SYSTEM AND METHOD FOR PREDICTIVE OID FIELD IDENTIFICATION

• US 20180240022A1
• Filed: 02/23/2017
• Published: 08/23/2018
• Est. Priority Date: 02/23/2017
• Status: Abandoned Application

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Tec Corporation (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Tec Corporation (Toshiba Corporation)
• Inventors: Channa, Jonathan, Ravichandran, Surya
• Application Number:
  US15/440,212
• Publication Number:
  US 20180240022A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 3/12 Digital output to print unit , e.g. line printer, chain printer
• CPC Class Codes: G06F 3/1203 Improving or facilitating administration, e.g. print management
• CPC Class Codes: G06F 3/121 Facilitating exception or error detection and recovery, e.g. fault, media or consumables depleted
• CPC Class Codes: G06F 3/1229 Printer resources management or printer maintenance, e.g. device status, power levels
• CPC Class Codes: G06F 3/1273 Print job history, e.g. logging, accounting, tracking
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

A system and method for predictive object identifier (OID) field identification for multifunction peripherals includes a processor configured to walk the managed information base (MIB) of a multifunction peripheral having unidentified OIDs, and save simple network management protocol (SNMP) data associated with the unidentified OIDs to a database. A machine learning process compares data associated with the unidentified OIDs with training data derived from prior training of the machine learning process to predict one or more candidate OID field types for one or several unidentified OIDs. One of the candidate OID field types can be selected by a user as the predicted OID field type, and the selection can be used to improve the training of the machine learning process. The machine learning process can be trained using data derived from walking the MIB of a plurality of multifunction peripherals having known MIBs and OIDs.

Claims

1. A system comprising:

a database;

a device controller including a processor, a memory, and a network interface, configured to

perform a managed information base (MIB) walk on a document processing device via the network interface and obtain simple network management protocol (SNMP) data having a plurality of unidentified object identifiers (Ms), and

store the SNMP data to the database; and

a machine learning system configured to predict at least one OID type of one or more of the unidentified OIDs.

2. The system of claim 1, wherein the machine learning system is configured to predict at least one OID type of an unidentified OID by comparing data associated with the unidentified OID with training data.

3. The system of claim 2, wherein the machine learning systems is configured to predict the at least one OID type based at least in part on changes over time of the data associated with the unidentified OID.

4. The system of claim 2, wherein the machine learning system is configured to generate the training data from each MIB walk of one or more document processing systems having known MIBs and OIDs.

5. The system of claim 2, further comprising:

a user interface configured to

display the one or more predicted OID types for an unknown OID,

monitor an input associated with the user interface for a user selection of one of the predicted OID types; and

save the predicted OID type of the OID to the database based on the user selection.

6. The system of claim 5, wherein the training data is updated based at least in part on the user selection of the predicted OID type of the OID.

7. The system of claim 1, wherein each OID type is selected from the group consisting of a count of printed pages, an indication of a paper level in a paper tray, a toner level, and an error indication.

8. The system of claim 1, further comprising:

a multifunction peripheral comprising the device controller.

9. The system of claim 1, further comprising:

a second processor configured to

retrieve the SNMP data from the database,

extract data associated with OIDs into a format suitable for use by the machine learning system, and

store the extracted data in the database.

10. A method comprising:

performing a managed information base (MIB) walk on a multifunction peripheral to obtain simple network management protocol (SNMP) data having a plurality of object identifiers (OIDs); and

predicting an OID type of at least one of the plurality of OIDs based at least in part on data associated with each OID.

11. The method of claim 10, wherein the MIB walk is performed by a second multifunction peripheral.

12. The method of claim 10, wherein the predicting is based on changes over time of the data associated with one or more OIDs.

13. The method of claim 12, further comprising comparing the changes over time of the data with training data derived at least in part from a MIB walk of a second multifunction peripheral having a known MIB and known OIDs.

14. The method of claim 13, further comprising:

training a machine learning process using SNMP data from the second multifunction peripheral with a known MIB, and

saving the training data into a database.

15. The method of claim 14, further comprising:

displaying, via a user interface, one or more predicted OID types in the database for an OID in the MIB of the multifunction peripheral;

monitoring an input associated with the user interface for a user selection of one of the predicted OID types; and

saving an OID type of the OID to the database based on the user selection.

16. The method of claim 15, further comprising:

updating the training data based at least in part on the user selection of OID type of the OID.

17. A document processing device, comprising:

a device controller including a processor and memory; and

a network interface,

wherein the processor is configured to

perform a managed information base (MIB) walk on a second document processing device via the network interface to obtain SNMP data having a plurality of unidentified object identifiers (OIDs),

save data associated with the unidentified OIDs to a database, and

receive a predicted OID type of at least one of the plurality of unidentified OIDs based at least in part on data associated with each OID in the database.

18. The document processing device of claim 17, wherein the processor is further configured to receive additional SNMP data that includes predicted OIDs and save the SNMP data to the database.

19. The document processing device of claim 17, wherein a MIB and associated OIDs of the second document processing device are unknown when the MIB walk is performed, and wherein a machine learning process compares the data associated with one or more of the OIDs in the database with training data to predict the OID type of at least one of the OIDs.

20. The document processing device of claim 17, wherein the predicted OID type is selected from the group consisting of a count of printed pages, an indication of a paper level in a paper tray, a toner level, and an error indication.