Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for inferring the geographical location of devices. One of the methods includes obtaining device information associated with a first device located at a respective geographical location, the device information including a plurality of events obtained from the first device, wherein least a one event of the obtained events contains ambiguous geographical location information that can be interpreted as relating to one of two or more alternative geographical locations; identifying the at least one event containing ambiguous geographical location information; and determining an estimate of the geographical location of the first device based at least in part on the device information taking into account that the at least one identified event contains ambiguous geographical location information.

Abstract: The specification relates to a client device utilizing an unintentional-selection module that disambiguates selection events for temporally proximate content. The client device records time stamps indicating a time a dynamic list is first presented and instances when the dynamic list is updated. An input selection indicating that a suggested search query has been chosen from the dynamic list of search suggestions is received and a time stamp for the input selection is recorded. A determination is made to see if the input selection is an unintentional selection. The input selection is determined as the unintentional selection when a difference between a time stamp for presenting a most recent dynamic list update and the time stamp of the input selection satisfies a user-specific threshold. The user-specific threshold is calculated with a machine learning system using user-specific latency times as training data.

Abstract: Methods, systems and apparatus for identifying modified images based on seed images that are known to be modified images. In an aspect, a method includes accessing data identifying a set of first seed images; for each first seed image, determining a respective first set of similar images from images in an image corpus, each similar image having a visual similarity score that is a measure of visual similarity of the similar image to the first seed image based on the image content of the similar image and the first seed image that satisfies a first seed image similarity threshold; and for each similar image in each respective first set of similar images, attributing to the similar image signal data of each first seed image for which the similar image has a respective visual similarity score satisfying the first seed image similarity threshold.

Abstract: Systems, methods and computer storage apparatuses for synthesizing terrain elevations under overpasses are described herein. An embodiment includes identifying one or more spans across an overpass in an overpasses model, where the overpasses model includes information for one or more overpasses and respective locations and widths of the spans. The embodiment associates one or more terrain elevation values with the one or more identified spans, where the terrain elevation values can be included in an elevation model corresponding to the overpasses model. The embodiment further includes interpolating terrain elevation values for one or more points across the identified spans and updating the elevation model with the interpolated terrain elevation values.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for providing query suggestions. One of the methods includes receiving query log data that identifies a query and a location where the query was issued. A point of interest near the location where the query was issued is identified. A category of the point of interest near the location where the query was issued is identified. The query is associated with the category of the point of interest near the location where the query was issued.

Abstract: Systems and methods for summarizing a guidebook result are provided. An exemplary system includes a transit trip identification module, a cost function generation module, a service window identification module, a daytime interval conversion module, and a guidebook summarization module. An exemplary method includes identifying a plurality of service windows comprising intervals of time over which the available transit trips satisfy a quality criterion.

Abstract: A computer-implemented method for assessing ratings using tip patterns is provided. The method includes obtaining tip information comprising a ratio of a tip amount associated with a bill for a service, the bill being associated with a service provider, generating a rating score based on the tip information and reference tip information, and generating an aggregate score associated with the service provider, based on the rating score. Systems and machine-readable media are also provided.

Abstract: Methods, systems, and apparatus for providing customized content in knowledge panels. In one aspect, a method includes receiving input from a user device; identifying, based on historical data describing user interactions for the user device, a topic of interest; identifying an entity responsive to the input; identifying eligible content items that are eligible for presentation in a knowledge panel that is to be presented with results responsive to the input, wherein at least one eligible content item is obtained from a first resource and at least one second eligible content item is obtained from a second resource; ranking the eligible content items based, in part, on the topic of interest; selecting one or more of the eligible content items based on the rankings; and providing, to the user device, data that causes each selected eligible content item to be presented in the knowledge panel in response to the input.

Abstract: The disclosed subject matter relates to computer implemented methods for logging graphical user interface events. In one aspect, a method includes receiving from a server, an identifier for a user interface element of a graphical user interface. The method further includes detecting a user interface event associated with the user interface element. The user interface event associated with the user interface element can be an operation performed on the user interface element or an effect caused by the operation performed on the user interface element. The method further includes entering into a log, the identifier for the user interface element and the user interface event associated with the user interface element. The method further includes sending the log to the server.

