Scientific research activity management and application platform supporting multidisciplinary sharing

Abstract

The invention relates to a scientific research activity management and application platform supporting multidisciplinary sharing. Comprising a scientific research activity management module deployed at a cloud end, and is configured to enable a user to perform scientific research activity management by running the scientific research activity management module without additionally installing software; the scientific research activity management module comprises a scientific research unit design environment and scientific research unit code packages of different subjects, the scientific research unit code packages are designed and generated by a user based on a multidisciplinary shared scientific research unit grammar defined by the scientific research unit design environment, and each scientific research unit code package at least comprises a scientific research protocol of the corresponding subject; the scientific research protocol is used for defining basic information, multi-modal information and data fields of scientific research experiments of the subject. According to the method, the diversification and customization requirements of different disciplinary scientific research data recording and scientific research activity management can be met, so that efficient accumulation of multidisciplinary expert knowledge is realized, and rich resources are provided for AI application based on interdisciplinary expert knowledge.

Description

Technical Field

[0001] The present application relates to the technical field of scientific research project management, and in particular to a scientific research activity management and application platform that supports multi-disciplinary sharing. Background Art

[0002] In recent years, artificial intelligence (AI) has shown increasing potential in supporting and enhancing scientific research innovation in the field of natural sciences. From protein structure prediction to drug discovery, from the identification of new chemical reactions to the synthesis of new materials, artificial intelligence has shown great potential to assist or even replace human scientists. Strategic use of artificial intelligence technology has the potential to accelerate the progress of natural science research and enhance the scientific and technological competitiveness of universities and enterprises.

[0003] Data is the foundation of science and the cornerstone of artificial intelligence. To widely realize AI-driven progress in natural science research, the first step is to promote the electronicization of multidisciplinary scientific research data. This is because, first of all, existing AI models have strict requirements for high-quality and large amounts of training data. Therefore, current AI-assisted scientific research is usually focused on specific field problems with relatively rich public data, such as protein structure, compound structure, medical images, and scientific literature. In contrast, in those natural science fields that are not covered by public data sets, AI-enabled research is still limited due to the difficulty in obtaining relevant scientific research data (including experimental plans, experimental data, etc.). Secondly, the significance of interdisciplinary research in promoting scientific discovery is becoming more and more obvious. On the one hand, the number of interdisciplinary studies is growing; on the other hand, interdisciplinary research is gradually becoming the source of major scientific breakthroughs. Therefore, creating a multidisciplinary scientific research data electronic platform is an important way to promote the electronicization of scientific research data and meet the future development of science. In order to promote the electronic recording of laboratory scientific research data, many feature-rich Electronic Lab Notebooks (ELNs) have been developed. However, these ELNs are usually designed for a single subject area and lack the versatility required to realize the electronicization of multidisciplinary scientific research data. For example, due to financial and labor costs, as well as significant professional barriers between different disciplinary research, existing platforms usually adopt a centralized design concept, providing users with predefined functions and data recording templates, but cannot support various customized research protocols, and therefore cannot record different types of scientific research data required by different protocols.

[0004] Therefore, the existing technology has not yet found a scientific research management and application platform that can well meet the diverse and fine-grained customization needs in scientific research data records of different disciplines. Therefore, it is not yet possible to efficiently accumulate high-precision and high-quality expert knowledge of multidisciplinary front-line scientific researchers through such a platform, thereby providing key resources for interdisciplinary AI research model training. Summary of the invention

[0005] This application is provided to solve the above-mentioned defects existing in the prior art. A scientific research activity management and application platform that supports multi-disciplinary sharing is needed, which enables users to run the scientific research activity management module deployed in the cloud without installing additional software, and adopt a unified scientific research unit grammar to design and generate scientific research protocols of different disciplines and manage scientific research activities. Through the platform of this application, the high-precision and high-quality expert knowledge of multi-disciplinary front-line scientific researchers can be efficiently accumulated, thereby providing key and rich resources for AI applications based on interdisciplinary expert knowledge.

[0006] According to the first scheme of the present application, there is provided a scientific research activity management and application platform supporting multi-disciplinary sharing, the scientific research activity management and application platform supporting multi-disciplinary sharing includes a scientific research activity management module deployed in the cloud, and is configured to enable users to manage scientific research activities by running the scientific research activity management module without the need to install additional software; the scientific research activity management module includes a scientific research unit design environment, and scientific research unit code packages of different disciplines designed and generated by users based on the scientific research unit syntax shared by multiple disciplines defined by the scientific research unit design environment, wherein each scientific research unit code package contains at least the scientific research protocol of the corresponding discipline, and the scientific research protocol is used to define the basic information, multimodal information and data fields of the scientific research experiment of the discipline.

[0007] The scientific research activity management and application platform that supports multi-disciplinary sharing provided by each embodiment of the present application provides users with a scientific research unit design environment deployed in the cloud, allowing users to design and generate scientific research unit code packages of different disciplines based on the scientific research unit syntax shared by multiple disciplines, breaking through the limitations of professional barriers between different disciplines. It only needs to design a scientific research protocol that describes the corresponding discipline to define the basic information, multimodal information and data fields of the scientific research experiment of the discipline, with low platform development and maintenance costs, and well meets the diversified and fine-grained customization needs in the scientific research data records of different disciplines. In addition, users can easily carry out scientific research activity management without installing additional software, providing the greatest convenience for researchers in various disciplines to use the platform, and it is easy to promote and use, so as to achieve the efficient accumulation of high-precision and high-quality expert knowledge of multi-disciplinary front-line researchers, thereby providing key and rich resources for AI applications based on interdisciplinary expert knowledge.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0009] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0011] FIG1( a ) shows a schematic diagram of the composition of a scientific research activity management and application platform supporting multi-disciplinary sharing according to an embodiment of the present application.

[0012] FIG1( b ) shows another schematic diagram of the composition of a scientific research activity management and application platform supporting multi-disciplinary sharing according to an embodiment of the present application.

[0013] FIG1( c ) shows another schematic diagram of the composition of a scientific research activity management and application platform supporting multi-disciplinary sharing according to an embodiment of the present application.

[0014] FIG1( d ) shows another schematic diagram of the composition of a scientific research activity management and application platform supporting multi-disciplinary sharing according to an embodiment of the present application.

[0015] FIG1( e ) shows another schematic diagram of the composition of a scientific research activity management and application platform supporting multi-disciplinary sharing according to an embodiment of the present application.

[0016] Figure 2 A schematic diagram of the composition structure of a scientific research unit code package according to an embodiment of the present application is shown.

[0017] FIG3( a ) shows a schematic diagram of a composition structure of a scientific research activity management module according to an embodiment of the present application.

[0018] FIG3( b ) shows another schematic diagram of the composition structure of the scientific research activity management module according to an embodiment of the present application.

[0019] Figure 4 A schematic diagram showing the steps of recording a scientific research unit in a scientific research unit recording environment according to an embodiment of the present application is shown.

[0020] FIG5( a ) shows a schematic diagram of an AI system tool chat interface according to an embodiment of the present application.

[0021] FIG5( b ) shows a schematic diagram of using an AI system tool to perform grammar checking of a customized scientific research unit according to an embodiment of the present application.

[0022] FIG5( c ) shows a schematic diagram of injecting relevant information of a scientific research unit as a situational context into a chat dialogue of an AI system tool according to an embodiment of the present application.

[0023] FIG5( d ) shows the answer given by GPT-4o to the user's question in the embodiment of the present application.

[0024] FIG5( e ) shows a schematic diagram of analyzing scientific research records using an AI system tool according to an embodiment of the present application.

[0025] FIG6( a ) shows a schematic diagram of a scientific research unit workflow diagram according to an embodiment of the present application.

[0026] FIG6( b ) shows a schematic diagram of a research path according to an embodiment of the present application.

[0027] FIG6( c ) is a schematic diagram showing scientific research data generated by executing a research path according to an embodiment of the present application.

[0028] Figure 7 A schematic diagram of the process of generating an automatically executable scientific research unit workflow using an AI system tool according to an embodiment of the present application is shown.

[0029] FIG8( a ) shows a schematic diagram of a form-style scientific research unit record interface according to an embodiment of the present application.

[0030] FIG8( b ) shows a schematic diagram of a scientific research unit recording interface in a WYSIWYG style according to an embodiment of the present application.

[0031] Fig. 9 A schematic diagram of a knowledge sharing section according to an embodiment of the present application is shown.

[0032] Fig.10 A schematic diagram showing scientific research conclusions automatically generated by an AI system tool according to an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solution and advantages of the embodiment of the present application clearer, the technical solution of the embodiment of the present application will be clearly and completely described in conjunction with the drawings of the embodiment of the present application. Obviously, the described embodiment is a part of the embodiment of the present application, not all of the embodiments. Based on the described embodiment of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] Unless otherwise defined, the technical terms or scientific terms used in this application shall have the common meanings understood by persons with ordinary skills in the field to which this application belongs. "Include" or "comprising" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, but do not exclude other elements or objects.

[0035] The words "first", "second" and similar words used in this application do not indicate any order, quantity or importance, but are only used to distinguish. Words such as "include" or "comprise" and similar words mean that the elements before the word include the elements listed after the word, and do not exclude the possibility of also covering other elements. The execution order of the various steps in the method described in this application in conjunction with the accompanying drawings is not intended to be limiting. As long as it does not affect the logical relationship between the various steps, several steps can be integrated into a single step, a single step can be decomposed into multiple steps, and the execution order of the various steps can be changed according to specific needs.

