DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This action is in response to amendments filed March 23rd, 2026. The status of the claims is as follows. Claims 1-10 are canceled herein. Claims 11, 13, 15-20 are amended. Claims 21-30 are newly added herein. Claims 11-30 are currently pending.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 11-20; 21-30 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Zaifman et al. (US20220190940A1, hereinafter “Zaifman”)
Regarding Claim 11,
Zaifman discloses receiving, by a computing device, resource data associated with weather data associated with a weather event affecting a geographic area and equipment data associated with one or more equipment components in the geographic area; providing, to a machine learning model, the resource data; (Zaifman [0009]; “Some implementations described herein provide a system that utilizes a machine learning model to predict network behavior based on weather events. For example, the system may receive historical network behavior data associated with a network that includes network devices and may receive historical weather data associated with a geographical location associated with the network. The system may receive historical action data identifying historical actions taken for the network in response to the historical weather data, and may train a correlation model, with the historical network behavior data, the historical weather data, and the historical action data, to generate a trained correlation model. The system may receive a weather event forecast associated with the geographical location and may process the weather event forecast, with the trained correlation model, to determine an anticipated behavior of the network in response to the weather event forecast. The system may process data identifying the anticipated behavior of the network, with the trained correlation model, to identify one or more actions to take in response to the anticipated behavior and may perform the one or more actions.
In this way, the system utilizes a machine learning model to predict network behavior based on weather events. The system may receive historical network behavior data identifying behaviors of a network during power outages and historical weather data identifying weather that causes the power outages. The system may train the machine learning model based on the historical network behavior data and the historical weather data. The system may utilize the trained machine learning model to predict power outages and network behavior based on weather event forecasts. The system may determine one or more actions to perform with the network when a power outage is predicted. Thus, the system conserves computing resources, networking resources, human resources, and/or the like associated with the network operating inefficiently, identifying network resources to allocate for the increased network utilization, handling consumer complaints associated with the network, and/or the like“ wherein historical resource data associated with weather and equipment data across a geographic area is received; wherein the resource data is provided to the machine learning model to predict power outages (equipment outages) associated with the geographic area
Zaifman [0013]; “As further shown in FIG. 1A, and by reference number 125, prediction system 115 may receive historical weather data associated with a geographical location associated with network 105. The historical weather data may correspond with a same or similar time period associated with the historical network behavior data. The historical weather data may include data associated with the geographical location, wind speeds and directions associated with the geographical location, precipitation amounts associated with the geographical location, lightning strikes associated with the geographical location, a storm (e.g., a hurricane, a tornado, a snowstorm, an ice storm, and/or the like) associated with the geographical location, and/or the like. Prediction system 115 may receive the historical weather data and may store the historical weather data in the data structure associated with prediction system 115. In some implementations, prediction system 115 provides, to a device associated with a weather service for the geographical location, a request for the historical weather data, and receives the historical weather data from the device associated with the weather service based on the request. In some implementations, prediction system 115 periodically receives the historical weather data, continuously receives the historical weather data, and/or the like”)
wherein the machine learning model is trained based on one or more features extracted from one or more resource data sets comprising one or more groups of weather data characteristics and equipment data characteristics (Zaifman [0010]; “In this way, the system utilizes a machine learning model to predict network behavior based on weather events. The system may receive historical network behavior data identifying behaviors of a network during power outages and historical weather data identifying weather that causes the power outages. The system may train the machine learning model based on the historical network behavior data and the historical weather data. The system may utilize the trained machine learning model to predict power outages and network behavior based on weather event forecasts. The system may determine one or more actions to perform with the network when a power outage is predicted. Thus, the system conserves computing resources, networking resources, human resources, and/or the like associated with the network operating inefficiently, identifying network resources to allocate for the increased network utilization, handling consumer complaints associated with the network, and/or the like“ wherein the machine learning trained on historical network behavior data and historical weather data reads on the machine learning model trained on features extracted from resource data sets comprising equipment data characteristics and weather data characteristics respectively
Zaifman [Figure 1A];
PNG
media_image1.png
522
708
media_image1.png
Greyscale
wherein the network comprising a number of network devices (110) thus reads on network outages comprising a number of equipment outages associated with the network outage)
