Abstract: Example embodiments described herein disclose a specially configured device to receive and recognize enhanced user interactions through a graphical user interface. A user device may accordingly receive and display a set of search results, detect a user input entered via a touch-input device related to a single item from among the set of search results, determine a pressure exerted upon the touch-input device corresponding to the user input, and based on at least the pressure of the user input, select and execute an appropriate commerce action.

Abstract: A method and a system segmenting a user viewing listings in online publications to render the listing according to a rule received from a seller. For example, the system receives one or more listings submitted by a seller. The listing comprises one or more modifiable parameters. The system also receives a rule from the seller, the rule associated with a first listing of the one or more listings. A profile is associated with a user based on data collected about the user. The first listing is rendered to the user based on the profile associated with the user and the rule by modifying the one or more parameters.

Abstract: In various example embodiments, devices, systems, and methods for a waist measuring belt are provided. An example waist measuring belt is made up of a belt buckle frame with attachments for a belt strap. The belt further includes a position measuring module coupled to the belt buckle frame that measures an attachment position of a second end of the belt strap to the belt buckle frame. The belt also includes a tension measuring module coupled to the belt buckle frame that measures a tension through the belt buckle frame and the belt strap. A memory and a wireless communication module attached to the belt may be used to store measurements and communicate with a mobile device or server. In various embodiments, estimated user waist sizes over time using measured values and belt-specific data may be used to estimate a user's waist size and generate a waist size history.

Abstract: A user may submit a search query to a search engine, which may process the search query and generate a set of results. Previous actions of the user or of other users may be used to identify recommended search queries. The recommended search queries may be presented to the user along with the search results for the query. The location of the recommended search queries may be fixed, set by the user, or determined on a query-by-query basis. A user interface element operable to cause the presentation of one or more recommended search queries may be presented after a delay. After an additional or independent delay, the recommended search queries may be presented automatically. The delays may be fixed, set by the user, or determined on a query-by-query basis.

Abstract: A query segmentation system segments a search query into a query segment that identifies search results from items stored on a database. The query segmentation system receives a query string, and the query string comprises a plurality of tokens. A first token and a second token are identified from the plurality of tokens, and a first vector and a second vector associated with the first token and the second token respectively are determined. The query segmentation system determines whether to include the first and second tokens in a single query segment based on the first and second vectors. The single query segment is processed to identify the search results from the database.

Abstract: Understanding emojis in the context of online experiences is described. In at least some embodiments, text input is received and a vector representation of the text input is computed. Based on the vector representation, one or more emojis that correspond to the vector representation of the text input are ascertained and a response is formulated that includes at least one of the one or more emojis. In other embodiments, input from a client machine is received. The input includes at least one emoji. A computed vector representation of the emoji is used to look for vector representations of words or phrases that are close to the computed vector representation of the emoji. At least one of the words or phrases is selected and at least one task is performed using the selected word(s) or phrase(s).

Abstract: Systems and methods generate browse node pages. A combination of a category and one or more aspects is identified by analyzing historical user behavior data associated with a network-based system. A determination is made regarding whether existing browse node pages for the network-based system includes a browse node page for the identified combination. Each browse node page for the network-based system is accessible by a respective uniform resource location (URL) and provides a grouping of items in a respective category with one or more respective aspects. Based on a determination that a browse node page does not exist for the identified combination of the category and the one or more aspects, a browse node page for the identified combination is generated. The generated browse node page corresponds with a URL and provides items matching the identified combination of the category and the one or more aspects.

Abstract: Methods and system for item matching are described. In one embodiment, compatibility-based text for an item may be accessed. A compatibility identifier may be identified based on the compatibility-based text. The compatibility identifier may be associated with an item cluster. The compatibility identifier may be used to identify a plurality of matching items. A result may be provided based on identification of the plurality of matching items. Additional methods and systems are disclosed.

Abstract: Techniques and systems are described that leverage computer vision as part of search to expand functionality of a computing device available to a user and increase operational computational efficiency as well as efficiency in user interaction. In a first example, user interaction with items of digital content is monitored. Computer vision techniques are used to identify digital images in the digital content, objects within the digital images, and characteristics of those objects. This information is used to assign a user to a user segment of a user population which is then used to control output of subsequent digital content to the user, e.g., recommendations, digital marketing content, and so forth.

