RETRIEVING CONTEXT FROM PREVIOUS SESSIONS

• US 20150356136A1
• Filed: 07/31/2014
• Published: 12/10/2015
• Est. Priority Date: 06/10/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Joshi, Ajay
• Granted Patent: US 10,275,485 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for retrieving and using contextual data from previous conversation sessions in conversational searches. In one aspect, a method includes receiving a first query for a first user session, determining that the first query refers to one or more tags in a first repository, the first repository associating respective identifiers to respective tags, each identifier representing a corresponding user session, determining one or more particular identifiers associated with the one or more tags in the first repository, retrieving particular contextual data associated with the determined particular identifiers in a second repository, the second repository associating respective identifiers to respective contextual data associated with corresponding user sessions represented by the respective identifiers, and performing an action responsive to the first query based on the retrieved particular contextual data.

Claims

1. A method comprising:

receiving, by one or more computers, a first query for a first user session;

determining, by the one or more computers, that the first query refers to one or more tags in a first repository, the first repository associating respective identifiers to respective tags, each identifier representing a corresponding user session;

determining, by the one or more computers, one or more particular identifiers associated with the one or more tags in the first repository;

retrieving, by the one or more computers, particular contextual data associated with the determined particular identifiers in a second repository, the second repository associating respective identifiers to respective contextual data associated with corresponding user sessions represented by the respective identifiers; and

performing, by the one or more computers, an action responsive to the first query based on the retrieved particular contextual data.

2. The method of claim 1, wherein the one or more tags include a time tag indicating a time earlier than the first user session, and wherein determining one or more particular identifiers associated with the one or more tags in the first repository comprises:

determining a plurality of candidate identifiers associated with the time tag in the first repository; and

selecting the one or more particular identifiers from the plurality of candidate identifiers based on remaining tags of the one or more tags.

3. The method of claim 1, wherein determining one or more particular identifiers comprises:

determining, for each tag of the tags, a plurality of respective candidate identifiers associated with the tag in the first repository; and

selecting the particular identifiers from the determined respective candidate identifiers by determining an overlap of the determined respective candidate identifiers, each identifier of the particular identifiers being associated with each tag of the tags in the first repository.

4. The method of claim 1, wherein the one or more tags comprise at least one of a session tag or an item tag, the session tag being associated with information about particular corresponding user sessions for the particular identifiers, the item tag being associated with at least one of particular queries in the particular corresponding user sessions or particular search results responsive to the particular queries.

5. The method of claim 4, further comprising determining that at least one of the particular queries or the particular search results refers to a particular item corresponding to the item tag, wherein performing an action comprises performing the action responsive to the first query based on the determined particular item.

6. The method of claim 1, further comprising, before determining that the first query refers to one or more tags in a first repository, determining that the first query lacks additional information required for performing the action and that the first query is not associated with a previous query for the first user session.

7. The method of claim 1, further comprising:

receiving, from a user, a second query for a second user session;

determining that at least one of the second query or a second search result responsive to the second query refers to a second item in a database, the database associating respective items to respective item tags;

determining one or more second item tags associated with the second item in the database;

storing the second item tags in the first repository; and

associating the second item tags with a second identifier representing the second user session in the first repository.

8. The method of claim 7, further comprising:

determining one or more second session tags for the second user session, the second session tags including at least one of a timestamp for the second user session, a location of the user for the second user session, or an action associated with the user before the second user session;

storing the second session tags in the first repository; and

associating the second session tags with the second identifier in the first repository.

9. The method of claim 7, further comprising:

determining second contextual data for the second query, the second contextual data including the second query, the second search result, and metadata associated with the second query and the second search result;

storing the second contextual data in the second repository; and

associating the second contextual data with the second identifier in the second repository.

10. A system, comprising:

a data processing apparatus; and

a non-transitory computer readable storage medium in data communication with the data processing apparatus and storing instructions executable by the data processing apparatus and upon such execution cause the data processing apparatus to perform operations comprising;

receiving a first query for a first user session;

determining that the first query refers to one or more tags in a first repository, the first repository associating respective identifiers to respective tags, each identifier representing a corresponding user session;

determining one or more particular identifiers associated with the one or more tags in the first repository;

retrieving particular contextual data associated with the determined particular identifiers in a second repository, the second repository associating respective identifiers to respective contextual data associated with corresponding user sessions represented by the respective identifiers; and

performing an action responsive to the first query based on the retrieved particular contextual data.

11. The system of claim 10, wherein the one or more tags include a time tag indicating a time earlier than the first user session, and wherein determining one or more particular identifiers associated with the one or more tags in the first repository comprises:

determining a plurality of candidate identifiers associated with the time tag in the first repository; and

selecting the one or more particular identifiers from the plurality of candidate identifiers based on remaining tags of the one or more tags.

12. The system of claim 10, wherein determining one or more particular identifiers comprises:

determining, for each tag of the tags, a plurality of respective candidate identifiers associated with the tag in the first repository; and

selecting the particular identifiers from the determined respective candidate identifiers by determining an overlap of the determined respective candidate identifiers, each identifier of the particular identifiers being associated with each tag of the tags in the first repository.

13. The system of claim 10, wherein the one or more tags comprise at least one of a session tag or an item tag, the session tag being associated with information about particular corresponding user sessions for the particular identifiers, the item tag being associated with at least one of particular queries in the particular corresponding user sessions or particular search results responsive to the particular queries.

