Shanghai Lepu Cloudmed Co., Ltd

Beijing Bytedance Network Technology Co., Ltd.

Chinese Academy of Sciences

Lepu Medical Technology (beijing) Co., Ltd.

Jun Cao

Chang Liu

Chuanyan Hu

Yan Jiang

Liang Tian

Tao Liu

Xue Yong Zhang

Kaifeng Zang

Lei Li

Pengfei Zhao

Mingxuan Wang

Weiwei Zhou

Zifang Zhao

Haitao Lu

Baoquan Wang

Zhe Li

Yi Wang

Peihao Zhu

Yue Zhang

Huili Cao

Erbin Wang

Zhiqiang Su

Jiayu Wang

Sen Qian

Tian Chi Zhao

Hongbo Xin

Zhou Qian

Youchao Lu

Zejian Wu

Youchao Lv

Yifang Wang

Tianchi Zhao

Biying Zhang

Hongdai Sun

A method for generating PPG signals may include sequentially performing single-frame red and green channel data calculation on all skin surface video data frame images of a frame image sequence of skin surface video data according to preset red and green light pixel threshold ranges to generate first red and green light signals; performing signal band-pass filtering preprocessing on the first red and green light signals to generate second red and green light digital signals; obtaining a preset signal determination identifier; determining whether to perform signal maximum frequency difference determination on the second red light signal and the second green light signal, and generating a first determination result; when the first determination result is an up-to-standard signal identifier, performing signal-to-noise ratio determination on the second red and/or green light signal to generate a second determination result; and when the second determination result is the up-to-standard signal identifier, generating a PPG signal.

Method and device for generating photoplethysmography signals

Provided are a method and apparatus for translating words in a picture, an electronic device, and a storage medium. The method includes: recognizing words embedded in a target picture to obtain at least one text line, each of which corresponds to one line of words; perform paragraph combination on the at least one text line to obtain at least one text paragraph; translating the at least one text paragraph into at least one target text paragraph in a specified language; and replacing the words in the target picture with the at least one target text paragraph.

Method for translating words in a picture, electronic device, and storage medium

An ECG information processing method and ECG workstation, wherein the method comprises: the ECG workstation receives the ECG data output by an ECG device, the ECG data includes ID of the measured object and the detection time information; perform ECG data analysis on the ECG data to generate report data; receive a report data query input by the user, query corresponding report data according to the user ID of the user, and generate report data query result list data; acquire the selected report data according to the selection instruction, determine output mode information and output format information according to the report output, and, selectively output report conclusion data, report entry data, and/or the partial data or all the data in the report graphic data, and convert the partial data or all the data in data format according to the output format information, to generate report output data.

ECG information processing method and ECG workstation

An automatic recognition and classification method for electrocardiogram heartbeat based on artificial intelligence, comprising: processing a received original electrocardiogram digital signal to obtain heartbeat time sequence data and lead heartbeat data; cutting the lead heartbeat data according to the heartbeat time sequence data to generate lead heartbeat analysis data; performing data combination on the lead heartbeat analysis data to obtain a one-dimensional heartbeat analysis array; performing data dimension amplification and conversion according to the one-dimensional heartbeat analysis array to obtain four-dimensional tensor data; and inputting the four-dimensional tensor data to a trained LepuEcgCatNet heartbeat classification model, to obtain heartbeat classification information. The method overcomes the defect that the conventional method only depends on single lead independent analysis for result summary statistics and thus classification errors are more easily obtained, and the accuracy of the electrocardiogram heartbeat classification is greatly improved.

Automatic recognition and classification method for electrocardiogram heartbeat based on artificial intelligence

An artificial intelligence self-learning-based automatic electrocardiography analysis method and apparatus, the method comprising data preprocessing, heartbeat feature detection, interference signal detection and heartbeat classification based on deep learning, signal quality evaluation and lead combination, heartbeat verification, analysis and calculation of electrocardiography events and parameters, and finally automatic output of reporting data, realizing an automated analysis method having a complete and rapid flow. The automatic electrocardiography analysis method may also record modification information of an automatic analysis result, collect modified data, and feed same back to the depth learning model to continue training, thereby continuously making improvements and improving the accuracy of the automatic analysis method.

Artificial intelligence self-learning-based automatic electrocardiography analysis method and apparatus

An electrocardiogram information dynamic monitoring method and dynamic monitoring system. The method includes a dynamic monitoring device receiving monitoring reference data input by a user or issued by a server; the data collection on a tested object so as to obtain electrocardiogram data of the tested object; the characteristic identification on the electrocardiogram data so as to obtain characteristic signals of the electrocardiogram data, implementing cardiac activity classification on the electrocardiogram data according to the characteristic signals, obtaining cardiac activity classification information according to electrocardiogram basic rule reference data, and generating electrocardiogram event data, wherein the electrocardiogram event data comprises device ID information of the dynamic monitoring device; the dynamic monitoring device determining corresponding electrocardiogram event information according to the electrocardiogram event data, and determining whether the electrocardiogram event information is electrocardiogram abnormality event information; and outputting alarm information when the electrocardiogram event information is electrocardiogram abnormality event information.

