Abstract: Disclosed are mechanisms for selecting a recommended item for a current item being viewed by a user account based on a view history of the user account with reduced bias. For a current item being viewed by the user account represented by a current node of a co-watch graph, embodiments can select a recommended item represented by an associated node in the co-watch graph likely being viewed by the user account, and determine a probability of the recommended item likely being viewed. The co-watch graph can be generated based on a view history of the user account. An edge between a first node and a second node of the co-watch graph can have a weight representing a number of co-occurrence times when the first item represented by the first node and the second item represented by the second node are viewed in sequence within a predetermined time interval.

Abstract: Systems and methods for automated contact generation based on content communications are disclosed herein. A rule is retrieved from a rules database, the rule defining criteria for identifying contact-related data within a content item electronically communicated from a source account to a destination account. Based on the rule, the contact-related data within the content item is identified. In response to identifying the contact-related data within the content item, the contact-related data is automatically extracted from the content item, a contact entry corresponding to the source account is automatically generated based on the extracted contact-related data, and the contact entry is automatically stored for the destination account in a contact database.

Abstract: A system for generating a stress disorder ration program includes a computing device configured to obtain a stress representation, ascertain an equanimity signature, wherein ascertaining the equanimity signature further comprises retrieving an acclimation element, determining a relative vector as a function of the acclimation element, and ascertaining the equanimity signature as a function of the relative vector and the stress representation using a stress machine-learning model, identify a physiological influence as a function of the equanimity signature, determine an edible as a function of the physiological influence, and generate a ration program as a function of the edible.

Abstract: Certain aspects of the present disclosure provide techniques for providing a chronologically-based search engine. Example methods includes presenting, on a display of an end-user device, live image data being captured by a camera of the end-user device, determining a pose of the end-user device, and sending the pose of the device to a server. The method also includes receiving location specific data from the server, the location specific data based on the pose of the end-user device, the location specific data including a first topic, and superimposing, on the live image data, based on the location specific data, (i) at least one highlighted area of an object associated with the first topic, and (ii) a query panel associated with the first topic superimposed proximate the object, the at least one highlighted area and the query panel being interactive elements associated with the first topic.

Abstract: A method for associating a device with a user including the action of receiving from a first computerized device operated by a first user a first data-content including a plurality of first data items, including clickstream data. An action of setting rules for computing scores representing similarity between a first data item received from the first computerized device and a second data item received from a second computerized device. An action of collecting the plurality of the first data items and the second data items, from the plurality of computerized devices of the plurality of computerized devices. An action of computing the score representing similarity between at least one pair of computerized devices respectively providing the first and the second data items. And an action of determining that the pair of computerized devices are operated by a same user if the score reaches a predetermine value.

Abstract: Embodiments are provided for detecting overlapping topics in a messaging system. In an example system, a plurality of trigger phrases is received, where each trigger phrase is configured to trigger a bot that receives the trigger phrase to select a corresponding topic for conversation. For each trigger phrase, a vector representation is generated. Measures of similarity are generated based at least on the vector representations, where each measure of similarity represents a degree of similarity between a respective pair of vector representations. A topic overlap is detected based on a pair of vector representations having a measure of similarity above a similarity threshold, where the topic overlap indicates two trigger phrases that are overlapping. The topic overlap is provided to an authoring tool that comprises one or more interactive elements to enable a user to change at least one of the two trigger phrases that are overlapping.

Abstract: This invention presents a system and method to acquire object measurements with and optical device and axial scanning mechanism, and to subsequently implement a digital processing algorithm to establish a match between similar object measurements acquired in the past. The digital processing algorithm consists of a probe-and-match strategy. It is generally challenging to determine whether or not an object, such as a work of art (e.g., a painting, drawing, sculpture, or collectable item), is the exact same object as something viewed previously with an extremely high degree of confidence. There is the potential for one object to look very similar to another object, but not be the same (i.e., to be a forgery). There is also the potential for one object to be the same object as viewed previously, but have changed significantly over time (e.g., aged or damaged). Being able to distinguish between these two cases is a difficult yet important task.

Abstract: An image retrieval system with high retrieval accuracy is provided. The image retrieval system includes a database and a processing portion. The database has a function of storing a plurality of pieces of database image data, and a database tag is linked to each of the plurality of pieces of database image data. The processing portion has a function of obtaining database image feature value data representing a feature value of the database image data for each piece of the database image data. The processing portion has a function of obtaining query image feature value data representing a feature value of the query image data. The processing portion has a function of calculating first similarity of the database image data to the query image data for each piece of the database image data. The processing portion has a function of obtaining a query tag linked to the query image data using some of the database tags.

