Construction and use method for domain-specific knowledge base for natural medicinal materials

Abstract

The present application relates to a construction and use method for a domain-specific knowledge base for natural medicinal materials, comprising: on the basis of element entries of various natural medicinal materials, such as botanical origins, medicinal parts and processing methods, generating natural medicinal material systematic names of the various natural medicinal materials by means of manual input or a systematic naming algorithm for natural medicinal materials, such that the natural medicinal material systematic names conform to a custom systematic naming rule for natural medicinal materials, and the custom systematic naming rule for natural medicinal materials at least requires the natural medicinal material systematic names to reflect the botanical origins, medicinal parts and processing methods of the natural medicinal materials; constructing structured and standardized natural medicinal material knowledge, natural medicinal material professional extended terms, natural medicinal material relationship sets and natural medicinal material related texts for the various natural medicinal materials, so as to generate a domain-specific knowledge base for natural medicinal materials; and, on the basis of user operation information, presenting content from the domain-specific knowledge base for natural medicinal materials that is matched with user demands.

Description

Construction and use of a domain-specific knowledge base for natural medicinal materials Technical Field

[0001] The present application relates to the field of natural medicinal material information processing and application, and in particular to a method for constructing and using a natural medicinal material domain-specific knowledge base. Background Art

[0002] Natural medicinal materials (NMMs) have long been recognized as a powerful reservoir of therapeutic agents, their importance reflected in the diversity and biological relevance of the compounds they produce. These compounds play key roles in addressing a wide range of pathological conditions, spanning infectious diseases to cancer, and continue to serve as a rich source of new drug leads. Furthermore, NMMs have an extensive history of clinical application worldwide, particularly in China, India, and the Arab world, demonstrating their enduring relevance in the global healthcare landscape. Despite their significant contributions to healthcare, NMMs are inherently complex. For example, even ingredients with the same origin and medicinal part may differ only in their preparation methods, resulting in different natural medicinal materials. Furthermore, since their names are often not strictly distinguished, knowledge related to NMMs is not stored in a rigorous manner consistent with the Chinese Pharmacopoeia (Current Edition). Consequently, accurate, standardized, and comprehensive domain-specific knowledge on NMMs is often difficult to easily and accurately access using traditional internet search tools or by searching existing databases.

[0003] In some cases, confusion and incomplete knowledge can lead searchers to incorrectly understand the term "ephedra." For example, when attempting to find its English translation online, one might obtain translations such as "Ma Huang," "Ephedra," or "Ephedrae Herba." However, the Chinese Pharmacopoeia (2020 Edition) details that the term "ephedra" refers to a natural medicinal herb derived from several different species, specifically Ephedra sinica (the herb ephedra), Ephedra intermedia (the herb ephedra), or Ephedra equisetina (the herb horsetail ephedra). Despite this classification change within the pharmacopoeia, current naming conventions tend to group these different species under the umbrella term "ephedra," and thus the corresponding English translation fails to reflect these three distinct "ephedra"s. Such unclear and imprecise terminology, resulting in incorrect or inaccurate knowledge acquisition, poses a significant obstacle to scientific research, inevitably undermining the reliability and validity of academic conclusions and even hindering research progress in the field.

[0004] Currently, the existing technology has not yet found a systematized and standardized naming for different types of natural medicinal materials, nor has it found a domain-specific knowledge base that stores standardized natural medicinal material knowledge, nor has it found a method that allows users to use this domain-specific knowledge base to meet their multi-angle and comprehensive needs for accurately and efficiently obtaining relevant knowledge in the field of natural medicinal materials.

[0005] Summary of the Invention

[0006] The present application is provided to solve the above-mentioned problems existing in the prior art.

[0007] There is a need for a method for constructing and using a domain-specific knowledge base for natural medicinal materials that can more clearly distinguish different types of natural medicinal materials and store domain-specific knowledge of natural medicinal materials in a standardized and structured manner, so that the constructed domain-specific knowledge base for natural medicinal materials can meet the needs of users for obtaining domain-specific knowledge of natural medicinal materials from multiple channels, multiple application angles, and in an all-round manner with higher efficiency and accuracy.

[0008] According to the first solution of the present application, a method for constructing and using a domain-specific knowledge base of natural medicinal materials is provided, comprising the following steps: based on element entries including species origin, medicinal parts and processing methods of various natural medicinal materials, generating natural medicinal material systematic names of various natural medicinal materials by manual input or through a natural medicinal material systematic naming algorithm, so that the natural medicinal material systematic names conform to the self-defined natural medicinal material systematic naming rules, and the self-defined natural medicinal material systematic naming rules at least require that the natural medicinal material systematic names reflect the species origin, medicinal parts and processing methods of the natural medicinal materials; constructing structured and standardized natural medicinal material knowledge, natural medicinal material systematic names ... The method comprises the following steps: generating a natural medicine domain knowledge base based on the generated natural medicine systematic naming, structured and standardized natural medicine knowledge, natural medicine professional extended terminology, natural medicine relationship set and natural medicine related text of various natural medicines; generating the natural medicine domain knowledge base based on the generated natural medicine systematic naming, structured and standardized natural medicine knowledge, natural medicine professional extended terminology, natural medicine relationship set and natural medicine related text of various natural medicines; and obtaining user operation information that defines the target natural medicine and usage requirements, and presenting the content that matches the usage requirements in the natural medicine systematic naming, structured and standardized natural medicine knowledge, natural medicine professional extended terminology, natural medicine relationship set and natural medicine related text of the target natural medicine in an associated manner.

