# US 2023/0274167 A1 · Task Learning System and Method, and Related Device > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0274167 A1 - Document ID: US20230274167A1 - Status: Published application - Kind: A1 - Application number: 18/309,376 - Filed: 2023-04-28 - Published: 2023-08-31 - Earliest claimed: 2020-11-03 - Assignees: Huawei Cloud Computing Technologies Co., Ltd. - Applicants: Huawei Cloud Computing Technologies Co., Ltd. - Inventors: Zimu Zheng; Jie Pu; Feng Wang; Jiahao Li - Web page: https://patentgrep.com/patent/US20230274167A1 ## CPC - G06N 3/096: Transfer learning - G06N 5/04: Inference or reasoning models - G06N 3/045: Combinations of networks - G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections - G06N 3/09: Supervised learning - G06N 3/0985: Hyperparameter optimisation; Meta-learning; Learning-to-learn - G06N 20/10: using kernel methods, e.g. support vector machines [SVM] - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A task learning system includes a knowledge base and a task processing apparatus. The knowledge base is configured to store task attributes and task models corresponding to the task attributes. The task processing apparatus is configured to: obtain an input sample; when an inference task corresponding to the input sample is an unknown task, generate an inference model for the unknown task based on the task attributes and the task models that are stored in the knowledge base module; and perform inference on the input sample by using the inference model to obtain a target inference result. ## Claims ### Claim 1 A task learning system, comprising: a knowledge base configured to store first task attributes and task models corresponding to the first task attributes; and a task processing apparatus coupled to the knowledge base and configured to: obtain an input sample; generate, when an inference task corresponding to the input sample is an unknown task, an inference model for the unknown task based on at least one task attribute of the first task attributes and a corresponding first task model of the task models, wherein the at least one task attribute corresponds to the input sample; and perform inference on the input sample using the inference model to obtain a target inference result. ### Claim 2 (depends on 1) The task learning system of claim 1, wherein the task processing apparatus is further configured to: determine a target task attribute of the input sample based on the input sample and a subset of the first task attributes that correspond to the input sample; and determine, based on the target task attribute, the at least one task attribute, and the corresponding first task model, that the inference task is the unknown task. ### Claim 3 (depends on 2) The task learning system of claim 2, wherein the task processing apparatus is further configured to determine, based on a difference between the target task attribute and the at least one task attribute, that the inference task is the unknown task. ### Claim 4 (depends on 2) The task learning system of claim 2, wherein the task processing apparatus is further configured to determine, based on any one or more of a confidence of performing inference on the input sample using each task model of the task models, a model migration rate, or a task model quality of the task models, that the inference task is the unknown task. ### Claim 5 (depends on 2) The task learning system of claim 2, wherein the task processing apparatus is further configured to generate the inference model for the unknown task based on the target task attribute, the at least one task attribute, and the corresponding first task model. ### Claim 6 (depends on 5) The task learning system of claim 5, wherein the knowledge base is further configured to store a task relationship that comprises one or more of a subordinate relationship or a migration relationship, and wherein the task processing apparatus is further configured to generate the inference model based on the target task attribute, the first task attributes, the task models, and the task relationship. ### Claim 7 (depends on 5) The task learning system of claim 5, wherein the task processing apparatus is further configured to: determine a plurality of candidate task models in the task models based on the target task attribute; and use the plurality of candidate task models as the inference model. ### Claim 8 (depends on 5) The task learning system of claim 5, wherein the knowledge base is further configured to store first training samples corresponding to the first task attributes, and wherein the task processing apparatus is further configured to: determine, based on the target task attribute, second training samples of the first training samples respectively corresponding to a plurality of candidate task models in the task models; retrain one or more candidate task models of the plurality of candidate task models based on the second training samples; and use, as the inference model, the one or more candidate task models. ### Claim 9 (depends on 5) The task learning system of claim 5, wherein the knowledge base is further configured to store first training samples corresponding to the first task attributes, and wherein the task processing apparatus is further configured to: determine, based on the target task attribute, second training samples of the first training samples respectively corresponding to a plurality of candidate task models in the task models; perform training based on the second training samples to obtain a new task model; and use the new task model as the inference model. ### Claim 10 (depends on 1) The task learning system of claim 1, wherein the task processing apparatus comprises: a model determiner deployed in a cloud or an edge side network and configured to generate, when the inference task corresponding to the input sample is the unknown task, the inference model based on the at least one task attribute and the corresponding first task model; and an inference performer deployed in the edge side network and configured to perform inference on the input sample using the inference model to obtain the target inference result. ### Claim 11 (depends on 1) The task learning system of claim 1, wherein the task processing apparatus further comprises: an attribute determiner deployed in an edge side network and configured to determine a target task attribute of the input sample based on the input sample and the at least one task attribute; and a task determiner deployed in the edge side network and configured to determine, based on the target task attribute, the at least one task attribute, and the corresponding first task model, that the inference task is the unknown task. ### Claim 12 (depends on 1) The task learning system of claim 1, wherein the knowledge base is deployed in a cloud. ### Claim 13 (depends on 1) The task learning system of claim 1, wherein the task processing apparatus is further configured to update, based on a target task attribute of the input sample and the inference model, one or more task attributes that are stored in the knowledge base and one or more task models that are stored in the knowledge base. ### Claim 14 (depends on 13) The task learning system of claim 13, wherein the task processing apparatus is further configured to add the target task attribute and the inference model to the knowledge base, and wherein the knowledge base is further configured to simultaneously store the first task attributes, the target task attribute, the task models, and the inference model. ### Claim 15 (depends on 13) The task learning system of claim 13, wherein the task processing apparatus is further configured to: replace a corresponding task attribute in the knowledge base with the target task attribute; and replace a corresponding task model in the knowledge base with the inference model. ### Claim 16 (depends on 14) The task learning system of claim 14, wherein the task processing apparatus comprises a knowledge base updater deployed in a cloud or an edge side network and configured to update, based on the target task attribute and the inference model, the at least one task attribute and the corresponding first task model. ### Claim 17 (depends on 1) The task learning system of claim 1, wherein when the inference model comprises a plurality of models, and wherein the task processing apparatus is further configured to: perform inference on the input sample using all models of the plurality of models to obtain inference results that are output by all the models of the plurality of models; and determine the target inference result from the inference results. ### Claim 18 A task learning method, comprising: obtaining an input sample; generating, when an inference task corresponding to the input sample is an unknown task, an inference model for the unknown task based on at least one task attribute of first task attributes in a knowledge base and a corresponding first task model of task models that are in the knowledge base, wherein the at least one task attribute corresponds to the input sample; and performing inference on the input sample using the inference model to obtain a target inference result. ### Claim 19 (depends on 18) The task learning method of claim 18, further comprising: determining a target task attribute of the input sample based on the input sample and the at least one task attribute; and determining, based on the target task attribute, the at least one task attribute, and the corresponding first task model, that the inference task is the unknown task. ### Claim 20 (depends on 19) The task learning method of claim 19, wherein determining, based on the target task attribute, the at least one task attribute, and the corresponding first task model, that the inference task is the unknown task comprises determining, based on a difference between the target task attribute and the at least one task attribute, that the inference task is the unknown task.