Abstract: A portable electronic device with image capturing capabilities automatically or semi-automatically adjusts one or more image capturing parameters based on an input attribute of user engagement with a single-action haptic input mechanism. For example, the duration for which a single-action control button carried on a frame of the device is pressed automatically determines an image stabilization mode for on-board processing of captured image data. In one example, an above-threshold press duration automatically activates a less rigorous image stabilization mode, while button release before expiry of the threshold automatically activates a more rigorous photo stabilization mode.

Abstract: Systems and methods for distributing photo filters based on the location of the object in the image are described. A photo filter publication system detects that a client device in communication with the system has captured an image, identifies an object in the image, identifies a location of the object in the image, identifies an image overlay associated with the identified location and having object criteria satisfied by the identified object, and provides the identified image overlay to the client device.

Abstract: Systems, methods, devices, server computers, storage media, and instructions for prioritized device action triggered by device scan data are described. In one embodiment, a mobile device performs a method that involves executing a messaging application with an image capture interface and a scanning input. An associated scanning mode comprises capture of scan data from a plurality of input/output modules of the first client device, analyzes the scan data to identify one or more scan data patterns by matching at least a portion of the scan data against a set of data patterns, and selects a priority system action based on the results of the matching of the portion of the scan data against the set of data patterns. In some embodiments, the priority system action is selected based on a priority ranking for identified scan data types.

Abstract: Systems, methods, devices, server computers, storage media, and instructions for prioritized device action triggered by device scan data are described. In one embodiment, a mobile device performs a method that involves executing a messaging application with an image capture interface and a scanning input. An associated scanning mode comprises capture of scan data from a plurality of input/output modules of the first client device, analyzes the scan data to identify one or more scan data patterns by matching at least a portion of the scan data against a set of data patterns, and selects a priority system action based on the results of the matching of the portion of the scan data against the set of data patterns. In some embodiments, the priority system action is selected based on a priority ranking for identified scan data types.

Abstract: This patent provides a phone case. The backplate and side plate constitute the accommodating cavity of phone, and it is the amplifying cavity; Reinforcing rib is equipped at the edge of back plate. It may protrude to the inside and butt against the mobile phone frame. When the phone falls, the reinforcing rib or side plate separates the phone screen or phone body from the ground, cushions the impact of the ground and transfers the impact force to the phone frame, to avoid that the impact force directly acts on the phone screen and body. It has the great anti-falling effect.

Abstract: Methods and systems for training a machine learning model include training a machine learning model using training data. A status of the machine learning model's training is determined based on an accuracy curve of the machine learning model over the course of the training. Parameters of the training are adjusted based on the status. Training of the machine learning model is completed using the adjusted parameters.

Abstract: Technology is disclosed for transferring money anonymously between a sender and a recipient by use of a one-time use token. The method includes generating a one-time use token account for association with a one-time use token. The method includes generating the token and providing the token to the sender device in a machine-readable and transferable format. The method includes receiving a request to charge the one-time use token account after the token has been provided to the recipient device as a form of payment for a transaction. The method includes determining that an amount of the transaction is less than an amount of funds associated with the token and that the time of the transaction is within a time period for the use of the token. The method includes facilitating a transfer to the recipient account and deducting the amount of the transaction from a sender account.

Abstract: System and methods for broadcasting and recording live shopping broadcasts. A broadcast stream from a presenter (e.g., influencer) is received and distributed to viewers (e.g., shoppers). Additionally, a start identifier for a product is received from the presenter during the broadcast stream, product details for the product are distributed to the viewers upon receipt of the start identifier for the product, and an end identifier for the product is received from the presenter during the broadcast stream. The broadcast stream is recorded, and portions of the broadcast stream are associated with the product corresponding to a time period between the start identifier and the end identifier to generate a product broadcast file (e.g., for display and presentation) along with the product in an online marketplace.

Abstract: A portable electronic device with image capturing capabilities automatically or semi-automatically adjusts one or more image capturing parameters based on an input attribute of user engagement with a single-action haptic input mechanism. For example, the duration for which a single-action control button carried on a frame of the device is pressed automatically determines an image stabilization mode for on-board processing of captured image data. In one example, an above-threshold press duration automatically activates a less rigorous image stabilization mode, while button release before expiry of the threshold automatically activates a more rigorous photo stabilization mode.

Abstract: Systems and methods are presented that provide for receiving, at a media overlay publication system from a first client device, content to generate a media overlay, and generating the media overlay using the content received from the client device. The generated media overlay is stored in a database associated with the media overlay publication system and associated with a first characteristic of the content received from the first client device. The media overlay is provided to a second client device when a second characteristic of context data associated with the second client device correlates to the first characteristic for the media overlay, causing a display of the media overlay on a user interface of the second client device.

