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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 03/28/2026 has been entered.
Detailed Action
Claims 36-55 are presented for examination in this application (17957069) filed
09/30/2022. The Examiner cites particular sections in the references as applied to the claims below for the convenience of the applicant(s). Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested that, in preparing responses, the applicant(s) fully consider the references in their entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the Examiner.
Response to Arguments
Applicant’s arguments and remarks filed 03/28/2026 have been fully considered. The arguments and remarks regarding the 35 U.S.C 101 rejections were found to be persuasive. The arguments and remarks regarding the 35 U.S.C 103 rejections were found to be persuasive however the amendments have necessitated a change in the references applied. The 35 U.S.C 101 rejections have been withdrawn, and the 35 U.S.C 103 rejections have been maintained via new ground of rejection.
35 U.S.C 103
Applicant’s response:
Applicant asserts “Claims 1-15 are rejected under 35 U.S.C. § 103 as allegedly being unpatentable over SULEM ("Graph Similarity Learning For Change-Point Detection In Dynamic Networks") in view of WANG ("Nonuniform Timeslicing of Dynamic Graphs Based on Visual Complexity"), ZADEH (US Patent Application Publication No. 2020/0287927) in further view of GOGOGLOU ("Navigating The Dynamics of Financial Embeddings Over Time"). For at least the reasons discussed during the interview and without acquiescing in the rejection, the cited sections of the applied references do not teach or suggest one or more features recited in the amended/new independent claims. Accordingly, Applicant respectfully requests that the Examiner withdraw this rejection.”.
Examiner’s response:
Applicant’s arguments with respect to claims 1-15 are considered moot in light of claims 1-15 being cancelled. Claims 36-55 do not recite identical features to claims 1-15, however regarding the limitations they do share, the arguments have been considered but are moot because the new ground of rejection does not rely on references applied in the prior rejection of record for any teaching or matter specifically challenged in the arguments.
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.
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.
Claims 36, 39-41 are rejected under 35 U.S.C 103 as being unpatentable under Huang et al. (“Laplacian Change Point Detection for Dynamic Graphs” hereinafter, Huang) in view of Sriharsha (US20210117868A1 hereinafter, Sriharsha) in further view of Huang (shenyangHuang/LAD/blob/master/datasets/UCI_processed/OCnodeslinks_chars.txt, hereinafter Huang 2).
Regarding claim 36:
Huang teaches a system for accurately predicting one or more change points in time- stamped tabular data, the system comprising (see pg. 349 section ‘Abstract’: “In this paper, we focus on change point detection in dynamic graphs and address two main challenges as sociated with this problem: I) how to compare graph snapshots across time, II) how to capture temporal dependencies.”):
…
accessing, via a network, a machine learning model trained on change point data for common nodes in multiple time-stamp-corresponding graphs, that respectively correspond to different time periods, to predict change point occurrences (see pg. 349 section ‘Abstract’: “In this paper, we focus on change point detection in dynamic graphs and address two main challenges associated with this problem: I) how to compare graph snapshots across time, II) how to capture temporal dependencies.”. Also see pg. 354 table 4 that mentions the use of a generative SBM model.);
…
inputting sets of graph embeddings for a plurality of time-stamped graphs into the machine learning model to predict an occurrence of a change point for a common node common to the three or more time-stamped graphs (see pg. 351 section 4.1: “In this work, we choose the singular values obtained through Singular Value Decomposition (SVD) [19] of the Laplacian matrix as graph embeddings for each snapshot. Figure 3 shows the visualization of the Laplacian spectrum and the corresponding anomaly scores detected by LAD for the Senate co-sponsorship network.”. Also look at pg. 353 section 4.4: “. One can then compute the short term and long term anomaly scores 𝑍𝑠 and 𝑍𝑙 based on cosine similarity. To best aggregate these two perspectives, we take 𝑍𝑡 = 𝑚𝑎𝑥(𝑍𝑠,𝑍𝑙) to decide if the current graph is more anomalous in abrupt or gradual changes. Now having a sequence of anomaly scores𝑍1,. . .,𝑍𝑡,how to best select the change points based on these scores? Different than [2, 24], we choose the points that have the largest increase in anomaly score when compared to the previous time step. Therefore, we have the final anomaly score 𝑍∗𝑡 = 𝑚𝑖𝑛(𝑍𝑡 −𝑍𝑡−1,0). The points with the largest 𝑍∗ are then selected as anomalies”);
and based on the predicted occurrence of the change point, presenting, (see figs. 4 and 5) and
(ii) associated with the predicted occurrence of the change point for the common node (see fig. 4)
Huang 1 does not explicitly teach one or more processors and one or more non-transitory media comprising instructions that, when executed by the one or more processors, cause operations, or presenting on a user interface a time stamp of a first graph of the three or more time-stamped graphs.
