Abstract: Embodiments are directed to a machine learning recommendation system. The system receives a user query for generating a recommendation for one or more items with an explanation associated with recommending the one or more items. The system obtains first features of at least one user and second features of a set of items. The system provides the first features and the second features to a first machine learning network for determining a predicted score for an item. The system provides a portion of the first features and a portion of the second features to second machine learning networks for determining explainability scores for an item and generating corresponding explanation narratives. The system provides the recommendation for one or more items and corresponding explanation narratives based on ranking predicted scores and explainability scores for the items.

Abstract: Embodiments described herein provide systems, methods, and devices for pre-training a multimodal encoder-decoder (MED) model for vision-language tasks. A method may include encoding, by an image encoder of the MED, an image into an image representation; encoding, by a text encoder of the MED, a text into a text representation; generating, by an image-grounded text encoder of the MED, a multimodal representation based on the image representation and the text; generating, by an image-grounded text decoder of the MED, a predicted text based on the image representation and the text; generating, through an image-text matching (ITM) head, a binary classification indicating whether the image and the text are a match; computing a first loss, ITM loss, and third loss based on the image representation, text representation, binary classification, predicted text and text; jointly updating the MED based on the first loss, the second loss and the third loss.

Abstract: Centralized channel management of a set group-based communication system is described. A channel management interface, of the group-based communication system, can be presented via a client of a user associated with a first organization, wherein the channel management interface includes communication channels associated with the first organization, wherein at least a first communication channel is associated with the first organization and a second organization, and wherein at least a second communication channel is associated with the first organization and a third organization. A request can be received via the channel management interface to initiate a channel management action associated with at least one of the first communication channel or the second communication channel and in response to receiving the request to initiate the channel management action, data associated with at least one of the first communication channel or the second communication channel can be updated.

Abstract: A text interaction record is received at a database system. The text interaction record may include interaction text from one or more messages between a client machine and a service provider. An input database record creation prompt that includes natural language instructions to generate database record field text based on the text interaction record may be determined. The input database record creation prompt may include some or all of the interaction text. The input database record creation prompt may be transmitted to a large language model for completion. A completed database record creation prompt may be received from the large language model. The completed database record creation prompt may include a text element created by the large language model based on the input database record creation prompt. A database record including a database field storing the text element may be generated in the database system.

Abstract: Apparatus, method, and graphical user interface (GUI) for presentation and navigation of code path data. Code path data samples, including temporal data, related to a plurality of code paths of program code are used to render an interactive GUI including a set of graphical elements representing a corresponding set of code paths. Each graphical element indicates resource utilization changes associated with a respective code path over a time period. The set of graphical elements are visually arranged in a first dimension and the period of time is indicated in a second dimension. Different techniques are used to represent resource utilization over time including extending the graphical elements in a third dimension or changing a width of the graphical elements within a plane defined by the first dimension and the second dimension.

Abstract: Techniques are disclosed in which a computer system implements schema changes for existing database objects by maintaining a logical name and a current physical name corresponding to an existing database object, where the logical name points to the current physical name. The system receives a schema change request specifying the logical name and format changes for the existing object. The system performs a schema change operation in response to the request, including: creating a new database object having a new physical name, copying and transforming data from the existing object to the new object according to the format changes, mirroring new writes directed to the logical name to both the existing and new objects, and causing the logical name to point to the new physical name instead of the current physical name after completing the copying. The system responds to subsequent queries, specifying the logical name, from the new object.

Abstract: Disclosed herein are system, method, and computer program product embodiments for sharing of collaborative documents with users via instant messaging. In one aspect, a collaborative application is configured to display one or more user interfaces associated with a collaborative application that allows a user to engage in a real-time chat between and among one or more users. The collaborative application may also present one or more user interfaces that allow the user to select one or more references of collaborative documents stored at a remote document datastore, and then share these references of collaborative documents with one or more users in the real-time chat. In one example, these references may be represented in real-time chat as a user interface element that visually present the collaborative document title and associated collaborative document pictogram or icon.

