CN-115735201-B - Method and system for presenting privacy-friendly query activity based on environmental signals

Abstract

Embodiments are directed to receiving a search query from a user, obtaining environmental signal(s) associated with an environment in which the user is located when the search query is received, processing the environmental signal(s) to generate privacy metrics associated with submission of the search query, obtaining additional environmental signal(s) associated with the environment in which the user is located when user input for a search interface is received, processing the additional environmental signal(s) to generate additional privacy metrics associated with the user input, selecting a subset of historical search queries from a superset of historical search queries for the user based at least on the privacy metrics and the additional privacy metrics, and in response to receiving user input for the search interface, causing the subset of historical search queries to be presented to the user.

Inventors

• Matthew Sheriff
• Victor Kelbner

Assignees

• 谷歌有限责任公司

Dates

Publication Date

20260508

Application Date

20211122

Priority Date

20201130

Claims (20)

1. 1. A method implemented by one or more processors, the method comprising: Receiving a search query via a client device of a user; Obtaining one or more environmental signals associated with an environment in which the user is located at a time when the search query is received, wherein the one or more environmental signals associated with the environment of the user include one or more of capturing audio data of environmental noise of the environment when the search query is received and capturing visual data of the environment when the search query is received; Processing the one or more environmental signals to generate a privacy metric associated with submission of the search query, wherein the privacy metric represents a metric of presence of a person that is not the user in an environment in which the user of the client device was located when the search query was received, and After generating the privacy metric associated with the submission of the search query: receiving user input for a search interface of the client device or an additional client device of the user; Obtaining one or more additional environmental signals associated with the environment in which the user is located at a subsequent time when the user input is received, wherein the subsequent time is after the time when the search query is received, wherein the one or more additional environmental signals associated with the environment of the user include one or more of capturing audio data of environmental noise of the environment when the user input is received and capturing visual data of the environment when the user input is received; processing the one or more additional environmental signals to generate an additional privacy metric associated with the user input, wherein the additional privacy metric represents a metric of presence of a person that is not the user in an environment in which the user of the client device is located when the user input is received; selecting a subset of the historical search queries from a superset of the user's historical search queries, wherein the selecting is based at least on the privacy metric and the additional privacy metric, and In response to receiving the user input for the search interface, causing the subset of the historical search queries to be presented to the user via the client device or the additional client device.
2. 2. The method of claim 1, wherein the one or more environmental signals associated with the environment of the user include location information corresponding to a location of the user when the search query is received.
3. 3. The method of claim 2, wherein the one or more environmental signals associated with the search query include at least the location information corresponding to the location of the user when the search query was received.
4. 4. The method of claim 3, wherein processing the one or more environmental signals to generate the privacy metric associated with the submission of the search query comprises: processing the location information corresponding to the location of the user when the search query is received using a machine learning model to generate an output associated with one or more types of the environment, Wherein generating the privacy metric associated with the submission of the search query is based on the output associated with one or more types of the environments.
5. 5. The method of claim 4, wherein the types of environments include one or more of public environments, semi-public environments, and private environments.
6. 6. The method of claim 2, wherein the one or more environmental signals associated with the search query include at least the audio data capturing the environmental noise of the environment at the time the search query was received.
7. 7. The method of claim 6, wherein processing the one or more environmental signals to generate the privacy metric associated with the submission of the search query comprises: The audio data capturing ambient noise of the environment when the search query is received is processed using a machine learning model to generate an output associated with one or more acoustic properties of the environment, Wherein generating the privacy metric associated with the submission of the search query is based on the output associated with the one or more acoustic attributes of the environment.
8. 8. The method of claim 7, wherein the one or more acoustic properties of the environment include one or more of a noise level of the environment and a classification of environmental noise detected in the environment.
9. 9. The method of claim 2, wherein the one or more environmental signals associated with the search query include at least capturing the visual data of the environment when the search query is received.
10. 10. The method of claim 9, wherein processing the one or more environmental signals to generate the privacy metric associated with the submission of the search query comprises: A machine learning model is used to process capturing the visual data of the environment when the search query is received to generate an output associated with one or more visual attributes of the environment, Wherein generating the privacy metric associated with the submission of the search query is based on the one or more visual attributes of the environment.
11. 11. The method of claim 10, wherein the one or more visual attributes of the environment include one or more of an indication of whether one or more additional users are present in the environment and an indication of one or more objects present in the environment.
12. 12. The method of claim 1, further comprising: comparing the privacy metric associated with the submission of the search query to the additional privacy metric associated with the user input to the search interface, and Based on the comparison, it is determined whether the additional privacy metric associated with the user input to the search interface matches the privacy metric associated with the submission of the search query.
13. 13. The method of claim 12, wherein selecting the subset of the historical search queries is in response to determining that the additional privacy metric associated with the user input to the search interface does not match the privacy metric associated with the submission of the search queries.
14. 14. The method of claim 13, wherein determining that the additional privacy metric associated with the user input for the search interface does not match the metric associated with the submission of the search query comprises determining that the additional privacy metric associated with the user input fails to satisfy a threshold privacy metric level of the privacy metric associated with the submission of the search query.
15. 15. The method of claim 12, further comprising: A selectable element is caused to be presented with the subset of the historical search queries, wherein the selectable element, when selected, causes one or more additional historical search queries not selected for inclusion in the subset to be presented to the user via the client device or the additional client device.
16. 16. The method of any one of claims 1-15, further comprising: Generating a prompt to solicit user selections associated with whether the search query should be included in the subset based on the privacy metric associated with the submission of the search query, and Causing the prompt to be presented to the user via the client device or the additional client device.
17. 17. A method implemented by one or more processors, the method comprising: Receiving a search query via a client device of a user; Processing a set of environmental signals associated with an environment in which the user is located at a time when the search query is received to generate a privacy metric associated with submission of the search query, wherein the set of environmental signals associated with the environment includes one or more of capturing audio data of environmental noise of the environment when the search query is received and capturing visual data of the environment when the search query is received, and wherein the privacy metric represents a measure of presence of a person that is not the user in the environment in which the user of the client device is located when the search query is received, and After generating the privacy metric associated with the submission of the search query: receiving user input for a search interface of the client device or an additional client device of the user; Processing an additional set of additional environmental signals associated with the environment in which the user is located at a subsequent time when the user input is received to generate an additional privacy metric associated with the user input, wherein the subsequent time is subsequent to the time, wherein the additional set of additional environmental signals associated with the environment includes one or more of capturing audio data of environmental noise of the environment when the user input is received and capturing visual data of the environment when the user input is received, and wherein the additional privacy metric represents a measure of presence of a person that is not the user in the environment in which the user of the client device is located when the user input is received; Responsive to receiving the user input for the search interface, causing a restricted historical search query to be presented via the client device or the additional client device based on the privacy metric and the additional privacy metric, wherein the restricted historical search query is restricted based on the privacy metric and the additional privacy metric; Receiving an additional search query via the client device or the additional client device, wherein the additional search query is an additional instance of the search query, and Processing a further additional set of environmental signals associated with the environment in which the user is located at a further subsequent time when the additional search query is received to modify the privacy metric associated with the submission of the search query, wherein the further subsequent time is subsequent to the time and the subsequent time.
18. 18. The method of claim 17, further comprising: After modifying privacy metrics associated with the submission of the search query: Receiving further user input for the search interface of the client device or the additional client device; Processing a further set of additional environment signals associated with the environment in which the user is located at a further subsequent time when the further user input is received to generate a further additional privacy metric associated with the user input, wherein the further subsequent time is subsequent to the time, the subsequent time and the further subsequent time, and In response to receiving the further user input for the search interface, causing an unrestricted historical search query to be presented via the client device or the additional client device, wherein the unrestricted historical search query is unrestricted based on the further additional privacy metric.
19. 19. The method of claim 18, wherein the limited history search query does not include the search query, and wherein the unrestricted history search query includes at least the search query.
20. 20. A system, comprising: At least one processor, and A memory storing instructions that, when executed, cause the at least one processor to perform the method of any one of claims 1 to 19.