Abstract: A machine may be configured to access an image of an item described by a description of the item. The machine may determine an image quality score of the image based on an analysis of the image. A request for search results that pertain to the description may be received by the machine, and the machine may present a search result that references the item's image, based on its image quality score. Also, the machine may access images of items and descriptions of items and generate a set of most frequent text tokens included in the item descriptions. The machine may identify an image feature exhibited by an item's image and determine that a text token from the corresponding item description matches one of the most frequent text tokens. A data structure may be generated by the machine to correlate the identified image feature with the text token.

Abstract: Various methods and systems for processing web crawling queries using a web crawling prioritization model based on classification operation performance. A classification operation for organizing products in a product listing platform is accessed. A web crawling engine is accessed for the classification operation. The web crawling engine operates based on a web crawling query prioritization model that supports determining web crawling priority scores that indicate a predicted performance improvement for classification operations executed with known data and web crawled data to be retrieved from executing a web crawling query operation. Using the web crawling prioritization model, a web crawling priority score is determined for a web crawling query for the corresponding classification operation. The classification operation is associated with a product in a product listing platform and known data for the product.

Abstract: Gesture functionality is provided in a computing environment. In example embodiments, a gesture input is received. A style difference is identified between a known gesture input of a set of known gesture inputs and the received gesture input. The set of known gesture inputs is caused to be modified to include the style difference by updating a database that stores the set of known gesture inputs.

Abstract: Methods, systems, and articles of manufacture, including computer program products, are provided for image cleanup. In some embodiments, there is provide a method which may include subsampling a first image to a first level image of a multiscale transform; performing, based on a machine learning model, an identification of a foreground portion of the first level image and a background portion of the first level image; generating, based on the identification of the foreground portion and the background portion, a first mask; upscaling the first mask to a resolution corresponding to the first image depicting the foreground item; applying the upscaled first mask to the first image to form a second image depicting the foreground item; and providing the second image depicting the foreground item to a publication system. Related systems and articles of manufacture, including computer program products, are also provided.

Abstract: A system and method for mirroring traffic data is described. A traffic proxy samples traffic data between a client device and a first web server. The traffic data comprises requests from the client device and corresponding responses from the first web server. The sampled traffic data is encoded and relayed to a second web server. The second web server comprises an updated version of a web service that is operating at the first web server. Responses from the first web server are compared with responses from the second web server based on the requests in the encoded sampled traffic data. The differences between the responses from the first web server and the second web server is stored.

Abstract: A user may request a recommendation for an item from other users. Other users may respond to the request by recommending for or against items. Users may up-vote or down-vote the recommendations or responses of other users. The recommendations of the other users may be used to identify items and provide one or more recommendations to the requesting user. The original question and the responses may form a conversation thread. The recommendations may be inserted into the thread as responses, may be presented alongside the thread, or may be presented at the end of the thread. The recommendations may be based on one or more attributes of the user. The weight of the recommendations provided by other users may vary.

Abstract: Deployment of a modified service affects the functioning of other services that make use of the service. To address the problems that deployment of modified executable code can cause in other services, a dependency lock is placed on candidate code to prevent deployment until tests on the client services are successfully completed. Developers of client services that rely on a supplier service are enabled to place a dependency lock on the service. As a result, deployment of the supplier service is only allowed when tests of the client services complete successfully. The administrator of the service being deployed may control which other users are able to add dependency locks without giving those users other permissions such as the ability to modify the source code of the service, the ability to deploy the service, and the like.

Abstract: Systems and methods for on demand local commerce are described. One example embodiment includes a device gathering location information and product interest associated with clients and client devices. The system may use location information in determining that the first plurality of client devices are within a first geographic area during a first time period, and may further use the interest information in calculating an interest level for a first product. A threshold may be identified and used in determining that the interest level for the first product exceeds the threshold. When the calculated interest level exceeds the threshold, a local commerce action is initiated. In various embodiments, the local commerce action may be a live on demand auction at a particular location, an offer associated with a geofenced area, a sales location recommendation to a merchant, or any other such local commerce action.

