DETAILED ACTION
Claims 1, 19 and 20 have been amended. Claims 8 and 12-13 have been previously cancelled. Claims 1-7, 9-11 and 14-21 remain pending in the application.
Claims 1, 19 and 20 are independent.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office 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 and Arguments
Applicant’s amendments to the Claims have overcome 101 rejections directed to non-statutory subject matter set forth in the Final Office Action. As a result, the 101 rejections directed to non-statutory subject matter have been withdrawn.
Applicant’s amendments to the Claims have not overcome 101 abstract idea rejections set forth in the Non-Final Office Action. As a result, the 101 abstract idea rejections have been maintained.
Applicant's arguments regarding rejections directed to amended claims under 35 U.S.C. § 103 have been fully considered but in moot in view of new ground of rejection.
Applicant amended independent claims to further specify:
… and electrical connections in at least one feeder network are at least partially un-mapped within an existing grid model;
…
for each of one or more of the feeder networks, generating a model input for a graph neural network (GNN) model, the generating comprising: identifying a respective set of electrical assets belonging to the feeder network based on the partition data, and representing the respective set of electrical assets as a respective set of nodes, wherein each node represents an electrical asset in the feeder network and includes a node feature specifying characteristics of the corresponding electrical asset;
for each of the one or more of the feeder networks, processing the model input using the GNN model to generate predicted connectivity data comprising, for each pair of nodes in the respective set of nodes, an edge connecting the pair of nodes and indicating a predicted physical connection between electrical assets represented by the pair of the nodes;
The teachings of Kann, Sun, Kuloor and Clark as disclosed in the previous office action are hereby incorporated by references to the extent applicable to the amended claims.
Another iteration of claim analysis has been made. Referring to the corresponding sections of the claim analysis below for details.
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.
Claims 1-7, 9-11 and 14-21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to abstract idea without significantly more.
The claim 19 recites:
A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising:
obtaining asset data for an electric power distribution system in a geographic area, in which the electric power distribution system comprises a plurality of electrical assets belonging to different feeder networks and electrical connections in at least one feeder network are at least partially un-mapped within an existing grid model, the asset data comprising: for each of the plurality of electrical assets of the electrical power distribution system, data indicating one or more characteristics of the electrical asset;
obtaining sensor data for the electric power distribution system, the sensor data comprising measurement data and sensor location data from a plurality of electric sensors; and
processing an input comprising the asset data, the measurement data, and the sensor location data to generate partition data, the partition data comprising: for each of the plurality of electrical assets, a partition identifier that assigns the electrical asset to one of a set of feeder networks;
for each of one or more of the feeder networks, generating a model input for a graph neural network (GNN) model, the generating comprising: identifying a respective set of electrical assets belonging to the feeder network based on the partition data, and representing the respective set of electrical assets as a respective set of nodes, wherein each node represents an electrical asset in the feeder network and includes a node feature specifying characteristics of the corresponding electrical asset;
for each of the one or more of the feeder networks, processing the model input using the GNN model to generate predicted connectivity data comprising, for each pair of nodes in the respective set of nodes, an edge connecting the pair of nodes and indicating a predicted physical connection between electrical assets represented by the pair of the nodes;
generating, based on the predicted connectivity data, a predicted electric grid connectivity map indicating locations of the plurality of electrical assets within the set of feeder networks; and
providing the predicted electric grid connectivity map on an output device.
Step 1:
The claim recites a system. Thus, the claim is directed to a product, which belongs to statutory categories of invention.
