# US 2021/0174151 A1 · Response based on hierarchical models > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0174151 A1 - Document ID: US20210174151A1 - Status: Published application - Kind: A1 - Application number: 16/770,740 - Filed: 2018-02-21 - Published: 2021-06-10 - Earliest claimed: 2018-02-21 - Assignees: Hewlett-Packard Development Company, L.P. - Applicants: Hewlett-Packard Development Company, L.P. - Inventors: Thomas Paula; Carlos Leao - Web page: https://patentgrep.com/patent/US20210174151A1 ## CPC - G06N 3/08: Learning methods - G06F 18/24: Classification techniques - G06F 18/24765: {Rule-based classification} - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/09: Supervised learning - G06V 10/765: {using rules for classification or partitioning the feature space} - G06V 10/768: {using context analysis, e.g. recognition aided by known co-occurring patterns} - H04L 63/1425: {Traffic logging, e.g. anomaly detection} - H04W 12/122: Counter-measures against attacks; Protection against rogue devices - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) ## Abstract Examples disclosed herein relate to determining a response based on hierarchical models. In one implementation, a processor applies a first model to an image of an environment to select a second model. The processor applies the selected second model to the image and creates an environmental description representation based on the output of the second model. The processor determines a response based on the environmental description information. ## Claims ### Claim 1 A computing system comprising: a storage to store a first, second, and third image classification model; a processor to: apply the first model to an image to determine a context associated with the environment depicted in the image; select at least one of the second and third model based on the determined context; apply the selected model to the image; determine a response based on output from the selected model; ### Claim 2 (depends on 1) The computing system of claim 1, wherein the processor is further to select a fourth model based on the output from the selected model. ### Claim 3 (depends on 1) The computing system of claim 1, wherein the processor is further to apply the second model to a first segment of the image and the third model to a second segment of the image. ### Claim 4 (depends on 1) The computing system of claim 1, wherein the determined context includes a location type. ### Claim 5 (depends on 1) The computing system of claim 1, wherein the processor is further to update the determined context based on output from the selected model. ### Claim 6 (depends on 1) The computing system of claim 1, wherein the output from the selected model is related to object types in the image. ### Claim 7 (depends on 1) The computing system of claim 1, wherein determining a response comprises: interpreting a communication based on the output of the selected model; and determining an answer to the interpreted communication. ### Claim 8 (depends on 1) The computing system of claim 1, wherein the processor is further to transmit information about at least one of the determined context and the output from the selected model to a second electronic device to cause the second electronic device to behave in a particular manner. ### Claim 9 A method, comprising: applying, by a processor, a first model to an image of an environment to select a second model; applying the selected second model to the image; creating an environmental description representation based on the output of the selected second model; and determining a response based on the environmental description information. ### Claim 10 (depends on 9) The method of claim 9, wherein selecting the second model comprises selecting the second model based on output from the first model related to a location type of the environment. ### Claim 11 (depends on 9) The method of claim 9, wherein the environmental description representation includes information about objects and corresponding positions in the image. ### Claim 12 (depends on 9) The method of claim 9, wherein creating the environmental description representation comprises creating the environmental description representation based on the second model and the first model. ### Claim 13 A machine-readable non-transitory storage medium comprising instructions executable by a processor to: apply hierarchical cascading models to an image of an environment to determine a description of the environment; parse a at least one of a query and command based on the description of the environment; and determine a response to the parsed at least of query and command. ### Claim 14 (depends on 13) The machine-readable non-transitory storage medium of claim 13, wherein a base model in the hierarchy of models is related to location type. ### Claim 15 (depends on 13) The machine-readable non-transitory storage medium of claim 13, wherein the output of the application of the models includes sets of information including object type, object position, and confidence level.