Personalized search based on account attributes

Patent metadata

Field	Value
Publication number	US-11531707-B1
Application number	US-201916584742-A
Country	US
Kind code	B1
Filing date	Sep 26, 2019
Priority date	Sep 26, 2019
Publication date	Dec 20, 2022
Grant date	Dec 20, 2022

Abstract

A system stores resources such as text articles, videos, and so forth for an organization. During operation, the system receives a query and provides a response. During initial use of the system, there is little or no historical data available to help determine which resource is most relevant to a particular query. In this “cold-start” situation, the system determines attributes associated with a user account of the user making the query. The query is used to search a data store and retrieve a set of resources based on a term match with the query and to find the resources which correspond to the attributes of the user account. This allows the system to provide simplified output that is more likely to be relevant to that particular user in the “cold-start” situation.

First claim

What is claimed is:

1. A method comprising:
receiving a first query at a first device, the first query associated with a first user account;
determining a set of resources from a data store based on the first query, wherein at least a portion of the set of resources is associated with a first attribute value;
determining text match scores for one or more resources of the set of resources based on word-level matches between terms of the first query and words within one or more resources of the set of resources;
determining historical data that is indicative of historical feedback data for previous queries that correspond to the first query;
determining, based on a metric associated with the historical data, that there is less than a threshold amount of historical feedback data for the previous queries, the metric comprising at least one of: a count of historical data records associated with previous queries, a count of a number of previous queries, or an amount of time that a resource has been available;
determining a second attribute value associated with the first user account;
determining a first resource of the set of resources based on one or more of the text match scores or a first correspondence between the first attribute value and the second attribute value;
responsive to determining that there is less than a threshold amount of historical feedback data for the previous queries, refraining from determining the first resource of the set of resources based on the historical data; and
providing response data including the first resource.

2. The method of claim 1 , further comprising:
receiving a second query at the first device, the second query corresponding to the first query and associated with a second user account;
determining the set of resources based on the second query;
determining a third attribute value associated with the second user account;
determining a second resource from the set of resources based on a second correspondence between a fourth attribute value associated with the second resource and the third attribute value associated with the second user account; and
providing second response data including the second resource to a computing device associated with the second query.

3. The method of claim 1 , further comprising:
determining the metric associated with historical data corresponding to the first query is greater than the threshold value;
determining total relevancy scores for the one or more resources of the set of resources based on a combination of the text match scores, the historical feedback data, and the first correspondence between the first attribute value and the second attribute value; and
determining the first resource of the set of resources having a highest total relevancy score;
wherein the response data includes the first resource of the set of resources having the highest total relevancy score.

4. The method of claim 1 , further comprising:
receiving a second resource at the first device;
providing an interface to a second device, the interface including at least one field accessible by a user to configure one or more resource attribute values including a set of rules to determine visibility of the second resource based on attribute values of user accounts; and
storing the second resource and the one or more resource attribute values in the data store.

5. The method of claim 1 , wherein the historical feedback data comprises at least one of: positive responses or negative responses.

6. A system comprising:
a communication interface;
one or more memories storing a data store and processor-executable instructions; and
one or more hardware processors to execute the processor-executable instructions to:
receive a first query associated with a first user account;
determine an attribute value associated with the first user account;
determine a first set of resources from the data store based on the first query, the first set of resources including a first resource having a first resource attribute value and a second resource having a second resource attribute value;
determine historical data including historical feedback data for previous queries corresponding to the first query;
determining, based on a metric associated with the historical data, that there is less than a threshold amount of historical feedback data for the previous queries, the metric comprising at least one of: a count of historical data records associated with previous queries, a count of a number of previous queries, or an amount of time that a resource has been available;
determine a first correspondence between the first resource attribute value of the first resource of the first set of resources and the attribute value of the first user account;
determine the first resource from the first set of resources based at least in part on the first correspondence;
responsive to determining that there is less than a threshold amount of historical feedback data for the previous queries, refraining from determining the first resource of the set of resources based on the historical data; and
provide response data including the first resource to a computing device associated with the first user account.

7. The system of claim 6 , wherein a first resource of the first set of resources comprises one or more of text data, image data, video data, or audio data.

8. The system of claim 6 , wherein the one or more hardware processors to execute the processor-executable instructions to:
determine the metric associated with the historical data is greater than or equal to the threshold value;
determine text match scores for the first set of resources relative to the first query, the text match scores including a first text match score for the first resource and a second text match score for the second resource;
determine total relevancy scores for the first set of resources based on one or more of the text match scores, the historical data, or the correspondence; and
determine the first resource of the first set of resources having a highest total relevancy score.

9. The system of claim 6 , wherein the one or more hardware processors to execute the processor-executable instructions to:
determine the metric associated with the historical data is greater than or equal to the threshold value;
determine one or more previous queries corresponding to the first query;
determine historical data related to the one or more previous queries including previous response data and feedback data;
determine one or more relevancy scores for the first set of resources based on one or more of text match scores and the historical data;
provide, to a machine learning module, the relevancy scores, the historical data, and data related to the first correspondence between the first resource attribute value of the first resource of the first set of resources and the attribute value of the first user account; and
determine the first resource using the machine learning module.

10. The system of claim 6 , wherein the one or more hardware processors to execute the processor-executable instructions to:
receive a third resource;
provide an interface including one or more controls accessible by a user to customize a third resource attribute value associated with the third resource, the interface including a field to receive a name for the resource attribute value; and
store the third resource and the third resource attribute value in the data store.

11. The system of claim 6 , wherein the one or more hardware processors to execute the processor-executable instructions to:
determine the metric associated with the historical data is greater than or equal to the threshol

Assignees

• Townsend Street Labs Inc
• Okta Inc

Inventors

• Samdani Rajhans
• Goyal Ankit
• Rappolt Pierre
• Wang Emily Yidan
• Patnaik Pratyus
• Potter William S
• Agarwal Suchit

Classifications

• G06F16/908

  using metadata automatically derived from the content · CPC title

• G06F16/90332 Primary

  Natural language query formulation or dialogue systems · CPC title

• G06F16/909

  using geographical or spatial information, e.g. location (spatiotemporally dependent retrieval from the web G06F16/9537) · CPC title

• G06F16/90344

  by using string matching techniques · CPC title

• G06F16/9035

  Filtering based on additional data, e.g. user or group profiles · CPC title