WO2022002029A1 - Drug trend analysis system and method therefor - Google Patents

Drug trend analysis system and method therefor Download PDF

Info

Publication number
WO2022002029A1
WO2022002029A1 PCT/CN2021/103021 CN2021103021W WO2022002029A1 WO 2022002029 A1 WO2022002029 A1 WO 2022002029A1 CN 2021103021 W CN2021103021 W CN 2021103021W WO 2022002029 A1 WO2022002029 A1 WO 2022002029A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
biological
drug
module
file
Prior art date
Application number
PCT/CN2021/103021
Other languages
French (fr)
Chinese (zh)
Inventor
乌玛尚卡尔·希夫尚卡尔
库玛·庞卡
坦·约西亚
汉斯·马库斯
Original Assignee
智慧芽信息科技(苏州)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 智慧芽信息科技(苏州)有限公司 filed Critical 智慧芽信息科技(苏州)有限公司
Publication of WO2022002029A1 publication Critical patent/WO2022002029A1/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/334Query execution
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/10ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Definitions

  • the present application relates to a drug trend analysis system and method thereof, in particular to a drug trend analysis system and method that can analyze the correlation of biological data according to file data.
  • the purpose of the present application is to provide a drug trend analysis system and method that can assist in preliminary analysis or statistics of the content of biological documents, and the system and method can analyze the correlation of biological data according to document data.
  • the purpose of the present application is to provide a drug trend analysis system and method, which can analyze different biological document data (such as patents, scientific literature, etc., but not limited thereto) to obtain a plurality of biological data (such as drug data, biological enterprise data, etc., but not limited thereto), and can establish correlations between different biological data and/or biological file data.
  • biological document data such as patents, scientific literature, etc., but not limited thereto
  • biological data such as drug data, biological enterprise data, etc., but not limited thereto
  • the purpose of the present application is to provide a drug trend analysis system and method, which can further generate correlation charts, statistical charts, etc. according to the correlation between different biological data and/or biological file data, so as to assist users in research and development (such as drugs research and development, etc., but not limited thereto), or assist users in deciding their research direction, research and development strategy/direction, business strategy or business layout.
  • a drug trend analysis method applied to a drug trend analysis system comprising a database and a server, the server accessing the database; the drug trend analysis method comprising: analyzing first file data by an analysis module of the server to obtain the first bioanalytical data, the second bioanalytical data, and a plurality of third bioanalytical data; the association identification module of the server according to at least one of the plurality of third bioanalytical data and the second bioanalytical data data to associate third document data from the database; and associate the first bioanalytical data with the second bioanalytical data, the plurality of third bioanalytical data by the association identification module with the third file data; wherein the analysis module is communicatively connected to the association identification module.
  • the first file data is clinical file data
  • the third file data is patent file data
  • the first bioanalysis data is drug code data or drug name data
  • the second bioanalysis data The data is biological enterprise entity data.
  • the plurality of third biological analysis data are drug data, disease data, gene data, gene sequence data, protein data, enzyme data, organism data, cell line data, cell bank serial number data, and target data, respectively.
  • One of data, structural data, species data, pathway data, and bioenterprise entity data are included in the plurality of third biological analysis data.
  • the drug trend analysis method further includes: analyzing the first file data or the third file data by the analysis module to obtain ninth biological data; associating fourth document data from the database according to the ninth biometric data; and associating the first bioanalytical data with the ninth biometric data and the fourth document by the association identification module data.
  • the first biological analysis data is drug code data
  • the ninth biological data is drug name data
  • the fourth file data is patent file data, clinical file data, scientific publication file data , news file data, and company report file data.
  • the association identification module associates the fourth file data from the database according to at least one of the plurality of third biometric data and the ninth biometric data.
  • the drug trend analysis method further includes: analyzing the first file data by the analysis module to obtain first biological data and second biological data; analyzing the second file data by the analysis module to obtain the third biometric data and the fourth biometric data; the first biometric data is associated with the second biometric data, the third biometric data, the fourth biometric data by the correlation identification module according to the analysis result biological data and the second file data.
  • the analysis result indicates that the similarity between the first biological data and the third biological data is greater than a predetermined similarity threshold.
  • the first biological data and the third biological data are both gene sequence data or protein data
  • the second biological data is drug data
  • the fourth biological data is disease data
  • the drug trend analysis method further includes: generating, by an image rendering module of the server, third image data according to a fifth instruction from the first device, and providing the third image data to the a first device; wherein the third image data includes the first bioanalytical data and the second bioanalytical data and the plurality of third bioanalytical data associated with the first bioanalytical data; wherein the The image rendering module is communicatively connected to the analysis module and the correlation identification module.
  • a drug trend analysis system includes: a database; and a server for accessing the database, the server comprising: an analysis module for analyzing first file data to obtain first biological analysis data, second biological analysis data and a plurality of third biological analysis data bioanalytical data; and a relevancy identification module for correlating third document data from the database according to at least one of the plurality of third bioanalytical data and the second bioanalytical data, the relevancy an identification module and associates the first bioanalytical data with the second bioanalytical data, the plurality of third bioanalytical data and the third file data; wherein the analysis module is in communication with the association identification module.
  • the first file data is clinical file data
  • the third file data is patent file data
  • the first bioanalysis data is drug code data or drug name data
  • the second bioanalysis data The data is biological enterprise entity data.
  • the plurality of third biological analysis data are drug data, disease data, gene data, gene sequence data, protein data, enzyme data, organism data, cell line data, cell bank serial number data, and target data, respectively.
  • One of data, structural data, species data, pathway data, and bioenterprise entity data are included in the plurality of third biological analysis data.
  • the analysis module analyzes the first file data or the third file data to obtain ninth biometric data; wherein the association identification module obtains the data from the ninth biometric data at least according to the ninth biometric data. and the association identification module associates the first biological analysis data with the ninth biological data and the fourth document data.
  • the first biological analysis data is drug code data
  • the ninth biological data is drug name data
  • the fourth file data is patent file data, clinical file data, scientific publication file data , news file data, and company report file data.
  • the association identification module associates the fourth file data from the database according to at least one of the plurality of third biometric data and the ninth biometric data.
  • the analysis module analyzes the first file data to obtain the first biological data and the second biological data; wherein the analysis module analyzes the second file data to obtain the third biological data and the fourth biological data. biometric data; and wherein the association identification module associates the first biometric data with the second biometric data, the third biometric data, the fourth biometric data and the second file data according to the analysis result .
  • the analysis result indicates that the similarity between the first biological data and the third biological data is greater than a predetermined similarity threshold.
  • the first biological data and the third biological data are both gene sequence data or protein data
  • the second biological data is drug data
  • the fourth biological data is disease data
  • the server includes an image rendering module that generates third image data according to a fifth instruction from the first device, and provides the third image data to the first device; wherein the third image data includes the first bioanalytical data and the second bioanalytical data and the plurality of third bioanalytical data associated with the first bioanalytical data; wherein the image rendering module
  • the analysis module, the correlation identification module and the providing module are communicatively connected.
  • a drug trend analysis system includes: a database; and a server for accessing the database; the server includes: an analysis module for analyzing first file data to obtain first biological data and second biological data, and analyzing the second file data to obtain the third biometric data and the fourth biometric data; the correlation identification module associates the first biometric data with the second biometric data, the third biometric data, and the fourth biometric data according to the analysis result and said second file data; and providing a module for associating said first biometric data, said second biometric data associated with said first biometric data, said third biometric data according to a first instruction from a first device biometric data and the fourth biometric data are provided to the first device; wherein the first device is communicatively connected to the server; wherein the server transmits the first biometric data, the second biometric data, the The third biometric data and the fourth biometric data are stored in the database; wherein the analysis module is communicatively connected to the association identification module and the providing module; and wherein the association identification module is communicatively connected to the providing
  • the database stores a plurality of biological data
  • the analysis module analyzes the first file data and the second file data, it is obtained according to at least one biological data among the plurality of biological data.
  • the first biometric data or the second biometric data or the third biometric data or the fourth biometric data is obtained according to at least one biological data among the plurality of biological data.
  • the analysis module includes a first natural language processing module, and the analysis module obtains the first biological data or the second biological data or the The third biometric data or the fourth biometric data.
  • the first biological data, the second biological data, the third biological data and the fourth biological data are drug data, drug code data, drug name data, disease data, gene data, respectively.
  • the correlation identification module includes a second natural language processing module, and the correlation identification module obtains the analysis result through the second natural language processing module.
  • associating the first biometric data with the second biometric data, the third biometric data, the fourth biometric data and the second file data according to the analysis result is performed by:
  • the correlation identification module generates first correlation data according to the analysis result, and the server stores the first correlation data in the database; wherein the first correlation data is associated with the first biological body data, and the first association data indicates that the first biometric data is associated with the second biometric data, the third biometric data, the fourth biometric data, and the second file data.
  • the server includes an image rendering module that generates first image data according to a second instruction from the first device, and provides the first image data to the first apparatus, said first image data comprising said first biometric data and said second biometric data, said third biometric data and said fourth biometric data associated with said first biometric data; wherein said image rendering A module communicatively connects the analysis module, the association identification module and the providing module.
  • the association identification module associates the first biological data with the first file data and the second file data according to the analysis result.
  • the association identification module when the first biometric data, the second biometric data, the third biometric data, and the fourth biometric data are all associated with fifth biometric data, and the first biometric data, the When the second biometric data, the third biometric data, and the fourth biometric data are data of different contents, the association identification module generates the second association data and the third association data, and the server does not storing the second association data and the third association data to the database; wherein the second association data indicates that the first biometric data has a first association with the fourth biometric data; The third association data indicates that the third biometric data and the second biometric data have a second association; wherein the first biometric data and the third biometric data are biometric data of the same type, and the The second biometric data is the same type of biometric data as the fourth biometric data.
  • the first biometric data and the third biometric data are drug data
  • the second biometric data and the fourth biometric data are disease data
  • the database stores a plurality of biological data
  • the server further includes a statistical module, the statistical module generates statistical data according to the plurality of biological data; wherein the providing module is based on data from the first device.
  • the third instruction of provides the statistical data to the first device; wherein the statistical module communicatively connects the analysis module, the correlation identification module and the providing module.
  • the server includes an image rendering module that generates second image data according to the statistical data; wherein the providing module renders the first image data according to a fourth instruction from the first device. Two image data are provided to the first device; wherein the image rendering module is communicatively connected to the analysis module, the correlation identification module, the statistics module and the providing module.
  • the server further includes a biological data classification module, and the biological data classification module combines the first biological data, the second biological data and the second biological data with the third natural language processing module of the biological data classification module The data, the third biological data and the fourth biological data are classified; wherein the biological data classification module communicatively connects the analysis module, the correlation identification module and the providing module.
  • the first document data and the second document data are one of patent document data, clinical document data, scientific publication document data, news document data, and company report document data, respectively.
  • the analysis result indicates that the similarity between the first biological data and the third biological data is greater than a predetermined similarity threshold.
  • the first biological data and the third biological data are both gene sequence data or protein data
  • the second biological data is drug data
  • the fourth biological data is disease data
  • a drug trend analysis method applied to a drug trend analysis system comprising a database and a server, the server accessing the database; the drug trend analysis method comprising: analyzing first file data by an analysis module of the server to obtain The first biological data and the second biological data; the second file data is analyzed by the analysis module to obtain the third biological data and the fourth biological data; the first biological data, the second biological data are analyzed by the server data, the third biological data and the fourth biological data are stored in the database; the first biological data is associated with the first biological data according to the analysis result of the analysis module by the correlation identification module of the server the second biometric data, the third biometric data, the fourth biometric data and the second file data; and the first biometric data is converted by the providing module of the server according to the first instruction from the first device , the second biometric data, the third biometric data and the fourth biometric data associated with the first biometric data are provided to the first device; wherein the first device is communicatively connected to the server; Wherein the analysis module is communicatively connected with the correlation
  • the database stores a plurality of biological data
  • the analysis module analyzes the first file data and the second file data, obtains the biological data according to at least one biological data of the plurality of biological data. to output the first biometric data or the second biometric data or the third biometric data or the fourth biometric data.
  • the analysis module includes a first natural language processing module, and the analysis module obtains the first biological data or the second biological data or the The third biometric data or the fourth biometric data.
  • the first biological data, the second biological data, the third biological data and the fourth biological data are drug data, drug code data, drug name data, disease data, gene data, respectively.
  • the correlation identification module includes a second natural language processing module, and the correlation identification module obtains the analysis result through the second natural language processing module.
  • associating the first biometric data with the second biometric data, the third biometric data, the fourth biometric data and the second file data according to the analysis result is performed by:
  • the relevancy identification module generates first relevancy data according to the analysis result, and the server stores the first relevancy data in the database; wherein the first relevancy data is related to the first relevancy data biometric data, and the first association data indicates that the first biometric data is associated with the second biometric data, the third biometric data, the fourth biometric data, and the second file data.
  • the drug trend analysis method further includes: generating, by an image rendering module of the server, first image data according to a second instruction from the first device, and providing the first image data to the first device, the first image data comprising the first biometric data and the second biometric data, the third biometric data and the fourth biometric data associated with the first biometric data;
  • the image rendering module is communicatively connected to the analysis module, the correlation identification module and the providing module.
  • the association identification module associates the first biological data with the first file data and the second file data according to the analysis result.
  • the drug trend analysis method further includes: when the first biological data, the second biological data, the third biological data and the fourth biological data are all associated with the fifth biological data , and when the first biometric data, the second biometric data, the third biometric data and the fourth biometric data are data of different contents, the association identification module generates the second association data and third association data, the server stores the second association data and the third association data in the database; wherein the second association data indicates that the first biological data is associated with the first biometric data Four biometric data has a first association; the third association data indicates that the third biometric data has a second association with the second biometric data; wherein the first biometric data and the third biometric data are the same type of biological data, and the second biological data and the fourth biological data are the same type of biological data.
  • the first biometric data and the third biometric data are drug data
  • the second biometric data and the fourth biometric data are disease data
  • the database stores a plurality of biological data;
  • the drug trend analysis method further comprises: generating, by a statistical module of the server, statistical data according to the plurality of biological data;
  • the third instruction of the first device provides the statistical data to the first device; wherein the statistics module communicatively connects the analysis module, the correlation identification module and the providing module.
  • the drug trend analysis method further includes: generating, by an image rendering module of the server, second image data according to the statistical data; and generating, by the providing module, based on fourth image data from the first device The instruction provides the second image data to the first device; wherein the image rendering module communicatively connects the analysis module, the correlation identification module, the statistics module and the providing module.
  • the drug trend analysis method further comprises: by the biological data classification module of the server through the third natural language processing module of the biological data classification module, the first biological data, the second biological data The second biological data, the third biological data and the fourth biological data are classified; wherein the biological data classification module communicatively connects the analysis module, the correlation identification module and the providing module.
  • the first document data and the second document data are one of patent document data, clinical document data, scientific publication document data, news document data, and company report document data, respectively.
  • the analysis result indicates that the similarity between the first biological data and the third biological data is greater than a predetermined similarity threshold.
  • the first biological data and the third biological data are both gene sequence data or protein data
  • the second biological data is drug data
  • the fourth biological data is disease data
  • FIG. 1 shows a system architecture diagram of the drug trend analysis system exemplified in the present application.
  • FIG. 2 is a partial screen diagram of the first device displaying biological data provided by the drug trend analysis system exemplified in the present application.
  • FIG. 3 is a partial screen diagram of the first device displaying biological data provided by the drug trend analysis system exemplified in the present application.
  • FIG. 4 shows a schematic diagram of part of the screen of the drug trend analysis system exemplified in the present application.
  • FIG. 5 is a partial screen schematic diagram of the drug trend analysis system exemplified in this application.
  • FIG. 6A is a partial screen schematic diagram of the drug trend analysis system exemplified in the present application.
  • FIG. 6B is a partial screen schematic diagram of the drug trend analysis system exemplified in the present application.
  • FIG. 6C is a partial screen diagram of the drug trend analysis system exemplified in the present application.
  • FIG. 6D is a partial screen diagram of the drug trend analysis system exemplified in the present application.
  • FIG. 7 is a partial screen schematic diagram of the drug trend analysis system exemplified in the application.
  • FIG. 8 is a partial screen schematic diagram of the drug trend analysis system exemplified in the application.
  • FIG. 9 is a partial screen schematic diagram of the drug trend analysis system exemplified in the application.
  • FIG. 10 is a schematic diagram of part of the screen of the drug trend analysis system of the example of the application.
  • FIG. 11 is a flow chart of the drug trend analysis method exemplified in the application.
  • FIG. 12 is a flow chart of the drug trend analysis method exemplified in the application.
  • FIG. 13A is a schematic diagram of a specific embodiment of the drug trend analysis method of the present application.
  • FIG. 13B is a schematic diagram of a specific embodiment of the drug trend analysis method of the present application.
  • FIG. 13C is a schematic diagram of a specific embodiment of the drug trend analysis method of the present application.
  • compositions, process, method, article or device containing a plurality of listed elements is not necessarily limited to only those listed elements, but may include compositions that are not expressly listed but are , process, method, article or other element inherent in the device.
  • the drug trend analysis system 100 includes a database 110 and a server 120 , wherein the database 110 stores a plurality of biological data, and the server 120 can access the database 110 .
  • the server 120 includes an analysis module 121 , a correlation identification module 123 , a provision module 125 , a biological data classification module 126 , a statistics module 127 and an image rendering module 129 .
  • the analysis module 121 includes a first natural language processing (NLP) module 121A, the correlation identification module 123 includes a second natural language processing module 123A, and the biological data classification module 126 includes a third natural language processing module 126A.
  • NLP natural language processing
  • the analysis module 121 is communicatively connected to the correlation identification module 123 and the providing module 125
  • the correlation identification module 123 is communicatively connected to the providing module 125
  • the statistics module 127 is communicatively connected to the analysis module 121
  • the image drawing module 129 communicates with the connection analysis module 121
  • the biological data classification module 126 communicates with the connection analysis module 121, the association identification module 123, the statistics module 127, and the image rendering module 129 and provision module 125.
  • the drug trend analysis system 100 includes one or more processors, and implements the database 110 , the server 120 , the analysis module 121 , the first natural language processing module 121A, the correlation Sex recognition module 123 , second natural language processing module 123A, providing module 125 , biological data classification module 126 , third natural language processing module 126A, statistics module 127 and image rendering module 129 .
  • the analysis module 121 analyzes the first file data to obtain the first biological data and the second biological data, and analyzes the second file data to obtain the third biological data and the fourth biological data.
  • the server then stores the first biometric data, the second biometric data, the third biometric data and the fourth biometric data to the database 110 .
  • the analysis module 121 obtains the first biological data and the second biological data according to at least one of the plurality of biological data stored in the database 110 , at least one of the third biometric data and the fourth biometric data.
  • the analysis module 121 can obtain the biological data stored in the database 110 by the biological data that is the same as the first biological data to generate (or analyze) the first biological data.
  • the analysis module 121 analyzes the first document data and/or the second document data
  • the natural language processing module 121A is used to obtain the first biological data, the second biological data, the third biological data and the At least one of the fourth biometric data.
  • the first document data and/or the second document data may be one of patent documents, clinical trial documents, scientific publication documents, news documents and company report documents, but not limited thereto.
  • the first biological data and/or the second biological data and/or the third biological data and/or the fourth biological data may be drug data, drug code data, drug name data, disease data, genetic data , gene sequence data, protein data, enzyme data, organism data, cell line data, cell bank serial number data, target data, structure data, species data, pathway data and biological enterprise entity data.
  • the first biological data can be a drug data
  • the second biological data can be a protein data
  • the third biological data can be a disease data
  • the fourth biological data can be a biological enterprise entity data.
  • the bio-enterprise entity may be a company, academic unit, institution, government agency or individual, but not limited thereto, for example, a bio-enterprise entity may be an applicant for a drug patent (this applicant may be an individual, a company or an organization, etc. ).
  • the first biometric data or the second biometric data or the third biometric data or the fourth biometric data can also be other bio-related data.
  • the association identification module 123 associates the first biometric data with the second biometric data, the third biometric data and the fourth biometric data according to the analysis result.
  • the correlation identification module 123 obtains the analysis result through the second natural language processing module 123A.
  • the analysis result of the correlation identification module 123 is that both the first biometric data and the second biometric data come from the first file data. Accordingly, the association identification module 123 associates the first biometric data with the second biometric data according to the analysis result.
  • the analysis result of the correlation identification module 123 is that the content of the second biometric data and the third biometric data are the same, the first biometric data and the second biometric data are both from the first file data, and the third biometric data and the fourth biometric data are all derived from the second file data. Accordingly, the association identification module 123 associates the first biometric data with the second biometric data, the third biometric data and the fourth biometric data according to the analysis result, and associates the first file data with the second file data.
  • the analysis result of the association identification module 123 is that the second biometric data is associated with the third biometric data (for example, the database stores a association data indicating that the second biometric data is associated with the third biometric data) , the first biometric data and the second biometric data both come from the first file data, and the third biometric data and the fourth biometric data both come from the second file data. Accordingly, the association identification module 123 associates the first biometric data with the second biometric data, the third biometric data and the fourth biometric data according to the analysis result, and associates the first file data with the second file data.
  • associating the first biometric data with the second biometric data, the third biometric data and the fourth biometric data according to the analysis result is performed by the association identification module 123 to generate the first association according to the analysis result
  • the server 120 stores the first correlation data in the database 110 .