[0036] It should also be understood that the term "and / or" in this application is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this application generally indicates that the associated objects before and after are in an "or" relationship.

[0037] In order to keep the following description of the embodiments of the present application clear and concise, the present application omits detailed descriptions of known functions and known components.

[0038] FIG1( a ) shows a schematic diagram of the composition of a scientific research activity management and application platform supporting multi-disciplinary sharing according to an embodiment of the present application.

[0039] As shown in Figure 1 (a), according to the embodiment of the present application, the scientific research activity management and application platform 10 supporting multi-disciplinary sharing includes at least a scientific research activity management module 11, and the scientific research activity management module 11 further includes a scientific research unit design environment 111, and scientific research unit code packages 121 and 122 corresponding to different disciplines, and so on.

[0040] According to an embodiment of the present application, in the scientific research unit design environment 111, a new scientific research unit syntax that can be shared by multiple disciplines is newly defined. Therefore, one or more users 12 in different disciplines can design the scientific research protocol of their corresponding discipline based on the scientific research unit syntax defined by the scientific research unit design environment 111 (hereinafter also referred to as the scientific research unit protocol, the two are not distinguished), including defining the basic information, multimodal information and data fields of the scientific research experiment of the discipline, and the files defining this information are packaged in a folder, that is, the scientific research unit code package of the discipline is generated, that is, a new scientific research unit (hereinafter also referred to as Research Unit, or abbreviated as RU, the three are not distinguished). For example, the scientific research unit code package 121 in Figure 1 (a) corresponds to the scientific research unit related to protein purification in the life science discipline, and the scientific research unit code package 122 corresponds to the scientific research unit related to carbon nanotube self-dispersion research in the materials science discipline. These scientific research unit code packages can be parsed and run by the scientific research activity management and application platform 10. Therefore, researchers from different disciplines can carry out scientific research experiments in the discipline by establishing scientific research units under the premise of following the corresponding discipline scientific research protocol.

[0041] As an example only, in a scientific research protocol, the basic information of a scientific research experiment may include, for example, the user using text to describe the detailed content of the research plan related to the research activity (such as an experiment), including introduction, methods, steps, etc.; multimodal information may include, for example, multimodal files inserted by the user, including images, videos, audios, documents (such as PDF), etc., to provide a more intuitive and detailed description of the research activity; data fields may include, for example, various data fields required in a user-defined research plan, and may include research variables, steps, and checkpoints related to the research activity. For example, if the user needs to add a data field for the solvent volume in the research plan to record the amount of solvent used in the experiment, a data field with an ID of solvent_volume may be defined so that the solvent volume can be recorded in the data field.

[0042] The scientific research unit syntax (hereinafter also referred to as scientific research unit Markdown, the two are not distinguished) in the embodiment of the present application is a newly defined lightweight markup language that can be shared by multiple disciplines. Users can customize the basic information, multimodal information and data fields in the scientific research protocol based on the scientific research unit syntax, such as by creating formatted text through a simple text editor. It is similar to the standard Markdown language, has a clear syntax, is compatible with the syntax of the standard Markdown specification (CommonMark), and at the same time, it has carried out syntax extensions applicable to the scientific research protocol, model, assigner and other content requirements of the scientific research unit in this application. Compared with the standard Markdown syntax, its uniqueness lies in that the scientific research unit Markdown provides users with template syntax. Using the template syntax, data fields (hereinafter also referred to as scientific research unit data fields, the two are not distinguished) can be inserted and customized. Users can generate scientific research unit variables with unique ID numbers, or scientific research unit steps, or scientific research unit checkpoints based on the template syntax of the data field. In the scientific research unit Markdown, {{...}} is used to represent the template. The commonly used templates for defining data fields such as scientific research unit variables, scientific research unit steps and scientific research unit checkpoints are shown in Table 1.

[0043] Table 1 Example of a template for defining data fields in a research protocol

[0044] According to the embodiment of the present application, the scientific research activity management and application platform 10 and the scientific research activity management module 11 can be deployed locally or in the cloud. From the perspective of facilitating multi-terminal sharing, it is usually preferred to be deployed in the cloud. Therefore, users do not need to install additional software locally, and can manage scientific research activities only by running the scientific research activity management module 11 in the cloud.

[0045] Figure 2 A schematic diagram of the composition structure of a scientific research unit code package according to an embodiment of the present application is shown.

[0046] Figure 2 Taking the scientific research unit code package 121 as an example, it can be seen that when the user designs the scientific research unit code package of the corresponding discipline based on the scientific research unit design environment, in addition to designing the scientific research protocol, the user can also design and generate a model (Model) of the scientific research unit. The model is used to define the type constraints and / or numerical verification relationships of the data fields, as well as the combined verification relationships of types and / or numerical values ​​between each data field.

[0047] More specifically, the type constraint includes constraining the corresponding data field to use predefined multimodal information during data entry, wherein the predefined multimodal information includes one or more of text, image, video, audio, and file. In some embodiments, the user can further define the data type (e.g., various numerical types, time types, etc.) of the data field previously defined in the scientific research protocol. For example, the solvent_volume data field is defined as a floating point number. Then, when the user enters non-floating point data (e.g., a string of letters) in the field, the system will indicate a type error.

[0048] The numerical validation relationship includes constraining the corresponding data field to follow a specified pattern and / or not exceed a preset value range when entering data. The user can further define validation rules for the data fields defined in the research protocol. For example, further validation rules are added for the solvent_volume data field and its type constraint (floating point number) to ensure that the floating point number filled in the data field must be greater than zero. In this case, if the user enters a negative floating point number, the system will display a numerical validation error.

[0049] The combined verification relationship includes constraining the type and / or value of each data field to satisfy a predetermined constraint relationship. As an example only, the so-called following the specified pattern can be, for example, using RegExp regular expression RE (RegularExpression) to constrain the composition rules and patterns of the character strings in the field, for example, constraining that the value recorded in a field related to an email address must contain and only have 1 "@" symbol, and so on. In other embodiments, other patterns and value range constraints can also be set, which are not listed here one by one. In this way, rapid identification of abnormal scientific research data can be achieved. If any verification relationship fails, the reason for the verification failure will be displayed, and the user can correct the value of the invalid data field one by one according to the error prompt until it is modified to a valid record. Through the above verification process, the platform can ensure that the data entered by the user meets the requirements.

[0050] like Figure 2As shown, in other embodiments, if the user defines multiple data fields with dependency and assignment relationships in the scientific research protocol, then these relationships can be further customized using an assigner. Specifically, when the user designs the scientific research unit code package of the corresponding discipline based on the scientific research unit design environment, it can also include an assigner for the data field, and the assigner is used to assign values ​​to the data field based on the data field dependency graph and the assignment rules. In some embodiments, the data field dependency graph is a single-level or multi-level directed acyclic graph, and the assignment relationship between the defined data fields is single dependency or multiple dependency, and each data field is assigned by at most one assigner. An assigner can take one or more upstream data fields as dependencies, and at the same time, a data field can actually be a dependency of one or more data fields, but for a specific data field, the method of determining its field value should be unique. Just as an example, if two data fields solvent_volume and solvent_volume_2 are defined in the scientific research protocol, and the user uses the assigner to define that solvent_volume_2 is always twice the value of solvent_volume, in this case, whenever a new value is entered for solvent_volume, the system will automatically set solvent_volume_2 to twice the solvent volume value. For example, if the value of solvent_volume is 5, the system will automatically assign a value of 10 to solvent_volume_2. This can greatly improve the efficiency and accuracy of scientific research data recording.

[0051] By defining the model of the scientific research unit, the user's input can be dynamically verified to ensure the accuracy of data entry; through the definition of the assigner, the multi-level and multi-dependent field dependency relationships can be automatically calculated according to the value of a certain input field, thereby ensuring that even if there are complex dependencies between multiple data fields, they can be efficiently entered and run correctly. This can significantly promote the electronic management of the laboratory's scientific research data, including data and orders for outsourced experiments, and realize efficient retrieval of scientific research plans, scientific research data and other related content.

[0052] FIG3 (a) shows a schematic diagram of a composition structure of a scientific research activity management module according to an embodiment of the present application. As shown in FIG3 (a), in some embodiments, the scientific research activity management module 11 includes not only a scientific research unit design environment 111, but also a scientific research unit recording environment 112, which provides a user with an environment for recording and storing data based on a designed scientific research unit.

[0053] Figure 4The following is a schematic diagram showing the steps of recording a scientific research unit in the scientific research unit recording environment according to an embodiment of the present application. As mentioned above, when the scientific research unit code package designed by the user includes the scientific research protocol of the corresponding discipline, the model of the scientific research unit, and the assigner of the data field, the scientific research unit recording environment 112 can perform the following steps when recording the relevant content of the scientific research unit: Figure 4 The steps shown.

[0054] First, in step 401, the model of the scientific research unit may be converted into a data field JSON Schema.

