict when John Doe will wake up the next morning to drive his car to work and the original equipment manufacturer (OEM) of the car can use this information to push a software update to the car"); and
transmit the control signal to the real world counterpart ([0022] "to push a software update to the car through the air while John Doe sleeps").
As per Claim 15, Martinez Canedo teaches wherein the real world counterpart is a machine, a workflow, a process, an entity or enterprise, or a combination thereof ([0022] "Real world physical objects such as cars, people, buildings, airplanes, highways, houses, transportation systems are represented in the DTG").
As per Claim 17, Martinez Canedo teaches wherein the knowledge graph comprises a plurality of nodes and edges connecting at least some of the plurality of nodes to one or more other nodes ([0006], [0021], [0023] "each node in the graph corresponds to a digital twin unit associated with the distinct physical object" , “Edges connecting nodes are used to represent the relationships between the DTUs. Edges can be, for example, spatial (e.g., aggregations, hierarchies, dependencies), temporal (e.g., life cycle stages, time-stamped data), interaction flow-related ... and/or business flow-related").
As per Claim 18, Martinez Canedo teaches wherein:
each of the variables corresponds to a node of the plurality of nodes ([0006], [0022]-[0023] "each node in the graph corresponds to a digital twin unit associated with the distinct physical object", “Edges connecting nodes are used to represent the relationships between the DTUs. Edges can be, for example, spatial (e.g., aggregations, hierarchies, dependencies),"); and
directed edges between nodes represent conditional dependencies between variables corresponding to the nodes. ([0006], [0023] "each node in the graph corresponds to a digital twin unit associated with the distinct physical object", “Edges connecting nodes are used to represent the relationships between the DTUs. Edges can be, for example, spatial (e.g., aggregations, hierarchies, dependencies),")
As per Claim 19, Martinez Canedo teaches wherein the variables are mapped to domain ontology classes of the ontology information and relationships between classes of the ontology information are mapped to dependencies between the variables ([0006], [00233]-[0024] "modify the sub-graphs and edge connections between the sub-graphs based on the data received via the one or more sensor interfaces", "existing general knowledge bases, ontonlogies, and tools are processed to extract data and incorporate it into the DTG via new DTUs": Incorporation of ontology-derived data into DTUs reads on mapping the variables to domain ontology classes; edge connections between DTU sub-graphs that derive from ontology-class relationships read on mapping class relationships to variable dependencies).
As per Claim 20, Martinez Canedo teaches wherein each of the edges corresponds to a use relation between two nodes of the plurality of nodes, wherein the knowledge graph represents syntactic relationships, semantic relationships, or both, and wherein the knowledge hierarchy information includes or corresponds to a knowledge hierarchy model ([0007] "the DTG comprises a first sub-graph corresponding to a first physical object and a second-graph corresponding to a second physical object connected by an edge indicating that the first physical object is using the second physical object"; [0021]-[0023] “a specialized database that uses graph structures for semantic queries (i.e., a “graph database”)”, "interaction flow-related (e.g., physical, information, and non-physical interfaces including machine-machine, machine-human, human-machine), and/or business flow-related (e.g., supply chain, customer orders, logistics, financials, organizational, etc.)": hierarchical sub-graph organization in paragraph [0021] corresponds to knowledge hierarchy model).
4. Claims 7-8 are rejected under 35 U.S.C. 103 as being unpatentable over Martinez Canedo (US 2020/0090085 A1) in view of Stojanovic (US 11,379,506 B2), further in view of Meyerzon (US 2022/0019908 A1), further in view of D'Orazio (“Distances with mixed type variables some modified Gower's coefficients”).
Martinez Canedo as modified by Stojanovic and Meyerzon teaches most all the instant invention as applied to claims 1-6 and 11-20 above.
As per Claim 7, Martinez Canedo as modified by Stojanovic and Meyerzon teaches performing the similarity measurements further includes: converting, …, knowledge graph variables into data points based on the knowledge graph and using the knowledge hierarchy information (Martinez Canedo: [0021]; Meyerzon [0030]); and
performing similarity measurements on the data points (Stojanovic: [0104], [0107] “Similarity metric module 314 can implement a method to determine the semantic similarity between two or more datasets. ... Similarity metric module 314 may perform similarity metric analysis as described in this disclosure including the descriptions with reference to FIGS. 6-15”).