Abstract: Computerized methods and systems for three-dimensional (3-D) displaying and navigating of search results are provided. In some embodiments, a criterion may be received from a user of a publication system. A database associated with the publication system may be searched based on the criterion. Search results retrieved from the database may be displayed on at least one side of a 3-D interface object. At least one control may be displayed proximate to the three 3-D interface object. The control may be used to navigate the 3-D interface object.

Abstract: An example embodiment includes a system server configured for social network-based inventory management. The system server includes processors and non-transitory computer-readable storage media communicatively coupled to the processors. The media store instructions that, in response to execution by the processors, cause the processors to perform operations. The operations include receiving category specifications and access category definitions for access categories. The access category definitions include relationship criteria for the access categories. The operations include identifying a relationship between a second user and a first user, comparing an identified relationship with the relationship criteria, and determining which of the access categories the second user is included based on the comparison.

Abstract: Sequential selections are presented by receiving an input on an active portion of a display of the computing device. While the input is received, a plurality of selections are sequentially displayed on the display. An indication is received that the input on the active portion of the display of the computing device has changed. In response to receiving the indication that the input has changed, the computing device stops presenting the plurality of selections and determines which selection of the plurality of selections was presented on the display when the input changed. The determined selection is then displayed.

Abstract: Methods, systems, and programs are presented for securing user-address information. A first memory is configured according to a first table that does not include information about user identifiers. Each entry in the first table includes a physical location identifier and information about a physical location. A second memory is configured according to a second table, where each entry in the second table includes the physical location identifier and an account identifier of a user for accessing a service. The first and second tables are configured to separate profile information from the address information of the user. Additionally, a firewall is configured to control access to the second memory. The firewall defines an authentication zone including the second memory but not the first memory, where access to the second memory by internal services is allowed and direct access by the user to the second memory is denied.

Abstract: Methods for face detection to address privacy in publishing image datasets is described. A method may include face classification in an online marketplace. A server system may receive, from a seller user device, a listing including an image for the online marketplace. The server system may classify, by at least one processor that implement a distribution-balance trained machine learning model, each human face candidate within the image as being one of a private human face or a non-private human face. The server system may receive, from a buyer user device, a search query that is mapped to the listing in the online marketplace. The server system may transmit, to the buyer user device, a query response including the listing that includes the image determined to not include any private human faces or obscures any private human faces within the image based on the classifying.

Abstract: An apparatus is provided including a processor, a memory, and a vehicle tracking portal. The vehicle tracking portal is configured to obtain vehicle identification information regarding a vehicle. Then diagnostic information regarding the vehicle can be obtained. Then, based on the vehicle identification and the diagnostic information, a recommended service for the vehicle can be determined. A user can then be alerted to the recommended service.

Abstract: In various exemplary embodiments, a system and an associated method to retrieve information related to marketplace items within an electronic environment are disclosed. A network architecture comprises a listing module to store the information related to the marketplace items. The related information includes one or more user-created items such as an image of a model with one or more tagged items worn by the model. Each of the one or more tagged items has associated descriptive metadata. A communications module is arranged to receive a query including search terms related to social fashion items from an end-user. A query engine is coupled to the communications module to match the search terms contained within the query to the associated descriptive metadata of the tagged items in the listing module. A processing module then displays to the end-user the model and the one or more tagged items.

Abstract: Deploying a point of presence (PoP) changes traffic flow to a cloud service provider. To determine if the PoP improves the performance of a cloud service to a client, actual network latencies between the client and the cloud service are measured. In more complex scenarios, multiple PoPs are used. The client sends multiple requests for the same content to the cloud provider. The requests are sent via different routes. The cloud provider serves the requests and collates the latency information. Based on the latency information, a route for a future request is selected, resources are allocated, or a user interface is presented. The process of determining the latency for content delivered by different routes may be repeated for content of different sizes. A future request is routed along the network path that provides the lowest latency for the data being requested.

Abstract: A screen is presented on a display of a user device, which includes an element occupying less than an entirety of the screen. A second screen is then presented on the display, which includes a second element occupying less than an entirety of the second screen. The user device receives an input that requests that a previously presented element be presented within the second screen next to enable comparison of the previously presented element with the second element. The user device presents, on the display of the user device and responsive to receiving the input, a contemporaneous view of the element next to the second element within the second screen.

