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 . 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.
DETAILED ACTION
The following FINAL Office Action is in response to communication filed on 2/16/2026.
Priority
Receipt is acknowledged of papers submitted under 35 U.S.C. 119(a)-(d), which papers have been placed of record in the file.
The Examiner has noted the Applicant claiming Priority from Provisional Application 63/323,689 filed 3/5/2022.
Status of Claims
Claims 1-20 are currently pending.
Claims 4, 13, 19 are currently amended.
Claims 1-20 are currently under examination and have been rejected as follows.
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Response to Amendment
The previously pending claim objections are withdrawn in view of the amendments.
The previously pending rejections under 35 USC 112 are withdrawn in view of the amendments.
The previously pending rejections under 35 USC 101 will be maintained. The 101 rejection is updated in view of the amendments.
The previously pending rejections under 35 USC 103 will be maintained. The 103 rejection is updated in view of the amendments.
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Response to Arguments
Regarding Applicant’s remarks pertaining to 35 USC 101:
Step 2A Prong 1:
Applicant argues on page 9 of remarks 2/16/2026:
“Under Step 2A, Prong One, Claim 1 does not recite a judicial exception within the enumerated abstract idea groupings.
“The examiner characterizes the claim as Certain Methods of Organizing Human Activity (mitigating risk, contracts, following rules). That mischaracterizes the claimed subject matter. Claim 1 does not recite contracts or economic transactions; it processes device-generated machine logs using trained predictive and ranking ML models and outputs a machine-generated ranked list tied to operation and maintenance of medical devices. The recited operations are not ‘mental processes’ because they require training and executing machine learning models on device logs and case data and computing probabilities/rankings for assignments - steps that unquestionably cannot practically be performed in the human mind….
“Claim 1 does not recite mathematical relationships, formulas/equations, or calculations.”
Examiner respectfully finds the argument unpersuasive. Applicant specification states at para [0003]: “…predictive maintenance activities are used to avoid unplanned downtime. For various parts of a medical imaging system, predictive models have been developed that aim to predict when a part is likely to fail soon, so that the part can be replaced preventively before it fails”, and at ¶ [0005]: Specialized remote service engineers (RSEs) are trained to review the raised alerts”. Consistent with the specification, the independent claims recite, describe, or set forth predicting medical device failure, generating alerts accordingly, and assigning the alerts to service engineers to perform the predictive maintenance fall within multiple abstract subgroupings. The claims fall within mitigating risk as it pertains to fundamental economic practices because they are directed to reducing risk of cost overruns due to unplanned downtime of assets, (see spec. end-¶ [0002]: “Unplanned down time can lead to considerable costs for the hospital, as no examinations can be scheduled for some time. It can also lead to patient dissatisfaction, as examinations may have to be rescheduled to a later time”; and claim 1 limitation “one or more predictive models trained to generate maintenance alerts for medical devices of a fleet of medical devices based on machine log data received from the medical devices). Allocating maintenance among a plurality of service engineers falls within agreements in the form of contracts and business relations as it pertains to commercial or legal interactions, and ranking maintenance tasks to be performed by service engineers falls within following rules or instructions as it pertains to managing personal behavior or interactions between people; each under the larger abstract grouping of Certain Methods of Organizing Human Activity (MPEP 2106.04(a)(2) II). See spec. ¶ [0010]: “rank alerts of a queue of alerts using the historical maintenance alerts data; receive unresolved alerts for medical devices of the fleet from the one or more predictive models; allocate the unresolved alerts amongst a plurality of SEs including the SE; rank the unresolved alerts allocated to the SE using the trained ranking ML model; and provide, on a display device accessible by a service engineer (SE), the ranked list of the unresolved alerts allocated to that SE.” Accordingly, the claims recite an abstract idea.
Step 2A Prong 2:
Applicant argues on page 11 of remarks 2/16/2026:
“Furthermore, the claimed combination improves the technological field of predictive maintenance for medical devices by transforming raw device log data… and case management history into a personalized, engineer-specific ranked alert list that reduces device downtime and accelerates maintenance.
“…The claim is directed to a non-generic, specific processing pipeline…. This is a specific, ordered set of technological steps, not mere ‘apply it’ instructions (MPEP 2106.05(f)).”
Examiner respectfully disagrees. While the claims recite additional elements which perform specific functions with computer technology, insufficient technological detail is apparent in the claims as to the improvement to the computer technology itself. Claim 1 recites: “[..] train an alert ranking machine learning (ML) model to rank alerts of a queue of alerts using the historical maintenance alerts data [..]”. Spec. ¶ [0039] provides additional detail on the queue ranking: “The alert handling history and profile of RSEs together with alert characteristics are used as input to an algorithm to estimate the probability of an alert being reviewed by an RSE. Subsequently, the alerts with their corresponding probability estimates are partitioned by RSE. The probability estimates are then ordered in descending order to provide personalized alerts to each of the RSEs that will later be presented in RMW.” However, insufficient details on the logical functions of the algorithm, such as calculating and partitioning probability estimates, much less improvement to the computer technology, are clear. The claims are directed to prioritizing a queue and merely use a computer to improve the performance of that determination—not the performance of a computer. (See MPEP 2106.05(a)(II)(i); A commonplace business method or mathematical algorithm being applied on a general-purpose computer, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015).
Step 2B:
Applicant argues on page 12 of remarks 2/16/2026:
“…the rejection fails under Step 2B because it does not establish with evidence that the additional recited elements, individually or in combination, are well-understood, routine, and conventional (WURC).
Examiner respectfully disagrees. Applicant specification discusses well-known predictive maintenance procedures in the industry in Background ¶ [0005]: “Specialized remote service engineers (RSEs) are trained to review the raised alerts, for example via a workstation computer that shows a ranked list of recent alerts. To each alert of type a priority P(a) is associated, so that all alerts that are raised by the multiple predictive models are simply ordered in order of priority. The RSEs typically consider the alerts in a top-down fashion, addressing the highest priority alerts first.” In Versata Dev. Group, Inc. v. SAP Am. mentioned above, the court found similar limitations to be well-understood, routine, and conventional in its industry (see p. 52: “arranging a hierarchy of organizational and product groups, storing pricing information, retrieving applicable pricing information, sorting pricing information, eliminating less restrictive pricing information, and determining the price”).
