Shulou(Shulou.com)11/24 Report--

CTOnews.com September 12 news, according to Tencent Health official account reported that Tencent Health recently released its medical model, and released the "intelligent question and answer, family doctor assistant, digital intelligence medical imaging platform and other multi-scene AI product matrix", and drug discovery platform "Yunshen" (iDrug).

▲ Tencent Health official account CTOnews.com according to the official account, this medical model is based on Tencent mixed-yuan model, adding more than 2.85 million medical entities, 12.5 million medical relationships, more than 98% of medical knowledge knowledge graph and medical literature, after 30 million including patients, doctors, pharmaceutical companies and other scenarios and medical process question-and-answer dialogue for multi-task fine-tuning And 360000 intensive learning of tagged data by expert doctors.

Tencent said that its medical model is suitable for scenarios such as copy generation, intelligent question and answer, medical record structure and retrieval, image report and auxiliary diagnosis, and can be embedded in the whole process of medical process. to achieve the overall improvement of medical service level and quality in application scenarios such as department guidance, doctor recommendation, pre-consultation, doctor-patient dialogue, automatic generation of medical records and intelligent hospital customer service.

At present, Shanghai Renji Hospital has taken the lead in using the Tencent medical model, focusing on the aging service of the Internet hospital, to create a highly anthropomorphic virtual digital image "Serena Williams".

In terms of AI driving drug discovery, Tencent claims that its "iDrug" platform already has the ability to accelerate the discovery of both small and macromolecular drugs.

Liu Wei, head of ▲ Tencent Health official account Tencent AIDD technology, said that in terms of protein structure prediction, the "iDrug" platform has developed a new algorithm framework tFold; has developed and launched 70 + ADMET properties in the prediction of ADMET attributes of drugs. Two skeleton transition molecular generation algorithms have been developed to find nM-level lead compounds, which have been effectively proved in 3-4 projects. At the same time, reinforcement learning technology has been introduced to meet 97% of the requirements for drug small molecule generation.

In terms of medical imaging research and application, Tencent Miying comprehensively upgraded the digital medical imaging platform, focusing on cloud application, scientific research and management of digital medical imaging, while equipped with artificial intelligence analysis capability. provide integrated medical imaging solutions for production, learning, research and management, and provide comprehensive support in the field of medical imaging for medical institutions, scientific research institutions and scientific and technological enterprises. The platform will further open more than 20 AI engines developed by Tencent to help scientific research institutions develop and train AI models independently.

Tencent also claimed that at present, Tencent Health Mini Program has connected more than 3000 registrable public hospitals, more than 5000 physical examination institutions, and vaccine services in more than 200 cities; medical insurance electronic vouchers cover more than 800000 institutions and more than 20000 hospitals; and Wechat channels have more than 600 million e-health card users and access to more than 5000 hospitals. Tencent Health further strengthens the connection between users and medical services, further promotes the openness of its capabilities, technologies and products, builds digital medical standards consistent with the industry, and creates a replicable innovation benchmark.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.