# US 11,443,220 B2 · Multiple choice decision engine for an electronic personal assistant > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,220 B2 - Document ID: US11443220B2 - Status: Granted - Kind: B2 - Application number: 15/881,013 - Filed: 2018-01-26 - Published: 2018-06-14 - Granted: 2022-09-13 - Earliest claimed: 2011-01-25 - Assignees: Telepahty Labs, Inc. - Applicants: Telepathy Labs, Inc. - Inventors: Damien Phelan Stolarz; David Joseph Diaz; James Rossfeld; Scott Raven; Christopher O'Malley; Christopher Kurpinski - Web page: https://patentgrep.com/patent/US11443220B2 ## CPC - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06F 3/01: Input arrangements or combined input and output arrangements for interaction between user and computer (G06F3/16 takes precedence) - G06F 3/012: {Head tracking input arrangements} - G06F 3/0482: Interaction with lists of selectable items, e.g. menus - G06F 3/14: Digital output to display device {; Cooperation and interconnection of the display device with other functional units} - G06F 16/242: Query formulation - G06F 16/245: Query processing - G06N 5/04: Inference or reasoning models - G06F 2203/011: Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract To simplify assisting a user in their day-to-day activities, a communication for performing an action may be sent to a user in the form of a query, where the query includes the most likely set of choices for the action arranged in a group of dichotomous (e.g., yes/no) or multiple choice answers. In this manner, a user may respond to the query by simply selecting one of the dichotomous or multiple choice answers. Historical logs of past actions, responses, queries, and so forth, may be used to predict future user actions or needs, and to formulate future queries for sending to the user. These techniques may be implemented, for example, through a remote coordination server or directly through a user's personal electronics device. ## Claims ### Claim 1 A method comprising: receiving a communication at a personal electronic device; analyzing the communication to determine a set of choices in response to the communication, where at least one choice from the set of choices has an associated task predicted for a user of the personal electronic device; creating, by a processor of the personal electronic device, a query from the set of choices, the query including at least one dichotomous or multiple choice question arranged in a hierarchical structure to select among the set of choices, the hierarchical structure having a root and one or more leaves, where the root of the hierarchical structure corresponds to the at least one choice, and the one or more leaves of the hierarchical structure correspond to the associated task predicted for the user of the personal electronic device; presenting the at least one dichotomous or multiple choice question to the user of the personal electronic device in a user interface of the personal electronic device; receiving an input in response to the at least one dichotomous or multiple choice question through the user interface; based on the input, traversing the hierarchical structure, by the processor, to reduce the set of choices to a selected choice; based on the selected choice, where the selected choice is the at least one choice from the set of choices having the associated task, determining one or more actions to accomplish the associated task; obtaining information for performing the one or more actions; and performing the one or more actions using the personal electronic device. ### Claim 2 (depends on 1) The method of claim 1, wherein the root and the one or more leaves are on a same level of the hierarchical structure. ### Claim 3 (depends on 1) The method of claim 1, wherein the root is on a first level of the hierarchical structure and the one or more leaves are on one or more second levels of the hierarchical structure that are different than the first level. ### Claim 4 (depends on 1) The method of claim 1, wherein the analyzing the communication is based on a user data source associated with the user of the personal electronic device. ### Claim 5 (depends on 4) The method of claim 4, wherein the user data source includes a historical log of past actions taken by the user of the personal electronic device, and where the analyzing includes discerning one or more patterns from the historical log of past actions to determine the set of choices. ### Claim 6 (depends on 1) The method of claim 1, wherein the analyzing the communication is based on an external data source associated with the user of the personal electronic device for inferring patterns of activity, behavior, or intent from the user of the personal electronic device. ### Claim 7 (depends on 1) The method of claim 1, wherein the analyzing the communication is based on a data store of historical user data for groups of users. ### Claim 8 (depends on 1) The method of claim 1 wherein the query further comprises multiple dichotomous or multiple choice questions, wherein each dichotomous or multiple choice question narrows down a decision made by the user of the personal electronic device for performing the associated task. ### Claim 9 (depends on 1) The method of claim 1, wherein the personal electronic device is a smartphone, a watch, a headset, or a vehicle. ### Claim 10 A computer program product comprising non-transitory computer executable code embodied in a non-transitory computer readable medium that, when executing on a personal electronics device, performs operations comprising: receiving a communication at the personal electronic device; analyzing the communication to determine a set of choices in response to the communication, where at least one choice from the set of choices has an associated task predicted for a user of the personal electronic