Granted Patent B2

US 11,334,581 · App. 15/377,016 · Granted May 17, 2022

Inventors: Adi Azaria (Tel Aviv, IL); Amir Orad (Tel Aviv, IL); Guy Levy Yurista (Rockville, MD); Guy Boyangu (Tel Aviv, IL); Eldad Farkash (Tel Aviv, IL); Ophir Marko (Netanya, IL)

Assignee: Sisense Ltd.

G06F16/2465

Abstract

Claims (47)

1. A method for providing sensory analytics responses, comprising:

collecting raw data from a plurality of data sources;

extracting, from the collected raw data, a subset of the raw data to be analyzed;

generating, based on the extracted subset of the raw data, an analytics dataset, wherein the analytics dataset includes a performance indicator;

determining, based on at least one received input, at least one query;

generating a plurality of user accounts, wherein each user account corresponds to a historical user and includes at least one sensory output selection rule for the user, wherein generating the plurality of user accounts further comprises determining, via machine learning, the at least one sensory output selection rule for each of the plurality of user accounts based on historical sensory outputs and historical sensory inputs received from the historical user corresponding to the user account in response to at least a portion of the historical sensory outputs;

identifying, for each query, a user account providing the query from among the generated plurality of user accounts;

determining, based on the analytics dataset and the plurality of user accounts, a response to the at least one query, wherein the response includes at least one sensory output, wherein the response is determined further based on the identified at least one user account, wherein determining the response further comprises selecting, based on the at least one sensory output selection rule of each of the identified at least one user account and the at least one query, the at least one sensory output, wherein each sensory output selection rule corresponds to at least one of the identified at least one user account, wherein each sensory output selection rule is determined based on metadata associated with a corresponding user account, wherein the metadata indicates at least one type of sensory output that is ineffective for a user of the corresponding user account, wherein the at least one type of sensory output that is ineffective for the user of the corresponding user account includes at least one type of sensory output that was determined to be ineffective based on the historical sensory inputs received from the user in response to the historical sensory outputs; and

causing projection of the determined at least one sensory output.

2. The method of claim 1 , wherein the analytics dataset is generated based on a subset of the collected raw data.

3. The method of claim 1 , wherein determining the at least one query further comprises:

parsing at least one textual input, wherein the at least one textual input is based on the at least one received input.

4. The method of claim 3 , further comprising:

determining, based on the at least one received input, the at least one textual input, wherein determining the at least one textual input includes at least one of: speech-to-text processing, and machine imaging.

5. The method of claim 1 , wherein a first user account corresponds to a first priority level, wherein a second user account corresponds to a second priority level, wherein the second priority level is lower than the first priority level, further comprising:

determining a response priority based on the priority level of the respective user account; and

providing the response based on the response priority such that a first portion of the response of the first priority is provided before a second portion of the response of the second priority.

6. The method of claim 1 , wherein the at least one query is determined further based on the performance indicator.

7. The method of claim 1 , wherein the metadata indicates at least one impairment of the user, wherein the at least one type of sensory output that is ineffective for the user of the corresponding user account includes at least one type of sensory output that that is ineffective for users having the at least one impairment.

8. A non-transitory computer readable medium having stored thereon instructions for causing one or more processing units to execute a method, the method comprising:

collecting raw data from a plurality of data sources;

extracting, from the collected raw data, a subset of the raw data to be analyzed;

generating, based on the extracted subset of the raw data, an analytics dataset, wherein the analytics dataset includes a performance indicator

determining, based on a received at least one input, at least one query;

generating a plurality of user accounts, wherein each user account corresponds to a historical user and includes at least one sensory output selection rule for the user, wherein generating the plurality of user accounts further comprises determining the at least one sensory output selection rule for each of the plurality of user accounts based on historical sensory outputs and historical sensory inputs received from the historical user corresponding to the user account in response to at least a portion of the historical sensory outputs;

identifying, for each query, a user account providing the query from among the generated plurality of user accounts;

determining, based on the analytics dataset and the plurality of user accounts, a response to the at least one query, wherein the response includes at least one sensory output, wherein the response is determined further based on the identified at least one user account, wherein determining the response further comprises selecting, based on the at least one sensory output selection rule of each of the identified at least one user account and the at least one query, the at least one sensory output, wherein each sensory output selection rule corresponds to at least one of the identified at least one user account, wherein each sensory output selection rule is determined based on metadata associated with a corresponding user account, wherein the metadata indicates at least one type of sensory output that is ineffective for a user of the corresponding user account, wherein the at least one type of sensory output that is ineffective for the user of the corresponding user account includes at least one type of sensory output that was determined to be ineffective based on the historical sensory inputs received from the user in response to the historical sensory outputs; and

causing projection of the determined at least one sensory output.

9. A system for providing sensory analytics responses, comprising:

a processing circuitry; and

a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:

collect raw data from a plurality of data sources;

extract, from the collected raw data, a subset of the raw data to been analyzed;

generate, based on the extracted subset of the raw data, an analytics dataset, wherein the analytics dataset includes a performance indicator;

determine, based on at least one received input, at least one query;

generate a plurality of user accounts, wherein each user account corresponds to a historical user and includes at least one sensory output selection rule for the user, wherein the system is further configured to generate the plurality of user accounts by determining, via machine learning, the at least one sensory output selection rule for each of the plurality of user accounts based on historical sensory outputs and historical sensory inputs received from the historical user corresponding to the user account in response to at least a portion of the historical sensory outputs;

identify, for each query, a user account providing the query from among the generated plurality of user accounts;

determine, based on the analytics dataset and the plurality of user accounts, a response to the at least one query, wherein the response includes at least one sensory output, wherein the response is determined further based on the identified at least one user account, wherein determining the response further comprises selecting, based on the at least one sensory output selection rule of each of the identified at least one user account and the at least one query, the at least one sensory output, wherein each sensory output selection rule corresponds to at least one of the identified at least one user account, wherein each sensory output selection rule is determined based on metadata associated with a corresponding user account, wherein the metadata indicates at least one type of sensory output that is ineffective for a user of the corresponding user account, wherein the at least one type of sensory output that is ineffective for the user of the corresponding user account includes at least one type of sensory output that was determined to be ineffective based on the historical sensory inputs received from the user in response to the historical sensory outputs; and

cause projection of the determined at least one sensory output.

10. The system of claim 9 , wherein the analytics dataset is generated based on a subset of the collected raw data.

11. The system of claim 9 , wherein the system is further configured to:

parse at least one textual input, wherein the at least one textual input is based on the at least one received input.

12. The system of claim 11 , wherein the system is further configured to:

determine, based on the at least one received input, the at least one textual input, wherein determining the at least one textual input includes at least one of: speech-to-text processing, and machine imaging.

13. The system of claim 9 , wherein the system is further configured to:

determine a response priority based on the priority level of the respective user account; and

provide the response based on the response priority such that a first portion of the response of the first priority is provided before a second portion of the response of the second priority.

Assignments (9)

Continuity (2)

Cited By (1)

US 12,683,963