Abstract: Provided is a method for preparing a hard carbon anode of a lithium/sodium ion battery by biochar, which includes the following steps: S1 biochar pretreatment, S2, preparing a precursor material and S3 pyrolysis carbonization, by a modification of the biochar, setting carbonization temperature and carbonization time, and controlling a cooling rate, so that the obtained biochar generates amorphous carbon after carbonization with low graphitization degree, few surface defects, larger charge-discharge specific capacity, and stable performance in the cycle charging and discharging process; at the same time, the process of the application is relatively simple, and a special complex process is reduced; the present method is suitable for a large-scale industrial production without special adjustment or control of a morphology; and the product performance is relatively good and thus has certain competitive advantages.

Abstract: Systems and methods for feature-based music selection may include (1) receiving user input selecting a music composition, (2) identifying features of the music composition including (i) a musical feature, relating to a musical quality of the music composition and (ii) a lyrical feature, relating to one or more of the music composition's lyrics, (3) determining that an additional music composition is similar to the music composition based on a comparison of the features of the music composition with features of the additional music composition, and (4) selecting the additional music composition to be added to a queue associated with the music composition based on the determination. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Systems, methods, and non-transitory computer-readable media can be configured to determine a video embedding for a video content item based at least in part on a first machine learning model. A set of music embeddings can be determined for a set of music content items based at least in part on a second machine learning model. The set of music content items can be ranked based at least in part on the video embedding and the set of music embeddings.

Abstract: Systems, methods, and non-transitory computer-readable media can be configured to determine a video embedding for a video content item based at least in part on a first machine learning model. A set of music embeddings can be determined for a set of music content items based at least in part on a second machine learning model. The set of music content items can be ranked based at least in part on the video embedding and the set of music embeddings.

Abstract: Systems and methods for text-based music selection through a music service may include (1) determining that a user of a social media application may be interested in sharing, via the social media application, music that relates to one or more key words, (2) providing the user with a music recommendation that relates to the one or more key words, (3) receiving input from the user accepting the music recommendation, and (4) in response to receiving the input, sharing the music composition via the social media application. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Systems, methods, and non-transitory computer-readable media can be configured to determine a video embedding for a video content item based at least in part on a first machine learning model. A set of music embeddings can be determined for a set of music content items based at least in part on a second machine learning model. The set of music content items can be ranked based at least in part on the video embedding and the set of music embeddings.

Abstract: Heterogeneous information networks can be used to detect whether a new transaction is fraudulent. Metapaths are determined based on the heterogeneous information. The transactions can be downsized. For each metapath, training transaction data and test transaction data be used to compute a feature vector “z.” A fraud detection system can use the features to generate a fraud detection model. The fraud detection model can be iteratively refined using machine learning. The fraud detection models can then be applied to new transactions to determine a risk score of the new transaction.

Abstract: A method for inferring venues from social messages includes: accessing a collection of venues and training a classifier that predicts whether a social message is linked to a venue in the collection of venues; receiving a new social message; for each venue in the collection of venues: identifying for the new social message corresponding meta-paths to the particular venue; encoding the corresponding meta-paths as a feature vector for the trained classifier; computing by the trained classifier a score for each venue in the collection of venues indicating whether the new social message is linked to the venue; and based on the scores, identifying at least one candidate venue as a predicted venue for the new social message and associating the predicted venue with the new social message. In some implementations, the new social message is not geotagged.

Abstract: A method associates social media messages with venues. A social network graph includes users, messages from users, and venues. The venues include multiple primary venues and a no-venue. A link between a message and the no-venue node indicates that the message is not associated with a primary venue. Training feature vectors are constructed that measure connectedness between messages and venues. The process trains a classifier to estimate probabilities that messages are associated with venues. A new social media message is received, and the process constructs a feature vector using the same features as the training vectors, measuring connectedness between the new message and the no-venue. The classifier computes a probability that the new message is associated with the no-venue. When the probability exceeds a predefined threshold, the new message is not associated with any of the primary venues. Otherwise, the new message is associated with one of the primary venues.

Abstract: In implementations of the subject matter described herein, a machine learning scheme is proposed. Features of historical inputs from a user as well as corresponding outputs presented to the user in response to the historical inputs are obtained, where the features are previously determined based on contexts of the historical inputs which indicate information related to the user. The features of the historical inputs are assigned into a plurality of groups. An association is determined on the basis of the plurality of groups of features. Specifically, an association indicating inter-group correlations of features from different ones of the groups is determined according to the obtained outputs. Therefore, in determining the association, intra-group correlations such as correlations of features within a group are excluded. In this way, the time and computation complexity for the association determination will be effectively reduced.

Abstract: A method associates social media messages with venues. A social network graph includes users, messages from users, and venues. The venues include multiple primary venues and a no-venue. A link between a message and the no-venue node indicates that the message is not associated with a primary venue. Training feature vectors are constructed that measure connectedness between messages and venues. The process trains a classifier to estimate probabilities that messages are associated with venues. A new social media message is received, and the process constructs a feature vector using the same features as the training vectors, measuring connectedness between the new message and the no-venue. The classifier computes a probability that the new message is associated with the no-venue. When the probability exceeds a predefined threshold, the new message is not associated with any of the primary venues. Otherwise, the new message is associated with one of the primary venues.

Abstract: A method for inferring venues from social messages includes: accessing a collection of venues and training a classifier that predicts whether a social message is linked to a venue in the collection of venues; receiving a new social message; for each venue in the collection of venues: identifying for the new social message corresponding meta-paths to the particular venue; encoding the corresponding meta-paths as a feature vector for the trained classifier; computing by the trained classifier a score for each venue in the collection of venues indicating whether the new social message is linked to the venue; and based on the scores, identifying at least one candidate venue as a predicted venue for the new social message and associating the predicted venue with the new social message. In some implementations, the new social message is not geotagged.