wherein the machine learning model is configured to filter the one or more resource data sets based on data indicative of one or more weather parameters and one or more average equipment outages (Zaifman [0013]; “As further shown in FIG. 1A, and by reference number 125, prediction system 115 may receive historical weather data associated with a geographical location associated with network 105. The historical weather data may correspond with a same or similar time period associated with the historical network behavior data. The historical weather data may include data associated with the geographical location, wind speeds and directions associated with the geographical location, precipitation amounts associated with the geographical location, lightning strikes associated with the geographical location, a storm (e.g., a hurricane, a tornado, a snowstorm, an ice storm, and/or the like) associated with the geographical location, and/or the like” wherein the machine learning model organizing the historical weather data according to geographical location and various weather parameters thus reads on the machine learning model configured to filter the resource data sets based on weather parameters
Zaifman [0010]; “The system may receive historical network behavior data identifying behaviors of a network during power outages and historical weather data identifying weather that causes the power outages” wherein the resource data comprising a plurality of identifying behaviors of the network during power outages thus reads on the model filtering the plurality of historical equipment behavior data parameters)
generating, by the machine learning model, based on the resource data, data indicative of a number of equipment outages associated with the geographic area (Zaifman [0031]; “In this way, prediction system 115 utilizes a machine learning model to predict network behavior based on weather events. Prediction system 115 may receive historical network behavior data identifying behaviors of network 105 during power outages, and historical weather data identifying weather that causes the power outages. Prediction system 115 may train the machine learning model based on the historical network behavior data and the historical weather data and may utilize the trained machine learning model to predict power outages and network behavior based on weather event forecasts” Zaifman [Figure 1A];
PNG
media_image1.png
522
708
media_image1.png
Greyscale
wherein the prediction of network power outages across a geographic area implicitly reads on predicting a quantile number of equipment outages (network devices of the network power outage) associated with that area)
causing, based on the number of equipment outages associated with the geographic area, an allocation of one or more asset resources to the geographic area; (Zaifman [0020]; “As shown in FIG. 1D, and by reference number 150, prediction system 115 may process data identifying the anticipated behavior of network 105, with the trained correlation model, to identify one or more actions to take in response to the anticipated behavior. The one or more actions may include actions to increase bandwidth of network 105, increase capacity of network 105, decrease transport latency associated with network 105, decrease packet latency associated with network 105, decrease packet jitter associated with network 105, increase capacities of network devices 110, increase bandwidths of network devices 110, and/or the like. For example, the one or more actions may include prediction system 115 causing one or more additional network devices 110 to be temporarily allocated for the geographical location; causing an autonomous vehicle with a network device 110 to be dispatched to the geographical location; providing a notification about the anticipated behavior to users of network 105 located in the geographical location; causing an order to be placed for a new network device 110, adjusting one or more parameters of one or more of network devices 110 based on the anticipated behavior; implement an upgrade to network 105; and/or the like. Further details of the one or more actions are described below in connection with FIG. 1E.
As shown in FIG. 1E, and by reference number 155, prediction system 115 may perform the one or more actions. In some implementations, performing the one or more actions includes prediction system 115 causing one or more additional network devices 110 to be temporarily allocated for the geographical location. For example, prediction system 115 may cause additional network devices 110, associated with other networks proximate to the geographical location, to be temporarily allocated for the geographical location. In this way, network 105 and the one or more additional network devices 110 may handle an increase in bandwidth utilization of network 105, a decrease in capacity of network 105, and/or the like. This may conserve computing resources, networking resources, human resources, and/or the like associated with network 105 operating inefficiently, identifying network resources to allocate for the increased network utilization, handling consumer complaints associated with network 105, and/or the like.” wherein the temporary allocation of additional network assets to the geographic area equipment depending on the prediction model’s determination reads on re-allocation, based on the prediction, of additional temporary asset resources to the geographic area independent of the initial deployment)
receiving impact data associated with one or more impacts caused by the weather event to the allocation of the one or more asset resources; (Zaifman [0012]; “As shown in FIG. 1A, and by reference number 120, prediction system 115 may receive historical network behavior data associated with network 105 that includes network devices 110. The historical network behavior data may include historical data identifying bandwidth utilizations by network 105, capacity of network 105, transport latencies associated with network 105, packet latencies associated with network 105, packet jitters associated with network 105, capacities of network devices 110, bandwidth utilizations of network devices 110, user behavior associated with network 105 during a power outage, customer issues identified based on the user behavior, and/or the like.”