Step 2A Prong one:
Claim 19 recites the limitations of “processing an input comprising the asset data, the measurement data, and the sensor location data to generate partition data, the partition data comprising: for each of the plurality of electrical assets, a partition identifier that assigns the electrical asset to one of a set of feeder networks; for each of one or more of the feeder networks, generating a model input for a graph neural network (GNN) model, the generating comprising: identifying a respective set of electrical assets belonging to the feeder network based on the partition data, and representing the respective set of electrical assets as a respective set of nodes, wherein each node represents an electrical asset in the feeder network and includes a node feature specifying characteristics of the corresponding electrical asset; for each of the one or more of the feeder networks, processing the model input using the GNN model to generate predicted connectivity data comprising, for each pair of nodes in the respective set of nodes, an edge connecting the pair of nodes and indicating a predicted physical connection between electrical assets represented by the pair of the nodes; generating, based on the predicted connectivity data, a predicted electric grid connectivity map indicating locations of the plurality of electrical assets within the set of feeder networks”. The recited “processing … to generate …, generating … identifying …; processing … to generate …; generating …” steps, as drafted, but for “using the GNN model”, are processes that, under its broadest reasonable interpretation, cover performance of the limitation in the mind or with pen and paper. For example, processing the asset data and the sensor data including the measurement data and location data to generate partition data, identifying a respective set of electrical assets based on the partition data and representing the respective set of electrical assets as set of nodes as model input, and generating an electric grid connectivity map based on the model input can be done in the mind or with pen and paper, the asset associated with the sensor that measured voltage value is similar to the voltage at the transformer and the location is within a distance threshold can be assigned and grouped to the feeder that the transformer is connected to and associate the sensor and the power line connection to the transformer ID, with the transformer and the meters as network nodes, and a distribution map can be drawn based on grouped nodes to connect the node of the sensor associated with to the transformer using the power line. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A Prong two:
Besides the abstract ideas, the claim recites additional elements of 1) “obtaining asset data for an electric power distribution system in a geographic area, in which the electric power distribution system comprises a plurality of electrical assets belonging to different feeder networks and electrical connections in at least one feeder network are at least partially un-mapped within an existing grid model, the asset data comprising: for each of the plurality of electrical assets of the electrical power distribution system, data indicating one or more characteristics of the electrical asset” and “obtaining sensor data for the electric power distribution system, the sensor data comprising measurement data and sensor location data from a plurality of electric sensors” that represent mere receiving data that is necessary for use of the recited judicial exception, and are recited at a high level of generality (For example, see MPEP 2106.05(g), which notes that mere data gathering, outputting and storing can be seen as insignificant extra-solution activity). These limitations are thus insignificant extra-solution activities and do not integrate the judicial exception into a practical application.
The recited 2) “one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations” are additional elements which are to implement the system. But the “computers” and “storage devices” are recited at high level of generality (no details whatsoever are provided other than it is “computers” or “storage devices”) that they represent no more than mere instructions to apply the judicial exceptions and does not integrate the judicial exception into a practical application. See also MPEP 2106.05(f).
The claim recites the additional limitations of 3) “using the GNN model”, this additional limitation is recited at high level of generality (no details whatsoever are provided other than “using”) that is merely applying GNN model on the recited judicial exception. These limitations are thus insignificant extra-solution activities and do not integrate the judicial exception into a practical application.
The recited 4) “providing the predicted electric grid connectivity map on an output device” is additional limitation that is recited at high level of generality (no details what so ever are provided other than causing to act), it is a general field of use and mere instruction to apply an exception (MPEP 2106.05(f)) or mere field of use and technological environment (MPEP 2016.05(h)) and does not integrate the judicial exception into a practical application.
Even when viewed in combination, these additional limitation and additional elements do not integrate the recited judicial exception into a practical application.
Step 2B:
The claim as a whole does not amounts to significantly more than the recited exception. The claim has the following additional limitations and elements:
1) “obtaining asset data for an electric power distribution system in a geographic area, in which the electric power distribution system comprises a plurality of electrical assets belonging to different feeder networks and electrical connections in at least one feeder network are at least partially un-mapped within an existing grid model, the asset data comprising: for each of the plurality of electrical assets of the electrical power distribution system, data indicating one or more characteristics of the electrical asset” and “obtaining sensor data for the electric power distribution system, the sensor data comprising measurement data and sensor location data from a plurality of electric sensors”;
2) “one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations”;
3) “using the GNN model”;
4) “providing the predicted electric grid connectivity map on an output device”.