Martinez Canedo as modified by Stojanovic and Meyerzon fails to teach explicitly using one-hot encoding.
D'Orazio teaches using one-hot encoding (Abstract "the choice of the distance function depends mainly on the type of the selected variables").
Martinez Canedo as modified by Stojanovic and Meyerzon and D'Orazio are analogous art because they are all related to a computer system including a similarity measurement.
It would have obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of cited references. Thus, one of ordinary skill in the art before the effective filling date of the claimed invention would have been motivated to incorporate D'Orazio into Martinez Canedo as modified by Stojanovic and Meyerzon’s invention for purpose of or managing a plurality of digital twins using a graph-based structure. In particular, Stojanovic teaches data enrichment system with similarity metric module is designed to identify datasets based on their metadata attributes and data values enabling easier indexing and high performance retrieval of data values (Stojanovic: [0016], [0018]) so that downstream processing can prioritize the highest-ranking variable groupings rather than treating all similar variables as equally salient and Meyerzon teaches cluster-driven recommendation-to-update step which accurately mine information (Meyerzon: [0001], [0026]). Further D'Orazio describes the advantage of being applicable for solving problems such as clustering, imputation, etc. of apply one-hot encoding as the canonical categorical-to-numerical pre-processing step that precedes the similarity-metric computation (pg 4).
As per Claim 8, Martinez Canedo as modified by Stojanovic and Meyerzon fails to teach explicitly wherein performing variable ranking calculations includes: calculating Gower's distance between each data point of the data points; and calculating weights for each data point of the data points based on the calculated Gower's distance for each data point to understand a similarity between the data points.
D'Orazio teaches calculating Gower's distance between each data point of the data points (Abstract "The most popular distance for mixed type variables is derived as the complement of the Gower's similarity coefficient; it is appealing because ranges between 0 and 1 and allows to handle missing values"; section 2-3 The Gower’s distance "The unweighted Gower’s distance assigns the same weight to each chosen variable and the final overall distance is just a simple average of distances calculated on each single variable"); and
calculating weights for each data point of the data points based on the calculated Gower's distance for each data point to understand a similarity between the data points (Abstract "reduce the unbalanced contribution of the different types of variables"; section 1-3 "the weights assigned to the different components of the overall distance are typically optimized taking into the characteristics of the clustering procedure”: the modification space reads on the recited per-data-point weighting based on Gower's distance).
5. Claims 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Martinez Canedo (US 20200090085 A1) in view of Stojanovic (US 20190138538 A1), Meyerzon (US 20220019908 A1) and D'Orazio (“Distances with mixed type variables some modified Gower's coefficients”), further in view of Edge (US 20210019558 A1).
Martinez Canedo as modified by Stojanovic and Meyerzon teaches most all the instant invention as applied to claims 1-6 and 11-20 above.
As per Claim 9, Martinez Canedo as modified by Stojanovic, Meyerzon, and D'Orazio teaches wherein performing variable clustering operations further includes:
performing, based on the weights of the data points, … clustering of the one or more components associated with the data points to generate a cluster graph (Martinez Canedo: [0021] “the DTG is also self-learning in the sense that algorithms may be used to analyze the morphing of the graph to identify emergent patterns and behaviors.”; Stojanovic: [0154], [0159], [0172], [0181] “Using a vector analysis method (e.g., K-means clustering), other words from the word augmentation list that are “close” to the words in the input data set can be identified”; D'Orazio: section I “the weights assigned to the different components of the overall distance are typically optimized taking into the characteristics of the clustering procedure;”; section 2.1. “The unweighted Gower’s distance assigns the same weight to each chosen variable and the final overall distance is just a simple average of distances calculated on each single variable.”)
Martinez Canedo as modified by Stojanovic, Meyerzon, and D'Orazio fails to teach explicitly density and distance based.
Edge teaches density and distance based ([0085], [0089]-[0093] “performing spatial clustering (e.g., DBSCAN) of the nodes in the embedding space”).
