A three-dimensional visualization method for biomedical platform data maps

Abstract

The present invention belongs to the field of three-dimensional visualization technology and discloses a three-dimensional visualization method for a biomedical platform data map. The method includes installing SQL Server in the biomedical platform; constructing a biomedical database through SQL services; collecting biomedical product data and production and sales geographic data through a vertical search engine; transmitting the data to the platform in the form of a data stream; cleaning the collected medical data and storing it in the biomedical database; constructing a biomedical platform map canvas through a map construction program; constructing a map model on the map canvas, and displaying the map model in association with the biomedical data through key geographic information in the biomedical data; and constructing a biomedical knowledge graph, and associating the knowledge graph with the map model through a vector file. The present invention can reduce the number of displayed tables by constructing a biomedical platform map canvas through a map construction program, thereby improving the efficiency of constructing data maps.

Description

Technical Field

[0001] The present invention belongs to the field of three-dimensional visualization technology, and in particular relates to a biomedical platform data map. Figure 3 dimensional visualization method. Background Art

[0002] The pharmaceutical industry and the biomedical engineering industry are the two pillars of the modern pharmaceutical industry. The biomedical industry is composed of the biotechnology industry and the pharmaceutical industry. Biomedical engineering is a general term for the comprehensive application of the principles and methods of life science and engineering science to understand the structure, function and other life phenomena of the human body at multiple levels of molecules, cells, tissues, organs and even the entire human body system from an engineering perspective, and to study artificial materials, products, devices and system technologies used for disease prevention, treatment, human function assistance and health care. However, the existing biomedical platform data is not available. Figure 3 The amount of biomedical data in the 3D visualization method is large, the time to build the data map is long, and the efficiency is low; at the same time, it is unable to display the medicinal properties of biomedicine.

[0003] Through the above analysis, the problems and defects of the existing technology are as follows:

[0004] (1) Existing biomedical platform data Figure 3 The amount of biomedical data is large, and building data maps takes a long time and is inefficient.

[0005] (2) Unable to demonstrate the medicinal properties of biopharmaceuticals. Summary of the Invention

[0006] In view of the problems existing in the prior art, the present invention provides a biomedical platform data map Figure 3 dimensional visualization method.

[0007] The present invention is achieved by a biomedical platform data Figure 3 Dimensional visualization methods include:

[0008] Step 1: Install SQLSERVER in the biomedical platform;

[0009] Step 2: Build a biomedical database using SQL services;

[0010] Step 3: Collect biopharmaceutical product data and production and sales geographic data through vertical search engines and transmit them to the platform in the form of data streams;

[0011] Step 4: Clean the collected medical data and store them in the biomedical database;

[0012] Step 5: Build a biomedical platform map canvas through a map building program;

[0013] Step 6: construct a map model on the map canvas, and associate the map model with the biomedical data through key geographic information in the biomedical data;

[0014] Step seven: Build a biomedical knowledge graph and associate the knowledge graph with the map model through a vector file.

[0015] Furthermore, the method for building a biomedical platform map canvas through a map building program is as follows:

[0016] 1) obtaining a biomedical data relationship from a biomedical data relationship table, and generating a first biomedical data map based on the biomedical data relationship, wherein the first biomedical data map includes biomedical data associated with the biomedical data relationship, wherein the biomedical data relationship includes source biomedical data and destination biomedical data;

[0017] 2) determining first biomedical data to be expanded from the biomedical data associated with the biomedical data relationship; obtaining a table relationship corresponding to the first biomedical data from a table relationship table, and generating a second biomedical data map based on the table relationship, wherein the second biomedical data map includes a data table associated with the first biomedical data, wherein the table relationship includes a source data table and a destination data table;

[0018] 3) Using a map building program to build a biomedical platform map canvas based on the biomedical data map;

[0019] Furthermore, before generating the first biomedical data map, the method further includes:

[0020] receiving table relationships included in biomedical data, and recording the table relationships of the biomedical data in the table relationship table;

[0021] Determining the biomedical data relationship according to the table relationship of each biomedical data recorded in the table relationship table;

[0022] The determined biomedical data relationship is recorded in the biomedical data relationship table.

