# US 2014/0156659 A1 · Fusing contextual inferences semantically > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2014/0156659 A1 - Document ID: US20140156659A1 - Status: Published application - Kind: A1 - Application number: 13/784,229 - Filed: 2013-03-04 - Published: 2014-06-05 - Earliest claimed: 2012-12-03 - Assignees: QUALCOMM Incorporated - Applicants: Qualcomm Incorporated - Inventors: Leonard Henry Grokop; Shankar Sadasivam; Edward Harrison Teague - Web page: https://patentgrep.com/patent/US20140156659A1 ## CPC - G06F 16/285: {Clustering or classification} - H04M 1/72448: with means for adapting the functionality of the device according to specific conditions - H04M 1/72454: according to context-related or environment-related conditions - H04M 2250/12: including a sensor for measuring a physical value, e.g. temperature or motion - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08) ## Abstract System and methods for performing context inference in a computing device are disclosed. In one embodiment, a method of performing context inference includes: determining, at a computing device, a first context class using context-related data from at least one data source associated with a mobile device; and determining, at the mobile device, a fusion class based on the first context class, the fusion class being associated with at least one characteristic that is common to the first context class and a second context class that is different from the first context class. ## Claims ### Claim 1 A method for performing context inference in a computing device, the method comprising: determining, at a computing device, a first context class using context-related data from at least one data source associated with a mobile device; and determining, at the computing device, a fusion class based on the first context class, the fusion class being associated with at least one characteristic that is common to the first context class and a second context class that is different from the first context class. ### Claim 2 (depends on 1) The method of claim 1 wherein the fusion class has an associated label that semantically encapsulates a label of the first context class and a label of the second context class. ### Claim 3 (depends on 1) The method of claim 1 further comprising obtaining information associated with an initial classification used to determine the first context class. ### Claim 4 (depends on 3) The method of claim 3 wherein obtaining the information associated with the initial classification comprises obtaining a confidence value associated with the initial classification. ### Claim 5 (depends on 4) The method of claim 4 wherein determining the fusion class is performed in response to the confidence value having an undesirable value. ### Claim 6 (depends on 3) The method of claim 3 wherein obtaining the information associated with the initial classification comprises identifying an operational property of the initial classification. ### Claim 7 (depends on 6) The method of claim 6 wherein determining the fusion class comprises is based on the operational property of the initial classification. ### Claim 8 (depends on 1) The method of claim 1 wherein the context-related data are first context-related data associated with a first time, the method further comprising determining the second context class using second context-related data associated with a second time that is after the first time, and wherein determining the fusion class is based on the first context class and the second context class. ### Claim 9 (depends on 1) The method of claim 1 wherein determining the first context class comprises selecting the first context class from a plurality of predetermined available context classes. ### Claim 10 (depends on 1) The method of claim 1 wherein determining the fusion class comprises selecting the fusion class from a plurality of predetermined available fusion classes. ### Claim 11 An apparatus comprising: first determining means for determining a first context class using context-related data from at least one data source associated with a mobile device; and second determining means, communicatively coupled to the first determining means, for determining a fusion class based on the first context class, the fusion class being associated with at least one characteristic that is common to the first context class and a second context class that is different from the first context class. ### Claim 12 (depends on 11) The apparatus of claim 11 wherein the fusion class has an associated label that semantically encapsulates a label of the first context class and a label of the second context class. ### Claim 13 (depends on 11) The apparatus of claim 11 wherein the first determining means comprise obtaining means for obtaining information associated with an initial classification used to determine the first context class. ### Claim 14 (depends on 13) The apparatus of claim 13 wherein the obtaining means are configured to obtain a confidence value associated with the initial classification. ### Claim 15 (depends on 14) The apparatus of claim 14 wherein the second determining means are configured to determine the fusion class in response to the confidence value having an undesirable value. ### Claim 16 (depends on 13) The apparatus of claim 13 wherein the obtaining means are configured to identify an operational property of the initial classification. ### Claim 17 (depends on 16) The apparatus of claim 16 wherein the second determining means are configured to determine the fusion class based on the operational property of the initial classification. ### Claim 18 (depends on 11) The apparatus of claim 11 wherein the context-related data are first context-related data associated with a first time, the second determining means being further for determining the second context class using second context-related data associated with a second time that is after the first time, and wherein the second determining means are configured to determine the fusion class based on the first context class and the second context class. ### Claim 19 (depends on 11) The apparatus of claim 11 wherein the first determining means are configured to determine the first context class by selecting the first