Medical research data layered exploration method and device, electronic equipment and medium

Abstract

The invention discloses a medical research data layered exploration method and device, electronic equipment and a medium. The method comprises the following steps: identifying a project demand document of a medical research project through a demand identification model, determining a data demand of the medical research project, and determining a standard library table matched with the data demand; generating a first-layer structured query statement and a second-layer structured query statement according to a data demand through a statement generation model; based on the standard library table, executing the first-layer structured query statement, and verifying the first query result through a result verification model; if the first query result passes the verification, executing a second-layer structured query statement on the first query result, and verifying a second query result through a result verification model; and taking the second query result passing the verification as a first probing result. The efficiency of medical research data exploration can be remarkably improved, and it is ensured that the first exploration result not only meets the overall requirements of a project, but also has high accuracy and integrity.

Description

Technical Field

[0001] This invention relates to the field of pharmaceutical research technology, and in particular to a method, apparatus, electronic device, storage medium, and program product for hierarchical exploration of pharmaceutical research data. Background Technology

[0002] When conducting pharmaceutical research projects, it is necessary to explore the data in the clinical data centers of medical institutions based on project requirements to determine whether there is sufficient data to meet the research needs of the project. In typical pharmaceutical research data projects, the data requirements are often written by pharmaceutical companies or business experts in the pharmaceutical field. The requirements are usually described in natural language, and data engineers need to convert the requirements into structured query statements. This process relies on the technical personnel's understanding of pharmaceutical business, which is prone to misunderstandings. Moreover, after being manually written, it requires multiple rounds of communication and confirmation with business personnel, which is time-consuming. Summary of the Invention

[0003] This invention provides a method, apparatus, electronic device, storage medium, and program product for hierarchical exploration of pharmaceutical research data, which can significantly improve the efficiency of pharmaceutical research data exploration and ensure that the first exploration results obtained not only meet the overall needs of the project but also have high accuracy and completeness.

[0004] According to one aspect of the present invention, a method for stratified exploration of pharmaceutical research data is provided, the method comprising:

[0005] The project requirement documents of a pharmaceutical research project are identified using a pre-built requirement identification model to determine the data requirements of the pharmaceutical research project and to identify multiple standard library tables that match the data requirements. The data requirements include data type, time range, and data range. The data type includes single data type and composite data type.

[0006] Using a pre-built statement generation model, a first-level structured query statement and a second-level structured query statement are generated according to the data requirements; wherein, the first-level structured query statement is used to query data of the single data type, and the second-level structured query statement is used to query data of the composite data type.

[0007] Based on the standard library tables, the first-level structured query statement is executed to obtain the first query result, and the first query result is verified by a pre-built result verification model; wherein, the requirement identification model, the statement generation model, and the result verification model are built based on a language model;

[0008] If the first query result passes the validation, the second-level structured query statement is executed on the first query result to obtain the second query result, and the second query result is validated by the result validation model.

[0009] If the second query result passes the validation, the second query result will be used as the first exploration result.

[0010] According to another aspect of the present invention, a medical research data stratification and exploration device is provided, the device comprising:

[0011] The project data requirements determination module is used to identify the project requirements document of a pharmaceutical research project through a pre-built requirements identification model, determine the data requirements of the pharmaceutical research project, and identify multiple standard library tables that match the data requirements; wherein, the data requirements include data type, time range, and data range; the data type includes single data type and composite data type;

[0012] The first query statement generation module is used to generate a first-level structured query statement and a second-level structured query statement according to the data requirements based on a pre-built statement generation model; wherein, the first-level structured query statement is used to query data of the single data type, and the second-level structured query statement is used to query data of the composite data type.

[0013] The first query result verification module is used to execute the first-level structured query statement based on the standard library table to obtain the first query result, and to verify the first query result through a pre-built result verification model; wherein, the requirement identification model, the statement generation model and the result verification model are built based on a language model;

[0014] The second query result verification module is used to execute the second-level structured query statement on the first query result if the first query result passes the verification, to obtain the second query result, and to verify the second query result through the result verification model.

[0015] The first exploration result determination module is used to take the second query result as the first exploration result if the second query result passes the verification.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the medical research data stratification exploration method according to any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the pharmaceutical research data hierarchical exploration method according to any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the pharmaceutical research data stratification exploration method as described in any of the embodiments of the present disclosure.