Regarding 1), as explained previously, are extra-solution activities, which for purposes of Step 2A Prong Two was considered insignificant. As indicated in MPEP 2016.05(d) II, receiving, transmitting and storing data are considered well-known, routine and conventional activities in the field, and do not add inventive concept into the claim.
Regarding 2), “computers” and “storage devices” are at best the equivalent of merely adding the words “apply it” to the judicial exception. Mere instructions to apply an exception cannot provide an inventive concept.
Regarding 3), “using the GNN model”, as explained previously, are extra-solution activities, which for purposes of Step 2A Prong Two was considered insignificant. As indicated by the following sources, using the GNN model for network connection mapping are considered well-known, routine and conventional activities in the field, as disclosed in Yubo US 20230018575 A1 and Sun US 20220268827 A1. These limitations therefore remain insignificant extra-solution activities even upon reconsideration and do not add inventive concept into the claim.
Regarding 4) “providing the generated electric grid connectivity map on an output device” is additional limitation that is a general field of use and mere instruction to apply an exception or mere field of use and technological environment and does not add an inventive concept.
Therefore, the claim directs to an abstract idea without significantly more, and is not patent eligible.
Regarding claim 1,
Step 1: The claim recites a method. Thus, the claim is directed to a process, which belongs to statutory categories of invention.
Step 2A and Step 2B: Similarly, as recited in the rejection of claim 19, claim 1 is directed to abstract idea without significantly more. The additional elements “for generating a representation of an electric power grid” that merely link the recited judicial exception to a particular technology environment or particular field of use, do not integrate the judicial exception into a practical application, and do not add inventive concept. Therefore claim 1 is not patent eligible.
Claim 2 depends on claim 1, and recites additional limitations of “obtaining load data for the electric power distribution system in the geographic area, the load data comprising: for each of a plurality of load locations of the electrical power distribution system, data indicating one or more characteristics of the load location” that represent mere receiving data that is necessary for use of the recited judicial exception, or mere instructions to apply the judicial exceptions on a computer, and are recited at a high level of generality. These limitations are thus insignificant extra-solution activities and are considered well-known, routine and conventional activities in the field, do not integrate the recited judicial exception into a practical application, and do not add inventive concept. The recited additional limitation of “the partition data further comprises: for each of the plurality of load locations, a partition identifier that assigns the load location to one of a set of feeder networks” that merely specifies some details of the “generating …” (“mental process” group of abstract idea) and does not change the fact that the claim 2 is directed to abstract idea without significantly more. Therefore claim 2 is not patent eligible.
Claim 3 depends on claim 2, and recites additional limitations of “obtaining association data that indicates connectivity or geographical associations between each of the plurality of electric sensors with one of the electrical assets or with one of the load locations” that represent mere receiving data that is necessary for use of the recited judicial exception, or mere instructions to apply the judicial exceptions on a computer, and are recited at a high level of generality. These limitations are thus insignificant extra-solution activities and are considered well-known, routine and conventional activities in the field, do not integrate the recited judicial exception into a practical application, and do not add inventive concept. The recited additional limitation of “performing a correlation analysis of the measurement data from each of the plurality of electric sensors to generate a correlation result between each pair of the plurality of electric sensors” and “generating the partition data based on the correlation results and the association data” that merely specifies some details of the “generating …” (“mental process” group of abstract idea) and does not change the fact that the claim 3 is directed to abstract idea without significantly more. Therefore claim 3 is not patent eligible.
Claim 4 depends on claim 3, and recites additional limitation of “the correlation result between a pair of electric sensors comprises a waveform correlation between the measurement data from the pair of electric sensors” that merely specifies some details of the “generating …” (“mental process” group of abstract idea) and does not change the fact that the claim 4 is directed to abstract idea without significantly more. Therefore claim 4 is not patent eligible.
Claim 5 depends on claim 3, and recites additional limitation of “the correlation result between a pair of electric sensors comprises a temporal correlation of electric outages indicated by the measurement data from the pair of electric sensors” that merely specifies some details of the “generating …” (“mental process” group of abstract idea) and does not change the fact that the claim 5 is directed to abstract idea without significantly more. Therefore claim 5 is not patent eligible.