Zaifman [0013]; “As further shown in FIG. 1A, and by reference number 125, prediction system 115 may receive historical weather data associated with a geographical location associated with network 105. The historical weather data may correspond with a same or similar time period associated with the historical network behavior data. The historical weather data may include data associated with the geographical location, wind speeds and directions associated with the geographical location, precipitation amounts associated with the geographical location, lightning strikes associated with the geographical location, a storm (e.g., a hurricane, a tornado, a snowstorm, an ice storm, and/or the like) associated with the geographical location, and/or the like.”
Zaifman [0014]; “As further shown in FIG. 1A, and by reference number 130, prediction system 115 may receive historical action data identifying historical actions taken for network 105 in response to the historical weather data. The historical action data may include data identifying adjustments to parameters associated with network 105 and/or network devices 110 based on the historical weather data, capacity requirement upgrades made to network 105 and/or network devices 110 based on the historical weather data, additional network devices 110 added to network based on the historical weather data, and/or the like”
Zaifman [0020]; “prediction system 115 may process data identifying the anticipated behavior of network 105, with the trained correlation model, to identify one or more actions to take in response to the anticipated behavior. The one or more actions may include actions to increase bandwidth of network 105, increase capacity of network 105, decrease transport latency associated with network 105, decrease packet latency associated with network 105, decrease packet jitter associated with network 105, increase capacities of network devices 110, increase bandwidths of network devices 110, and/or the like. For example, the one or more actions may include prediction system 115 causing one or more additional network devices 110 to be temporarily allocated for the geographical location; causing an autonomous vehicle with a network device 110 to be dispatched to the geographical location” wherein the historical network, weather, and action data read on impact data of the one or more impacts caused by the weather event to the allocation of the one or more asset resources (historical network outage data caused by historical weather forecast data impacting historical action data comprising the allocation of asset resources)
providing, to the machine learning model, the impact data; generating, by the machine learning model, based on the impact data, data indicative of an updated number of equipment outages associated with the geographic area; (Zaifman [0031]; “In this way, prediction system 115 utilizes a machine learning model to predict network behavior based on weather events. Prediction system 115 may receive historical network behavior data identifying behaviors of network 105 during power outages, and historical weather data identifying weather that causes the power outages. Prediction system 115 may train the machine learning model based on the historical network behavior data and the historical weather data and may utilize the trained machine learning model to predict power outages and network behavior based on weather event forecasts” wherein the historical network behavior data, weather data, and action data (impact data) is provided to the machine learning in order to generate data indicative of an updated number of equipment outages associated with the geographic area (predicted power outages associated with network device equipment outages)
and causing, based on the updated number of equipment outages associated with the geographic area, a re-allocation of the one or more asset resources to the geographic area (Zaifman [0020]; “As shown in FIG. 1D, and by reference number 150, prediction system 115 may process data identifying the anticipated behavior of network 105, with the trained correlation model, to identify one or more actions to take in response to the anticipated behavior. The one or more actions may include actions to increase bandwidth of network 105, increase capacity of network 105, decrease transport latency associated with network 105, decrease packet latency associated with network 105, decrease packet jitter associated with network 105, increase capacities of network devices 110, increase bandwidths of network devices 110, and/or the like. For example, the one or more actions may include prediction system 115 causing one or more additional network devices 110 to be temporarily allocated for the geographical location; causing an autonomous vehicle with a network device 110 to be dispatched to the geographical location; providing a notification about the anticipated behavior to users of network 105 located in the geographical location; causing an order to be placed for a new network device 110, adjusting one or more parameters of one or more of network devices 110 based on the anticipated behavior; implement an upgrade to network 105; and/or the like. Further details of the one or more actions are described below in connection with FIG. 1E.
