Ricoh Company, Ltd.

Other

Chinese Academy of Sciences

Beijing Jingdong Qianshi Technology Co., Ltd.

Beijing Digital Union Web Science and Technology Company Limited

Yongwei Zhang

Bin Dong

Shanshan Jiang

Lei Ding

Yixuan Tong

Jiashi Zhang

Wei Wang

Yu Wang

Yunkai Deng

Guodong Jin

Kaiyu Liu

Yuping Zhang

Yajun Long

Dacheng Liu

Chunlei Men

Congan Yang

Yu Sha

A method and an apparatus for named entity recognition, and a non-transitory computer-readable recording medium are provided. In the method, text elements are traversed according to a text span to obtain candidate entity words. Then, a class to which the candidate entity word belongs is recognized. The recognizing of the class includes generating a prompt template corresponding to the candidate entity word, and concatenating the text to be recognized and the prompt template to obtain a concatenated text; generating vector representations of the text elements in the concatenated text; generating the vector representation of the candidate entity word according to the vector representations of the text elements of each candidate entity word in the concatenated text, and the vector representation of the text element of the mask word; and classifying the vector representation of the candidate entity word to obtain the class of the candidate entity word.

Method and apparatus for named entity recognition, and non-transitory computer-readable recording medium

Disclosed are a table recognition method and apparatus. The table recognition method includes steps of obtaining an image vision feature and a character content feature of a table image; fusing the image vision feature and the character content feature of the table image to acquire a first fusion feature, and carrying out recognition based on the first fusion feature to acquire a table structure; and performing, based on the table structure, character recognition on the table image to acquire table character contents.

Table recognition method and apparatus and non-transitory computer-readable medium

A method and an apparatus for sequence labeling on an entity text, and a non-transitory computer-readable recording medium are provided. In the method, a start position of an entity text within a target text is determined. Then, a first matrix is generated based on the start position of the entity text. Elements in the first matrix indicates focusable weights of each word with respect to other words in the target text. Then, a named entity recognition model is generated using the first matrix. The named entity recognition model is obtained by training using first training data, the first training data includes word embeddings corresponding to respective texts in a training text set, and the texts are texts whose entity label has been labeled. Then, the target text is input to the named entity recognition model, and probability distribution of the entity label is output.

Method and apparatus for sequence labeling on entity text, and non-transitory computer-readable recording medium

The present disclosure provides a control method of a UAV, a control device of a UAV, and a computer-readable storage medium, and relates to the technical field of UAVs. The control method of a UAV includes: determining a deviation between a vertical mapping point on the ground and a landing point of the UAV, the deviation comprising a deviation in a horizontal axis direction of a camera coordinate system and a deviation in a vertical axis direction of the camera coordinate system; and generating speed control amounts of the UAV in the horizontal axis direction and the vertical axis direction of the camera coordinate system by a controller, using the deviation in the horizontal axis direction and the deviation in the vertical axis direction.

Unmanned aerial vehicle control method, unmanned aerial vehicle control device, and computer readable storage medium

A method and an apparatus for fusing position information, and a non-transitory computer-readable recording medium are provided. In the method, words of an input sentence are segmented to obtain a first sequence of words in the input sentence, and absolute position information of the words in the first sequence is generated. Then, subwords of the words in the first sequence are segmented to obtain a second sequence including subwords, and position information of the subwords in the second sequence are generated, based on the absolute position information of the words in the first sequence, to which the respective subwords belong. Then, the position information of the subwords in the second sequence are fused into a self-attention model to perform model training or model prediction.

Method and apparatus for fusing position information, and non-transitory computer-readable recording medium

A method and apparatus for generating a NLFM signal in real time, and a computer storage medium are disclosed, including: determining a signal parameter of a signal according to a system parameter, the signal parameter includes: a signal bandwidth, a signal pulse width and a PSLR; determining a power spectrum density function according to PSLR; calculating the power spectrum density function to obtain a group delay vector; calculating a frequency axial vector according to a system sampling rate; calculating a time axial vector according to the signal pulse width; performing linear interpolation calculation on the group delay vector to obtain an instantaneous frequency vector; integrating the instantaneous frequency vector to obtain a phase vector; determining a signal time domain discrete vector; and generating a digital signal according to the signal time domain discrete vector, and performing digital-to-analog conversion on the digital signal to obtain the NLFM signal.

Method and apparatus for generating non-linear frequency modulation signal in real time and computer storage medium

This invention provides the download system of APP, determination method of installation type and storage medium. The determination method of the installation types of APP includes: obtaining the installation event of the target APP and the information of the target APP; detecting the device features of the terminal where the target APP is installed and obtaining the application list and application installation history of the terminal, wherein the application list is used to record the information of the application existing in the terminal and the application installation history is used to record the event of installing the APP in the terminal and the information of the installed APP; judging the device type of the terminal according to the device features; using the information of the target APP to match in the application list and application installation history and get the installation status of the target APP in the terminal; determining the installation type of the target APP according to the device type and installation status. The scheme of this invention can enable the application program to identify the quality of promotion channels.

Download system of app, determination method of installation type and storage medium

Knowledge graph processing method and device are disclosed. The method includes steps of obtaining an entity set containing a first entity, a second entity, and relation information; acquiring text information and image information related to the first entity and the second entity; generating a first structural information vector of the first entity and a second structural information vector of the second entity, and creating a first text information vector of the first entity, a first image information vector of the first entity, a second text information vector of the second entity, and a second image information vector of the second entity; and building a joint loss function so as to attain a first target vector of the first entity, a second target vector of the second entity, and a target relation vector of the relation information between the first entity and the second entity.

Knowledge graph processing method and device

Provided are a method and an apparatus for range ambiguity suppression based on orthogonal nonlinear frequency modulation (NLFM) waveforms. The method includes that: according to transmitted orthogonal NLFM signals, a waveform sequence of the transmitted signals corresponding to an obtained echo signal is determined; a set of range matched filters is constructed according to the waveform sequence and the orthogonal NLFM signals; range compression is performed on the echo signal by using the set of range matched filters to obtain range-compressed data; and synthetic aperture radar (SAR) imaging is performed according to the range-compressed data, to obtain an imaging result, and the imaging result is outputted. A non-transitory computer-readable storage medium is also provided.

Method for range ambiguity suppression based on multi-degree-of-freedom frequency modulation signal

A method, an apparatus and an electronic device for performing entity linking, and a non-transitory computer-readable recording medium are provided. The method includes constructing training data including a plurality of sets of labeled data using an existing unambiguous entity database where unambiguous entities corresponding to respective entity words are stored, each set of the labeled data including a text having an entity word and an unambiguous entity linked with the entity word; training an unambiguous entity recognition model whose output is a matching probability between an entity word in a text and an unambiguous entity using the training data; and inputting a text having an entity word to be recognized into the unambiguous entity recognition model, and determining an unambiguous entity linked with the entity word to be recognized based on an output result of the unambiguous entity recognition model.

Growing community of inventors

Beijing, China

Yongwei Zhang