The present specification discloses a model training method and apparatus, a service processing method and apparatus, a storage medium, and a device. The model training method includes: obtaining a historical conversation; determining a target conversation content from the historical conversation; inputting the historical conversation into a to-be-trained feature extraction model for the feature extraction model to determine a conversation content feature corresponding to the target conversation content as a first feature based on a conversation content other than the target conversation content in the historical conversation, and to determine a conversation content feature corresponding to the target conversation content as a second feature based on the target conversation content; and training the feature extraction model with an optimization goal of reducing a deviation between the first feature and the second feature, where the trained feature extraction model is used to determine an output conversation content feature corresponding to each input conversation content, and send the output conversation content feature for a receiving end to perform service processing based on the received output conversation content feature.

Systems and methods for visual content processing. A method includes applying teacher models to training candidates in order to output instances of a custom object label. The training candidates are selected using a student model based on search configuration parameters. A first set of media content is generated by labeling the training candidates based on the instances of the custom object label output by the teacher models. A custom model is created using the teacher models. The custom model is a machine learning model trained using the first set of media content. A subset of a second set of media content is obtained. The subset of the second set of media content is selected based on outputs of the custom model as applied to the second set of media content. An advanced machine learning model is applied to the obtained subset of the second set of media content.

A method of providing text information associated with content includes identifying content including an image uploaded to a content server, extracting text from the image included in the content, and providing text information including the extracted text as the text information associated with the content.

A method of training a text quality assessment model, a method of determining text quality, an electronic device, and a storage medium are provided. The method of training the text quality assessment model includes: determining a first text satisfying a condition of being a negative sample and a second text satisfying a condition of being a positive sample from a plurality of texts based on indicators for the texts; for any text of the first text and the second text, adding a label to the text based on the condition satisfied by the text, wherein the label indicates a category of the text, and the category includes a low-quality category for the negative sample and a non-low-quality category for the positive sample; and constituting a training set by the first text having a label and the second text having a label, to train the text quality assessment model.

Methods, devices and computer-readable media for processing a compressed video to perform an inference task are disclosed. Processing the compressed video may include selecting a subset of frame encodings of the compressed video, or zero or more modalities (RGB, motion vectors, residuals) of a frame encoding, for further processing to perform the inference task. Pre-existing motion vector and/or residual information in frame encodings of the compressed video are leveraged to adaptively and efficiently perform the inference task. In some embodiments, the inference task is an action recognition task, such as a human action recognition task.

Provided in the present disclosure are a text recognition method, and a model and an electronic device, which are applied to a mode in which primary classification is first performed from different dimensions, and secondary classification is then performed, such that the meaning of text is analyzed from different dimensions, thereby improving the accuracy of text recognition. The method includes: acquiring text to be recognized, and performing primary classification on the text to obtain a plurality of text features, wherein the primary classification is used for performing feature extraction on the text from different dimensions, and there are differences between features extracted from the different dimensions (100); splicing the plurality of text features, so as to obtain spliced features (101); and performing secondary classification on the spliced features to obtain a text category corresponding to the text, wherein the secondary classification is used for classifying the spliced features (102).

A non-standard user interface object identification system includes an object candidate extractior that extracts one or more objects from an image, a first similarity analyzer that determines object type candidates of the one or more objects in accordance with similarities between the one or more objects and a standard user interface (UI) element, a second similarity analyzer that selects object type-specific weight values in accordance with layout characteristics of the one or more objects and determines object types of the one or more objects using the object type candidates and the object type-specific weight values, and an object identifier that receives type and characteristic information of a search target object and identifies the search target object in accordance with characteristic information and the object types of the one or more objects.

A method includes receiving, from a user device associated with a user, a plurality of annotated documents. Each respective annotated document includes one or more fields and each respective field labeled by a respective annotation. The method includes, for a threshold number of iterations, randomly selecting a respective subset of annotated documents from the plurality of annotated documents; training a respective model on the respective subset of annotated documents; and generating, using the plurality of annotated documents not selected for the respective subset of annotated documents, a respective evaluation of the respective model. The method also includes providing, to the user device, each respective evaluation.

A method, system, and computer program product are disclosed. The method includes receiving a set of documents, selecting a topic, and determining that a first document from the set contains a topic label for the topic. The method also includes generating a topic sentiment score for the first document and adding the topic sentiment score to a set of training data. Additionally, the method includes determining that a second document from the set does not contain the topic label, generating an average sentiment score for the second document, and generating a bias factor for the average sentiment score.

The subject invention pertains to methods and systems for classifying leukocytes using artificial intelligence called AIRFIHA (artificial-intelligence enabled reagent-free imaging hematology analyzer) that can accurately classify subpopulations of leukocytes in a label-free manner. AIRFIHA can not only subtype lymphocytes into B and T cell but is capable of sorting different types of T cells subtypes. AIRFIHA is realized through training a two-step neural network using label-free images of separated leukocytes acquired from a custom-built quantitative phase microscope. Owing to its easy operation, low cost, and strong discerning capability of complex leukocyte subpopulations, AIRFIHA is clinically translatable and can also be deployed in resource-limited settings.