[0009] According to the construction and use method of the natural medicinal material domain knowledge base in the embodiment of the present application, by defining the system naming rules of natural medicinal materials, and the system naming of natural medicinal materials generated under the constraints of the rules, the species origin, medicinal parts and processing methods of the natural medicinal materials can be reflected in a more standardized and structured manner, so that different types of natural medicinal materials can be distinguished more clearly, more clearly and more reliably with consistent standards. At the same time, the constructed natural medicinal material domain knowledge base also stores a variety of data sets such as structured and standardized natural medicinal material knowledge, natural medicinal material professional extended terms, natural medicinal material relationship sets and natural medicinal material related texts, so that the natural medicinal material domain knowledge base can meet the user's needs for obtaining natural medicinal material domain knowledge from multiple channels, multiple application angles and in a more convenient, efficient, accurate and intelligent manner. To a certain extent, it breaks the barriers to the acquisition, learning and application of natural medicinal material domain knowledge, and can significantly promote the standardized management and innovative application of natural medicinal material domain knowledge, thereby contributing to the progress of natural medicinal material academic research, new drug development, clinical application and international exchange.

[0010] 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. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In the drawings, which are not necessarily drawn to scale, the same reference numerals may describe similar components in different views. The same reference numerals with letter suffixes or different letter suffixes may represent different instances of similar components. The accompanying drawings illustrate various embodiments generally by way of example and not limitation, and together with the description and claims, serve to illustrate the disclosed embodiments. Such embodiments are illustrative and are not intended to be exhaustive or exclusive of the present apparatus or method.

[0012] FIG1 is a flow chart showing a method for constructing and using a natural medicinal material domain-specific knowledge base according to an embodiment of the present application.

[0013] FIG2( a ) shows an example of a natural medicinal material system naming of agricultural natural medicinal materials according to an embodiment of the present application.

[0014] FIG2( b ) shows an example of a natural medicinal material system naming for processing natural medicinal materials according to an embodiment of the present application.

[0015] FIG2( c ) shows a schematic diagram of naming elements of a natural medicinal material systematic name according to an embodiment of the present application.

[0016] FIG2( d ) shows a naming example of the natural medicinal material systematic names and natural medicinal material common names of ANMM and PNMM according to an embodiment of the present application.

[0017] FIG3( a ) shows a schematic diagram of an interactive interface for constructing a systematic naming system for natural medicinal materials according to an embodiment of the present application.

[0018] FIG3( b ) shows another schematic diagram of an interactive interface for constructing a systematic naming system for natural medicinal materials according to an embodiment of the present application.

[0019] FIG3( c ) shows a schematic diagram of an interactive interface with a knowledge page summary according to an embodiment of the present application.

[0020] FIG3( d ) shows a schematic diagram of an interactive interface with items requiring attention according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the technical solution of the present application, the present application is described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present application are further described in detail below in conjunction with the accompanying drawings and specific embodiments, but are not intended to limit the present application.

[0022] The words "first", "second" and similar terms used in this application do not indicate any order, quantity or importance, but are only used to distinguish. Words such as "include" or "comprise" mean that the elements before the word include the elements listed after the word, and do not exclude the possibility of also including other elements. The execution order of the various steps in the method described in this application with reference to the accompanying drawings is not intended to be limiting. As long as the logical relationship between the various steps is not affected, 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.

[0023] It should also be understood that the term "and / or" in this application is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Furthermore, the character " / " in this application generally indicates that the associated objects are in an "or" relationship.

[0024] Figure 1 shows a flow chart of a method for constructing and using a natural medicinal material domain-specific knowledge base according to an embodiment of the present application. As shown in Figure 1 , the natural medicinal material domain-specific knowledge base can be constructed and used according to steps 101 to 104 .

[0025] In step 101, first, based on the element entries of various natural medicinal materials including species origin, medicinal parts and processing methods, systematic nomenclatures (Systematic Nomenclature for Natural Medicinal Materials, SNNMM) of various natural medicinal materials can be generated through manual entry or through a natural medicinal material systematic naming algorithm, so that the systematic nomenclature of various natural medicinal materials conforms to the custom natural medicinal material systematic naming rules. The custom natural medicine systematic naming rules at least require that the systematic nomenclature of natural medicinal materials reflect the species origin, medicinal parts and processing methods of the natural medicinal materials.

[0026] It is worth noting that in this application, natural medicinal materials are divided into three different categories, namely:

[0027] Raw Natural Medicinal Materials (RNMM): RNMM refers to unprocessed NMM. When referring to natural medicinal materials based on species, RNMM refers to the species in its natural state.

[0028] Agricultural NMM (ANMM): These NMM are derived from primary production of RNMM. ANMM are generally regulated as agricultural products and are not intended for direct clinical use, pharmaceutical production, or as a direct pharmaceutical ingredient.

[0029] Processed NMM (PNMM): PNMM is the final product obtained after a specific processing of ANMM and is generally regulated as a drug. Upon approval, PNMM is eligible for clinical use, formulation development, or as a pharmaceutical ingredient.