[0022] The technical solution of this invention identifies project requirement documents for pharmaceutical research projects using a pre-built requirement identification model, determines the data requirements of the pharmaceutical research project, and identifies multiple standard library tables that match the data requirements. The data requirements include data type, time range, and data range; the data type includes single data type and composite data type. A pre-built statement generation model generates a first-level structured query statement and a second-level structured query statement based on the data requirements. The first-level structured query statement is used to query data of the single data type, and the second-level structured query statement is used to query data of the composite data type. Based on the standard library tables, the first-level structured query statement is executed to obtain a first query result, which is then validated using a pre-built result validation model. The requirement identification model, the statement generation model, and the result validation model are built based on a language model. If the first query result passes validation, the second-level structured query statement is executed on the first query result to obtain a second query result, which is then validated using the result validation model. If the second query result passes validation, it is used as the first exploration result. The technical solution of this invention, through a demand identification model, a statement generation model, and a result verification model built based on a language model, automatically completes the entire process of data demand identification, query statement generation, query statement execution, and query result verification, which can significantly improve the efficiency of medical research data exploration. Simultaneously, through a hierarchical query and verification mechanism, it can ensure that the obtained initial exploration results not only meet the overall project requirements but also possess high accuracy and completeness.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a method for hierarchical exploration of pharmaceutical research data provided in Embodiment 1 of the present invention;

[0026] Figure 2 This is a flowchart of a method for hierarchical exploration of pharmaceutical research data provided in Embodiment 2 of the present invention;

[0027] Figure 3 This is a flowchart illustrating the hierarchical execution and validation of a structured query statement according to Embodiment 2 of the present invention.

[0028] Figure 4 This is a schematic diagram of the structure of a pharmaceutical research data stratification and exploration device according to Embodiment 3 of the present invention;

[0029] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the pharmaceutical research data hierarchical exploration method of this invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Example 1

[0033] Figure 1 This is a flowchart of a method for hierarchical exploration of pharmaceutical research data provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where hierarchical exploration of data required for pharmaceutical research is required. This method can be executed by a pharmaceutical research data hierarchical exploration device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0034] S110. Identify the project requirement documents of the pharmaceutical research project through a pre-built requirement identification model, determine the data requirements of the pharmaceutical research project, and identify multiple standard library tables that match the data requirements; wherein, the data requirements include data type, time range, and data range; the data type includes single data type and composite data type.

[0035] The requirement identification model, built upon a language model, is used to identify data requirements in project requirement documents. Project requirement documents are structured documents describing the goals, scope, functions, and performance requirements of a pharmaceutical research project. Data requirements are the specifications for the type, format, scope, and accuracy of data needed to achieve the research objectives in a pharmaceutical research project. Standard library tables are predefined database tables with standardized formats and data formats, used to store and manage specific types of data, providing a foundation for data retrieval.

[0036] The data requirements include data type, time range, and data scope. Data type describes the type of data required, including single data types and composite data types. Composite data types are composed of at least two associated single data types. For example, a single data type could be "compound," "clinical trial," etc.; a composite data type could be "compound-clinical trial-adverse reaction," etc.; a time range could be "January 1, 2020 to December 31, 2023," etc.; and a data scope could be "adverse reaction grade greater than or equal to level three," etc.

[0037] In this embodiment of the invention, a pre-built requirement identification model can be used to identify project requirement documents for pharmaceutical research projects. This allows for the rapid and accurate extraction of key data requirements from complex project requirement documents, avoiding omissions and misunderstandings that can occur with manual identification, and improving the efficiency and accuracy of requirement identification. After determining the data requirements of the pharmaceutical research project, it is also necessary to identify multiple standard library tables that match these data requirements, providing a foundation for subsequent data queries.

[0038] Optionally, the step of identifying the project requirement document of the pharmaceutical research project through a pre-built requirement identification model to determine the data requirements of the pharmaceutical research project and to determine multiple standard library tables that match the data requirements includes: inputting the project requirement document into the requirement identification model; performing word segmentation and entity recognition on the project requirement document through the requirement identification model to determine the data requirements of the pharmaceutical research project; and matching the field information of the data requirements with the field information in the pre-built standard library tables to obtain multiple standard library tables that match the data requirements.