Abstract: A data propagation system stores operator/machine/implement combinations, and corresponding settings data indicative of settings on the machine or implement for the corresponding combination. When a machine is connected to an implement, an identity of an operator is detected, along with an identity of the machine and an identity of the implement. The data propagation system determines whether settings data is available for that operator/machine/implement combination. If so, the settings data is obtained and the machine and implement are automatically controlled based upon the retrieved settings data.

Abstract: A method including pre-screening second images from a database for a search result based on a first image and also based on respective substring distances between first binary substrings for the first image and respective second binary substrings for each of the second images. The method further can include after the pre-screening, determining a respective image distance for each third image of third images of the search result, wherein the respective image distance is between the first image and the each third image of the third images of the search result, and after determining the respective image distance for each third image of the third images of the search result, when the respective image distance for a particular one of the third images is greater than a predetermined image distance threshold, removing the particular one of the third images from the search result before the search result is displayed on a user device requesting the search result. Other embodiments are disclosed.

Abstract: Technologies and techniques for processing drug data in a specialized medical computer system. Autonomous moving code may be received via a communications interface from a computer network, where the autonomous movable code includes patient data, lab test data, demographic data, and diagnosis data. The autonomous movable code is executed in a system agent manager and processed in a learning module, where the learning module performs predictive processing to determine if an opioid abuse condition exists. New autonomous movable code may be generated that includes information and/or instructions regarding the opioid abuse condition. The new autonomous movable code is then transmitted back to the computer network.

Abstract: Provided are systems and methods for determining behaviors of a user that are associated with earning secondary income. In one example, a method may include receiving a request from a user device, identifying productivity attributes and consumption attributes of a user associated with the user device based on behavior of the user captured over time, determining a recommended value-generating behavior for the user via execution of a collaborative filtering model, where the collaborative filtering model receives the productivity and consumption attributes of the user and determines the recommended value-generating behavior based on historical value-generating behavior of other users having similar productivity attributes and consumption attributes, and transmitting the recommended value-generating behavior to the user device via a content channel between the server and the user device.

Abstract: Methods and apparatus for predicting an association between input data in a first modality and data in a second modality using a statistical model trained to represent interactions between data having a plurality of modalities including the first modality and the second modality, the statistical model comprising a plurality of encoders and decoders, each of which is trained to process data for one of the plurality of modalities, and a joint-modality representation coupling the plurality of encoders and decoders. The method comprises selecting, based on the first modality and the second modality, an encoder/decoder pair or a pair of encoders, from among the plurality of encoders and decoders, and processing the input data with the joint-modality representation and the selected encoder/decoder pair or pair of encoders to predict the association between the input data and the data in the second modality.

Abstract: An online system receives, from a client device of a posting user, a script for a voice-based content item. The online system retrieves a voice synthesis model stored in the user profile of the posting user and generates a synthetic audio stream using the retrieved voice synthesis model and based on the received script. The online system presents the generated synthetic audio stream to the posting user and receives instructions for modifying the synthetic audio stream. The online system generates a second audio stream based on the received instructions and composes the voice-based tent item based on the generated second audio stream.

Abstract: Methods for analyzing elements of a first text collection, and devices and methods for searching for information in a set of digital data, in particular in a computer network.

Abstract: A method implements a table discovery service. The method includes receiving a query string, converting the query string to a query graph, and identifying a selected graph, of a set of graphs, that matches the query graph. The method further includes transmitting a notification identifying a previously generated table corresponding to the selected graph, receiving a notification response to accept the previously generated table, and transmitting data from the previously generated table in response to the query string.

Abstract: According to one embodiment, a method, computer system, and computer program product for provisioning a tag schema. The embodiment may include determining data types for tag-keys within an existing ecosystem of tags. Each tag of the existing ecosystem comprises a tag-key and a tag-value. The embodiment may include performing pairwise clustering of the tags within the ecosystem. The embodiment may include identifying a main tag-key within each cluster of tags. The embodiment may include grouping the clusters into a broader category. The embodiment may include providing a tag schema recommendation for the ecosystem based on the grouped clusters.