Claim 6 depends on claim 3, and recites additional limitation of “in response to determining that a correlation between the measurement data from a first electric sensor associated with a first electrical asset or a first load location and the measurement data from a second electric sensor associated with a second electrical asset or a second load location exceeds a threshold, assigning the first electrical asset or load location and the second electrical asset or load location to a same feeder network” that merely specifies some details of the “generating …” (“mental process” group of abstract idea) and does not change the fact that the claim 6 is directed to abstract idea without significantly more. Therefore claim 6 is not patent eligible.
Claim 7 depends on claim 1, and recites additional limitation of “generating a model input that comprises at least a portion of the asset data and at least a portion of the sensor data; and processing the model input using a partition machine learning model to generate the partition data” that merely specifies some details of the “generating …” (“mental process” group of abstract idea) and does not change the fact that the claim 7 is directed to abstract idea without significantly more. Therefore claim 7 is not patent eligible.
Claim 9 depends on claim 8, and recites additional limitation of “the predictive connectivity data further comprises data characterizing network connectivity characteristics for a plurality of load locations” that merely specifies some details of the “generating …” (“mental process” group of abstract idea) and does not change the fact that the claim 9 is directed to abstract idea without significantly more. Therefore claim 9 is not patent eligible.
Claim 10 depends on claim 8, and recites additional limitation of “the predictive connectivity data further comprises data characterizing one or more properties of one or more connection paths” that merely specifies some details of the “generating …” (“mental process” group of abstract idea) and does not change the fact that the claim 10 is directed to abstract idea without significantly more. Therefore claim 10 is not patent eligible.
Claim 11 depends on claim 10, and recites additional limitation of “the one or more properties comprise: a power rating, a line impedance, or line length of the one or more connection paths” that merely specifies some details of the “generating …” (“mental process” group of abstract idea) and does not change the fact that the claim 11 is directed to abstract idea without significantly more. Therefore claim 11 is not patent eligible.
Claim 14 depends on claim 12, and recites additional limitation of “the GNN further generates an updated node feature for each node, the updated node feature indicating one or more of: one or more electrical assets or loads connected to the node; or phase characteristics of current through the node” that merely specifies some details of the “processing … to generate …” (“mental process” group of abstract idea) and does not change the fact that the claim 14 is directed to abstract idea without significantly more. Therefore claim 14 is not patent eligible.
Claim 15 depends on claim 1, and recites additional limitation of “determining one or more pole locations from geospatial data; and for each pole location: determining a subset of the plurality of electrical assets located at the pole location based on the geospatial data; determining one or more feeders located at the pole location based the geospatial data and the partition data; and in response to determining that a single feeder is located at the pole location, updating the partition data to indicate the subset of the plurality of electrical assets being connected to the single feeder” that merely specifies some details of the “processing … to generate …” (“mental process” group of abstract idea) and does not change the fact that the claim 15 is directed to abstract idea without significantly more. Therefore claim 15 is not patent eligible.
Claim 16 depends on claim 1, and recites additional elements of “the plurality of electric sensors comprises one or more powerline sensors, wherein each powerline sensor repetitively measures one or more electric parameters through a power line of the electric power distribution system at a plurality of measurement time points” that merely link the recited judicial exception to a particular technology environment or particular field of use, do not integrate the judicial exception into a practical application, and do not add inventive concept. Therefore claim 16 is not patent eligible.
Claim 17 depends on claim 1, and recites additional elements of “the plurality of electric sensors comprises one or more utility meter sensors installed at one or more respective load locations, wherein each utility meter sensor repetitively measures a power consumption at the respective load location at a plurality of measurement time points” that merely link the recited judicial exception to a particular technology environment or particular field of use, do not integrate the judicial exception into a practical application, and do not add inventive concept. Therefore claim 17 is not patent eligible.