[0055] Then, in step 402, based on the data field JSON Schema, a structured storage scheme is automatically generated for the scientific research unit, so that when the user submits the scientific research record based on the scientific research unit for storage, and each data field conforms to the constraints and verification relationship of the model, the scientific research record is stored as a JSON that conforms to the structured storage scheme corresponding to the scientific research unit. In an embodiment of the present application, whether the user-defined data field is a simple text or a more complex multimodal data, the scientific research unit recording environment 112 can automatically generate a corresponding data structure for it, and ensure the consistency and integrity of the data during the entry and storage process. Since the automatically generated data structure is based on standardized protocols and definitions, scientific research data can be easily shared globally. This automation of structured storage not only simplifies the work of scientific researchers, but also improves the reproducibility of scientific research data and the ability to collaborate across laboratories. In addition, through the automatically generated data structure, scientific researchers can focus on experiments and data records without worrying about underlying data management issues. This feature greatly reduces the data management burden of scientific researchers and improves the efficiency of scientific research work.

[0056] In other embodiments, the scientific research unit recording environment 112 can be further configured as follows: based on the scientific research protocol and the data field JSON Schema, a corresponding scientific research unit recording interface is automatically generated for the scientific research unit, and the scientific research unit recording interface has a stylized style obtained based on the custom scientific research unit syntax parsing and interactive controls corresponding to the data type of each data field obtained based on the data field JSON Schema parsing. For example, font settings associated with the title level can be provided according to the basic style of the scientific research unit Markdown, and the recording interface of multimodal information with different data types can be set to a form style, an embedded WYSIWYG style, etc. as needed. In this way, it can adapt to the diverse needs of scientific research data and effectively improve the convenience and accuracy of operations of scientific researchers in the recording process.

[0057] FIG8 (a) and FIG8 (b) are schematic diagrams showing the form style and WYSIWYG style scientific research unit record interface according to an embodiment of the present application. Figure 4 In step 401, the model of the scientific research unit has been converted into a data field JSON Schema. For example, the user has defined different data types (such as string, integer, floating point number, Boolean value, date, enumeration value, etc.) for different fields in the model. In this case, in the scientific research unit record interface 800 shown in Figures 8 (a) and 8 (b), appropriate interactive controls can be generated for each data field. More specifically, the scientific research unit record environment 112 can parse the data type specially annotated for each field in the data field JSON Schema, and thus generate corresponding interactive controls. Just as an example, for example, in Figures 8 (a) and 8 (b), interactive controls 801 and interactive controls 801' are interactive controls generated based on data fields annotated as positive integer data types. Therefore, it can be seen that the interactive controls 801 and interactive controls 801' automatically generated in the scientific research unit record interface 800 have buttons for increasing and decreasing values; while interactive controls 802 and interactive controls 802' are interactive controls generated based on data fields with data types of time, so they use clock dials as prompt legends. The scientific research unit record interface 800 can help scientists focus their time and energy on the definition and development of substantive content such as scientific research protocols, models, data fields, etc. in scientific research plans, without having to worry about issues such as scientific research record interfaces, scientific research data storage structures and methods. This enables scientists to efficiently design high-quality scientific research plans that meet actual scientific research needs in a user-friendly manner in their daily scientific research activities, and use them for scientific research data recording.

[0058] FIG3 (b) shows another schematic diagram of the composition structure of the scientific research activity management module according to an embodiment of the present application. As shown in FIG3 (b), the scientific research activity management module 11 may include a scientific research unit design environment 111, a scientific research unit recording environment 112, and a scientific research report generation and reader 113. The scientific research report generation and reader 113 is at least configured to respond to the user's first operation on the scientific research unit, based on the historical scientific research records of the scientific research unit, to run locally and automatically generate a formatted scientific research report of the scientific research unit, and enable the user to read the generated formatted scientific research report locally. In addition, the scientific research report generation and reader 113 can support formatted output of report content, such as PDF format, etc., which are not listed here one by one. Users can use these reports directly for literature publication, internal discussion or printing, which greatly simplifies the generation process of scientific research records and reports. It is worth noting that when rendering scientific research reports, only the scientific research agreement, data field JSON Schema, and JSON of scientific research records of scientific research units related to the scientific research unit code package need to be used. In addition, the data field JSON Schema will be automatically generated and saved when the platform loads the user-defined scientific research unit code package for the first time. Subsequent users do not need to run the Python file of the scientific research unit model or execute Python code again when generating scientific research reports. They only need to call the generated data field JSON Schema file, which eliminates the security risks when users read and generate scientific research reports locally. For this reason, scientific research units can be used as a standard format for research data exchange in the future.

[0059] FIG1 (b) shows another schematic diagram of the composition of the scientific research activity management and application platform supporting multi-disciplinary sharing according to the embodiment of the present application. As shown in FIG1 (b), the scientific research activity management and application platform 10 includes a scientific research activity management module 11 and scientific research unit code packages of different disciplines, and can also include a scientific research unit sharing and application tool 13. The scientific research unit sharing and application tool 13 can be configured, for example, to: generate a unique ID number for each scientific research record of the scientific research unit, and associate the unique ID number with the record time, so that each scientific research record is non-tamperable; when the user wants to modify the scientific research record based on the submitted scientific research record, a copy of the scientific research record is generated for the user, and a new unique ID number is generated for the copy of the scientific research record, and is associated with the modification time, so that the user can modify it on the copy with the new unique ID number. Due to the above method of making the data non-tamperable, the scientific research activity management and application platform according to the embodiment of the present application can actually be used as an evidence platform for the history / record of scientific research activities, for example, when scientific research evidence is required for certain matters. For example, in the field of scientific research, there are often disputes over who first discovered a phenomenon. If the relevant researchers have recorded the phenomenon in the platform of this application and the relevant scientific research data has been left on the platform, then these non-tamperable scientific research records can be used as evidence of their scientific discovery.

[0060] In other embodiments, the scientific research unit sharing and application tool 13 is further configured to: in response to a second operation of a scientific research unit by a user with corresponding authority, mark a level for the scientific research unit, wherein the level is divided into at least a laboratory level and a project level from high to low, and provide a user access control mechanism corresponding to the disclosure level for each level and / or each scientific research unit; and set a level mark corresponding to the scientific research unit level division for each user.

[0061] In some embodiments, as an example only, providing a corresponding user access control mechanism for each level and / or each scientific research unit may specifically include the following contents: setting access rights open to all users for each laboratory level; setting access rights for users marked at a specific level for each project level; when a specific user has access rights for a specific project, the specific user has access rights to all scientific research units in the specific project.

[0062] As an example only, setting access rights for users with specific level tags for each project layer may specifically include: setting all users to have access rights for the project layer; or, only users with the same laboratory layer tag have access rights for the project layer; or, only users with the same project layer tag have access rights for the project layer.

[0063] As an example only, providing a corresponding user access control mechanism for each level and / or each scientific research unit may also include: in response to a third operation of a user with corresponding authority, setting a group tag for users with the same laboratory layer tag, and setting access rights to a specific project layer accordingly for users with each group tag.

[0064] Other user access control mechanisms can be set up according to the specific characteristics and requirements of disciplines and institutions. This application does not list them one by one here. The reference principle is to maximize sharing while ensuring the security of experimental plans, experimental data and privacy management requirements.

[0065] FIG1( c ) shows another schematic diagram of the composition of a scientific research activity management and application platform supporting multi-disciplinary sharing according to an embodiment of the present application.

[0066] As shown in FIG. 1( c ), based on the component structure of the scientific research activity management and application platform 10 shown in FIG. 1( a ), it may further include a knowledge sharing section corresponding to each scientific research unit. Fig. 9 A schematic diagram of a knowledge sharing section according to an embodiment of the present application is shown. Fig. 9 The knowledge sharing section 900 for the protein purification research unit shown can support real-time discussion among multiple people, provide a rich text editor, support comment and reply functions, and can provide a voting mechanism, etc., which will not be described in detail here. Different research units usually correspond to different subject areas. Therefore, setting up knowledge sharing sections separately can make it more convenient for the maintainer of the research unit or other interested users to provide or obtain professional knowledge related to the research activities of the research unit and more focused on the field in the form of questions and answers in the knowledge sharing section.

[0067] In an embodiment of the present application, the contents of the scientific research protocol and the knowledge sharing section can all come from the expert experience and knowledge of community users, and the contents of the knowledge sharing section can be updated in real time and dynamically on the scientific research activity management and application platform without modifying the scientific research unit code package, which gives the knowledge sharing section a more flexible update feature.

[0068] In other embodiments, the scientific research activity management and application platform 10 can be further configured to use the content in the knowledge sharing section to update the scientific research protocol of the corresponding scientific research unit. As an example only, the update of the above scientific research protocol can be triggered regularly or manually by the user, so that the latest domain knowledge in the knowledge sharing section can be incorporated into the scientific research unit code package, so that the newly generated scientific research unit using the same scientific research unit code package has more advanced characteristics in the field.

[0069] In the case where the scientific research activity management and application platform includes a knowledge sharing section corresponding to each scientific research unit, the scientific research unit sharing and application tool 13 shown in FIG1( b) can be further configured to support cross-laboratory or cross-project sharing and application of relevant information and data of the scientific research unit, wherein the relevant information and data include the code package, scientific research record and knowledge sharing section of the scientific research unit, specifically including the following steps: In response to the fourth operation of the user (not shown), a copy of the code package of the upstream scientific research unit is created, and the copy of the code package of the upstream scientific research unit is applied to the downstream scientific research unit with the same or lower disclosure level. In the case where the user chooses to synchronize scientific research records, the historical scientific research records of the upstream scientific research unit are linked to the downstream scientific research unit. In this way, even if the upstream project is deleted for some reason, the corresponding scientific research unit in the downstream project can still continue to run without being affected.

