13 results about "Content Model" patented technology

In accordance with the described techniques, a tone embedding system includes one or more generative content models and a neural network trained to extract tone from input content. The tone embedding system receives a set of multimodal input content associated with an entity, and a content generation prompt. Based on the content generation prompt, the one or more generative content models produce generated content. Further, the neural network is employed to generate an entity embedding capturing a tone conveyed by the set of multimodal input content, as well as a content embedding capturing a tone conveyed by the generated content. The generated content is output based on a degree of alignment between the entity embedding and the content embedding meeting a tone alignment threshold.

The invention relates to the field of online education and intelligent teaching, and discloses a teaching resource code adaptive optimization and resource personalized recommendation method and system. According to the method, dynamic feature codes including dynamic difficulty, quality and timeliness are introduced, and a static feature region and a dynamic feature region are separately managed; constructing a quaternary heterogeneous graph neural network, and generating a high-confidence pseudo tag from three perspectives of group behavior consistency, time sequence behavior rationality and content relevance through a graph model, a time sequence model and a content model; adaptively calculating a resource feature update value to form closed-loop optimization; and realizing personalized recommendation through a deep learning model based on the user portrait. According to the method, the problems of static resource coding, difficulty in mining implicit behaviors, high cost of cold start and manual intervention and the like in a traditional method are solved, recommendation normal form upgrading from a passive response demand to an active prediction demand is realized, and the accuracy and efficiency of teaching resource recommendation are remarkably improved.

A method provided herein includes accessing, using a monitoring engine, a computing file provided to a second computing device via a computing file exchange platform. In some embodiments, the method includes identifying, using the computing file and a computing file content model, a content deficiency associated with the computing file. In some embodiments, the method includes generating, using the content deficiency and the computing file content model, a responsive action procedure. In some embodiments, the method includes generating a responsive action procedure link interface element. In some embodiments, the responsive action procedure link interface element includes a responsive action procedure link representation corresponding to the responsive action procedure. In some embodiments, the method includes causing the responsive action procedure link interface element to be rendered to an interface associated with the computing file exchange platform.

The application provides an intelligent teaching system interoperability model based on a subject knowledge graph by extending the SCORM specification, and comprises the following sub-models: sub-model 1, a structure framework of the subject knowledge graph; sub-model 2, a sharable intelligent content object KCO based on the subject knowledge graph; sub-model 3, a KCO runtime environment conforming to the SCORM specification; and sub-model 4, a KCO content packaging model KCOCP conforming to the SCORM specification. The application takes the subject knowledge graph as a knowledge base, and extends the content model of the SCORM specification from a multimedia-based structured courseware to intelligent learning content combined with the subject knowledge graph, so that the overall intelligence of the teaching system conforming to the SCORM specification can be greatly improved.

This invention relates to the field of B2B foreign trade website building technology, and in particular to a content model construction and unified engine execution method, system, and device. The method includes: the client configuring fields of the content model; the server constructing the fields into a tree-like field structure according to hierarchical relationships, storing the tree-like field structure as metadata, and assembling a model definition object based on the read metadata; the client recursively rendering the form interface based on the model definition object; the server generating data validation rules based on the configuration parameters in the metadata, and validating the form data submitted by the client based on the data validation rules; the server storing the validated form data according to the field attributes in the metadata, and performing state management, soft deletion, and sorting processing on the content data. This invention can solve the problems of high coupling between model and code, complex field nesting, difficulty in expansion, code redundancy, and difficulty in ensuring consistency of state across multiple modules in existing technologies.

Described are systems and processes for generating personalized content for a user upon cold start of an additional service by leveraging first user data having user consent for a first service and providing substitute data for the user for a second service where the user has no second user data or does not provide consent for use of the second user data. The first user data and the substitute data are input to a content model that may be trained in part with some null values. The content model generates personalized content for the additional service. The personalized content may be cached and retrieved, in part, after the user initiates use with the additional service. The personalized content may be presented to the user based on information from the first user data to create a personalized presentation of at least a portion of the cached personalized content.

