http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114334018-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_2e2492f44c6b0c6b4ae464d40c75d199 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N10-60 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16C20-70 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16C20-50 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16C10-00 |
filingDate | 2021-12-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f6cc32836bcdd2c6b69fb795ab9e7d00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_50d1cd9e13d101e01123710c56f8c7ff http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_770854314ebbc960dcb1bd98d10e6c56 |
publicationDate | 2022-04-12-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-114334018-A |
titleOfInvention | Method, device and storage medium for obtaining molecular feature description |
abstract | The application relates to a method, a device and a storage medium for obtaining molecular feature description. The method comprises the following steps: acquiring a structural characteristic value of a target molecule; calculating an overlapping matrix based on the minimum Slater group and the structural characteristic value of the target molecule; based on the overlapping matrix, solving a wave function coefficient when the target molecule is used as a quantum system by adopting a semi-empirical quantum mechanical method; according to the wave function coefficient, solving a density matrix when the target molecule is used as a quantum system; regularizing the minimum Slater basis group to obtain a transformation matrix; and obtaining the characteristic description of the target molecule according to the density matrix and the transformation matrix. The technical scheme of the application can quickly acquire the molecular feature description so as to train the deep neural network. |
priorityDate | 2021-12-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Predicate | Subject |
---|---|
isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID414860077 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID6852 |
Total number of triples: 19.