# US 2023/0410995 A1 · Multi-criteria fair queueing of alerts

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0410995 A1
- Document ID: US20230410995A1
- Status: Published application
- Kind: A1
- Application number: 18/032,204
- Filed: 2021-10-14
- Published: 2023-12-21
- Earliest claimed: 2020-10-22
- Assignees: Koninklijke Philips N.V.
- Applicants: Koninklijke Philips N.V.
- Inventors: Johannes Henricus Maria Korst; Mauro Barbieri; Serverius Petrus Paulus Pronk; Marc André Peters; Qi Gao
- Web page: https://patentgrep.com/patent/US20230410995A1

## CPC

- G05B 23/0283: {Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] (preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06)}
- G16H 40/40: for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06Q 10/20: Administration of product repair or maintenance
- G06N 3/045: Combinations of networks
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A method (100) of generating a ranked list (42) of alerts (30) from files (32) of electronic devices (12) includes: applying predictive models (34) to data of the files to generate maintenance alerts for the electronic devices; assigning discrete values for a set of criteria (36) to each maintenance alert whereby the maintenance alert has a share computed as a product of the assigned discrete values; performing a credit-based queuing process (38) to assign the maintenance alerts to slots of a ranked list, wherein in the credit-based queuing process the maintenance alerts accumulate credits in accord with the shares computed for the respective maintenance alerts; and displaying, on a display device (24) operatively connected with the at least one electronic processor, the maintenance alerts as the ranked list in accordance with the assignments of the maintenance alerts to the slots of the ranked list.

## Claims

### Claim 1

A non-transitory computer readable medium storing instructions executable by at least one electronic processor to perform a method of generating a ranked list of alerts from files of electronic devices, the method comprising:
applying predictive models to data of the files to generate maintenance alerts for the electronic devices;
assigning discrete values for a set of criteria to each maintenance alert whereby the maintenance alert has a share computed as a product of the assigned discrete values;
performing a credit-based queuing process to assign the maintenance alerts to slots of a ranked list, wherein in the credit-based queuing process the maintenance alerts accumulate credits in accord with the shares computed for the respective maintenance alerts; and
displaying, on a display device operatively connected with the at least one electronic processor, the maintenance alerts as the ranked list in accordance with the assignments of the maintenance alerts to the slots of the ranked list.

### Claim 2 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein each criterion of the set of criteria assume discrete values of a set of discrete values in which the sum of the discrete values of the set of discrete values equals one.

### Claim 3 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein the method further comprises:
recomputing the set of discrete values for a single criterion of the set of the criteria while ensuring the sum of the discrete values of the set of discrete values remains equal to one.

### Claim 4 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein the credit-based queuing process is a credit-based fair queuing process in which each iteration of the credit-based fair queuing process includes:
increasing the credit for each maintenance alert by an amount equal to the share computed for the maintenance alert;
assigning the maintenance alert having a highest accumulated credit to a current slot of the ranked list; and
after the assigning, decreasing the credit of the maintenance alert assigned to the current slot by a predetermined amount.

### Claim 5 (depends on 4)

The non-transitory computer readable medium of claim 4, wherein the predetermined amount comprises 1.00.

### Claim 6 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein the set of criteria include a predictive model criterion whose assigned value for a maintenance alert corresponds to the predictive model that generated the maintenance alert and a timeframe assigned to the maintenance alert by the predictive model.

### Claim 7 (depends on 6)

The non-transitory computer readable medium of claim 6, wherein the set of criteria further include one or more of:
a criterion based on a maintenance contract for the electronic device for which the maintenance alert is generated;
a criterion based on a satisfaction level of an owner of the electronic device for which the maintenance alert is generated.

### Claim 8 (depends on 7)

The non-transitory computer readable medium of claim 7, wherein the criterion based on a satisfaction level of an owner of the electronic device for which the maintenance alert is generated includes a potential downtime during servicing of the electronic device, and the credit-based queuing process includes:
analyzing the generated maintenance alert with machine learning algorithms to predict possible downtime of the electronic device.

### Claim 9 (depends on 6)

The non-transitory computer readable medium of claim 6, wherein the electronic devices comprise medical imaging devices of a plurality of different imaging modalities, and the set of criteria further includes:
a criterion based on the imaging modality of the medical imaging device for which the maintenance alert is generated.