[0023] Furthermore, the biomedical data relationship table includes a connection table corresponding to the biomedical data relationship, wherein a target data table in a table relationship of source biomedical data included in the biomedical data relationship and a source data table in a table relationship of the target biomedical data are the same, and the same data table is the connection table corresponding to the biomedical data relationship.

[0024] The obtaining of the table relationship corresponding to the first biomedical data from the table relationship table and generating the second biomedical data map according to the table relationship includes:

[0025] Obtaining the table relationship of the first biomedical data from the table relationship table to obtain a table relationship set;

[0026] querying a biomedical data relationship including the first biomedical data from a biomedical data relationship table, wherein the queryed biomedical data relationship includes second biomedical data associated with the first biomedical data;

[0027] If the second biomedical data included in the queried biomedical data relationship is in an unexpanded state, obtaining the connection table corresponding to the queried biomedical data relationship from the biomedical data relationship table;

[0028] Acquire at least one table relationship including the connection table from the table relationship set, and modify the connection table in the acquired table relationship to the second biomedical data;

[0029] A second biomedical data map is generated according to the updated table relationship set.

[0030] Furthermore, the query method:

[0031] Obtaining biomedical text data to be queried; inputting the biomedical text data to be queried into a synonym standard database to obtain attribute categories of keywords of the biomedical text data to be queried;

[0032] Inputting the attribute category into a mapping rule library to obtain a medical data query result of the biomedical text data to be queried;

[0033] The biomedical text data to be queried is professional descriptive information biomedical text data or non-professional descriptive information biomedical text data;

[0034] The step of inputting the biomedical text data to be queried into a synonym standard database to obtain the attribute categories of the keywords of the biomedical text data to be queried comprises: inputting the biomedical text data to be queried into a synonym standard database, and obtaining the keywords of the biomedical text data to be queried according to a synonym standard table of the synonym standard database; and obtaining the attribute categories of the keywords of the biomedical text data to be queried according to the keywords and a plurality of sub-databases of the synonym standard database;

[0035] The biomedical text data to be queried is input into a synonym standard database, and keywords of the biomedical text data to be queried are obtained according to a synonym standard table of the synonym standard database.

[0036] Automatically segmenting the biomedical text data to be queried;

[0037] Comparing the segmented biomedical text data with a pre-set synonym standard table in a synonym standard database to obtain keywords for the biomedical text data to be queried;

[0038] The synonym standard database includes multiple pieces of structured information;

[0039] Each of the plurality of structured information includes the correct name of the keyword, the synonyms of the keyword, and the attribute category of the keyword;

[0040] The attribute categories include disease categories, symptom categories, syndrome categories, efficacy categories and prescription categories;

[0041] The multiple sub-databases of the synonym standard database include a disease database, a symptom database, a syndrome database, an efficacy database and a prescription database;

[0042] The attribute categories of the keywords of the biomedical text data to be queried obtained based on the keywords and multiple sub-databases of the synonym standard database include:

[0043] Classifying the keywords according to attribute categories;

[0044] The classified keywords are respectively input into the sub-database of the synonym standard database for query, and the attribute categories of the keywords of the biomedical text data to be queried are obtained.

[0045] Furthermore, the construction process of the mapping rule base includes:

[0046] Obtaining the number of levels of language variables and the number of mapping rules, and establishing a form of the mapping rules according to the number of levels of language variables and the number of mapping rules;

[0047] Obtain the mapping relationship between disease categories, symptom categories, syndrome categories, treatment method categories, and prescription categories;

[0048] A mapping rule library is constructed according to the form and mapping relationship of the mapping rules.