[0030] In countries and regions such as China, due to the different application methods of ANMM and PNMM, the two often have different regulatory frameworks - the former is an agricultural product and the latter is a medicine. Historically, ANMM and the PNMM derived from them usually share the same name. For example, the agricultural product of the above-ground part of Artemisia annual and the further processed medicinal products are both called "Artemisiae annual Herba". This ambiguity in naming complicates the management of NMM. Therefore, in this application, especially for ANMM and PNMM, the systematic naming of various natural medicinal materials is required to at least reflect the species origin, medicinal part and preparation method of the natural medicinal material. In this way, the ambiguity of NMM naming can be effectively reduced, so that drugs can be better regulated, and the adverse consequences that may arise from the misuse of drugs can also be avoided.

[0031] The above-mentioned natural medicinal material systematic naming rules are a series of customized requirements for generating correct natural medicinal material systematic naming. In addition to requiring the natural medicinal material systematic naming to reflect the species origin, medicinal part and processing method of the natural medicinal material, it also stipulates specific naming rules and academic basis such as species origin, medicinal part, processing method, etc., the standard language used for each element, whether it is case sensitive, and if necessary, it can also include correct and incorrect demonstrations of natural medicinal material systematic naming under specific conditions, etc., which are not listed here one by one.

[0032] In step 102 , structured and standardized natural medicinal material knowledge, natural medicinal material professional extended terminology, natural medicinal material relationship sets, and natural medicinal material related texts of various natural medicinal materials may be constructed.

[0033] Among them, the natural medicinal materials related texts can be a collection of texts or hypertext materials from various authoritative natural medicinal materials classics and academic works; the structured and standardized natural medicinal materials knowledge of natural medicinal materials can be based on the above-mentioned natural medicinal materials related information from various authoritative natural medicinal materials classics and academic works, and is obtained after being structured and standardized in a general or customized document or hyperdocument format; the natural medicinal materials professional extended terminology is generated on the basis of natural medicinal materials terminology to meet the professional application needs of retrieval, translation, etc. of natural medicinal materials knowledge, such as coreference word annotation, multilingual translation, etc.; the relationship in the natural medicinal materials relationship set can be any relationship between various objects such as natural medicinal materials terms and entities, including but not limited to synonym relationships and inclusion relationships between two terms.

[0034] In step 103, the natural medicinal material domain-specific knowledge base is generated based on the generated systematic nomenclature of various natural medicinal materials, structured and standardized natural medicinal material knowledge, natural medicinal material professional extended terminology, natural medicinal material relationship set and natural medicinal material related text.

[0035] As an example only, when constructing a domain-specific knowledge base for natural medicinal materials according to an embodiment of the present application, for example, a document-based database such as MongoDB can be used, which has the advantages of both relational and non-relational databases. It can support the integration and structuring of diverse data sets, including but not limited to the systematic naming of the various natural medicinal materials mentioned above, structured and standardized natural medicinal material knowledge, professional extended terminology for natural medicinal materials, natural medicinal material relationship sets, and natural medicinal material-related texts, etc. Each data set can be retrieved and applied by users independently or in association with each other in different ways, such as from different entrances.

[0036] Furthermore, to ensure data reliability and accuracy, the data in these datasets must be manually reviewed before being added to the natural medicinal materials domain knowledge base as standard data. In other embodiments, for example, the reviewer and the original references used in the review can also be recorded and presented to ensure that they are cited.

[0037] In step 104, user operation information defining the target natural medicinal material and usage requirements can be obtained, and the systematic naming of the target natural medicinal material, structured and standardized natural medicinal material knowledge, natural medicinal material professional extended terminology, natural medicinal material relationship set and content matching the usage requirements in natural medicinal material-related texts are presented in an associated manner.

[0038] Specifically, the user operation information for defining the target natural medicinal materials and usage requirements may, for example, be a user using the Name application to systematically name a new target natural medicinal material that he or she wishes to add to the natural medicinal material domain knowledge base, or a user obtaining domain knowledge about the target natural medicinal material through an interactive dialogue in the Chat application interface, or a user inputting a translation requirement for terms or text containing target natural medicinal materials and / or domain knowledge related to the target natural medicinal materials in the Translate application interface for multilingual translation, etc. This application does not impose any specific restrictions on this.

[0039] According to the construction and use method of the natural medicinal material domain knowledge base in the embodiment of the present application, by defining the system naming rules of natural medicinal materials, and the system naming of natural medicinal materials generated under the constraints of the rules, the species origin, medicinal parts and processing methods of the natural medicinal materials can be reflected in a more standardized and structured manner, so that different types of natural medicinal materials can be distinguished more clearly, more clearly and more reliably with consistent standards. At the same time, the constructed natural medicinal material domain knowledge base also stores a variety of data sets such as structured and standardized natural medicinal material knowledge, natural medicinal material professional extended terms, natural medicinal material relationship sets and natural medicinal material related texts, so that the natural medicinal material domain knowledge base can meet the user's needs for obtaining natural medicinal material domain knowledge from multiple channels, multiple application angles and in a more convenient, efficient, accurate and intelligent manner. To a certain extent, it breaks the barriers to the acquisition, learning and application of natural medicinal material domain knowledge, and can significantly promote the standardized management and innovative application of natural medicinal material domain knowledge, thereby promoting the progress of natural medicinal material academic research, clinical application and international exchange.