Claim 18 depends on claim 1, and recites additional elements of “the sensor data further comprises sensor information for each of the plurality of electric sensors, and the sensor information comprises one or more of: a location of the electric sensor; an address associated with the electric sensor; a type of the electric sensor; or a sensor ID” that merely link the recited judicial exception to a particular technology environment or particular field of use, do not integrate the judicial exception into a practical application, and do not add inventive concept. Therefore claim 18 is not patent eligible.
Regarding claim 20,
Step 1: The claim recites non-transitory computer storage media. Thus, the claim is directed to a product, which belongs to statutory categories of invention.
Step 2A and Step 2B: Similarly, as recited in the rejection of claim 19, claim 20 is directed to abstract idea without significantly more. The additional elements “non-transitory computer storage media” are recited at high level of generality that they represent no more than mere instructions to apply the judicial exceptions, and they do not integrate the judicial exception into a practical applicant and do not add an inventive concept. Therefore, claim 20 is not patent eligible.
Claim 21 depends on claim 1, and recites additional limitation of “generating, based on the predicted connectivity data, a prediction of one or more of operations or faults of the electric power grid” that merely specifies some details of the “generating …” (“mental process” group of abstract idea) and does not change the fact that the claim 21 is directed to abstract idea without significantly more. The additional limitation of “providing the prediction for display on an output device” is recited at high level of generality, it is a general field of use and mere instruction to apply an exception or mere field of use and technological environment, does not integrate the judicial exception into a practical application and does not add an inventive concept. Therefore claim 21 is not patent eligible.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-4, 9-11 and 14-21 are rejected under 35 U.S.C. 103 as being unpatentable over Kann US 20160109491 A1 in view of Sun US 20220268827 A11.
Regarding claim 19, Kann teaches a system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations (Figs. 1&5 [0023] [0050] sever 128) comprising:
obtaining asset data for an electric power distribution system in a geographic area, in which the electric power distribution system comprises a plurality of electrical assets belonging to different feeder networks and electrical connections in at least one feeder network are at least partially un-mapped within an existing grid model (Fig. 12 [0088] a request to generate a meter-to-transformer topology report for a plurality of meters and transformers in a geographic area, i.e. “electrical connections in at least one feeder network are at least partially un-mapped within an existing grid model”), the asset data comprising: for each of the plurality of electrical assets of the electrical power distribution system, data indicating one or more characteristics of the electrical asset (Figs. 1, 8&12 [0020] [0021] [0088] power distribution environment 100 comprises transformers and electrical meters belonging to different feeder networks of 104 and 108 i.e. “the electric power distribution system comprises a plurality of electrical assets belonging to different feeder networks”, receiving request to generate meter-to-transformer topology report, [0021] [0065] [0068] accessing the location information 804 indicating a power distribution area to be mapped, the location information including list of assets such as transformers, the utility poles, meters and distribution power lines, and loads such as house in a neighborhood, and locations of the assets and loads, i.e. “data indicating one or more characteristics of the electrical asset”);
obtaining sensor data for the electric power distribution system, the sensor data comprising measurement data and sensor location data from a plurality of electric sensors (Figs. 1, 5, 8&12 [0050] [0089] [0065] [0068] receiving time-stamped voltage values of meters and location information of meter); and
processing an input comprising the asset data, the measurement data, and the sensor location data to generate partition data, the partition data comprising: for each of the plurality of electrical assets, a partition identifier that assigns the electrical asset to one of a set of feeder networks (Figs. 1, 5, 8&12 [0051] [0052] [0090] each meter is correlated to corresponding transformer based on the time-stamped voltage values and location data of the meter, and Figs. 7-8 [0064] each meter is assigned to a specific transformer with unique transformer ID);
for each of one or more of the feeder networks, generating a model input for a model, the generating comprising: identifying a respective set of electrical assets belonging to the feeder network based on the partition data, and representing the respective set of electrical assets as a respective set of nodes, wherein each node represents an electrical asset in the feeder network (Figs. 1 and 7-8 [0020] [0051] [0052] [0058] – [0060] [0062] the correlated partition data is converted into a correlation data structure with each transformer node with unique ID as header and all of the meter nodes that correlated the corresponding transformer node listed in the rows below the header row, i.e. the meters nodes connected to the transformer node is identified as a respective set of electrical assets belonging to the feeder network, [0063] –[0065] the correlation data structure is input into a mapping module i.e. “model”);
for each of the one or more of the feeder networks, processing the model input using the model to generate predicted connectivity data comprising, for each pair of nodes in the respective set of nodes, an edge connecting the pair of nodes and indicating a predicted physical connection between electrical assets represented by the pair of the nodes; generating, based on the predicted connectivity data, a predicted electric grid connectivity map indicating locations of the plurality of electrical assets within the set of feeder networks (Figs. 1, 5, 8-10 &12 [0066] [0068] [0091] the model generating the predicted connectivity data comprising: the power distribution lines, the transformers on the utility poles, the meters and the house the meters are associated with, are represented by nodes, with line segments i.e. “edge” connecting the nodes to represent the electrical connection between the corresponding nodes, together with locations, are displayed on an electric grid connectivity map 900 and 1000); and
providing the predicted electric grid connectivity map on an output device. (Fig. 9 [0066] the map is displayed on a mobile device).