[0070] Next, when the public level of the downstream research unit is the same as that of the upstream research unit, the knowledge sharing section of the upstream research unit is synchronized with the knowledge sharing section of the downstream research unit in both directions; when the public level of the downstream research unit is lower than that of the upstream research unit, the knowledge sharing section of the upstream research unit is synchronized with the knowledge sharing section of the downstream research unit in one direction. Since an upstream research unit can be applied by multiple downstream projects, a radial research unit network can be formed around a research unit in the platform, and the central node is the upstream research unit. Through the two-way synchronization of the knowledge sharing section, the application of research units gradually evolves from individual behavior to community collaboration behavior. This research unit network naturally evolves into a community with a theme (the theme is the content of the research unit). With the continuous application of upstream and downstream, problems about the research unit can be gradually discovered, and the research unit can be continuously improved in practical application through continuous feedback and optimization of the community. This community-driven model effectively transforms individual experience accumulation into collective wisdom, laying a solid foundation for the long-term development of research units.

[0071] Through the above steps, the scientific research unit designed by the user can be applied to different laboratories or different projects in the platform of the embodiment of the present application by one key. In this way, the user of the platform can conveniently apply the scientific research unit designed and provided by others without having any scientific research unit writing experience, which promotes the global sharing of scientific research units and scientific research programs. On the other hand, scientific researchers can share their research plans and data records through the platform, so that other laboratories can easily reproduce these experiments, improve the repeatability of scientific research programs and scientific research results, and in addition, promote scientific research cooperation worldwide by sharing scientific experience across laboratories, projects and scientific research units.

[0072] FIG1 (d) shows another schematic diagram of the composition of the scientific research activity management and application platform supporting multi-disciplinary sharing according to an embodiment of the present application. Based on the composition structure shown in FIG1 (a), the scientific research activity management and application platform 10 can further include an AI system tool 14 with a large language model as the core. FIG5 (a) shows a schematic diagram of the chat interface of the AI ​​system tool according to an embodiment of the present application.

[0073] As shown in FIG5(a), the AI ​​system tool 14 is configured to include a chat interface 141. As an example only, the chat interface 141 is named “AI Masterbrain”, and the chat interface 141, for example, receives content and instructions from a user in a chat conversation. In addition, the chat interface 141 may automatically generate a scientific research unit code package for the user when receiving relevant information introduced through “Add context”. The scientific research unit code package may also be revised through the user's interaction with the AI ​​system tool 14 in the dialog box of the chat interface 141.

[0074] 5(b) is a schematic diagram showing a grammar check of a customized scientific research unit using an AI system tool according to an embodiment of the present application.

[0075] As shown in FIG5 (b), the AI ​​system tool 14 also includes a scientific research unit grammar checker 142 for checking whether the code conforms to the custom scientific research unit grammar. Thus, automatically generating a scientific research unit code package for the user, and revising the scientific research unit code package through the user's interaction with the AI ​​system tool 14 in the chat interface 141 further includes: when the user provides the AI ​​system tool 14 with a protocol document to be converted into a scientific research protocol in the chat interface 141, injecting the custom scientific research unit grammar and the example of conversion from the reference document to the scientific research protocol as the context into the chat dialogue, and making the large language model perform the following operations: generating a scientific research protocol in the scientific research unit code package based on the chat dialogue with the context; generating a model of the scientific research unit in the scientific research unit code package based on the generated scientific research protocol and the chat dialogue with the context; generating an assigner of the data field in the scientific research unit code package based on the scientific research protocol, the model and the chat dialogue with the context in the generated scientific research unit code package. In this way, providing the chat dialogue with the situational context to the AI ​​system tool 14 can help it to more accurately determine the data type of the data field, especially some specific data types that require direct reading of the original document to be converted provided by the user to accurately determine. On this basis, the grammatical part corresponding to the model and evaluator in the scientific research unit syntax of this application is used to sequentially and more accurately generate the model of the scientific research unit and the evaluator of the data field in the scientific research unit code package.

[0076] On this basis, the scientific research unit grammar checker 142 is used to perform scientific research unit grammar check on the scientific research unit code package generated by the large language model, and the grammar check result is fed back to the large language model, so that the large language model can generate the scientific research unit code package again based on the grammar check result until the grammar in the generated scientific research unit code package is completely correct.

[0077] It is worth noting that since the platform according to the embodiment of the present application is an actively developed framework, the scientific research unit grammar shared by multiple disciplines in the platform is also constantly updated. Therefore, in order to ensure that the AI ​​system tool can continue to be compatible with the latest scientific research unit grammar, in the embodiment of the present application, the strategy of fine-tuning the model is not adopted. Instead, as mentioned above, the context length of the large language model is significantly enhanced (such as qwen-long supports 10,000,000 tokens context, gpt-4o supports 128,000 tokens context), and the currently used scientific research unit grammar version is injected into the conversation as the situational context. This method greatly improves the generation efficiency of scientific research units and ensures that the large language model generates content that conforms to the latest scientific research unit grammar based on a comprehensive understanding of the latest scientific research unit grammar.

[0078] In other embodiments, when a user asks questions or gives modification suggestions for a specified part of a scientific research unit code package in the chat interface 141, the large language model provides an explanation of the user's question, or provides a revision plan for the specified part that satisfies the modification suggestions given by the user, thereby achieving targeted optimization of the scientific research plan. For example, a user can ask questions about the grammar of a scientific research unit, and the system tool can give a detailed answer.

[0079] Through AI-driven automatic generation of scientific research protocols, researchers no longer need to manually write complex scientific research protocols, which reduces the learning threshold of the scientific research unit framework, simplifies the process of starting scientific research projects, and significantly reduces the difficulty of scientific research unit design. In addition, AI can understand the scientific research needs of different disciplines and generate appropriate scientific research protocols for interdisciplinary projects, which is particularly important for projects involving cooperation among multiple disciplines, and improves the coordination and implementation efficiency of interdisciplinary projects.

[0080] In some embodiments, when a user opens a chat interface 141 under a specific scientific research unit and asks a question, relevant information of the specific scientific research unit is injected into the chat dialogue as a situational context, so that the AI ​​system tool 14 generates an answer associated with the specific scientific research unit in the chat 141, wherein the relevant information of the scientific research unit includes at least the scientific research protocol in the scientific research unit code package, and the content in each knowledge sharing section corresponding to the scientific research unit that can be obtained according to the publicity level of the scientific research unit.

[0081] Unlike general chatbots (such as ChatGPT), the AI-assisted research unit QA function provided by the AI ​​system tool has two unique features: first, it can make full use of the research unit information related to the dialogue (such as research agreements); second, it can use the content in the knowledge sharing section related to the research unit, as well as the knowledge resources within the entire platform. As a result, the deeply integrated AI system tool can more accurately answer users' questions about specific research activity scenarios, and enhance the intelligent support for scientific research data recording and analysis.

[0082] FIG5(c) is a schematic diagram showing how to inject relevant information of a scientific research unit as context into an AI system tool chat dialogue according to an embodiment of the present application. As shown in FIG5(c), a user asks the following question in a scientific research unit related to protein purification (Purification of Lipoylated H Protein): How can I improve the yield? Since the AI ​​system tool injects relevant information of the scientific research unit into the conversation, in this embodiment, the relevant information is the scientific research agreement of the scientific research unit. Therefore, the following answer will be given according to this specific scenario: To improve the yield in the protein purification experiment, consider the following strategies: 1. Optimize Lysis Conditions: Adjust buffer composition, temperature, and duration to maximize protein release.

[0083] 2. Minimize Protein Loss: Use gentle techniques, keep the process cold, and reduce the number of purification steps.

[0084] 3. Optimize Affinity Chromatography: Fine-tune binding and elution conditions specific to your protein's affinity tag.

[0085] 4. Prevent Proteolysis: Add protease inhibitors and work quickly at cold temperatures to prevent protein degradation.

[0086] 5. Carefully Concentrate and Refold Protein: Use appropriate methods to avoid loss and aggregation during concentration and refolding.

[0087] It can be seen that the above answer is more specific, targeted and in-depth than the general ChatGPT answer shown in Figure 5 (d). This is because the research protocol of the scientific research unit injected into the conversation by the AI ​​system tool provides it with clear experimental background information, allowing it to understand that the conversation takes place in the experimental scenario of protein purification, and to infer that the "yield" mentioned by the user refers to "the yield in the protein purification experiment", thereby giving a more professional and targeted answer. Therefore, even if the user knows nothing about AI background knowledge, the AI ​​system tool can automatically provide answers tailored to the scenario of the scientific research unit through simple scientific research unit customization without any secondary development of AI, which greatly improves the practicality and convenience of AI in scientific research applications.