[0040] In some embodiments, the systematic nomenclature of natural medicinal materials can specifically be composed of a triplet of [natural medicinal material ID, natural medicinal material systematic name, natural medicinal material generic name], wherein the natural medicinal material ID (NMM ID), the natural medicinal material systematic name (NMM Systematic Name, NMMSN), and the natural medicinal material generic name (NMM Generic Name, NMMGN) are all globally unique, so that agricultural natural medicinal materials and derived processed natural medicinal materials, as well as processed natural medicinal materials using different processing methods, can be distinguished from each other. In addition, the natural medicinal material systematic name of agricultural natural medicinal materials at least includes the species origin and the medicinal part; the natural medicinal material systematic name of the processed natural medicinal material at least includes the species origin, the medicinal part, and the processing method; wherein the species origin is expressed in Latin, and the medicinal part and processing method are expressed in English.

[0041] As mentioned above, the systematic nomenclature of natural medicinal materials in this application is mainly for ANMM and PNMM. Figures 2(a) and 2(b) respectively show examples of the systematic nomenclature of agricultural natural medicinal materials and processed natural medicinal materials according to the embodiments of this application. As shown in Figure 2(a), the NMM ID of the agricultural natural medicinal material is NMM-0001, the corresponding NMMSN is Artemisia annual Part-aerial, NMMSN-zh is Artemisia annua aerial part, NMMGN is Qing-hao, and NMMGN-zh is Artemisia annua. That is, the [natural medicinal material ID, natural medicinal material systematic name, natural medicinal material common name] triple is [NMM-0001, Artemisia annual Part-aerial, Qing-hao]. As shown in Figure 2(b), the NMM ID of the processed natural medicinal material is NMM-0002, the corresponding NMMSN is Artemisla annual Part-aerial Segmented, NMMSN-zh is the segmented aerial part of Artemisia annua, NMMGN is Qing-hao-duan, and NMMGN-zh is Artemisia annua segment. That is, the [natural medicinal material ID, natural medicinal material system name, natural medicinal material common name] triplet is [NMM-0002, Artemisla annual Part-aerial Segmented, Qing-hao-duan]. As can be seen from Figure 2(a) and Figure 2(b), the agricultural natural medicinal material [NMM-0001, Artemisla annual Part-aerial, Qing-hao] and the processed natural medicinal material derived from it [NMM-0002, Artemisla annual Part-aerial Segmented, Qing-hao-duan] have different NMM IDs, NMMSNs, and NMMGNs, so they can be completely distinguished from each other. In fact, each element in the triplet of each natural medicinal material is globally unique.

[0042] For a clearer explanation, FIG2(c) shows a schematic diagram of naming elements of the systematic name of natural medicinal materials according to an embodiment of the present application, and FIG2(d) shows naming examples of the systematic name of natural medicinal materials and the common name of natural medicinal materials of ANMM and PNMM according to an embodiment of the present application.

[0043] In Figure 2(c), La is represented in Latin, and En is represented in English. As can be seen from Figure 2(c), the systematic name of an agricultural natural medicinal material includes at least the species origin and the medicinal part, while the systematic name of a processed natural medicinal material includes at least the species origin, the medicinal part, and the processing method, with the species origin being represented in Latin. Optionally, the systematic names of agricultural natural medicinal materials and processed natural medicinal materials can also include their respective special descriptions. When these special descriptions are included, the systematic name of an agricultural natural medicinal material can typically be expressed as [species origin medicinal part special description], while the systematic name of a processed natural medicinal material can be expressed as [species origin medicinal part special description processing method]. For some natural medicinal materials, they must possess certain unique characteristics or undergo processing in a specific origin before they can be used as medicine. For these natural medicinal materials, English adjectives, adjective phrases, or appositives can be used to represent the special description. For other natural medicinal materials, when the authentic production area needs to be specifically identified, geographical terms can be used as special descriptions. The place of origin of authentic Chinese natural medicinal materials is typically the standard English name of the provincial capital of the People's Republic of China. In NMMSN-zh, "provincial capital standard abbreviation + production" is used as the Chinese equivalent. The special description section may also include other supplementary information, which is not listed here.

[0044] As shown in Figure 2(d), taking the natural medicinal materials with the species origin of Ephedra as an example, the species origin can be Ephedra sinica (plant grass ephedra), Ephedra intermedia (plant medium ephedra) or Ephedra equisetina (plant horsetail ephedra), and its medicinal part is Stem herbaceous (herbaceous stem), but the current naming convention tends to use a general term to refer to natural medicinal materials based on these different species. For example, the Chinese Pharmacopoeia collectively refers to them as "Ephedrae Herba (ephedra)". By using the natural medicinal material systematic nomenclature of the present application, the natural medicinal materials collectively referred to as Ephedrae Herba (ephedra) in the Chinese Pharmacopoeia can be distinguished and identified as three different natural medicinal materials according to their species origin or medicinal part. Their systematic names are: Ephedra sinica Stem-herbaceous (grass ephedra herbaceous stem), Ephedra intermedia Stem-herbaceous (middle ephedra herbaceous stem) and Ephedra equisetina (equisetina herbaceous stem); their common names are: Cao-ma-huang (grass ephedra), Zhong-ma-huang (middle ephedra), and Mu-zei-ma-huang (equisetina herbaceous stem). As shown in Figure 2(d), taking the natural medicinal material with the species origin of Curcuma as an example, its medicinal part can be Rhizome (rhizome) or Root tuber (tuber). For the medicinal part of Rhizome, there are two processing methods: Cleaned and Sliced. For the Cleaned processing method, there is also a special description of Freshly sliced. Therefore, for the same species origin, if at least one of the medicinal part, special description and processing method is different, the generated natural medicinal material system names will be different from each other. Therefore, even if the species origin and medicinal part are the same, natural medicinal materials processed using different processing methods can be distinguished from each other.

