Parte del contenido de esta aplicación no está disponible en este momento.
Si esta situación persiste, contáctenos aComentarios y contacto
1. (WO2019068075) MACHINE ANALYSIS
Nota: Texto obtenido mediante procedimiento automático de reconocimiento óptico de caracteres.
Solo tiene valor jurídico la versión en formato PDF

We Claim:

1 . A method of producing vehicles comprising:

in a vehicle production process, manufacturing vehicle components of different types, and assembling the vehicle components to form vehicles;

creating a set of vehicle records, each being a record of one of the vehicles entering active service;

performing vehicle repairs on a subset of the vehicles after they have entered active service;

creating a respective record of each of the vehicle repairs, each of which comprises or indicates a vehicle age or usage value, and records a vehicle component fault identified in the vehicle repair;

receiving at a data processing stage the vehicle records and vehicle repair records, wherein a predictive algorithm executed at the data processing stage processes the received records so as to, for each type of vehicle component:

1 ) identify a respective set of the vehicle repair records relating to that type of vehicle component, and

2) use the respective set of vehicle repair records to predict a respective number of or resource value for vehicle component faults of that type for the set of vehicle records based on: a number of vehicles recorded in the set of vehicle records, and a current age or usage of each of the recorded vehicles;

comparing the predictions for the different vehicle component types to identify a problem with a particular one of the vehicle component types; and

adapting the vehicle production process, so as to remedy the identified problem with the particular vehicle component type for later vehicles produced in the adapted vehicle production process.

2. A method according to claim 1 , wherein the identified problem is remedied by: reengineering the particular type of vehicle component,

reengineering a vehicle model having the particular attribute or the particular type of vehicle component

adapting a manufacturing process in which the particular type of vehicle component is manufactured, or

• adapting an assembly process in which a model of vehicle having the particular attribute or the particular type of vehicle component are assembled,

3. A method according to claim 1 , comprising:

determining, for each type of vehicle component, a profile for the respective set of vehicle repair records based on a number of or resource value for vehicle component faults recorded in the set of vehicle repair records for different historical vehicle age or usage values, the profile being used to make the prediction.

4. A method according to claim 3, wherein the profile is a backup profile, in that the profile matches the set of vehicle records according to secondary matching criteria, wherein the method comprises a step of determining that no preferred profile matching the set of vehicle records according to primary matching criteria is available.

5. A method according to claim 4, wherein the respective set of vehicle records all relate to the same vehicle model and, for each vehicle component type, the prediction is made for a specific type of repair operation corresponding to that vehicle component type, wherein the determining step comprises determining that no profile for that specific type of repair operation and that model is available, and the backup profile is selected according to the following profile hierarchy:

1 . a profile for the specific type of repair operation and a model group which comprises the vehicle model and at least one other vehicle model;

2. a profile for a similar vehicle model and the specific type of repair operation; 3. a profile for the same vehicle model and a repair operation category, which covers the specific type of repair operation and at least one other specific type of repair operation;

4. a profile for a similar vehicle model and said repair operation category,

5. a profile for the same vehicle model across all repair operations;

6. a profile for said model group across all repair operations;

7. a profile for a similar model of vehicle across all repair operations.

6. A method according to claim 4, wherein, for each vehicle component type, the prediction is made for a particular type of repair operation corresponding to that vehicle component type, and the backup profile is a profile for a particular category of repair operation covering multiple types of repair operation, or a profile across all repair operations.

7. A method according to claim 4, wherein the respective set of vehicle records all relate to the same vehicle model, and the backup profile is a profile for a different model of vehicle, or a model group comprising the vehicle model and at least one other vehicle model.

8. A method according to claim 1 , wherein, in determining the predicted number/resource value, a time lag is accounted for using a model of the time lag, the time lag caused by delays in receiving recent repair records.

9. A method according to claim 4, wherein the profile comprises, for each of a set of historical vehicle age or usage values, a corresponding resource or count value calculated from the set of repair records;

wherein the step of determining the profile comprises: determining a total number of or resource value for vehicle component faults recorded in the filtered set of vehicle repair records, each resource or count value being calculated as a proportion of the total; and

wherein the method comprises calculating an earnings value for each of the historical vehicle age or usage values of the profile based on the corresponding resource or count value of the profile and the number of vehicles recorded in the set of vehicle records whose current age or usage matches that historical vehicle age or usage value of the profile.