[0088] In some embodiments, for example, when a user asks the same question again, the AI ​​system tool can also dynamically obtain the content in the knowledge sharing section available in the scientific research unit through the search service, and apply it to the answer. In this way, not only can efficient retrieval of scientific research protocols, scientific research plans and scientific research data be achieved, but also cross-disciplinary scientific research Q&A can be achieved, and the shareability of scientific research plans, data and expert experience within and between laboratories and even globally can be improved. The scientific research knowledge carried by the platform is interwoven into an organic whole, so that knowledge can be efficiently disseminated and applied in a wide range of scientific research communities, and cross-project and cross-laboratory scientific research cooperation and knowledge sharing can be promoted.

[0089] In other embodiments, the AI ​​system tool allows the user to use buttons such as Add context to independently select background knowledge that can be applied when the AI ​​system tool answers. As an example only, when the AI ​​system tool is opened in the scientific research protocol interface, it can be assumed that the AI ​​injects all protocol information related to the scientific research protocol; in other cases, when the user opens the AI ​​system tool in the knowledge sharing section interface, the scientific research protocol information and knowledge of the knowledge sharing section contained in the scientific research unit are injected by default. Of course, the user can also configure the scope of the context at this time, such as whether to use the knowledge of all knowledge sharing sections under the project, or the knowledge of the publicly accessible knowledge sharing sections under the laboratory, or the entire platform, and so on. In addition, users can also inject historical records as context into the AI ​​system tool, so that the AI ​​system tool will be able to take historical records into consideration when performing intelligent analysis of questions.

[0090] Fig. 5 (e) shows a schematic diagram of analyzing scientific research records using an AI system tool according to an embodiment of the present application. As shown in Fig. 5 (e), when a user opens a chat interface 141 under a specific scientific research unit and requests to analyze a scientific research record 143 (the numbers 219, 218, 217, etc. shown in the figure are exemplary simplified scientific research record IDs, corresponding to 5 scientific research records with different unique IDs, which correspond to the No. #5, No. #4, and No. #3 scientific research records shown in 144, respectively), the scientific research protocol corresponding to the scientific research unit and the JSON Schema of the scientific research unit data field are used as the context context, so that the AI ​​system tool 14 generates an analysis report on the scientific research record of the specific scientific research unit based on the historical scientific research record 144 of the specific scientific research unit and the context context. Since the separation of the scientific research unit code package and the scientific research record is achieved in the embodiment according to the present application, that is to say, if you want to understand any scientific research record generated based on the same scientific research unit code package, you only need to provide the scientific research unit code package and its corresponding data field JSON Schema. Therefore, even if you want to analyze multiple scientific research records, as long as they correspond to the same scientific research unit code package, you only need to provide the scientific research protocol and the scientific research unit data field JSON Schema as context once, without repeated provision, which can save resources and be more efficient without losing any valid information. Of course, in the case of a more in-depth analysis and understanding of each scientific research record, the model and evaluator part of the scientific research record can be selectively injected into the AI ​​system tool 14 as a scenario context, and this application does not limit this.

[0091] In other embodiments, the user may also open the chat interface 141 under a specific scientific research unit and request an analysis of the scientific research record with a specified analysis intent. In this case, the scientific research protocol corresponding to the scientific research unit, the scientific research unit data field JSON Schema, and the specified analysis intent are used as the scenario context, so that the AI ​​system tool 14 generates an answer or analysis report for the specified analysis intent of the scientific research record of the specific scientific research unit based on the historical scientific research records and scenario context of the specific scientific research unit. In addition, according to the embodiments of the present application, multiple rounds of dialogue are also supported, and when the user proposes further or completely different analysis intentions in different rounds of dialogue, the analysis results of the previous round can be provided to the AI ​​system tool 14 as the scenario context, so that the AI ​​system tool 14 can perform a deeper and more comprehensive analysis.

[0092] The AI ​​system tool according to the embodiment of the present application can build a bridge between different fields by understanding scientific research protocols and data from different disciplines. Researchers can use this tool to quickly understand and apply experimental data and methods from other disciplines, greatly reducing the knowledge barriers between disciplines. In addition, the AI ​​system tool can not only answer questions related to the protocol, but also provide suggestions based on existing data to help researchers optimize experimental results. It is a powerful assistant / AI mentor for scientists to improve scientific research efficiency, and can also promote one-click analysis of scientific research data, AI-based heuristic suggestion generation, and scientific research report generation.

[0093] FIG1(e) shows another schematic diagram of the composition of the scientific research activity management and application platform supporting multi-disciplinary sharing according to an embodiment of the present application. As shown in FIG1(e), based on FIG1(d), the scientific research activity management and application platform 10 can further include a scientific research process integration tool 15.

[0094] In some embodiments, the scientific research process integration tool 15 can be configured, for example, to generate an automatically executable scientific research unit workflow (also referred to as RUW below) based on a scientific research unit workflow diagram (hereinafter also referred to as RUWG) given by a user, or based on a scientific research unit workflow diagram and workflow diagram logic (hereinafter also referred to as RUWGL) given by a user, using the AI ​​system tool 14, wherein the scientific research unit workflow diagram is a directed graph and includes multiple scientific research units, and the disciplines corresponding to each of the multiple scientific research units are the same or different.

[0095] It is worth noting that the scientific research activity management and application platform according to the embodiment of the present application may include scientific research units from any of the same or different fields. Therefore, the scientific research unit workflow diagram in the embodiment of the present application can be a combination of scientific research units of any of the same or different fields / disciplines in any way. In other embodiments, it is not even necessary to pre-design a workflow diagram with a perfect form, but according to the goal of the characteristics to be achieved, multiple scientific research units of interest are selected as nodes in the same scientific research unit workflow diagram as needed, and only when necessary, the workflow diagram logic is used to constrain and limit, and the form is flexible. As an example only, the above-mentioned workflow method can be applied to multiple fields such as carbon nanotube material self-dispersion research, new drug discovery, protein engineering, bioengineering fermentation research, chemical synthesis of gold nanoparticles and single-cell sequencing research. For example, each scientific research unit can represent a step in the scientific research activities of the same discipline or similar disciplines, and multiple scientific research units can be combined according to experimental requirements to construct a complex experimental workflow, thereby helping users to achieve automated management of experimental steps or multiple stages of research projects. As an example only, the regular maintenance work of a set of scientific research instruments can be designed as a workflow, and each scientific research unit in the workflow represents the maintenance work of different scientific research instruments. Then, through the automatic design and automatic execution of the workflow, the electronic and intelligent maintenance of scientific research instruments can be realized.

[0096] In other embodiments, each scientific research unit can represent the experimental steps of different disciplines. The flexible collaborative working mode of the scientific research units can also enable cross-disciplinary research and greatly promote the efficient generation of multidisciplinary cross-disciplinary / integrated innovation results. In addition, the workflow mode can also provide methodology and implementation support for industrialized scientific research that scientific research automation equipment relies on.

[0097] Taking the ultrasonic dispersion research of carbon nanotubes as an example, Figure 6 (a) shows a schematic diagram of the scientific research unit workflow diagram according to an embodiment of the present application, and Figure 6 (b) shows a schematic diagram of the research path (also referred to as the scientific research unit path, hereinafter also referred to as RUP) according to an embodiment of the present application.

[0098] In Figure 6 (a) and Figure 6 (b), RU1-RU4 represent four research units, RU1 represents the preparation of dispersion from carbon nanotube powder, RU2 represents ultrasonic dispersion, RU3 represents the preparation of low-concentration dispersion from high-concentration carbon nanotube dispersion, and RU4 represents dispersion characterization. In the actual research on ultrasonic dispersion of carbon nanotubes, the above-mentioned research units can be carried out in sequence to achieve specific research goals. As shown in Figure 6 (b), in research path 1, carbon nanotube powder is first used to prepare a high-concentration dispersion (RU1), then the dispersion is dispersed using ultrasonic technology (RU2), and then the dispersion results are characterized to verify the effect of this dispersion (RU4). The characterization results show that the current dispersion structure has not yet reached the expected state, so the high-concentration dispersion is prepared as a low-concentration dispersion (RU3), then ultrasonically dispersed again (RU2), and finally characterized (RU4). The characterization results meet expectations, and the process can be terminated at this time (End).

[0099] However, in real scientific research, other research paths similar to research path 1 are usually not exhaustive. For example, based on the dispersion characterization results, it can be determined whether it is necessary to re-ultrasonicate and then characterize (which means repeating the RU2→RU4 process), or further dilute the dispersion and then characterize it after ultrasonication (which means repeating the RU3→RU2→RU4 process). The above process can be repeated until a satisfactory dispersion result is obtained. Research path 2-research path 6 show some possible research paths, but all possible paths are often not exhaustive. Therefore, Figure 6 (a) shows a workflow diagram consisting of four research units, RU1, RU2, RU3 and RU4. It can be seen that this is a directed graph that can constitute multiple research paths. Users can describe a scientific research process by defining such a directed graph, in which each directed edge represents the logical relationship between each RU. Such a directed graph can well handle logical relationships with a cyclic topological structure. The workflow graph can be regarded as a "path set" consisting of all reasonable research paths. It can be seen that research paths 1-research paths 6 in Figure 6 (b) all conform to the topological structure of the workflow graph in Figure 6 (a).

[0100] In order to make the research path generated based on the workflow diagram conform to the logic of scientific research in this field, the workflow diagram can be supplemented with corresponding workflow diagram logic. In the above embodiment, the workflow diagram logic can include the following 4 items: 1. The entire dispersion process must be carried out in a solution system. The preparation of dispersions from solid powders can only be the first step of the experiment: RU1 must be the starting point of the research path.