Kann does not explicitly further teach the model is a graph neural network (GNN) model and each node includes a node feature specifying characteristics of the corresponding electrical asset.
Sun explicitly teaches in an analogous art that the model is a graph neural network (GNN) model and each node includes a node feature specifying characteristics of the corresponding electrical asset (Figs. 1A&1B&7 [0018] [0020] [0046] – [0049] [0095] processing input data using the trained fault detection graph neural network GNN model to generate nodes and links to represent predicted physical connections between electrical assets represented by the nodes; Figs. 1A&1B [0020] [0046] – [0049] generating feeder branch attribute data set and node attribute data set as input for a fault detection neural network i.e. “includes a node feature specifying characteristics of the corresponding electrical asset”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kann to incorporate the teachings of Sun, because they all directed to power line configurations, to make the system wherein the model is a graph neural network (GNN) model and each node includes a node feature specifying characteristics of the corresponding electrical asset. One of ordinary skill in the art would have been motivated to do this modification so as to output a classification of the fault and the fault location, as Sun teaches in [0020].
Regarding claim 20, it is directed to a non-transitory computer storage media storing instructions of carrying out the system with similar limitations as set forth in claim 19. Since Kann and Sun teach the claimed system, they teach the program for implementing the system.
Regarding claim 1, it is directed to a method of carrying out the system with similar limitations as set forth in claim 19. Since Kann and Sun teach the claimed system, they teach the program for implementing the system.
Regarding claim 2, Kann further teaches obtaining load data for the electric power distribution system in the geographic area, the load data comprising: for each of a plurality of load locations of the electrical power distribution system, data indicating one or more characteristics of the load location (Figs. 1, 8&12 [0088] receiving request to generate meter-to-transformer topology report, [0021] [0065] [0068] accessing the location information 804 indicating a power distribution area to be mapped, the location information including loads such as house, a utilities service point identifier including endpoint number and account number in a neighborhood, and locations of the assets and loads, i.e. “the load data comprising: for each of a plurality of load locations of the electrical power distribution system, data indicating one or more characteristics of the load location”); and
the partition data further comprises: for each of the plurality of load locations, a partition identifier that assigns the load location to one of a set of feeder networks (Figs. 1, 5, 7-9 &12 [0066] [0068] [0091] the power distribution lines, the transformers on the utility poles, the meters and the house the meters are associated with, are assigned to the specific transformer with unique transformer ID, together with locations, are displayed on an electric grid connectivity map 900).
Regarding claim 3, Kann further teaches performing a correlation analysis of the measurement data from each of the plurality of electric sensors to generate a correlation result between each pair of the plurality of electric sensors; obtaining association data that indicates connectivity or geographical associations between each of the plurality of electric sensors with one of the electrical assets or with one of the load locations; and generating the partition data based on the correlation results and the association data (Figs. 1, 5, 8&12 [0051] [0052] [0090] each meter is assigned to corresponding transformer based on the time-stamped voltage values correlation and location data of the meter, and Figs. 7-8 [0064] each meter is assigned to a specific transformer with unique transformer ID).
