# US 2023/0274641 A1 · Hierarchical transfer learning system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0274641 A1 - Document ID: US20230274641A1 - Status: Published application - Kind: A1 - Application number: 17/681,092 - Filed: 2022-02-25 - Published: 2023-08-31 - Earliest claimed: 2022-02-25 - Assignees: Toyota Motor Engineering & Manufacturing North America, Inc. - Applicants: Toyota Motor Engineering & Manufacturing North America, Inc. - Inventors: Xuewei Qi; Kentaro Oguchi; Yongkang Liu; Emrah Akin Sisbot - Web page: https://patentgrep.com/patent/US20230274641A1 ## CPC - G08G 1/096775: {where the origin of the information is a central station} - G06N 3/096: Transfer learning - G06V 10/82: using neural networks - G06V 10/87: {using selection of the recognition techniques, e.g. of a classifier in a multiple classifier system} - G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle - G08G 1/0129: {for creating historical data or processing based on historical data} - G08G 1/0133: {for classifying traffic situation} - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/084: Backpropagation, e.g. using gradient descent - G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93}) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Systems, methods, and other embodiments described herein relate to improving the performance of a device in different geographic locations by using transfer learning to provide a customized learning model for the different locations. In one embodiment, a method includes receiving segments of a model from separate members in a geographic hierarchy and assembling the segments into the model. The segments include at least a first segment, a second segment, and a third segment. The method includes processing sensor data using the model to provide an output for assisting a device. ## Claims ### Claim 1 A system, comprising: one or more processors, and a memory communicably coupled to the one or more processors and storing: a control module including instructions that, when executed by the one or more processors cause the one or more processors to: receive segments of a model from separate members in a geographic hierarchy; assemble the segments into the model, wherein the segments include at least a first segment, a second segment, and a third segment; and process sensor data using the model to provide an output for assisting a device. ### Claim 2 (depends on 1) The system of claim 1, wherein the control module includes instructions to determine a current location of the device, and select the separate members based at least on the current location of the device. ### Claim 3 (depends on 1) The system of claim 1, wherein the control module includes instructions to request the segments from the separate members, and responsive to requesting the segments, receive the segments. ### Claim 4 (depends on 1) The system of claim 1, wherein the control module includes instructions to transmit the model to one or more devices that are capable of processing sensor data using the model. ### Claim 5 (depends on 1) The system of claim 1, wherein the first segment is based at least on an aggregate of trained weights from a plurality of devices within a first region, the second segment is based at least on an aggregate of trained weights from a plurality of devices within a second region, the third segment is based at least on an aggregate of trained weights from a plurality of devices within a third region, wherein the second region is a sub-region of and smaller than the first region, and wherein the third region is a sub-region of and smaller than the second region. ### Claim 6 (depends on 1) The system of claim 1, wherein the device is one of a mobile device and a stationary device. ### Claim 7 (depends on 1) The system of claim 1, wherein the first segment includes common traffic rules, the second segment includes area specific trends, and the third segment includes local behaviors. ### Claim 8 A method, comprising: receiving segments of a model from separate members in a geographic hierarchy; assembling the segments into the model, wherein the segments include at least a first segment, a second segment, and a third segment; and processing sensor data using the model to provide an output for assisting a device. ### Claim 9 (depends on 8) The method of claim 8, further comprising: determining a current location of the device, and selecting the separate members based at least on the current location of the device. ### Claim 10 (depends on 8) The method of claim 8, further comprising: requesting the segments from the separate members, and responsive to requesting the segments, receiving the segments. ### Claim 11 (depends on 8) The method of claim 8, further comprising: transmitting the model to one or more devices that are capable of processing sensor data using the model. ### Claim 12 (depends on 8) The method of claim 8, wherein the first segment is based at least on an aggregate of trained weights from a plurality of devices within a first region, the second segment is based at least on an aggregate of trained weights from a plurality of devices within a second region, the third segment is based at least on an aggregate of trained weights from a plurality of devices within a third region, wherein the second region is a sub-region of and smaller than the first region, and wherein the third region is a sub-region of and smaller than the second region. ### Claim 13 (depends on 8) The method of claim 8, wherein the device is one of a mobile device and a stationary device. ### Claim 14 (depends on 8) The method of claim 8, wherein the first segment includes common traffic rules, the second segment includes area specific trends, and the third segment includes local behaviors. ### Claim 15 A non-transitory computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to: receive segments of a model from separate members in a geographic hierarchy; assemble the segments into the model, wherein the segments include at least a first segment, a second segment, and a third segment; and process sensor data using the model to provide an output for assisting a device. ### Claim 16 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the instructions include instructions to determine a current location of the device, and select the separate members based at least on the current location of the device. ### Claim 17 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the instructions include instructions to request the segments from the separate members, and responsive to requesting the segments, receive the segments. ### Claim 18 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the instructions include instructions to transmit the model to one or more devices that are capable of processing sensor data using the model. ### Claim 19 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the first segment is based at least on an aggregate of trained weights from a plurality of devices within a first region, the second segment is based at least on an aggregate of trained weights from a plurality of devices within a second region, the third segment is based at least on an aggregate of trained weights from a plurality of devices within a third region, wherein the second region is a sub-region of and smaller than the first region, and wherein the third region is a sub-region of and smaller than the second region. ### Claim 20 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the device is one of a mobile device and a stationary device.