[0101] 2. Each dispersed system must go through the preparation, sonication, and characterization stages: a research path must include at least one (RU1 → RU2 → RU4) instance, and this order is irreversible.

[0102] 3. Based on the characterization results, determine if: 1) the sample needs to be sonicated again (RU4 → RU2), or, 2) the dispersion solution needs to be further diluted before sonication (RU4 → RU3 → RU2). After repeating either of these two paths, characterization must be performed again (RU4) to confirm subsequent results. Based on the results of RU4, these two paths can be followed alternately.

[0103] 4. The characterization process (RU4) is the only quality control step in the experiment and can appear in the middle of the steps, but must always be the last step in the research path.

[0104] 5. When the characterization results (RU4) meet the research objectives, the research path can be terminated.

[0105] In the process of conducting scientific research according to the research path generated based on the workflow diagram, the scientific research data obtained can be considered as the scientific research records generated by the scientific research units on the path conducting research in the connection order. Figure 6 (c) shows a schematic diagram of scientific research data generated by executing the research path according to the embodiment of the present application. Figure 6 (c) shows the scientific research records generated in sequence by each scientific research unit when executing the research path 1 in Figure 6 (b), where RUR i Indicates the scientific research record generated in step i, with the superscript RU j This means that the research record is from RU j The above scientific research data can also be represented as a scientific research record list as shown in Figure 6 (c).

[0106] Figure 7 FIG. 1 is a schematic diagram showing a process of using an AI system tool to generate an automatically executable scientific research unit workflow according to an embodiment of the present application. Figure 7 As shown, the specific process of using AI system tools to generate automatically executable scientific research unit workflows is as follows.

[0107] In step 701, based on the scientific research unit workflow diagram given by the user and the current scientific research intention (hereinafter also referred to as RP) given by the user / automatically generated by the AI ​​system tool, combined with the research progress of the preceding scientific research unit in the scientific research unit workflow, the AI ​​system tool can be used to determine whether there is a feasible research strategy for the current scientific research intention. If the judgment in step 701 is "yes", proceed to step 702.

[0108] Assume that the user gives an arbitrary research unit workflow (RUW) defined by a research unit workflow graph (RUWG) and a workflow graph logic (RUWGL). The RUW can be expressed as follows: RUW = (RUWG, RUWGL)(1) RUWG = (RUs, RUEs)(2) RUs = {RU1, RU2, . . . , RU m}(3) Among them, RUs in formula (3) represents the set of scientific research units that constitute RUWG, and RUEs in formula (2) represents the set of edges in RUWG.

[0109] The work that the AI ​​system tool needs to accomplish can be expressed as follows (4): (RUW, RP) → Automated process? → RC(4) That is, given a RUW and a RP, can we apply the RUs in the RUW to generate a RUP, obtain the RURs corresponding to each RU on the RUP, and finally obtain the RC (scientific research conclusion) corresponding to the RP? The above problem can be described by the following equations (5) to (8): (5) (6) End(7) (8) Here, n represents the total number of RUs in the research path RUP. Represents the i-th RU passed on the path. Note that i only represents the position number, not the RU number. Represents the i-th RU on the path (i.e. ) The RUR generated by . In this way, a sequence of RUR is obtained , which contains the RUR generated by the RU corresponding to steps 1 to n on this RUP. Therefore, as shown in formula (5), by comprehensively analyzing RUW and The characteristics of the RP (including the information of RUP) can be automatically analyzed by AI1 to obtain the RC corresponding to the RP, where AI1 refers to an artificial intelligence algorithm that has been trained to solve the above problems. It can be a single deep learning network or composed of multiple sub-networks with different functions. This application does not impose any restrictions on this.

[0110] The above process can be further decomposed into the following formula (9): (9) In the above process, when a RP is given, we can let the AI ​​system tool target the RP, combine various information of the RUW, and design a feasible research strategy (RS) for the RP. The core purpose of this step is to allow the AI ​​system tool to comprehensively and comprehensively think about the RUW and the corresponding RP, and carry out the following two key steps: 1. Determine whether the RP can be properly solved through some reasonable application of the RUW; 2a. If the judgment is no, the user should be directly informed that the RP is not suitable for the application of the RUW to solve; 2b. If the judgment is yes, what is the specific RS that should be applied to achieve the RP, and give a specific RS, so as to guide how to select a suitable RU through an automated method in the future to provide guidance for scientific research. Just as an example, for the RUW related to the self-dispersion research of carbon nanotubes shown in Figures 6 (a) and 6 (b), it is obviously not suitable for the RP of "studying how cells divide by mitosis". Therefore, in the embodiment of the present application, the rationality of the RP can be judged first. If it is judged to be unreasonable, the conclusion that the RUW cannot support the current RP will be given, that is, there is no feasible research strategy for the current scientific research intention. In other embodiments, different RPs actually require different research strategies. For example, for the RUW related to the self-dispersion research of carbon nanotubes shown in Figures 6 (a) and 6 (b), two different RPs, "Study how to use m-cresol to disperse carbon nanotubes to an average diameter of 20-30 nm under as little ultrasound as possible" and "Study how to use m-cresol to disperse carbon nanotubes to an average diameter of 20-30 nm under as little dilution as possible", require different RSs. The generation of the above RS can be achieved by the method represented by the following formula (10): (10) The above formula (10) indicates that AI method 2 (AI2) is used to automatically determine whether a given RUW can support the study of RP. If so, RS is given. If not, the RUP is terminated (End). AI2 can be an AI method under the same framework as AI1, or an independent AI method dedicated to RS generation, which is not limited in this application.

[0111] Next, when the AI ​​system tool determines that there is a feasible research strategy for the current scientific research intention, in step 702, the scientific research unit for the next scientific research is automatically selected in the scientific research unit workflow diagram, or the current research path is terminated according to the research progress of each scientific research unit. It can be understood that the current research path will be terminated only in the following two cases: 1. Each current scientific research unit has completed its own research, and has achieved the required scientific research intention and can obtain the corresponding scientific research conclusion; 2. Despite repeated attempts to apply the RUs involved in the RUW, the target RP cannot be achieved.

[0112] After obtaining RS, the first RU can be selected in an automated manner according to the following formula (11): ): (11) Similarly, AI3 can be an AI method under the same framework as AI1 or AI2, or it can be an independent AI method dedicated to RU selection, and this application does not impose any restrictions on this.

[0113] Then, by applying and executing , that is, when After completing the scientific research, you can obtain the corresponding RUR ( ), on this basis, the AI ​​system tools can be used to analyze , to obtain a phased conclusion ( ). This interim conclusion can include rich meaning dimensions beyond the literal meaning of "summary", such as: 1) What interim conclusions can the current RUR provide for RP; 2) Whether it is sufficient to respond to RP; 3) If it is not sufficient to respond, whether there are any further plans for subsequent scientific research; 4) Since scientific research has great unknowns and uncertainties, AI system tools can also reflect on the rationality of RS at this time, and how to make appropriate adjustments if it is unreasonable; 5) Whether abnormal / special phenomena and / or abnormal / special data worthy of attention are found during the research process, etc., which are not listed here one by one. The process can be expressed as the following formula (12): (12) Similarly, AI4 can be an AI method under the same framework as AI1, AI2 or AI3, or it can be an independent AI method dedicated to generating RC, and this application does not impose any restrictions on this.

[0114] In the subsequent steps, the process of formula (11)-formula (12) can be repeated to select each RU on the RUP in turn until the end (End). The general representation of this process is shown in formula (13)-formula (15): (13) (14) (15) In equations (13) to (15), when i = 1, , , then the form of formula (14) is consistent with that of formula (11), and the form of formula (15) is consistent with that of formula (12).

[0115] In an embodiment of the present application, when there is a feasible research strategy, after the scientific research unit at each step in the research path completes the scientific research, the AI ​​system tool can be used to automatically generate interim conclusions based on the historical scientific research records of the research path, and automatically select the scientific research unit in the workflow diagram of the scientific research unit to carry out the next scientific research while taking the interim conclusions into consideration.

[0116] In some embodiments, the interim conclusions may include, for example, whether the historical scientific research record data can meet the current scientific research intention, whether the current scientific research strategy is effective, whether it needs to be revised or optimized based on real scientific research data, and suggestions for the next step, etc. It can also be other results based on certain evaluation criteria to evaluate the previous scientific research process or scientific research results. This application does not make specific limitations here. In other words, the scientific research unit that is to carry out scientific research in the next step is not selected based on a static strategy, but is related to the actual scientific research records of the current scientific research unit, and even the interim conclusions formed by the previous scientific research process. In this way, not only can a research path that can be automatically executed be generated for any user-designed or given scientific research unit workflow diagram in a general way, but the scientific research process can also be dynamically adjusted to make the entire scientific research process close to the optimal, which can promote the efficient execution of iterative optimization scientific research.

[0117] Next, in step 703, after the current research path is completed, the AI ​​system tool is used to automatically generate a scientific research conclusion for the scientific research unit workflow diagram and the current scientific research intention given by the user based on the historical scientific research records of the current research path.