[0039] In this embodiment of the invention, when identifying the project requirement document of a pharmaceutical research project using a pre-built requirement identification model to determine the data requirements of the pharmaceutical research project and to identify multiple standard library tables that match the data requirements, the project requirement document can first be input into the requirement identification model. The model then performs word segmentation and entity recognition on the project requirement document to determine the data type, time range, and data range required by the pharmaceutical research project, which serve as the data requirements for the project, and generates a data requirement table. Subsequently, the field information of the data requirements in the data requirement table can be matched with the field information in a pre-defined standard library table to obtain the mapping relationship between the data requirement fields and the standard library table fields. This allows for the identification of multiple standard library tables that match the data requirements, avoiding the bias and time-consuming nature of manual matching.

[0040] S120. Using a pre-built statement generation model, generate a first-level structured query statement and a second-level structured query statement according to data requirements; wherein, the first-level structured query statement is used to query data of a single data type, and the second-level structured query statement is used to query data of a composite data type.

[0041] The statement generation model is built upon a language model and is used to automatically generate structured query statements based on given data requirements. The first-level structured query statement, also known as the basic filtering layer structured query statement, is used to query a single standard library table corresponding to a single data type. The second-level structured query statement, also known as the association and integration layer structured query statement, is used to query and integrate data of at least two single data types contained within a composite data type.

[0042] In this embodiment of the invention, a first-level structured query statement and a second-level structured query statement can be generated according to data requirements through a pre-built statement generation model. This eliminates the need for manual writing of complex structured query statements, reduces the requirements for technical personnel's ability to write structured query statements, and improves the efficiency of structured query statement generation.

[0043] Optionally, generating a first-level structured query statement and a second-level structured query statement based on the data requirements using a pre-built statement generation model includes: for the single data type, generating a first-level structured query statement based on the field information, time range, and data range of the single data type using the statement generation model; and for the composite data type, generating a second-level structured query statement based on the field information of at least two single data types contained in the composite data type using the statement generation model.

[0044] In this embodiment of the invention, when generating a first-level structured query statement and a second-level structured query statement based on data requirements using a pre-built statement generation model, for a single data type, the statement generation model can generate a first-level structured query statement based on the field information, time range, and data range of the single data type to achieve preliminary filtering of data in the standard library table. For example, the first-level structured query statement could be: SELECT * FROM trial_adverse_reaction WHERE ar_grade 3 AND trial_date BETWEEN '2020-01-01' AND '2023-12-31'. For composite data types, a statement generation model can be used to generate a second-level structured query statement with correlation based on the field information of at least two single data types contained in the composite data type, so as to achieve multi-dimensional data integration. For example, the second-level structured query statement can be: SELECT c.compound_name, t.trial_id, a.ar_grade FROM compound c JOIN clinical_trial t ON c.compound_id = t.compound_id JOIN trial_adverse_reaction a ON t.trial_id =a.trial_id.

[0045] S130. Based on the standard library tables, execute the first-level structured query statement to obtain the first query result, and verify the first query result through a pre-built result verification model; wherein, the requirement identification model, the statement generation model and the result verification model are built based on the language model.

[0046] The result verification model is built on a language model and is used to comprehensively and accurately verify the query results to ensure that the obtained data meets the project requirements.

[0047] In this embodiment of the invention, a first-level structured query statement can be executed based on multiple standard library tables that match the data requirements to obtain a first query result from the multiple standard library tables. Then, the first query result is input into a pre-built result verification model, and the first query result is verified according to a preset first verification rule.

[0048] S140. If the first query result passes the validation, execute the second-level structured query statement on the first query result to obtain the second query result, and validate the second query result through the result validation model.

[0049] In this embodiment of the invention, if the first query result passes the validation, it indicates that the data in the first query result meets the requirements of the first validation rule. At this time, a second-level structured query statement is executed on the first query result to obtain the second query result. Similarly, the second query result is input into the result validation model, and the second query result is validated according to the preset second validation rule.

[0050] S150. If the second query result passes the validation, the second query result shall be used as the first exploration result.

[0051] In this embodiment of the invention, if the second query result passes the verification, it indicates that the data in the second query result meets the requirements of the second verification rule. At this time, the second query result can be used as the first exploration result, and the first exploration result can be presented to the technical personnel. By performing layered queries and verifications, and gradually refining and verifying the data, it can be ensured that the final obtained first exploration result not only meets the overall requirements of the project but also has high accuracy and completeness.