Further, independent claim limitations recite “generate a ranked list of the unresolved alerts allocated to a service engineer (SE) using the trained ranking ML model; and provide, on a display device accessible by the SE, the ranked list of the unresolved alerts allocated to the SE”. This is not dissimilar to invoking computers or other machinery merely as a tool to perform an existing process, and more specifically, requiring the use of software to tailor information and provide it to the user on a generic computer, as tested per MPEP 2106.05(f)(2)(v).
Accordingly, the previously pending rejections under 35 USC 101 will be maintained. The 101 rejection is updated in view of the amendments.
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Regarding Applicant’s remarks pertaining to 35 USC 103:
Applicant argues on page 13 of remarks 2/16/2026:
“Under Broadest Reasonable Interpretation, the cited combination fails to teach or suggest at least the following claim 1 limitations: (i) ‘instructions ... to train an alert ranking machine learning (ML) model ... using the historical maintenance alerts data’ and (ii) ‘generate a ranked list of the unresolved alerts allocated to a service engineer (SE) using the trained ranking ML model’.”
Examiner respectfully disagrees. Sigtermans teaches generating maintenance alerts for a fleet of devices, using machine learning to rank the alerts according to historical data, and displaying the ranked alerts (see ¶ [0045], [0178], [0179], [0188], [0197]). Sigtermans does not specifically teach the fleet of device being medical devices nor the allocation of the alerts to individual service engineers. However, Patil in analogous art of predictive maintenance optimization cures these deficiencies (see ¶ [0007], [0033], [0038]). Patil and Sigtermans are found as analogous art of predictive maintenance optimization. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Sigtermans’ predictive maintenance modeling method to have included Patil’s teachings around allocating specific service engineers to medical devices for maintenance. The benefit of these additional features would have reduced long hours of maintenance activity and improved customer satisfaction (Patil ¶ [0005]).
Applicant argues on page 13 of remarks 2/16/2026:
“Claim 1 recites executable "instructions ... to train an alert ranking machine learning (ML) model ... to rank alerts ... using the historical maintenance alerts data’….”
Continued on page 14: “However, Sigtermans' cited passages describe: (a) constructing predictive models for failure detection ([0045]); (b) validating such models against historic data ([0069]); and (c) computing and applying a hand-crafted ‘priority metric’ to alerts ([0178]-[0179]), followed by display ([0197]). None of these passages teaches or suggests training a separate ‘alert ranking ML model’ on the historic alerts data to learn to rank alerts….
“Patil similarly does not teach an ML ‘ranking model’ trained on historical maintenance alerts data to rank predictive alerts. Patil's disclosures relate to (i) identifying service tasks from logs for medical imaging devices ([0007]) and (ii) presenting a dynamic, personalized checklist to an FSE ([0011]) and taking into account mandatory tasks during optimization ([0028]). These are optimizer/checklist concepts-distinct from training an ML model specifically for ranking predictive alerts generated by predictive models.”
Examiner respectfully disagrees. Sigtermans discloses considerable detail around using a model to rank alerts based on historical data (see ¶ [0178], [0179], [0188]). Additional support for the application of ML models for predicting machine failure and alert generation is found at Sigtermans ¶ [0045]: “At present, significant effort is expended on the creation of predictive models, and more specifically predictive models which predict failures. Methodologies, which may for example include statistical process control approaches, machine learning approaches and data mining approaches, can be employed to create predictive models which can predict machine failure and generate alerts before failure occurs”. Patil expands on using ML models to “prioritize”, broadly/reasonably interpreted as “rank”, the alerts at ¶ [0033]: “The predictive mode is performed using machine-learning (ML) models that can be trained on historic system data and are modelled to identify drifts in parameter values of the key sensing elements of the subsystem of the medical imaging device. One such example is the pressure of Helium gas for a system. If the model alerting on low helium pressure triggers during or near the planned maintenance window, then this item can be prioritized and appear on the FSE' s checklist 130. If the values are within the acceptable limits and the predictive model indicates that this parameter can continue to stay in this acceptable range for the next few months, then this item will be removed from the top of the checklist 130 and can be identified as a low priority item”.
Applicant argues on page 14 of remarks 2/16/2026:
“…Sigtermans' ranking and display are global (unattended alerts ranked by priority), with no allocation to individual engineers and no per-engineer ranked list. Patil's personalized checklist is a service plan/tasks presentation for an assigned FSE (e.g., mandatory service tasks prioritized), not a ranked list of ‘unresolved alerts’ produced by predictive models and then ranked per engineer using a trained ranking ML model.”
Examiner respectfully disagrees. Patil discloses the FSE’s checklist as including prioritized unresolved alerts. See again Patil ¶ [0033]: “…If the model alerting on low helium pressure triggers during or near the planned maintenance window, then this item can be prioritized and appear on the FSE's checklist 130. If the values are within the acceptable limits and the predictive model indicates that this parameter can continue to stay in this acceptable range for the next few months, then this item will be removed from the top of the checklist 130 and can be identified as a low priority item”. Additional support for ranking is found at Patil ¶ [0035]: “The component lister module 136 is also configured to provide a health status based on both the predictive and reactive modes of monitoring from the device status checker module 132. A severity level of the faults is also provided…. If the errors have the potential to lead to a system shut down or lead to unusable system, these issues are indicated as high priority and are placed on the top of the checklist 130. The output of the component lister module 136 is a list of components that need to be checked in the descending order of severity in terms of affecting the system function”.
Applicant argues on page 15 of remarks 2/16/2026:
“Moreover, the cited art also solves different problems using different mechanisms: Sigtermans prioritizes alerts via a defined priority metric and displays unattended alerts… while Patil generates and presents an optimized service plan/checklist to an assigned FSE…. Conflating these teachings to reconstruct Applicant's claimed per-SE ML alert-ranking pipeline constitutes impermissible hindsight.”
