NEURAL MODELS FOR KEY PHRASE DETECTION AND QUESTION GENERATION

    公开(公告)号:US20210134173A1

    公开(公告)日:2021-05-06

    申请号:US17143303

    申请日:2021-01-07

    IPC分类号: G09B7/02 G06N3/02 G06Q50/20

    摘要: A method, system, and storage device storing a computer program, for generating questions based on provided content, such as, for example, a document having words. The method comprises automatically estimating the probability of interesting phrases in the provided content, and generating a question in natural language based on the estimating. In one example embodiment herein, the estimating includes predicting the interesting phrases as answers, and the estimating is performed by a neural model. The method further comprises conditioning a question generation model based on the interesting phrases predicted in the predicting, the question generation model generating the question. The method also can include training the neural model. In one example, the method further comprises identifying start and end locations of the phrases in the provided content, and the identifying includes performing a dot product attention mechanism parameterizing a probability distribution.

    PEER-TO-PEER SCHOLARSHIP, MENTORSHIP, AND APPRENTICESHIP DISTRIBUTED APPLICATION, METHOD, AND SYSTEM USING A BLOCKCHAIN

    公开(公告)号:US20210110497A1

    公开(公告)日:2021-04-15

    申请号:US17129894

    申请日:2020-12-21

    摘要: A blockchain configuration may provide a simple and secure infrastructure for students to identify subject matter experts as tutors and career mentors, as well as earn scholarship funds in the form of microtransactions of digital currency. One example method may comprise one or more of transmitting a query to a network of devices to respond in exchange for a microtransaction reward of digital currency; receiving a plurality of responses from the network of devices; determining one or more best responses from among the plurality of responses; transmitting the reward to the one or more devices that provided the one or more best responses; combining data related to the query, responses, best answers, and microtransactions into a block of data; and recording the block of data on a blockchain. The method may also include validating the query and plurality of responses in exchange for a microtransaction according to a blockchain proof-of-work configuration.

    METHODS AND SYSTEMS FOR REPRESENTING USAGE OF AN ELECTRONIC LEARNING SYSTEM

    公开(公告)号:US20210082071A1

    公开(公告)日:2021-03-18

    申请号:US17038138

    申请日:2020-09-30

    申请人: D2L Corporation

    IPC分类号: G06Q50/20 G09B5/00 G09B7/02

    摘要: A method and system for representing usage of an electronic learning system. The method and system involve receiving an input indicative of a selection of a property of the electronic learning system to be represented, the property including a course content provided by the electronic learning system and an activity available for that course content; receiving representation parameters that define a scope of the usage to be represented; determining an event count for the property during the period of interest; and generating a usage indicator for the property based at least on the event count. The usage indicator is generally reflective of at least a usage amount of the property during the period of interest.

    Virtual assistant acquisitions and training

    公开(公告)号:US10928976B2

    公开(公告)日:2021-02-23

    申请号:US14293619

    申请日:2014-06-02

    摘要: Techniques and architectures for implementing a team of virtual assistants are described herein. The team may include multiple virtual assistants that are configured with different characteristics, such as different functionality, base language models, levels of training, visual appearances, personalities, and so on. The characteristics of the virtual assistants may be configured by trainers, end-users, and/or a virtual assistant service. The virtual assistants may be presented to end-users in conversation user interfaces to perform different tasks for the users in a conversational manner. The different virtual assistants may adapt to different contexts. The virtual assistants may additionally, or alternatively, interact with each other to carry out tasks for the users, which may be illustrated in conversation user interfaces.

    GLOBAL LANGUAGE EDUCATION AND CONVERSATIONAL CHAT SYSTEM

    公开(公告)号:US20210049922A1

    公开(公告)日:2021-02-18

    申请号:US16993200

    申请日:2020-08-13

    申请人: Charles Isgar

    发明人: Charles Isgar

    摘要: Described is a global language education and conversational chat system. The system includes a user computing device, a language speaker computing device and a server having a memory, wherein the user computing device and the language speaker computing device are coupled to the server through a connection established by an app operating on each of the user computing device and the language speaker computing device. The system operates to connect the user computing device and the language speaker computing device for an audio or an audio/video chat in the language of the language speaker. The system includes components that may provide recording of chats, analysis of chats and reports on proficiency, accuracy, and the like, of the user speaking the language foreign to the user.

    MATCHING APPARATUS USING SYLLABUSES
    120.
    发明申请

    公开(公告)号:US20210042868A1

    公开(公告)日:2021-02-11

    申请号:US16978427

    申请日:2018-08-21

    发明人: Masahiro TAKEUCHI

    摘要: The present disclosure relates to a matching apparatus for calculating a matching score between a company that desires to employ a student and a student that desires to be employed, and the purpose thereof is to calculate a matching score that accurately represents the matching degree between the two by using syllabuses of respective subjects. A job offerer such as a company inputs required skill items by specifying corresponding dictionary nodes “1001” and “1002”. All dictionary nodes are associated in advance with syllabuses having relevance thereto among the syllabuses prepared for the respective subjects. A job seeker such as a student submits information on subjects taken. Associations between the subjects taken and syllabuses thereof are stored.