Sriharsha, however, analogously teaches one or more processors and one or more non-transitory media comprising instructions that, when executed by the one or more processors, cause operations (see para [1222]: “These computer program instructions may also be stored in a non-transitory computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the acts specified in the flow chart and/or block diagram block or blocks.”)
presenting on a user interface a time stamp of a first graph of the three or more time-stamped graphs (see para [1109]: “The information derived from an ingested time-series data value may be a probability distribution. For example, the drift detector 6008 can determine a probability distribution for an ingested raw machine data element (e.g., a time-series data value) using the online Bayesian changepoint detection algorithm. The probability distribution may be associated with a time (e.g., a timestamp associated with the ingested raw machine data element). Before, during, and/or after the drift detector 6008 determines the probability distribution for the ingested raw machine data element, the drift detector 6008 can analyze previously generated probability distributions (e.g., generated for previously ingested raw machine data elements) and discard any of the previously generated probability distributions associated with a time outside a time window.”. Also see para [1146]: “In FIG. 77, the intake system 210 is depicted as having additional components that communicate with graphical user interface (“GUI”) pipeline creator 7720, including function repository 7712 and processing pipeline repository 7714.”).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings of Huang 1 and Sriharsha before him or her, to modify the system of claim 36 to include attributes of one or more processors and one or more non-transitory media comprising instructions that, when executed by the one or more processors, cause operations and presenting on a user interface a time stamp of a first graph of the three or more time-stamped graphs in order to allow a user to view anomalies within a time series (see Sriharsha at para [0862]: “he anomalies detected by the anomaly detector 3406 may be surfaced via one or more user interfaces that can be displayed by a client device 204. For example, the anomaly detector 3406 or another component in the data intake and query system 108 can generate user interface data based on the anomalies detected by the anomaly detector 3406 such that the user interface data, when rendered by a client device 204, causes the client device 204 to display one or more user interfaces depicting the anomaly information.”).
Huang 1 does not explicitly teach in connection with obtaining three or more time-stamped graphs (i) collectively derived from tabular data rows and time stamps associated with events that correspond to the tabular data rows and (ii) are respectively isolated to a single row of the tabular data rows and to a single time stamp of the time stamps that are different from other ones of the three or more time-stamped graphs.
Huang 2, however, analogously teaches in connection with obtaining three or more time-stamped graphs (i) collectively derived from tabular data rows and time stamps associated with events that correspond to the tabular data rows and (see OCnodeslinks_chars.txt, one of the datasets that Huang 1 uses, which shows a list of independent time-stamped graphs separated by rows)
(ii) are respectively isolated to a single row of the tabular data rows and to a single time stamp of the time stamps that are different from other ones of the three or more time-stamped graphs (see OCnodeslinks_chars.txt, one of the datasets that Huang 1 uses, which shows a list of independent time-stamped graphs separated by rows).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings Huang 1, Sriharsha, and Huang 2 before him or her, to modify the system of claim 36 to include attributes of obtaining three or more time-stamped graphs (i) collectively derived from tabular data rows and time stamps associated with events that correspond to the tabular data rows and (ii) are respectively isolated to a single row of the tabular data rows and to a single time stamp of the time stamps that are different from other ones of the three or more time-stamped graphs in order to extend to multi-view dynamic graphs (see Huang 2 util README.md: “Extending to Multi-view Dynamic Graphs: Laplacian Change Point Detection for Single and Multi-view Dynamic Graphs (preprint), github”).
Regarding claim 39:
Huang 1 in view of Sriharsha in further view of Huang 2 teaches the system of claim 36.
Huang 1 further teaches wherein presenting the time stamp comprises: identifying a graph of the plurality of time-stamped graphs that includes an instance of the common node associated with the predicted occurrence of the change point for the common node; and using a respective time stamp corresponding to the graph as the time stamp associated with the predicted occurrence of the change point for the common node (see pg. 349 section ‘Abstract’: “In this paper, we focus on change point detection in dynamic graphs and address two main challenges as sociated with this problem: I) how to compare graph snapshots across time, II) how to capture temporal dependencies.”. Also see figs. 4 and 5).