[0052] The technical solution of this invention identifies the project requirement document of a pharmaceutical research project through a pre-built requirement identification model, determines the data requirements of the pharmaceutical research project, and identifies multiple standard library tables that match the data requirements. The data requirements include data type, time range, and data range; the data type includes single data type and composite data type. A pre-built statement generation model generates a first-level structured query statement and a second-level structured query statement based on the data requirements. The first-level structured query statement is used to query data of a single data type, and the second-level structured query statement is used to query data of composite data types. Based on the standard library tables, the first-level structured query statement is executed to obtain a first query result, which is then validated using a pre-built result validation model. The requirement identification model, statement generation model, and result validation model are built based on a language model. If the first query result passes validation, the second-level structured query statement is executed to obtain a second query result, which is then validated using the result validation model. If the second query result passes validation, it is used as the first exploration result. The technical solution of this invention, through a demand identification model, a statement generation model, and a result verification model built based on a language model, automatically completes the entire process of data demand identification, query statement generation, query statement execution, and query result verification, which can significantly improve the efficiency of medical research data exploration. Simultaneously, through a hierarchical query and verification mechanism, it can ensure that the obtained initial exploration results not only meet the overall project requirements but also possess high accuracy and completeness.

[0053] Example 2

[0054] Figure 2 This is a flowchart of a method for stratified exploration of pharmaceutical research data provided in Embodiment 2 of the present invention. This embodiment is an optimization based on the above embodiments; schemes not described in detail in the embodiments of the present invention are described in the above embodiments. Figure 2 As shown, the method includes:

[0055] S210. Identify the project requirement documents of the pharmaceutical research project through a pre-built requirement identification model, determine the data requirements of the pharmaceutical research project, and identify multiple standard library tables that match the data requirements.

[0056] S220. Using a pre-built statement generation model, generate first-level structured query statements and second-level structured query statements according to data requirements.

[0057] S230. Based on the standard library tables, execute the first-level structured query statement to obtain the first query result, and verify the first query result through a pre-built result verification model.

[0058] Optionally, the step of verifying the first query result through a pre-built result verification model includes: determining whether the data volume of the first query result is within a preset range using the result verification model; if so, determining that the first query result has passed verification; otherwise, generating and displaying a first verification prompt message, the first verification prompt message being used to indicate that the first query result corresponding to the first layer structured query statement has failed verification.

[0059] In this embodiment of the invention, the first query result is verified using a pre-built result verification model. Specifically, the result verification model determines whether the data volume of the first query result falls within a preset range. The preset range can be set by technicians according to actual conditions, and this embodiment of the invention does not limit this setting. If yes, the first query result is determined to have passed verification; otherwise, a first verification prompt is generated and displayed. The first verification prompt indicates that the verification of the first query result corresponding to the first-level structured query statement has failed. Optionally, the first verification prompt also includes a first anomaly cause analysis, which allows technicians to adjust the parameters of the first-level structured query statement based on the first anomaly cause analysis. For example, if the filtering result for a certain standard library table is empty, it may be because the time range of the first-level structured query statement does not match the actual time of the clinical trial. In this case, technicians can modify the time range in the first-level structured query statement.

[0060] Optionally, the step of validating the first query result using a pre-built result validation model further includes: updating the first-level structured query statement in response to a parameter adjustment operation for the first-level structured query statement, and returning to execute the first-level structured query statement.

[0061] In this embodiment of the invention, after the technician adjusts the parameters of the first-level structured query statement based on the first abnormality cause analysis, the first-level structured query statement can be updated in response to the parameter adjustment operation for the first-level structured query statement, and the execution of the first-level structured query statement can be returned.

[0062] S240. If the first query result passes the validation, execute the second-level structured query statement on the first query result to obtain the second query result, and validate the second query result through the result validation model.

[0063] Optionally, the step of verifying the second query result through the result verification model includes: determining whether there is a logical contradiction in the data of the second query result through the result verification model; if not, determining that the second query result has passed the verification; otherwise, generating and displaying a second verification prompt message, the second verification prompt message being used to indicate that the verification of the second query result corresponding to the second-level structured query statement has failed.

[0064] In this embodiment of the invention, the second query result is validated using a result validation model. Specifically, the model determines whether there are logical contradictions in the data within the second query result. If not, the second query result validation passes; otherwise, a second validation prompt is generated and displayed. This prompt indicates that the validation of the second query result corresponding to the second-level structured query statement has failed. Optionally, the second validation prompt also includes a second anomaly cause analysis, which allows technicians to adjust the parameters of the first-level and second-level structured query statements based on the second anomaly cause analysis.