[0049] Furthermore, the step of modifying the connection table in the obtained table relationship into the second biomedical data includes:

[0050] When the source data table in the obtained table relationship is the connection table, modifying the source data table in the table relationship to the second biomedical data;

[0051] When the target data table in the obtained table relationship is the connection table, modifying the target data table in the table relationship to the second biomedical data;

[0052] After the second biomedical data map is generated, the state of the first biomedical data is updated to an expanded state.

[0053] Furthermore, the method for constructing the biomedical knowledge graph is as follows:

[0054] (1) Obtain the attribute data of biomedicine; obtain the interactions between biomedicines based on the attribute data of biomedicine and construct a knowledge graph.

[0055] The acquisition of biomedical attribute data includes:

[0056] Get all relevant properties of biopharmaceuticals;

[0057] Perform data cleaning on all relevant attributes of biopharmaceuticals;

[0058] The deep learning PCNN algorithm is used to extract the relationship between biomedicine and characteristic attributes in related attributes;

[0059] The data cleaning at least includes supplementing missing values, deleting noise data and data conversion;

[0060] The method of extracting the relationship between biomedicine and characteristic attributes in related attributes by using the deep learning PCNN algorithm includes:

[0061] Perform position encoding on the data of related attributes, encoding them according to the distance between each word in the sentence and the entity;

[0062] Cut a text in the manual data into three parts by cutting it at two entities respectively.

[0063] After concatenating the position features and text features, the above three segments of data are respectively extracted through CNN;

[0064] The extracted features are concatenated after passing through the maxpooling layer and then sent to the softmax layer to finally obtain the relation classification;

[0065] The interaction between the biomedicines at least includes information on medication combinations and contraindications.

[0066] Furthermore, the method for constructing a biomedical knowledge graph also includes backtesting and sampling the interactions between biomedicines in the constructed knowledge graph, and performing manual verification to optimize the constructed knowledge graph.

[0067] Furthermore, the method for constructing a knowledge graph of biomedicine also includes obtaining the maximum attribute value of the biomedicine and the number of its nearest associated biomedicines. If the number of all relevant attributes of the biomedicine is greater than its maximum attribute value and / or the number of nearest associated biomedicines is greater than a set value, all relevant attributes of the biomedicine are pruned.

[0068] In combination with the above technical solutions and the technical problems solved, please analyze the advantages and positive effects of the technical solutions to be protected by the present invention from the following aspects:

[0069] First, in view of the technical problems existing in the above-mentioned prior art and the difficulty of solving these problems, this paper closely combines the technical solutions to be protected by the present invention and the results and data during the research and development process, and analyzes in detail and in depth how the technical solutions of the present invention solve the technical problems and some creative technical effects brought about by solving the problems. The specific description is as follows:

[0070] The present invention uses a map construction program to build a biomedical platform map canvas method. The method can generate a corresponding first biomedical data map according to the biomedical data relationship, determine the first biomedical data to be displayed from the first biomedical data map, generate and display the second biomedical data map corresponding to the table relationship associated with the first biomedical data to be displayed, and can reduce the number of displayed tables, thereby improving the efficiency of building data maps, solving the existing biomedical platform data map. Figure 3 The three-dimensional visualization method solves the problems of large amount of biomedical data, long time to build data map and low efficiency; at the same time, by constructing a biomedical knowledge graph construction method to obtain the attribute data of biomedicine, and obtain the interaction between biomedicines based on the attribute data, it realizes the display of biomedical medicinal properties, solving the problem that existing technology cannot display the medicinal properties of biomedicine.

[0071] Second, considering the technical solution as a whole or from the perspective of the product, the technical effects and advantages of the technical solution to be protected by the present invention are described in detail as follows:

[0072] The present invention uses a map construction program to build a biomedical platform map canvas method, which can generate a corresponding first biomedical data map based on the biomedical data relationship, determine the first biomedical data to be displayed from the first biomedical data map, and generate and display a second biomedical data map corresponding to the table relationship associated with the first biomedical data to be displayed, which can reduce the number of displayed tables and thus improve the efficiency of constructing data maps; at the same time, by constructing a biomedical knowledge graph construction method, the attribute data of the biomedicine is obtained, and the interaction between the biomedicines is obtained based on the attribute data, thereby realizing the display of the medicinal properties of the biomedicine. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 The biomedical platform data provided by the embodiment of the present invention is Figure 3 Flowchart of the 3D visualization method.