As shown in FIG. 1E, and by reference number 155, prediction system 115 may perform the one or more actions. In some implementations, performing the one or more actions includes prediction system 115 causing one or more additional network devices 110 to be temporarily allocated for the geographical location. For example, prediction system 115 may cause additional network devices 110, associated with other networks proximate to the geographical location, to be temporarily allocated for the geographical location. In this way, network 105 and the one or more additional network devices 110 may handle an increase in bandwidth utilization of network 105, a decrease in capacity of network 105, and/or the like. This may conserve computing resources, networking resources, human resources, and/or the like associated with network 105 operating inefficiently, identifying network resources to allocate for the increased network utilization, handling consumer complaints associated with network 105, and/or the like.” wherein the temporary allocation of additional network assets to the geographic area equipment depending on the prediction model’s determination reads on re-allocation, based on the prediction, of additional temporary asset resources to the geographic area independent of the initial deployment; wherein the re-allocation performed based on the predicted number of equipment outages reads on the re-allocation performed based on the updated number of equipment outages)
Regarding Claim 12,
Zaifman teaches the method of Claim 11 (and thus the rejection of Claim 11 is incorporated). Zaifman further discloses wherein the weather data comprises a storm classifier indicative of a windstorm, a thunderstorm, a hurricane, a cyclone, a blizzard, an ice storm, or a snow storm (Zaifman [0013]; “The historical weather data may include data associated with the geographical location, wind speeds and directions associated with the geographical location, precipitation amounts associated with the geographical location, lightning strikes associated with the geographical location, a storm (e.g., a hurricane, a tornado, a snowstorm, an ice storm, and/or the like) associated with the geographical location, and/or the like.”)
Regarding Claim 13,
Zaifman teaches the method of Claim 12 (and thus the rejection of Claim 12 is incorporated). Zaifman further discloses wherein the storm classifier is associated with one or more storm characteristics comprising max winds, max gusts, lightning, max rain, max snow, max temp, min temp, average temp, or an affected geographic area (Zaifman [0013]; “The historical weather data may include data associated with the geographical location, wind speeds and directions associated with the geographical location, precipitation amounts associated with the geographical location, lightning strikes associated with the geographical location, a storm (e.g., a hurricane, a tornado, a snowstorm, an ice storm, and/or the like) associated with the geographical location, and/or the like.”)
Regarding Claim 14,
Zaifman teaches the method of Claim 11 (and thus the rejection of Claim 11 is incorporated). Zaifman further discloses wherein the equipment data comprises data indicative of the one or more equipment components in the geographic area (Zaifman [0018]; “ In some implementations, the trained correlation model may determine that the anticipated behavior of network 105 is associated with a power outage for the geographical location when the anticipated behavior of network 105 satisfies a threshold (e.g., a threshold utilization of network 105, a threshold capacity of network 105, a threshold transport latency associated with network 105, a threshold packet latency associated with network 105, packet jitter associated with network 105, threshold capacities of network devices 110, threshold bandwidth utilizations of network devices 110, and/or the like). For example, the trained correlation model may distinguish rapid rises in utilization of network 105 caused by faulty equipment or other anomalies from rapid rises in utilization of network 105 caused by actual power failures. The trained correlation model may determine that the anticipated behavior of network 105 is not associated with a power outage for the geographical location when the anticipated behavior of network 105 fails to satisfy the threshold. For example, the trained correlation model may determine that specific heavy weather events (e.g., wind speeds greater than fifty miles per hour, multiple lightning strikes per minute, and/or the like), within the geographical location, cause above-normal activity and stress within network 105, such as increased utilization of bandwidth of network 105, increased transport latencies of network 105, and/or the like.” wherein the network behavior data read as equipment data comprises data such as latency, bandwidth, and capacity associated with the equipment components in the geographic area)