Description

Method and system for presenting privacy-friendly query activity based on environmental signals Background A user can submit a search query via various client devices, such as a smart phone, tablet, wearable device, automobile system, standalone personal assistant device, and the like. Further, the search query can be submitted using various input modalities (e.g., verbal, touch, and/or typing). Search results responsive to the respective search queries can be provided (e.g., visually and/or audibly) as output at the respective client devices. The user can interact with the search interface to submit a search query. Historical search queries previously submitted by users are typically presented at a search interface as query suggestions prior to receiving the search query or as auto-completion suggestions for portions of the query entered by the user. However, for privacy reasons, a user may wish to have some historical search queries not presented at the search interface based on the context in which the user was located when interacting with the search interface. To ensure privacy, a user may selectively enter a private browsing mode or an anonymous mode to submit a search query. However, in these modes, the historical search queries may never be presented to the user as query suggestions, and the user may need to provide a greater amount of input to resubmit one of the historical search queries. Disclosure of Invention Embodiments disclosed herein are directed to generating privacy metrics associated with user input received at a user's client device, and adapting presentation of historical search queries based on the privacy metrics. The privacy metric can represent a privacy level of an environment in which a user of the client device is located when user input is received for the search interface. The privacy metric can be determined based on processing one or more environmental signals associated with an environment in which a user of the client device is located when the user input is received. The one or more environmental signals can include, for example, location information corresponding to a location of a user when the search query is received, audio data that captures environmental noise of the environment when the search query is received, and/or visual data that captures the environment when the search query is received. The privacy metric can additionally or alternatively be determined based on one or more terms of the received search query. Further, privacy metrics associated with user input to the search interface can be compared to a plurality of corresponding privacy metrics associated with the user's historical search queries to determine whether the historical search queries should be presented to the user. For example, assume that a user of a client device submits a search query for "symptoms of infectious disease # 19" at a search interface of the client device. Further assume that when a user submits a search query, one or more environmental signals indicate that the user is located in the home and that no other person is in the home. In this example, the privacy metric indicating the environment in which the user was located when the search query was submitted may be highly private. Additionally or alternatively, the privacy metric may indicate that the search query may be highly private based on one or more terms of the search query including terms related to the medical condition (e.g., a request for symptoms of a disease). Further, assume that the user is then commuted to work via the train and detects user input to the search interface of the client device. Further assume that when a user submits a search query, one or more environmental signals indicate that the user is commuting to work and that there are others on the train. In this example, the additional privacy metric that indicates the environment in which the user was located when the search query was submitted is public. As a result, the subset of historical search queries presented to the user in response to receiving user input for the search interface may exclude search queries that are "symptoms of infectious disease #19," and may exclude any other historical search queries associated with corresponding privacy metrics that indicate that the environment in which the user was located was likely privacy when the historical search queries were submitted. In various implementations, the one or more environmental signals can be processed using respective Machine Learning (ML) model(s), and privacy metrics can be generated based on output generated across the ML model(s). For example, in embodiments in which the one or more environmental signals include location information corresponding to a user's location when the search query is received, the location information can be processed using the classification model(s) to generate output associated with one or more types of environments (e.g., public-type environments, se