[0065] Optionally, the step of validating the second query result through the result validation model further includes: in response to parameter adjustment operations for the first-level structured query statement and the second-level structured query statement, updating the first-level structured query statement and the second-level structured query statement, and returning to execute the first-level structured query statement.

[0066] In this embodiment of the invention, after the technician adjusts the parameters of the first-level structured query statement and the second-level structured query statement according to the second abnormality cause analysis, the first-level structured query statement and the second-level structured query statement can be updated in response to the parameter adjustment operation of the first-level structured query statement and the second-level structured query statement, and the execution of the first-level structured query statement can be returned.

[0067] S250. If the second query result passes the validation, the second query result shall be used as the first exploration result.

[0068] S260. Generate a third-level structured query statement based on preset rules using the statement generation model; wherein, the third-level structured query statement is used for data filtering based on preset rules.

[0069] The third-level structured query statement, also known as the precise filtering layer structured query statement, is used to further filter the data from the second probe results that have passed the verification.

[0070] In this embodiment of the invention, a statement generation model can be used to generate a third-level structured query statement according to preset rules. This allows for data filtering based on the validated second-level query results, ensuring data accuracy. The preset rules can be set by technical personnel according to actual conditions, such as "excluding duplicate case data" and "removing missing data." The embodiments of the present invention do not limit this to "10% of records", etc. For example, the third-level structured query statement can be: "SELECT * FROM joined_data WHERE duplicate_flag = 0 AND missing_rate 10%.

[0071] S270. Execute the third-level structured query statement on the second query result to obtain the third query result, and verify the third query result through the result verification model.

[0072] Optionally, the step of validating the third query result through the result validation model includes: determining whether the third query result meets all data requirements through the result validation model; if so, determining that the third query result has passed the validation; otherwise, generating and displaying a third validation prompt message, which is used to indicate that the validation of the third query result corresponding to the third-level structured query statement has failed.

[0073] In this embodiment of the invention, the third query result is validated using a result validation model. Specifically, the model determines whether the third query result meets all data requirements. If so, the third query result validation is deemed successful; otherwise, a third validation prompt is generated and displayed. This prompt indicates that the validation of the third query result corresponding to the third-level structured query statement failed. Optionally, the third validation prompt also includes a third anomaly cause analysis, which allows technicians to adjust the parameters of the first-level, second-level, and third-level structured query statements based on the third anomaly cause analysis.

[0074] Optionally, the step of validating the third query result through the result validation model further includes: in response to parameter adjustment operations for the first-level structured query statement, the second-level structured query statement, and the third-level structured query statement, updating the first-level structured query statement, the second-level structured query statement, and the third-level structured query statement, and returning to execute the first-level structured query statement.

[0075] In this embodiment of the invention, after the technician adjusts the parameters of the first-level structured query statement, the second-level structured query statement, and the third-level structured query statement based on the third abnormality cause analysis, the first-level structured query statement, the second-level structured query statement, and the third-level structured query statement can be updated in response to the parameter adjustment operation of the first-level structured query statement, the second-level structured query statement, and the third-level structured query statement, and the execution of the first-level structured query statement can be returned.

[0076] S280. If the third query result passes the validation, the third query result is used as the second exploration result and displayed.

[0077] In this embodiment of the invention, if the third query result passes the validation, the third query result can be used as the second probe result and displayed. For example, Figure 3 This diagram illustrates a hierarchical execution and validation process for structured query statements.

[0078] The technical solution of this invention identifies project requirement documents for pharmaceutical research projects using a pre-built requirement identification model, determines the data requirements of the pharmaceutical research projects, and identifies multiple standard library tables that match the data requirements. A pre-built statement generation model generates a first-level structured query statement and a second-level structured query statement based on the data requirements. Based on the standard library tables, the first-level structured query statement is executed to obtain a first query result, which is then validated using a pre-built result validation model. If the first query result passes validation, the second-level structured query statement is executed to obtain a second query result, which is also validated using the result validation model. If the second query result passes validation, it is used as the first exploration result. A third-level structured query statement is generated using the statement generation model according to preset rules. This third-level structured query statement is used for data filtering based on the preset rules. The third-level structured query statement is executed on the second query result to obtain a third query result, which is then validated using the result validation model. If the third query result passes validation, it is used as the second exploration result and displayed. The technical solution of this invention, through a demand identification model, a statement generation model, and a result verification model built based on a language model, automatically completes the entire process of data demand identification, query statement generation, query statement execution, and query result verification, which can significantly improve the efficiency of medical research data exploration. Simultaneously, through a hierarchical query and verification mechanism, it can ensure that the obtained initial exploration results not only meet the overall project requirements but also possess high accuracy and completeness.