[0118] Fig.10 A schematic diagram showing a scientific research conclusion automatically generated by an AI system tool according to an embodiment of the present application. Fig.10 As shown, the scientific research conclusion may include multiple aspects, such as whether the scientific research conducted through each node in the workflow diagram has achieved the conclusion of the scientific research intention given by the user, or whether some special phenomena, data or process discoveries worthy of further study have been observed in the entire research path history, or suggestions for potential new research directions and strategy optimization in the future, etc. This application does not impose any restrictions on this.

[0119] In other words, in the process of generating and executing scientific research paths, a sequence of RCs is actually generated. (n represents the total number of RU applications in this RUP). These intermediate conclusions can also assist in the generation of final scientific research conclusions. Therefore, formula (5) can be expanded to the following formula (16): (16) In some embodiments, since for an RU, its essence is to define a scientific research scheme with adjustment space, and this adjustment space actually comes from the data field defined in the scientific research protocol of the RU. For example, in the ultrasonic dispersion RU in Figure 6 (a) and Figure 6 (b), a data field related to ultrasonic time is defined in its scientific research protocol. That is to say, if you want to apply this RU, you need to first know the value of this data field before you can obtain the corresponding scientific research record. Usually, this part of the data field can be called parameter data field (and the others can be called feedback data field). Therefore, while automatically selecting the scientific research unit that will carry out scientific research in the next step in the scientific research unit workflow diagram, it is also necessary to further use the AI ​​system tool to automatically design scientific research parameters that meet the current scientific research intention for the scientific research unit that should carry out scientific research in the next step. The predicted scientific research parameters will be correspondingly assigned to the various parameter data fields defined in the scientific research protocol of the scientific research unit, so that the scientific research unit can carry out research under the condition that the parameters are determined. The automatic derivation of scientific research parameters that meet the current scientific research intention using the AI ​​system tool can be expressed as follows (17): (17) in, Representative scientific research records The collection of all data fields in ( ) is a collection of parameter data fields; AI5 can be an AI method under the same framework as AI1, AI2, AI3 or AI4, or it can be an independent AI method dedicated to deriving parameter data field values, and this application does not impose any restrictions on this.

[0120] Therefore, in the embodiments of the present application, for the first time, a series of AI automation methods such as AI1-AI5 in the AI ​​system tools are creatively implemented in a general way to coordinate the application and development of each RU, and AI scientific research automation is achieved under any given workflow diagram (or workflow diagram + workflow diagram logic) and scientific research intention.

[0121] In other embodiments, the scientific research process integration tool can be further configured to integrate the generated automatically executable scientific research unit workflow into a single scientific research unit code package. Specifically, for example, each scientific research unit to be applied in the scientific research unit workflow can be defined in any scientific research project. It is worth noting that these scientific research units should be defined under the same scientific research project in the same laboratory. As mentioned above, the scientific research unit workflow is essentially to obtain a list of scientific research records related to the scientific research unit workflow. Therefore, the user can define the scientific research unit workflow in the scientific research protocol to a workflow-type scientific research unit variable with an ID such as cnt_dispersion. In this way, a scientific research unit workflow can be integrated into a single scientific research unit code package, so that it can be shared with all users worldwide in the same way as the scientific research unit code package.

[0122] As more and more institutions and laboratories use the scientific research activity management and application platform that supports multidisciplinary sharing according to the embodiments of the present application, the most extensive scientific research activities in each laboratory will also be efficiently digitized and digitized, which will prepare first-hand data nutrients from the real scientific research front line for future AI scientific research models. Whether these scientific research data are used for AI applications by these laboratories themselves or in cooperation with AI researchers / laboratories through data cooperation, these data will become nutrients for the next generation of artificial intelligence. As a result, it will surely promote the spiral progress of data-intelligence, promote the formation of a global interdisciplinary unified scientific community and social network, promote global scientific research equality, promote the rapid release and sharing of scientific research data, promote the circulation of scientific research data as an asset element, promote global scientific research cooperation and division of labor, and promote scientific research automation. Play a more important role.

[0123] In addition, the scientific research activity management and application platform according to the embodiment of the present application is also applicable to various scenarios with potential customized record requirements. As an example only, it can be directly applied to the electronic medical record scenario. Similar to the scientific research described in other embodiments of the present application, in the medical / hospital / clinical scenario, each institution / department has the need for medical data recording (such as electronic medical records), and the content and type specifications of the data required to be recorded in different departments, different diseases, and different medical scenarios are not the same. It can be imagined that if each records in a customized manner, it will not only be inefficient, but also not conducive to sharing and experience accumulation. With the help of the scientific research activity management and application platform in the embodiment of the present application, users in different professional fields can customize the protocols, models and assigners of medical records according to the scientific research unit syntax, and tailor the medical record method of this profession according to specific needs. Moreover, the customized scientific research unit code package can be widely shared in different departments, so that one-time design can be achieved, and the whole hospital / cross-hospital application can be achieved to achieve unification and standardization for specific medical records. Therefore, the present application has huge application potential and significant economic benefits in multiple industries.

[0124] In addition, although exemplary embodiments have been described herein, the scope includes any and all embodiments based on the present application with equivalent elements, modifications, omissions, combinations (e.g., various embodiments intersecting schemes), adaptations or changes. The elements in the claims will be interpreted broadly based on the language adopted in the claims, and are not limited to the examples described in this specification or during the execution of the application, and the examples will be interpreted as non-exclusive. Therefore, this specification and examples are intended to be considered as examples only, and the true scope and spirit are indicated by the claims and the full scope of their equivalents.

[0125] The above description is intended to be illustrative rather than restrictive. For example, the above examples (or one or more schemes thereof) may be used in combination with each other. For example, a person of ordinary skill in the art may use other embodiments when reading the above description. In addition, in the above-mentioned specific embodiments, various features may be grouped together to simplify the present application. This should not be interpreted as an intention that a disclosed feature that is not required to be protected is necessary for any claim. On the contrary, the subject matter of the present application may be less than all the features of a particular disclosed embodiment. Thus, the claims are incorporated herein into the specific embodiments as examples or embodiments, wherein each claim is independently a separate embodiment, and it is considered that these embodiments may be combined with each other in various combinations or arrangements. The scope of the present application should be determined with reference to the claims and the full scope of equivalent forms granted by these claims.

[0126] The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.

Claims

1. A scientific research activity management and application platform supporting multi-disciplinary sharing, characterized by: It includes a scientific research activity management module deployed in the cloud and configured to enable users to manage scientific research activities by running the scientific research activity management module without installing additional software; The scientific research activity management module includes a scientific research unit design environment, and scientific research unit code packages of different disciplines designed and generated by users based on the scientific research unit syntax shared by multiple disciplines defined in the scientific research unit design environment, wherein each scientific research unit code package contains at least the scientific research protocol of the corresponding discipline, and the scientific research protocol is used to define the basic information, multimodal information and data fields of the scientific research experiments of the discipline.

2. The scientific research activity management and application platform according to claim 1, characterized in that: The scientific research unit design environment is further configured so that the scientific research unit code package of the corresponding discipline designed by the user includes a model of the scientific research unit, and the model is used to define the type constraints and / or value verification relationships of the data fields, and the combination verification relationships of types and / or values ​​between various data fields; wherein, The type constraint includes constraining the corresponding data field to use predefined multimodal information during data entry, wherein the predefined multimodal information includes one or more of text, image, video, audio, and file; The numerical verification relationship includes constraining the corresponding data field to follow a specified pattern and / or not exceed a preset value range when data is entered; The combined verification relationship includes constraining the type and / or value of each data field to satisfy a predetermined constraint relationship.

3. The scientific research activity management and application platform according to claim 2, characterized in that: The scientific research unit design environment is further configured so that the scientific research unit code package of the corresponding discipline designed by the user includes a data field assigner, and the assigner is used to assign values ​​to the data fields based on the data field dependency graph and the assignment rules by the user, wherein: The data field dependency graph is a single-level or multi-level directed acyclic graph, the assignment relationship between the defined data fields is single-dependency or multi-dependency, and each data field is assigned a value by at most one assigner.

4. The scientific research activity management and application platform according to any one of claims 1 to 3, characterized in that: The scientific research unit syntax provides the user with a template syntax of the data field so that the user can generate a scientific research unit variable, or a scientific research unit step, or a scientific research unit checkpoint with a unique ID number based on the template syntax of the data field.

5. The scientific research activity management and application platform according to claim 3, characterized in that: The scientific research activity management module also includes a scientific research unit recording environment, and the scientific research unit recording environment is configured as follows: Convert the scientific research unit model into a data field JSON Schema; Based on the data field JSON Schema, a structured storage solution is automatically generated for the scientific research unit, so that when the user submits the scientific research record based on the scientific research unit and each data field conforms to the constraints and verification relationship of the model, the scientific research record will be stored as JSON that conforms to the structured storage solution corresponding to the scientific research unit.

6. The scientific research activity management and application platform according to claim 5, characterized in that: The research unit recording environment is further configured as follows: Based on the scientific research agreement and the data field JSON Schema, a corresponding scientific research unit record interface is automatically generated for the scientific research unit. The scientific research unit record interface has a stylized style obtained based on the custom scientific research unit syntax parsing and interactive controls corresponding to the data type of each data field obtained based on the data field JSON Schema parsing.