Abstract: A system for conducting a computer-based, simultaneous, multiple round, descending clock auction for basic generation services includes a web server for receiving bid data for one or more users for basic generation service products, an application server host application software, which processes the one or more bids according to at least one auction rule, tracks the auction, monitors the auction, and/or determines when to end the auction, and a database server, which stores auction data. A method of conducting a computer-based, simultaneous, multiple round, descending clock auction for basic generation services includes the repeating steps of receiving bids indicating desired tranche units of basic generation service products, calculating next round prices for each product, and sending round results to bidders. The system for and method of conducting a computer-based auction includes receiving and processing a withdrawal request or a switch request from at least one of the qualified bidders.

Abstract: A computer processing system is provided for enhancing video-based language learning. The system includes a video server for storing videos that use one or more languages to be learned. The system further includes a video metadata database for storing translations of sentences uttered in the videos, character profiles of characters appearing in the videos, and mappings between the sentences and a learner profile. The system also includes a learner profile database for storing learner profiles. The system additionally includes a semantic analyzer and matching engine for finding, for at least a given video and a given learner, alternative sentences for and responsive to the translations of the sentences uttered in the given video that conflict with a respective learner profile for the given learner. The computer processing system further includes a presentation system for playing back the given video and providing the alternative sentences to the given learner.

Abstract: Dynamic content tags are generated as content is received by a dynamic content tagging system. A natural language processor (NLP) tokenizes the content and extracts contextual N-grams based on local or global context for the tokens in each document in the content. The contextual N-grams are used as input to a generative model that computes a weighted vector of likelihood values that each contextual N-gram corresponds to one of a set of unlabeled topics. A tag is generated for each unlabeled topic comprising the contextual N-gram having a highest likelihood to correspond to that unlabeled topic. Topic-based deep learning models having tag predictions below a threshold confidence level are retrained using the generated tags, and the retrained topic-based deep learning models dynamically tag the content.

Abstract: Systems, methods, and devices for human-machine interfaces for utterance-based playlist selection are disclosed. In one method, a list of playlists is traversed and a portion of each is audibly output until a playlist command is received. Based on the playlist command, the traversing is stopped and a playlist is selected for playback. In examples, the list of playlists is modified based on a modification input.

Abstract: A method for document similarity analysis. The method includes generating a reference document content identifier for a reference document, including identifying frequently occurring terms in reference document content, encoding each frequently occurring term in a term identifier and combining the term identifiers to form the reference document content identifier associated with the reference document. The method also includes obtaining at least one document similarity value by comparing the reference document content identifier to a set of archived document content identifiers stored in a document repository.

Abstract: A system is provided for resolving data errors. The system is configured to obtain an erroneous data element received from a source system and generate a plurality of probable data values for the data element. For each probable data value of the plurality of probable data values, the system verifies whether the probable data value can be processed successfully by an Extract, Transform and Load (ETL) logic and by one or more target applications configured to process the data element. The system determines one of the probable data values as a suggested data value of the data element, based on the verification of the probable data values. The system outputs the suggested data value for processing by the ETL logic.

Abstract: An electronic device is provided. The electronic device includes a processor, and a memory, wherein the memory stores instructions that, when executed, cause the processor to receive a user input including a request for performing a first task that requires at least one parameter for execution and not including the entire at least one parameter, transmit first data related to the user input to an external server, receive a first sequence of states of the electronic device for performing the first task from the external server, perform not all but some of the first sequence of the states while displaying at least some of states changed in the first sequence, and after the performing of the some of the first sequence, display a GUI that is required for performing the first task and represents that a user is requested to provide at least one parameter omitted in the user input.

Abstract: A technique involves normalizing identification of users (e.g., different customer organizations) across disparate local systems (e.g., different electronic platforms that provide different products and/or services). Such normalization of user identification enables a provider to accurately ascertain a particular user of multiple disparate local systems even when the multiple disparate local systems identify that user using different identification schemes. Accordingly, the provider is able to offer enhanced support to that user across the multiple disparate local systems. For example, with such normalization of user identification, the provider may employ a single authentication system across the various local systems thus enabling the user to authenticate via the same authentication process regardless of which local system the user attempts to access.