[0079] Example 3

[0080] Figure 4 This is a schematic diagram of a pharmaceutical research data stratification and exploration device provided in Embodiment 3 of the present invention. Figure 4 As shown, the device includes:

[0081] The project data requirements determination module 310 is used to identify the project requirements document of the pharmaceutical research project through a pre-built requirements identification model, determine the data requirements of the pharmaceutical research project, and determine multiple standard library tables that match the data requirements; wherein, the data requirements include data type, time range, and data range; the data type includes single data type and composite data type;

[0082] The first query statement generation module 320 is used to generate a first-level structured query statement and a second-level structured query statement according to the data requirements based on a pre-built statement generation model; wherein, the first-level structured query statement is used to query data of the single data type, and the second-level structured query statement is used to query data of the composite data type.

[0083] The first query result verification module 330 is used to execute the first-level structured query statement based on the standard library table to obtain the first query result, and to verify the first query result through a pre-built result verification model; wherein, the requirement identification model, the statement generation model and the result verification model are built based on a language model.

[0084] The second query result verification module 340 is used to execute the second-level structured query statement on the first query result if the first query result passes the verification, to obtain the second query result, and to verify the second query result through the result verification model.

[0085] The first exploration result determination module 350 is used to take the second query result as the first exploration result if the second query result passes the verification.

[0086] Optional, the project data requirements determination module 310 includes:

[0087] A data requirement determination unit is used to input the project requirement document into the requirement identification model, and use the requirement identification model to perform word segmentation and entity recognition on the project requirement document to determine the data requirements of the medical research project.

[0088] The standard library table matching unit is used to match the field information of the data requirement with the field information of a preset standard library table to obtain multiple standard library tables that match the data requirement.

[0089] Optionally, the first query statement generation module 320 includes:

[0090] The first query statement generation unit is used to generate a first-level structured query statement for the single data type based on the field information, time range, and data range of the single data type through the statement generation model.

[0091] The second query statement generation unit is used to generate a second-level structured query statement for the composite data type based on the statement generation model and the field information of at least two single data types contained in the composite data type.

[0092] Optionally, the first query result verification module 330 is specifically used for:

[0093] The result verification model is used to determine whether the data volume of the first query result is within a preset range.

[0094] If yes, the first query result is confirmed to have passed the verification; otherwise, a first verification prompt message is generated and displayed. The first verification prompt message is used to indicate that the first query result corresponding to the first-level structured query statement has failed the verification.

[0095] Optionally, the first query result verification module 330 is also specifically used for:

[0096] In response to a parameter adjustment operation for the first-level structured query statement, update the first-level structured query statement and return to execute the first-level structured query statement.

[0097] Optionally, the second query result verification module 340 is specifically used for:

[0098] The result verification model is used to determine whether there are logical contradictions in the data of the second query result;

[0099] If not, the second query result is confirmed to have passed the verification; otherwise, a second verification message is generated and displayed. The second verification message is used to indicate that the verification of the second query result corresponding to the second-level structured query statement has failed.

[0100] Optionally, the second query result verification module 340 is also specifically used for:

[0101] In response to parameter adjustment operations for the first-level structured query statement and the second-level structured query statement, update the first-level structured query statement and the second-level structured query statement, and return to execute the first-level structured query statement.

[0102] Optionally, the device further includes:

[0103] The second query statement generation module is used to generate a third-level structured query statement based on the statement generation model and preset rules; wherein, the third-level structured query statement is used for data filtering based on the preset rules.

[0104] The third query result verification module is used to execute the third-level structured query statement on the second query result to obtain the third query result, and to verify the third query result through the result verification model;

[0105] The second exploration result determination module is used to, if the third query result passes the verification, take the third query result as the second exploration result and display the second exploration result.

[0106] Optionally, the third query result verification module is specifically used for:

[0107] The result verification model is used to determine whether the third query result meets all data requirements.

[0108] If yes, the third query result verification is confirmed to be successful; otherwise, a third verification prompt message is generated and displayed. The third verification prompt message is used to indicate that the third query result verification corresponding to the third-level structured query statement has failed.

