# US 11,308,169 B1 · Generating multi-perspective responses by assistant systems

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,308,169 B1
- Document ID: US11308169B1
- Status: Granted
- Kind: B1
- Application number: 16/176,312
- Filed: 2018-10-31
- Granted: 2022-04-19
- Earliest claimed: 2018-04-20
- Assignees: Meta Platforms, Inc.
- Applicants: Meta Platforms, Inc.
- Inventors: Emmanouil Koukoumidis; Michael Robert Hanson; Rajen Subba; Heidi Young; Rushin Shah; Jinsong Yu; Benoit F. Dumoulin; Jeremy Gillmor Kahn; Chandrasekhar Iyer
- Web page: https://patentgrep.com/patent/US11308169B1

## CPC

- G06Q 10/00: Administration; Management
- G06F 3/011: {Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00)}
- G06F 3/013: {Eye tracking input arrangements (G06F3/015 takes precedence)}
- G06F 3/017: {Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883)}
- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G06F 7/14: Merging, i.e. combining at least two sets of record carriers each arranged in the same ordered sequence to produce a single set having the same ordered sequence
- G06F 8/31: {Programming languages or programming paradigms}
- G06F 9/44505: {Configuring for program initiating, e.g. using registry, configuration files}
- G06F 9/4451: {User profiles; Roaming}
- G06F 9/453: {Help systems}
- G06F 16/176: Support for shared access to files; File sharing support
- G06F 16/2255: {Hash tables}
- G06F 16/2365: {Ensuring data consistency and integrity}
- G06F 16/243: {Natural language query formulation}
- G06F 16/24552: {Database cache management}
- G06F 16/24575: {using context}
- G06F 16/24578: {using ranking}
- G06F 16/248: Presentation of query results
- G06F 16/3322: {using system suggestions (G06F16/3325 takes precedence)}
- G06F 16/3323: {using document space presentation or visualization, e.g. category, hierarchy or range presentation and selection}
- G06F 16/3329: Natural language query formulation
- G06F 16/3344: {using natural language analysis}
- G06F 16/338: Presentation of query results
- G06F 16/90332: {Natural language query formulation or dialogue systems}
- G06F 16/90335: {Query processing}
- G06F 16/9038: Presentation of query results
- G06F 16/904: Browsing; Visualisation therefor (for navigating the web G06F16/954; browsing optimisation for the web G06F16/957)
- G06F 16/951: Indexing; Web crawling techniques
- G06F 16/9532: Query formulation
- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F 18/2411: based on the proximity to a decision surface, e.g. support vector machines
- G06F 21/6245: {Protecting personal data, e.g. for financial or medical purposes}
- G06F 40/205: Parsing
- G06F 40/274: Converting codes to words; Guess-ahead of partial word inputs
- G06F 40/295: Named entity recognition
- G06F 40/30: Semantic analysis
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 5/027: {Frames}
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06Q 10/40: Business processes related to social networking or social networking services
- G06Q 10/42: Determination of affinities or common interests between users
- G06Q 10/48: using social graphs
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/82: using neural networks
- G06V 20/10: Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59)
- G06V 40/28: {Recognition of hand or arm movements, e.g. recognition of deaf sign language (static hand signs G06V40/113)}
- G10L 15/02: Feature extraction for speech recognition; Selection of recognition unit
- G10L 15/063: {Training}
- G10L 15/07: to the speaker
- G10L 15/16: using artificial neural networks
- G10L 15/1815: {Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning}
- G10L 15/1822: {Parsing for meaning understanding}
- G10L 15/183: using context dependencies, e.g. language models
- G10L 15/187: Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 17/06: Decision making techniques; Pattern matching strategies
- G10L 17/22: Interactive procedures; Man-machine interfaces
- H04L 5/02: Channels characterised by the type of signal
- H04L 12/2816: {Controlling appliance services of a home automation network by calling their functionalities (arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station; in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom H04Q9/00)}
- H04L 41/20: {Network management software packages}
- H04L 41/22: comprising specially adapted graphical user interfaces [GUI]
- H04L 43/0882: Utilisation of link capacity
- H04L 43/0894: Packet rate
- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- H04L 51/18: Commands or executable codes
- H04L 51/216: Handling conversation history, e.g. grouping of messages in sessions or threads
- H04L 51/52: for supporting social networking services
- H04L 63/102: {Entity profiles}
- H04L 67/306: User profiles
- H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)}
- H04L 67/5651: Reducing the amount or size of exchanged application data
- H04L 67/75: Indicating network or usage conditions on the user display
- H04W 12/08: Access security
- G06F 2216/13: Prefetching
- G10L 13/00: Speech synthesis; Text to speech systems
- G10L 13/04: Details of speech synthesis systems, e.g. synthesiser structure or memory management
- G10L 17/00: Speaker identification or verification techniques
- G10L 2015/223: {Execution procedure of a spoken command}
- G10L 2015/225: {Feedback of the input speech}
- H04L 51/046: Interoperability with other network applications or services
- H04L 51/222: using geographical location information, e.g. messages transmitted or received in proximity of a certain spot or area
- H04L 67/10: in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46)
- H04L 67/53: using third party service providers
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- 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

In one embodiment, a method includes receiving a user query from a client system associated with a first user, determining a plurality of dialog-intents, each being associated with a particular agent of a plurality of agents, executing a plurality of tasks corresponding to the user query via the plurality of agents corresponding to the plurality of dialog-intents, receiving a plurality of execution results corresponding to the plurality of tasks from the plurality of agents, respectively, selecting two or more of the plurality of execution results for combination, generating a multi-perspective response based on the selected execution results by a stitching model, wherein the multi-perspective response comprises a natural-language response combining the selected execution results, and sending instructions for presenting the multi-perspective response to the first user to the client system in response to the user query.

