Dynamic digital information retrieval implemented via artificial intelligence
Methods, apparatus, and processor-readable storage media for dynamic digital information retrieval are provided herein. An example computer-implemented method includes training a machine learning object detection model using server component images and one or more features of the server component images; determining a type of server device captured by at least one camera-derived input, wherein determining the type of server device comprises analyzing the at least one camera-derived input using the machine learning object detection model; identifying one or more server components captured by the at least one camera-derived input by analyzing, within a context of the determined type of server device, the at least one camera-derived input using the machine learning object detection model; and outputting, to at least one display, information pertaining to the identified server components, wherein the information is retrieved from a data source related to the determined type of server device.
1. A computer-implemented method comprising:
training a machine learning object detection model using multiple server component images and one or more features of the multiple server component images;
determining a type of server device captured by at least one camera-derived input, wherein determining the type of server device comprises analyzing the at least one camera-derived input using the machine learning object detection model;
identifying one or more server components captured by the at least one camera-derived input by analyzing, within a context of the determined type of server device, the at least one camera-derived input, wherein identifying the one or more server components comprises:
identifying at least one region of the camera-derived input associated with the one or more server components by processing at least a portion of the at least one camera-derived input using the machine learning object detection model;
identifying one or more portions of the at least one identified region comprising at least a given amount of component coverage by processing the at least one identified region using at least one non-maximum suppression algorithm;
performing component recognition by processing the one or more identified portions using at least one spatial pooling algorithm; and
classifying the one or more server components by processing results of the component recognition using at least one classifier algorithm; and
outputting, to at least one display, information pertaining to the one or more identified server components, wherein the information is retrieved from at least a portion of a data source related to the determined type of server device, wherein the at least a portion of a data source related to the determined type of server device comprises at least a portion of at least one hardware manual, and wherein the at least a portion of the at least one hardware manual comprises one or more portions pertaining to the one or more identified server components of the determined type of server device;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.
2. The computer-implemented method of claim 1 , wherein the machine learning object detection model comprises a region-based convolutional neural network model.
3. The computer-implemented method of claim 1 , wherein the one or more features of the multiple server component images comprises component color.
4. The computer-implemented method of claim 1 , wherein the one or more features of the multiple server component images comprises component scale.
5. The computer-implemented method of claim 1 , wherein the one or more features of the multiple server component images comprises component orientation.
6. The computer-implemented method of claim 1 , wherein the one or more features of the multiple server component images comprises component edge detail.
7. The computer-implemented method of claim 1 , wherein the one or more features of the multiple server component images comprises component illumination.
8. The computer-implemented method of claim 1 , wherein the at least one camera-derived input comprises at least one of a live video input, a stored video input, a new image input, and a stored image input.
9. The computer-implemented method of claim 1 , wherein the one or more server components comprises at least one of a port, a slot, a switch, a power indicator, an information tag, a drive, a panel, a disk, and a connector.
10. The computer-implemented method of claim 1 , wherein identifying the one or more server components comprises performing, via the machine learning object detection model, feature extraction over the at least one camera-derived input.
11. The computer-implemented method of claim 10 , wherein performing the feature extraction comprises extracting, from the at least one camera-derived input, one or more component features comprising at least one of component color, component scale, component orientation, component edge detail, and component illumination.
12. The computer-implemented method of claim 10 , wherein identifying the one or more server components comprises determining, based at least in part on the feature extraction, one or more regions of the determined type of server device captured by the at least one camera-derived input.
13. The computer-implemented method of claim 1 , wherein outputting the information pertaining to the one or more identified server components comprises displaying the information via an interface of a mobile device, wherein the mobile device captured the at least one camera-derived input.
14. The computer-implemented method of claim 1 , wherein the steps are performed by a software application executing on the at least one processing device, wherein the at least one processing device comprises a mobile device.
15. A non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes said at least one processing device:
to train a machine learning object detection model using multiple server component images and one or more features of the multiple server component images;
to determine a type of server device captured by at least one camera-derived input, wherein determining the type of server device comprises analyzing the at least one camera-derived input using the machine learning object detection model;
to identify one or more server components captured by the at least one camera-derived input by analyzing, within a context of the determined type of server device, the at least one camera-derived input, wherein identifying the one or more server components comprises:
identifying at least one region of the camera-derived input associated with the one or more server components by processing at least a portion of the at least one camera-derived input using the machine learning object detection model;
identifying one or more portions of the at least one identified region comprising at least a given amount of component coverage by processing the at least one identified region using at least one non-maximum suppression algorithm;
performing component recognition by processing the one or more identified portions using at least one spatial pooling algorithm; and
classifying the one or more server components by processing results of the component recognition using at least one classifier algorithm; and
to output, to at least one display, information pertaining to the one or more identified server components, wherein the information is retrieved from at least a portion of a data source related to the determined type of server device, wherein the at least a portion of a data source related to the determined type of server device comprises at least a portion of at least one hardware manual, and wherein the at least a portion of the at least one hardware manual comprises one or more portions pertaining to the one or more identified server components of the determined type of server device.
16. The non-transitory processor-readable storage medium of claim 15 , wherein the machine learning object detection model comprises a region-based convolutional neural network model.
17. The non-transitory processor-readable storage medium of claim 15 , wherein identifying the one or more server components comprises performing, via the machine learning object detection model, feature extraction over the at least one camera-derived input.
18. An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
said at least one processing device being configured:
to train a machine learning object detection model using multiple server component images and one or more features of the multiple server component images;
to determine a type of server device captured by at least one camera-derived input, wherein determining the type of server device comprises analyzing the at least one camera-derived input using the machine learning object detection model;
to identify one or more server components captured by the at least one camera-derived input by analyzing, within a context of the determined type of server device, the at least one camera-derived input, wherein identifying the one or more server components comprises:
identifying at least one region of the camera-derived input associated with the one or more server components by processing at least a portion of the at least one camera-derived input using the machine learning object detection model;
identifying one or more portions of the at least one identified region comprising at least a given amount of component coverage by processing the at least one identified region using at least one non-maximum suppression algorithm;
performing component recognition by processing the one or more identified portions using at least one spatial pooling algorithm; and
classifying the one or more server components by processing results of the component recognition using at least one classifier algorithm; and
to output, to at least one display, information pertaining to the one or more identified server components, wherein the information is retrieved from at least a portion of a data source related to the determined type of server device, wherein the at least a portion of a data source related to the determined type of server device comprises at least a portion of at least one hardware manual, and wherein the at least a portion of the at least one hardware manual comprises one or more portions pertaining to the one or more identified server components of the determined type of server device.
19. The apparatus of claim 18 , wherein the machine learning object detection model comprises a region-based convolutional neural network model.
20. The apparatus of claim 18 , wherein identifying the one or more server components comprises performing, via the machine learning object detection model, feature extraction over the at least one camera-derived input.