7. The scientific research activity management and application platform according to claim 1, characterized in that: The scientific research activity management module further includes a scientific research report generation and reader, which is configured as follows: in response to a user's first operation on a scientific research unit, based on the historical scientific research records of the scientific research unit, it runs locally and automatically generates a formatted scientific research report of the scientific research unit, and enables the user to read the generated formatted scientific research report locally.

8. The scientific research activity management and application platform according to any one of claims 1 to 3, characterized in that: The scientific research activity management and application platform further includes a scientific research unit sharing and application tool, and the scientific research unit sharing and application tool is configured as: Generate a unique ID number for each scientific research record of the scientific research unit, and associate the unique ID number with the record time to make each scientific research record non-tamperable; When a user wants to make modifications based on a submitted scientific research record, a copy of the scientific research record is generated for the user, and a new unique ID number is generated for the copy of the scientific research record and associated with the modification time, so that the user can make modifications on the copy with the new unique ID number.

9. The scientific research activity management and application platform according to claim 8, characterized in that: The research unit sharing and application tool is further configured as: In response to a second operation on a scientific research unit by a user with corresponding authority, a level is marked for the scientific research unit, the level is divided into at least a laboratory level and a project level from high to low, and a user access control mechanism corresponding to a disclosure level is provided for each level and / or each scientific research unit; and Set a level tag for each user that corresponds to the level division of scientific research units.

10. The scientific research activity management and application platform according to claim 9, characterized in that: Provide corresponding user access control mechanisms for each level and / or each scientific research unit, including: Set up access permissions for each lab level that are open to all users; Set up access permissions for users tagged at a specific level for each project level; When a specific user has access rights to a specific project, the specific user has access rights to all scientific research units in the specific project.

11. The scientific research activity management and application platform according to claim 10, characterized in that: Setting the access permissions for users tagged at a specific level for each project level includes: Set all users to have access permissions for the project layer; or, Only users with the same lab tier tag have access to that project tier; or, Only users with the same project layer tag have access permissions to that project layer.

12. The scientific research activity management and application platform according to claim 9, characterized in that: Providing corresponding user access control mechanisms for each level and / or each scientific research unit also includes: In response to a third operation by a user with corresponding permissions, a group tag is set for users with the same laboratory layer tag, and access permissions to a specific project layer are correspondingly set for users with each group tag.

13. The scientific research activity management and application platform according to any one of claims 1 to 3, characterized in that: The scientific research activity management and application platform further includes a knowledge sharing section corresponding to each scientific research unit, so that the maintainer of the scientific research unit or other interested users can provide or obtain knowledge related to the scientific research activities of the scientific research unit in the form of questions and answers in the knowledge sharing section.

14. The scientific research activity management and application platform according to claim 13, characterized in that: The scientific research activity management and application platform is further configured to use the content in the knowledge sharing section to update the scientific research agreement of the corresponding scientific research unit.

15. The scientific research activity management and application platform according to claim 9, characterized in that: The scientific research activity management and application platform further includes a knowledge sharing section corresponding to each scientific research unit, so that the maintainer of the scientific research unit or other interested users can provide or obtain knowledge related to the scientific research activities of the scientific research unit in the form of questions and answers in the knowledge sharing section; The research unit sharing and application tool is further configured to support cross-laboratory or cross-project sharing and application of relevant information and data of the research unit, wherein the relevant information and data include the code package, research record and knowledge sharing section of the research unit, specifically including: In response to the fourth operation of the user, a code package copy of the upstream scientific research unit is created, and the code package copy of the upstream scientific research unit is applied to the downstream scientific research unit with the same or lower disclosure level, and in the case where the user chooses to synchronize scientific research records, the historical scientific research records of the upstream scientific research unit are linked to the downstream scientific research unit; When the disclosure level of the downstream scientific research unit is the same as that of the upstream scientific research unit, the knowledge sharing section of the upstream scientific research unit and the knowledge sharing section of the downstream scientific research unit are synchronized bidirectionally; when the disclosure level of the downstream scientific research unit is lower than that of the upstream scientific research unit, the knowledge sharing section of the upstream scientific research unit is synchronized unidirectionally to the knowledge sharing section of the downstream scientific research unit.

16. The scientific research activity management and application platform according to any one of claims 1 to 3, characterized in that: The scientific research activity management and application platform further includes an AI system tool with a large language model as the core. The AI ​​system tool is configured to include a chat interface, and can automatically generate scientific research unit code packages for users, and revise the scientific research unit code packages through the user's interaction with the AI ​​system tool in the chat interface.

17. The scientific research activity management and application platform according to claim 16, characterized in that: The AI ​​system tool is further configured to include a research unit syntax checker for checking whether the code complies with the custom research unit syntax; Automatically generating a scientific research unit code package for a user, and revising the scientific research unit code package through the user's interaction with the AI ​​system tool in the chat interface further includes: When the user provides the AI ​​system tool with a protocol document to be converted into a scientific research protocol in the chat interface, the custom scientific research unit grammar and the example of conversion from the reference document to the scientific research protocol are injected into the chat dialogue as the situational context, and the large language model is enabled to: generate the scientific research protocol in the scientific research unit code package based on the chat dialogue with the situational context; generate the model of the scientific research unit in the scientific research unit code package based on the generated scientific research protocol and the chat dialogue with the situational context; generate the assigner of the data field in the scientific research unit code package based on the scientific research protocol, the model in the generated scientific research unit code package and the chat dialogue with the situational context; Performing a scientific research unit grammar check on the scientific research unit code package generated by the large language model using a scientific research unit grammar checker, and feeding back the grammar check result to the large language model, so that the large language model generates the scientific research unit code package again based on the grammar check result, until the grammar in the generated scientific research unit code package is completely correct; When a user asks a question or gives a modification suggestion for a specified part of a scientific research unit code package in the chat interface, the large language model provides an explanation to the user's question or a revision plan for the specified part.

18. The scientific research activity management and application platform according to claim 16, characterized in that: The AI ​​system tool is further configured to: When a user opens a chat interface under a specific scientific research unit and asks a question, the relevant information of the specific scientific research unit is injected into the chat dialogue as a situational context, so that the AI ​​system tool generates an answer associated with the specific scientific research unit in the chat interface, wherein the relevant information of the scientific research unit includes at least the scientific research protocol in the code package of the scientific research unit, and the content in each knowledge sharing section corresponding to the scientific research unit that can be obtained according to the publicity level of the scientific research unit.

19. The scientific research activity management and application platform according to claim 16, characterized in that: The AI ​​system tool is further configured to: When a user opens a chat interface under a specific scientific research unit and requests to analyze scientific research records, the scientific research protocol corresponding to the scientific research unit and the JSON Schema of the scientific research unit data field are used as the context, so that the AI ​​system tool generates an analysis report on the scientific research records of the specific scientific research unit based on the historical scientific research records and context of the specific scientific research unit; or, When a user opens a chat interface under a specific scientific research unit and requests an analysis of the scientific research records with a specified analysis intent, the scientific research protocol corresponding to the scientific research unit, the scientific research unit data field JSON Schema, and the specified analysis intent are used as the situational context, so that the AI ​​system tool generates an answer or analysis report for the specified analysis intent of the scientific research records of the specific scientific research unit based on the historical scientific research records of the specific scientific research unit and the situational context.

20. The scientific research activity management and application platform according to claim 16, characterized in that: The scientific research activity management and application platform further includes a scientific research process integration tool, which is configured as follows: Based on the scientific research unit workflow diagram given by the user, or the scientific research unit workflow diagram and workflow diagram logic given by the user, an AI system tool is used to generate an automatically executable scientific research unit workflow, wherein the scientific research unit workflow diagram is a directed graph and includes multiple scientific research units, and the disciplines corresponding to each of the multiple scientific research units are the same or different.

21. The scientific research activity management and application platform according to claim 20, characterized in that: The use of AI system tools to generate an automatically executable scientific research unit workflow specifically includes: Based on the scientific research unit workflow diagram given by the user and the current scientific research intention given by the user, combined with the research progress of the previous scientific research unit in the scientific research unit workflow, use AI system tools to determine whether there is a feasible research strategy for the current scientific research intention; In the case of a feasible research strategy: automatically select the next research unit in the workflow diagram of the research unit for research, or terminate the current research path according to the research progress of each research unit; After the current research path is completed, the AI ​​system tool is used to automatically generate scientific research conclusions for the scientific research unit workflow diagram and the current scientific research intention given by the user based on the historical scientific research records of the current research path.

22. The scientific research activity management and application platform according to claim 21, characterized in that: Automatically selecting the scientific research unit that should carry out scientific research in the next step in the workflow diagram of the scientific research unit further includes: automatically designing scientific research parameters that meet the current scientific research intentions for the scientific research unit that should carry out scientific research in the next step.

23. The scientific research activity management and application platform according to claim 21, characterized in that: In the case of a feasible research strategy: automatically selecting the research unit in the research unit workflow diagram that should carry out research next further includes: When there is a feasible research strategy: after the current scientific research unit completes the scientific research, the AI ​​system tool is used to automatically generate interim conclusions based on the historical scientific research records of the research path, and taking the interim conclusions into consideration, the scientific research unit that will carry out the next scientific research is automatically selected in the workflow diagram of the scientific research unit.

24. The scientific research activity management and application platform according to claim 20, characterized in that: The scientific research process integration tool is further configured as: The generated automatable research unit workflows are integrated into a single research unit code package.

Images