Examiner respectfully disagrees. Patil and Sigtermans are found as analogous art of predictive maintenance optimization. Both references address the problem of anticipating and mitigating machine failure, as described in Applicant specification ¶ [0002]-[0003]. See Sigtermans ¶ [0005]: “…This may comprise monitoring parameter values of the lithographic system and making predictions of future performance or events based on these parameter values using a model of the system operation. The disclosure herein describes a methods relating to such predictive maintenance of lithographic systems, or systems in general”, and Patil ¶ [0002]: The maintenance of medical imaging systems (e.g., magnetic resonance (MR), positron emission tomography (PET), computed tomography (CT), interventional- X ray, etc.) is preferably proactive, rather than being reactive to unexpected failures. This can partly be realized by preventively replacing system parts that are statistically likely to fail in the near future”. Thus, the references are both analogous to each other and to the instant application.
Accordingly, the previously pending rejections under 35 USC 103 will be maintained. The 103 rejection is updated in view of the amendments.
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1-20 are directed to a non-transitory computer readable medium or article of manufacture which is a statutory category.
Step 2A Prong One: The claims recite, describe, or set forth a judicial exception of an abstract idea (see MPEP 2106.04(a)). Specifically, the claims recite, describe or set forth mitigating risk, agreements in the form of contracts, and following rules or instructions, including: “generate maintenance alerts for medical devices”, “historical maintenance alerts data”, “rank alerts of a queue of alerts using the historical maintenance alerts data”, “receive unresolved alerts”, “generate a global ranking the unresolved alerts”, “allocate the unresolved alerts amongst a plurality of service engineers”, “generate a ranked list of the unresolved alerts allocated to an SE”, and “provide… the ranked list of the unresolved alerts allocated to that SE”. Predicting medical device failure, generating alerts accordingly, and assigning the alerts to service engineers to perform the predictive maintenance falls within mitigating risk at it pertains to fundamental economic practices; allocating maintenance among a plurality of service engineers falls within agreements in the form of contracts and business relations as it pertains to commercial or legal interactions; and ranking maintenance tasks to be performed by service engineers falls within following rules or instructions as it pertains to managing personal behavior or interactions between people; each under the larger abstract grouping of Certain Methods of Organizing Human Activity (MPEP 2106.04(a)(2) II). Accordingly, the claims recite an abstract idea.
Step 2A Prong Two: Independent claims 1, 13, 19 recite the following additional elements: “non-transitory computer readable medium”, “predictive models”, “electronic processor”, “alert ranking machine learning (ML) model”, and “display device”. The functions of these additional elements include examples such as generating maintenance alerts for medical devices, storing historical maintenance alerts, training ML models to rank alerts in a queue using historical data, receiving unresolved alerts, ranking unresolved alerts, allocating alerts to service engineers, and displaying ranked lists of alerts. Insufficient details on the logical functions of the algorithm, much less improvement to the computer technology, are clear. The claims are directed to prioritizing a queue and merely use a computer to improve the performance of that determination—not the performance of a computer. The additional elements are recited at a high level of generality (i.e. as a generic computer performing functions of identifying patterns in data, communicating and presenting data, etc.) such that they amount to no more than mere instructions to apply the exception using generic computer components.
The additional element “machine learning model” language merely requires execution of an algorithm that can be performed by a generic computer component and provides no detail regarding the operation of that algorithm. As such, the claim requirement amounts to mere instructions to implement the abstract idea on a computer, and, therefore, is not sufficient to make the claim patent eligible. See Alice, 573 U.S. at 226 (determining that the claim limitations “data processing system,” “communications controller,” and “data storage unit” were generic computer components that amounted to mere instructions to implement the abstract idea on a computer); October 2019 Guidance Update at 11–12 (recitation of generic computer limitations for implementing the abstract idea “would not be sufficient to demonstrate integration of a judicial exception into a practical application”). Such a generic recitation of “machine learning model” alone is insufficient to show a practical application of the recited abstract idea.
Therefore, these functions can be viewed as not meaningfully different than a business method or mathematical algorithm being applied on a general-purpose computer as tested per MPEP 2106.05(f)(2)(i). Further, independent claim limitations recite “generate a ranked list of the unresolved alerts allocated to a service engineer (SE) using the trained ranking ML model; and provide, on a display device accessible by the SE, the ranked list of the unresolved alerts allocated to the SE”. This is not dissimilar to invoking computers or other machinery merely as a tool to perform an existing process, and more specifically, requiring the use of software to tailor information and provide it to the user on a generic computer, as tested per MPEP 2106.05(f)(2)(v).The claims are directed to an abstract idea and the judicial exception does not integrate the abstract idea into a practical application.
Step 2B: According to MPEP 2106.05(f)(1), considering whether the claim recites only the idea of a solution or outcome i.e., the claims fail to recite the technological details of how the actual technological solution to the actual technological problem is accomplished. The recitation of claim limitations that attempt to cover an entrepreneurial and thus abstract solution to an entrepreneurial problem with no technological details on how the technological result is accomplished and no description of the mechanism for accomplishing the result do not provide significantly more than the judicial exception.
Dependent claims 2-12, 14-18, 20 do not appear to provide any additional computer-based elements, let alone for such additional computer-based elements to integrate the abstract idea into practical application (Step 2A prong two) or providing significantly more (Step 2B).
Further, dependent claims 2-12, 14-18, 20 merely incorporate the additional elements recited in claims 1, 13, 19 along with further narrowing of the abstract idea of claims 1, 13, 19 and their execution of the abstract idea. Specifically, the dependent claims narrow the “non-transitory computer readable medium”, “predictive models”, “electronic processor”, “alert ranking machine learning (ML) model”, and “display device” to capabilities such as allocating, ranking, including, generating, ordering, computing, and comprising various forms of data such as alerts, SEs, SE performance, global rankings, deadlines, customer contract terms, customer satisfaction information, SE expertise, modalities, system types, alert-SE pairs, probabilities, ranked lists, etc. which, when evaluated per MPEP 2106.05(f)(2) represent mere invocation of computers to perform existing processes. Therefore, the additional elements recited in the claimed invention individually and in combination fail to integrate a judicial exception into a practical application (Step 2A prong two) and for the same reasons they also fail to provide significantly more (Step 2B). Thus, claims 1-20 are reasoned to be patent ineligible.
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
REJECTIONS BASED ON PRIOR ART
Examiner Note: Some rejections will contain bracketed comments preceded by an “EN” that will denote an examiner note. This will be placed to further explain a rejection.