[0045] As shown in Fig. 2(d), similar to the systematic name of natural medicinal materials, the common names of each natural medicinal material are also globally unique and different from each other. Therefore, in the constructed special domain knowledge base of natural medicinal materials, any one of the [natural medicinal material ID, systematic name of natural medicinal material, common name of natural medicinal material] triple can retrieve a unique natural medicinal material. It can also be seen from Fig. 2(d) that using the systematic naming method of natural medicinal materials in this application, natural medicinal materials that are collectively called Curcumae Rhizoma (Zedoary Turmeric) in the Chinese Pharmacopoeia but are actually different from each other can be distinguished and identified as three different natural medicinal materials according to their species origin, medicinal part or processing method. Their common names of natural medicinal materials are respectively: Wen-yu-jin-pian (Tablet of Wenyujin), Guang-xi-e-zhu-pian (Tablet of Guangxi Zedoary Turmeric) and Dan-e-zhu-pian (Tablet of Single Zedoary Turmeric). Similarly, according to the systematic naming method of natural medicinal materials in the embodiments of this application, natural medicinal materials that are collectively called Curcumae Radix (Turmeric) in the Chinese Pharmacopoeia can be identified as four natural medicinal materials. Their common names of natural medicinal materials are respectively: Wen-yu-jin-gen-pian (Tablet of Wenyujin Root), Guang-xi-e-zhu-gen-pian (Tablet of Guangxi Zedoary Turmeric Root), Dan-e-zhu-gen-pian (Tablet of Single Zedoary Turmeric Root) and Jiang-huang-gen-pian (Tablet of Turmeric Root).

[0046] The natural medicinal material-related text in the special domain knowledge base of natural medicinal materials according to the embodiments of this application at least includes the Chinese Pharmacopoeia: 2020 Edition: Volume I. In the case of an update of the Chinese Pharmacopoeia version, the special domain knowledge base of natural medicinal materials in this application will also be updated accordingly, so as to ensure that the natural medicinal material-related text therein can include the updated implementation version of the Chinese Pharmacopoeia.

[0047] Correspondingly, the structured and standardized natural medicinal material knowledge in the special domain knowledge base of natural medicinal materials according to the embodiments of this application can also be obtained by structuring and standardizing the natural medicinal material-related information in the Chinese Pharmacopoeia: 2020 Edition: Volume I or the updated implementation version of the Chinese Pharmacopoeia, and covers all natural medicinal materials in the Chinese Pharmacopoeia: 2020 Edition: Volume I or the updated implementation version of the Chinese Pharmacopoeia.

[0048] Therefore, compared with obtaining knowledge about natural medicinal materials from the Chinese Pharmacopoeia or other existing natural medicinal materials, the natural medicinal materials systematic nomenclature according to the embodiment of the present application can use any element in the [natural medicinal material ID, natural medicinal material systematic name, natural medicinal material common name] triple to more clearly distinguish between different types of natural medicinal materials. In particular, it can avoid the confusion that may be caused by the fact that the same medicinal material name actually corresponds to multiple different species origins and / or preparation methods. This is of great significance for the research in related fields such as traditional Chinese medicine and the use of natural medicinal materials. In particular, it can eliminate the barriers caused by the names of natural medicinal materials for junior personnel who are not deeply involved in this field.

[0049] The construction method of the natural medicinal material naming system is described in detail below with reference to FIG3(a) to FIG3(d).

[0050] Figure 3 (a) shows a schematic diagram of an interactive interface for constructing a natural medicinal material system naming according to an embodiment of the present application. As shown in Figure 3 (a), the construction and use method of the natural medicinal material domain knowledge base according to an embodiment of the present application supports interaction with users through the web page of the website, and provides naming element entries including species base source, medicinal part, special description and processing method on the interactive interface 300 of the web page. In some embodiments, entries such as natural medicinal material types can also be provided to users on the interactive interface 300, so that users can use such as drop-down boxes to specify the type of natural medicinal material, including ANMM-Plant (agricultural natural medicinal material-plant medicine), ANMM-Animal (agricultural natural medicinal material-animal medicine), ANMM-Fungal (agricultural natural medicinal material-fungal medicine), ANMM-Algal (agricultural natural medicinal material-algae medicine), PNMM (processed natural medicinal material), etc. The options of specific natural medicinal material types can be set according to the actual situation of the current development of the natural medicinal material field, and this application does not limit this.

[0051] Furthermore, the element information corresponding to each named element entered by the user can be received based on the interactive interface 300, and the natural medicinal material systematic naming algorithm can be used to construct a natural medicinal material systematic naming that matches the element information corresponding to each named element.

[0052] Figure 3(b) shows another schematic diagram of an interactive interface for constructing a systematic naming of natural medicinal materials according to an embodiment of the present application. In Figure 3(b), in the interactive interface 300, the text box that receives the user's input of each naming element information can provide the user with automatic completion options, so that the user can reduce the manual input content by selecting the automatic completion options, thereby more conveniently and accurately entering the various naming elements of the natural medicinal material systematic naming that they want to construct.