## Claims

### Claim 1

A method comprising, by one or more computing systems:
receiving, from a client system associated with a user, a user query;
determining, based on the user query, a plurality of dialog-intents, wherein each dialog-intent is associated with a particular agent of a plurality of agents;
executing, via the plurality of agents corresponding to the plurality of dialog-intents, a plurality of tasks corresponding to the user query;
receiving, from the plurality of agents, a plurality of execution results corresponding to the plurality of tasks, respectively;
selecting two or more of the plurality of execution results for combination;
generating, by a stitching model, a multi-perspective response based on the selected execution results, wherein the multi-perspective response comprises a natural-language response combining the selected execution results; and
sending, to the client system in response to the user query, instructions for presenting the multi-perspective response to the user.

### Claim 2 (depends on 1)

The method of claim 1, wherein the plurality of dialog-intents are determined by a natural-language understanding module.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
determining, by a natural-language understanding module, one or more slots associated with each of the plurality of dialog-intents.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
determining a plurality of relevance scores of the plurality of execution results with respect to the user query, respectively; and
ranking the plurality of execution results based on their respective relevance scores;
wherein selecting the two or more of the plurality of execution results for combination comprises selecting execution results based on their respective rankings.

### Claim 5 (depends on 1)

The method of claim 1, wherein selecting the two or more of the plurality of execution results for combination comprises:
determining, based on one or more machine-learning models, whether one or more of the plurality of execution results are mutually exclusive results with respect to each execution result of the plurality of execution results; and
filtering one or more of the mutually exclusive results from the plurality of execution results;
wherein selecting the two or more of the plurality of execution results for combination comprises selecting two or more execution results from the post-filtered plurality of execution results.

### Claim 6 (depends on 1)

The method of claim 1, wherein selecting the two or more of the plurality of execution results for combination comprises:
calculating, for each execution result of the plurality of execution results, an entropy value based on the information entropy of the respective execution result; and
calculating, for each execution result of the plurality of execution results, information-gain values of the execution result based on its respective entropy value with respect to the entropy values of each other execution result of the plurality of execution results;
wherein selecting the two or more of the plurality of execution results for combination comprises selecting two or more execution results based on their respective information-gain values.

### Claim 7 (depends on 1)

The method of claim 1, wherein generating the multi-perspective response comprises:
determining an order of the selected execution results; and
combining, by the stitching model, the selected execution results based on the determined order.

### Claim 8 (depends on 7)

The method of claim 7, wherein the order of the selected execution results is determined based on a sequential-language model.

### Claim 9 (depends on 8)

The method of claim 8, wherein the sequential-language model is trained based on a plurality of training data of human-combined utterances.

### Claim 10 (depends on 7)

The method of claim 7, wherein the order of the selected execution results is determined based on one or more predefined rules.

### Claim 11 (depends on 7)

The method of claim 7, wherein the order of the selected execution results is determined based on user profile data associated with the user.

### Claim 12 (depends on 7)

The method of claim 7, wherein the order of the selected execution results is determined based on execution times associated with the selected execution results.

### Claim 13 (depends on 7)

The method of claim 7, wherein the order of the selected execution results is determined based on history data of user interactions by the user with agents corresponding to the selected execution results.

### Claim 14 (depends on 7)

The method of claim 7, wherein the order of the selected execution results is determined based on linguistic grounding.

### Claim 15 (depends on 1)

The method of claim 1, wherein the multi-perspective response is based on one or more modalities.

### Claim 16 (depends on 15)

The method of claim 15, wherein the one or more modalities comprise one or more of text, audio, image, or video.

### Claim 17

One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
receive, from a client system associated with a user, a user query;
determine, based on the user query, a plurality of dialog-intents, wherein each dialog-intent is associated with a particular agent of a plurality of agents;
execute, via the plurality of agents corresponding to the plurality of dialog-intents, a plurality of tasks corresponding to the user query;
receive, from the plurality of agents, a plurality of execution results corresponding to the plurality of tasks, respectively;
select two or more of the plurality of execution results for combination;
generate, by a stitching model, a multi-perspective response based on the selected execution results, wherein the multi-perspective response comprises a natural-language response combining the selected execution results; and
send, to the client system in response to the user query, instructions for presenting the multi-perspective response to the user.

### Claim 18

A system comprising: one or more processors; and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to:
receive, from a client system associated with a user, a user query;
determine, based on the user query, a plurality of dialog-intents, wherein each dialog-intent is associated with a particular agent of a plurality of agents;
execute, via the plurality of agents corresponding to the plurality of dialog-intents, a plurality of tasks corresponding to the user query;
receive, from the plurality of agents, a plurality of execution results corresponding to the plurality of tasks, respectively;
select two or more of the plurality of execution results for combination;
generate, by a stitching model, a multi-perspective response based on the selected execution results, wherein the multi-perspective response comprises a natural-language response combining the selected execution results; and
send, to the client system in response to the user query, instructions for presenting the multi-perspective response to the user.

### Claim 19 (depends on 1)

The method of claim 1, wherein the plurality of dialog-intents are determined based on one or more same slots associated with the user query.