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
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 of this title, 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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
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 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over:
Sigtermans et al. US 20200342333 A1, hereinafter Sigtermans in view of
Patil et al. WO 2022013047, hereinafter Patil. As per,
Regarding claims 1,19: Sigtermans teaches:
A non-transitory computer readable medium storing:
one or more predictive models trained to generate maintenance alerts for [..] devices of a fleet of medical devices based on machine log data received from the [..] devices (Sigtermans ¶ [0045]: Methodologies, which may for example include statistical process control approaches, machine learning approaches and data mining approaches, can be employed to create predictive models which can predict machine failure and generate alerts before failure occurs. Some of the methods used are Bayesian inference, Neural networks, Support Vector Machines etc. ¶ [0047]: …This event log is generated by each subsystem. ¶ [0050]: …this methodology can also be combined with other existing modelling approaches. This enables a causal mapping of the network to be performed, from which extreme event to failure event paths and root causes can be determined);
historical maintenance alerts data including at least historical maintenance alerts generated by the one or more predictive models for the fleet of [..] devices (Sigtermans mid-¶ [0069]: Backend testing comprises applying the model on historic data for which outcomes are known, and comparing the known outcomes to the model's predictions for those outcomes);
instructions readable and executable by at least one electronic processor to:
train an alert ranking machine learning (ML) model to rank alerts of a queue of alerts using the historical maintenance alerts data (Sigtermans ¶ [0045]: At present, significant effort is expended on the creation of predictive models, and more specifically predictive models which predict failures. Methodologies, which may for example include statistical process control approaches, machine learning approaches and data mining approaches, can be employed to create predictive models which can predict machine failure and generate alerts before failure occurs. Mid-¶ [0178]: The method may comprise determining a priority metric for each alert which is a measure of the instantaneous impact of the alerts. A reference model and corresponding reference priority metric is then identified; this may be the model having the highest priority metric (and therefore highest instantaneous impact value for an intervention) at the time the impact is generated. The priority metric may be defined on a logarithmic scale, such that alerts may be ranked, for example, from 1 to 5 or 1 to 10, with each ranking representing an order of magnitude greater intervention benefit impact than a previous ranking, relative to the reference priority metric. The alerts can then be given a priority ranking based on the priority metric values at a given time. ¶ [0179]: FIG. 13 is a flow diagram illustrating a method to prioritize alerts…. [0188] At step 1320, as in the previous embodiment, Backend test results [EN: historical data] are used to determine a benefit metric);
receive unresolved alerts for [..] devices of the fleet from the one or more predictive models; generate a ranked list of the unresolved alerts [..] (claim 1) / rank the unresolved alerts [..] (claim 19) using the trained ranking ML model; and provide, on a display device accessible by the SE, the ranked list of the unresolved alerts [..] (Sigtermans ¶ [0197]: At step 1370, the (unattended) [EN: unresolved] alerts are displayed according to their priority ranking for the appropriate time (which may be the instant time). The priority metrics and the priority ranking may be recalculated at regular intervals, for example on a daily basis, half-daily basis or (multi or singular) hourly basis. Changes in relative priority metrics for each unattended alert will result in a specified change in the alert representation. The displaying of the priority rankings may be performed as part of a front end process, while the other steps of the method may be performed as a back end process which may or may not be part of the front end).
Although Sigtermans teaches generating maintenance alerts for a fleet of devices, using machine learning to rank the alerts according to historical data, and displaying the ranked alerts, Sigtermans does not specifically teach the fleet of device being medical devices nor the allocation of the alerts to individual service engineers.
However, Patil in analogous art of predictive maintenance optimization teaches or suggests:
generate maintenance alerts for medical devices… based on machine log data received from the medical devices (Patil ¶ [0007]: In one aspect, an apparatus for scheduling field service for a fleet of medical imaging devices includes at least one electronic processor programmed to: identify one or more service tasks to be performed during upcoming field service on a medical imaging device to be serviced of the fleet based on content of one or more machine and/or service logs of the medical imaging device to be serviced)
generate a ranked list of the [..] alerts allocated to a service engineer (SE) (claim 1) / allocate the [..] alerts amongst a plurality of SEs including the SE (claim 19) (Patil ¶ [0011]: Another advantage resides in a dynamic and personalized checklist presented to a FSE assigned to service a medical imaging device. ¶ [0033]: The predictive mode is performed using machine-learning (ML) models that can be trained on historic system data and are modelled to identify drifts in parameter values of the key sensing elements of the subsystem of the medical imaging device. One such example is the pressure of Helium gas for a system. If the model alerting on low helium pressure triggers during or near the planned maintenance window, then this item can be prioritized and appear on the FSE' s checklist 130. If the values are within the acceptable limits and the predictive model indicates that this parameter can continue to stay in this acceptable range for the next few months, then this item will be removed from the top of the checklist 130 and can be identified as a low priority item. ¶ [0035]: “The component lister module 136 is also configured to provide a health status based on both the predictive and reactive modes of monitoring from the device status checker module 132. A severity level of the faults is also provided…. If the errors have the potential to lead to a system shut down or lead to unusable system, these issues are indicated as high priority and are placed on the top of the checklist 130. The output of the component lister module 136 is a list of components that need to be checked in the descending order of severity in terms of affecting the system function”. End-¶ [0038]: The FSE work analyzer 144 is configured to implement a model (such as a Hidden Markov Model (HMM)) to analyze this retrieved data and output a recommended FSE (and an associated efficiency score) to perform the tasks in the service plan 130).