Abstract: Methods and systems for displaying, to a user interface, categories of items for the user to select from for querying the system, in order to enable the system to return to the user images of items of the type desired by the user for possible purchase. The items categories of items can be presented to the user interface visually in silhouette form so that the user can select brand and the silhouette image of the type of item desired. Upon selection of the silhouette image, a query is sent to the system and images of the desired type of item are returned to the user interface for presentation to the user, along with certain attributes of the items.

Abstract: A system and method of identifying suspicious item-related features are disclosed. In some embodiments, a new item listing is received. The item listing may correspond to a request to list an item for sale on an e-commerce website. Item-related data for the item listing may be extracted. The item-related data can be used by a model to classify the new item listing. The model may be trained on data comprising identifications of which item listings in the sample of item listings are suspicious and identifications of which item listings in the sample of item listings are not suspicious may be received.

Abstract: Automatic workflow generation is described. One or more files containing code statements for accessing and modifying information in a destination database is received. The code statements are parsed from the one or more files and dependencies between the code statements are determined. A dependency graph is built by arranging the code statements according to the dependencies between the code statements. The dependency graph is partitioned by identifying at least one barrier code statement having an unclear dependency and dividing the dependency graph between code statements occurring prior to the at least one barrier code statement and code statements occurring after the at least one barrier code statement. Jobs are scheduled based on the partitioned dependency graph, and the code statements are annotated according to the scheduled jobs. A workflow is then automatically generated based on the annotated code statements.

Abstract: In some examples, a system comprises a memory device for storing instructions and a processor which executes instructions causing the system to perform operations comprising receiving an instruction to transfer a state of a first device to a second device, and packaging information relating to the state of the first device in a file. The packaging of the information relating to the state of the first device includes recording each application executing on the first device in a list maintained in the file, and transferring the file containing information relating to the state of the first device to the second device, either directly or indirectly based on an availability of connections between the first device and the second device. The file, when processed by the second device, causes the second device to reproduce the state of the first device. In some example, reproducing the state of the first device includes the second device downloading, from one or more of the locations, one or more of the applications.

Abstract: Methods, systems, and computer programs are presented for adding new features to a network service. A method includes receiving an image depicting an object of interest. A category set is determined for the object of interest and an image signature is generated for the image. Using the category set and the image signature, the method identifies a set of publications within a publication database and assigns a rank to each publication. The method causes presentation of the ranked list of publications at a computing device from which the image was received.

Abstract: A machine may be configured to perform A/B testing on mobile applications. For example, the machine receives an identifier of a user from a mobile device that requests a layout description of a user interface, determines the layout description that provides a configuration of one or more elements of the user interface according to an experiment variant associated with an experiment, and causes display of the one or more elements of the user interface on the mobile device based on the layout description.

Abstract: Methods and systems for improving memory utilization and access speed of database indexes are disclosed. A representation of attributes of items listed on a network-based publication system is identified. The representation includes a plurality of lists of the attributes as a sequence of serialized attributes, each of which stores an attribute identifier (ID) and data corresponding to the attribute identifier. A compact or compressed structure is used to represent the attribute IDs. This representation allows a reader application to quickly determine whether an attribute ID is present in the lists or not. Directly-addressable variable-length codes (DACs) are used, in an unconventional manner, to represent the data. By representing the data in this way, the index takes up less memory for certain types of data and the reader application is able to gain faster access to the index.

Abstract: Techniques for generating a digital wardrobe are presented herein. A transceiver can be configured to receive a request having a garment identifier and a user identifier. Additionally, an access module can be configured to access a first garment model, access a body model of the user corresponding to the user identifier, and access a second garment model corresponding to the user identifier. Furthermore, a processor can be configured by a garment simulation module to position the body model inside the first garment model and the second garment model, and calculate simulated forces based on the positioning. Moreover, a rendering module can be configured to generate an image of the garment models draped on the body model based on the calculated simulated forces. Subsequently, a display module can be configured to cause presentation of the generated image on a display of a device.