  • the first correlation data is related to the first biological data, and the first correlation data indicates that the first biological data is related to the second biological data, the third biological data and the fourth biological data.
  • the first association data includes three association data, which respectively indicate that the first biometric data is related to the second biometric data, the first biometric data is related to the third biometric data and the first biometric data A relationship is associated with the fourth biological data.
  • the providing module 125 associates the first biometric data with the second biometric data and the third biometric data associated with the first biometric data according to the first instruction from the first device (not shown).
  • the fourth biometric data is provided to the first device.
  • the first device is communicatively connected to the server 120 .
  • the first device may be a desktop computer, a smart phone, or a notebook computer, but not limited thereto.
  • the first instruction is an instruction of the user to take the first biological data as a retrieval target or an analysis target.
  • the association identification module 123 associates the first biological data with the first file data and the second file data according to the analysis result.
  • the providing module 125 provides the first biometric data, the second biometric data, the third biometric data and the fourth biometric data associated with the first biometric data to the first biometric data according to the first instruction from the first device (not shown).
  • the first file data and the second file data associated with the first biological data can be provided to the first device according to the file providing instruction from the first device (or the first file data and the second file data can be directly provided.
  • the two file data are provided to the first device without the need for the first device to additionally input a file providing instruction).
  • the biological data classification module 126 classifies the first biological data, the second biological data, the third biological data and the fourth biological data through the third natural language processing module 126A of the biological data classification module .
  • the third natural language processing module 126A of the biological data classification module classifies the first biological data and/or the second biological data and/or the third biological data and/or the fourth biological data as drugs data, disease data, gene data, protein data, enzyme data, organism data, cell line data, cell bank serial number data, target data, structure data, species data, pathway data and One of the biological enterprise entity data.
  • the image rendering module 129 generates the first image data according to the second instruction from the first device, and provides the first image data to the first device (in different specific embodiments, by providing The module 125 or the image rendering module 129 provides the first image data to the first device).
  • the first image data includes the first biometric data and second biometric data, third biometric data and fourth biometric data associated with the first biometric data.
  • the first image data when the first image data is displayed, the first image data also shows that the first biometric data is related to the second biometric data, the third biometric data and the fourth biometric data.
  • the first image data is a knowledge structure graph.
  • the association identification module 123 when the first biometric data, the second biometric data, the third biometric data and the fourth biometric data are all associated with the fifth biometric data, and the first biometric data, the second biometric data, and the third biometric data
  • the association identification module 123 When the fourth biometric data is data of different content, the association identification module 123 generates the second association data and the third association data, and the server 120 stores the second association data and the third association data in the database 110 .
  • the second correlation data indicates that the first biological data has a first correlation with the fourth biological data
  • the third correlation data indicates that the third biological data has a second correlation with the second biological data.
  • the first biometric data and the third biometric data are the same type of biometric data, and the second biometric data and the fourth biometric data are the same type of biometric data.
  • the first biometric data and the third biometric data are drug data, and the second biometric data and the fourth biometric data are disease data.
  • the first association indicates that the first biometric data may be applicable to the fourth biometric data
  • the third association data indicates that the third biometric data may be applicable to the second biometric data. Therefore, the correlation identification module 123 can find out the possible new application fields of a certain medicine according to different file data.
  • the analysis result indicates that the similarity between the first biological data and the third biological data is greater than a predetermined similarity threshold, which means that the first biological data and the third biological data have a great similarity or correlation .
  • the first biological data and the third biological data are both gene sequence data
  • the second biological data is drug data (eg, drug name data or drug code data)
  • the fourth biological data is disease data.
  • the first biological data and the third biological data are both protein data
  • the second biological data is drug data (eg, drug name data or drug code data)
  • the fourth biological data is disease data.
  • the correlation identification module 123 can find out the possible new application fields of a certain medicine according to different file data, or can find out the existing medicines that may be useful for a certain disease (eg, COVID 19 (Coronavirus Disease)). .
  • the statistics module 127 generates statistical data (this is the first statistical data) according to a plurality of biological data stored in the database 110 .
  • the providing module 125 may provide the statistical data to the first device according to the third instruction from the first device.
  • the image rendering module 129 may generate the second image data according to the statistical data.
  • the providing module may provide the second image data to the first device according to the fourth instruction from the first device.
  • the database 110 also stores a plurality of file data.
  • the statistics module 127 may generate the second statistical data according to the plurality of document data stored in the database 110 .
  • the providing module 125 may provide at least one of the plurality of file data stored in the database 110 to the first device according to an instruction of the first device.
  • the providing module 125 may provide the second statistical data to the first device according to another instruction of the first device.
  • the second image data is a knowledge structure graph.
  • the analysis module 121 may analyze the first document data to obtain first bioanalytical data, second bioanalytical data and a plurality of third bioanalytical data.
  • the association identification module 123 can associate the third document data from the database 110 according to at least one of the plurality of third bioanalytical data and the second bioanalytical data.
  • the association identification module 123 further associates the first bioanalytical data with the second bioanalytical data, the plurality of third bioanalytical data, and the third document data.
  • the first file data is clinical file data
  • the third file data is patent file data
  • the first bioanalysis data is drug data (for example, it can be drug code data or drug name data)
  • the second bioanalysis data is drug data.
  • the data is biological enterprise entity data.
  • the plurality of third biological analysis data are respectively drug data, disease data, gene data, gene sequence data, protein data, enzyme data, organism data, cell line data, cell bank serial number data, label data.
  • the analysis module 121 may analyze the first file data or the third file data to derive ninth biological data.
  • the correlation identification module 123 can associate the fourth document data from the database 110 according to at least the ninth biological data, and the correlation identification module 123 can associate the first biological analysis data with the ninth biological data and the fourth document data .
  • the first biological analysis data is drug code data
  • the ninth biological data is drug name data.
  • the fourth document data is one of patent document data, clinical document data, scientific publication document data, news document data, and company report document data.
  • the association identification module 123 can associate the fourth document data from the database 110 according to at least one of the plurality of third biometric analysis data and the ninth biometric data.
  • the analysis module 121 may analyze the first document data to obtain the first biological data and the second biological data.
  • the analysis module 121 can analyze the second file data to obtain the third biological data and the fourth biological data.
  • the association identification module 123 can associate the first biometric data with the second biometric data, the third biometric data, the fourth biometric data and the second file data according to the analysis result.
  • the analysis result indicates that the similarity between the first biometric data and the third biometric data is greater than a predetermined similarity threshold, which means that the first biometric data and the third biometric data have a great similarity or Relevance.
  • the first biological data and the third biological data are both gene sequence data
  • the second biological data is drug data (eg, drug name data or drug code data)
  • the fourth biological data is disease data.
  • the first biological data and the third biological data are both protein data
  • the second biological data is drug data (eg, drug name data or drug code data)
  • the fourth biological data is disease data.
  • the correlation identification module 123 can find out the possible new application fields of a certain medicine according to different file data, or can find out the existing medicines that may be useful for a certain disease (eg, COVID 19 (Coronavirus Disease)) .
  • the image rendering module 129 of the server 120 may generate the third image data according to the fifth instruction from the first device, and provide the third image data to the first device.
  • the third image data includes first bioanalytical data and second bioanalytical data and a plurality of third bioanalytical data associated with the first bioanalytical data.
  • the third image data further includes ninth biological data, first file data, third file data and fourth file data.
  • FIG. 2 illustrates a partial screen diagram of the first device displaying the biological data provided by the drug trend analysis system of the example of the present application.
  • the providing module provides the first biometric data, the second biometric data associated with the first biometric data, the third biometric data and the third biometric data according to the first instruction 212 from the first device.
  • the biometric data, the fourth biometric data, and the first file data and the second file data associated with the first biometric data are provided to the first device.
  • FIG. 2 shows a picture displayed on the display of the first device.
  • the link 211 includes the first biological data
  • the link 213 includes the second biological data
  • the link 215 includes the third biological data
  • the link 217 includes the fourth biological data
  • the link 214 includes the first file data
  • the link 216 includes the first file data. Include second file data.
  • FIG. 3 illustrates a partial screen diagram of a specific embodiment in which the first device displays the biological data provided by the drug trend analysis system of the present application.
  • the providing module of the drug trend analysis system converts the first biological data, the second biological data associated with the first biological data, The third biometric data, the fourth biometric data, and the first and second file data associated with the first biometric data are provided to the first device.
  • FIG. 3 shows a picture displayed on the display of the first device.
  • the link 312 includes the first biometric data
  • the link 314 includes the second biometric data and the third biometric data
  • the link 316 includes the fourth biometric data
  • the link 311 includes the first file data and the second file data.
  • FIG. 4 illustrates a partial screen diagram of a specific embodiment of the drug trend analysis system of the present application.
  • the biological data classification module classifies each biological data
  • the user can search or query the biological data through the links 411 - 417 , and can search or query the document data through the links 421 - 423 .
  • the picture of the drug trend analysis system can be displayed on the display of the first device.
  • FIG. 5 illustrates a partial screen diagram of a specific embodiment of the drug trend analysis system of the present application.
  • the drug trend analysis system has classified biological data through the biological data classification module, and has generated the first statistical data and the second statistical data according to the biological data and the document data through the statistical module, so as to achieve various differences analysis. Therefore, the user can view different analysis results through the links 511-516.
  • FIG. 6A to FIG. 6D illustrate some schematic diagrams of different specific embodiments of the drug trend analysis system of the present application.
  • the drug trend analysis system has classified the biological data through the biological data classification module, and has generated the first statistical data and the second statistical data according to the biological data and the file data through the statistical module, so as to achieve various analyze. Therefore, the user can view different analysis results or statistical results by selection.
  • patent document data eg, see images 611, 612
  • view analysis or statistics of ontology biological data eg, see image 613
  • drugs Analytical results or statistical results of biological data of drug classes
  • optionally viewing analytical results or statistical results of biological data of the clinical trial study phase
  • FIG. 7 illustrates a partial screen diagram of a specific embodiment of the drug trend analysis system of the present application.
  • the user can know from the image 713 that the drug trend analysis analyzes the ventricular biological data according to the data of multiple files and is related to 123 literature file data, 265 patent file data, 422 news file data, 54 serial number biological data data, 23 compound biological data, 87 clinical trial biological data, and 25 drug data.
  • the user can view the target biological data, drug biological data, and patent document data simultaneously associated with the ventricular biological data and the left ventricular biological data according to the images 715 , 717 , and 719 between the image 711 and the image 713 , respectively.
  • FIG. 8 illustrates a partial screen diagram of a specific embodiment of the drug trend analysis system of the present application.
  • the statistics module of the drug trend analysis system can count the number of occurrences of different biological data in the file data of different companies in different years, and then generate a plurality of corresponding statistical data.
  • the image drawing module of the drug trend analysis system can generate the second image 810 according to the statistical data.
  • the point 812 in the image 810 represents the number of times the biological data "neoplasm" appeared in the file data associated with the biological enterprise entity data "PFIZER” in 2017 (the darker the color, the more appearance). more times).
  • the point 814 in the image 810 indicates the number of times the disease data "virus disease” appeared in the document data associated with the bio-enterprise entity data "GSK Corporation” in 2011 (lighter colors indicate occur less frequently).
  • FIG. 9 illustrates a partial screen diagram of a specific embodiment of the drug trend analysis system of the present application.
  • the statistics module of the drug trend analysis system can count the number of clinical trials of different biological enterprise entities for different biological data, and then generate a plurality of corresponding statistical data.
  • the image drawing module of the drug trend analysis system can generate the second image 910 according to the statistical data.
  • the section 912 in the image 910 indicates the number of clinical trials of the biological enterprise entity data "Merk Sharp & Dohme Corp.” for the disease data "gastrointestinal disease”.
  • FIG. 10 illustrates a partial screen diagram of a specific embodiment of the drug trend analysis system of the present application.
  • the image 1010 displays the first biometric data 1011 and the second biometric data 1012 , the third biometric data 1013 and the fourth biometric data 1014 associated with the first biometric data 1011 .
  • Image 1010 and arrows 1016 indicate that the second biometric data 1012 is associated with the first biometric data 1011
  • arrows 1017 indicate that the third biometric data 1013 is associated with the first biometric data 1011
  • arrows 1018 indicate that the fourth biometric data 1014 is associated with the first biometric data 1011 Biodata 1011.
  • a drug trend analysis method 1100 is applied to a drug trend analysis system including a database and a server, wherein the server accesses the database, and the server includes an analysis module, a correlation identification module, and a provision module.
  • the module is communicatively connected to the correlation identification module and the providing module, the correlation identification module is communicatively connected to the providing module, and the server is communicatively connected to the first device.
  • the drug trend analysis method 1100 starts at step 1110, where the analysis module of the server analyzes the first file data to obtain the first biological data and the second biological data.
  • step 1120 the analysis module analyzes the second file data to obtain the third biological data and the fourth biological data.
  • step 1130 the server stores the first biometric data, the second biometric data, the third biometric data and the fourth biometric data in the database.
  • the database stores a plurality of biological data
  • the analysis module obtains the first biological data and/or the second biological data according to at least one of the plurality of biological data data and/or third biometric data and/or fourth biometric data.
  • the analysis module includes a first natural language processing module, and the analysis module obtains the first biological data and/or the second biological data and/or the third biological data and/or the natural language processing module through the natural language processing module. or fourth biometric data.
  • the first biological data, the second biological data, the third biological data and the fourth biological data are drug data, drug code data, drug name data, disease data, gene data, gene sequence data, protein data, respectively.
  • the first biological data may be drug data
  • the second biological data may be pathway data
  • the third biological data may be target data
  • the fourth biological data may be biological enterprise entity data.
  • the biological enterprise entity may be a company, an academic unit, an institution, a government agency or an individual, but not limited thereto.
  • the first biometric data or the second biometric data or the third biometric data or the fourth biometric data can also be other bio-related data.
  • the association identification module of the server associates the first biometric data with the second biometric data, the third biometric data and the fourth biometric data according to the analysis result.
  • the correlation identification module includes a second natural language processing module, and the correlation identification module obtains the analysis result through the second natural language processing module.
  • the associating the first biological data with the second biological data, the third biological data and the fourth biological data according to the analysis result is that the correlation identification module generates the first correlation data according to the analysis result
  • the server stores the first association data to the database.
  • the first association data is associated with the first biometric data, and the first association data indicates that the first biometric data is associated with the second biometric data, the third biometric data and the fourth biometric data.
  • the association identification module associates the first biological data with the first file data and the second file data according to the analysis result.
  • the providing module of the server provides the first biometric data, the second biometric data related to the first biometric data, the third biometric data and the fourth biometric data to the user according to the first instruction from the first device. first device.
  • the server of the drug trend analysis system includes an image drawing module, and the image drawing module communicates with the analysis module, the correlation identification module and the providing module.
  • the drug trend analysis method further includes the steps of: generating, by an image rendering module of the server, first image data according to a second instruction from the first device, and providing the first image data to the first device.
  • the first image data includes first biometric data and second biometric data, third biometric data and fourth biometric data associated with the first biometric data.
  • the drug trend analysis method further includes the following steps: when the first biological data, the second biological data, the third biological data and the fourth biological data are all related to the fifth biological data, and the first biological data,
  • the association identification module When the second biometric data, the third biometric data, and the fourth biometric data are data of different contents, the association identification module generates the second association data and the third association data, and the server stores the second association data and the third association data.
  • the relational data is stored in the database.
  • the second correlation data indicates that the first biological data has a first correlation with the fourth biological data
  • the third correlation data indicates that the third biological data has a second correlation with the second biological data.
  • the first biometric data and the third biometric data are the same type of biometric data
  • the second biometric data and the fourth biometric data are the same type of biometric data.
  • the first biological data and the third biological data are drug data
  • the second biological data and the fourth biological data are disease data.
  • the database stores a plurality of biological data
  • the server of the drug trend analysis system includes a statistics module and an image drawing module.
  • the statistics module communicates and connects the analysis module, the correlation identification module and the providing module
  • the image drawing module communicates and connects the analysis module, the correlation identification module, the statistics module and the providing module.
  • the drug trend analysis method further includes the following steps: generating statistical data according to a plurality of biological data by a statistical module of the server; providing the statistical data to the first device by the providing module according to a third instruction from the first device; image drawing module of the server generating second image data according to the statistical data; and providing, by the providing module, the second image data to the first device according to a fourth instruction from the first device.
  • the server of the drug trend analysis system includes a biological data classification module, wherein the biological data classification module communicates with the analysis module, the correlation identification module and the providing module.
  • the drug trend analysis method further includes the following steps: the first biological data, the second biological data, the third biological data and the fourth biological data are processed by the biological data classification module of the server through the third natural language processing module of the biological data classification module. Classification.
  • the analysis result indicates that the similarity between the first biometric data and the third biometric data is greater than a predetermined similarity threshold, which indicates that the first biometric data and the third biometric data have a great similarity or correlation sex.
  • the first biological data and the third biological data are both gene sequence data
  • the second biological data is drug data (eg, drug name data or drug code data)
  • the fourth biological data is disease data.
  • the first biological data and the third biological data are both protein data
  • the second biological data is drug data (eg, drug name data or drug code data)
  • the fourth biological data is disease data.
  • the correlation identification module 123 can find out the possible new application fields of a certain medicine according to different file data, or can find out the existing medicines that may be useful for a certain disease (eg, COVID 19 (Coronavirus Disease)). .
  • FIG. 12 illustrates a flow chart of a specific embodiment of the drug trend analysis method of the present application.
  • a drug trend analysis method 1200 is applied to a drug trend analysis system including a database and a server, wherein the server accesses the database.
  • the drug trend analysis method 1200 starts at step 1210, and the analysis module of the server analyzes the first file data to obtain first bioanalytical data, second bioanalytical data and a plurality of third bioanalytical data.
  • the association identification module of the server associates the third file data from the database according to at least one of the plurality of third bioanalysis data and the second bioanalysis data.
  • the association identifying module associates the first bioanalytical data with the second bioanalytical data, a plurality of third bioanalytical data and the third file data.
  • the analysis module communicates with the correlation identification module.
  • the first file data is clinical file data
  • the third file data is patent file data
  • the first bio-analysis data is drug code data or drug name data
  • the second bio-analysis data is bio-enterprise entity data.
  • the plurality of third biological analysis data are respectively drug data, disease data, gene data, gene sequence data, protein data, enzyme data, organism data, cell line data, cell bank serial number data, and target data. , structural data, species data, pathway data, and one of bioenterprise entity data.
  • the drug trend analysis method 1200 further includes: analyzing the first file data or the third file data by the analyzing module to obtain ninth biological data; and correlate the fourth file data with the correlation identification module; and correlate the first biological analysis data with the ninth biological data and the fourth file data by the correlation identification module.
  • the first biological analysis data is drug code data
  • the ninth biological data is drug name data.
  • the fourth document data is one of patent document data, clinical document data, scientific publication document data, news document data and company report document data.
  • the association identification module associates the fourth document data from the database according to at least one of the plurality of third biometric analysis data and the ninth biometric data.
  • the drug trend analysis method 1200 further includes: analyzing the first file data by the analysis module to obtain the first biological data and the second biological data; analyzing the second file data by the analysis module to obtain the third biological data data and the fourth biological data; the correlation identification module associates the first biological data with the second biological data, the third biological data, the fourth biological data and the second file data according to the analysis result.
  • the analysis result indicates that the similarity between the first biometric data and the third biometric data is greater than a predetermined similarity threshold, which means that the first biometric data and the third biometric data have a great similarity or correlation sex.
  • the first biological data and the third biological data are both gene sequence data
  • the second biological data is drug data (eg, drug name data or drug code data)
  • the fourth biological data is disease data.
  • the first biological data and the third biological data are both protein data
  • the second biological data is drug data (for example, drug name data or drug code data)
  • the fourth biological data is disease data.
  • the drug trend analysis method 1200 further includes: generating, by the image rendering module of the server, third image data according to the fifth instruction from the first device, and providing the third image data to the first device.
  • the third image data includes first bioanalytical data and second bioanalytical data and a plurality of third bioanalytical data associated with the first bioanalytical data.
  • the image drawing module communicates with the analysis module and the correlation identification module.
  • the third image data further includes ninth biological data, first file data, third file data and fourth file data.
  • FIG. 13A illustrates a schematic diagram of a specific embodiment of the drug trend analysis method of the present application.
  • the analysis module of the server can first analyze the drug code data 1311 , the biological enterprise entity data 1312 and the third biological analysis data 1313 , 1314 , 1315 , 1316 and 1317 from the clinical file data 1310 .
  • the clinical file data 1310 is the first file data
  • the drug code data 1311 is the first bioanalysis data
  • the biological enterprise entity data 1312 is the second bioanalysis data.
  • the third bioanalytical data 1313 is disease data indicating that the drugs in the clinical file data 1310 are available for osteoporosis.
  • the association identification module of the server can obtain the associated patent document data 1322 , 1324 , 1326 according to at least one of the third biometric analysis data 1313 , 1314 , 1315 , 1316 , and 1317 and the biological enterprise entity data 1312 .
  • the association identification module may derive associated scientific publication file data 1331- 1336.
  • drug name data 1339 may be derived from scientific publication file data 1332 by the analysis module.
  • the association identification module may not only derive the associated patent document data or scientific publication document from at least one of the third bioanalytical data 1313 , 1314 , 1315 , 1316 , 1317 and/or the biological enterprise entity data 1312 Data, the correlation identification module can also obtain news file data, company report file data, etc. according to at least one of the third bioanalytical data 1313, 1314, 1315, 1316, 1317 and/or the bio-enterprise entity data 1312. This is limited.
  • FIG. 13C illustrates a schematic diagram of a specific embodiment of the drug trend analysis method of the present application.
  • the analysis module can analyze the sequence 1340 of drugs in the clinical document data 1310 from the document data obtained by the association identification module.
  • the correlation identification module can further correlate various related document data 1351-1356 (in this example, patent document data, etc., but it is not limited in practice).
  • the drug trend analysis system can use the obtained bioanalytical data, document data (such as patent document data, etc., but not limited thereto) and related data of document data (such as the filing date of patent document data, applicant, etc.) data) to analyze and predict trends for this drug.