14. The system of claim 13, wherein the operations further comprise determining that at least one of the particular queries or the particular search results refers to a particular item corresponding to the item tag, and wherein performing an action comprises performing the action responsive to the first query based on the determined particular item.

15. The system of claim 10, wherein the operations further comprise, before determining that the first query refers to one or more tags in a first repository, determining that the first query lacks additional information required for performing the action and that the first query is not associated with a previous query for the first user session.

16. The system of claim 10, wherein the operations further comprise:

receiving, from a user, a second query for a second user session;

determining that at least one of the second query or a second search result responsive to the second query refers to a second item in a database, the database associating respective items to respective item tags;

determining one or more second item tags associated with the second item in the database;

storing the second item tags in the first repository; and

associating the second item tags with a second identifier representing the second user session in the first repository.

17. The system of claim 16, wherein the operations further comprise:

determining one or more second session tags for the second user session, the second session tags including at least one of a timestamp for the second user session, a location of the user for the second user session, or an action associated with the user before the second user session;

storing the second session tags in the first repository; and

associating the second session tags with the second identifier in the first repository.

18. The system of claim 16, wherein the operations further comprise:

determining second contextual data for the second query, the second contextual data including the second query, the second search result, and metadata associated with the second query and the second search result;

storing the second contextual data in the second repository; and

associating the second contextual data with the second identifier in the second repository.

19. A non-transitory computer readable storage medium storing instructions executable by a data processing apparatus and upon such execution cause the data processing apparatus to perform operations comprising:

receiving a first query for a first user session;

determining that the first query refers to one or more tags in a first repository, the first repository associating respective identifiers to respective tags, each identifier representing a corresponding user session;

determining one or more particular identifiers associated with the one or more tags in the first repository;

retrieving particular contextual data associated with the determined particular identifiers in a second repository, the second repository associating respective identifiers to respective contextual data associated with corresponding user sessions represented by the respective identifiers; and

performing an action responsive to the first query based on the retrieved particular contextual data.

20. The computer readable storage medium of claim 19, wherein the one or more tags include a time tag indicating a time earlier than the first user session, and wherein determining one or more particular identifiers associated with the one or more tags in the first repository comprises:

determining a plurality of candidate identifiers associated with the time tag in the first repository; and

selecting the one or more particular identifiers from the plurality of candidate identifiers based on remaining tags of the one or more tags.

21. The computer readable storage medium of claim 19, wherein determining one or more particular identifiers comprises:

determining, for each tag of the tags, a plurality of respective candidate identifiers associated with the tag in the first repository; and

selecting the particular identifiers from the determined respective candidate identifiers by determining an overlap of the determined respective candidate identifiers, each identifier of the particular identifiers being associated with each tag of the tags in the first repository.

22. The computer readable storage medium of claim 19, wherein the one or more tags comprise at least one of a session tag or an item tag, the session tag being associated with information about particular corresponding user sessions for the particular identifiers, the item tag being associated with at least one of particular queries in the particular corresponding user sessions or particular search results responsive to the particular queries.

23. The computer readable storage medium of claim 22, wherein the operations further comprise determining that at least one of the particular queries or the particular search results refers to a particular item corresponding to the item tag, and wherein performing an action comprises performing the action responsive to the first query based on the determined particular item.

24. The computer readable storage medium of claim 19, wherein the operations further comprise, before determining that the first query refers to one or more tags in a first repository, determining that the first query lacks additional information required for performing the action and that the first query is not associated with a previous query for the first user session.

25. The computer readable storage medium of claim 19, wherein the operations further comprise:

receiving, from a user, a second query for a second user session;

determining that at least one of the second query or a second search result responsive to the second query refers to a second item in a database, the database associating respective items to respective item tags;

determining one or more second item tags associated with the second item in the database;

storing the second item tags in the first repository; and

associating the second item tags with a second identifier representing the second user session in the first repository.

26. The computer readable storage medium of claim 25, wherein the operations further comprise:

determining one or more second session tags for the second user session, the second session tags including at least one of a timestamp for the second user session, a location of the user for the second user session, or an action associated with the user before the second user session;

storing the second session tags in the first repository; and

associating the second session tags with the second identifier in the first repository.

27. The computer readable storage medium of claim 25, wherein the operations further comprise:

determining second contextual data for the second query, the second contextual data including the second query, the second search result, and metadata associated with the second query and the second search result;

storing the second contextual data in the second repository; and

associating the second contextual data with the second identifier in the second repository.

28. A method, comprising:

receiving, by one or more computers, a query for a user session;

determining, by the one or more computers, that the query refers to a time indicator, the time indicator indicating a time earlier than the user session;

determining, by the one or more computers, that the query refers to one or more item labels in an index repository, the index repository associating respective user sessions to respective time labels for the user sessions and respective item labels for queries in the user sessions;

determining, by the one or more computers, a plurality of candidate user sessions in the index repository, each candidate user session being associated with a respective time label corresponding to the time indicator;

determining, by the one or more computers, one or more particular user sessions associated with the one or more item labels within the determined candidate user sessions;

retrieving, by the one or more computers, particular contextual data associated with the determined particular user sessions in a data repository, the data repository associating respective user sessions to respective contextual data for the user sessions; and

performing, by the one or more computers, an action responsive to the query based on the retrieved particular contextual data.