[0109] Optionally, the third query result verification module is further specifically used for:

[0110] In response to parameter adjustment operations for the first-level structured query statement, the second-level structured query statement, and the third-level structured query statement, update the first-level structured query statement, the second-level structured query statement, and the third-level structured query statement, and return to execute the first-level structured query statement.

[0111] The pharmaceutical research data hierarchical exploration device provided in this embodiment of the invention can execute the pharmaceutical research data hierarchical exploration method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0112] Example 4

[0113] Figure 5A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0114] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0115] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0116] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the stratified probing method for medical research data.

[0117] In some embodiments, the pharmaceutical research data hierarchical probing method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the pharmaceutical research data hierarchical probing method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the pharmaceutical research data hierarchical probing method by any other suitable means (e.g., by means of firmware).

[0118] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0119] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0120] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0121] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0122] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0123] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0124] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0125] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0126] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for stratified exploration of pharmaceutical research data, characterized in that, The method comprises: identifying a project demand document of a medical research project through a pre-constructed demand identification model, determining data requirements of the medical research project, and determining a plurality of standard library tables matched with the data requirements; wherein the data requirements comprise data types, time ranges, and data ranges; the data types comprise single data types and composite data types; generating first-level structured query statements and second-level structured query statements according to the data requirements through a pre-constructed statement generation model; wherein the first-level structured query statements are used for querying data of the single data types, and the second-level structured query statements are used for querying data of the composite data types; based on the standard library tables, executing the first-level structured query statements to obtain first query results, and checking the first query results through a pre-constructed result checking model; wherein the demand identification model, the statement generation model, and the result checking model are constructed based on a language model; if the first query results pass the check, executing the second-level structured query statements on the first query results to obtain second query results, and checking the second query results through the result checking model; if the second query results pass the check, taking the second query results as first probe results.

2. The method of claim 1, wherein, The method comprises: inputting the project demand document into the demand identification model, performing word segmentation and entity recognition on the project demand document through the demand identification model, and determining the data requirements of the medical research project; according to field information of the data requirements, matching the field information with field information in a pre-set standard library table to obtain a plurality of standard library tables matched with the data requirements.

3. The method of claim 1, wherein, The method comprises: for the single data types, generating first-level structured query statements according to field information, time ranges, and data ranges of the single data types through the statement generation model; for the composite data types, generating second-level structured query statements according to field information of at least two single data types contained in the composite data types through the statement generation model.

4. The method of claim 1, wherein, The method comprises: judging, through the result checking model, whether a data amount of the first query results is located in a pre-set interval; if yes, determining that the first query results pass the check, otherwise, generating and displaying first checking prompt information, the first checking prompt information being used for prompting that the first query results corresponding to the first-level structured query statements fail to pass the check.

5. The method of claim 4, wherein, The method further comprises: In response to the parameter adjustment operation for the first layer structured query statement, the first layer structured query statement is updated, and the first layer structured query statement is executed.

6. The method of claim 1, wherein, The second query result is verified by the result verification model, including: The result verification model is used to determine whether the data in the second query result has logical contradictions. If not, it is determined that the second query result passes the verification, otherwise a second verification prompt information is generated and displayed, which is used to prompt that the second query result corresponding to the second layer structured query statement fails the verification.

7. The method of claim 6, wherein, Also includes: In response to the parameter adjustment operation for the first layer structured query statement and the second layer structured query statement, the first layer structured query statement and the second layer structured query statement are updated, and the first layer structured query statement is executed.

8. The method of claim 1, wherein, After the second query result is taken as the first probe result, it also includes: The third layer structured query statement is generated according to a preset rule by the statement generation model; wherein the third layer structured query statement is used for data filtering based on the preset rule; The third query result is obtained by executing the third layer structured query statement on the second query result, and the third query result is verified by the result verification model; If the third query result passes the verification, the third query result is taken as the second probe result, and the second probe result is displayed.

9. The method of claim 8, wherein, The third query result is verified by the result verification model, including: The result verification model is used to determine whether the third query result meets all data requirements; If yes, it is determined that the third query result passes the verification, otherwise a third verification prompt information is generated and displayed, which is used to prompt that the third query result corresponding to the third layer structured query statement fails the verification.

10. The method of claim 9, wherein, Also includes: In response to the parameter adjustment operation for the first layer structured query statement, the second layer structured query statement and the third layer structured query statement, the first layer structured query statement, the second layer structured query statement and the third layer structured query statement are updated, and the first layer structured query statement is executed.

Images