Regarding claim 4, Kann further teaches the correlation result between a pair of electric sensors comprises a waveform correlation between the measurement data from the pair of electric sensors (Fig. 4 [0049] [0054] [0064] a series time stamp voltage values between a pair of the meters or between a meter and sensor of transformer are correlated).
Regarding claim 9, Kann further teaches the predictive connectivity data further comprises data characterizing network connectivity characteristics for a plurality of load locations (Figs. 9&10 [0091] [0092] the output that indicating a meter that lost power or has undergone a change in connections, the meter is associated with the house it is installed with i.e. “data characterizing network connectivity characteristics for a plurality of load locations”).
Regarding claim 10, Sun further teaches the predictive connectivity data further comprises data characterizing one or more properties of one or more connection paths ([0130] attributes if the fault branch, the impedance at fault location and distance between the nodes of the fault branch).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kann to incorporate the teachings of Sun, because they all directed to power line configurations, to make the method wherein the output further comprises data characterizing one or more properties of one or more connection paths. One of ordinary skill in the art would have been motivated to do this modification so as to output a classification of the fault and the fault location, as Sun teaches in [0020].
Regarding claim 11, Sun further teaches the one or more properties comprise: a power rating, a line impedance, or line length of the one or more connection paths ([0130] the impedance at fault location and distance between the nodes of the fault branch).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kann to incorporate the teachings of Sun, because they all directed to power line configurations, to make the method wherein the one or more properties comprise: a power rating, a line impedance, or line length of the one or more connection paths. One of ordinary skill in the art would have been motivated to do this modification so as to output a classification of the fault and the fault location, as Sun teaches in [0020].
Regarding claim 14, Sun further teaches the graph neural network further generates an updated node feature for each node, the updated node feature indicating one or more of:
one or more electrical assets or loads connected to the node; or
phase characteristics of current through the node ([0130] fault phases of the fault branch).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kann to incorporate the teachings of Sun, because they all directed to power line configurations, to make the method wherein the graph neural network further generates an updated node feature for each node, the updated node feature indicating one or more of: one or more electrical assets or loads connected to the node; or phase characteristics of current through the node. One of ordinary skill in the art would have been motivated to do this modification so as to output a classification of the fault and the fault location, as Sun teaches in [0020].
Regarding claim 15, Kann further teaches:
determining one or more pole locations from geospatial data; and for each pole location: determining a subset of the plurality of electrical assets located at the pole location based on the geospatial data; determining one or more feeders located at the pole location based the geospatial data and the partition data; and in response to determining that a single feeder is located at the pole location, updating the partition data to indicate the subset of the plurality of electrical assets being connected to the single feeder (Figs. 1&9 [0021] [0066] – [0068] a plurality of single transformer mounted on corresponding utility pole is identified i.e. “determining that a single feeder is located at the pole location”, and a group of meters connected with a plurality of power lines i.e. “a subset of the plurality of electrical assets located at the pole location” are assigned to each transformer i.e. “, updating the partition data to indicate the subset of the plurality of electrical assets being connected to the single feeder”).
Regarding claim 16, Kann further teaches the plurality of electric sensors comprises one or more powerline sensors, wherein each powerline sensor repetitively measures one or more electric parameters through a power line of the electric power distribution system at a plurality of measurement time points (Fig. 9 [0021] [0025] meters installed at houses measuring a series time-stamp power consumptions and voltages).
Regarding claim 17, Kann further teaches the plurality of electric sensors comprises one or more utility meter sensors installed at one or more respective load locations, wherein each utility meter sensor repetitively measures a power consumption at the respective load location at a plurality of measurement time points (Fig. 9 [0021] [0025] meters installed at houses measuring a series time-stamp power consumptions).
Regarding claim 18, Kann further teaches the sensor data further comprises sensor information for each of the plurality of electric sensors, and the sensor information comprises one or more of:
a location of the electric sensor (Fig. 5 [0052] locations of meters);
an address associated with the electric sensor;
a type of the electric sensor; or
a sensor ID.