[0074] Figure 2 This is a flow chart of a method for building a biomedical platform map canvas through a map building program provided by an embodiment of the present invention.

[0075] Figure 3 This is a flow chart of the method for constructing a biomedical knowledge graph provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0076] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0077] 1. Explanatory Examples In order to enable those skilled in the art to fully understand how to implement the present invention, this section provides an illustrative example that expands upon the technical solutions of the claims.

[0078] like Figure 1 As shown, the present invention provides a biomedical platform data Figure 3 The dimensional visualization method includes the following steps:

[0079] S101, install SQLSERVER in the biomedical platform;

[0080] S102, building a biomedical database using SQL services;

[0081] S103: Collect biopharmaceutical product data and production and sales geographic data through vertical search engines and transmit them to the platform in the form of data streams;

[0082] S104: Cleaning the collected medical data and storing it in a biomedical database;

[0083] S105, building a biomedical platform map canvas through a map building program;

[0084] S106, constructing a map model on the map canvas, and associating the map model with the biomedical data through key geographic information in the biomedical data for display;

[0085] S107, construct a biomedical knowledge graph and associate the knowledge graph with the map model through a vector file.

[0086] The present invention uses a map construction program to build a biomedical platform map canvas method, which can generate a corresponding first biomedical data map based on the biomedical data relationship, determine the first biomedical data to be displayed from the first biomedical data map, and generate and display a second biomedical data map corresponding to the table relationship associated with the first biomedical data to be displayed, which can reduce the number of displayed tables and thus improve the efficiency of constructing data maps; at the same time, by constructing a biomedical knowledge graph construction method, the attribute data of the biomedicine is obtained, and the interaction between the biomedicines is obtained based on the attribute data, thereby realizing the display of the medicinal properties of the biomedicine.

[0087] like Figure 2 As shown, the method for building a biomedical platform map canvas through a map building program provided by the present invention is as follows:

[0088] S201, obtaining a biomedical data relationship from a biomedical data relationship table, and generating a first biomedical data map based on the biomedical data relationship, wherein the first biomedical data map includes biomedical data associated with the biomedical data relationship, wherein the biomedical data relationship includes source biomedical data and destination biomedical data;

[0089] S202: Determine first biomedical data to be expanded from the biomedical data associated with the biomedical data relationship; obtain a table relationship corresponding to the first biomedical data from a table relationship table, and generate a second biomedical data map based on the table relationship, wherein the second biomedical data map includes a data table associated with the first biomedical data, wherein the table relationship includes a source data table and a destination data table;

[0090] S203, building a biomedical platform map canvas based on the biomedical data map through a map building program;

[0091] The present invention uses a map construction program to build a biomedical platform map canvas method, which can generate a corresponding first biomedical data map based on the biomedical data relationship, determine the first biomedical data to be displayed from the first biomedical data map, and generate and display a second biomedical data map corresponding to the table relationship associated with the first biomedical data to be displayed. This can reduce the number of displayed tables and thereby improve the efficiency of building data maps.

[0092] Before generating the first biomedical data map provided by the present invention, the method further includes:

[0093] receiving table relationships included in biomedical data, and recording the table relationships of the biomedical data in the table relationship table;

[0094] Determining the biomedical data relationship according to the table relationship of each biomedical data recorded in the table relationship table;

[0095] The determined biomedical data relationship is recorded in the biomedical data relationship table.

[0096] The biomedical data relationship table provided by the present invention includes a connection table corresponding to the biomedical data relationship, wherein the target data table in a table relationship of the source biomedical data included in the biomedical data relationship and the source data table in a table relationship of the target biomedical data are the same, and the same data table is the connection table corresponding to the biomedical data relationship.