Patil and Sigtermans are found as analogous art of predictive maintenance optimization. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Sigtermans’ predictive maintenance modeling method to have included Patil’s teachings around allocating specific service engineers to medical devices for maintenance. The benefit of these additional features would have reduced long hours of maintenance activity and improved customer satisfaction (Patil ¶ [0005]). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Sigtermans in view of Patil (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of predictive maintenance optimization. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Sigtermans in view of Patil above, the to- be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Regarding claim 13: Sigtermans teaches:
A non-transitory computer readable medium storing:
one or more predictive models trained generate maintenance alerts for [..] devices of a fleet of [..] devices based on machine log data received from the [..] devices (Sigtermans ¶ [0045]: Methodologies, which may for example include statistical process control approaches, machine learning approaches and data mining approaches, can be employed to create predictive models which can predict machine failure and generate alerts before failure occurs. Some of the methods used are Bayesian inference, Neural networks, Support Vector Machines etc. ¶ [0047]: …This event log is generated by each subsystem. ¶ [0050]: …this methodology can also be combined with other existing modelling approaches. This enables a causal mapping of the network to be performed, from which extreme event to failure event paths and root causes can be determined);
historical maintenance alerts data including at least historical maintenance alerts generated by the one or more predictive models for the fleet of [..] devices (Sigtermans mid-¶ [0069]: Backend testing comprises applying the model on historic data for which outcomes are known, and comparing the known outcomes to the model's predictions for those outcomes); and
instructions readable and executable by at least one electronic processor to:
train an alert ranking machine learning (ML) model to rank alerts of a queue of alerts using the historical maintenance alerts data (Sigtermans mid-¶ [0178]: The method may comprise determining a priority metric for each alert which is a measure of the instantaneous impact of the alerts. A reference model and corresponding reference priority metric is then identified; this may be the model having the highest priority metric (and therefore highest instantaneous impact value for an intervention) at the time the impact is generated. The priority metric may be defined on a logarithmic scale, such that alerts may be ranked, for example, from 1 to 5 or 1 to 10, with each ranking representing
an order of magnitude greater intervention benefit impact than a previous ranking, relative to the reference priority metric. The alerts can then be given a priority ranking based on the priority metric values at a given time. ¶ [0179]: FIG. 13 is a flow diagram illustrating a method to prioritize alerts…. [0180] 1310-Backend test results [EN: historical data]);
receive unresolved alerts for [..] devices of the fleet from the one or more predictive models;
generate a global ranking of the unresolved alerts using the trained ranking ML model (Sigtermans ¶ [0197]: At step 1370, the (unattended) [EN: unresolved] alerts are displayed according to their priority ranking for the appropriate time (which may be the instant time). The priority metrics and the priority ranking may be recalculated at regular intervals, for example on a daily basis, half-daily basis or (multi or singular) hourly basis. Changes in relative priority metrics for each unattended alert will result in a specified change in the alert representation. The displaying of the priority rankings may be performed as part of a front end process, while the other steps of the method may be performed as a back end process which may or may not be part of the front end);
allocate the unresolved alerts [..] (Sigtermans ¶ [0197]: At step 1370, the (unattended) [EN: unresolved] alerts are displayed according to their priority ranking for the appropriate time (which may be the instant time). The priority metrics and the priority ranking may be recalculated at regular intervals, for example on a daily basis, half-daily basis or (multi or singular) hourly basis);
Although Sigtermans teaches generating maintenance alerts for a fleet of devices, using machine learning to rank the alerts according to historical data, and displaying the ranked alerts, Sigtermans does not specifically teach the fleet of device being medical devices nor the allocation of the alerts to individual service engineers.
However, Patil in analogous art of predictive maintenance optimization teaches or suggests:
allocate the [..] alerts amongst a plurality of service engineers (SEs) (Patil ¶ [0011]: Another advantage resides in a dynamic and personalized checklist presented to a FSE assigned to service a medical imaging device);
order the [..] alerts allocated to a SE in accordance with the global ranking of the unresolved alerts to generate a ranked list of the unresolved alerts allocated to the SE (Patil ¶ [0011]: Another advantage resides in a dynamic and personalized checklist presented to a FSE assigned to service a medical imaging device. ¶ [0028]: The optimizer also preferably takes into account a priority ranking of the service tasks, for example prioritizing service tasks deemed to be mandatory either because they are currently manifesting (i.e., the customer has specifically complained about the problem) or because the device vendor has identified certain tasks as mandatory. Optionally, this may be an iterative process); and
provide, on a display device accessible by an SE, the ranked list of the [..] alerts allocated to that SE (Patil ¶ [0055]: At an operation 210, the service plan 130 is displayed on the display device 105 of the service device 102. In some examples, the FSE using the service device 102 can retrieve the service plan 130 based on inputs entered via the at least one user input device 103 via a graphical user interface (GUI) displayed on the display device 105. The service plan 130 can be updated on the display device 105 based on, for example, updates to the priority levels in the service tasks in the service plan, completion of one or more the services tasks, and so forth. In other examples, the user inputs can include an indication of a ranking of one or more of the services tasks in the service plan 130 to update the service plan based on how the FSE views the priority of the service tasks).
Patil and Sigtermans are found as analogous art of predictive maintenance optimization. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Sigtermans’ predictive maintenance modeling method to have included Patil’s teachings around allocating specific service engineers to medical devices for maintenance. The benefit of these additional features would have reduced long hours of maintenance activity and improved customer satisfaction (Patil ¶ [0005]). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Sigtermans in view of Patil (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of predictive maintenance optimization. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Sigtermans in view of Patil above, the to- be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Regarding claim 2: Sigtermans / Patil teaches all the limitations of claim 1 above.
Sigtermans further teaches:
the generation of the ranked list of the unresolved alerts allocated to the SE includes:
allocating the unresolved alerts [..] (Sigtermans ¶ [0197]: At step 1370, the (unattended) [EN: unresolved] alerts are displayed according to their priority ranking for the appropriate time (which may be the instant time). The priority metrics and the priority ranking may be recalculated at regular intervals, for example on a daily basis, half-daily basis or (multi or singular) hourly basis); and
ranking the unresolved alerts [..] using the trained ranking ML model (Sigtermans ¶ [0045]: Methodologies, which may for example include statistical process control approaches, machine learning approaches and data mining approaches, can be employed to create predictive models which can predict machine failure and generate alerts before failure occurs).
Although Sigtermans teaches generating maintenance alerts for a fleet of devices and using machine learning to rank the alerts according to historical data, Sigtermans does not specifically teach the allocation of the alerts to individual service engineers.
However, Patil in analogous art of predictive maintenance optimization teaches or suggests:
allocating the unresolved alerts amongst a plurality of SEs including the SE (Patil ¶ [0011]: Another advantage resides in a dynamic and personalized checklist presented to a FSE assigned to service a medical imaging device);
ranking the unresolved alerts allocated to the SE (Patil ¶ [0011]: Another advantage resides in a dynamic and personalized checklist presented to a FSE assigned to service a medical imaging device. ¶ [0028]: The optimizer also preferably takes into account a priority ranking of the service tasks, for example prioritizing service tasks deemed to be mandatory either because they are currently manifesting (i.e., the customer has specifically complained about the problem) or because the device vendor has identified certain tasks as mandatory. Optionally, this may be an iterative process).