Abstract: Methods, systems and apparatus for identifying modified images based on visual dissimilarity to a first image. In an aspect, a method includes determining, for each of a first image and a second image, a respective set of local image feature descriptions; determining one or more unmatched regions of the images that include unmatched image features and that correspond to one or more same respective regions in both the first image and the second image; determining, for each of the one or more unmatched regions of the images, a modification measure based on the image data corresponding to the unmatched region in the first image and the image data corresponding to the unmatched region in the second image; and determining that the second image is a modification of the first image when one of the modification measures meets a modification measure threshold.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining image search results. One of the methods includes receiving a query from a client device and determining that the query is a recurrent query, wherein a recurrent query is a query that is predominantly received from a particular geographic region during a particular time period. The location of the client device is determined based at least in part on the particular geographic region.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for providing dynamic search results. One of the methods includes providing an ordered plurality of first search results to a client device at a first point in time wherein the first search results are responsive to a first query received from the client device. At a second point in time following the first point in time, a lack of selection of any of the first search results by a user of the client device. In response to the detecting, providing the second search results to the client device before selection of any of the first search results by the user of the client device.

Abstract: Indoor navigation may be utilized in combination with predetermined location goals to guide consumers to places they do or might want to visit in a retail establishment or other space. The user may be provided with assistance in locating items on a predetermined list, such as by checking map information on the user's device and by interacting with one or more location detection devices. Statistics related to the user's shopping experience may also be provided to the user. The user can optionally allow the store to review the list, statistics, or other information so the store can analyze the presentation, how the items were found, and even what the user actually purchased.

Abstract: Systems and techniques are provided for dynamically generating a list of selectable options based on one or more applicable factors, which include visual representations of input components that can be used to select from among the options. For example, an icon corresponding to an input component may be displayed proximate to a respective selectable option such that activating the input component elects the selectable option. Additionally, each icon may be visually similar to its respective input component.

Abstract: A system is configured to receive a search query; obtain search results, based on the search query, that identify documents relevant to the search query; identify image attributes associated with one or more of the documents; obtain classification metrics that include information for determining a measure of image intent associated with the one or more of the documents; determine the measure of image intent, associated with the one or more of the documents, based on the image attributes and the classification metrics; determine whether the measure of image intent satisfies a threshold; generate a search results document that selectively includes the image results or the search results based on whether the measure of image intent satisfies the threshold; and provide the search results document.

Abstract: Aspects of the present disclosure relates generally to deciding which part of a panoramic image is most important and using that as a reference point for displaying the panoramic image to user. For example, a 360 degree panoramic image associated with orientation and location information may be identified. Related images, for example, in content and location may also be identified. The related images may be projected as points on a unit circle representing the orientations of the panoramic image. The point farthest from an average location of the points may be removed until the average location of the points is at least a minimum distance from the center of the circle. When this occurs, an angular location of the average location relative to the circle may be identified as a reference orientation. The reference orientation may be associated with the panoramic image, and the association may be stored in memory.

Abstract: Techniques for determining one or more preferred languages for a user are provided. The preferred languages may be determined based upon a set of language indicators. The language indicators are analyzed using, for example, rules-based techniques, clustering, language classifiers, and the like, or combinations thereof. Language indicators can include or be derived from information about the user's behavior, location, preferences, social connections, or other data related to the user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying and ranking entities for reference as search results. In one aspect, a method includes receiving data identifying resources that are relevant to a query. The data for each resource can include a relevance score, a list of references to entity realizations included in the resource, and for each reference to an entity realization in the list, one or more resource reference scores. For each resource and for each reference to an entity realization in the resource, a partial score for the reference can be determined from the resource reference scores for the reference and the relevance score for the resource. For each reference to an entity realization, a reference score for the reference is determined from each of the partial scores for the reference. Search results can be ranked based on the reference scores.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for displaying search results referencing resources of two different types. In an aspect, a search system receives a search query for a search of a first resources. The search system determines a second resource score for the search query. The second resource score is measure of relatedness of the query to the second resources and is independent of a search property ratio of the query. If the second resource score meets a threshold, then the search system conducts a full search of second resources in addition to the search of the first resources.

Abstract: A computing device is configured to provide a search results document that includes information regarding images that have been identified as relevant to a search query, and receive a request to access an image provided in the search results document. The image may be associated with a document that includes the image. The computing device is configured to determine, based on the request, whether the document is image-centric with respect to the image, and selectively provide, based on whether the document is image-centric with respect to the image, an image overlay document corresponding to the image or the document associated with the image. The image overlay document may be provided when the document is not image-centric with respect to the image, and the document may be provided when the document is image-centric with respect to the image.