Electrocardiogram information dynamic monitoring method and dynamic monitoring system

A detection report data generation method including acquiring event type information of an electrocardiogram event corresponding to electrocardiogram event data, wherein the event data has one or more pieces of event type information; screening the event data according to signal quality evaluation indexes so as to obtain report conclusion data and report entry data; carrying out quality assessment on an event segment included in the event data according to the signal quality evaluation indexes, and determining a pre-selected sample segment according to a quality assessment result; determining position information of an event heart beat in the pre-selected sample segment, and determining segment interception parameters; carrying out interception processing on the pre-selected sample segment according to the segment interception parameters so as to obtain a typical data segment; generating report graphic data according to the typical data segment; and outputting the entry data, the graphic data and the conclusion data.

Detection report data generation method

Provided are a method for acquiring a parallel corpus, an electronic device, and a storage medium. The method includes: acquiring text data in a target document; performing language detection on the text data; in response to the text data including at least two languages, retaining the text data; detecting a distribution proportion of words in each of the at least two languages among the retained text data; in response to each distribution proportion of words in a first language and in a second language being greater than a preset proportion threshold, retaining the detected text data; extracting sentences in the first language as a first sentence set and sentences in the second language as a second sentence set; performing sentence alignment on the first sentence set and the second sentence set; and determining sentence pairs with alignment degrees greater than a preset alignment degree threshold as the parallel corpus.

Method for acquiring a parallel corpus, electronic device, and storage medium

An electrocardiogram information processing method and workstation system. The method includes receiving electrocardiogram data output by multiple devices; performs data analysis on the electrocardiogram data, and generating report data and stores same; receiving a report data query by a user, queries corresponding report data according to a user ID of the user, and generating report result list for display and output; receiving a selection by the user, and obtaining selected report data according to the selection; receiving a report data consultation request input by the user; obtaining a user ID of an associated user corresponding to the user ID according to the report data consultation request, and sending the report data to a user equivalent of the associated user according to the user ID of the associated user; and receiving a consultation result feedback data sent by the user equivalent of the associated user.

Electrocardiogram information processing method and electrocardiogram workstation system

An artificial intelligence self-learning-based static electrocardiography analysis method and apparatus, the method comprising data preprocessing, heartbeat detection, heartbeat classification based on a depth learning method, heartbeat verification, heartbeat waveform feature detection, measurement and analysis of electrocardiography events, and finally automatic output of reporting data, realizing an automated static electrocardiograph analysis method having a complete and rapid flow. The static electrocardiography analysis method can also record modification information of an automatic analysis result, collect modified data, and feed same back to the depth learning model to continue training, thereby continuously making improvements and improving the accuracy of the automatic analysis method.

Artificial intelligence self-learning-based static electrocardiography analysis method and apparatus

An artificial intelligence-based interference recognition method for an electrocardiogram, comprising: cutting and sampling heart beat data of a first data amount, and inputting the heart beat data to be recognized that is obtained by cutting and sampling into an interference recognition binary classification model for interference recognition; in a sequence of the heart beat data, performing signal anomaly determination on a heart beat data segment where an inter-beat interval is greater than or equal to a preset interval determination threshold value, so as to determine whether the heart beat data segment is an abnormal signal; if the heart beat data segment is not an abnormal signal, determining a starting data point and an ending data point of sliding sampling in the heart beat data segment according to a set time with a preset time width, and performing sliding sampling on the data segment from the starting data point until the ending data point so as to obtain multiple sampling data segments; and using each sampling data segment as heart beat data to be recognized for interference recognition.

Artificial intelligence-based interference recognition method for electrocardiogram

A self-learning dynamic electrocardiography analysis method employing artificial intelligence. The method comprises: pre-processing data, performing cardiac activity feature detection, interference signal detection and cardiac activity classification on the basis of a deep learning method, performing signal quality evaluation and lead combination, examining cardiac activity, performing analytic computations on an electrocardiogram event and parameters, and then automatically outputting report data. The method achieves an automatic analysis method for a quick and comprehensive dynamic electrocardiography process, and recording of modification information of an automatic analysis result, while also collecting and feeding back modification data to a deep learning model for continuous training, thereby continuously improving and enhancing the accuracy of the automatic analysis method. Also disclosed is a self-learning dynamic electrocardiography analysis device employing artificial intelligence.

Method and device for self-learning dynamic electrocardiography analysis employing artificial intelligence

A photomultiplier tube including a photocathode, an electron multiplier, an electron collector, and a power lead, wherein the photocathode and the electron multiplier are disposed in a sealed transparent vacuum envelope, the electron collector and the power lead are connected with an external circuit outside the vacuum envelope, the photocathode is formed on the entire inner surface of the vacuum envelope, and the electron multiplier is located on the internal center of the vacuum envelope to receive photoelectrons from the photocathode in all directions for electrons multiplication. Because the effective photocathode area is increased, the detection efficiency of unit light-receiving area is improved.

Growing community of inventors

Beijing, China

Jun Cao