Rationales to have modified / combined Sigtermans / Patil are above and reincorporated.
Regarding claims 3, 20: Sigtermans / Patil teaches all the limitations of claim 2 above.
Sigtermans further teaches:
the ranking of the unresolved alerts [..] using the trained ranking ML model is based in part [..] (Sigtermans ¶ [0197]: At step 1370, the (unattended) [EN: unresolved] alerts are displayed according to their priority ranking for the appropriate time (which may be the instant time);
[..].
Although Sigtermans teaches generating maintenance alerts for a fleet of devices and using machine learning to rank unresolved alerts according to historical data, Sigtermans does not specifically teach the historical data including service engineer performance data used to rank the alerts.
However, Patil in analogous art of predictive maintenance optimization teaches or suggests:
the historical maintenance alerts data further includes performance data of the plurality of SEs in resolving the historical maintenance alerts (Patil ¶ [0038]: A FSE work analyzer 144 is configured to compute an efficiency of an FSE for a given service work… the FSE work analyzer 144 is configured retrieve, from the parts/FSE database 140, historical data [EN: performance data] related to about activity time, error rate, dependability, accident rate, turnover time, job experience and knowledge), and
the alert ranking ML model is trained to rank the alerts of the queue of alerts using the historical maintenance alerts data including the performance data of the plurality of SEs (Patil continued at end-¶ [0038]: The FSE work analyzer 144 is configured to implement a model (such as a Hidden Markov Model (HMM)) to analyze this retrieved data and output a recommended FSE (and an associated efficiency score) to perform the
tasks in the service plan 130), and
the ranking of the [..] alerts allocated to the SE using the trained ranking ML model is based in part on the performance data of the SE
(Patil continued at end-¶ [0038]: The FSE work analyzer 144 is configured to implement a model (such as a Hidden Markov Model (HMM)) to analyze this retrieved data and output a recommended FSE (and an associated efficiency score) to perform the tasks in the service plan 130).
Rationales to have modified / combined Sigtermans / Patil are above and reincorporated.
Regarding claim 4: Sigtermans / Patil teaches all the limitations of claim 1 above.
Sigtermans further teaches:
the generation of the ranked list of the unresolved alerts [..] includes:
generating a global ranking of the unresolved alerts using the trained ranking ML model (Sigtermans ¶ [0197]: At step 1370, the (unattended) [EN: unresolved] alerts are displayed according to their priority ranking for the appropriate time (which may be the instant time). The priority metrics and the priority ranking may be recalculated at regular intervals, for example on a daily basis, half-daily basis or (multi or singular) hourly basis. Changes in relative priority metrics for each unattended alert will result in a specified change in the alert representation. The displaying of the priority rankings may be performed as part of a front end process, while the other steps of the method may be performed as a back end process which may or may not be part of the front end);
allocating the unresolved alerts [..] (Sigtermans ¶ [0197]: At step 1370, the (unattended) [EN: unresolved] alerts are displayed according to their priority ranking for the appropriate time (which may be the instant time). The priority metrics and the priority ranking may be recalculated at regular intervals, for example on a daily basis, half-daily basis or (multi or singular) hourly basis);
[..].
Although Sigtermans teaches generating maintenance alerts for a fleet of devices and using machine learning to rank unresolved alerts according to historical data, Sigtermans does not specifically teach ranking the alerts for the service engineer in accordance with a global ranking.
However, Patil in analogous art of predictive maintenance optimization teaches or suggests:
allocating the [..] alerts amongst a plurality of SEs including the SE (Patil ¶ [0011]: Another advantage resides in a dynamic and personalized checklist presented to a FSE assigned to service a medical imaging device); and
ordering the [..] alerts allocated to the SE in accordance with the global ranking of the unresolved alerts (Patil ¶ [0011]: Another advantage resides in a dynamic and personalized checklist presented to a FSE assigned to service a medical imaging device. ¶ [0028]: The optimizer also preferably takes into account a priority ranking of the service tasks, for example prioritizing service tasks deemed to be mandatory either because they are currently manifesting (i.e., the customer has specifically complained about the problem) or because the device vendor has identified certain tasks as mandatory. Optionally, this may be an iterative process).
Patil and Sigtermans are found as analogous art of predictive maintenance optimization. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Sigtermans’ predictive maintenance modeling method to have included Patil’s teachings around ranking the alerts for the service engineer in accordance with a global ranking. The benefit of these additional features would have reduced long hours of maintenance activity and improved customer satisfaction (Patil ¶ [0005]). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Sigtermans in view of Patil (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of predictive maintenance optimization. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Sigtermans in view of Patil above, the to- be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Regarding claims 5, 14: Sigtermans / Patil teaches all the limitations of claims 1, 13 above.
Sigtermans further teaches:
the historical maintenance alerts data further includes information on the predictive models that generated the respective historical maintenance alerts, deadlines of the respective historical maintenance alerts (Sigtermans ¶ [0165]: Therefore, based on the alert and corresponding benefit metric, a management action may be performed, for example an alert expiry time can be calculated for some or all of the alerts),
[..].
Although Sigtermans teaches the historical maintenance alerts data including deadlines of the respective historical maintenance alerts, Sigtermans does not specifically teach historical maintenance alerts data including customer contract terms nor customer satisfaction information.
However, Patil in analogous art of predictive maintenance optimization teaches or suggests:
customer contract terms associated with the medical devices of the respective historical maintenance (Patil ¶ [0003]: …a majority of customers opt for an annual maintenance contract for these devices, performed by a field service engineer (FSE) (also referred to herein as an SE). The FSE typically relies on set of checklist or job order sheets that define what kind of activity needs to be carried for each component. The checklist usually includes information such as how to perform tests on the device, a comparisons of an observed outcome with given possible outcomes), and customer satisfaction information associated with the medical devices of the respective historical maintenance (Patil ¶ [0028]: …The optimizer also preferably takes into account a priority ranking of the service tasks, for example prioritizing service tasks deemed to be mandatory either because they are currently manifesting (i.e., the customer has specifically complained about the problem)…. ¶ [0056]: The customer complaints that were raised by the users of the system in the specific time frame, (for example, 30 days) is also mentioned. These indicators highlight necessary actions that need to be take along with the regular checklist).