[0097] The obtaining of the table relationship corresponding to the first biomedical data from the table relationship table and generating the second biomedical data map according to the table relationship includes:

[0098] Obtaining the table relationship of the first biomedical data from the table relationship table to obtain a table relationship set;

[0099] querying a biomedical data relationship including the first biomedical data from a biomedical data relationship table, wherein the queryed biomedical data relationship includes second biomedical data associated with the first biomedical data;

[0100] If the second biomedical data included in the queried biomedical data relationship is in an unexpanded state, obtaining the connection table corresponding to the queried biomedical data relationship from the biomedical data relationship table;

[0101] Acquire at least one table relationship including the connection table from the table relationship set, and modify the connection table in the acquired table relationship to the second biomedical data;

[0102] A second biomedical data map is generated according to the updated table relationship set.

[0103] The query method provided by the present invention:

[0104] Obtaining biomedical text data to be queried; inputting the biomedical text data to be queried into a synonym standard database to obtain attribute categories of keywords of the biomedical text data to be queried;

[0105] Inputting the attribute category into a mapping rule library to obtain a medical data query result of the biomedical text data to be queried;

[0106] The biomedical text data to be queried is professional descriptive information biomedical text data or non-professional descriptive information biomedical text data;

[0107] The step of inputting the biomedical text data to be queried into a synonym standard database to obtain the attribute categories of the keywords of the biomedical text data to be queried comprises: inputting the biomedical text data to be queried into a synonym standard database, and obtaining the keywords of the biomedical text data to be queried according to a synonym standard table of the synonym standard database; and obtaining the attribute categories of the keywords of the biomedical text data to be queried according to the keywords and a plurality of sub-databases of the synonym standard database;

[0108] The biomedical text data to be queried is input into a synonym standard database, and keywords of the biomedical text data to be queried are obtained according to a synonym standard table of the synonym standard database.

[0109] Automatically segmenting the biomedical text data to be queried;

[0110] Comparing the segmented biomedical text data with a pre-set synonym standard table in a synonym standard database to obtain keywords for the biomedical text data to be queried;

[0111] The synonym standard database includes multiple pieces of structured information;

[0112] Each of the plurality of structured information includes the correct name of the keyword, the synonyms of the keyword, and the attribute category of the keyword;

[0113] The attribute categories include disease categories, symptom categories, syndrome categories, efficacy categories and prescription categories;

[0114] The multiple sub-databases of the synonym standard database include a disease database, a symptom database, a syndrome database, an efficacy database and a prescription database;

[0115] The attribute categories of the keywords of the biomedical text data to be queried obtained based on the keywords and multiple sub-databases of the synonym standard database include:

[0116] Classifying the keywords according to attribute categories;

[0117] The classified keywords are respectively input into the sub-database of the synonym standard database for query, and the attribute categories of the keywords of the biomedical text data to be queried are obtained.

[0118] The construction process of the mapping rule base provided by the present invention includes:

[0119] Obtaining the number of levels of language variables and the number of mapping rules, and establishing a form of the mapping rules according to the number of levels of language variables and the number of mapping rules;

[0120] Obtain the mapping relationship between disease categories, symptom categories, syndrome categories, treatment method categories, and prescription categories;

[0121] A mapping rule library is constructed according to the form and mapping relationship of the mapping rules.

[0122] The present invention provides the method of modifying the connection table in the obtained table relationship into the second biomedical data, including:

[0123] When the source data table in the obtained table relationship is the connection table, modifying the source data table in the table relationship to the second biomedical data;

[0124] When the target data table in the obtained table relationship is the connection table, modifying the target data table in the table relationship to the second biomedical data;

[0125] After the second biomedical data map is generated, the state of the first biomedical data is updated to an expanded state.

[0126] like Figure 3 As shown, the method for constructing a biomedical knowledge graph provided by the present invention is as follows:

[0127] S301, obtaining attribute data of biomedicine; obtaining the interaction between biomedicines based on the attribute data of biomedicine, and constructing a knowledge graph.