Regarding claim 40:
Huang 1 in view of Sriharsha in further view of Huang 2 teaches the system of claim 36.
Huang 1 does not explicitly teach wherein the machine learning model comprises: a Euclidean distance-based model, a naive Bayesian model, or an encoder-decoder model.
Sriharsha, however, analogously teaches wherein the machine learning model comprises: a Euclidean distance-based model, a naive Bayesian model, or an encoder-decoder model (see para [1105]: “To address these technical deficiencies, a modified version of an online Bayesian changepoint detection algorithm can be used to detect shifts in the trend or pattern of ingested time-series data in real-time as the time-series data (e.g., raw machine data) is ingested. ”).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings Huang 1, Sriharsha, and Huang 2 before him or her, to modify the system of claim 40 to include attributes of wherein the machine learning model comprises: a Euclidean distance-based model, a naive Bayesian model, or an encoder-decoder model in order to increase performance and optimization (see Sriharsha at para [1104-1105]: “Application of the Exchangeability Martingales in an online setting would result in a similar situation. Thus, using the K-S test or Exchangeability Martingales in an online setting may be very computationally intensive and result in slow performance if computing resources are limited” … “To address these technical deficiencies, a modified version of an online Bayesian changepoint detection algorithm can be used to detect shifts in the trend or pattern of ingested time-series data in real-time as the time-series data (e.g., raw machine data) is ingested”).
Regarding claim 41:
Huang 1 in view of Sriharsha in further view of Huang 2 teaches the system of claim 36.
Huang 1 further teaches wherein inputting the sets of graph embeddings into the machine learning model comprises inputting a collection of graph embeddings into the machine learning model, the collection of graph embeddings comprising the sets of graph embeddings and other sets of graph embeddings that do not represent the common node common to the three or more time-stamped graphs (see pg. 351 section 4.1: “In this work, we choose the singular values obtained through Singular Value Decomposition (SVD) [19] of the Laplacian matrix as graph embeddings for each snapshot. Figure 3 shows the visualization of the Laplacian spectrum and the corresponding anomaly scores detected by LAD for the Senate co-sponsorship network.”. Also look at pg. 353 section 4.4: “. One can then compute the short term and long term anomaly scores 𝑍𝑠 and 𝑍𝑙 based on cosine similarity. To best aggregate these two perspectives, we take 𝑍𝑡 = 𝑚𝑎𝑥(𝑍𝑠,𝑍𝑙) to decide if the current graph is more anomalous in abrupt or gradual changes. Now having a sequence of anomaly scores𝑍1,. . .,𝑍𝑡,how to best select the change points based on these scores? Different than [2, 24], we choose the points that have the largest increase in anomaly score when compared to the previous time step. Therefore, we have the final anomaly score 𝑍∗𝑡 = 𝑚𝑖𝑛(𝑍𝑡 −𝑍𝑡−1,0). The points with the largest 𝑍∗ are then selected as anomalies”) [(Examiner’s note: Huang enters in all graph embeddings regardless of whether they do or do not have a common node to other graphs.)]
Claims 42, 45-50, and 52-55 are rejected under 35 U.S.C 103 as being unpatentable under Huang et al. (“Laplacian Change Point Detection for Dynamic Graphs” hereinafter, Huang) in view of Sriharsha (US20210117868A1 hereinafter, Sriharsha).