Patil and Sigtermans are found as analogous art of predictive maintenance optimization. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Sigtermans’ predictive maintenance modeling method to have included Patil’s teachings around historical maintenance alerts data including customer contract terms and customer satisfaction information. The benefit of these additional features would have reduced long hours of maintenance activity and improved customer satisfaction (Patil ¶ [0005]). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Sigtermans in view of Patil (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of predictive maintenance optimization. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Sigtermans in view of Patil above, the to- be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Regarding claims 6, 15: Sigtermans / Patil teaches all the limitations of claims 1, 13 above.
Although Sigtermans teaches generating maintenance alerts for a fleet of devices and using machine learning to rank the alerts according to historical data, Sigtermans does not specifically teach the alerts being ranked based on expertise data including modalities or system types of the devices for which the service engineer has expertise.
However, Patil in analogous art of predictive maintenance optimization teaches or suggests:
the alerts are ranked based on expertise data including modalities or system types of the one or more medical devices for which each SE has expertise (Patil ¶ [0052]: In some embodiments, the FSE identification operation 206 can include ranking the identified available FSEs based at least on an experience level of the FSEs for the medical imaging device to be serviced and/or the identified one or more service tasks. In this embodiment, the optimization operation 208 can include optimizing the service plan 130 additionally based on the identified one or more available FSEs and the service completion times for instances of the one or more service tasks indicated as performed by the identified one or more FSEs in the Parts/FSE database 140).
Patil and Sigtermans are found as analogous art of predictive maintenance optimization. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Sigtermans’ predictive maintenance modeling method to have included Patil’s teachings around the alerts being ranked based on expertise data including modalities or system types of the devices for which the service engineer has expertise. The benefit of these additional features would have reduced long hours of maintenance activity and improved customer satisfaction (Patil ¶ [0005]). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Sigtermans in view of Patil (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of predictive maintenance optimization. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Sigtermans in view of Patil above, the to- be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Regarding claims 7, 16: Sigtermans / Patil teaches all the limitations of claims 6, 15 above.
Although Sigtermans teaches generating maintenance alerts for a fleet of devices and using machine learning to rank the alerts according to historical data, Sigtermans does not specifically teach generating alert-SE pairs based on service engineer expertise data.
However, Patil in analogous art of predictive maintenance optimization teaches or suggests:
generating alert-SE pairs based on the expertise data (Patil ¶ [0038]: …The FSE work analyzer 144 is configured to assigning the ‘best’ or ‘most qualified’ FSE based on the pertaining problem. To determine the most qualified FSE to handle a particular task or service plan, the FSE work analyzer 144 is configured retrieve, from the parts/FSE database 140, historical data related to about activity time, error rate, dependability, accident rate, turnover time, job experience and knowledge, a distance of FSE from the impacted site, among others (these are merely non-limiting examples).
Patil and Sigtermans are found as analogous art of predictive maintenance optimization. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Sigtermans’ predictive maintenance modeling method to have included Patil’s teachings around generating alert-SE pairs based on service engineer expertise data. The benefit of these additional features would have reduced long hours of maintenance activity and improved customer satisfaction (Patil ¶ [0005]). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Sigtermans in view of Patil (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of predictive maintenance optimization. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Sigtermans in view of Patil above, the to- be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Regarding claims 8, 17: Sigtermans / Patil teaches all the limitations of claims 7, 16 above.
Sigtermans further teaches:
computing probabilities for each alert [..] based on the historical alert data and the expertise data (Sigtermans ¶ [0070]: The results of the backend testing [EN: historical data] can then be used to determine a benefit metric, (e.g., a probability density function (PDF)). The benefit metric may quantify the benefit of attending to an extreme data event (or, in a more specific example, an alert generated as a consequence of a detected extreme data event) as a function of the causal delay. This PDF can be used in determining a dynamic alert prioritization, as will be subsequently described. Such a benefit metric may take the form of underlying probability distributions for the predicted failure events);
[..].
Although Sigtermans teaches generating maintenance alerts for a fleet of devices and using machine learning to rank the alerts according to computed probabilities, Sigtermans does not specifically teach computing probabilities for alert-service engineer pairs.
However, Patil in analogous art of predictive maintenance optimization teaches or suggests:
computing probabilities for each alert-SE pair (See Patil ¶ [0039] describing Hidden Markov Model computation of probabilities for recommending FSEs for alerts [EN: SE-alert pairs]); and
allocating the alerts to corresponding SEs based on the computed probabilities (Patil ¶ [0038]: The FSE work analyzer 144 is configured to implement a model (such as a Hidden Markov Model (Hl'v1M)) to analyze this retrieved data and output a recommended FSE (and an associated efficiency score) to perform the tasks in the service plan 130).
Patil and Sigtermans are found as analogous art of predictive maintenance optimization. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Sigtermans’ predictive maintenance modeling method to have included Patil’s teachings around computing probabilities for alert-service engineer pairs. The benefit of these additional features would have reduced long hours of maintenance activity and improved customer satisfaction (Patil ¶ [0005]). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Sigtermans in view of Patil (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of predictive maintenance optimization. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Sigtermans in view of Patil above, the to- be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Regarding claims 9, 18: Sigtermans / Patil teaches all the limitations of claims 8, 17 above.
Although Sigtermans teaches generating maintenance alerts for a fleet of devices and displaying the alerts, Sigtermans does not specifically teach displaying a personalized list of alerts for a service engineer on their device.
However, Patil in analogous art of predictive maintenance optimization teaches or suggests:
the alerts allocated to the corresponding SEs are displayed on a corresponding display device operable by each SE (Patil ¶ [0011]: Another advantage resides in a dynamic and personalized checklist presented to a FSE assigned to service a medical imaging device. ¶ [0055]: At an operation 210, the service plan 130 is displayed on the display device 105 of the service device 102. In some examples, the FSE using the service device 102 can retrieve the service plan 130 based on inputs entered via the at least one user input device 103 via a graphical user interface (GUI) displayed on the display device 105).