Regarding claim 21, Kann further teaches generating, based on the predicted connectivity data, a prediction of one or more of operations or faults of the electric power grid (Figs. 8&12 [0063] – [0066] [0091] [0092] the model input data is processed by mapping module to generate an output that indicating a meter that lost power or a transformer or meter has undergone a change in connections i.e. “a prediction of one or more of operations or faults of the electric power grid”); and
providing the prediction for display on an output device (Figs. 9&10 [0091] [0092] a blinking indicator showing a meter that lost power or a transformer or meter has undergone a change in connections).
Claims 5-6 are rejected under 35 U.S.C. 103 as being unpatentable over Kann in view of Sun as applied to claims 1-4, 9-11 and 14-21 above, further in view of Kuloor US 20190041445 A12.
Regarding claim 5, neither Kann nor Sun explicitly further teach the correlation result between a pair of electric sensors comprises a temporal correlation of electric outages indicated by the measurement data from the pair of electric sensors.
Kuloor explicitly teaches in an analogous art that the correlation result between a pair of electric sensors comprises a temporal correlation of electric outages indicated by the measurement data from the pair of electric sensors (Figs. 6-7 [0045] [0046] outage temporal pattern of the meters and sensors of transformer are correlated).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kann and Sun to incorporate the teachings of Kuloor, because they all directed to power line configurations, to make the method wherein the correlation result between a pair of electric sensors comprises a temporal correlation of electric outages indicated by the measurement data from the pair of electric sensors. One of ordinary skill in the art would have been motivated to do this modification so as to identify the meters connected to the transformer, as Kuloor teaches in [0046].
Regarding claim 6, Kuloor further teaches in response to determining that a correlation between the measurement data from a first electric sensor associated with a first electrical asset or a first load location and the measurement data from a second electric sensor associated with a second electrical asset or a second load location exceeds a threshold, assigning the first electrical asset or load location and the second electrical asset or load location to a same feeder network ([0055] [0056] claim 6, meter correlated to the group of meters associated with specific transformer when the correlation is above a threshold, and assigned to that transformer).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kann and Sun to incorporate the teachings of Kuloor, because they all directed to power line configurations, to make the method wherein in response to determining that a correlation between the measurement data from a first electric sensor associated with a first electrical asset or a first load location and the measurement data from a second electric sensor associated with a second electrical asset or a second load location exceeds a threshold, assigning the first electrical asset or load location and the second electrical asset or load location to a same feeder network. One of ordinary skill in the art would have been motivated to do this modification so as to identify the meters connected to the transformer, as Kuloor teaches in [0046].
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Kann in view of Sun as applied to claims 1-4, 9-11 and 14-21 above, further in view of Clark US 20200064385 A13.
Regarding claim 7, neither Kann nor Sun explicitly further teach generating a model input that comprises at least a portion of the asset data and at least a portion of the sensor data; and processing the model input using a partition machine learning model to generate the partition data.
Clark explicitly teaches in an analogous art that generating a model input that comprises at least a portion of the asset data and at least a portion of the sensor data; and processing the model input using a partition machine learning model to generate the partition data (Fig. 5A [0059] - [0062] GIS data and time series voltage data i.e. “a portion of the asset data and at least a portion of the sensor data” is input to a machine learning model for correlation).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kann and Sun to incorporate the teachings of Clark, because they all directed to power line configurations, to make the method wherein generating a model input that comprises at least a portion of the asset data and at least a portion of the sensor data; and processing the model input using a partition machine learning model to generate the partition data. One of ordinary skill in the art would have been motivated to do this modification so as to identify the meters connected to the transformer, as Clark teaches in [0062].
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Michael Tang whose telephone number is (571)272-7437. The examiner can normally be reached M-F 7:30-4 EST.
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, Thomas Lee can be reached on (571)272-3667. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/M.T./Examiner, Art Unit 2115
/VINCENT H TRAN/Primary Examiner, Art Unit 2115
1 Kann and Sun are the prior arts of record
2 Kuloor is the prior art of record
3 Clark is the prior art of record