Abstract: A method for associating a device with a user including the action of receiving from a first computerized device operated by a first user a first data content including a plurality of first data items, including clickstream data. An action of setting rules for computing scores representing similarity between a first data item received from the first computerized device and a second data item received from a second computerized device. An action of collecting the plurality of the first data items and the second data items, from the plurality of computerized devices of the plurality of computerized devices. An action of computing the score representing similarity between at least one pair of computerized devices respectively providing the first and the second data items. And an action of determining that the pair of computerized devices are operated by a same user if the score reaches a predetermined value.

Abstract: Claim verification is facilitated by identifying a selection of textual content within a user interface, accessing a claim detection module, inputting the textual content into the claim detection module to detect one or more claims within the selection of textual content, accessing an evidence extraction module, using the evidence extraction module to automatically search one or more reference repositories for one or more related references that have content that is related to the detected one or more claims, automatically determining whether the content in the one or more related references supports or refutes the one or more claims using a claim verification module, and, in response to determining a set of references of the one or more related references supports or refutes the one or more claims, presenting a support indicator or a refute indicator within the user interface in association with the one or more claims.

Abstract: A device may receive a request to identify items that satisfy parameters of the request. The device may identify a plurality of items that satisfy the parameters. The device may generate a plurality of explanation sets. An explanation set of the plurality of explanation sets may relate to an item of the plurality of items. The explanation set may include at least one of: a positive explanation indicating that the item is positively associated with a first characteristic that relates to a first preference of a user, or a negative explanation indicating that the item is negatively associated with a second characteristic that relates to a second preference of the user. The device may select an item from the plurality of items based on the plurality of explanation sets. The device may provide information that includes an explanation set of the item selected.

Abstract: Data-deduplicating includes comparing a first record of a data-store with a second record of the data-store but instead of using a static weight for a field, the present data-deduplicating dynamically assigns a first weight for the first score to generate a first weighted score, wherein the first weight is based on one or both of the first value or the second value; and assigns a second weight for the second score to generate a second weighted score. A composite score is calculated based on the first weighted score and the second weighted score; and it is determined whether or not the first record and the second record are duplicate records, based on the composite score.

Abstract: Affinity-based listing recommendations are created and used in a public data exchange. Listings can be evaluated against one another for affinity or similarity such that users working with a particular dataset can be presented with other datasets that share an affinity. Affinity can be determined from both the dataset metadata as well as information from the dataset content. Calculation of affinity scores can be pre-computed and stored, in advance of use, or determined on-the-fly. Presentation of most-similar listings can be deterministic, can contain randomization, can employ time-decay, can be weighted, and can make use of a tiered-sum approach.

Abstract: Methods and systems are described for generating dynamic interface options using machine learning models. The dynamic interface options may be generated in real time and reflect the likely goals and/or intents of a user. The machine learning model may provide these features by interpreting multi-modal feature inputs. For example, the machine learning model may include a first machine learning model, wherein the first machine learning model comprises a convolutional neural network, and a second machine learning model, wherein the second machine learning model performs a Weight of Evidence (WOE) analysis.

Abstract: A system, method and computer-readable medium for determining a data domain associated with data, including parsing a document to generate one or more document indexes corresponding to the document, the one or more document indexes comprising a plurality of index terms and location information, determining a syntactic confidence score corresponding to a non-dictionary term in the plurality of index terms based on a syntactic analysis of the non-dictionary term, determining a proximity confidence score corresponding to the non-dictionary term based on the location information and at least one proximity query associated with the non-dictionary term and one or more other terms in the document index, determining a semantic confidence score based on a plurality of dictionary terms in the plurality of index terms, and determining an overall confidence score corresponding to the non-dictionary term based on the syntactic confidence score, the proximity confidence score, and the semantic confidence score.

Abstract: Methods, systems, and devices for analyzing communication messages (e.g., emails or activities) to determine relationship strength using a distributed graph are described. In some systems, a user may be associated with a specific tenant. A database server of the system may receive communication messages associated with the user and a target user. The server may perform a natural language processing (NLP) analysis on the communication messages to extract metadata, and may generate or update a distributed graph indicating connections between users based on the extracted metadata. Using the connections of the graph, the server may calculate a closeness score between the user and the target user. Additionally, the server may calculate closeness scores between the target and other users associated with the tenant, and may determine the users with the greatest closeness scores. The server may send a suggestion for the determined users to initiate communication with the target.