### Claim 10 (depends on 6)

The non-transitory computer readable medium of claim 6, wherein the electronic devices comprise a plurality of medical imaging devices, and the set of criteria further includes a volume of examinations using the plurality of medical imaging device relative to the number of medical imaging devices.

### Claim 11 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein the method further includes:
discarding maintenance alerts having a share of zero.

### Claim 12 (depends on 1)

The non-transitory computer readable medium of claim 1, wherein the method further includes:
removing maintenance alerts having a share of indeterminable value.

### Claim 13

A non-transitory computer readable medium storing instructions executable by at least one electronic processor to perform a method of generating a ranked list of alerts from files of electronic devices, the method comprising:
applying predictive models to data of the files to generate maintenance alerts for the electronic devices;
assigning discrete values for a set of criteria to each maintenance alert whereby the maintenance alert has a share computed as a product of the assigned discrete values;
performing a credit-based queuing process to assign the maintenance alerts to slots of a ranked list, wherein in the credit-based queuing process the maintenance alerts accumulate credits in accord with the shares computed for the respective maintenance alerts, wherein the credit-based queuing process is a credit-based fair queuing process in which each iteration of the credit-based fair queuing process includes:
increasing the credit for each maintenance alert by an amount equal to the share computed for the maintenance alert;
assigning the maintenance alert having a highest accumulated credit to a current slot of the ranked list; and
after the assigning, decreasing the credit of the maintenance alert assigned to the current slot by a predetermined amount; and
displaying, on a display device operatively connected with the at least one electronic processor, the maintenance alerts as the ranked list in accordance with the assignments of the maintenance alerts to the slots of the ranked list.

### Claim 14 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein each criterion of the set of criteria assume discrete values of a set of discrete values in which the sum of the discrete values of the set of discrete values equals one.

### Claim 15 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein the method further comprises:
recomputing the set of discrete values for a single criterion of the set of the criteria while ensuring the sum of the discrete values of the set of discrete values remains equal to one.

### Claim 16 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein the predetermined amount comprises 1.00.

### Claim 17 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein the set of criteria include (1) a predictive model criterion whose assigned value for a maintenance alert corresponds to the predictive model that generated the maintenance alert and (2) a timeframe assigned to the maintenance alert by the predictive model.

### Claim 18 (depends on 17)

The non-transitory computer readable medium of claim 17, wherein the set of criteria further include one or more of:
a criterion based on a maintenance contract for the electronic device for which the maintenance alert is generated;
a criterion based on a satisfaction level of an owner of the electronic device for which the maintenance alert is generated.

### Claim 19 (depends on 17)

The non-transitory computer readable medium of claim 17, wherein the electronic devices comprise medical imaging devices of a plurality of different imaging modalities, and the set of criteria further includes:
a criterion based on the imaging modality of the medical imaging device for which the maintenance alert is generated.

### Claim 20

A method of generating a ranked list of alerts from files of electronic devices, the method comprising:
applying predictive models to data of the files to generate maintenance alerts for the electronic devices;
assigning discrete values for a set of criteria to each maintenance alert whereby the maintenance alert has a share computed as a product of the assigned discrete values, wherein the set of criteria include (1) a predictive model criterion whose assigned value for a maintenance alert corresponds to the predictive model that generated the maintenance alert and (2) a timeframe assigned to the maintenance alert by the predictive model;
performing a credit-based queuing process to assign the maintenance alerts to slots of a ranked list, wherein in the credit-based queuing process the maintenance alerts accumulate credits in accord with the shares computed for the respective maintenance alerts, wherein the credit-based queuing process is a credit-based fair queuing process in which each iteration of the credit-based fair queuing process includes:
increasing the credit for each maintenance alert by an amount equal to the share computed for the maintenance alert;
assigning the maintenance alert having a highest accumulated credit to a current slot of the ranked list; and
after the assigning, decreasing the credit of the maintenance alert assigned to the current slot by a predetermined amount; and
displaying, on a display device operatively connected with the at least one electronic processor, the maintenance alerts as the ranked list in accordance with the assignments of the maintenance alerts to the slots of the ranked list.