Patil and Sigtermans are found as analogous art of predictive maintenance optimization. It would have been obvious to one skilled in the art, before the effective filing date of the invention, to have modified Sigtermans’ predictive maintenance modeling method to have included Patil’s teachings around displaying a personalized list of alerts for a service engineer on their device. The benefit of these additional features would have reduced long hours of maintenance activity and improved customer satisfaction (Patil ¶ [0005]). The predictability of such modifications and/or variations, would have been corroborated by the broad level of skill of one of ordinary skills in the art as articulated by Sigtermans in view of Patil (see MPEP 2143 G).
Further, the claimed invention could have also been viewed as a mere combination of old elements in a similar field of predictive maintenance optimization. In such combination each element would have merely performed the same function as it did separately. Thus, one of ordinary skill in the art would have recognized that, given existing technical ability to combine the elements, as evidenced by Sigtermans in view of Patil above, the to- be combined elements would have fit together like pieces of a puzzle in a logical, complementary, technologically feasible and/or economically desirable manner. Thus, it would have been reasoned that the results of the combination would have been predictable (see MPEP 2143 A).
Regarding claim 10: Sigtermans / Patil teaches all the limitations of claim 7 above.
[..]
computing probabilities for each alert [..] (Sigtermans ¶ [0070]: The results of the backend testing [EN: historical data] can then be used to determine a benefit metric, (e.g., a probability density function (PDF)). The benefit metric may quantify the benefit of attending to an extreme data event (or, in a more specific example, an alert generated as a consequence of a detected extreme data event) as a function of the causal delay. This PDF can be used in determining a dynamic alert prioritization, as will be subsequently described. Such a benefit metric may take the form of underlying probability distributions for the predicted failure events)
Although Sigtermans teaches generating maintenance alerts for a fleet of devices and computing probabilities for the alerts, Sigtermans does not specifically teach allocating the alerts to individual service engineers.
However, Patil in analogous art of predictive maintenance optimization teaches or suggests:
allocating the alerts to corresponding SEs (Patil ¶ [0038]: The FSE work analyzer 144 is configured to implement a model (such as a Hidden Markov Model (Hl'v1M)) to analyze this retrieved data and output a recommended FSE (and an associated efficiency score) to perform the tasks in the service plan 130); and
computing probabilities for each alert allocated to each corresponding SE based on the historical alert data, the performance data, and the expertise data (See Patil ¶ [0039] describing Hidden Markov Model computation of probabilities for recommending FSEs for alerts [EN: SE-alert pairs]. Patil ¶ [0038]: …The FSE work analyzer 144 is configured to assigning the ‘best’ or ‘most qualified’ FSE based on the pertaining problem. To determine the most qualified FSE to handle a particular task or service plan, the FSE work analyzer 144 is configured retrieve, from the parts/FSE database 140, historical data related to about activity time, error rate, dependability, accident rate, turnover time, job experience and knowledge, a distance of FSE from the impacted site, among others (these are merely non-limiting examples)).
Rationales to have modified / combined Sigtermans / Patil are above and reincorporated.
Regarding claim 11: Sigtermans / Patil teaches all the limitations of claim 10 above.
Although Sigtermans teaches generating maintenance alerts for a fleet of devices and displaying the alerts, Sigtermans does not specifically teach displaying a personalized list of alerts for a service engineer on their device.
However, Patil in analogous art of predictive maintenance optimization teaches or suggests:
the alerts allocated to the corresponding SEs are displayed as a ranked list of alerts on a corresponding display device operable by each SE (Patil ¶ [0011]: Another advantage resides in a dynamic and personalized checklist presented to a FSE assigned to service a medical imaging device. ¶ [0055]: At an operation 210, the service plan 130 is displayed on the display device 105 of the service device 102. In some examples, the FSE using the service device 102 can retrieve the service plan 130 based on inputs entered via the at least one user input device 103 via a graphical user interface (GUI) displayed on the display device 105. The service plan 130 can be updated on the display device 105 based on, for example, updates to the priority levels in the service tasks in the service plan, completion of one or more the services tasks, and so forth. In other examples, the user inputs can include an indication of a ranking of one or more of the services tasks in the service plan 130 to update the service plan based on how the FSE views the priority of the service tasks).
Rationales to have modified / combined Sigtermans / Patil are above and reincorporated.
Regarding claim 12: Sigtermans / Patil teaches all the limitations of claim 1 above.
Although Sigtermans teaches generating optimized maintenance alerts for a fleet of devices, Sigtermans does not specifically teach the devices being medical imaging devices.
However, Patil in analogous art of predictive maintenance optimization teaches or suggests:
the one or more medical devices comprise medical imaging devices (Patil ¶ [0007]: In one aspect, an apparatus for scheduling field service for a fleet of medical imaging devices includes at least one electronic processor programmed to: identify one or more service tasks to be performed during upcoming field service on a medical imaging device to be serviced of the fleet based on content of one or more machine and/or service logs of the medical imaging device to be serviced).
Rationales to have modified / combined Sigtermans / Patil are above and reincorporated.
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Conclusion
The following art is made of record and considered pertinent to Applicant’s disclosure:
Namboothiri; Rajeev Krishnan et al. US 20180107965 A1, Methods and systems related to allocating field engineering resources for power plant maintenance.
ZHOU; Nianjun et al. US 20210302953 A1, Context-awareness in preventative maintenance.
Wang; Zhuang et al. US 20150227838 A1, Log-based predictive maintenance.
LOBO; Boniface et al. US 20190149951 A1, Web mapping distance determination using cache.
Williams, Emrys US 20040078721 A1, Service operations on a computer system.
TELATAR; Mahir Erdem et al. US 20140350989 A1, Maintenance procedure system and method.
SIEBEL THOMAS M et al. US 20170006135 A1, Systems and methods for data processing and enterprise ai applications.
KUHRMAN KARL W et al. WO 02054223 A1, Method and system for predicting machine or process faults.
Hossain, Md Anwar, et al. "Improvement of medical imaging equipment management in public hospitals of Bangladesh." 2012 International Conference on Biomedical Engineering (ICoBE). IEEE, 2012.
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to REED M. BOND whose telephone number is (571) 270-0585. The examiner can normally be reached Monday - Friday 8:00 am - 5:00 pm.
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, Patricia Munson can be reached at (571) 270-5396. 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.
/REED M. BOND/Examiner, Art Unit 3624 March 30, 2026
/HAMZEH OBAID/Primary Examiner, Art Unit 3624 April 1, 2026
Prosecution Insights