[0053] In some embodiments, the webpage where the interactive interface 300 is located supports switching between different display modes. In addition to the Chinese display mode shown in Figures 3(a) and 3(b), other supported display modes may include, for example, at least an English display mode, an English-Chinese display mode, and a Chinese-English display mode. Display modes for other languages ​​and / or other comparison modes may also be added as needed, which is not limited in this application. In different display modes, display items such as species origin, medicinal part, special description, preparation method, and natural medicinal material type will be prompted in different languages / multi-language comparison modes, thus meeting the needs of users with different language usage habits.

[0054] It is worth noting that the interactive interface 300 shown in Figures 3(a) to 3(d) can be provided to the builders of the natural medicinal materials domain knowledge base during the initial construction phase, or it can be provided to users of the natural medicinal materials domain knowledge base such as medical researchers, so that they can try to add new natural medicinal materials discovered by them to the natural medicinal materials domain knowledge base.

[0055] If the natural medicinal material systematic naming is successfully constructed, a natural medicinal material information input box (not shown) can be further presented to the user on the interactive interface 300. Additionally or optionally, a natural medicinal material information input box can be presented to the user on a knowledge page (not shown) corresponding to the natural medicinal material systematic naming, so that the user can fill in the natural medicinal material information associated with the natural medicinal material systematic naming in text form or according to the first grammatical rule. After the user submits the information, the natural medicinal material information is reviewed. There is no restriction on the content of the natural medicinal material information, but when reviewing the natural medicinal material information submitted by the user, it should first be checked whether the information has new information that has not yet been included in the natural medicinal material domain knowledge base. If so, it is necessary to confirm whether the new information has a clear reference basis, that is, whether there is relevant reliable literature citation.

[0056] In some embodiments, the natural medicinal material systematic nomenclature submitted by the user can be successfully constructed, but the natural medicinal material systematic nomenclature is already included in the existing natural medicinal material domain-specific knowledge base. In this case, the following operations can be performed:

[0057] First, a knowledge page summary associated with the natural medicinal material systematic nomenclature can be presented to the user on the interactive interface 300, so that the user can view detailed information about the natural medicinal material systematic nomenclature by clicking on the knowledge page summary. FIG3(c) shows a schematic diagram of an interactive interface with a knowledge page summary according to an embodiment of the present application. As shown in FIG3(c), the user can click "Expand" below the knowledge page summary to view detailed information about the natural medicinal material systematic nomenclature and its corresponding natural medicinal material.

[0058] In other embodiments, a natural medicinal material information input box (not shown) may be presented to the user on the interactive interface 300 so that the user can enter and submit natural medicinal material information associated with the natural medicinal material systematic nomenclature in text form or according to the first grammatical rule. Furthermore, the natural medicinal material information submitted by the user needs to be reviewed to always maintain the credibility and accuracy of the knowledge and information in the natural medicinal material domain knowledge base. Generally, the review of natural medicinal material information requires manual participation, that is, manual or semi-manual review is performed.

[0059] In other embodiments, if it is determined that the natural medicinal material systematic nomenclature is not yet included in the natural medicinal material domain-specific knowledge base and has passed manual review, the natural medicinal material information is associated with the natural medicinal material systematic nomenclature and is included in the natural medicinal material domain-specific knowledge base. For example, the natural medicinal material information can be converted into structured and standardized natural medicinal material knowledge, and the structured and standardized natural medicinal material knowledge is associated with the natural medicinal material systematic nomenclature and is included in the natural medicinal material domain-specific knowledge base.

[0060] More specifically, as an example only, the natural medicinal material information can be converted into natural medicinal material knowledge in a customized multilingual Markdown format, wherein the natural medicinal material professional extended terms in the natural medicinal material knowledge in the multilingual Markdown format are co-referenced and annotated with their corresponding co-referential subjects.

[0061] Multilingual Markdown (MLMD) is a new, customized Markdown syntax designed specifically for multilingual documents. It can organize and embed content in multiple languages ​​in parallel in a single document to achieve parallel comparison, unified management and optimized display. This method not only makes document writing and editing more convenient, but also provides a structured solution for processing and analyzing multilingual data. Since MLMD has good versatility, it can not only adapt to the needs of coreference annotations of natural medicinal materials domain knowledge websites, switching display of Chinese-English / English-Chinese / Chinese / English or other multilingual display modes, but can also be applied to other application scenarios, including but not limited to multilingual content management, internationalization and localization project management, machine translation, etc. MLMD has complete grammatical rules, and in this application, only coreference annotations as its core grammar are illustrated.

[0062] The core linguistic principle of coreference annotation grammar is coreference agreement. That is, when we understand that a certain word in a language refers to a certain inherent concept or entity, we actually understand that the word is essentially a coreference to a certain inherent concept or entity. Take the following sentences (1) to (3) as an example:

[0063] (1) Shennong is considered by the Chinese to be the founder of medicine.

[0064] (2) Emperor Yan is considered by the Chinese to be the founder of medicine.

[0065] (3)Shennong is regarded as the founder of medicine and pharmacy by Chinese people.

[0066] For those with some background knowledge, the three sentences above, regardless of whether the nouns used are "Shennong," "Yandi," or "Shennong," can all be understood to refer to the same historical figure: Shennong. However, those without relevant knowledge might interpret them as three distinct concepts. The specially designed coreference annotation grammar in MLMD is designed to help users easily annotate coreference relationships in text, facilitating human understanding and, in machine translation and text processing, enabling machines to better understand the meaning of text.

