Abstract: The present embodiments relate to automated memory creation and retrieval from moment content items. In some implementations, the automated memory creation and retrieval system can obtain moment content items from user-designated sources with a single user perspective or multiple user perspectives. The moment content items can be assigned tags and arranged in chronological order. The arranged moment content items can be clustered into memory content items based on clustering conditions. Once memory content items are created, they can be arranged into a memory hierarchy made up of connected nodes. In some implementations, the memory content items are also linked together based on similarity in various dimensions in a memory graph. The automated memory creation and retrieval system can receive search criteria for memories from a user interface and provide the user with memories from matched nodes in the memory hierarchy or linked memories in the memory graph.

Abstract: A conversation augmentation system can automatically augment a conversation with content items based on natural language from the conversation. The conversation augmentation system can select content items to add to the conversation based on determined user “intents” generated using machine learning models. The conversation augmentation system can generate intents for natural language from various sources, such as video chats, audio conversations, textual conversations, virtual reality environments, etc. The conversation augmentation system can identify constraints for mapping the intents to content items or context signals for selecting appropriate content items. In various implementations, the conversation augmentation system can add selected content items to a storyline the conversation describes or can augment a platform in which an unstructured conversation is occurring.

Abstract: A conversation augmentation system can automatically augment a conversation with content items based on natural language from the conversation. The conversation augmentation system can select content items to add to the conversation based on determined user “intents” generated using machine learning models. The conversation augmentation system can generate intents for natural language from various sources, such as video chats, audio conversations, textual conversations, virtual reality environments, etc. The conversation augmentation system can identify constraints for mapping the intents to content items or context signals for selecting appropriate content items. In various implementations, the conversation augmentation system can add selected content items to a storyline the conversation describes or can augment a platform in which an unstructured conversation is occurring.

Abstract: A conversation augmentation system can automatically augment a conversation with content items based on natural language from the conversation. The conversation augmentation system can select content items to add to the conversation based on determined user “intents” generated using machine learning models. The conversation augmentation system can generate intents for natural language from various sources, such as video chats, audio conversations, textual conversations, virtual reality environments, etc. The conversation augmentation system can identify constraints for mapping the intents to content items or context signals for selecting appropriate content items. In various implementations, the conversation augmentation system can add selected content items to a storyline the conversation describes or can augment a platform in which an unstructured conversation is occurring.

Abstract: An automatic memory system can automatically identify and present content items that match a user's natural language (NL) input. The automatic memory system can compute a match score between the NL input and each of multiple potential memory content items. The automatic memory system can compute the match score using a variety of algorithms and/or machine learning models such as an image/NL matching process to get a first match score, a tag matching process to get a second match score, and/or a combination match score from the first and second match scores. The automatic memory system can select one or more of the content items with the highest match score(s). The automatic memory system can provide the selected content items, such as by suggesting them to the NL providing user, automatically displaying or playing them, inserting them into the conversation thread, etc.

Abstract: A conversation augmentation system can automatically augment a conversation with content items based on natural language from the conversation. The conversation augmentation system can select content items to add to the conversation based on determined user “intents” generated using machine learning models. The conversation augmentation system can generate intents for natural language from various sources, such as video chats, audio conversations, textual conversations, virtual reality environments, etc. The conversation augmentation system can identify constraints for mapping the intents to content items or context signals for selecting appropriate content items. In various implementations, the conversation augmentation system can add selected content items to a storyline the conversation describes or can augment a platform in which an unstructured conversation is occurring.

Abstract: A conversation augmentation system can automatically augment a conversation with content items based on natural language from the conversation. The conversation augmentation system can select content items to add to the conversation based on determined user “intents” generated using machine learning models. The conversation augmentation system can generate intents for natural language from various sources, such as video chats, audio conversations, textual conversations, virtual reality environments, etc. The conversation augmentation system can identify constraints for mapping the intents to content items or context signals for selecting appropriate content items. In various implementations, the conversation augmentation system can add selected content items to a storyline the conversation describes or can augment a platform in which an unstructured conversation is occurring.

Abstract: The present embodiments relate to automated memory creation and retrieval from moment content items. In some implementations, the automated memory creation and retrieval system can obtain moment content items from user-designated sources with a single user perspective or multiple user perspectives. The moment content items can be assigned tags and arranged in chronological order. The arranged moment content items can be clustered into memory content items based on clustering conditions. Once memory content items are created, they can be arranged into a memory hierarchy made up of connected nodes. In some implementations, the memory content items are also linked together based on similarity in various dimensions in a memory graph. The automated memory creation and retrieval system can receive search criteria for memories from a user interface and provide the user with memories from matched nodes in the memory hierarchy or linked memories in the memory graph.

Abstract: The present embodiments relate to automated memory creation and retrieval from moment content items. In some implementations, the automated memory creation and retrieval system can obtain moment content items from user-designated sources with a single user perspective or multiple user perspectives. The moment content items can be assigned tags and arranged in chronological order. The arranged moment content items can be clustered into memory content items based on clustering conditions. Once memory content items are created, they can be arranged into a memory hierarchy made up of connected nodes. In some implementations, the memory content items are also linked together based on similarity in various dimensions in a memory graph. The automated memory creation and retrieval system can receive search criteria for memories from a user interface and provide the user with memories from matched nodes in the memory hierarchy or linked memories in the memory graph.