[0128] The present invention obtains the attribute data of biomedicine by constructing a biomedicine knowledge graph construction method, and obtains the interaction between biomedicines based on the attribute data to realize the display of biomedicine medicinal properties.

[0129] The biomedical attribute data provided by the present invention includes:

[0130] Get all relevant properties of biopharmaceuticals;

[0131] Perform data cleaning on all relevant attributes of biopharmaceuticals;

[0132] The deep learning PCNN algorithm is used to extract the relationship between biomedicine and characteristic attributes in related attributes;

[0133] The data cleaning at least includes supplementing missing values, deleting noise data and data conversion;

[0134] The method of extracting the relationship between biomedicine and characteristic attributes in related attributes by using the deep learning PCNN algorithm includes:

[0135] Perform position encoding on the data of related attributes, encoding them according to the distance between each word in the sentence and the entity;

[0136] Cut a text in the manual data into three parts by cutting it at two entities respectively.

[0137] After concatenating the position features and text features, the above three segments of data are respectively extracted through CNN;

[0138] The extracted features are concatenated through the maxpooling layer and then sent to the softmax layer to finally obtain the relation classification.

[0139] The interactions between biomedicines provided by the present invention at least include information on medication combinations and information on contraindications.

[0140] The method for constructing a biomedical knowledge graph provided by the present invention also includes backtesting and sampling the interactions between biomedicines in the constructed knowledge graph, and performing manual verification to optimize the constructed knowledge graph.

[0141] The method for constructing a knowledge graph of biomedicine provided by the present invention also includes obtaining the maximum attribute value of the biomedicine and the number of its nearest associated biomedicines. If the number of all relevant attributes of the biomedicine is greater than its maximum attribute value and / or the number of nearest associated biomedicines is greater than a set value, all relevant attributes of the biomedicine are pruned.

[0142] 2. Application Examples: In order to demonstrate the creativity and technical value of the technical solution of the present invention, this section provides application examples of the claimed technical solution on specific products or related technologies.

[0143] The present invention uses a map construction program to build a biomedical platform map canvas method, which can generate a corresponding first biomedical data map based on the biomedical data relationship, determine the first biomedical data to be displayed from the first biomedical data map, and generate and display a second biomedical data map corresponding to the table relationship associated with the first biomedical data to be displayed, which can reduce the number of displayed tables and thus improve the efficiency of constructing data maps; at the same time, by constructing a biomedical knowledge graph construction method, the attribute data of the biomedicine is obtained, and the interaction between the biomedicines is obtained based on the attribute data, thereby realizing the display of the medicinal properties of the biomedicine.

[0144] When the present invention is working, first, SQL services are installed in the biomedical platform; a biomedical database is constructed through the SQL services; then biomedical product data and production and sales geographic data are collected through a vertical search engine; and the data are transmitted to the platform in the form of a data stream; the collected medical data is cleaned and stored in the biomedical database; then a map canvas of the biomedical platform is built through a map construction program; a map model is constructed on the map canvas, and the map model is associated with the biomedical data through key geographic information in the biomedical data for display; finally, a biomedical knowledge graph is constructed, and the knowledge graph and the map model are associated through a vector file.

[0145] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware portion can be implemented using dedicated logic; the software portion can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. Those skilled in the art will appreciate that the above-mentioned devices and methods can be implemented using computer-executable instructions and / or contained in processor control code, for example, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The devices and modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, or can be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0146] 3. Evidence of the effects of the embodiments: The embodiments of the present invention have achieved some positive effects during the development or use process, and indeed have great advantages over the existing technology. The following content describes them with reference to the data, charts, etc. of the experimental process.

[0147] The present invention uses a map construction program to build a biomedical platform map canvas method, which can generate a corresponding first biomedical data map based on the biomedical data relationship, determine the first biomedical data to be displayed from the first biomedical data map, and generate and display a second biomedical data map corresponding to the table relationship associated with the first biomedical data to be displayed, which can reduce the number of displayed tables and thus improve the efficiency of constructing data maps; at the same time, by constructing a biomedical knowledge graph construction method, the attribute data of the biomedicine is obtained, and the interaction between the biomedicines is obtained based on the attribute data, thereby realizing the display of the medicinal properties of the biomedicine.