[0067] The specific syntax of coreference annotation in MLMD is as follows:

[0068] Use the double bracket [[]] syntax. Basic coreference annotations include the following two forms:

[0069] 1. When a word and its reference are consistent: [[word reference]]

[0070] 2. When a word and its reference are inconsistent: [[word reference|word display]]

[0071] According to the above grammar, the above sentences (1) to (3) can be annotated as follows:

[0072] (1) Shennong is considered by the Chinese to be the founder of medicine.

[0073] (2) Shennong is considered by the Chinese to be the founder of medicine.

[0074] (3)[[Shennong|Shennong]]is regarded as the founder of medicine and pharmacy by Chinese people.

[0075] This shows that Shennong serves as the subject of the concept "Shennong," while Yandi and Shennong serve as coreferences of the concept. In this case, Shennong can be called the coreference subject of all coreferences of the concept "Shennong." Through the above coreference annotation, even those without relevant knowledge can understand that these three sentences are actually referring to the same person, "Shennong."

[0076] In the natural medicinal material knowledge converted into the multilingual Markdown format, the natural medicinal material professional extended terminology can also use the above-mentioned coreference annotation grammar to perform coreference annotation with its corresponding coreference subject, for example, taking the following sentences (4) and (5) as examples:

[0077] (4) Artificial intelligence empowers the modernization of traditional Chinese medicine.

[0078] (5) Artificial intelligence empowers the modernization of [[Traditional Chinese Medicine|Traditional Chinese Medicine]]

[0079] Since the connotations of Traditional Chinese Medicine and Traditional Chinese Medicine in the above sentences (4) and (5) are essentially the same, Traditional Chinese Medicine can be co-referenced to Traditional Chinese Medicine, thereby achieving a unified annotation of the extended terminology of natural medicinal materials. Therefore, after completing the co-reference annotation, when sentence (4) is displayed in HTML, the co-reference hyperlink in the sentence will be "Traditional Chinese Medicine", while it actually points to the page of "Traditional Chinese Medicine".

[0080] In other embodiments, when annotating the natural medicinal material professional extended term corresponding to each natural medicinal material, the coreference subject it points to is the natural medicinal material ID of the natural medicinal material. As an example only, for example, Artemisia annua corresponds to the natural medicinal material with NMM ID NMM-0001, so Artemisia annua in sentence (6) can be coreference-annotated and converted into sentence (7):

[0081] (6) Artemisia annua is a natural medicinal material.

[0082] (7) [[NMM-0001|Artemisia annua]] is a natural medicinal material.

[0083] In addition, since the natural medicinal material professional extended terminology in the embodiment of the present application itself includes the translation of natural medicinal material terms in different languages, sentence (6) can include sentence (8) in addition to sentence (7) after coreference annotation:

[0084] (8)[[NMM-0001|Qing-hao]]is a kind of Natural Medicinal Material.

[0085] By using sentences (7) and (8), the requirements of cross-language coreference agreement and terminology standardization are met at the same time.

[0086] It can be seen that the natural medicinal material knowledge converted into a customized multilingual Markdown format, due to its coreference annotation of coreference subjects, not only makes information retrieval more standardized, but also improves the accessibility of natural medicinal material knowledge in research and application, thereby further expanding the potential of natural medicinal materials in future clinical applications and new drug development.

[0087] In some other embodiments, when it is determined that the natural medicinal material systematic nomenclature is already included in the natural medicinal material domain-specific knowledge base, it is further determined whether the natural medicinal material information contains new information that has not yet been included in the natural medicinal material domain-specific knowledge base. After the new information that has not yet been included passes manual review, the natural medicinal material information is associated with the natural medicinal material systematic nomenclature and is included in the natural medicinal material domain-specific knowledge base.

[0088] Correspondingly, in the case that the new information that has not yet been included fails to pass manual review, review opinions can be provided to the user on the interactive interface, or review opinions can be provided to the user on the interactive interface and the natural medicinal material information can be returned to the user so that the user can modify the natural medicinal material information and submit it again.

[0089] The natural medicinal material system naming rules according to the embodiment of the present application include at least one rule for generating items requiring attention, such as multi-species origin naming rules and multi-medicinal part naming rules. When the natural medicinal material system naming is successfully constructed, but its construction process involves related rules and therefore includes one or more items requiring attention, the items requiring attention can be presented to the user on the interactive interface 300. Figure 3(d) shows a schematic diagram of an interactive interface with items requiring attention according to an embodiment of the present application. As shown in Figure 3(d), the user is prompted with various items requiring attention encountered during the natural medicinal material system naming process, such as a warning such as "Multiple species origins detected". The manner and location of the presentation of the items requiring attention are not specifically limited in this application, as long as they can serve to prompt the user with relevant information.

[0090] In some embodiments, the web page where the interactive interface 300 is located also provides collection, download and reference options, so that the user can add the natural medicinal material knowledge presented on the web page to the user's private profile, or download the original data associated with the natural medicinal material knowledge, or reference the page of natural medicinal material knowledge presented on the web page.

[0091] According to the embodiment of the present application, the natural medicinal material relationships in the natural medicinal material relationship set in the natural medicinal material domain knowledge base can be represented as manually annotated [source object (Source), relationship (Relation), target object (Target)] triples, wherein the relationship includes at least one of a synonym relationship, an inclusion relationship, a derived / superior relationship, a derived / subordinate relationship, and a peer relationship.

