METHOD AND APPARATUS FOR RECOMMENDING DOCUMENT, ELECTRONIC DEVICE AND MEDIUM

    公开(公告)号:EP3961426A3

    公开(公告)日:2022-06-29

    申请号:EP21218467.5

    申请日:2021-12-31

    IPC分类号: G06F16/35

    摘要: The present disclosure provides a method and apparatus of recommending a document, a device, a medium, and a product, relating to fields of intelligent recommendation, deep learning etc. The method of recommending a document includes: acquiring a document operated by a user, as a reference document; determining, from a plurality of initial documents, at least one candidate document for the reference document, wherein a document content of each candidate document is associated with a document content of the reference document, based on preset knowledge system data; and recommending a target document in the at least one candidate document to the user, the target document including a document that the user is currently interested in and a document that the user is interested in after a preset time period.

    METHOD AND APPARATUS FOR SEARCHING INSTANT MESSAGING OBJECT, ELECTRONIC DEVICE AND STORAGE MEDIUM

    公开(公告)号:EP4053715A3

    公开(公告)日:2022-12-07

    申请号:EP22184240.4

    申请日:2022-07-12

    IPC分类号: G06F16/903

    摘要: The disclosure provides a method and apparatus for searching an instant messaging object and a storage medium, and relates to the field of artificial intelligence technologies. The method includes: receiving a search request of a first object, and determining a type of the search request (101); obtaining at least one recall set of the first object based on a client-side search engine in an instant messaging system in response to the type of the search request being a first type (102); obtaining at least one candidate object corresponding to a search keyword in the search request based on the search keyword and the at least one recall set (103); obtaining feature information of each candidate object (104); and responding to the search request by sorting the at least one candidate object based on the feature information (105).

    METHOD AND APPARATUS FOR DENOISING CLICK DATA, ELECTRONIC DEVICE AND STORAGE MEDIUM

    公开(公告)号:EP4123479A3

    公开(公告)日:2023-05-17

    申请号:EP22211845.7

    申请日:2022-12-07

    摘要: The invention relates to technical fields of big data and cloud services. The invention includes: acquiring a set of click data that includes pieces of first click data and a real label for each piece of first click data; extracting a feature vector of each piece of first click data with a graph model; dividing feature vectors into feature vector sets; obtaining trained binary classification models by training binary classification models with the feature vector sets; for each feature vector, obtaining prediction values by predicting the feature vector with the trained binary classification models, and calculating a prediction label of the feature vector based on the prediction values; and removing noise data in the first click data, based on the first click data, the real labels and the prediction labels of the first click data. The invention may denoise click data without event tracking in the application program in advance.

    METHOD AND APPARATUS FOR DENOISING CLICK DATA, ELECTRONIC DEVICE AND STORAGE MEDIUM

    公开(公告)号:EP4123479A2

    公开(公告)日:2023-01-25

    申请号:EP22211845.7

    申请日:2022-12-07

    IPC分类号: G06F16/958

    摘要: The invention relates to technical fields of big data and cloud services. The invention includes: acquiring a set of click data that includes pieces of first click data and a real label for each piece of first click data; extracting a feature vector of each piece of first click data with a graph model; dividing feature vectors into feature vector sets; obtaining trained binary classification models by training binary classification models with the feature vector sets; for each feature vector, obtaining prediction values by predicting the feature vector with the trained binary classification models, and calculating a prediction label of the feature vector based on the prediction values; and removing noise data in the first click data, based on the first click data, the real labels and the prediction labels of the first click data. The invention may denoise click data without event tracking in the application program in advance.

    METHOD AND APPARATUS FOR SEARCHING INSTANT MESSAGING OBJECT, ELECTRONIC DEVICE AND STORAGE MEDIUM

    公开(公告)号:EP4053715A2

    公开(公告)日:2022-09-07

    申请号:EP22184240.4

    申请日:2022-07-12

    IPC分类号: G06F16/903

    摘要: The disclosure provides a method and apparatus for searching an instant messaging object and a storage medium, and relates to the field of artificial intelligence technologies. The method includes: receiving a search request of a first object, and determining a type of the search request (101); obtaining at least one recall set of the first object based on a client-side search engine in an instant messaging system in response to the type of the search request being a first type (102); obtaining at least one candidate object corresponding to a search keyword in the search request based on the search keyword and the at least one recall set (103); obtaining feature information of each candidate object (104); and responding to the search request by sorting the at least one candidate object based on the feature information (105).

    METHOD AND APPARATUS FOR RECOMMENDING DOCUMENT, ELECTRONIC DEVICE AND MEDIUM

    公开(公告)号:EP3961426A2

    公开(公告)日:2022-03-02

    申请号:EP21218467.5

    申请日:2021-12-31

    IPC分类号: G06F16/35

    摘要: The present disclosure provides a method and apparatus of recommending a document, a device, a medium, and a product, relating to fields of intelligent recommendation, deep learning etc. The method of recommending a document includes: acquiring a document operated by a user, as a reference document; determining, from a plurality of initial documents, at least one candidate document for the reference document, wherein a document content of each candidate document is associated with a document content of the reference document, based on preset knowledge system data; and recommending a target document in the at least one candidate document to the user, the target document including a document that the user is currently interested in and a document that the user is interested in after a preset time period.