The invention discloses a webpage development and deployment method and device based on a micro front end and a medium, and relates to the technical field of enterprise-level application development, operation and maintenance integration. The method comprises the following steps: analyzing a webpage service function, strictly limiting each micro front-end module in a single service entity, and packaging a complete front-end life cycle; according to the method, a Monorepo warehouse structure management module is adopted, a module boundary is defined through a root directory pnpm-workspace. Yaml, and cross-module dependence is declared by using a workspace protocol in Package.json; when the version hash field of the associated Headless CMS content model is changed, a Webhook construction request is automatically triggered; creating a temporary Pod on the basis of Kubernetes to execute construction, declaring a destruction strategy in a Pod annotation, and injecting version Hash into an environment variable to drive multi-stage Docker construction; and finally, starting a canary release process, and gradually switching a user request to a new version module through a flow controller.

The application discloses a kind of based on XML fragmentation literature abstract content processing method, including the literature being converted into XML format is divided into fragmented data unit, according to four kinds of mode of chapter, chapter, section and theme constitutes data content model, data content model is dynamically associated by key word semantic relation, extract fragmented data application unit in key word and subject content unit, content unit is dynamically reorganized according to literature abstract demand.The application has beneficial effect that metadata automatic indexing accuracy is >95%, text Xml automatic annotation accuracy is >90%, can effectively improve the prerequisite of target extraction accuracy under the condition of reducing the cost of text decomposition.

Methods and systems herein identify and redact personally identifiable information. A PII sensitivity detection framework includes multiple layers where each layer corresponds to a computer model. The framework analyzes data stored within different data tables and predicts whether a data column includes PII. The first layer corresponds to an artificial intelligence model that analyzes each column metadata and predicts a first score indicative of a likelihood of PII. The second layer corresponds to a rule-based computer model that uses various rules to determine a second score indicative of a likelihood of PII for each column. The third layer corresponds to a column content model that analyzes content of each column using various natural language processing techniques to generate a third score indicative of a likelihood of PII. The framework masks data being presented to a user based on the scores generated via execution of one or more of the layers.

This specification discloses a model training method and apparatus, and a content generation method and apparatus. The training method includes: generating first content that conforms to the content requirements of the original input information using a content model; and training a style model based on the first content and the original input information to further generate second predicted content that conforms to the style requirements based on the first content. The content generation method includes: generating target content that conforms to the content and style requirements of the input information using a content model and a style model, based on the input information.

Methods and systems herein identify and redact personally identifiable information. A PII sensitivity detection framework includes multiple layers where each layer corresponds to a computer model. The framework analyzes data stored within different data tables and predicts whether a data column includes PII. The first layer corresponds to an artificial intelligence model that analyzes each column metadata and predicts a first score indicative of a likelihood of PII. The second layer corresponds to a rule-based computer model that uses various rules to determine a second score indicative of a likelihood of PII for each column. The third layer corresponds to a column content model that analyzes content of each column using various natural language processing techniques to generate a third score indicative of a likelihood of PII. The framework masks data being presented to a user based on the scores generated via execution of one or more of the layers.

The invention discloses an intelligent generation method and device for a presentation file, and the method comprises the steps: responding to an information input operation triggered by an information input region in a web page, and obtaining input information which comprises theme information, website information and multi-type document information; generating an outline based on the information; when the outline is edited into a final target outline, responding to triggering of a template selection operation, calling a presentation file template library, and decoupling the target outline to obtain a target content model, the target content model comprising content describing a logical relationship between different types of texts in different types of pages; and if a target PowerPoint template in the PowerPoint template library is selected, generating a target PowerPoint conforming to the target PowerPoint template based on the target content model. The purpose of automatically generating the PPT through simple input is achieved, and the defect that the time needed for manually generating and replacing the PPT is long is overcome.

This invention discloses a method for constructing a dynamic graded and zoned graphite resource model, comprising the following steps: Step 1: Obtaining basic information data of the graphite resource system, including geographical location information of the graphite resource distribution area, including longitude and latitude; Step 2: Dividing the graphite resources into zones based on their location; Step 3: Obtaining the storage volume of graphite resources in different zones, establishing a database for storage, and further classifying the zones according to the existing content of graphite resources; Step 4: Establishing an existing content model based on the graphite resource content of the graded zones; Step 5: Obtaining the consumption volume of graphite resources in the graded zones over the past ten years, as well as the methods of graphite consumption, and establishing analysis models for different zones; Step 6: Coupled with the existing content model and the analysis model to obtain a dynamic model of graphite resource graded and zoned distribution, reflecting the content curves of graphite resources in different zones over the next ten years, as well as the methods of graphite consumption.