Regarding claim 42:
Huang 1 teaches accessing a machine learning model trained on change point data for common nodes in multiple time-stamp-corresponding graphs, that respectively correspond to different time periods, to predict change point occurrences (see pg. 349 section ‘Abstract’: “In this paper, we focus on change point detection in dynamic graphs and address two main challenges as sociated with this problem: I) how to compare graph snapshots across time, II) how to capture temporal dependencies.”. Also see pg. 354 table 4 that mentions the use of a generative SBM model.);
in connection with obtaining in connection with obtaining a plurality of time-stamped graphs (i) collectively derived from data entries and time stamps associated with events that correspond to the data entries and (ii) respectively corresponding to a different time stamp of the time stamps
inputting sets of graph embeddings for a plurality of time-stamped graphs into the machine learning model to predict an occurrence of a change point for a common node common to the plurality of time-stamped graphs (see pg. 351 section 4.1: “In this work, we choose the singular values obtained through Singular Value Decomposition (SVD) [19] of the Laplacian matrix as graph embeddings for each snapshot. Figure 3 shows the visualization of the Laplacian spectrum and the corresponding anomaly scores detected by LAD for the Senate co-sponsorship network.”. Also look at pg. 353 section 4.4: “. One can then compute the short term and long term anomaly scores 𝑍𝑠 and 𝑍𝑙 based on cosine similarity. To best aggregate these two perspectives, we take 𝑍𝑡 = 𝑚𝑎𝑥(𝑍𝑠,𝑍𝑙) to decide if the current graph is more anomalous in abrupt or gradual changes. Now having a sequence of anomaly scores𝑍1,. . .,𝑍𝑡,how to best select the change points based on these scores? Different than [2, 24], we choose the points that have the largest increase in anomaly score when compared to the previous time step. Therefore, we have the final anomaly score 𝑍∗𝑡 = 𝑚𝑖𝑛(𝑍𝑡 −𝑍𝑡−1,0). The points with the largest 𝑍∗ are then selected as anomalies”);
and based on the predicted occurrence of the change point, presenting, (see figs. 4 and 5) and
Huang 1 does not explicitly teach one or more non-transitory, computer-readable media comprising instructions that, when executed by one or more processors, cause operations.
Sriharsha, however, analogously teaches one or more non-transitory, computer-readable media comprising instructions that, when executed by one or more processors, cause operations (see para [1222]: “These computer program instructions may also be stored in a non-transitory computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the acts specified in the flow chart and/or block diagram block or blocks.”)
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings of Huang 1 and Sriharsha before him or her, to modify the non-transitory, computer-readable media of claim 49 to include attributes of one or more non-transitory, computer-readable media comprising instructions that, when executed by one or more processors, cause operations in order to direct a computer to operate in a particular manner (see Sriharsha para [1222]: “These computer program instructions may also be stored in a non-transitory computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the acts specified in the flow chart and/or block diagram block or blocks.”)
Regarding claim 45:
Huang 1 in view of Sriharsha teaches the method of claim 42.
Huang 1 further teaches wherein presenting the time stamp associated with the predicted occurrence of the change point for the node comprises: identifying a graph of the plurality of time-stamped graphs that includes an instance of the node associated with the predicted occurrence of the change point for the node; and using a respective time stamp corresponding to the graph as the time stamp associated with the predicted occurrence of the change point for the node (see pg. 349 section ‘Abstract’: “In this paper, we focus on change point detection in dynamic graphs and address two main challenges as sociated with this problem: I) how to compare graph snapshots across time, II) how to capture temporal dependencies.”. Also see figs. 4 and 5).
Regarding claim 53:
Claim 53 recites analogous limitations to claim 45 and therefore is rejected on the same grounds.
Regarding claim 46:
Huang 1 in view of Sriharsha teaches the method of claim 42.
Huang 1 further teaches wherein the sets of graph embeddings respectively represent nodes and edges of the plurality of time-stamped graphs (see pg. 351 section 4.1: “In this work, we choose the singular values obtained through Singular Value Decomposition (SVD) [19] of the Laplacian matrix as graph embeddings for each snapshot”. Also see pg. 351 section 3.1: “Let the interval of interest be from timestamp 1 to𝑇. A corresponding set of graph snapshots G is written as {G𝑡}𝑇 𝑡=1 , where each G𝑡 = (V𝑡,E𝑡) represents the static graph at timestamp t. V𝑡 and E𝑡 are the set of nodes and edges respectively. Define an edge 𝑒 = (𝑖, 𝑗,𝑤) ∈ E𝑡 as the connection between node𝑖 and node 𝑗 at timestamp𝑡 in the dynamic graph with weight. … We use an adjacency matrix A𝑡 ∈ R𝑛×𝑛 to represent edges in E𝑡 where 𝑛 = |V𝑡|. Similar to [24, 27, 47, 50], the number of nodes in the graph is assumed to be constant across all timestamps (thus maintaining the shape of the adjacency matrix A𝑡)”).
Regarding claim 54:
Claim 54 recites analogous limitations to claim 46 and therefore is rejected on the same grounds.
Regarding claim 47:
Huang 1 in view of Sriharsha teaches the method of claim 42.
Huang 1 does not explicitly teach wherein the machine learning model comprises: a Euclidean distance-based model, a naive Bayesian model, or an encoder-decoder model.