Regarding Claim 15,
Zaifman teaches the method of Claim 11 (and thus the rejection of Claim 11 is incorporated). Zaifman further discloses deploying, based on the allocation of the one or more asset resources, the one or more asset resources to the geographic area (Zaifman [0020]; “As shown in FIG. 1D, and by reference number 150, prediction system 115 may process data identifying the anticipated behavior of network 105, with the trained correlation model, to identify one or more actions to take in response to the anticipated behavior. The one or more actions may include actions to increase bandwidth of network 105, increase capacity of network 105, decrease transport latency associated with network 105, decrease packet latency associated with network 105, decrease packet jitter associated with network 105, increase capacities of network devices 110, increase bandwidths of network devices 110, and/or the like. For example, the one or more actions may include prediction system 115 causing one or more additional network devices 110 to be temporarily allocated for the geographical location; causing an autonomous vehicle with a network device 110 to be dispatched to the geographical location; providing a notification about the anticipated behavior to users of network 105 located in the geographical location; causing an order to be placed for a new network device 110, adjusting one or more parameters of one or more of network devices 110 based on the anticipated behavior; implement an upgrade to network 105; and/or the like. Further details of the one or more actions are described below in connection with FIG. 1E.
As shown in FIG. 1E, and by reference number 155, prediction system 115 may perform the one or more actions. In some implementations, performing the one or more actions includes prediction system 115 causing one or more additional network devices 110 to be temporarily allocated for the geographical location. For example, prediction system 115 may cause additional network devices 110, associated with other networks proximate to the geographical location, to be temporarily allocated for the geographical location. In this way, network 105 and the one or more additional network devices 110 may handle an increase in bandwidth utilization of network 105, a decrease in capacity of network 105, and/or the like. This may conserve computing resources, networking resources, human resources, and/or the like associated with network 105 operating inefficiently, identifying network resources to allocate for the increased network utilization, handling consumer complaints associated with network 105, and/or the like.” wherein the deployment of varying asset resources to the geographic area equipment depending on the prediction model’s determination reads on deploying, based on the prediction, asset resources to the geographic area)
Regarding Claim 16,
Zaifman teaches the method of Claim 11 (and thus the rejection of Claim 11 is incorporated). Zaifman further discloses training the machine learning model (Zaifman [0009]; “The system may receive historical action data identifying historical actions taken for the network in response to the historical weather data, and may train a correlation model, with the historical network behavior data, the historical weather data, and the historical action data, to generate a trained correlation model. The system may receive a weather event forecast associated with the geographical location and may process the weather event forecast, with the trained correlation model, to determine an anticipated behavior of the network in response to the weather event forecast. The system may process data identifying the anticipated behavior of the network, with the trained correlation model, to identify one or more actions to take in response to the anticipated behavior and may perform the one or more actions.”)