device; creating, by a processor of the personal electronic device, a query from the set of choices, the query including at least one dichotomous or multiple choice question arranged in a hierarchical structure to select among the set of choices, the hierarchical structure having a root and one or more leaves, where the root of the hierarchical structure corresponds to the at least one choice, and the one or more leaves of the hierarchical structure correspond to the associated task predicted for the user of the personal electronic device; presenting the at least one dichotomous or multiple choice question to the user of the personal electronic device in a user interface of the personal electronic device; receiving an input in response to the at least one dichotomous or multiple choice question through the user interface; based on the input, traversing the hierarchical structure, by the processor, to reduce the set of choices to a selected choice; based on the selected choice, where the selected choice is the at least one choice from the set of choices having the associated task, determining one or more actions to accomplish the associated task; obtaining information for performing the one or more actions; and performing the one or more actions using the personal electronic device. ### Claim 11 (depends on 10) The computer program product of claim 10, wherein the root and the one or more leaves are on a same level of the hierarchical structure. ### Claim 12 (depends on 10) The computer program product of claim 10, wherein the analyzing the communication is based on a user data source associated with the user of the personal electronic device. ### Claim 13 (depends on 10) The computer program product of claim 10, wherein the analyzing the communication is based on an external data source associated with the user of the personal electronic device for inferring patterns of activity, behavior, or intent from the user of the personal electronic device. ### Claim 14 (depends on 10) The computer program product of claim 10, wherein the analyzing the communication is based on a data store of historical user data for groups of users. ### Claim 15 (depends on 10) The computer program product of claim 10 wherein the query further comprises multiple dichotomous or multiple choice questions, wherein each dichotomous or multiple choice question narrows down a decision made by the user of the personal electronic device for performing the associated task. ### Claim 16 (depends on 10) The computer program product of claim 10, wherein the personal electronic device is a smartphone, a watch, a headset, or a vehicle. ### Claim 17 A personal electronic device comprising: a processor; a memory; and a user interface, the processor coupled to the memory and to the user interface, the processor configured to: receive a communication, analyze the communication to determine a set of choices in response to the communication, where at least one choice from the set of choices has an associated task predicted for a user, create a query from the set of choices, the query including at least one dichotomous or multiple choice question arranged in a hierarchical structure to select among the set of choices, the hierarchical structure having a root and one or more leaves, where the root of the hierarchical structure corresponds to the at least one choice, and the one or more leaves of the hierarchical structure correspond to the associated task, present, on the user interface, the at least one dichotomous or multiple choice question to the user, receive, at the user interface, an input in response to the at least one dichotomous or multiple choice question, based on the input, traverse the hierarchical structure to reduce the set of choices to a selected choice; based on the selected choice, where the selected choice is the at least one choice from the set of choices having the associated task, determine one or more actions to accomplish the associated task; obtain information for performing the one or more actions; and perform the one or more actions using the personal electronic device. ### Claim 18 A method comprising: receiving a communication at a personal electronic device; analyzing the communication to determine a set of choices in response to the communication, where at least one choice from the set of choices has an associated task predicted for a user of the personal electronic device; selecting, by a processor of the personal electronic device, the at least one choice based on at least one data source; determining, by the processor, one or more actions to accomplish the associated task; obtaining, by the processor, information for performing the one or more actions; and performing the one or more actions using the personal electronic device. ### Claim 19 (depends on 18) The method of claim 18, wherein the at least one data source includes current circumstances, activities, and known data about the user. ### Claim 20 (depends on 18) The method of claim 18, further comprising: creating, by the processor of the personal electronic device, a confirmation query from the selected choice, the confirmation query including at least one dichotomous question arranged in a hierarchical structure, the hierarchical structure having a root and one or more leaves, where the root of the hierarchical structure corresponds to the at least one choice, and the one or more leaves of the hierarchical structure correspond to the associated task; presenting the at least one dichotomous question to the user of the personal electronic device in a user interface of the personal electronic device; receiving an input in response to the at least one dichotomous question through the user interface; and based on the input, either confirming the selected choice; or selecting another choice based on the at least one data source.