Abstract: A method and system for processing information in a social network system are disclosed. The method includes: in a network system, especially in a social network system, adding a piece of information having a new information structure to serve as a basic unit for expression intension of a user while enabling a user to be capable of continuously releasing a piece of information having a simple structure as a basic unit for expressing intensions. This information having the new structure describes relative locations of multiple basic units expressing meanings when being exhibited, and the meanings thereof are expressed by using a combination of the recited basic units in a manner of the multiple basic units. As such, information expression efficiency in the system is improved, and the information screening capability is enhanced, thereby naturally implementing structured reorganization of the information and significantly improving the information processing capability of the system.

Abstract: A server system receives a plurality of comments on a post in an online service, receives feedback on respective comments of the plurality of comments from users of the online service and retrieves feedback weights for the users. The server system ranks the plurality of comments using the feedback and feedback weights and provides the plurality of comments, ordered in accordance with the ranking, for display.

Abstract: Methods and system for determining a similarity relationship between a plurality of digital assets and a target digital asset comprises creating a normalized semantic feature vector associated with a search query, discovering the target asset based on the normalized semantic feature vector, generating a normalized latent feature vector associated with the target asset, comparing the normalized semantic feature vector with semantic feature vectors for each of the digital assets to generate a semantic comparison value, comparing the normalized target latent feature vector with latent feature vectors for each of the digital assets to generate a latent comparison value, blending the semantic comparison vector value with the latent feature comparison vector value to create a target comparison value for each of the digital assets, and reporting the digital assets having the highest target comparison values to the user or group of users.

Abstract: A method trains a neural network to identify an event based on discrepancies in answers to factoid questions at different times. One or more processors identify answers to a series of factoid questions. The processor(s) compare the answers from the series of factoid questions in order to determine discrepancies in the answers at different times, and then train a neural network to identify an event based on the discrepancies in the answers at the different times.

Abstract: A Searchable Application Representation is generated with the exact structure, content, functionality, and behavior of the Native Mobile Applications and is searchable by Search Engines by providing metadata pointing to the Native Mobile Applications. The Search Engine searches the Searchable Application Representation. When the Search Engine finds the Searchable Application Representation, Pointer, Metadata and Search Material to Corresponding Native Mobile Application on the Internet, the Search Engine becomes aware of the Native Mobile Application and can search the Content contained in the Searchable Application Representation. The Search Engine finds and ranks Content in the Searchable Representation and Pointer, Metadata, and Search Material corresponding to such Content in the Native Mobile Application is passed to the Search Engine, which can use such information to determine the relevancy of such Content according to a certain Search Criteria.

Abstract: Methods, apparatus, and database management systems are disclosed for providing, organizing, and present database search results and, more specifically, systems and methods for a chronological-based search engine. One method includes presenting live image data being captured by a camera of the end-user device. The method also includes determining a pose of the end-user device. The pose including a location of the end-user device. Additionally, the method includes sending the pose of the end-user device to an augmented reality platform entity and receiving closed captioning data from the augmented reality platform entity. The closed captioning data is based on the location of the end-user device and includes indications of first topics within the closed captioning data. The method includes superimposing the closed captioning data onto the live image data.

Abstract: A system, method, and computer-readable storage medium configured to facilitate user purpose in a computing architecture.

Abstract: A first client device associated with a first account of a content management system can receive a first or latest version of a synchronized content item. The first client device can determine differences or the “diff” between the first version and a second or next-to-latest version of the content item and upload the first version and the diff to the content management system. Upon receiving the first version and the diff, the content management system can store the first version and the diff and download them to the second client device. The second client device can generate a notification when the download finishes and present the notification with an interface element for requesting presentation of the diff. When the second client device detects a selection of the interface element, the second client device can present the diff.

Abstract: The present disclosure describes a method, apparatus, and storage medium for annotating image. The method includes extracting, by a device, a visual feature of an image through a generative adversarial network model, and sequentially inputting M pieces of random noise into the generative adversarial network model. In response to each of the M pieces of random noise being inputted into the generative adversarial network model, the method includes performing a determinantal point process (DPP) on the visual feature of the image and the each random noise through the generative adversarial network model to obtain N tag subsets, and selecting a distinct tag subset from the N tag subsets through the generative adversarial network model. The method also includes outputting M distinct tag subsets through the generative adversarial network model after the M pieces of random noise are inputted into the generative adversarial network model.