Regarding Claim 17,
Zaifman teaches the method of Claim 16 (and thus the rejection of Claim 16 is incorporated). Zaifman further discloses determining the one or more resource data sets, wherein the one or more resource data comprise one or more groups of resource characteristics, wherein each group of resource characteristics of the one or more groups of resource characteristics is labeled according to a predefined feature of a plurality of predefined features; (Zaifman [0010]; “In this way, the system utilizes a machine learning model to predict network behavior based on weather events. The system may receive historical network behavior data identifying behaviors of a network during power outages and historical weather data identifying weather that causes the power outages. The system may train the machine learning model based on the historical network behavior data and the historical weather data.” wherein the resource data comprising network behavior and historical weather data reads on weather data and equipment data
Zaifman [0013]; “As further shown in FIG. 1A, and by reference number 125, prediction system 115 may receive historical weather data associated with a geographical location associated with network 105. The historical weather data may correspond with a same or similar time period associated with the historical network behavior data. The historical weather data may include data associated with the geographical location, wind speeds and directions associated with the geographical location, precipitation amounts associated with the geographical location, lightning strikes associated with the geographical location, a storm (e.g., a hurricane, a tornado, a snowstorm, an ice storm, and/or the like) associated with the geographical location, and/or the like. Prediction system 115 may receive the historical weather data and may store the historical weather data in the data structure associated with prediction system 115. In some implementations, prediction system 115 provides, to a device associated with a weather service for the geographical location, a request for the historical weather data, and receives the historical weather data from the device associated with the weather service based on the request. In some implementations, prediction system 115 periodically receives the historical weather data, continuously receives the historical weather data, and/or the like” wherein the resource data comprises groups of labeled weather resource characteristics (precipitation, storm, wind direction) and each group of resource characteristics is defined according to some selection of predefined features (storm group defined as “hurricane”, “snowstorm”, “icestorm”, etc)))
determining, based on the one or more resource data sets, a plurality of features for the machine learning model; training, based on a first portion of the one or more resource data sets, the machine learning model according to the plurality of features; (Zaifman [0034]; “As shown by reference number 205, a machine learning model may be trained using a set of observations. The set of observations (e.g., bandwidth utilizations by network 105, capacity of network 105, transport latencies associated with network 105, packet latencies associated with network 105, packet jitters associated with network 105, and/or the like) may be obtained from historical data, such as data gathered during one or more processes described herein. In some implementations, the machine learning system may receive the set of observations (e.g., as input) from prediction system 115, as described elsewhere herein. As shown by reference number 210, the set of observations includes a feature set. The feature set may include a set of variables, and a variable may be referred to as a feature. A specific observation may include a set of variable values (or feature values) corresponding to the set of variables. In some implementations, the machine learning system may determine variables for a set of observations and/or variable values for a specific observation based on input received from prediction system 115. For example, the machine learning system may identify a feature set (e.g., one or more features and/or feature values) by extracting the feature set from structured data, by performing natural language processing to extract the feature set from unstructured data, by receiving input from an operator, and/or the like. As an example, a feature set for a set of observations may include a first feature of historical network behavior data, a second feature of historical weather data, a third feature of historical action data, and so on. As shown, for a first observation, the first feature may have a value of network behavior 1, the second feature may have a value of weather data 1, the third feature may have a value of action 1, and so on. These features and feature values are provided as examples and may differ in other examples.” wherein the observations comprising unstructured historical weather and network behavior data read on resource data; wherein the extracted NLP feature values from the observations comprising inputted historical weather and equipment data reads on determining a plurality of features for the machine learning model; wherein the machine learning model trained through the features reads on training the machine learning model according to a plurality of features based on the resource data)
testing, based on a second portion of the one or more resource data sets, the machine learning model; and outputting, based on the testing, the machine learning model (Zaifman [Figure 2];
PNG
media_image2.png
528
716
media_image2.png
Greyscale
Wherein supervised learning of the trained model on a set of new observations reads on testing, using a second portion of resource data observations, the machine learning model and afterwards outputting the resulting trained model and its anticipated network behaviors)
Regarding Claim 18,
Zaifman teaches the method of Claim 17 (and thus the rejection of Claim 17 is incorporated). Zaifman further discloses generating, based on the one or more groups of weather data characteristics and equipment data characteristics, the one or more resource data sets (Zaifman [Figure 2];
PNG
media_image3.png
534
739
media_image3.png
Greyscale