Abstract: Systems and methods are presented that provide for receiving, at a media overlay publication system from a first client device, content to generate a media overlay, and generating the media overlay using the content received from the client device. The generated media overlay is stored in a database associated with the media overlay publication system and associated with a first characteristic of the content received from the first client device. The media overlay is provided to a second client device when a second characteristic of context data associated with the second client device correlates to the first characteristic for the media overlay, causing a display of the media overlay on a user interface of the second client device.

Abstract: Techniques for unattended object detection using machine learning are disclosed. A machine learning policy, for use in identifying unattended objects in a captured image depicting one or more objects, is generated. The generating includes determining a level of occlusion in the captured image relating to the objects, and determining the machine learning policy based on the determined level of occlusion. A machine learning model is selected, from among a plurality of pre-defined machine learning models, based on the generated machine learning policy. An unattended object is detected in the captured image using the selected machine learning model.

Abstract: Systems and methods for distributing photo filters based on the location of the object in the image are described. A photo filter publication system detects that a client device in communication with the system has captured an image, identifies an object in the image, identifies a location of the object in the image, identifies an image overlay associated with the identified location and having object criteria satisfied by the identified object, and provides the identified image overlay to the client device.

Abstract: In an embodiment, a method performed by a payment service system (PSS) includes receiving from a first payment application associated with the PSS, a request to generate a token. The method includes identifying account information associated with the recipient. The method includes generating an anonymizing token associated with the recipient. The method includes storing an association between the account information of the recipient and the anonymizing token. The method includes providing for display of the anonymizing token within the first payment application. The anonymizing token anonymously embeds recipient information and the account information of the recipient.

Abstract: A service provider may receive item price information and/or point of sale (POS) transaction information from a plurality of merchant devices associated with a plurality of merchants. The service provider may categorize the plurality of merchants according to the types of items offered by the respective merchants, and may further categorize the merchants according to the locations at which they conduct business. The service provider may subsequently determine a price recommendation or other pricing information for a particular item offered by a particular merchant. A merchant device of the particular merchant may present the pricing information in a user interface that enables the merchant to view projected sales at various different price points. Further, the merchant may be able to specify one or more factors used for determining the recommend price, such as a desired business model, a desired clientele, a desired profit margin, or the like.

Abstract: An information processing method, a server, and a computer storage medium are provided. The method includes: generating a first information identification code according to first information, the first information representing an information source; providing the first information identification code to a terminal; receiving a first request from the terminal and allowing a terminal user of the terminal to follow an information service, the first request carrying the first information; and recording the first information and tracking and obtaining conversion information of the information source according to the first information.

Abstract: Systems and methods for distributing photo filters based on the location of the object in the image are described. A photo filter publication system detects that a client device in communication with the system has captured an image, identifies an object in the image, identifies a location of the object in the image, identifies an image overlay associated with the identified location and having object criteria satisfied by the identified object, and provides the identified image overlay to the client device.

Abstract: A portable electronic device with image capturing capabilities automatically or semi-automatically adjusts one or more image capturing parameters based on an input attribute of user engagement with a single-action haptic input mechanism. For example, the duration for which a single-action control button carried on a frame of the device is pressed automatically determines an image stabilization mode for on-board processing of captured image data. In one example, an above-threshold press duration automatically activates a less rigorous image stabilization mode, while button release before expiry of the threshold automatically activates a more rigorous photo stabilization mode.

Abstract: Techniques for unattended object detection using machine learning are disclosed. A machine learning policy, for use in identifying unattended objects in a captured image depicting one or more objects, is generated. The generating includes determining a level of occlusion in the captured image relating to the objects, and determining the machine learning policy based on the determined level of occlusion. A machine learning model is selected, from among a plurality of pre-defined machine learning models, based on the generated machine learning policy. An unattended object is detected in the captured image using the selected machine learning model.

Abstract: Systems and methods provide for a server computer to receive a request from a first device to share a plurality of media content items with a second device, the request including a unique identifier for each of the plurality of media content items. The server computer determines a subset of the plurality of media content items to be processed by the first device, generates instructions for processing the subset of the plurality of media content items by the first device, and sends the instructions to the first device. The server computer receives the processed media content items for the subset of the plurality of media content items that were processed by the first device, generates a message enabling access to processed media content items for the plurality of media content items, and sends the generated message to the second device.