Martinez Canedo as modified by Stojanovic and Meyerzon and D'Orazio, and Edge are analogous art because they are all related to a computer system including a similarity measurement.
It would have obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of cited references. Thus, one of ordinary skill in the art before the effective filling date of the claimed invention would have been motivated to incorporate Edge into Martinez Canedo as modified by Stojanovic, Meyerzon and D'Orazio’s invention for purpose of or managing a plurality of digital twins using a graph-based structure to provide an improved metric for the analysis of the collected data with accuacty (Edge: [0002], [0089]). In particular, Stojanovic teaches data enrichment system with similarity metric module is designed to identify datasets based on their metadata attributes and data values enabling easier indexing and high performance retrieval of data values (Stojanovic: [0016], [0018]) so that downstream processing can prioritize the highest-ranking variable groupings rather than treating all similar variables as equally salient and Meyerzon teaches cluster-driven recommendation-to-update step which accurately mine information (Meyerzon: [0001], [0026]). Further D'Orazio describes the advantage of being applicable for solving problems such as clustering, imputation, etc. of apply one-hot encoding as the canonical categorical-to-numerical pre-processing step that precedes the similarity-metric computation (pg 4).
As per Claim 10, Martinez Canedo as modified by Stojanovic, Meyerzon, and D'Orazio teaches wherein performing variable clustering operations further includes:
grouping closely coupled variables of the cluster graph together to form clusters based on one or more grouping thresholds (Meyerzon: [0103] "The disclosed mining systems may perform clustering on a number of the instances to determine potential entity names"); and
identifying one or more similar variables of a particular cluster of the clusters, one or more relationships of the one or more variables of a cluster, or both, wherein the recommendation is generated based on the identified one or more similar variables, or a combination thereof (Meyerzon: [0159], [0043], [0103] "The disclosed mining systems may then query the knowledge graph with the potential entity names to obtain a set of candidate entity records ... update the knowledge graph with the updated matching candidate entity records": The cluster-driven candidate-entity-record query and update corresponds to the recited identification of similar variables and relationships within a cluster as the basis for the recommendation.).
Response to Arguments
6. Applicant's arguments filed on 07/22/2026 have been fully considered but they are not persuasive.
Examiner respectfully withdraws Objections to Specification in view of the amendment and/or applicant’s arguments.
Examiner respectfully withdraws Claim Objections in view of the amendment and/or applicant’s arguments.
Applicants have argued that:
PNG
media_image1.png
213
701
media_image1.png
Greyscale
The arguments 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. As rejected above, it is Examiner’s position that Meyerzon teaches the claimed limitation. In particular, Meyerzon's link by clustering process 1040 expressly creates links between entities of the knowledge graph as a function of clustering output ([0184], [0103]), the knowledge graph merge/link process 550 updates the knowledge graph based on the output of the clustering process 546 ([0158]), and the update process 1050 stores the merged, updated, and newly linked entity records into the knowledge graph ([0185]).
With respect to dependent claim 3, applicants have argued that:
PNG
media_image2.png
118
710
media_image2.png
Greyscale
Claim 3 recites its operations in the alternative, joined by “or”. A rejection needs only show one of the recited alternatives, and the rejection of record relied on Martinez Canedo for the modifying alternatives ([0024], [0006]). Moreover, the argument fails even as to the merging alternative, because Meyerzon expressly teaches merging a mined knowledge graph with an existing knowledge graph: the knowledge graph merge process 550 merges entities from the clustering process 546, ENER topics 547, and user-based topics 564 with the existing knowledge graph 310 ([0158]), and the multiple toolkit linking system is configured to link and conflate topics from multiple sources ([0038]).
Thus 103 rejection maintains.
Conclusion
7. Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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.
8. Any inquiry concerning this communication or earlier communications from the examiner should be directed to EUNHEE KIM whose telephone number is (571)272-2164. The examiner can normally be reached Monday-Friday 9am-5pm ET.
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, Ryan Pitaro can be reached at (571)272-4071. 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.
EUNHEE KIM
Primary Examiner
Art Unit 2188
/EUNHEE KIM/ Primary Examiner, Art Unit 2188
Prosecution Insights