Abstract

A drug trend analysis system, which can perform analysis targeting different biological file data (such as patents and scientific literature, but not limited thereto) to obtain a plurality of pieces of biological data (such as drug data and biological enterprise data, but not limited thereto), and can establish correlations between different biological data and/or biological file data. In addition, the drug trend analysis system can further generate correlation charts, statistical charts, etc. according to the correlations between the different biological data and/or biological file data, so as to assist a user with research and development (such as drug research and development, but not limited thereto), or assist the user with determining a research direction, a research and development strategy/direction, a business strategy or a business layout.

Description

药物趋势分析系统及其方法Drug trend analysis system and method therefor
本申请要求于2020年6月29日提交中国专利局,申请号为2020106052823,申请名称为“药物趋势分析系统及其方法”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。This application claims the priority of the Chinese patent application filed on June 29, 2020 with the application number 2020106052823 and the application name is "Drug Trend Analysis System and Method", the entire contents of which are incorporated in this application by reference .
技术领域technical field
本申请涉及药物趋势分析系统及其方法,尤其涉及可根据文件数据以分析出生物数据之关联性的药物趋势分析系统及其方法。The present application relates to a drug trend analysis system and method thereof, in particular to a drug trend analysis system and method that can analyze the correlation of biological data according to file data.
背景技术Background technique
目前从临床试验到批准药物的典型时间约为7至10年。而在此期间,相关信息可能仅会出现在不易被人发现的专利文件或其他文件中。因此,相关研究人员或机构很可能不会注意到所述些文件中记载的相关信息。此外,即便相关研究人员或机构发现所述些文件,仍可能因为文件过多、数据量过于庞大或繁杂而无法有效的了解所述些文件中所载的内容。对此,将需要一种可协助对生物文件内容进行初步分析或统计的药物趋势分析系统及方法。The typical time from clinical trials to approved drugs is currently around 7 to 10 years. During this time, the relevant information may only appear in patent documents or other documents that are not easily discovered. Therefore, the relevant researchers or institutions may not be aware of the relevant information recorded in these documents. In addition, even if the relevant researchers or institutions find these documents, they may not be able to effectively understand the contents contained in the documents because of the excessive number of documents, the large or complicated data volume. In this regard, there will be a need for a drug trend analysis system and method that can assist in the preliminary analysis or statistics of the content of biological documents.
发明内容SUMMARY OF THE INVENTION
本申请的目的在于提供一种可协助对生物文件内容进行初步分析或统计的药物趋势分析系统及方法,所述系统及方法可根据文件数据以分析出生物数据的关联性。The purpose of the present application is to provide a drug trend analysis system and method that can assist in preliminary analysis or statistics of the content of biological documents, and the system and method can analyze the correlation of biological data according to document data.
本申请的目的在于提供一种药物趋势分析系统及方法,其可针对不同的生物文件数据(例如专利、科学文献等,但不以此为限)进行分析,以得出多个生物数据(例如药物数据、生物企业数据等,但不以此为限),并可建立不同生物数据及/或生物文件数据间的关联性。The purpose of the present application is to provide a drug trend analysis system and method, which can analyze different biological document data (such as patents, scientific literature, etc., but not limited thereto) to obtain a plurality of biological data (such as drug data, biological enterprise data, etc., but not limited thereto), and can establish correlations between different biological data and/or biological file data.
本申请的目的在于提供一种药物趋势分析系统及方法,可进一步根据不同生物资料及/或生物文件数据间的关联性以产生关联性图表、统计图表等,藉以协助使用者进行研发(例如药物研发等,但不以此为限),或协助使用者决定其研究方向、研发策略/方向、商业策略或商业布局。The purpose of the present application is to provide a drug trend analysis system and method, which can further generate correlation charts, statistical charts, etc. according to the correlation between different biological data and/or biological file data, so as to assist users in research and development (such as drugs research and development, etc., but not limited thereto), or assist users in deciding their research direction, research and development strategy/direction, business strategy or business layout.
本申请的上述目的通过以下技术手段来实现。The above object of the present application is achieved by the following technical means.
一种药物趋势分析方法,应用于包含数据库以及服务器的药物趋势分析系统,所述服务器访问所述数据库;所述药物趋势分析方法包括:由所述服务器的分析模块分析第一文件数据以得出第一生物分析数据、第二生物分析数据与多个第三生物分析数据;由所述服务器的关联性识别模块根据所述多个第三生物分析数据其中至少一者以及所述第二生物分析数据,以自所述数据库中关联出第三文件数据;以及由所述关联性识别模块将所述第一生物分析数据关联于所述第二生物分析数据、所述多个第三生物分析数据与所述第三文件数据;其中所述分析模块通信连接所述关联性识别模块。A drug trend analysis method, applied to a drug trend analysis system comprising a database and a server, the server accessing the database; the drug trend analysis method comprising: analyzing first file data by an analysis module of the server to obtain the first bioanalytical data, the second bioanalytical data, and a plurality of third bioanalytical data; the association identification module of the server according to at least one of the plurality of third bioanalytical data and the second bioanalytical data data to associate third document data from the database; and associate the first bioanalytical data with the second bioanalytical data, the plurality of third bioanalytical data by the association identification module with the third file data; wherein the analysis module is communicatively connected to the association identification module.
在一实施例中,所述第一文件数据为临床文件数据,所述第三文件数据为专利文件数据,所述第一生物分析数据为药物代号数据或药物名称数据,所述第二生物分析数据为生物企业实体数据。In one embodiment, the first file data is clinical file data, the third file data is patent file data, the first bioanalysis data is drug code data or drug name data, and the second bioanalysis data The data is biological enterprise entity data.
在一实施例中,所述多个第三生物分析数据分别为药物数据、疾病数据、基因数据、基因序列数据、蛋白质数据、酶数据、有机体数据、细胞株数据、细胞库序号数据、标靶数据、结构数据、物种数据、途径数据以及生物企业实体数据其中一者。In one embodiment, the plurality of third biological analysis data are drug data, disease data, gene data, gene sequence data, protein data, enzyme data, organism data, cell line data, cell bank serial number data, and target data, respectively. One of data, structural data, species data, pathway data, and bioenterprise entity data.
在一实施例中,所述药物趋势分析方法进一步包括:由所述分析模块分析所述第一文件数据或所述第三文件数据以得出第九生物数据;由所述关联性识别模块至少根据所述第九生物数据以自所述数据库中关联出第四文件数据;以及由所述关联性识别模块将所述第一生物分析数据关联于所述第九生物数据与所述第四文件数据。In one embodiment, the drug trend analysis method further includes: analyzing the first file data or the third file data by the analysis module to obtain ninth biological data; associating fourth document data from the database according to the ninth biometric data; and associating the first bioanalytical data with the ninth biometric data and the fourth document by the association identification module data.
在一实施例中,所述第一生物分析数据为药物代号数据,所述第九生物数据为药物名称数据,其中所述第四文件数据为专利文件数据、临床文件数据、科学出版物文件数据、新闻文件数据以及公司报告文件数据其中一者。In one embodiment, the first biological analysis data is drug code data, the ninth biological data is drug name data, and the fourth file data is patent file data, clinical file data, scientific publication file data , news file data, and company report file data.
在一实施例中,所述关联性识别模块根据所述多个第三生物分析数据其中至少一者以及所述第九生物数据,以自所述数据库中关联出所述第四文件数据。In one embodiment, the association identification module associates the fourth file data from the database according to at least one of the plurality of third biometric data and the ninth biometric data.
在一实施例中,所述药物趋势分析方法进一步包括:由所述分析模块分析所述第一文件数据以得出第一生物数据与第二生物数据;由所述分析模块分析第二文件数据以得出第三生物数据与第四生物数据;由所述关联性识别模块根据分析结果将所述第一生物数据关联于所述第二生物数据、所述第三生物数据、所述第四生物数据与所述第二文件数据。In one embodiment, the drug trend analysis method further includes: analyzing the first file data by the analysis module to obtain first biological data and second biological data; analyzing the second file data by the analysis module to obtain the third biometric data and the fourth biometric data; the first biometric data is associated with the second biometric data, the third biometric data, the fourth biometric data by the correlation identification module according to the analysis result biological data and the second file data.
在一实施例中,所述分析结果指出所述第一生物数据与所述第三生物数据的相似度大于预定的相似度临界值。In one embodiment, the analysis result indicates that the similarity between the first biological data and the third biological data is greater than a predetermined similarity threshold.
在一实施例中,所述第一生物数据与所述第三生物数据均为基因序列数据或均为蛋白质数据,所述第二生物数据为药物数据,所述第四生物数据为疾病数据。In one embodiment, the first biological data and the third biological data are both gene sequence data or protein data, the second biological data is drug data, and the fourth biological data is disease data.
在一实施例中,所述药物趋势分析方法进一步包括:由所述服务器的图像绘制模块根据来自第一装置的第五指令产生第三图像数据,并将所述第三图像数据提供给所述第一装置;其中所述第三图像数据包含所述第一生物分析数据以及关联于所述第一生物分析数据的所述第二生物分析数据与所述多个第三生物分析数据;其中所述图像绘制模块通信连接所述分析模块与所述关联性识别模块。In one embodiment, the drug trend analysis method further includes: generating, by an image rendering module of the server, third image data according to a fifth instruction from the first device, and providing the third image data to the a first device; wherein the third image data includes the first bioanalytical data and the second bioanalytical data and the plurality of third bioanalytical data associated with the first bioanalytical data; wherein the The image rendering module is communicatively connected to the analysis module and the correlation identification module.
一种药物趋势分析系统包括:数据库;以及服务器,访问所述数据库,所述服务器包含:分析模块,分析第一文件数据以得出第一生物分析数据、第二生物分析数据与多个第三生物分析数据;以及关联性识别模块,根据所述多个第三生物分析数据其中至少一者以及所述第二生物分析数据,以自所述数据库中关联出第三文件数据,所述关联性识别模块并将所述第一生物分析数据关联于所述第二生物分析数据、所述多个第三生物分析数据与所述第三文件数据;其中所述分析模块通信连接所述关联性识别模块。A drug trend analysis system includes: a database; and a server for accessing the database, the server comprising: an analysis module for analyzing first file data to obtain first biological analysis data, second biological analysis data and a plurality of third biological analysis data bioanalytical data; and a relevancy identification module for correlating third document data from the database according to at least one of the plurality of third bioanalytical data and the second bioanalytical data, the relevancy an identification module and associates the first bioanalytical data with the second bioanalytical data, the plurality of third bioanalytical data and the third file data; wherein the analysis module is in communication with the association identification module.
在一实施例中,所述第一文件数据为临床文件数据,所述第三文件数据为专利文件数据,所述第一生物分析数据为药物代号数据或药物名称数据,所述第二生物分析数据为生物企业实体数据。In one embodiment, the first file data is clinical file data, the third file data is patent file data, the first bioanalysis data is drug code data or drug name data, and the second bioanalysis data The data is biological enterprise entity data.
在一实施例中,所述多个第三生物分析数据分别为药物数据、疾病数据、基因数据、基因序列数据、蛋白质数据、酶数据、有机体数据、细胞株数据、细胞库序号数据、标靶数据、结构数据、物种数据、途径数据以及生物企业实体数据其中一者。In one embodiment, the plurality of third biological analysis data are drug data, disease data, gene data, gene sequence data, protein data, enzyme data, organism data, cell line data, cell bank serial number data, and target data, respectively. One of data, structural data, species data, pathway data, and bioenterprise entity data.
在一实施例中,所述分析模块分析所述第一文件数据或所述第三文件数据以得出第九生物数据;其中所述关联性识别模块至少根据所述第九生物数据以自所述数据库中关联出第四文件数据;且其中所述关联性识别模块将所述第一生物分析数据关联于所述第九生物数据与所述第四文件数据。In one embodiment, the analysis module analyzes the first file data or the third file data to obtain ninth biometric data; wherein the association identification module obtains the data from the ninth biometric data at least according to the ninth biometric data. and the association identification module associates the first biological analysis data with the ninth biological data and the fourth document data.
在一实施例中,所述第一生物分析数据为药物代号数据,所述第九生物数据为药物名称数据,其中所述第四文件数据为专利文件数据、临床文件数据、科学出版物文件数据、新闻文件数据以及公司报告文件数据其中一者。In one embodiment, the first biological analysis data is drug code data, the ninth biological data is drug name data, and the fourth file data is patent file data, clinical file data, scientific publication file data , news file data, and company report file data.
在一实施例中,所述关联性识别模块根据所述多个第三生物分析数据其中至少一者以及所述第九生物数据,以自所述数据库中关联出所述第四文件数据。In one embodiment, the association identification module associates the fourth file data from the database according to at least one of the plurality of third biometric data and the ninth biometric data.
在一实施例中,所述分析模块分析所述第一文件数据以得出第一生物数据与第二生物数据;其中所述分析模块分析第二文件数据以得出第三生物数据与第四生物数据;且其中所述关联性识别模块根据分析结果将所述第一生物数据关联于所述第二生物数据、所述第三生物数据、所述第四生物数据与所述第二文件数据。In one embodiment, the analysis module analyzes the first file data to obtain the first biological data and the second biological data; wherein the analysis module analyzes the second file data to obtain the third biological data and the fourth biological data. biometric data; and wherein the association identification module associates the first biometric data with the second biometric data, the third biometric data, the fourth biometric data and the second file data according to the analysis result .
在一实施例中,所述分析结果指出所述第一生物数据与所述第三生物数据的相似度大于预定的相似度临界值。In one embodiment, the analysis result indicates that the similarity between the first biological data and the third biological data is greater than a predetermined similarity threshold.
在一实施例中,所述第一生物数据与所述第三生物数据均为基因序列数据或均为蛋白质数据,所述第二生物数据为药物数据,所述第四生物数据为疾病数据。In one embodiment, the first biological data and the third biological data are both gene sequence data or protein data, the second biological data is drug data, and the fourth biological data is disease data.
在一实施例中,所述服务器包含图像绘制模块,所述图像绘制模块根据来自第一装置的第五指令产生第三图像数据,并将所述第三图像数据提供给所述第一装置;其中所述第三图像数据包含所述第一生物分析数据以及关联于所述第一生物分析数据的所述第二生物分析数据与所述多个第三生物分析数据;其中所述图像绘制模块通信连接所述分析模块、所述关联性识别模块与所述提供模块。In one embodiment, the server includes an image rendering module that generates third image data according to a fifth instruction from the first device, and provides the third image data to the first device; wherein the third image data includes the first bioanalytical data and the second bioanalytical data and the plurality of third bioanalytical data associated with the first bioanalytical data; wherein the image rendering module The analysis module, the correlation identification module and the providing module are communicatively connected.
一种药物趋势分析系统包括:数据库;以及服务器,访问所述数据库;所述服务器包括:分析模块,分析第一文件数据以得出第一生物数据和第二生物数据,并分析第二文件数据以得出第三生物数据和第四生物数据;关联性识别模块,根据分析结果将所述第一生物数据关联于所述第二生物数据、所述第三生物数据、所述第四生物数据与所述第二文件数据;以及提供模块,根据来自第一装置的第一指令,将所述第一生物数据、关联于所述第一生物数据的所述第二生物数据、所述第三生物数据和所述第四生物数据提供给所述第一装置;其中所述第一装置通信连接所述服务器;其中所述服务器将所述第一生物数据、所述第二生物数据、所述第三生物数据和所述第四生物数据存储至所述数据库;其中所述分析模块通信连接所述关联性识别模块和所述提供模块;以及其中所述关联性识别模块通信连接所述提供模块。A drug trend analysis system includes: a database; and a server for accessing the database; the server includes: an analysis module for analyzing first file data to obtain first biological data and second biological data, and analyzing the second file data to obtain the third biometric data and the fourth biometric data; the correlation identification module associates the first biometric data with the second biometric data, the third biometric data, and the fourth biometric data according to the analysis result and said second file data; and providing a module for associating said first biometric data, said second biometric data associated with said first biometric data, said third biometric data according to a first instruction from a first device biometric data and the fourth biometric data are provided to the first device; wherein the first device is communicatively connected to the server; wherein the server transmits the first biometric data, the second biometric data, the The third biometric data and the fourth biometric data are stored in the database; wherein the analysis module is communicatively connected to the association identification module and the providing module; and wherein the association identification module is communicatively connected to the providing module .
在一实施例中,所述数据库存储多个生物数据,所述分析模块分析所述第一文件数据和所述第二文件数据时,根据所述多个生物数据中的至少一个生物数据得出所述第一生物数据或所述第二生物数据或所述第三生物数据或所述第四生物数据。In one embodiment, the database stores a plurality of biological data, and when the analysis module analyzes the first file data and the second file data, it is obtained according to at least one biological data among the plurality of biological data. The first biometric data or the second biometric data or the third biometric data or the fourth biometric data.
在一实施例中,所述分析模块包括第一自然语言处理学模块,所述分析模块通过所述自然语言处理学模块以得出所述第一生物数据或所述第二生物数据或所述第三生物数据或所述第四生物数据。In one embodiment, the analysis module includes a first natural language processing module, and the analysis module obtains the first biological data or the second biological data or the The third biometric data or the fourth biometric data.
在一实施例中,所述第一生物数据、所述第二生物数据、所述第三生物数据和所述第四生物数据分别为药物数据、药物代号数据、药物名称数据、疾病数据、基因数据、基因序列数据、蛋白质数据、酶数据、有机体数据、细胞株数据、细胞库序号数据、标靶数据、结构数据、物种数据、途径数据以及生物企业实体数据其中一个。In one embodiment, the first biological data, the second biological data, the third biological data and the fourth biological data are drug data, drug code data, drug name data, disease data, gene data, respectively. One of data, gene sequence data, protein data, enzyme data, organism data, cell line data, cell bank serial number data, target data, structure data, species data, pathway data and biological enterprise entity data.
在一实施例中,所述关联性识别模块包括第二自然语言处理学模块,所述关联性识别 模块通过所述第二自然语言处理学模块得出所述分析结果。In one embodiment, the correlation identification module includes a second natural language processing module, and the correlation identification module obtains the analysis result through the second natural language processing module.
在一实施例中,根据所述分析结果将所述第一生物数据关联于所述第二生物数据、所述第三生物数据、所述第四生物数据和所述第二文件数据,是由所述关联性识别模块根据所述分析结果产生第一关联性数据,所述服务器并将所述第一关联性数据存储至所述数据库;其中所述第一关联性数据关联所述第一生物数据,且所述第一关联性数据指出所述第一生物数据关联所述第二生物数据、所述第三生物数据、所述第四生物数据和所述第二文件数据。In one embodiment, associating the first biometric data with the second biometric data, the third biometric data, the fourth biometric data and the second file data according to the analysis result is performed by: The correlation identification module generates first correlation data according to the analysis result, and the server stores the first correlation data in the database; wherein the first correlation data is associated with the first biological body data, and the first association data indicates that the first biometric data is associated with the second biometric data, the third biometric data, the fourth biometric data, and the second file data.
在一实施例中,所述服务器包括图像绘制模块,所述图像绘制模块根据来自所述第一装置的第二指令产生第一图像数据,并将所述第一图像数据提供给所述第一装置,所述第一图像数据包括所述第一生物数据以及关联所述第一生物数据的所述第二生物数据、所述第三生物数据和所述第四生物数据;其中所述图像绘制模块通信连接所述分析模块、所述关联性识别模块和所述提供模块。In one embodiment, the server includes an image rendering module that generates first image data according to a second instruction from the first device, and provides the first image data to the first apparatus, said first image data comprising said first biometric data and said second biometric data, said third biometric data and said fourth biometric data associated with said first biometric data; wherein said image rendering A module communicatively connects the analysis module, the association identification module and the providing module.
在一实施例中,所述关联性识别模块根据所述分析结果将所述第一生物数据关联所述第一文件数据和所述第二文件数据。In one embodiment, the association identification module associates the first biological data with the first file data and the second file data according to the analysis result.
在一实施例中,当所述第一生物数据、所述第二生物数据、所述第三生物数据和所述第四生物数据均关联第五生物数据,且所述第一生物数据、所述第二生物数据、所述第三生物数据和所述第四生物数据均为不同内容的数据时,所述关联性识别模块产生第二关联性数据以及第三关联性数据,所述服务器并将所述第二关联性数据以及所述第三关联性数据存储至所述数据库;其中所述第二关联性数据指出所述第一生物数据与所述第四生物数据具有第一关联性;所述第三关联性数据指出所述第三生物数据与所述第二生物数据具有第二关联性;其中所述第一生物数据与所述第三生物数据为同类型的生物数据,所述第二生物数据与所述第四生物数据为同类型的生物数据。In one embodiment, when the first biometric data, the second biometric data, the third biometric data, and the fourth biometric data are all associated with fifth biometric data, and the first biometric data, the When the second biometric data, the third biometric data, and the fourth biometric data are data of different contents, the association identification module generates the second association data and the third association data, and the server does not storing the second association data and the third association data to the database; wherein the second association data indicates that the first biometric data has a first association with the fourth biometric data; The third association data indicates that the third biometric data and the second biometric data have a second association; wherein the first biometric data and the third biometric data are biometric data of the same type, and the The second biometric data is the same type of biometric data as the fourth biometric data.
在一实施例中,所述第一生物数据与所述第三生物数据为药物数据,所述第二生物数据与所述第四生物数据为疾病数据。In one embodiment, the first biometric data and the third biometric data are drug data, and the second biometric data and the fourth biometric data are disease data.
在一实施例中,所述数据库存储多个生物数据,所述服务器进一步包括统计模块,所述统计模块根据所述多个生物数据产生统计数据;其中所述提供模块根据来自所述第一装置的第三指令将所述统计数据提供给所述第一装置;其中所述统计模块通信连接所述分析模块、所述关联性识别模块与所述提供模块。In one embodiment, the database stores a plurality of biological data, and the server further includes a statistical module, the statistical module generates statistical data according to the plurality of biological data; wherein the providing module is based on data from the first device. The third instruction of provides the statistical data to the first device; wherein the statistical module communicatively connects the analysis module, the correlation identification module and the providing module.
在一实施例中,所述服务器包括图像绘制模块,所述图像绘制模块根据所述统计数据产生第二图像数据;其中所述提供模块根据来自所述第一装置的第四指令将所述第二图像 数据提供给所述第一装置;其中所述图像绘制模块通信连接所述分析模块、所述关联性识别模块、所述统计模块与所述提供模块。In one embodiment, the server includes an image rendering module that generates second image data according to the statistical data; wherein the providing module renders the first image data according to a fourth instruction from the first device. Two image data are provided to the first device; wherein the image rendering module is communicatively connected to the analysis module, the correlation identification module, the statistics module and the providing module.
在一实施例中,所述服务器进一步包括生物数据分类模块,所述生物数据分类模块通过所述生物数据分类模块的第三自然语言处理学模块将所述第一生物数据、所述第二生物数据、所述第三生物数据以及所述第四生物数据进行分类;其中所述生物数据分类模块通信连接所述分析模块、所述关联性识别模块与所述提供模块。In one embodiment, the server further includes a biological data classification module, and the biological data classification module combines the first biological data, the second biological data and the second biological data with the third natural language processing module of the biological data classification module The data, the third biological data and the fourth biological data are classified; wherein the biological data classification module communicatively connects the analysis module, the correlation identification module and the providing module.
在一实施例中,所述第一文件数据与所述第二文件数据分别为专利文件数据、临床文件数据、科学出版物文件数据、新闻文件数据以及公司报告文件数据其中一者。In one embodiment, the first document data and the second document data are one of patent document data, clinical document data, scientific publication document data, news document data, and company report document data, respectively.
在一实施例中,所述分析结果指出所述第一生物数据与所述第三生物数据的相似度大于预定的相似度临界值。In one embodiment, the analysis result indicates that the similarity between the first biological data and the third biological data is greater than a predetermined similarity threshold.
在一实施例中,所述第一生物数据与所述第三生物数据均为基因序列数据或均为蛋白质数据,所述第二生物数据为药物数据,所述第四生物数据为疾病数据。In one embodiment, the first biological data and the third biological data are both gene sequence data or protein data, the second biological data is drug data, and the fourth biological data is disease data.