Sriharsha, however, analogously teaches wherein the machine learning model comprises: a Euclidean distance-based model, a naive Bayesian model, or an encoder-decoder model (see para [1105]: “To address these technical deficiencies, a modified version of an online Bayesian changepoint detection algorithm can be used to detect shifts in the trend or pattern of ingested time-series data in real-time as the time-series data (e.g., raw machine data) is ingested. ”).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings of Huang 1 and Sriharsha before him or her, to modify the method of claim 47 to include attributes of wherein the machine learning model comprises: a Euclidean distance-based model, a naive Bayesian model, or an encoder-decoder model in order to increase performance and optimization (see Sriharsha at para [1104-1105]: “Application of the Exchangeability Martingales in an online setting would result in a similar situation. Thus, using the K-S test or Exchangeability Martingales in an online setting may be very computationally intensive and result in slow performance if computing resources are limited” … “To address these technical deficiencies, a modified version of an online Bayesian changepoint detection algorithm can be used to detect shifts in the trend or pattern of ingested time-series data in real-time as the time-series data (e.g., raw machine data) is ingested”).
Regarding claim 55:
Claim 55 recites analogous limitations to claim 47 and therefore is rejected on the same grounds.
Regarding claim 48:
Huang 1 in view of Sriharsha teaches the method of claim 42.
Huang 1 further teaches wherein inputting the sets of graph embeddings into the machine learning model comprises inputting a collection of graph embeddings into the machine learning model, the collection of graph embeddings comprising the sets of graph embeddings and other sets of graph embeddings that do not include the node common to the plurality of time-stamped graphs (see pg. 351 section 4.1: “In this work, we choose the singular values obtained through Singular Value Decomposition (SVD) [19] of the Laplacian matrix as graph embeddings for each snapshot. Figure 3 shows the visualization of the Laplacian spectrum and the corresponding anomaly scores detected by LAD for the Senate co-sponsorship network.”. Also look at pg. 353 section 4.4: “. One can then compute the short term and long term anomaly scores 𝑍𝑠 and 𝑍𝑙 based on cosine similarity. To best aggregate these two perspectives, we take 𝑍𝑡 = 𝑚𝑎𝑥(𝑍𝑠,𝑍𝑙) to decide if the current graph is more anomalous in abrupt or gradual changes. Now having a sequence of anomaly scores𝑍1,. . .,𝑍𝑡,how to best select the change points based on these scores? Different than [2, 24], we choose the points that have the largest increase in anomaly score when compared to the previous time step. Therefore, we have the final anomaly score 𝑍∗𝑡 = 𝑚𝑖𝑛(𝑍𝑡 −𝑍𝑡−1,0). The points with the largest 𝑍∗ are then selected as anomalies”); [(Examiner’s note: Huang enters in all graph embeddings regardless of whether they do or do not have a common node to other graphs.)].
Regarding claim 49:
Huang 1 teaches accessing a machine learning model trained on change point data for common nodes in multiple time-stamp-corresponding graphs, that respectively correspond to different time periods, to predict change point occurrences (see pg. 349 section ‘Abstract’: “In this paper, we focus on change point detection in dynamic graphs and address two main challenges as sociated with this problem: I) how to compare graph snapshots across time, II) how to capture temporal dependencies.”. Also see pg. 354 table 4 that mentions the use of a generative SBM model.);
in connection with obtaining in connection with obtaining a plurality of time-stamped graphs (i) collectively derived from data entries and time stamps associated with events that correspond to the data entries and (ii) respectively corresponding to a different time stamp of the time stamps
inputting sets of graph embeddings for a plurality of time-stamped graphs into the machine learning model to predict an occurrence of a change point for a common node common to the plurality of time-stamped graphs (see pg. 351 section 4.1: “In this work, we choose the singular values obtained through Singular Value Decomposition (SVD) [19] of the Laplacian matrix as graph embeddings for each snapshot. Figure 3 shows the visualization of the Laplacian spectrum and the corresponding anomaly scores detected by LAD for the Senate co-sponsorship network.”. Also look at pg. 353 section 4.4: “. One can then compute the short term and long term anomaly scores 𝑍𝑠 and 𝑍𝑙 based on cosine similarity. To best aggregate these two perspectives, we take 𝑍𝑡 = 𝑚𝑎𝑥(𝑍𝑠,𝑍𝑙) to decide if the current graph is more anomalous in abrupt or gradual changes. Now having a sequence of anomaly scores𝑍1,. . .,𝑍𝑡,how to best select the change points based on these scores? Different than [2, 24], we choose the points that have the largest increase in anomaly score when compared to the previous time step. Therefore, we have the final anomaly score 𝑍∗𝑡 = 𝑚𝑖𝑛(𝑍𝑡 −𝑍𝑡−1,0). The points with the largest 𝑍∗ are then selected as anomalies”);
and based on the predicted occurrence of the change point, presenting, (see figs. 4 and 5) and
Huang 1 does not explicitly teach one or more non-transitory, computer-readable media comprising instructions that, when executed by one or more processors, cause operations.