Abstract: A machine is configured to determine fashion preferences of users and to provide item recommendations based on the fashion preferences. For example, the machine accesses an indication of a fashion style of a user. The fashion style is determined based on automatically captured data pertaining to the user. The machine identifies, based on the fashion style, one or more fashion items from an inventory of fashion items. The machine generates one or more selectable user interface elements for inclusion in a user interface. The one or more user interface elements correspond to the one or more fashion items. The machine causes generation and display of the user interface that includes the one or more selectable user interface elements. A selection of a selectable user interface element results in display of a combination of an image of a particular fashion item and an image of an item worn by the user.

Abstract: Systems and methods change a user interface for the purpose of guiding a user in supplementing a product listing with an image to evidence the product's authenticity. Example embodiments include a machine-implemented method for accessing at least one database to retrieve an authenticity criterion mapped to a product and at least one reference image that depicts adequate detail of a product specimen to fulfill the authenticity criterion. The machine can further cause a user device to display the reference image to the user along with a suggestion that the user submit a candidate image depicting similar detail of the product. In some example embodiments, the method further includes retrieving the candidate image, confirming receipt of the candidate image, and displaying the candidate image, as well as adjusting a rank for a candidate specimen based on various factors.

Abstract: In various example embodiments, a system and method for computing a query feature score that can be used by a machine learning algorithm to rank search results is described. A query is received. The assigned probabilities for the arbitrary query is retrieved. The assigned probabilities is based on a probability model for a query feature. A score is computed for the query feature based on the assigned probabilities for the arbitrary query.

Abstract: Systems and methods for multi-signal fault analysis are described. The system receives signal message information, over a network, from a collection device comprised of a plurality of mobile devices including a first mobile device and a second mobile device that are associated with a first user. The first signal message information includes a first maintenance message including characterization information that was received by the first mobile device from a component that includes a sensor that operates to sense a first part that is assembled into a vehicle. The second signal message information includes signal information that was received by the second mobile device including an audio signal that a microphone in the second mobile device sensed. The system analyzes the multi-signal information to diagnose a problem and communicate a message to the first user with a diagnosis of the problem.

Abstract: A system is configured to detect a small, but meaningful, anomaly within one or more metrics associated with a platform. The system displays visuals of the metrics so that a user monitoring the platform can effectively notice a problem associated with the anomaly and take appropriate action to remediate the problem. A first visual includes a radar-based visual that renders an object representing data for a set of metrics being monitored. A second visual includes a tree map visual that includes sections where each section is associated with an attribute used to compose the set of metrics. Via the display of the visuals, the techniques provide an improved way of representing a large number of metrics (e.g., hundreds, thousands, etc.) being monitored for a platform. Moreover, the techniques are configured to expose useful information associated with the platform in a manner that can be effectively interpreted by a user.

Abstract: A system and method of an intelligent shopping infrastructure is provided. A data storage of current inventory from a plurality of merchants is maintained. User preferences that indicate an item affinity of a user are retrieved. Furthermore, a location of the user is detected. Using the detected location, available inventory, and item affinity, an available item from the current inventory of a merchant located within a predetermined distance to the location of the user that match the item affinity of the user is identified. The available item is presented on a user interface of a client device of the user.

Abstract: Example embodiments of the present disclosure include a system comprising a computer-readable storage medium storing at least one program and a computer-implemented method for providing a dynamic content delivery search system. In example embodiments, entry of a first keyword of a search string comprising a plurality of keywords is detected. The first keyword is identified after entry of the first keyword and prior to entry of a second keyword of the search string. A first set of matching results that match the identified first keyword is determined. Entry of the second keyword is detected and the second keyword identified. Using the second keyword, the first set of matching results is refined. The resulting search results are presented to a user.

Abstract: In an example, a text sentence comprising a plurality of words is obtained. Each of the plurality of words is passed through a deep compositional character-to-word model to encode character-level information of each of the plurality of words into a character-to-word expression. The character-to-word expressions are combined with pre-trained word embeddings. The combined character-to-word expressions and pre-trained word embeddings are fed into one or more bidirectional long short-term memories to learn contextual information for each of the plurality of words. Then, sequential conditional random fields are applied to the contextual information for each of the plurality of words.