一种药物趋势分析方法,应用于包括数据库以及服务器的药物趋势分析系统,所述服务器访问所述数据库;所述药物趋势分析方法包括:由所述服务器的分析模块分析第一文件数据以得出第一生物数据与第二生物数据;由所述分析模块分析第二文件数据以得出第三生物数据与第四生物数据;由所述服务器将所述第一生物数据、所述第二生物数据、所述第三生物数据与所述第四生物数据存储至所述数据库;由所述服务器的关联性识别模块根据所述分析模块的分析结果将所述第一生物数据关联于所述第二生物数据、所述第三生物数据、所述第四生物数据和所述第二文件数据;以及由所述服务器的提供模块根据来自第一装置的第一指令,将所述第一生物数据、关联于所述第一生物数据的所述第二生物数据、所述第三生物数据与所述第四生物数据提供给所述第一装置;其中所述第一装置通信连接所述服务器;其中所述分析模块通信连接所述关联性识别模块与所述提供模块;其中所述关联性识别模块通信连接所述提供模块。A drug trend analysis method, applied to a drug trend analysis system comprising a database and a server, the server accessing the database; the drug trend analysis method comprising: analyzing first file data by an analysis module of the server to obtain The first biological data and the second biological data; the second file data is analyzed by the analysis module to obtain the third biological data and the fourth biological data; the first biological data, the second biological data are analyzed by the server data, the third biological data and the fourth biological data are stored in the database; the first biological data is associated with the first biological data according to the analysis result of the analysis module by the correlation identification module of the server the second biometric data, the third biometric data, the fourth biometric data and the second file data; and the first biometric data is converted by the providing module of the server according to the first instruction from the first device , the second biometric data, the third biometric data and the fourth biometric data associated with the first biometric data are provided to the first device; wherein the first device is communicatively connected to the server; Wherein the analysis module is communicatively connected with the correlation identification module and the providing module; wherein the correlation identification module is communicatively connected with the providing module.
在一实施例中,所述数据库存储多个生物数据,所述分析模块分析所述第一文件数据与所述第二文件数据时,根据所述多个生物数据中的至少一个生物数据以得出所述第一生物数据或所述第二生物数据或所述第三生物数据或所述第四生物数据。In one embodiment, the database stores a plurality of biological data, and when the analysis module analyzes the first file data and the second file data, obtains the biological data according to at least one biological data of the plurality of biological data. to output the first biometric data or the second biometric data or the third biometric data or the fourth biometric data.
在一实施例中,所述分析模块包括第一自然语言处理学模块,所述分析模块通过所述自然语言处理学模块以得出所述第一生物数据或所述第二生物数据或所述第三生物数据或所述第四生物数据。In one embodiment, the analysis module includes a first natural language processing module, and the analysis module obtains the first biological data or the second biological data or the The third biometric data or the fourth biometric data.
在一实施例中,所述第一生物数据、所述第二生物数据、所述第三生物数据与所述第 四生物数据分别为药物数据、药物代号数据、药物名称数据、疾病数据、基因数据、基因序列数据、蛋白质数据、酶数据、有机体数据、细胞株数据、细胞库序号数据、标靶数据、结构数据、物种数据、途径数据以及生物企业实体数据其中一者。In one embodiment, the first biological data, the second biological data, the third biological data and the fourth biological data are drug data, drug code data, drug name data, disease data, gene data, respectively. One of data, gene sequence data, protein data, enzyme data, organism data, cell line data, cell bank serial number data, target data, structure data, species data, pathway data and biological enterprise entity data.
在一实施例中,所述关联性识别模块包括第二自然语言处理学模块,所述关联性识别模块通过所述第二自然语言处理学模块以得出所述分析结果。In one embodiment, the correlation identification module includes a second natural language processing module, and the correlation identification module obtains the analysis result through the second natural language processing module.
在一实施例中,根据所述分析结果将所述第一生物数据关联于所述第二生物数据、所述第三生物数据、所述第四生物数据和所述第二文件数据,是由所述关联性识别模块根据所述分析结果产生第一关联性数据,所述服务器并将所述第一关联性数据存储至所述数据库;其中所述第一关联性数据关联于所述第一生物数据,且所述第一关联性数据指出所述第一生物数据关联于所述第二生物数据、所述第三生物数据、所述第四生物数据和所述第二文件数据。In one embodiment, associating the first biometric data with the second biometric data, the third biometric data, the fourth biometric data and the second file data according to the analysis result is performed by: The relevancy identification module generates first relevancy data according to the analysis result, and the server stores the first relevancy data in the database; wherein the first relevancy data is related to the first relevancy data biometric data, and the first association data indicates that the first biometric data is associated with the second biometric data, the third biometric data, the fourth biometric data, and the second file data.
在一实施例中,所述药物趋势分析方法进一步包括:由所述服务器的图像绘制模块根据来自所述第一装置的第二指令产生第一图像数据,并将所述第一图像数据提供给所述第一装置,所述第一图像数据包括所述第一生物数据以及关联于所述第一生物数据的所述第二生物数据、所述第三生物数据与所述第四生物数据;其中所述图像绘制模块通信连接所述分析模块、所述关联性识别模块与所述提供模块。In one embodiment, the drug trend analysis method further includes: generating, by an image rendering module of the server, first image data according to a second instruction from the first device, and providing the first image data to the first device, the first image data comprising the first biometric data and the second biometric data, the third biometric data and the fourth biometric data associated with the first biometric data; Wherein, the image rendering module is communicatively connected to the analysis module, the correlation identification module and the providing module.
在一实施例中,所述关联性识别模块根据所述分析结果将所述第一生物数据关联所述第一文件数据与所述第二文件数据。In one embodiment, the association identification module associates the first biological data with the first file data and the second file data according to the analysis result.
在一实施例中,所述药物趋势分析方法进一步包括:当所述第一生物数据、所述第二生物数据、所述第三生物数据与所述第四生物数据均关联于第五生物数据,且所述第一生物数据、所述第二生物数据、所述第三生物数据与所述第四生物数据均为不同内容的数据时,所述关联性识别模块产生第二关联性数据以及第三关联性数据,所述服务器将所述第二关联性数据以及所述第三关联性数据存储至所述数据库;其中所述第二关联性数据指出所述第一生物数据与所述第四生物数据具有第一关联性;所述第三关联性数据指出所述第三生物数据与所述第二生物数据具有第二关联性;其中所述第一生物数据与所述第三生物数据为同类型的生物数据,所述第二生物数据与所述第四生物数据为同类型的生物数据。In one embodiment, the drug trend analysis method further includes: when the first biological data, the second biological data, the third biological data and the fourth biological data are all associated with the fifth biological data , and when the first biometric data, the second biometric data, the third biometric data and the fourth biometric data are data of different contents, the association identification module generates the second association data and third association data, the server stores the second association data and the third association data in the database; wherein the second association data indicates that the first biological data is associated with the first biometric data Four biometric data has a first association; the third association data indicates that the third biometric data has a second association with the second biometric data; wherein the first biometric data and the third biometric data are the same type of biological data, and the second biological data and the fourth biological data are the same type of biological data.
在一实施例中,所述第一生物数据与所述第三生物数据为药物数据,所述第二生物数据与所述第四生物数据为疾病数据。In one embodiment, the first biometric data and the third biometric data are drug data, and the second biometric data and the fourth biometric data are disease data.
在一实施例中,所述数据库存储多个生物数据;所述药物趋势分析方法进一步包括:由所述服务器的统计模块根据所述多个生物数据产生统计数据;以及由所述提供模块根据 来自所述第一装置的第三指令将所述统计数据提供给所述第一装置;其中所述统计模块通信连接所述分析模块、所述关联性识别模块与所述提供模块。In one embodiment, the database stores a plurality of biological data; the drug trend analysis method further comprises: generating, by a statistical module of the server, statistical data according to the plurality of biological data; The third instruction of the first device provides the statistical data to the first device; wherein the statistics module communicatively connects the analysis module, the correlation identification module and the providing module.
在一实施例中,所述药物趋势分析方法进一步包括:由所述服务器的图像绘制模块根据所述统计数据产生第二图像数据;以及由所述提供模块根据来自所述第一装置的第四指令将所述第二图像数据提供给所述第一装置;其中所述图像绘制模块通信连接所述分析模块、所述关联性识别模块、所述统计模块与所述提供模块。In one embodiment, the drug trend analysis method further includes: generating, by an image rendering module of the server, second image data according to the statistical data; and generating, by the providing module, based on fourth image data from the first device The instruction provides the second image data to the first device; wherein the image rendering module communicatively connects the analysis module, the correlation identification module, the statistics module and the providing module.
在一实施例中,所述药物趋势分析方法进一步包括:由所述服务器的生物数据分类模块通过所述生物数据分类模块的第三自然语言处理学模块将所述第一生物数据、所述第二生物数据、所述第三生物数据以及所述第四生物数据进行分类;其中所述生物数据分类模块通信连接所述分析模块、所述关联性识别模块与所述提供模块。In one embodiment, the drug trend analysis method further comprises: by the biological data classification module of the server through the third natural language processing module of the biological data classification module, the first biological data, the second biological data The second biological data, the third biological data and the fourth biological data are classified; wherein the biological data classification module communicatively connects the analysis module, the correlation identification module and the providing module.
在一实施例中,所述第一文件数据与所述第二文件数据分别为专利文件数据、临床文件数据、科学出版物文件数据、新闻文件数据以及公司报告文件数据其中一者。In one embodiment, the first document data and the second document data are one of patent document data, clinical document data, scientific publication document data, news document data, and company report document data, respectively.
在一实施例中,所述分析结果指出所述第一生物数据与所述第三生物数据的相似度大于预定的相似度临界值。In one embodiment, the analysis result indicates that the similarity between the first biological data and the third biological data is greater than a predetermined similarity threshold.
在一实施例中,所述第一生物数据与所述第三生物数据均为基因序列数据或均为蛋白质数据,所述第二生物数据为药物数据,所述第四生物数据为疾病数据。In one embodiment, the first biological data and the third biological data are both gene sequence data or protein data, the second biological data is drug data, and the fourth biological data is disease data.
本申请前述各方面及其它方面依据下述的非限制性具体实施例详细说明以及参照附图将更加明显。The foregoing and other aspects of the present application will be more apparent in light of the following detailed description of non-limiting specific examples and with reference to the accompanying drawings.
附图说明Description of drawings
图1显示本申请示例的药物趋势分析系统的系统架构图。FIG. 1 shows a system architecture diagram of the drug trend analysis system exemplified in the present application.
图2为第一装置显示本申请示例的药物趋势分析系统所提供的生物数据的部分画面示意图。FIG. 2 is a partial screen diagram of the first device displaying biological data provided by the drug trend analysis system exemplified in the present application.
图3为第一装置显示本申请示例的药物趋势分析系统所提供的生物数据的部分画面示意图。FIG. 3 is a partial screen diagram of the first device displaying biological data provided by the drug trend analysis system exemplified in the present application.
图4显示本申请示例的药物趋势分析系统的部分画面示意图。FIG. 4 shows a schematic diagram of part of the screen of the drug trend analysis system exemplified in the present application.
图5为本申请示例的药物趋势分析系统的部分画面示意图。FIG. 5 is a partial screen schematic diagram of the drug trend analysis system exemplified in this application.
图6A为本申请示例的药物趋势分析系统的部分画面示意图。FIG. 6A is a partial screen schematic diagram of the drug trend analysis system exemplified in the present application.
图6B为本申请示例的药物趋势分析系统的部分画面示意图。FIG. 6B is a partial screen schematic diagram of the drug trend analysis system exemplified in the present application.
图6C为本申请示例的药物趋势分析系统的部分画面示意图。FIG. 6C is a partial screen diagram of the drug trend analysis system exemplified in the present application.
图6D为本申请示例的药物趋势分析系统的部分画面示意图。FIG. 6D is a partial screen diagram of the drug trend analysis system exemplified in the present application.
图7为本申请示例的药物趋势分析系统的部分画面示意图。FIG. 7 is a partial screen schematic diagram of the drug trend analysis system exemplified in the application.
图8为本申请示例的药物趋势分析系统的部分画面示意图。FIG. 8 is a partial screen schematic diagram of the drug trend analysis system exemplified in the application.
图9为本申请示例的药物趋势分析系统的部分画面示意图。FIG. 9 is a partial screen schematic diagram of the drug trend analysis system exemplified in the application.
图10为本申请示例的药物趋势分析系统的部分画面示意图。FIG. 10 is a schematic diagram of part of the screen of the drug trend analysis system of the example of the application.
图11为本申请示例的药物趋势分析方法的流程图。FIG. 11 is a flow chart of the drug trend analysis method exemplified in the application.
图12为本申请示例的药物趋势分析方法的流程图。FIG. 12 is a flow chart of the drug trend analysis method exemplified in the application.
图13A为本申请药物趋势分析方法一具体实施例的示意图。FIG. 13A is a schematic diagram of a specific embodiment of the drug trend analysis method of the present application.
图13B为本申请药物趋势分析方法一具体实施例的示意图。FIG. 13B is a schematic diagram of a specific embodiment of the drug trend analysis method of the present application.
图13C为本申请药物趋势分析方法一具体实施例的示意图。FIG. 13C is a schematic diagram of a specific embodiment of the drug trend analysis method of the present application.
具体实施方式detailed description
除非特别定义,否则所有于此所用的技术及科学名词均与本领域技术人员所通常理解的意义相同。若于本文中所用定义与其他公开文献中所载定义有所矛盾或不一致,则应以此处所用的定义为准。Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. In the event of conflict or inconsistency between definitions used herein and definitions contained in other publications, the definitions used herein shall control.
如本文中所用者,术语「选自(selected from)」、「由…构成(composed of)」与「包括(comprising)」同义。如本文中所用者,术语「包括(comprises,comprising)」、「包含(includes,including)」、「具有(has,having)」、「含有(contains,containing)」、或其任何其他变型,是意欲涵盖非排他性的涵括。例如,含有清单列出的复数元素的一组合物、制程、方法、制品或装置不一定仅限于清单上所列出的这些元素而已,而是可以包括未明确列出但却是所述组合物、制程、方法、制品或装置固有的其他元素。As used herein, the terms "selected from", "composed of" and "comprising" are synonymous. As used herein, the terms "comprises, comprising," "includes, including," "has, having," "contains, containing," or any other variation thereof, are It is intended to cover non-exclusive inclusions. For example, a composition, process, method, article or device containing a plurality of listed elements is not necessarily limited to only those listed elements, but may include compositions that are not expressly listed but are , process, method, article or other element inherent in the device.
请参阅图1,其例示说明了根据本申请示例的药物趋势分析系统的系统架构图。如图1所示实施例,药物趋势分析系统100包括数据库110以及服务器120,其中数据库110存储多个生物数据,服务器120可访问数据库110。服务器120包括分析模块121、关联性识别模块123、提供模块125、生物数据分类模块126、统计模块127以及图像绘制模块129。分析模块121包括第一自然语言处理学(Natural Language Processing,NLP)模块121A,关联性识别模块123包括第二自然语言处理学模块123A,生物数据分类模块126包括第三自然语言处理学模块126A。在一个具体实施例中,分析模块121通信连接关联性识别模块123与提供模块125,关联性识别模块123通信连接提供模块125,统计模块127通信连接分析模块121、关联性识别模块123与提供模块125,图像绘制模块129通信连接分析模块121、关联性识别模块123、统计模块127与提供模块125,生物数据分 类模块126通信连接分析模块121、关联性识别模块123、统计模块127、图像绘制模块129与提供模块125。在一个具体实施例中,药物趋势分析系统100包括一或多个处理器,并以硬件与软件协同运作的方式实施数据库110、服务器120、分析模块121、第一自然语言处理学模块121A、关联性识别模块123、第二自然语言处理学模块123A、提供模块125、生物数据分类模块126、第三自然语言处理学模块126A、统计模块127以及图像绘制模块129。Please refer to FIG. 1 , which illustrates a system architecture diagram of a drug trend analysis system according to an example of the present application. In the embodiment shown in FIG. 1 , the drug trend analysis system 100 includes a database 110 and a server 120 , wherein the database 110 stores a plurality of biological data, and the server 120 can access the database 110 . The server 120 includes an analysis module 121 , a correlation identification module 123 , a provision module 125 , a biological data classification module 126 , a statistics module 127 and an image rendering module 129 . The analysis module 121 includes a first natural language processing (NLP) module 121A, the correlation identification module 123 includes a second natural language processing module 123A, and the biological data classification module 126 includes a third natural language processing module 126A. In a specific embodiment, the analysis module 121 is communicatively connected to the correlation identification module 123 and the providing module 125 , the correlation identification module 123 is communicatively connected to the providing module 125 , and the statistics module 127 is communicatively connected to the analysis module 121 , the correlation identification module 123 and the providing module 125, the image drawing module 129 communicates with the connection analysis module 121, the association identification module 123, the statistics module 127 and the providing module 125, the biological data classification module 126 communicates with the connection analysis module 121, the association identification module 123, the statistics module 127, and the image rendering module 129 and provision module 125. In a specific embodiment, the drug trend analysis system 100 includes one or more processors, and implements the database 110 , the server 120 , the analysis module 121 , the first natural language processing module 121A, the correlation Sex recognition module 123 , second natural language processing module 123A, providing module 125 , biological data classification module 126 , third natural language processing module 126A, statistics module 127 and image rendering module 129 .
在图1所示实施例中,分析模块121分析第一文件数据以得出第一生物数据与第二生物数据,并分析第二文件数据以得出第三生物数据与第四生物数据。服务器接着将第一生物数据、第二生物数据、第三生物数据与第四生物数据存储至数据库110。在一个具体实施例中,分析模块121分析第一文件数据及/或第二文件数据时,根据存储于数据库110的多个生物数据其中至少一者以得出第一生物数据、第二生物数据、第三生物数据以及第四生物数据其中至少一者。例如在一个具体实施例中,当存储于数据库110的某个生物数据与第一生物数据相同时,则分析模块121可通过存储在数据库110中与第一生物数据相同的所述生物数据以得出(或分析出)第一生物数据。在一个具体实施例中,分析模块121分析第一文件数据及/或第二文件数据时,系通过自然语言处理学模块121A以得出第一生物数据、第二生物数据、第三生物数据以及第四生物数据其中至少一者。在不同具体实施例中,第一文件数据及/或第二文件数据可为专利文件、临床试验文件、科学出版物文件、新闻文件以及公司报告文件其中一者,但不以此为限。In the embodiment shown in FIG. 1 , the analysis module 121 analyzes the first file data to obtain the first biological data and the second biological data, and analyzes the second file data to obtain the third biological data and the fourth biological data. The server then stores the first biometric data, the second biometric data, the third biometric data and the fourth biometric data to the database 110 . In a specific embodiment, when analyzing the first file data and/or the second file data, the analysis module 121 obtains the first biological data and the second biological data according to at least one of the plurality of biological data stored in the database 110 , at least one of the third biometric data and the fourth biometric data. For example, in a specific embodiment, when a certain biological data stored in the database 110 is the same as the first biological data, the analysis module 121 can obtain the biological data stored in the database 110 by the biological data that is the same as the first biological data to generate (or analyze) the first biological data. In a specific embodiment, when the analysis module 121 analyzes the first document data and/or the second document data, the natural language processing module 121A is used to obtain the first biological data, the second biological data, the third biological data and the At least one of the fourth biometric data. In different embodiments, the first document data and/or the second document data may be one of patent documents, clinical trial documents, scientific publication documents, news documents and company report documents, but not limited thereto.
本申请对于得出(或分析出)生物数据的方式、得出知识结构图的方式或本申请对于其他步骤的做法亦可参考第CN109448793A号专利(发明名称为「基因序列的权利范为认定、检索及侵权判定方法」)、第CN110413814A号专利(发明名称为「图像数据库建立方法、搜索方法、电子设备和存储介质」)、第US20180276340号专利(发明名称为「SYSTEM AND METHOD FOR DRUG TARGET AND BIOMARKER DISCOVERY AND DIAGNOSIS USING A MULTIDIMENSIONAL MULTISCALE MODULE MAP」)以及第US20190005395号专利(发明名称为「A METHOD AND SYSTEM FOR ONTOLOGY-BASED DYNAMIC LEARNING AND KNOWLEDGE INTEGRATION FROM MEASUREMENT DATA AND TEXT」),本申请在此以引用方式将上述各篇专利所载之全部内容并入本文中。This application can also refer to the patent No. CN109448793A (the title of invention is "The right to gene sequence recognition, Retrieval and Infringement Determination Method”), Patent No. CN110413814A (named “Image Database Establishment Method, Search Method, Electronic Device and Storage Medium”), Patent No. US20180276340 (named “SYSTEM AND METHOD FOR DRUG TARGET AND BIOMARKER” DISCOVERY AND DIAGNOSIS USING A MULTIDIMENSIONAL MULTISCALE MODULE MAP") and US20190005395 (named "A METHOD AND SYSTEM FOR ONTOLOGY-BASED DYNAMIC LEARNING AND KNOWLEDGE INTEGRATION FROM MEASUREMENT DATA AND TEXT"), which are hereby incorporated by reference The entire contents of each of the aforementioned patents are incorporated herein.
在不同具体实施例中,第一生物数据及/或第二生物数据及/或第三生物数据及/或第四生物数据可为药物数据、药物代号数据、药物名称数据、疾病数据、基因数据、基因序列数据、蛋白质数据、酶数据、有机体数据、细胞株数据、细胞库序号数据、标靶数据、结 构数据、物种数据、途径数据以及生物企业实体数据其中一者。例如第一生物数据可为一药物数据,第二生物数据可为一蛋白质数据,第三生物数据可为一疾病数据,第四生物数据可为一生物企业实体数据。其中,生物企业实体可为公司、学术单位、机构、政府机构或个人,但不以此为限,例如生物企业实体可为某药物专利的申请人(此申请人可能为个人或公司或机构等)。在另一个具体实施例中,第一生物数据或第二生物数据或第三生物数据或第四生物数据亦可为其他与生物相关的数据。In different embodiments, the first biological data and/or the second biological data and/or the third biological data and/or the fourth biological data may be drug data, drug code data, drug name data, disease data, genetic data , gene sequence data, protein data, enzyme data, organism data, cell line data, cell bank serial number data, target data, structure data, species data, pathway data and biological enterprise entity data. For example, the first biological data can be a drug data, the second biological data can be a protein data, the third biological data can be a disease data, and the fourth biological data can be a biological enterprise entity data. Among them, the bio-enterprise entity may be a company, academic unit, institution, government agency or individual, but not limited thereto, for example, a bio-enterprise entity may be an applicant for a drug patent (this applicant may be an individual, a company or an organization, etc. ). In another specific embodiment, the first biometric data or the second biometric data or the third biometric data or the fourth biometric data can also be other bio-related data.
在图1所示实施例中,关联性识别模块123根据分析结果将第一生物数据关联于第二生物数据、第三生物数据与第四生物数据。在一个具体实施例中,关联性识别模块123通过第二自然语言处理学模块123A以得出所述分析结果。在一个具体实施例中,关联性识别模块123的分析结果为第一生物数据与第二生物数据皆来自于第一文件数据。据此,关联性识别模块123根据分析结果将第一生物数据关联于第二生物数据。在一个具体实施例中,关联性识别模块123的分析结果为第二生物数据与第三生物数据内容相同,第一生物数据与第二生物数据皆来自于第一文件数据,且第三生物数据与第四生物数据皆来自于第二文件数据。据此,关联性识别模块123根据分析结果将第一生物数据关联于第二生物数据、第三生物数据以及第四生物数据,并将第一文件数据关联于第二文件数据。在一个具体实施例中,关联性识别模块123的分析结果为第二生物数据与第三生物数据相关联(例如数据库存储一关联性数据,其指出第二生物数据与第三生物数据相关联),第一生物数据与第二生物数据皆来自于第一文件数据,且第三生物数据与第四生物数据皆来自于第二文件数据。据此,关联性识别模块123根据分析结果将第一生物数据关联于第二生物数据、第三生物数据以及第四生物数据,并将第一文件数据关联于第二文件数据。In the embodiment shown in FIG. 1 , the association identification module 123 associates the first biometric data with the second biometric data, the third biometric data and the fourth biometric data according to the analysis result. In a specific embodiment, the correlation identification module 123 obtains the analysis result through the second natural language processing module 123A. In a specific embodiment, the analysis result of the correlation identification module 123 is that both the first biometric data and the second biometric data come from the first file data. Accordingly, the association identification module 123 associates the first biometric data with the second biometric data according to the analysis result. In a specific embodiment, the analysis result of the correlation identification module 123 is that the content of the second biometric data and the third biometric data are the same, the first biometric data and the second biometric data are both from the first file data, and the third biometric data and the fourth biometric data are all derived from the second file data. Accordingly, the association identification module 123 associates the first biometric data with the second biometric data, the third biometric data and the fourth biometric data according to the analysis result, and associates the first file data with the second file data. In a specific embodiment, the analysis result of the association identification module 123 is that the second biometric data is associated with the third biometric data (for example, the database stores a association data indicating that the second biometric data is associated with the third biometric data) , the first biometric data and the second biometric data both come from the first file data, and the third biometric data and the fourth biometric data both come from the second file data. Accordingly, the association identification module 123 associates the first biometric data with the second biometric data, the third biometric data and the fourth biometric data according to the analysis result, and associates the first file data with the second file data.