Abstract: The present disclosure provides techniques for calculating an entity's cybersecurity risk based on identified relationships between the entity and one or more vendors. Customer/vendor relationships may impact the cybersecurity risk for each of the parties involved because a security compromise of a downstream or upstream provider can lead to a compromise of multiple other companies. For example, if organization A uses B (e.g., a cloud service provider) to store files, and B is compromised, this may lead to organization A being compromised (e.g., the files organization A stored using B may have been compromised by the breach of B's cybersecurity). Embodiments of the present disclosure further provide a technique for calculating a cybersecurity risk score for an organization based on identified customer/vendor relationships.

Abstract: A system and method are disclosed for capturing, tracking, analyzing and automating analog and digital interactions. Embodiments include a system comprising one or more end user systems, one or more entity systems, and a computer operatively coupled to a display device. The computer is configured to monitor one or more communications on first and second communication channels between the end user and entity systems, group the one or more communications on the first and second communication channels by communication subject, and display the grouped communications on the display device.

Abstract: A query is received that requests issues relevant to a user. Thereafter, a plurality of issues responsive to the query are retrieved. The retrieved issues are ranked using a first machine learning model to result in a first subset of the retrieved issues. The first subset of the retrieved issues are then ranked using a second, different machine learning model to result in a second subset of the retrieved issues which are a subset of the first subset of the retrieved issues. Data can then be provided which is responsive the query and includes at least a portion of the second subset of the retrieved issues. Related apparatus, systems, techniques and articles are also described.

Abstract: In one embodiment, a method includes receiving program content and data describing program content from a content source, and automatically identifying, based on user preferences of a first user, one or more relevant products or services displayed in the program content. Product-related metadata associated with the program content is identified. The product-related metadata including data relating to the one or more relevant products or services displayed in the program content. The program content is communicated to a display device for presentation to a first user in a first portion of the display device, and the product-related metadata is communicated to a second display device for presentation to a second user substantially simultaneously with the presentation of the program content in the first display device. A user commentary is received from the second device, the user commentary generated by the second user and associated with the program content or product-related metadata.

Abstract: Systems and techniques are generally described for generating visually blended recommendation grids. In some examples, a selection of a first item and a second item displayed on a display may be received. In various examples, the first item may be displayed in a first element of a grid and the second item may be displayed in a second element of the grid. In some examples, a third element of the grid that is disposed between the first element and the second element along an axis of the grid may be determined. In various examples, a third item may be determined for display in the third element of the grid based at least in part on a blended representation of an embedding of the first item and an embedding of the second item. The third item may be displayed in the third element of the grid.

Abstract: Methods and systems for providing access to contents which are semantically related to a displayed content(s). The access can be provided through a multi-dimensional user interface (UI). The method includes detecting a predefined gesture with respect to a first content. Based on the detected gesture, determining closest semantically linked content (second content). The semantic link between the first content and the second content can be established based on parameters such as sharing history, frequency of usage, type, a location, similarity, hierarchy, key words/phrases, tags, and so on. The semantically linked contents can be assigned onto distinct dimensions of the multi-dimensional UI space. The multi-dimensional UI space can be traversed through different dimensions using the predefined gesture, and each traversal from one dimension to another can be semantically linked.

Abstract: A system to create a stacked classifier model combination or classifier ensemble has been designed for identification of undisclosed flaws in software components on a large-scale. This classifier ensemble is capable of at least a 54.55% improvement in precision. The system uses a K-folding cross validation algorithm to partition a sample dataset and then train and test a set of N classifiers with the dataset folds. At each test iteration, trained models of the set of classifiers generate probabilities that a sample has a flaw, resulting in a set of N probabilities or predictions for each sample in the test data. With a sample size of S, the system passes the S sets of N predictions to a logistic regressor along with “ground truth” for the sample dataset to train a logistic regression model. The trained classifiers and the logistic regression model are stored as the classifier ensemble.

Abstract: In certain embodiments, document-based resolution of user inquiries may be facilitated. A predicted intent of the user is determined based on chat activity information associated with the user. A response to a user inquiry may be provided to the user via a chat interface based on the predicted intent. User response may be obtained for the response, which may indicate a failure in providing a resolution to the user (e.g., regarding a user inquiry). Upon detecting a failure in providing the resolution, a document associated with the user and matching the predicted intent may be obtained and presented to via the chat interface. The document may have content related to the predicted intent. The document may be presented as a response to the user response to seek a confirmation from the user regarding its relevance to the user inquiry.