Abstract: Aspects of the present disclosure involve an apparatus, systems, and methods for providing intelligent laundering alerts. Example embodiments involve an intelligent garment tag that may be affixed to garments, and may store and provide information about the garment to which it is affixed. The information stored thereon describes various aspects of the garment including color, fabric, and laundering information. The intelligent garment tags further include an alert component for providing laundering alerts (e.g., a flashing or colored light, a warning noise, or a vibration) based on, for example, garment color compatibility or laundering device (e.g., washing machine or clothes dryer) compatibility.

Abstract: Systems and methods for statistical dynamic geofencing are discussed. For example, a method for statistical dynamic geofencing can include operations such as receiving a location-based campaign request, analyzing demographic data, determining a geofence parameter, generating a geofence, and distributing location-aware advertisements. The location-based campaign request can include a list of points of interest (POIs) and a target demographic parameter. The demographic data can include data from geographic areas surrounding at least a portion of the POIs as well as data related to the target demographic parameter. The geofence can be generated based at least in part on the geofence parameter, where the geofence parameter directly affects either the size or shape of the geofence. The location-aware advertisements are distributed to a plurality of mobile devices determined to be within the geofence.

Abstract: Event data for an application execution is accessed from a table of logged events, the event data comprising a sequence, a hierarchy, and a start time and duration for each event. Dependency data for each event is also accessed to determine whether the start time for an event is dependent on the prior completion of at least one other event. A waterfall representation is then generated, the representation including an entry for each event in the sequence, with a start time and duration represented for each event. Based on the dependencies and hierarchy, it is determined, for each event with a start time that is later than the start time of an event which precedes it in the sequence, whether the event's start time is dependent on the prior completion of at least one preceding event. The start time for each event may then be advanced based on the determination.

Abstract: In an online marketplace, buyers and sellers engage in transactions. Some transactions are fraudulent. The online marketplace uses a fraud detection system that identifies fraudulent transactions before an account holder is defrauded. In some example embodiments of the systems and methods described herein, a fraud detection system uses information that is indirectly associated with a transaction to determine if the transaction is fraudulent. A user interface is provided that shows relationships between accounts and objects. In response to input received via the user interface, the fraud detection system performs an action on an account, an object, or a transaction.

Abstract: A video is provided to viewers using a web-based platform without restricted audio, such as a copyrighted soundtrack. To do so, a video comprising at least two audio layers is received. The audio layers can include separate and distinct audio layers or a mix of audio from separate sources. A restricted audio element is identified in a first audio layer and a speech element is identified in a second audio layer. A stitched text string can be generated by performing speech-to-text on both audio layers and removing the text corresponding to the restricted audio element of the second audio layer. When playing back the video, a portion of the video is muted based on the restricted audio element. A voice synthesizer is employed to generate audible sound during the muted portion using the stitched text string.

Abstract: Techniques for integrating a product model into a user supplied image are presented herein. A method is disclosed that includes receiving an image of a user space from a user, receiving one or more definitions that describe the user space, retrieving, based on search terms provided by the user, one or more items available at a networked marketplace that fit within the definitions of the user space, and generating a composite image by overlaying an image of one of the items on the image of the user space. The method further scales the image of the item according to the definition of the user space and the physical dimensions of the item, and depicts virtual guidelines indicating a current scale of the image of the item.

Abstract: Methods for enhancing or automating a review process of annotation tags for a set of tokens is described. A system may receive a list of tokens with associated tags for each token for a data set and may output any identified inconsistencies where a token is assigned at least two different tags. For example, instead of a human looking at each token individually or taking a sample set of the tags for review, the described techniques may look at all tokens with the associated tags in a set of data and may leverage reorganizing the tokens and associated tags to highlight errors to be fixed. Accordingly, the system may look across all tokens within an entire data set, while a review (e.g., by a human) of possible errors of the data set is limited to the highlighted errors flagged by the system.

Abstract: Methods and systems for improved categorization of queries are disclosed. In one aspect, first queries having query results limited to a particular category are identified. Second queries including a first query are also identified. For identified second queries, a pattern is generated based on the second query and the included first query, and a rank of the first query's particular category in results for the second query and a percentage of the second query's results having a category equivalent to the included first query's particular category are determined. The ranks and percentages are aggregated for matching patterns, and second patterns with aggregated ranks and percentages meeting a criterion are determined. Results for a third query are limited to a category equivalent to a particular category for a first query included in the third query, and then transmitted over a computer network to a client device.