在一个具体实施例中,所述根据分析结果将第一生物数据关联于第二生物数据、第三生物数据与第四生物数据,是由关联性识别模块123根据所述分析结果产生第一关联性数据,服务器120并将第一关联性数据存储至数据库110中。其中第一关联性数据关联于第一生物数据,且第一关联性数据指出第一生物数据系关联于第二生物数据、第三生物数据与第四生物数据。在一个具体实施例中,第一关联性数据包含三个关联性数据,其分别指出第一生物数据系关联于第二生物数据、第一生物数据系关联于第三生物数据以及第一生物数据系关联于第四生物数据。In a specific embodiment, associating the first biometric data with the second biometric data, the third biometric data and the fourth biometric data according to the analysis result is performed by the association identification module 123 to generate the first association according to the analysis result The server 120 stores the first correlation data in the database 110 . The first correlation data is related to the first biological data, and the first correlation data indicates that the first biological data is related to the second biological data, the third biological data and the fourth biological data. In a specific embodiment, the first association data includes three association data, which respectively indicate that the first biometric data is related to the second biometric data, the first biometric data is related to the third biometric data and the first biometric data A relationship is associated with the fourth biological data.
在图1所示实施例中,提供模块125根据来自第一装置(图未示)的第一指令,将第一生物数据与关联于第一生物数据的第二生物数据、第三生物数据与第四生物数据提供给第一装置。其中,第一装置通信连接服务器120。在不同具体实施例中,第一装置可为桌 面计算机、智能型手机、笔记本电脑,但不以此为限。在一个具体实施例中,所述第一指令是用户以第一生物数据作为检索目标或分析目标的指令。在一个具体实施例中,关联性识别模块123根据所述分析结果将第一生物数据关联于第一文件数据与第二文件数据。如此,提供模块125根据来自第一装置(图未示)的第一指令,将第一生物数据与关联于第一生物数据的第二生物数据、第三生物数据与第四生物数据提供给第一装置时,可进一步根据来自第一装置的文件提供指令而将关联于第一生物数据的第一文件数据与第二文件数据提供给第一装置(或是可直接提供第一文件数据与第二文件数据提供给第一装置,而无需第一装置另行输入文件提供指令)。In the embodiment shown in FIG. 1 , the providing module 125 associates the first biometric data with the second biometric data and the third biometric data associated with the first biometric data according to the first instruction from the first device (not shown). The fourth biometric data is provided to the first device. The first device is communicatively connected to the server 120 . In different specific embodiments, the first device may be a desktop computer, a smart phone, or a notebook computer, but not limited thereto. In a specific embodiment, the first instruction is an instruction of the user to take the first biological data as a retrieval target or an analysis target. In a specific embodiment, the association identification module 123 associates the first biological data with the first file data and the second file data according to the analysis result. In this way, the providing module 125 provides the first biometric data, the second biometric data, the third biometric data and the fourth biometric data associated with the first biometric data to the first biometric data according to the first instruction from the first device (not shown). When a device is used, the first file data and the second file data associated with the first biological data can be provided to the first device according to the file providing instruction from the first device (or the first file data and the second file data can be directly provided. The two file data are provided to the first device without the need for the first device to additionally input a file providing instruction).
在图1所示实施例中,生物数据分类模块126通过生物数据分类模块的第三自然语言处理学模块126A将第一生物数据、第二生物数据、第三生物数据以及第四生物数据进行分类。在一个具体实施例中,生物数据分类模块的第三自然语言处理学模块126A将第一生物数据及/或第二生物数据及/或第三生物数据及/或第四生物数据分类为药物类数据、疾病类数据、基因类数据、蛋白质类数据、酶类数据、有机体类数据、细胞株类数据、细胞库序号类数据、标靶类数据、结构类数据、物种类数据、途径类数据以及生物企业实体类数据其中一者。In the embodiment shown in FIG. 1 , the biological data classification module 126 classifies the first biological data, the second biological data, the third biological data and the fourth biological data through the third natural language processing module 126A of the biological data classification module . In one embodiment, the third natural language processing module 126A of the biological data classification module classifies the first biological data and/or the second biological data and/or the third biological data and/or the fourth biological data as drugs data, disease data, gene data, protein data, enzyme data, organism data, cell line data, cell bank serial number data, target data, structure data, species data, pathway data and One of the biological enterprise entity data.
在图1所示实施例中,图像绘制模块129根据来自第一装置的第二指令以产生第一图像数据,并将第一图像数据提供给第一装置(在不同具体实施例中,可由提供模块125或图像绘制模块129提供第一图像数据予第一装置)。其中,第一图像数据包括所述第一生物数据以及关联于所述第一生物数据的第二生物数据、第三生物数据与第四生物数据。在一个具体实施例中,于显示第一图像数据时,第一图像数据并显示出第一生物数据与第二生物数据、第三生物数据以及第四生物数据系具有关联性的。在一个具体实施例中,第一图像数据为一种知识结构图。In the embodiment shown in FIG. 1 , the image rendering module 129 generates the first image data according to the second instruction from the first device, and provides the first image data to the first device (in different specific embodiments, by providing The module 125 or the image rendering module 129 provides the first image data to the first device). Wherein, the first image data includes the first biometric data and second biometric data, third biometric data and fourth biometric data associated with the first biometric data. In a specific embodiment, when the first image data is displayed, the first image data also shows that the first biometric data is related to the second biometric data, the third biometric data and the fourth biometric data. In a specific embodiment, the first image data is a knowledge structure graph.
在一个具体实施例中,当第一生物数据、第二生物数据、第三生物数据与第四生物数据均关联于第五生物数据,且第一生物数据、第二生物数据、第三生物数据与第四生物数据均为不同内容的数据时,关联性识别模块123产生第二关联性数据以及第三关联性数据,服务器120并将第二关联性数据以及第三关联性数据存储至数据库110。其中,第二关联性数据指出第一生物数据与第四生物数据具有第一关联性,第三关联性数据指出第三生物数据与第二生物数据具有第二关联性。其中,第一生物数据与第三生物数据为同类型的生物数据,而第二生物数据与第四生物数据为同类型的生物数据。在一个具体实施例中,第一生物数据与所述第三生物数据为药物数据,而第二生物数据与所述第四生物数据为疾 病数据。第一关联性指出第一生物数据可能可应用于第四生物数据,第三关联性数据指出第三生物数据可能可应用于第二生物数据。由此,关联性识别模块123即可根据不同的文件数据以找出某药物可能具有的新应用领域。In a specific embodiment, when the first biometric data, the second biometric data, the third biometric data and the fourth biometric data are all associated with the fifth biometric data, and the first biometric data, the second biometric data, and the third biometric data When the fourth biometric data is data of different content, the association identification module 123 generates the second association data and the third association data, and the server 120 stores the second association data and the third association data in the database 110 . The second correlation data indicates that the first biological data has a first correlation with the fourth biological data, and the third correlation data indicates that the third biological data has a second correlation with the second biological data. The first biometric data and the third biometric data are the same type of biometric data, and the second biometric data and the fourth biometric data are the same type of biometric data. In a specific embodiment, the first biometric data and the third biometric data are drug data, and the second biometric data and the fourth biometric data are disease data. The first association indicates that the first biometric data may be applicable to the fourth biometric data, and the third association data indicates that the third biometric data may be applicable to the second biometric data. Therefore, the correlation identification module 123 can find out the possible new application fields of a certain medicine according to different file data.
在一个具体实施例中,分析结果指出第一生物数据与第三生物数据的相似度大于预定的相似度临界值,即表示第一生物数据与第三生物数据具有极大的相似度或关联性。在一具体实施例中,第一生物数据与第三生物数据均为基因序列数据,第二生物数据为药物数据(例如可为药物名称数据或药物代号数据),第四生物数据为疾病数据。在另一具体实施例中,第一生物数据与第三生物数据均为蛋白质数据,第二生物数据为药物数据(例如可为药物名称数据或药物代号数据),第四生物数据为疾病数据。藉此,关联性识别模块123即可根据不同的文件数据以找出某药物可能具有的新应用领域,或是可针对某疾病(例如COVID 19(Coronavirus Disease))找出现有的可能有用的药物。In a specific embodiment, the analysis result indicates that the similarity between the first biological data and the third biological data is greater than a predetermined similarity threshold, which means that the first biological data and the third biological data have a great similarity or correlation . In a specific embodiment, the first biological data and the third biological data are both gene sequence data, the second biological data is drug data (eg, drug name data or drug code data), and the fourth biological data is disease data. In another specific embodiment, the first biological data and the third biological data are both protein data, the second biological data is drug data (eg, drug name data or drug code data), and the fourth biological data is disease data. In this way, the correlation identification module 123 can find out the possible new application fields of a certain medicine according to different file data, or can find out the existing medicines that may be useful for a certain disease (eg, COVID 19 (Coronavirus Disease)). .
在图1所示实施例中,统计模块127根据存储于数据库110的多个生物数据产生统计数据(此为第一统计数据)。其中,提供模块125可根据来自第一装置的第三指令而将统计数据提供给第一装置。在一个具体实施例中,图像绘制模块129可根据统计数据产生第二图像数据。提供模块并可根据来自所述第一装置的第四指令将第二图像数据提供给第一装置。在一个具体实施例中,数据库110并存储多个文件数据。统计模块127可根据存储于数据库110中的多个文件数据产生第二统计数据。提供模块125可根据第一装置的指令将存储于数据库110中的多个文件数据其中至少一者提供给第一装置。提供模块125并可根据第一装置的另一指令将第二统计数据提供给第一装置。在一个具体实施例中,第二图像数据为一种知识结构图。In the embodiment shown in FIG. 1 , the statistics module 127 generates statistical data (this is the first statistical data) according to a plurality of biological data stored in the database 110 . The providing module 125 may provide the statistical data to the first device according to the third instruction from the first device. In a specific embodiment, the image rendering module 129 may generate the second image data according to the statistical data. The providing module may provide the second image data to the first device according to the fourth instruction from the first device. In a specific embodiment, the database 110 also stores a plurality of file data. The statistics module 127 may generate the second statistical data according to the plurality of document data stored in the database 110 . The providing module 125 may provide at least one of the plurality of file data stored in the database 110 to the first device according to an instruction of the first device. The providing module 125 may provide the second statistical data to the first device according to another instruction of the first device. In a specific embodiment, the second image data is a knowledge structure graph.
在图1所示实施例中,分析模块121可分析第一文件数据以得出第一生物分析数据、第二生物分析数据与多个第三生物分析数据。关联性识别模块123可根据多个第三生物分析数据其中至少一者以及第二生物分析数据,以自数据库110中关联出第三文件数据。关联性识别模块123进一步将第一生物分析数据关联于第二生物分析数据、多个第三生物分析数据与第三文件数据。在一具体实施例中,第一文件数据为临床文件数据,第三文件数据为专利文件数据,第一生物分析数据为药物数据(例如可为药物代号数据或药物名称数据),第二生物分析数据为生物企业实体数据。在一具体实施例中,所述多个第三生物分析数据分别为药物数据、疾病数据、基因数据、基因序列数据、蛋白质数据、酶数据、有机体数据、细胞株数据、细胞库序号数据、标靶数据、结构数据、物种数据、途径数据以及生物企业实体数据其中一者。In the embodiment shown in FIG. 1 , the analysis module 121 may analyze the first document data to obtain first bioanalytical data, second bioanalytical data and a plurality of third bioanalytical data. The association identification module 123 can associate the third document data from the database 110 according to at least one of the plurality of third bioanalytical data and the second bioanalytical data. The association identification module 123 further associates the first bioanalytical data with the second bioanalytical data, the plurality of third bioanalytical data, and the third document data. In a specific embodiment, the first file data is clinical file data, the third file data is patent file data, the first bioanalysis data is drug data (for example, it can be drug code data or drug name data), and the second bioanalysis data is drug data. The data is biological enterprise entity data. In a specific embodiment, the plurality of third biological analysis data are respectively drug data, disease data, gene data, gene sequence data, protein data, enzyme data, organism data, cell line data, cell bank serial number data, label data. One of target data, structural data, species data, pathway data, and bioenterprise entity data.
在一个具体实施例中,分析模块121可分析第一文件数据或第三文件数据以得出第九生物数据。关联性识别模块123可至少根据所述第九生物数据以自数据库110中关联出第四文件数据,关联性识别模块123并会将第一生物分析数据关联于第九生物数据与第四文件数据。在一具体实施例中,第一生物分析数据为药物代号数据,第九生物数据为药物名称数据。所述第四文件数据为专利文件数据、临床文件数据、科学出版物文件数据、新闻文件数据以及公司报告文件数据其中一者。在一具体实施例中,关联性识别模块123可根据多个第三生物分析数据其中至少一者以及第九生物数据,以自数据库110中关联出第四文件数据。In a specific embodiment, the analysis module 121 may analyze the first file data or the third file data to derive ninth biological data. The correlation identification module 123 can associate the fourth document data from the database 110 according to at least the ninth biological data, and the correlation identification module 123 can associate the first biological analysis data with the ninth biological data and the fourth document data . In a specific embodiment, the first biological analysis data is drug code data, and the ninth biological data is drug name data. The fourth document data is one of patent document data, clinical document data, scientific publication document data, news document data, and company report document data. In a specific embodiment, the association identification module 123 can associate the fourth document data from the database 110 according to at least one of the plurality of third biometric analysis data and the ninth biometric data.
在一个具体实施例中,分析模块121可分析第一文件数据以得出第一生物数据与第二生物数据。分析模块121可分析第二文件数据以得出第三生物数据与第四生物数据。关联性识别模块123可根据分析结果将第一生物数据关联于第二生物数据、第三生物数据、第四生物数据与第二文件数据。在一具体实施例中,所述分析结果指出第一生物数据与第三生物数据的相似度大于预定的相似度临界值,即表示第一生物数据与第三生物数据具有极大的相似度或关联性。在一具体实施例中,第一生物数据与第三生物数据均为基因序列数据,第二生物数据为药物数据(例如可为药物名称数据或药物代号数据),第四生物数据为疾病数据。在另一具体实施例中,第一生物数据与第三生物数据均为蛋白质数据,第二生物数据为药物数据(例如可为药物名称数据或药物代号数据),第四生物数据为疾病数据。藉此,关联性识别模块123即可根据不同的文件数据以找出某药物可能具有的新应用领域,或是可针对某疾病(例如COVID 19(Coronavirus Disease))找出现有的可能有用的药物。In a specific embodiment, the analysis module 121 may analyze the first document data to obtain the first biological data and the second biological data. The analysis module 121 can analyze the second file data to obtain the third biological data and the fourth biological data. The association identification module 123 can associate the first biometric data with the second biometric data, the third biometric data, the fourth biometric data and the second file data according to the analysis result. In a specific embodiment, the analysis result indicates that the similarity between the first biometric data and the third biometric data is greater than a predetermined similarity threshold, which means that the first biometric data and the third biometric data have a great similarity or Relevance. In a specific embodiment, the first biological data and the third biological data are both gene sequence data, the second biological data is drug data (eg, drug name data or drug code data), and the fourth biological data is disease data. In another specific embodiment, the first biological data and the third biological data are both protein data, the second biological data is drug data (eg, drug name data or drug code data), and the fourth biological data is disease data. In this way, the correlation identification module 123 can find out the possible new application fields of a certain medicine according to different file data, or can find out the existing medicines that may be useful for a certain disease (eg, COVID 19 (Coronavirus Disease)) .
在一个具体实施例中,服务器120的图像绘制模块129可根据来自第一装置的第五指令而产生第三图像数据,并将所述第三图像数据提供给第一装置。其中第三图像数据包括第一生物分析数据以及关联于第一生物分析数据的第二生物分析数据与多个第三生物分析数据。在一具体实施例中,第三图像数据并包括第九生物数据、第一文件数据、第三文件数据与第四文件数据。In a specific embodiment, the image rendering module 129 of the server 120 may generate the third image data according to the fifth instruction from the first device, and provide the third image data to the first device. The third image data includes first bioanalytical data and second bioanalytical data and a plurality of third bioanalytical data associated with the first bioanalytical data. In a specific embodiment, the third image data further includes ninth biological data, first file data, third file data and fourth file data.
请参阅图2,其例示说明了第一装置显示本申请示例的药物趋势分析系统所提供的生物数据的部分画面示意图。如图2所示,当第一装置输入第一指令212时,提供模块根据来自第一装置的第一指令212,将第一生物数据、关联于第一生物数据的第二生物数据、第三生物数据、第四生物数据与关联于第一生物数据的第一文件数据与第二文件数据提供给第一装置。图2中所示为第一装置的显示器所显示的画面。其中,链接211内包括第一 生物数据,链接213内包括第二生物数据,链接215内包括第三生物数据,链接217内包括第四生物数据,链接214内包括第一文件数据,链接216内包括第二文件数据。Please refer to FIG. 2 , which illustrates a partial screen diagram of the first device displaying the biological data provided by the drug trend analysis system of the example of the present application. As shown in FIG. 2, when the first device inputs the first instruction 212, the providing module provides the first biometric data, the second biometric data associated with the first biometric data, the third biometric data and the third biometric data according to the first instruction 212 from the first device. The biometric data, the fourth biometric data, and the first file data and the second file data associated with the first biometric data are provided to the first device. FIG. 2 shows a picture displayed on the display of the first device. The link 211 includes the first biological data, the link 213 includes the second biological data, the link 215 includes the third biological data, the link 217 includes the fourth biological data, the link 214 includes the first file data, and the link 216 includes the first file data. Include second file data.
请参阅图3,其例示说明了第一装置显示本申请药物趋势分析系统所提供的生物数据的一个具体实施例的部分画面示意图。如图3所示,当第一装置提供第一指令给药物趋势分析系统时,药物趋势分析系统的提供模块根据第一指令将第一生物数据、关联于第一生物数据的第二生物数据、第三生物数据、第四生物数据与关联于第一生物数据的第一文件数据与第二文件数据提供给第一装置。图3中所示为第一装置的显示器所显示的画面。其中,链接312内包括第一生物数据,链接314内包括第二生物数据与第三生物数据,链接316内包括第四生物数据,链接311内包括第一文件数据与第二文件数据。Please refer to FIG. 3 , which illustrates a partial screen diagram of a specific embodiment in which the first device displays the biological data provided by the drug trend analysis system of the present application. As shown in FIG. 3 , when the first device provides the first instruction to the drug trend analysis system, the providing module of the drug trend analysis system converts the first biological data, the second biological data associated with the first biological data, The third biometric data, the fourth biometric data, and the first and second file data associated with the first biometric data are provided to the first device. FIG. 3 shows a picture displayed on the display of the first device. The link 312 includes the first biometric data, the link 314 includes the second biometric data and the third biometric data, the link 316 includes the fourth biometric data, and the link 311 includes the first file data and the second file data.
请参阅图4,其例示说明了本申请药物趋势分析系统一个具体实施例的部分画面示意图。如图4所示实施例,由于生物数据分类模块以将各个生物数据进行分类,因此用户可通过连结411~417寻找或查询生物数据,并可通过连结421~423寻找或查询文件数据。应了解,药物趋势分析系统的画面系可由第一装置显示于其显示器上。Please refer to FIG. 4 , which illustrates a partial screen diagram of a specific embodiment of the drug trend analysis system of the present application. In the embodiment shown in FIG. 4 , since the biological data classification module classifies each biological data, the user can search or query the biological data through the links 411 - 417 , and can search or query the document data through the links 421 - 423 . It should be understood that the picture of the drug trend analysis system can be displayed on the display of the first device.
请参阅图5,其例示说明了本申请药物趋势分析系统一个具体实施例的部分画面示意图。如图5所示,由于药物趋势分析系统已通过生物数据分类模块将生物数据进行分类,并已通过统计模块根据生物数据与文件数据产生第一统计数据以及第二统计数据,以达成各种不同的分析。因此,使用者可通过连结511~516观看不同的分析结果。Please refer to FIG. 5 , which illustrates a partial screen diagram of a specific embodiment of the drug trend analysis system of the present application. As shown in FIG. 5 , because the drug trend analysis system has classified biological data through the biological data classification module, and has generated the first statistical data and the second statistical data according to the biological data and the document data through the statistical module, so as to achieve various differences analysis. Therefore, the user can view different analysis results through the links 511-516.
请参阅图6A至图6D,其例示说明了本申请药物趋势分析系统不同具体实施例的部分画面示意图。如图所示,由于药物趋势分析系统已通过生物数据分类模块将生物数据进行分类,并已通过统计模块根据生物数据与文件数据产生第一统计数据以及第二统计数据,藉以达成各种不同的分析。因此,使用者可通过选择观看不同的分析结果或统计结果。例如可选择观看专利文件数据的分析结果或统计结果(例如参见图像611、612),或可选择观看本体(ontology)生物数据的分析结果或统计结果(例如参见图像613),或可选择观看药物类别(drug classes)生物数据的分析结果或统计结果(例如参见图像614),或可选择观看临床试验研究阶段(clinical trial study phase)生物数据的分析结果或统计结果(例如参见图像615),或可选择观看药物标靶类别(drug target classes)生物数据的分析结果或统计结果(例如参见图像616),或可选择观看药物生物数据的分析结果或统计结果(例如参见图像621、622、624),或可选择观看功能指针生物数据的分析结果或统计结果(例如参见图像623)。Please refer to FIG. 6A to FIG. 6D , which illustrate some schematic diagrams of different specific embodiments of the drug trend analysis system of the present application. As shown in the figure, because the drug trend analysis system has classified the biological data through the biological data classification module, and has generated the first statistical data and the second statistical data according to the biological data and the file data through the statistical module, so as to achieve various analyze. Therefore, the user can view different analysis results or statistical results by selection. For example, one may choose to view analysis or statistics of patent document data (eg, see images 611, 612), or may choose to view analysis or statistics of ontology biological data (eg, see image 613), or may choose to view drugs Analytical results or statistical results of biological data of drug classes (see eg image 614), or optionally viewing analytical results or statistical results of biological data of the clinical trial study phase (see eg image 615), or Option to view analytical results or statistics of biological data of drug target classes (see eg image 616), or option to view analytical results or statistical results of biological data of drugs (eg see images 621, 622, 624) , or optionally to view analysis results or statistical results of functional pointer biometric data (see, eg, image 623).
请参阅图7,其例示说明了本申请药物趋势分析系统一个具体实施例的部分画面示意 图。如图7所示,用户可根据图像713得知药物趋势分析根据多个文件数据分析出心室生物数据关联于123个文献文件数据、265个专利文件数据、422个新闻文件数据、54个序号生物数据、23个化合物生物数据、87个临床试验生物数据以及25个药物数据。用户并可根据图像711与图像713之间的图像715、717、719分别查看同时与心室生物数据以及左心室生物数据相关联的标靶生物数据、药物生物数据、专利文件数据。Please refer to FIG. 7 , which illustrates a partial screen diagram of a specific embodiment of the drug trend analysis system of the present application. As shown in Figure 7, the user can know from the image 713 that the drug trend analysis analyzes the ventricular biological data according to the data of multiple files and is related to 123 literature file data, 265 patent file data, 422 news file data, 54 serial number biological data data, 23 compound biological data, 87 clinical trial biological data, and 25 drug data. The user can view the target biological data, drug biological data, and patent document data simultaneously associated with the ventricular biological data and the left ventricular biological data according to the images 715 , 717 , and 719 between the image 711 and the image 713 , respectively.
请参阅图8,其例示说明了本申请药物趋势分析系统一个具体实施例的部分画面示意图。如图8所示,药物趋势分析系统的统计模块可统计在不同年份中,不同生物数据于不同公司的文件数据中出现的次数,并进而产生多个对应的统计数据。而药物趋势分析系统的图像绘制模块可根据所述些统计数据产生第二图像810。其中,图像810中的点812即以颜色表示生物数据「肿瘤(neoplasm)」于2017年时,在与生物企业实体数据「PFIZER公司」相关联的文件数据中出现的次数(颜色越深表示出现次数越多)。而图像810中的点814即以颜色表示疾病数据「病毒疾病(virus disease)」于2011年时,在与生物企业实体数据「GSK公司」相关联的文件数据中出现的次数(颜色越浅表示出现次数越少)。Please refer to FIG. 8 , which illustrates a partial screen diagram of a specific embodiment of the drug trend analysis system of the present application. As shown in FIG. 8 , the statistics module of the drug trend analysis system can count the number of occurrences of different biological data in the file data of different companies in different years, and then generate a plurality of corresponding statistical data. The image drawing module of the drug trend analysis system can generate the second image 810 according to the statistical data. Among them, the point 812 in the image 810 represents the number of times the biological data "neoplasm" appeared in the file data associated with the biological enterprise entity data "PFIZER" in 2017 (the darker the color, the more appearance). more times). The point 814 in the image 810 indicates the number of times the disease data "virus disease" appeared in the document data associated with the bio-enterprise entity data "GSK Corporation" in 2011 (lighter colors indicate occur less frequently).