Sriharsha, however, analogously teaches one or more non-transitory, computer-readable media comprising instructions that, when executed by one or more processors, cause operations (see para [1222]: “These computer program instructions may also be stored in a non-transitory computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the acts specified in the flow chart and/or block diagram block or blocks.”)
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings of Huang 1 and Sriharsha before him or her, to modify the non-transitory, computer-readable media of claim 49 to include attributes of one or more non-transitory, computer-readable media comprising instructions that, when executed by one or more processors, cause operations in order to direct a computer to operate in a particular manner (see Sriharsha para [1222]: “These computer program instructions may also be stored in a non-transitory computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the acts specified in the flow chart and/or block diagram block or blocks.”)
Regarding claim 50:
Huang 1 in view of Sriharsha teaches the non-transitory, computer-readable media of claim 49.
Huang 1 further teaches wherein each time-stamp graph of the plurality of time-stamped graphs is independent of events before or after a respective time stamp corresponding to the time-stamped graph such that the time- stamped graph represents a snapshot limited to events occurring during a time period represented by the respective time stamp (see pg. 351 section 3.1: “Let the interval of interest be from timestamp 1 to𝑇. A corresponding set of graph snapshots G is written as {G𝑡}𝑇 𝑡=1 , where each G𝑡 = (V𝑡,E𝑡) represents the static graph at timestamp t. V𝑡 and E𝑡 are the set of nodes and edges respectively.” Also see pg. 354 section 5.4.1: “Pure Setting. Here, we only introduce changepoints, where the adjustments in community structure persists until the next change point is reached. We generate a temporal network with 151 time points where each snapshot is produced through SBM parametrized by 𝑠 and P”).
Regarding claim 52:
Huang 1 in view of Sriharsha teaches the non-transitory, computer-readable media of claim 49.
Huang 1 further teaches wherein each time-stamp graph of the plurality of time-stamped graphs is generated from events associated with a respective time stamp corresponding to the time-stamped graph and not generated from other events not associated with the respective time stamp (see pg. 351 section 3.1: “Let the interval of interest be from timestamp 1 to𝑇. A corresponding set of graph snapshots G is written as {G𝑡}𝑇 𝑡=1 , where each G𝑡 = (V𝑡,E𝑡) represents the static graph at timestamp t. V𝑡 and E𝑡 are the set of nodes and edges respectively.”. Also see pg. 354 section 5.4.1: “Pure Setting. Here, we only introduce changepoints, where the adjustments in community structure persists until the next change point is reached. We generate a temporal network with 151 time points where each snapshot is produced through SBM parametrized by 𝑠 and P”).
Allowable Subject Matter
Claims 37, 38, 43, 44, and 51 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Regarding claims 37, 38, 43, 44, and 51, the closest prior art of record to the limitations of the aforementioned claims, Huang et al. (“Laplacian Change Point Detection for Dynamic graphs” hereinafter, Huang 1) teaches specifying time stamps of time-stamped graphs that have common nodes with other time-stamped graphs, however Huang 1 does not teach presenting the time-stamped graphs without specifying the time stamps.
When viewed individually or in combination with other prior art of record, the limitations specified in claims 37, 48, 43, 44, and 51 are distinct.
Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure:
Sulem et al. — “Graph Similarity Learning for Change-Point Detection in Dynamic Networks”
Wang et al. — “Nonuniform Timeslicing of Dynamic graphs Based on Visual Complexity”
Zadeh et al. — US20200287927
Gogoglou et al. — “Navigating the Dynamics of Financial Embeddings Over Time”
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Andrew A Bracero whose telephone number is (571)270-0592. The examiner can normally be reached Monday - Friday 9:00 a.m. - 5:00 p.m. 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, David Yi can be reached at Monday - Friday 9:00 a.m. - 5:00 p.m. ET at (571)270-7519. 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.
/ANDREW BRACERO/Examiner, Art Unit 2126
/DAVID YI/Supervisory Patent Examiner, Art Unit 2126
Prosecution Insights