Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for automatic image selection for online product catalogs. An image selection system gathers feature data for images of an item included in listings posted to an online marketplace. The image selection system uses the feature data as input in a machine learning model to determine probability scores indicating an estimated probability that each image is suitable to represent the item. The machine learning model is trained based on a set of training images of the item that have been labeled to indicate whether they are suitable to represent the image. The image selection system compares the probability scores and selects an image to represent the item as a stock image based on the comparison.

Abstract: Systems and methods are provided for extracting entities from received speech. The systems and methods perform operations comprising receiving an audio file comprising speech input and processing, by a speech recognition engine, the audio file comprising the speech input to generate an initial character-based representation of the speech input. The operations further comprise processing, by an entity extractor, the initial character-based representation of the speech input to generate an estimated set of entities of the speech input. The operations further comprise generating, by the speech recognition engine, a textual representation of the speech input based on the estimated set of entities of the speech input.

Abstract: Systems and methods are provided for performing speech to intent classification. The systems and methods perform operations comprising: receiving an audio file comprising speech input; processing, by a speech recognition engine, the audio file comprising the speech input to generate an initial character-based representation of the speech input; processing, by an intent classifier, the initial character-based representation of the speech input to generate an estimated intent of the speech input; and generating, by the speech recognition engine, a textual representation of the speech input based on the estimated intent of the speech input.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for automatic image selection for online product catalogs. An image selection system gathers feature data for images of an item included in listings posted to an online marketplace. The image selection system uses the feature data as input in a machine learning model to determine probability scores indicating an estimated probability that each image is suitable to represent the item. The machine learning model is trained based on a set of training images of the item that have been labeled to indicate whether they are suitable to represent the image. The image selection system compares the probability scores and selects an image to represent the item as a stock image based on the comparison.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for automatic image selection for online product catalogs. An image selection system gathers feature data for images of an item included in listings posted to an online marketplace. The image selection system uses the feature data as input in a machine learning model to determine probability scores indicating an estimated probability that each image is suitable to represent the item. The machine learning model is trained based on a set of training images of the item that have been labeled to indicate whether they are suitable to represent the image. The image selection system compares the probability scores and selects an image to represent the item as a stock image based on the comparison.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for automatic image selection for online product catalogs. An image selection system gathers feature data for images of an item included in listings posted to an online marketplace. The image selection system uses the feature data as input in a machine learning model to determine probability scores indicating an estimated probability that each image is suitable to represent the item. The machine learning model is trained based on a set of training images of the item that have been labeled to indicate whether they are suitable to represent the image. The image selection system compares the probability scores and selects an image to represent the item as a stock image based on the comparison.

Abstract: A granular encryption database management system characterized by hierarchical internal key management using asymmetric encryption of the user's keys, which are stored within a (local) encryption key table. Data is encrypted, decrypted, stored, and accessed from rows within the database (hereinafter ‘instances’). Instances are ordered in categories called Types. Instances are encrypted with Instance keys. All instances of the same type have their Instance keys generated by means of a hash function of their common Type's key, while Type keys are generated from the key of the higher category which is often the Master key of the whole system.

Abstract: Systems and methods may implement database technology using distributed logical unit repositories (DLURs). DLURs may use a database structure related to a specific logical unit such as a customer, employee, or the like. Information used in DLUR database structures may include data, database structure, functions, and the like that helps form a complete model for a logical unit. In one embodiment, queries to a system concerning entities can be answered immediately by accessing a database using DLURs, which obviates the need to consult a number of databases in parallel and greatly reduces memory and time required to provide the requested information.

Abstract: A granular encryption database management system characterized by hierarchical internal key management using asymmetric encryption of the user's keys, which are stored within a (local) encryption key table. Data is encrypted, decrypted, stored, and accessed from rows within the database (hereinafter ‘instances’). Instances are ordered in categories called Types. Instances are encrypted with Instance keys. All instances of the same type have their Instance keys generated by means of a hash function of their common Type's key, while Type keys are generated from the key of the higher category which is often the Master key of the whole system.

Abstract: The invention comprises systems and methods for implementation of database technology using ‘Distributed logical unit repositories’ (DLUR). This is a new type of database which contains information and database structure related to a specific logical unit such as a customer, employee or the like. The information comprises data, database structure, functions, and any other data necessary to form a complete model of the information concerning the logical unit. Queries concerning entities can then be answered immediately by accessing this database, obviating the step of consulting a number of databases in parallel and greatly reducing memory and time required.

Abstract: A method of operating an appliance operating the ANDROID operating system in which code of a calling application is operative to send to the ANDROID operating system or other application an Intent object. The Intent object encapsulates an “Activity Action” string and optional auxiliary data relating to the Intent object. The user is presented with a user interface comprising not currently installed applications capable of handling the Intent. Upon user selection of an application not currently installed on the appliance operating the ANDROID operating system, the selected application is installed on the appliance. Subsequently the matching activity in the installed application is launched. Afterwards the Intent is passed to the Activity, capable of handling the aforementioned Intent, in the now launched application.

Abstract: A method of operating an Android appliance in which code of a calling application is operative to send an Android operating system or other application an Intent object. The Intent object encapsulates a “Activity Action” string and optional auxiliary data relating to the Intent object. The user is presented with a user interface of comprising not currently installed applications capable of handling the Intent. Upon user selection of an application not currently installed on the Android appliance, the selected application is installed on the Android appliance. Subsequently the matching activity in the installed application is launched. Afterwards the Intent is passed to the Activity, capable of handling the aforementioned Intent, in the now launched application.

Abstract: A computer implemented method for indexing multimedia vectors and for searching and retrieving a query vector using a locality sensitive hashing. Indexing is performed by calculating hash codes from the multimedia vectors using several hash functions. Each hash code is a different subset of the entries in the hash vector. The method utilizes the structure of the hash vector space in order to define the hash codes in a way that improves the retrieval efficiency. Retrieval is performed by applying the hash functions to a query vector and measuring the distances between the query vector and multimedia vectors with hash codes identical to the hash codes of the query vector.