Wherein the generated feature sets comprising groups of historical network behavior, weather data, and action data reads on determined pluralities of resource data sets to generate the resource data observations)
Regarding Claim 19,
Zaifman teaches the method of Claim 17 (and thus the rejection of Claim 17 is incorporated). Zaifman further discloses determining baseline feature levels for each group of resource characteristics of the one or more groups of resource characteristics; labeling the baseline feature levels for each group of resource characteristics of the one or more groups of resource characteristics as at least one predefined feature of the plurality of predefined features; and generating, based on the labeled baseline feature levels, the one or more resource data sets (Zaifman [Figure 2];
PNG
media_image2.png
528
716
media_image2.png
Greyscale
Wherein the target variables of the groups of observation values being determined for supervised learning read on determining baseline feature levels for each group of resource characteristics; wherein the labeled baseline feature values are labeled under the predefined feature of network behavior; wherein the resource data observations are generated comprising the anticipated network behavior target variable baselines)
Regarding Claim 20,
Zaifman teaches the method of Claim 17 (and thus the rejection of Claim 17 is incorporated). Zaifman further discloses determining, from the one or more resource data sets, features present in two or more resource data sets of a plurality of resource data sets as a first set of candidate resource characteristics; (Zaifman [Figure 2];
PNG
media_image2.png
528
716
media_image2.png
Greyscale
Zaifman [0039]; “In some implementations, the machine learning model may be trained on a set of observations that do not include a target variable. This may be referred to as an unsupervised learning model. In this case, the machine learning model may learn patterns from the set of observations without labeling or supervision, and may provide output that indicates such patterns, such as by using clustering and/or association to identify related groups of items within the set of observations”
Zaifman [0043]; “In some implementations, the trained machine learning model 225 may classify (e.g., cluster) the new observation in a cluster, as shown by reference number 240. The observations within a cluster may have a threshold degree of similarity. As an example, if the machine learning system classifies the new observation in a first cluster (e.g., a network behavior data cluster), then the machine learning system may provide a first recommendation. Additionally, or alternatively, the machine learning system may perform a first automated action and/or may cause a first automated action to be performed (e.g., by instructing another device to perform the automated action) based on classifying the new observation in the first cluster.” wherein the unsupervised learning of the model to cluster related groups of items within the sets of observations based on a plurality of thresholds used for similarity comparison reads on determining, from the resource data observations, whether a threshold is exceeded between features present within a plurality of observations; wherein the clustering based on a plurality of related groups of items within the sets of observations thus reads on features of a first set)
and determining, from the one or more resource data sets, features of the second set of candidate resource characteristics that satisfy a second threshold score as a third set of candidate resource characteristics, wherein the plurality of features comprises the third set of candidate resource characteristics (Zaifman [0018]; “In some implementations, the trained correlation model may determine that the anticipated behavior of network 105 is associated with a power outage for the geographical location when the anticipated behavior of network 105 satisfies a threshold (e.g., a threshold utilization of network 105, a threshold capacity of network 105, a threshold transport latency associated with network 105, a threshold packet latency associated with network 105, packet jitter associated with network 105, threshold capacities of network devices 110, threshold bandwidth utilizations of network devices 110, and/or the like). For example, the trained correlation model may distinguish rapid rises in utilization of network 105 caused by faulty equipment or other anomalies from rapid rises in utilization of network 105 caused by actual power failures. The trained correlation model may determine that the anticipated behavior of network 105 is not associated with a power outage for the geographical location when the anticipated behavior of network 105 fails to satisfy the threshold. For example, the trained correlation model may determine that specific heavy weather events (e.g., wind speeds greater than fifty miles per hour, multiple lightning strikes per minute, and/or the like), within the geographical location, cause above-normal activity and stress within network 105, such as increased utilization of bandwidth of network 105, increased transport latencies of network 105, and/or the like” wherein the plurality of thresholds (threshold utilization, threshold capacity, threshold transport latency, etc.) read as a plurality of threshold scores for comparison between resource data characteristic items from the aforementioned first set, thus reading on the plurality of sets of candidate resource characteristics
Zaifman [0034]; “ For example, the machine learning system may identify a feature set (e.g., one or more features and/or feature values) by extracting the feature set from structured data, by performing natural language processing to extract the feature set from unstructured data, by receiving input from an operator, and/or the like.” wherein the determination of the plurality of features comprises the structured data encompassing clustered groups of data)
Claims 21-30 recite an apparatus comprising one or more processors and a memory storing processor-executable instructions to perform the methods of Claims 11-20 respectively. Thus, Claims 21-30 are rejected for reasons set forth in the rejection of Claims 11-20.
Response to Arguments
The Examiner acknowledges the Applicant’s amendments to Claims 11, 13, 15-20.