请参阅图9,其例示说明了本申请药物趋势分析系统一个具体实施例的部分画面示意图。如图9所示,药物趋势分析系统的统计模块可统计不同生物企业实体对于不同生物数据的临床试验数量,并进而产生多个对应的统计数据。而药物趋势分析系统的图像绘制模块可根据所述些统计数据产生第二图像910。其中,图像910中的区段912即指示出生物企业实体数据「Merk Sharp&Dohme Corp.」对于疾病数据「胃肠道疾病(gastrointestinal disease)」的临床试验数量。Please refer to FIG. 9 , which illustrates a partial screen diagram of a specific embodiment of the drug trend analysis system of the present application. As shown in FIG. 9 , the statistics module of the drug trend analysis system can count the number of clinical trials of different biological enterprise entities for different biological data, and then generate a plurality of corresponding statistical data. The image drawing module of the drug trend analysis system can generate the second image 910 according to the statistical data. The section 912 in the image 910 indicates the number of clinical trials of the biological enterprise entity data "Merk Sharp & Dohme Corp." for the disease data "gastrointestinal disease".
请参阅图10,其例示说明了本申请药物趋势分析系统一个具体实施例的部分画面示意图。如图10所示,图像1010显示出第一生物数据1011以及关联于第一生物数据1011的第二生物数据1012、第三生物数据1013与第四生物数据1014。图像1010并以箭头1016表示第二生物数据1012关联于第一生物数据1011,以箭头1017表示第三生物数据1013关联于第一生物数据1011,以箭头1018表示第四生物数据1014关联于第一生物数据1011。Please refer to FIG. 10 , which illustrates a partial screen diagram of a specific embodiment of the drug trend analysis system of the present application. As shown in FIG. 10 , the image 1010 displays the first biometric data 1011 and the second biometric data 1012 , the third biometric data 1013 and the fourth biometric data 1014 associated with the first biometric data 1011 . Image 1010 and arrows 1016 indicate that the second biometric data 1012 is associated with the first biometric data 1011, arrows 1017 indicate that the third biometric data 1013 is associated with the first biometric data 1011, and arrows 1018 indicate that the fourth biometric data 1014 is associated with the first biometric data 1011 Biodata 1011.
请参阅图11,其例示说明了本申请药物趋势分析方法一个具体实施例的流程图。如图11所示,药物趋势分析方法1100系应用于包括数据库以及服务器的药物趋势分析系统,其中所述服务器访问所述数据库,所述服务器包括分析模块、关联性识别模块、以及提供模块,分析模块通信连接关联性识别模块与提供模块,关联性识别模块通信连接提供模块,服务器通信连接第一装置。药物趋势分析方法1100开始于步骤1110,由服务器的分析模块分析第一文件数据以得出第一生物数据与第二生物数据。接着,进行步骤1120,由分析 模块分析第二文件数据以得出第三生物数据与第四生物数据。接着,进行步骤1130,由服务器将第一生物数据、第二生物数据、第三生物数据与第四生物数据存储至数据库。Please refer to FIG. 11 , which illustrates a flow chart of a specific embodiment of the drug trend analysis method of the present application. As shown in FIG. 11 , a drug trend analysis method 1100 is applied to a drug trend analysis system including a database and a server, wherein the server accesses the database, and the server includes an analysis module, a correlation identification module, and a provision module. The module is communicatively connected to the correlation identification module and the providing module, the correlation identification module is communicatively connected to the providing module, and the server is communicatively connected to the first device. The drug trend analysis method 1100 starts at step 1110, where the analysis module of the server analyzes the first file data to obtain the first biological data and the second biological data. Next, in step 1120, the analysis module analyzes the second file data to obtain the third biological data and the fourth biological data. Next, in step 1130, the server stores the first biometric data, the second biometric data, the third biometric data and the fourth biometric data in the database.
在一个具体实施例中,数据库存储多个生物数据,分析模块分析第一文件数据与第二文件数据时,根据多个生物数据其中至少一者以得出第一生物数据及/或第二生物数据及/或第三生物数据及/或第四生物数据。在一个具体实施例中,分析模块包括第一自然语言处理学模块,分析模块系通过自然语言处理学模块以得出第一生物数据及/或第二生物数据及/或第三生物数据及/或第四生物数据。In a specific embodiment, the database stores a plurality of biological data, and when analyzing the first file data and the second file data, the analysis module obtains the first biological data and/or the second biological data according to at least one of the plurality of biological data data and/or third biometric data and/or fourth biometric data. In a specific embodiment, the analysis module includes a first natural language processing module, and the analysis module obtains the first biological data and/or the second biological data and/or the third biological data and/or the natural language processing module through the natural language processing module. or fourth biometric data.
在一个具体实施例中,第一生物数据、第二生物数据、第三生物数据与第四生物数据分别为药物数据、药物代号数据、药物名称数据、疾病数据、基因数据、基因序列数据、蛋白质数据、酶数据、有机体数据、细胞株数据、细胞库序号数据、标靶数据、结构数据、物种数据、途径数据以及生物企业实体数据其中一者。例如第一生物数据可为药物数据,第二生物数据可为途径数据,第三生物数据可为标靶数据,第四生物数据可为生物企业实体数据。其中,生物企业实体可为公司、学术单位、机构、政府机构或个人,但不以此为限。在另一个具体实施例中,第一生物数据或第二生物数据或第三生物数据或第四生物数据亦可为其他与生物相关的数据。In a specific embodiment, the first biological data, the second biological data, the third biological data and the fourth biological data are drug data, drug code data, drug name data, disease data, gene data, gene sequence data, protein data, respectively. One of data, enzyme data, organism data, cell line data, cell bank serial number data, target data, structure data, species data, pathway data, and bioenterprise entity data. For example, the first biological data may be drug data, the second biological data may be pathway data, the third biological data may be target data, and the fourth biological data may be biological enterprise entity data. Among them, the biological enterprise entity may be a company, an academic unit, an institution, a government agency or an individual, but not limited thereto. In another specific embodiment, the first biometric data or the second biometric data or the third biometric data or the fourth biometric data can also be other bio-related data.
接着,进行步骤1140,由服务器的关联性识别模块根据分析结果将第一生物数据关联于第二生物数据、第三生物数据与第四生物数据。在一个具体实施例中,关联性识别模块包括第二自然语言处理学模块,所述关联性识别模块系通过第二自然语言处理学模块以得出所述分析结果。在一个具体实施例中,所述根据分析结果将第一生物数据关联于第二生物数据、第三生物数据与第四生物数据,是由关联性识别模块根据分析结果产生第一关联性数据,服务器将第一关联性数据存储至数据库。其中第一关联性数据关联于第一生物数据,且第一关联性数据指出第一生物数据关联于第二生物数据、第三生物数据与第四生物数据。在一个具体实施例中,关联性识别模块并根据所述分析结果将第一生物数据关联于第一文件数据与第二文件数据。Next, go to step 1140, the association identification module of the server associates the first biometric data with the second biometric data, the third biometric data and the fourth biometric data according to the analysis result. In a specific embodiment, the correlation identification module includes a second natural language processing module, and the correlation identification module obtains the analysis result through the second natural language processing module. In a specific embodiment, the associating the first biological data with the second biological data, the third biological data and the fourth biological data according to the analysis result is that the correlation identification module generates the first correlation data according to the analysis result, The server stores the first association data to the database. The first association data is associated with the first biometric data, and the first association data indicates that the first biometric data is associated with the second biometric data, the third biometric data and the fourth biometric data. In a specific embodiment, the association identification module associates the first biological data with the first file data and the second file data according to the analysis result.
接着,进行步骤1150,由服务器的提供模块根据来自第一装置的第一指令,将第一生物数据、关联于第一生物数据的第二生物数据、第三生物数据与第四生物数据提供给第一装置。Next, go to step 1150, the providing module of the server provides the first biometric data, the second biometric data related to the first biometric data, the third biometric data and the fourth biometric data to the user according to the first instruction from the first device. first device.
在一个具体实施例中,药物趋势分析系统的服务器包括图像绘制模块,图像绘制模块通信连接分析模块、关联性识别模块与提供模块。药物趋势分析方法进一步包括以下步骤:由服务器的图像绘制模块根据来自第一装置的第二指令产生第一图像数据,并将第一图像 数据提供给第一装置。其中第一图像数据包括第一生物数据以及关联于第一生物数据的第二生物数据、第三生物数据与第四生物数据。In a specific embodiment, the server of the drug trend analysis system includes an image drawing module, and the image drawing module communicates with the analysis module, the correlation identification module and the providing module. The drug trend analysis method further includes the steps of: generating, by an image rendering module of the server, first image data according to a second instruction from the first device, and providing the first image data to the first device. The first image data includes first biometric data and second biometric data, third biometric data and fourth biometric data associated with the first biometric data.
在一个具体实施例中,药物趋势分析方法进一步包括以下步骤:当第一生物数据、第二生物数据、第三生物数据与第四生物数据均关联于第五生物数据,且第一生物数据、第二生物数据、第三生物数据与第四生物数据均为不同内容的数据时,关联性识别模块产生第二关联性数据以及第三关联性数据,服务器并将第二关联性数据以及第三关联性数据存储至数据库。其中第二关联性数据指出第一生物数据与第四生物数据具有第一关联性,第三关联性数据指出第三生物数据与第二生物数据具有第二关联性。其中,第一生物数据与第三生物数据为同类型的生物数据,第二生物数据与第四生物数据为同类型的生物数据。例如在一个具体实施例中,第一生物数据与第三生物数据为药物数据,第二生物数据与第四生物数据为疾病数据。In a specific embodiment, the drug trend analysis method further includes the following steps: when the first biological data, the second biological data, the third biological data and the fourth biological data are all related to the fifth biological data, and the first biological data, When the second biometric data, the third biometric data, and the fourth biometric data are data of different contents, the association identification module generates the second association data and the third association data, and the server stores the second association data and the third association data. The relational data is stored in the database. The second correlation data indicates that the first biological data has a first correlation with the fourth biological data, and the third correlation data indicates that the third biological data has a second correlation with the second biological data. The first biometric data and the third biometric data are the same type of biometric data, and the second biometric data and the fourth biometric data are the same type of biometric data. For example, in a specific embodiment, the first biological data and the third biological data are drug data, and the second biological data and the fourth biological data are disease data.
在一个具体实施例中,数据库存储多个生物数据,药物趋势分析系统的服务器包括统计模块以及图像绘制模块。统计模块通信连接分析模块、关联性识别模块与提供模块,图像绘制模块通信连接分析模块、关联性识别模块、统计模块与提供模块。药物趋势分析方法进一步包括以下步骤:由服务器的统计模块根据多个生物数据产生统计数据;由提供模块根据来自第一装置的第三指令将统计数据提供给第一装置;由服务器的图像绘制模块根据统计数据产生第二图像数据;以及由提供模块根据来自第一装置的第四指令将第二图像数据提供给第一装置。In a specific embodiment, the database stores a plurality of biological data, and the server of the drug trend analysis system includes a statistics module and an image drawing module. The statistics module communicates and connects the analysis module, the correlation identification module and the providing module, and the image drawing module communicates and connects the analysis module, the correlation identification module, the statistics module and the providing module. The drug trend analysis method further includes the following steps: generating statistical data according to a plurality of biological data by a statistical module of the server; providing the statistical data to the first device by the providing module according to a third instruction from the first device; image drawing module of the server generating second image data according to the statistical data; and providing, by the providing module, the second image data to the first device according to a fourth instruction from the first device.
在一个具体实施例中,药物趋势分析系统的服务器包括生物数据分类模块,其中生物数据分类模块通信连接分析模块、关联性识别模块与提供模块。药物趋势分析方法进一步包括以下步骤:由服务器的生物数据分类模块通过生物数据分类模块的第三自然语言处理学模块将第一生物数据、第二生物数据、第三生物数据以及第四生物数据进行分类。In a specific embodiment, the server of the drug trend analysis system includes a biological data classification module, wherein the biological data classification module communicates with the analysis module, the correlation identification module and the providing module. The drug trend analysis method further includes the following steps: the first biological data, the second biological data, the third biological data and the fourth biological data are processed by the biological data classification module of the server through the third natural language processing module of the biological data classification module. Classification.
在一个具体实施例中,分析结果指出第一生物数据与第三生物数据的相似度大于预定的相似度临界值,此极表示第一生物数据与第三生物数据具有极大的相似度或关联性。在一具体实施例中,第一生物数据与第三生物数据均为基因序列数据,第二生物数据为药物数据(例如可为药物名称数据或药物代号数据),第四生物数据为疾病数据。在另一具体实施例中,第一生物数据与第三生物数据均为蛋白质数据,第二生物数据为药物数据(例如可为药物名称数据或药物代号数据),第四生物数据为疾病数据。藉此,关联性识别模块123即可根据不同的文件数据以找出某药物可能具有的新应用领域,或是可针对某疾病(例如COVID 19(Coronavirus Disease))找出现有的可能有用的药物。In a specific embodiment, the analysis result indicates that the similarity between the first biometric data and the third biometric data is greater than a predetermined similarity threshold, which indicates that the first biometric data and the third biometric data have a great similarity or correlation sex. In a specific embodiment, the first biological data and the third biological data are both gene sequence data, the second biological data is drug data (eg, drug name data or drug code data), and the fourth biological data is disease data. In another specific embodiment, the first biological data and the third biological data are both protein data, the second biological data is drug data (eg, drug name data or drug code data), and the fourth biological data is disease data. In this way, the correlation identification module 123 can find out the possible new application fields of a certain medicine according to different file data, or can find out the existing medicines that may be useful for a certain disease (eg, COVID 19 (Coronavirus Disease)). .
请参阅第图12,其例示说明了本申请药物趋势分析方法一具体实施例的流程图。如第图12所示,药物趋势分析方法1200应用于包括数据库以及服务器的药物趋势分析系统,其中所述服务器访问所述数据库。药物趋势分析方法1200开始于步骤1210,由服务器的分析模块分析第一文件数据以得出第一生物分析数据、第二生物分析数据与多个第三生物分析数据。接着,进行步骤1120,由服务器的关联性识别模块根据多个第三生物分析数据其中至少一者以及第二生物分析数据,以自数据库中关联出第三文件数据。接着,进行步骤1130,由关联性识别模块将第一生物分析数据关联于第二生物分析数据、多个第三生物分析数据与第三文件数据。其中分析模块通信连接关联性识别模块。在一具体实施例中,第一文件数据为临床文件数据,第三文件数据为专利文件数据,第一生物分析数据为药物代号数据或药物名称数据,第二生物分析数据为生物企业实体数据。在一具体实施例中,多个第三生物分析数据分别为药物数据、疾病数据、基因数据、基因序列数据、蛋白质数据、酶数据、有机体数据、细胞株数据、细胞库序号数据、标靶数据、结构数据、物种数据、途径数据以及生物企业实体数据其中一者。Please refer to FIG. 12 , which illustrates a flow chart of a specific embodiment of the drug trend analysis method of the present application. As shown in FIG. 12, a drug trend analysis method 1200 is applied to a drug trend analysis system including a database and a server, wherein the server accesses the database. The drug trend analysis method 1200 starts at step 1210, and the analysis module of the server analyzes the first file data to obtain first bioanalytical data, second bioanalytical data and a plurality of third bioanalytical data. Next, go to step 1120, the association identification module of the server associates the third file data from the database according to at least one of the plurality of third bioanalysis data and the second bioanalysis data. Next, go to step 1130 , the association identifying module associates the first bioanalytical data with the second bioanalytical data, a plurality of third bioanalytical data and the third file data. The analysis module communicates with the correlation identification module. In a specific embodiment, the first file data is clinical file data, the third file data is patent file data, the first bio-analysis data is drug code data or drug name data, and the second bio-analysis data is bio-enterprise entity data. In a specific embodiment, the plurality of third biological analysis data are respectively drug data, disease data, gene data, gene sequence data, protein data, enzyme data, organism data, cell line data, cell bank serial number data, and target data. , structural data, species data, pathway data, and one of bioenterprise entity data.
在一个具体实施例中,药物趋势分析方法1200进一步包括:由分析模块分析第一文件数据或第三文件数据以得出第九生物数据;由关联性识别模块至少根据第九生物数据以自数据库中关联出第四文件数据;以及由关联性识别模块将第一生物分析数据关联于第九生物数据与第四文件数据。在一具体实施例中,第一生物分析数据为药物代号数据,第九生物数据为药物名称数据。而第四文件数据为专利文件数据、临床文件数据、科学出版物文件数据、新闻文件数据以及公司报告文件数据其中一者。在一具体实施例中,关联性识别模块根据所述多个第三生物分析数据其中至少一者以及第九生物数据,以自数据库中关联出第四文件数据。In a specific embodiment, the drug trend analysis method 1200 further includes: analyzing the first file data or the third file data by the analyzing module to obtain ninth biological data; and correlate the fourth file data with the correlation identification module; and correlate the first biological analysis data with the ninth biological data and the fourth file data by the correlation identification module. In a specific embodiment, the first biological analysis data is drug code data, and the ninth biological data is drug name data. The fourth document data is one of patent document data, clinical document data, scientific publication document data, news document data and company report document data. In a specific embodiment, the association identification module associates the fourth document data from the database according to at least one of the plurality of third biometric analysis data and the ninth biometric data.
在一个具体实施例中,药物趋势分析方法1200进一步包括:由分析模块分析第一文件数据以得出第一生物数据与第二生物数据;由分析模块分析第二文件数据以得出第三生物数据与第四生物数据;由关联性识别模块根据分析结果将第一生物数据关联于第二生物数据、第三生物数据、第四生物数据与第二文件数据。在一具体实施例中,分析结果指出第一生物数据与第三生物数据的相似度大于预定的相似度临界值,此即表示第一生物数据与第三生物数据具有极大的相似度或关联性。在一具体实施例中,第一生物数据与第三生物数据均为基因序列数据,第二生物数据为药物数据(例如可为药物名称数据或药物代号数据),第四生物数据为疾病数据。在另一具体实施例中,第一生物数据与第三生物数据均为蛋白质数据,第二生物数据为药物数据(例如可为药物名称数据或药物代号数据), 第四生物数据为疾病数据。藉此,关联性识别模块123即可根据不同的文件数据以找出某药物可能具有的新应用领域,或是可针对某疾病(例如COVID 19(Coronavirus Disease))找出现有的可能有用的药物。In a specific embodiment, the drug trend analysis method 1200 further includes: analyzing the first file data by the analysis module to obtain the first biological data and the second biological data; analyzing the second file data by the analysis module to obtain the third biological data data and the fourth biological data; the correlation identification module associates the first biological data with the second biological data, the third biological data, the fourth biological data and the second file data according to the analysis result. In a specific embodiment, the analysis result indicates that the similarity between the first biometric data and the third biometric data is greater than a predetermined similarity threshold, which means that the first biometric data and the third biometric data have a great similarity or correlation sex. In a specific embodiment, the first biological data and the third biological data are both gene sequence data, the second biological data is drug data (eg, drug name data or drug code data), and the fourth biological data is disease data. In another specific embodiment, the first biological data and the third biological data are both protein data, the second biological data is drug data (for example, drug name data or drug code data), and the fourth biological data is disease data. In this way, the correlation identification module 123 can find out the possible new application fields of a certain medicine according to different file data, or can find out the existing medicines that may be useful for a certain disease (eg, COVID 19 (Coronavirus Disease)). .
在一个具体实施例中,药物趋势分析方法1200进一步包括:由服务器的图像绘制模块根据来自第一装置的第五指令产生第三图像数据,并将第三图像数据提供给第一装置。其中第三图像数据包括第一生物分析数据以及关联于第一生物分析数据的第二生物分析数据与多个第三生物分析数据。且其中图像绘制模块通信连接所述分析模块与关联性识别模块。在一具体实施例中,第三图像数据并包括第九生物数据、第一文件数据、第三文件数据与第四文件数据。In a specific embodiment, the drug trend analysis method 1200 further includes: generating, by the image rendering module of the server, third image data according to the fifth instruction from the first device, and providing the third image data to the first device. The third image data includes first bioanalytical data and second bioanalytical data and a plurality of third bioanalytical data associated with the first bioanalytical data. And wherein the image drawing module communicates with the analysis module and the correlation identification module. In a specific embodiment, the third image data further includes ninth biological data, first file data, third file data and fourth file data.
请参阅图13A,其例示说明了本申请药物趋势分析方法一具体实施例的示意图。如图13A所示,服务器的分析模块可先自临床文件数据1310分析出药物代号数据1311、生物企业实体数据1312以及第三生物分析数据1313、1314、1315、1316、1317。其中,临床文件数据1310即为第一文件数据,药物代号数据1311即为第一生物分析数据,生物企业实体数据1312即为第二生物分析数据。第三生物分析数据1313为疾病数据,其指示出临床文件数据1310中的药物可用于骨质疏松症。接着,服务器的关联性识别模块可根据第三生物分析数据1313、1314、1315、1316、1317其中至少一者以及生物企业实体数据1312得出相关联的专利文件数据1322、1324、1326。Please refer to FIG. 13A , which illustrates a schematic diagram of a specific embodiment of the drug trend analysis method of the present application. As shown in FIG. 13A , the analysis module of the server can first analyze the drug code data 1311 , the biological enterprise entity data 1312 and the third biological analysis data 1313 , 1314 , 1315 , 1316 and 1317 from the clinical file data 1310 . The clinical file data 1310 is the first file data, the drug code data 1311 is the first bioanalysis data, and the biological enterprise entity data 1312 is the second bioanalysis data. The third bioanalytical data 1313 is disease data indicating that the drugs in the clinical file data 1310 are available for osteoporosis. Then, the association identification module of the server can obtain the associated patent document data 1322 , 1324 , 1326 according to at least one of the third biometric analysis data 1313 , 1314 , 1315 , 1316 , and 1317 and the biological enterprise entity data 1312 .
请参阅图13B,其例示说明了本申请药物趋势分析方法一具体实施例的示意图。如图13B所示,关联性识别模块可根据第三生物分析数据1313、1314、1315、1316、1317其中至少一者及/或生物企业实体数据1312得出相关联的科学出版物文件数据1331~1336。并可由分析模块自科学出版物文件数据1332得出药物名称数据1339。应了解,关联性识别模块并非仅可根据第三生物分析数据1313、1314、1315、1316、1317其中至少一者及/或生物企业实体数据1312得出相关联的专利文件数据或科学出版物文件数据,关联性识别模块亦可根据第三生物分析数据1313、1314、1315、1316、1317其中至少一者及/或生物企业实体数据1312得出新闻文件数据、公司报告文件数据等,但不以此为限。Please refer to FIG. 13B , which illustrates a schematic diagram of a specific embodiment of the drug trend analysis method of the present application. As shown in FIG. 13B , the association identification module may derive associated scientific publication file data 1331- 1336. And drug name data 1339 may be derived from scientific publication file data 1332 by the analysis module. It should be understood that the association identification module may not only derive the associated patent document data or scientific publication document from at least one of the third bioanalytical data 1313 , 1314 , 1315 , 1316 , 1317 and/or the biological enterprise entity data 1312 Data, the correlation identification module can also obtain news file data, company report file data, etc. according to at least one of the third bioanalytical data 1313, 1314, 1315, 1316, 1317 and/or the bio-enterprise entity data 1312. This is limited.
请参阅图13C,其例示说明了本申请药物趋势分析方法一具体实施例的示意图。如图13C所示,分析模块可自关联性识别模块所得出的文件数据中,分析出临床文件数据1310中的药物的序列1340。藉此,关联性识别模块可再进一步关联出相关联的各种文件数据1351~1356(在此示例中为专利文件数据等,但实际上并不以此为限)。而后,药物趋势分析系统可藉由所得出的生物分析数据、文件数据(例如专利文件数据等,但不以此为限) 及文件数据的相关数据(例如专利文件数据的申请日、申请人等数据)以分析及预测此药物的趋势。Please refer to FIG. 13C , which illustrates a schematic diagram of a specific embodiment of the drug trend analysis method of the present application. As shown in FIG. 13C , the analysis module can analyze the sequence 1340 of drugs in the clinical document data 1310 from the document data obtained by the association identification module. In this way, the correlation identification module can further correlate various related document data 1351-1356 (in this example, patent document data, etc., but it is not limited in practice). Then, the drug trend analysis system can use the obtained bioanalytical data, document data (such as patent document data, etc., but not limited thereto) and related data of document data (such as the filing date of patent document data, applicant, etc.) data) to analyze and predict trends for this drug.
至此,本申请的药物趋势分析系统及其方法已经由上述说明及图式加以说明。然应了解,本申请的各个具体实施例仅是用于说明,在不脱离本申请申请专利范围与精神下可进行各种改变,且均应包括于本申请的专利范围中。因此,本说明书所描述的各具体实施例并非用以限制本申请,本申请的真实范围与精神公开于随附权利要求的范围。So far, the drug trend analysis system and method of the present application have been described by the above description and drawings. However, it should be understood that the specific embodiments of the present application are only for illustration, and various changes can be made without departing from the scope and spirit of the patent application of the application, and should be included in the patent scope of the application. Therefore, the specific embodiments described in this specification are not intended to limit the application, and the true scope and spirit of the application are disclosed in the scope of the appended claims.
虽然本申请已以较佳实施例进行以上公开,然其并非用以限定本申请,任何所属技术领域中技术人员,在不脱离本申请的精神和范围内,可变更与组合上述各种实施例。Although the present application has been disclosed above with preferred embodiments, it is not intended to limit the present application. Any person skilled in the art can change and combine the above-mentioned various embodiments without departing from the spirit and scope of the present application. .