[0148] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with this technical field within the technical scope disclosed by the present invention and within the spirit and principles of the present invention should be covered by the scope of protection of the present invention.

Claims

1. A three-dimensional visualization method for a biomedical platform data map, characterized in that: The method for three-dimensional visualization of a biomedical platform data map comprises the following steps: Step 1: Install SQL Server in the biomedical platform; Step 2: Build a biomedical database using SQL services; Step 3: Collect biopharmaceutical product data and production and sales geographic data through vertical search engines and transmit them to the platform in the form of data streams; Step 4: Clean the collected medical data and store them in the biomedical database; Step 5: Build a biomedical platform map canvas through a map building program; Step 6: construct a map model on the map canvas, and associate the map model with the biomedical data through key geographic information in the biomedical data; Step 7: Build a biomedical knowledge graph and associate the knowledge graph with the map model through a vector file; The method for building a biomedical platform map canvas using a map building program is as follows: 1) obtaining a biomedical data relationship from a biomedical data relationship table, and generating a first biomedical data map based on the biomedical data relationship, wherein the first biomedical data map includes biomedical data associated with the biomedical data relationship, wherein the biomedical data relationship includes source biomedical data and destination biomedical data; 2) determining first biomedical data to be expanded from the biomedical data associated with the biomedical data relationship; obtaining a table relationship corresponding to the first biomedical data from a table relationship table, and generating a second biomedical data map based on the table relationship, wherein the second biomedical data map includes a data table associated with the first biomedical data, wherein the table relationship includes a source data table and a destination data table; 3) Use the map construction program to build a biomedical platform map canvas based on the biomedical data map The method for constructing a biomedical knowledge graph is as follows: (1) Obtaining biomedical attribute data; obtaining the interactions between biomedical products based on the biomedical attribute data, and constructing a knowledge graph; The acquisition of biomedical attribute data includes: Get all relevant properties of biopharmaceuticals; Perform data cleaning on all relevant attributes of biopharmaceuticals; The deep learning PCNN algorithm is used to extract the relationship between biomedicine and characteristic attributes in related attributes; The data cleaning at least includes supplementing missing values, deleting noise data and data conversion; The method of extracting the relationship between biomedicine and characteristic attributes in related attributes by using the deep learning PCNN algorithm includes: Perform position encoding on the data of related attributes, encoding them according to the distance between each word in the sentence and the entity; Cut a text in the manual data into three parts by cutting it at two entities respectively. After concatenating the position features and text features, the above three segments of data are respectively extracted through CNN; The extracted features are concatenated after passing through the max pooling layer and then sent to the softmax layer to finally obtain the relation classification; The interactions between the biomedicines include at least information on medication combinations and contraindications.

2. The three-dimensional visualization method of the biomedical platform data map according to claim 1, characterized in that: Before generating the first biomedical data map, the method further includes: receiving table relationships included in biomedical data, and recording the table relationships of the biomedical data in the table relationship table; Determining the biomedical data relationship according to the table relationship of each biomedical data recorded in the table relationship table; The determined biomedical data relationship is recorded in the biomedical data relationship table.

3. The method for three-dimensional visualization of a biomedical platform data map according to claim 2, wherein: The biomedical data relationship table includes a connection table corresponding to the biomedical data relationship, wherein the target data table in a table relationship of the source biomedical data included in the biomedical data relationship and the source data table in a table relationship of the target biomedical data are the same, and the same data table is the connection table corresponding to the biomedical data relationship. The obtaining of the table relationship corresponding to the first biomedical data from the table relationship table and generating the second biomedical data map according to the table relationship includes: Obtaining the table relationship of the first biomedical data from the table relationship table to obtain a table relationship set; querying a biomedical data relationship including the first biomedical data from a biomedical data relationship table, wherein the queryed biomedical data relationship includes second biomedical data associated with the first biomedical data; If the second biomedical data included in the queried biomedical data relationship is in an unexpanded state, obtaining the connection table corresponding to the queried biomedical data relationship from the biomedical data relationship table; Acquire at least one table relationship including the connection table from the table relationship set, and modify the connection table in the acquired table relationship to the second biomedical data; A second biomedical data map is generated according to the updated table relationship set.