Abstract: The present embodiments relate to automated memory creation and retrieval from moment content items. In some implementations, the automated memory creation and retrieval system can obtain moment content items from user-designated sources with a single user perspective or multiple user perspectives. The moment content items can be assigned tags and arranged in chronological order. The arranged moment content items can be clustered into memory content items based on clustering conditions. Once memory content items are created, they can be arranged into a memory hierarchy made up of connected nodes. In some implementations, the memory content items are also linked together based on similarity in various dimensions in a memory graph. The automated memory creation and retrieval system can receive search criteria for memories from a user interface and provide the user with memories from matched nodes in the memory hierarchy or linked memories in the memory graph.

Abstract: An automatic memory system can automatically identify and present content items that match a user's natural language (NL) input. The automatic memory system can compute a match score between the NL input and each of multiple potential memory content items. The automatic memory system can compute the match score using a variety of algorithms and/or machine learning models such as an image/NL matching process to get a first match score, a tag matching process to get a second match score, and/or a combination match score from the first and second match scores. The automatic memory system can select one or more of the content items with the highest match score(s). The automatic memory system can provide the selected content items, such as by suggesting them to the NL providing user, automatically displaying or playing them, inserting them into the conversation thread, etc.

Abstract: In one embodiment, a method includes sending information configured to render a virtual space on a display device associated with a first user, wherein the virtual space provides a virtual experience to the first user; receiving a pause input from the first user to enter a pause mode; and causing the first user to enter the pause mode, wherein the virtual experience within the virtual space is paused for the first user.

Abstract: In one embodiment, a method includes sending information configured to render a virtual space on a display device associated with a first user, the virtual space comprising a virtual room; receiving an input from a first user selecting a particular virtual object; calculating a score for a set of interactive-surface types, the score being based on a current context, wherein the current context is based on information associated with the virtual object; selecting, from the set of interactive-surface types, one of the interactive-surface types based on the selected interactive-surface type having a score greater than a threshold score; and sending information configured to render an interactive surface that is of the selected interactive-surface type.

Abstract: In one embodiment, a method includes sending information configured to render a virtual space on a display device; receiving a first input from a first controller device, wherein the first controller device is associated with a first location on a body of a user; sending information configured to render a user interface comprising a menu of items, the menu of items comprising one or more interactive elements; receiving a second input from a second controller device, wherein the second controller device is associated with a second location on the body of the user, and wherein the second input indicates a selection of a particular interactive element; and sending information configured to render a response to the selection of the particular interactive element on a display device associated with the user.

Abstract: In one embodiment, a method includes receiving first visual information associated with at least a portion of a 360-degree perspective; determining that the first visual information is not sufficient to render a complete 360-degree perspective on a display device associated with a first user; receiving second visual information, wherein the second visual information comprises information configured to render a display of one or more videos from one or more second users; and sending rendering information, wherein the rendering information comprises information configured to render a unified 360-degree perspective on the display device, wherein: a first portion of the unified 360-degree perspective is based on the first visual information, and a second portion of the unified 360-degree perspective is based on the second visual information.

Abstract: In one embodiment, a method includes receiving first visual information associated with at least a portion of a 360-degree perspective; determining that the first visual information is not sufficient to render a complete 360-degree perspective on a display device associated with a first user; receiving second visual information, wherein the second visual information comprises information configured to render a display of one or more videos from one or more second users; and sending rendering information, wherein the rendering information comprises information configured to render a unified 360-degree perspective on the display device, wherein: a first portion of the unified 360-degree perspective is based on the first visual information, and a second portion of the unified 360-degree perspective is based on the second visual information.

Abstract: In one embodiment, a method includes receiving first visual information associated with at least a portion of a 360-degree perspective; determining that the first visual information is not sufficient to render a complete 360-degree perspective on a display device associated with the first user; retrieving second visual information; and sending information configured to render a unified 360-degree perspective on the display device, wherein: a first portion of the unified 360-degree perspective is based on the first visual information, and a second portion of the unified 360-degree perspective is based on the second visual information.

Abstract: In one embodiment, a method includes sending information configured to render a virtual space on a display device, the virtual space comprising a virtual representation of a first body part of a first user; sending information configured to render a first virtual device that is associated with the representation of the first body part, the first virtual device comprising a display region; receiving a notification item associated with the first user; and sending information configured to render a representation of the notification item in the display region of the first virtual device.

Abstract: In one embodiment, a method includes sending information configured to render a virtual space on a display device associated with a first user, the virtual space comprising a virtual room; receiving an input from a first user selecting a particular virtual object; calculating a score for a set of interactive-surface types, the score being based on a current context, wherein the current context is based on information associated with the virtual object; selecting, from the set of interactive-surface types, one of the interactive-surface types based on the selected interactive-surface type having a score greater than a threshold score; and sending information configured to render an interactive surface that is of the selected interactive-surface type.