Claims (20)

  1. 一种药物趋势分析方法,应用于包含数据库以及服务器的药物趋势分析系统,所述服务器访问所述数据库;所述药物趋势分析方法包括:A drug trend analysis method is applied to a drug trend analysis system comprising a database and a server, and the server accesses the database; the drug trend analysis method comprises:
    由所述服务器的分析模块分析第一文件数据以得出第一生物分析数据、第二生物分析数据与多个第三生物分析数据;Analyzing the first file data by the analysis module of the server to obtain first bioanalytical data, second bioanalytical data and a plurality of third bioanalytical data;
    由所述服务器的关联性识别模块根据所述多个第三生物分析数据其中至少一者以及所述第二生物分析数据,以自所述数据库中关联出第三文件数据;以及Correlating third document data from the database by the association identification module of the server according to at least one of the plurality of third bioanalytical data and the second bioanalytical data; and
    由所述关联性识别模块将所述第一生物分析数据关联于所述第二生物分析数据、所述多个第三生物分析数据与所述第三文件数据;associating the first bioanalytical data with the second bioanalytical data, the plurality of third bioanalytical data, and the third file data by the correlation identification module;
    其中所述分析模块通信连接所述关联性识别模块。Wherein the analysis module is communicatively connected to the correlation identification module.
  2. 如权利要求1所述的药物趋势分析方法,其中所述第一文件数据为临床文件数据,所述第三文件数据为专利文件数据,所述第一生物分析数据为药物代号数据或药物名称数据,所述第二生物分析数据为生物企业实体数据。The drug trend analysis method according to claim 1, wherein the first file data is clinical file data, the third file data is patent file data, and the first biological analysis data is drug code data or drug name data , the second biological analysis data is biological enterprise entity data.
  3. 如权利要求1所述的药物趋势分析方法,其中所述多个第三生物分析数据分别为药物数据、疾病数据、基因数据、基因序列数据、蛋白质数据、酶数据、有机体数据、细胞株数据、细胞库序号数据、标靶数据、结构数据、物种数据、途径数据以及生物企业实体数据其中一者。The drug trend analysis method according to claim 1, wherein the plurality of third biological analysis data are drug data, disease data, gene data, gene sequence data, protein data, enzyme data, organism data, cell line data, One of cell bank serial number data, target data, structural data, species data, pathway data, and bioenterprise entity data.
  4. 如权利要求1所述的药物趋势分析方法,进一步包括:The drug trend analysis method of claim 1, further comprising:
    由所述分析模块分析所述第一文件数据或所述第三文件数据以得出第九生物数据;analyzing the first file data or the third file data by the analysis module to derive ninth biological data;
    由所述关联性识别模块至少根据所述第九生物数据以自所述数据库中关联出第四文件数据;以及by the association identification module to associate fourth document data from the database based on at least the ninth biometric data; and
    由所述关联性识别模块将所述第一生物分析数据关联于所述第九生物数据与所述第四文件数据。The first bioanalytical data is associated with the ninth biometric data and the fourth file data by the association identification module.
  5. 如权利要求4所述的药物趋势分析方法,其中所述第一生物分析数据为药物代号数据,所述第九生物数据为药物名称数据,其中所述第四文件数据为专利文件数据、临床文件数据、科学出版物文件数据、新闻文件数据以及公司报告文件数据其中一者。The drug trend analysis method according to claim 4, wherein the first biological analysis data is drug code data, the ninth biological data is drug name data, and wherein the fourth document data is patent document data, clinical document data One of data, scientific publication file data, news file data, and company report file data.
  6. 如权利要求4所述的药物趋势分析方法,其中所述关联性识别模块根据所述多个第三生物分析数据其中至少一者以及所述第九生物数据,以自所述数据库中关联出所述第四文件数据。The drug trend analysis method according to claim 4, wherein the correlation identification module is based on at least one of the plurality of third biological analysis data and the ninth biological data to correlate all the data from the database. Describe the fourth file data.
  7. 如权利要求1所述的药物趋势分析方法,进一步包括:The drug trend analysis method of claim 1, further comprising:
    由所述分析模块分析所述第一文件数据以得出第一生物数据与第二生物数据;Analyzing the first file data by the analysis module to obtain first biological data and second biological data;
    由所述分析模块分析第二文件数据以得出第三生物数据与第四生物数据;analyzing the second file data by the analysis module to obtain third biological data and fourth biological data;
    由所述关联性识别模块根据分析结果将所述第一生物数据关联于所述第二生物数据、所述第三生物数据、所述第四生物数据与所述第二文件数据。The association identification module associates the first biometric data with the second biometric data, the third biometric data, the fourth biometric data and the second file data according to the analysis result.
  8. 如权利要求7所述的药物趋势分析方法,其中所述分析结果指出所述第一生物数据与所述第三生物数据的相似度大于预定的相似度临界值。The drug trend analysis method of claim 7, wherein the analysis result indicates that the similarity between the first biological data and the third biological data is greater than a predetermined similarity threshold.
  9. 如权利要求8所述的药物趋势分析方法,其中所述第一生物数据与所述第三生物数据均为基因序列数据或均为蛋白质数据,所述第二生物数据为药物数据,所述第四生物数据为疾病数据。The drug trend analysis method according to claim 8, wherein the first biological data and the third biological data are both gene sequence data or both are protein data, the second biological data is drug data, and the first biological data is drug data. Four biological data are disease data.
  10. 如权利要求1所述的药物趋势分析方法,进一步包括:The drug trend analysis method of claim 1, further comprising:
    由所述服务器的图像绘制模块根据来自第一装置的第五指令产生第三图像数据,并将所述第三图像数据提供给所述第一装置;generating third image data by an image rendering module of the server according to a fifth instruction from the first device, and providing the third image data to the first device;
    其中所述第三图像数据包含所述第一生物分析数据以及关联于所述第一生物分析数据的所述第二生物分析数据与所述多个第三生物分析数据;wherein the third image data includes the first bioanalytical data and the second bioanalytical data and the plurality of third bioanalytical data associated with the first bioanalytical data;
    其中所述图像绘制模块通信连接所述分析模块与所述关联性识别模块。Wherein, the image rendering module is communicatively connected to the analysis module and the correlation identification module.
  11. 一种药物趋势分析系统,包括:A drug trend analysis system including:
    数据库;以及database; and
    服务器,访问所述数据库,所述服务器包含:A server, accessing the database, the server comprising:
    分析模块,分析第一文件数据以得出第一生物分析数据、第二生物分析数据与多个第三生物分析数据;以及an analysis module that analyzes the first file data to obtain first bioanalytical data, second bioanalytical data and a plurality of third bioanalytical data; and
    关联性识别模块,根据所述多个第三生物分析数据其中至少一者以及所述第二生物分析数据,以自所述数据库中关联出第三文件数据,所述关联性识别模块并将所述第一生物分析数据关联于所述第二生物分析数据、所述多个第三生物分析数据与所述第三文件数据;A correlation identification module, according to at least one of the plurality of third biological analysis data and the second biological analysis data, to correlate third file data from the database, the correlation identification module and the the first bioanalytical data is associated with the second bioanalytical data, the plurality of third bioanalytical data and the third file data;
    其中所述分析模块通信连接所述关联性识别模块。Wherein the analysis module is communicatively connected to the correlation identification module.
  12. 如权利要求11所述的药物趋势分析系统,其中所述第一文件数据为临床文件数据,所述第三文件数据为专利文件数据,所述第一生物分析数据为药物代号数据或药物名称数据,所述第二生物分析数据为生物企业实体数据。The drug trend analysis system of claim 11, wherein the first file data is clinical file data, the third file data is patent file data, and the first bioanalysis data is drug code data or drug name data , the second biological analysis data is biological enterprise entity data.
  13. 如权利要求11所述的药物趋势分析系统,其中所述多个第三生物分析数据分别为药物数据、疾病数据、基因数据、基因序列数据、蛋白质数据、酶数据、有机体数据、 细胞株数据、细胞库序号数据、标靶数据、结构数据、物种数据、途径数据以及生物企业实体数据其中一者。The drug trend analysis system according to claim 11, wherein the plurality of third biological analysis data are drug data, disease data, gene data, gene sequence data, protein data, enzyme data, organism data, cell line data, One of cell bank serial number data, target data, structural data, species data, pathway data, and bioenterprise entity data.
  14. 如权利要求11所述的药物趋势分析系统,其中所述分析模块分析所述第一文件数据或所述第三文件数据以得出第九生物数据;其中所述关联性识别模块至少根据所述第九生物数据以自所述数据库中关联出第四文件数据;且其中所述关联性识别模块将所述第一生物分析数据关联于所述第九生物数据与所述第四文件数据。The drug trend analysis system of claim 11, wherein the analysis module analyzes the first file data or the third file data to derive ninth biological data; wherein the correlation identification module is based on at least the The ninth biological data is associated with fourth document data from the database; and wherein the association identification module associates the first biological analysis data with the ninth biological data and the fourth document data.
  15. 如权利要求14所述的药物趋势分析系统,其中所述第一生物分析数据为药物代号数据,所述第九生物数据为药物名称数据,其中所述第四文件数据为专利文件数据、临床文件数据、科学出版物文件数据、新闻文件数据以及公司报告文件数据其中一者。The drug trend analysis system according to claim 14, wherein the first biological analysis data is drug code data, the ninth biological data is drug name data, wherein the fourth document data is patent document data, clinical document data One of data, scientific publication file data, news file data, and company report file data.
  16. 如权利要求14所述的药物趋势分析系统,其中所述关联性识别模块根据所述多个第三生物分析数据其中至少一者以及所述第九生物数据,以自所述数据库中关联出所述第四文件数据。15. The drug trend analysis system of claim 14, wherein the correlation identification module correlates all the data from the database according to at least one of the plurality of third biological analysis data and the ninth biological data Describe the fourth file data.
  17. 如权利要求11所述的药物趋势分析系统,其中所述分析模块分析所述第一文件数据以得出第一生物数据与第二生物数据;其中所述分析模块分析第二文件数据以得出第三生物数据与第四生物数据;且其中所述关联性识别模块根据分析结果将所述第一生物数据关联于所述第二生物数据、所述第三生物数据、所述第四生物数据与所述第二文件数据。The drug trend analysis system of claim 11, wherein the analysis module analyzes the first file data to derive first biological data and second biological data; wherein the analysis module analyzes the second file data to derive the third biometric data and the fourth biometric data; and wherein the association identification module associates the first biometric data with the second biometric data, the third biometric data, and the fourth biometric data according to the analysis result with the second file data.
  18. 如权利要求17所述的药物趋势分析系统,其中所述分析结果指出所述第一生物数据与所述第三生物数据的相似度大于预定的相似度临界值。The drug trend analysis system of claim 17, wherein the analysis result indicates that the similarity between the first biological data and the third biological data is greater than a predetermined similarity threshold.
  19. 如权利要求18所述的药物趋势分析系统,其中所述第一生物数据与所述第三生物数据均为基因序列数据或均为蛋白质数据,所述第二生物数据为药物数据,所述第四生物数据为疾病数据。The drug trend analysis system according to claim 18, wherein the first biological data and the third biological data are both gene sequence data or both are protein data, the second biological data is drug data, and the first biological data is drug data. Four biological data are disease data.
  20. 如权利要求11所述的药物趋势分析系统,其中所述服务器包含图像绘制模块,所述图像绘制模块根据来自第一装置的第五指令产生第三图像数据,并将所述第三图像数据提供给所述第一装置;其中所述第三图像数据包含所述第一生物分析数据以及关联于所述第一生物分析数据的所述第二生物分析数据与所述多个第三生物分析数据;其中所述图像绘制模块通信连接所述分析模块、所述关联性识别模块与所述提供模块。The drug trend analysis system of claim 11, wherein the server comprises an image rendering module, the image rendering module generates third image data according to the fifth instruction from the first device, and provides the third image data to the first device; wherein the third image data includes the first bioanalytical data and the second bioanalytical data and the plurality of third bioanalytical data associated with the first bioanalytical data ; wherein the image rendering module is communicatively connected to the analysis module, the correlation identification module and the providing module.
PCT/CN2021/103021 2020-06-29 2021-06-29 Drug trend analysis system and method therefor WO2022002029A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010605282.3A CN113934811A (en) 2020-06-29 2020-06-29 Drug trend analysis system and method
CN202010605282.3 2020-06-29