Abstract: Embodiments described herein provide systems and methods for document recommendation. A system receives a set of training data including a plurality of documents. The system determines whether the set of training data includes annotated contextual information corresponding to the plurality of documents. The system trains supervised and/or unsupervised models based on the availability of data. The models are used to generate vectors representing the documents. During a live text conversation, text from the conversation may be vectorized using the models and the vectors compared to those representing the documents in order to find the most relevant documents. The system may generate an indication of a recommended document.

Abstract: Disclosed herein are system, method, and device embodiments for providing a mobile interface powered by artificial intelligence. A user remains on a single user-interface page, conducting interactions with a customer relationship management tool using natural language. The technique leverages a large language model as an intermediary middle-layer, allowing a user to engage core functions. The technique builds an appropriate prompt including the natural language and uses the large language model to build an execution plan that references tools and tasks performable in the customer relationship management tool. By chaining prompts, the technique incorporates prior interactions into subsequent prompts. Mobile-specific information such as location, images, and scanned barcodes may be included in a prompts. Running the large language model on the client device allows the user to perform CRM functions while operating in an offline mode, a mode that secures user data and enhances privacy.

Abstract: A system allows translation across API models represented using different API description languages. The system stores model bindings from a common visualization model format to multiple API description languages. The model bindings map constructs of the API description language to and from modeling constructs of the common visualization model format. The system uses the model bindings to convert API models to and from representations based on API description languages to the common visualization model format. The system used the common visualization model format to generate visualizations of the API model that can be displayed via a user interface and also allow users to modify the API model.

Abstract: Described herein are systems, apparatus, methods and computer program products for machine learning intent classification. In various embodiments, historical utterances provided by users may be utilized for bot training. Context and personally identifiable information may be removed from the utterances. The utterances may be associated with vectors. The utterances and vectors may be used to determine recommendations.

Abstract: A user interface comprising at least a set of reaction icons configured to initiate a search of content of a communication platform is described. In an example, at least the set of reaction icons can be presented via the user interface of the communication platform, wherein individual reaction icons of the set of reaction icons are selectable as search parameters in the user interface. In response to receiving a selection of at least one reaction icon, a search for content, associated with the at least one reaction icon, stored in a database associated with the communication platform can be initiated.

Abstract: The technology disclosed can query configuration management system data and includes cross table selection criteria and joined data return.

Abstract: The disclosure generally relates to an enterprise group-based communication system. Group-based communication channels may be created and access by client devices associated with users within the enterprise group-based communication system that have various identifiers associated therewith.

Abstract: Disclosed herein is computer technology that provides adaptive mechanisms for learning concepts that are expressed by natural language sentences, and then applies this learning to appropriately classify new natural language sentences with the relevant concept that they express.

Abstract: Embodiments described herein provide systems, methods, and devices for generating enhanced vison-language training data. A method may include: receiving, from a communication interface, a first training dataset of image-text pairs and a second training dataset of annotated image-text pairs; fine-tuning an image-grounded text decoder and an image-grounded text encoder using the second training dataset of annotated image-text pairs; generating, by the fine-tuned image-grounded text decoder, a predicted text based on a training image from the first training dataset; generating, by the fine-tuned image-grounded text encoder, a filtering decision based on the training image and the predicted text; adding the training image and the predicted text to form a third training dataset of image-text pairs depending on the filter decision; and training a vision-language model using the third training dataset of image-text pairs.

Abstract: A request to search a database field in a database table for a query value may be received. The query value may be hashed with a designated hash function and a designated hash key to produce a designated keyed-hash value. A row in the database table may be identified based on the designated keyed-hash value. The identified row may include a keyed-hash field value that matches the designated keyed-hash value. The identified row may include an encrypted field value generated by encrypting an unencrypted field value matching the query value. One or more data values associated with the identified row may be transmitted in response to the request.