10. A method according to claim 9, further comprising:

determining a total number of vehicles recorded in the respective set of vehicle records; and

calculating a maturity value for the set of vehicle records from the earnings values, by calculating a total earnings value from the earnings values as a proportion of the total number of vehicles.

11. A method according to claim 10, comprising:

identifying one or more existing vehicle repair records corresponding to the set of vehicle records; and

determining a number of or resource value for repair operations or vehicle component faults recorded in the existing vehicle repair records; and

wherein the predicted number of or resource value for vehicle component faults is determined for each vehicle component type based on the maturity value calculated for the set of vehicle records and the number of or resource value for vehicle component faults recorded in the existing vehicle repair records.

12. A method according to claim 9, wherein, in determining the predicted number/resource value, a time lag is accounted for using a model of the time lag, the time lag caused by delays in receiving recent repair records, and the model is used to adapt the earnings value.

13. A method of predicting vehicle repair operations or vehicle component faults, the method comprising, at a processing stage:

selecting, by a predictive algorithm executed at the data processing stage, a set of vehicle repair records for use in making a prediction, each of the vehicle repair records being a record of a vehicle repair performed after the vehicle entered active service, each of which comprises or indicates a historical vehicle age or usage value, and records a repair operation or vehicle component fault; and

determining a profile for the set of vehicle repair records based on a number of or resource value for repair operations or vehicle component faults recorded in the set of vehicle repair records for different historical vehicle age or usage values, the profile being used to make the prediction, the profile comprising, for each of a set of historical vehicle age or usage values, a corresponding resource or count value calculated from the set of repair records;

wherein the predictive algorithm uses the profile to predict a number of or resource value for repair operations or vehicle component faults for a set of vehicle records, each of the vehicle records being a record of a vehicle entering active service, based on: a number of vehicles recorded in the set of vehicle records, and a current age or usage of each of the recorded vehicles; and

wherein the profile is a backup profile, in that the profile matches the set of vehicle records according to secondary matching criteria, wherein the method comprises a step of determining that no preferred profile matching the set of vehicle records according to primary matching criteria is available.

14. A method according to claim 13, wherein the set of vehicle records all relate to the same vehicle model, and the backup profile is a profile for a different model of vehicle, or a model group comprising the vehicle model and at least one other vehicle model.

15. A method according to claim 13, wherein the prediction is made for a particular type of repair operation, and the backup profile is a profile for a particular category of repair operation covering multiple types of repair operation, or a profile across all repair operations.

16. A method according to claim 13, wherein the set of vehicle records all relate to the same vehicle model and the prediction is made for a specific type of repair operation, wherein the determining step comprises determining that no profile for that specific type of repair operation and that model is available, and the backup profile is selected according to the following profile hierarchy:

1 . a profile for the specific type of repair operation and a model group which comprises the vehicle model and at least one other vehicle model;

2. a profile for a similar vehicle model and the specific type of repair operation;

3. a profile for the same vehicle model and a repair operation category, which covers the specific type of repair operation and at least one other specific type of repair operation;

4. a profile for a similar vehicle model and said repair operation category,

5. a profile for the same vehicle model across all repair operations;

6. a profile for said model group across all repair operations;

7. a profile for a similar model of vehicle across all repair operations.

17. A method according to claim 13, wherein the prediction is made by performing a non-parametric analysis based on the number of vehicles recorded in the set of

vehicle records, the current age or usage of each of the vehicles, and the resource or count values of the profile.

18. A method according to claim 13, wherein the set of vehicle repair records is selected by filtering a larger set of available vehicle repair records based on a particular type of repair operation or a particular type of vehicle component and a particular vehicle attribute or set of vehicle attributes, such that each repair record of the selected set relates to the particular type of repair operation or vehicle component and to a vehicle having the particular (set of) vehicle attribute(s) or a similar (set of) vehicle attribute(s), the predicted number or resource value being a predicted number of or resource value for repair operations/vehicle component faults of the particular type and for vehicles having the particular (set of) vehicle attribute(s).

19. A system for predicting vehicle repair operations or vehicle component faults, the system comprising:

electronic storage configured to hold computer readable instructions for executing a predictive algorithm; and

one or more hardware processors coupled to the electronic storage and configured to execute computer readable instructions, the computer readable instructions being configured, when executed, to implement the method of claim 13.

20. A non-transitory computer readable medium having computer readable instructions configured, when executed on one or more processors, to implement the method of claim 13.