Applicant’s arguments filed March 23rd, 2026, traversing the rejection of claims 11-20 under 35 U.S.C. § 101 have been fully considered and are fully persuasive.
Applicant’s arguments regarding the 35 U.S.C. § 102(a)(1) rejection of claims 11-20 of the previous office action have been considered, have been fully considered, but are not fully persuasive.
Applicant alleges, on Pages 17-18 of Remarks, that Zaifman does not teach or suggest “causing, based on the updated number of equipment outages associated with the geographic area, a re-allocation of the one or more asset resources to the geographic area”.
Examiner respectfully disagrees. Prior art Zaifman discloses [0020]; “As shown in FIG. 1E, and by reference number 155, prediction system 115 may perform the one or more actions. In some implementations, performing the one or more actions includes prediction system 115 causing one or more additional network devices 110 to be temporarily allocated for the geographical location. For example, prediction system 115 may cause additional network devices 110, associated with other networks proximate to the geographical location, to be temporarily allocated for the geographical location. In this way, network 105 and the one or more additional network devices 110 may handle an increase in bandwidth utilization of network 105, a decrease in capacity of network 105, and/or the like.” Examiner maintains that the additional allocation of asset resources to the geographical location reads on a re-allocation of asset resources to the geographic area. Such allocation being performed according to the prediction system’s output which, as aforementioned in the rejection of Claim 11, comprises an updated number of equipment outages associated with the geographic area thus reads on a re-allocation of asset resources caused by the trained machine learning model’s predicted number of equipment outages.
Regarding Applicant’s argument that Zaifman is silent as to whether the trained correlation model may receive “impact data associated with one or more impacts caused by the weather event”, examiner points to the broadest reasonable interpretation of the claim language “impact data” used by applicant in Claim 11. Examiner has determined that the historical network data, network actions, and weather data continuously received by the trained machine learning model is interpretable as the claimed “impact data associated with one or more impacts caused by the weather event”. Consequently, the amended new limitations regarding the “receiving impact data …, providing, to the machine learning model, the impact data … generating, by the machine learning model, based on the impact data, data indicative of an updated number of equipment outages … and causing … a re-allocation of the one or more asset resources” is interpreted by examiner as being no different from the machine learning model receiving historical network data, weather data, and action data to generate a predicted “updated” number of equipment outages and causing a “re-allocation” of the one or more resources. Notably, since all allocation performed by Zaifman is interpretable as a re-allocation (Zaifman performs network actions comprising additional temporary allocations of asset resources depending on network behaviors and outages, such additional allocations reads on the allocations being “re-allocations” on top of some initial deployment), the allocation based on the predicted equipment outage number (based on historical network data, historical weather data, historical action data) is equivalent under broadest reasonable interpretation to the re-allocation based on the updated equipment outage number (derived based on impact data comprising historical network data, historical weather data, historical action data).
Applicant alleges, on pages 18-19 of Remarks, that Zaifman fails to specifically teach that the correlation model may predict “a number of equipment outages” associated with the power outages and network behavior.
Examiner respectfully disagrees. Zaifman’s disclosure of network outages implicitly reads on equipment outages since each network outage is demonstrably associated with a quantifiable number of network device outages (Zaifman [Figure 1A];
PNG
media_image1.png
522
708
media_image1.png
Greyscale
wherein the network comprising a number of network devices (110) thus reads on network outages comprising a number of equipment outages associated with the network outage). As such, Zaifman’s correlation model predicting network outages thus reads on a predicted number of equipment outages.
The rejection of Claim 11 under 35 U.S.C. § 102(a)(1) has been maintained.
The rejection of Claims 12-20 under 35 U.S.C. § 102(a)(1), which depend directly or indirectly from Claim 11, have been maintained.
Conclusion
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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JONATHAN J KIM whose telephone number is (571)272-0523. The examiner can normally be reached 8-6.
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, Matt Ell can be reached on (571) 270-3264. 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.
/JONATHAN J KIM/Examiner, Art Unit 2141
/ANDREW L TANK/Primary Examiner, Art Unit 2141
Prosecution Insights