Publications (1)

Publication Number Publication Date
WO2022002029A1 true WO2022002029A1 (en) 2022-01-06

Family

ID=79272967

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/103021 WO2022002029A1 (en) 2020-06-29 2021-06-29 Drug trend analysis system and method therefor

Country Status (2)

Country Link
CN (1) CN113934811A (en)
WO (1) WO2022002029A1 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107861996A (en) * 2017-10-16 2018-03-30 中国医学科学院医学信息研究所 A kind of medicine evidence-based database Diagrams automatic creation system
US20180276340A1 (en) * 2015-01-23 2018-09-27 Data4Cure, Inc. System and method for drug target and biomarker discovery and diagnosis using a multidimensional multiscale module map
CN109791797A (en) * 2016-12-05 2019-05-21 智慧芽信息科技(苏州)有限公司 According to the systems, devices and methods of chemical structure similarity searching and display available information in large database concept
CN109903816A (en) * 2019-01-29 2019-06-18 郑州金域临床检验中心有限公司 A kind of pharmacogenomic analysis system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180276340A1 (en) * 2015-01-23 2018-09-27 Data4Cure, Inc. System and method for drug target and biomarker discovery and diagnosis using a multidimensional multiscale module map
CN109791797A (en) * 2016-12-05 2019-05-21 智慧芽信息科技(苏州)有限公司 According to the systems, devices and methods of chemical structure similarity searching and display available information in large database concept
CN107861996A (en) * 2017-10-16 2018-03-30 中国医学科学院医学信息研究所 A kind of medicine evidence-based database Diagrams automatic creation system
CN109903816A (en) * 2019-01-29 2019-06-18 郑州金域临床检验中心有限公司 A kind of pharmacogenomic analysis system

Also Published As

Publication number Publication date
CN113934811A (en) 2022-01-14

Similar Documents

Publication Publication Date Title
Hegde et al. Similar image search for histopathology: SMILY
US11581070B2 (en) Electronic medical record summary and presentation
Paramei Singing the Russian blues: An argument for culturally basic color terms
Hellsten et al. Implicit media frames: Automated analysis of public debate on artificial sweeteners
Rubin et al. iPad: Semantic annotation and markup of radiological images
Hund et al. Visual analytics for concept exploration in subspaces of patient groups: making sense of complex datasets with the doctor-in-the-loop
US9892279B2 (en) Creating an access control policy based on consumer privacy preferences
Mackenzie et al. Living multiples: How large-scale scientific data-mining pursues identity and differences
Read et al. Sizing the problem of improving discovery and access to NIH-funded data: a preliminary study
Phan et al. Racial formations as data formations
Dorsey et al. Working together to advance symptom science in the precision era
Baughan et al. Sequestration of imaging studies in MIDRC: a multi-institutional data commons
WO2022002029A1 (en) Drug trend analysis system and method therefor
Van Meenen et al. Making Biomedical Sciences publications more accessible for machines
Loyek et al. BioIMAX: A Web 2.0 approach for easy exploratory and collaborative access to multivariate bioimage data
CN114756752A (en) Medical information searching method, device, equipment and storage medium
Huang et al. Development of the Lymphoma Enterprise Architecture Database: A caBIG™ Silver Level Compliant System
Zhou et al. A novel framework for bringing smart big data to proactive decision making in healthcare
Harrison Jr Pathology informatics questions and answers from the University of Pittsburgh pathology residency informatics rotation
Kim et al. Explorative analyses of nursing research data
Zhu et al. Embedding, aligning and reconstructing clinical notes to explore sepsis
Reifegerste et al. Content Analysis in the Research Field of Health Coverage
Petram et al. Transforming historical research practices–a digital infrastructure for the VOC archives (GLOBALISE)
Kuhlmann et al. The THESEUS use cases
Dinsmore et al. An audit of the'two-glass' test for urethritis

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21833374

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21833374

Country of ref document: EP

Kind code of ref document: A1