4. The three-dimensional visualization method of the biomedical platform data map according to claim 3, characterized in that: Query method: Obtaining biomedical text data to be queried; inputting the biomedical text data to be queried into a synonym standard database to obtain attribute categories of keywords of the biomedical text data to be queried; Inputting the attribute category into a mapping rule library to obtain a medical data query result of the biomedical text data to be queried; The biomedical text data to be queried is professional descriptive information biomedical text data or non-professional descriptive information biomedical text data; The step of inputting the biomedical text data to be queried into a synonym standard database to obtain the attribute categories of the keywords of the biomedical text data to be queried comprises: inputting the biomedical text data to be queried into a synonym standard database, and obtaining the keywords of the biomedical text data to be queried according to a synonym standard table of the synonym standard database; and obtaining the attribute categories of the keywords of the biomedical text data to be queried according to the keywords and a plurality of sub-databases of the synonym standard database; The biomedical text data to be queried is input into a synonym standard database, and keywords of the biomedical text data to be queried are obtained according to a synonym standard table of the synonym standard database. Automatically segmenting the biomedical text data to be queried; Comparing the segmented biomedical text data with a pre-set synonym standard table in a synonym standard database to obtain keywords for the biomedical text data to be queried; The synonym standard database includes multiple pieces of structured information; Each of the plurality of structured information includes the correct name of the keyword, the synonyms of the keyword, and the attribute category of the keyword; The attribute categories include disease categories, symptom categories, syndrome categories, efficacy categories and prescription categories; The multiple sub-databases of the synonym standard database include a disease database, a symptom database, a syndrome database, an efficacy database and a prescription database; The attribute categories of the keywords of the biomedical text data to be queried obtained based on the keywords and multiple sub-databases of the synonym standard database include: Classifying the keywords according to attribute categories; The classified keywords are respectively input into the sub-database of the synonym standard database for query, and the attribute categories of the keywords of the biomedical text data to be queried are obtained.

5. The three-dimensional visualization method of the biomedical platform data map according to claim 4, characterized in that: The construction process of the mapping rule base includes: Obtaining the number of levels of language variables and the number of mapping rules, and establishing a form of the mapping rules according to the number of levels of language variables and the number of mapping rules; Obtain the mapping relationship between disease categories, symptom categories, syndrome categories, treatment method categories, and prescription categories; A mapping rule library is constructed according to the form and mapping relationship of the mapping rules.

6. The method for three-dimensional visualization of a biomedical platform data map according to claim 3, wherein: The step of modifying the connection table in the obtained table relationship into the second biomedical data includes: When the source data table in the obtained table relationship is the connection table, modifying the source data table in the table relationship to the second biomedical data; When the target data table in the obtained table relationship is the connection table, modifying the target data table in the table relationship to the second biomedical data; After the second biomedical data map is generated, the state of the first biomedical data is updated to an expanded state.

7. The method for three-dimensional visualization of a biomedical platform data map according to claim 1, wherein: The method for constructing a biomedical knowledge graph also includes backtesting and sampling the interactions between biomedicines in the constructed knowledge graph, and performing manual verification to optimize the constructed knowledge graph.

8. The method for three-dimensional visualization of a biomedical platform data map according to claim 1, wherein: The method for constructing a knowledge graph of biomedicine also includes obtaining the maximum attribute value of the biomedicine and the number of its nearest associated biomedicines. If the number of all relevant attributes of the biomedicine is greater than its maximum attribute value and / or the number of nearest associated biomedicines is greater than a set value, all relevant attributes of the biomedicine are pruned.

Images