context class from a plurality of predetermined available context classes. ### Claim 20 (depends on 11) The apparatus of claim 11 wherein the second determining means are configured to determine the fusion class by selecting the fusion class from a plurality of predetermined available fusion classes. ### Claim 21 A mobile device comprising: at least one data source; a target state classifier communicatively coupled to the at least one data source and configured to determine a first context class using context-related data from the at least one data source; and a fusion classifier, communicatively coupled to the target state classifier, configured to determine a fusion class based on the first context class, the fusion class being associated with at least one characteristic that is common to the first context class and a second context class that is different from the first context class. ### Claim 22 (depends on 21) The mobile device of claim 21 wherein the fusion class has an associated label that semantically encapsulates a label of the first context class and a label of the second context class. ### Claim 23 (depends on 21) The mobile device of claim 21 wherein the target state classifier is configured to obtain information associated with an initial classification used to determine the first context class. ### Claim 24 (depends on 23) The mobile device of claim 23 wherein the target state classifier is configured to obtain a confidence value associated with the initial classification. ### Claim 25 (depends on 24) The mobile device of claim 24 wherein the fusion classifier is configured to determine the fusion class in response to the confidence value having an undesirable value. ### Claim 26 (depends on 23) The mobile device of claim 23 wherein the target state classifier is configured to identify an operational property of the initial classification. ### Claim 27 (depends on 26) The mobile device of claim 26 wherein the fusion classifier is configured to determine the fusion class based on the operational property of the initial classification. ### Claim 28 (depends on 21) The mobile device of claim 21 wherein the context-related data are first context-related data associated with a first time, the fusion classifier is configured to determine the second context class using second context-related data associated with a second time that is after the first time, and the fusion classifier is configured to determine the fusion class based on the first context class and the second context class. ### Claim 29 (depends on 21) The mobile device of claim 21 wherein the target state classifier is configured to determine the first context class by selecting the first context class from a plurality of predetermined available context classes. ### Claim 30 (depends on 21) The mobile device of claim 21 wherein the fusion classifier is configured to determine the fusion class by selecting the fusion class from a plurality of predetermined available fusion classes. ### Claim 31 A processor-readable storage medium comprising processor-readable instructions configured to cause a processor to: determine a first context class using context-related data from at least one data source associated with a mobile device; and determine a fusion class based on the first context class, the fusion class being associated with at least one characteristic that is common to the first context class and a second context class that is different from the first context class. ### Claim 32 (depends on 31) The storage medium of claim 31 wherein the fusion class has an associated label that semantically encapsulates a label of the first context class and a label of the second context class. ### Claim 33 (depends on 31) The storage medium of claim 31 further comprising instructions configured to cause the processor to obtain information associated with an initial classification used to determine the first context class. ### Claim 34 (depends on 33) The storage medium of claim 33 wherein the instructions configured to cause the processor to obtain the information associated with the initial classification comprise instructions configured to cause the processor to obtain a confidence value associated with the initial classification. ### Claim 35 (depends on 34) The storage medium of claim 34 wherein the instructions configured to cause the processor to determine the fusion class are configured to cause the processor to determine the fusion class in response to the confidence value having an undesirable value. ### Claim 36 (depends on 33) The storage medium of claim 33 wherein the instructions configured to cause the processor to obtain the information associated with the initial classification comprise instructions configured to cause the processor to identify an operational property of the initial classification. ### Claim 37 (depends on 36) The storage medium of claim 36 wherein the instructions configured to cause the processor to determine the fusion class are configured to cause the processor to determine the fusion class based on the operational property of the initial classification. ### Claim 38 (depends on 31) The storage medium of claim 31 wherein the context-related data are first context-related data associated with a first time, the storage medium further comprising instructions configured to cause the processor to determine the second context class using second context-related data associated with a second time that is after the first time, and wherein the instructions configured to cause the processor to determine the fusion class are configured to cause the processor to determine the fusion class based on the first context class and the second context class. ### Claim 39 (depends on 31) The storage medium of claim 31 wherein the instructions configured to cause the processor to determine the first context class are configured to cause the processor to select the first context class from a plurality of predetermined available context classes. ### Claim 40 (depends on 31) The storage medium of claim 31 wherein the instructions configured to cause the processor to determine the fusion class are configured to cause the processor to select the fusion class from a plurality of predetermined available fusion classes.