[0092] As an example only, synonym relationships include: [Traditional Chinese Medicine, Synonym (Synonym), Chinese Medicine]; inclusion relationships include: [natural medicinal materials, inclusion, processed natural medicinal materials]; derived / superior relationships include: [Artemisia annua, derived / superior, plant Artemisia annua]; derived / subordinate relationships include: [Artemisia annua, derived / subordinate, Artemisia annua segment]; peer relationships include: [Ginseng root, peer, ginseng leaf].

[0093] In addition, the source object and the target object can be nouns and terms in different languages, respectively. For example, a synonym relationship can also include [natural medicinal material, cross-language synonym, Natural Medicinal Material], etc.

[0094] In other embodiments, the natural medicinal materials domain knowledge base according to the embodiments of the present application may also include other data sets, and the present application does not limit this. As long as it uses unified standard NMM ID, NMMSN and NMMGN, and annotation method based on coreference subjects, it can be unified managed and jointly applied with existing data sets.

[0095] 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., solutions that intersect various embodiments), adaptations, or changes. The elements in the claims are to be interpreted broadly based on the language employed in the claims and are not limited to the examples described in this specification or during the prosecution of this application, which examples are to be interpreted as non-exclusive. Therefore, this specification and examples are intended to be considered as examples only, with the true scope and spirit being indicated by the following claims and the full scope of their equivalents.

[0096] The above description is intended to be illustrative rather than restrictive. For example, the above examples (or one or more of their solutions) can be used in combination with each other. For example, those 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 can be grouped together to simplify the 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 specific disclosed embodiment. Thus, the following claims are incorporated into the specific embodiments as examples or embodiments, wherein each claim is independently a separate embodiment, and it is considered that these embodiments can be combined with each other in various combinations or arrangements. The scope of the present invention should be determined with reference to the appended claims and the full scope of equivalents to which these claims are entitled.

[0097] The above embodiments are merely exemplary embodiments of the present application and are not intended to limit the present invention. The scope of protection of the present invention is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present invention within the spirit and scope of protection of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the scope of protection of the present invention.

Claims

1. A method for constructing and using a natural medicinal material domain knowledge base, characterized in that: The steps include: Based on the element entries including species origin, medicinal parts and processing methods of various natural medicinal materials, the natural medicinal material systematic names of various natural medicinal materials are generated through manual input or through the natural medicinal material systematic naming algorithm, so that the natural medicinal material systematic naming conforms to the self-defined natural medicinal material systematic naming rules, and the self-defined natural medicine systematic naming rules at least require that the natural medicinal material systematic naming reflects the species origin, medicinal parts and processing methods of the natural medicinal material; Construct structured and standardized natural medicinal material knowledge, natural medicinal material professional extended terminology, natural medicinal material relationship set and natural medicinal material related texts for various natural medicinal materials; Generate the natural medicinal material domain-specific knowledge base based on the generated natural medicinal material systematic nomenclature, structured and standardized natural medicinal material knowledge, natural medicinal material professional extended terminology, natural medicinal material relationship set and natural medicinal material related text of various natural medicinal materials; and Obtain user operation information that defines the target natural medicinal material and usage requirements, and present the target natural medicinal material's natural medicinal material system nomenclature, structured and standardized natural medicinal material knowledge, natural medicinal material professional extended terminology, natural medicinal material relationship set, and content matching the usage requirements in natural medicinal material-related texts in an associated manner.

2. The method of construction and use according to claim 1, characterized in that: The natural medicinal material systematic naming is composed of a triplet of [natural medicinal material ID, natural medicinal material systematic name, natural medicinal material common name], wherein the natural medicinal material ID, the natural medicinal material systematic name and the natural medicinal material common name are all globally unique, so that agricultural natural medicinal materials and derived processed natural medicinal materials, as well as processed natural medicinal materials using different processing methods, can be distinguished from each other; The natural medicinal material systematic name of agricultural natural medicinal materials at least includes the species origin and medicinal parts; the natural medicinal material systematic name of processed natural medicinal materials at least includes the species origin, medicinal parts and processing methods; wherein the species origin is expressed in Latin.

3. The method of construction and use according to claim 2, characterized in that: The natural medicinal material system name of agricultural natural medicinal materials also includes special descriptions; the natural medicinal material system name of processed natural medicinal materials also includes special descriptions.

4. The method of construction and use according to any one of claims 1 to 3, characterized in that: The relevant texts on natural medicinal materials include at least the "Chinese Pharmacopoeia: 2020 Edition: Volume 1" or an updated and implemented version of the "Chinese Pharmacopoeia".

5. The method of construction and use according to any one of claims 1 to 3, characterized in that: The structured and standardized natural medicinal materials knowledge is obtained by structuring and standardizing the natural medicinal materials related information in the "Chinese Pharmacopoeia: 2020 Edition: Volume 1" or an updated and implemented version of the "Chinese Pharmacopoeia", and covers all natural medicinal materials in the "Chinese Pharmacopoeia: 2020 Edition: Volume 1" or an updated and implemented version of the "Chinese Pharmacopoeia".

6. The method of construction and use according to any one of claims 1 to 3, characterized in that: The construction and use methods further include: Interact with users through web pages of the website and provide entries of naming elements including species origin, medicinal parts, special descriptions and processing methods on the interactive interface of the web pages; Receive the element information corresponding to each named element filled in by the user, and use the natural medicinal material systematic naming algorithm to construct a natural medicinal material systematic naming that matches the element information corresponding to each named element.

7. The method of construction and use according to claim 6, characterized in that: The webpage supports switching between different display modes, wherein the display modes at least include a Chinese display mode, an English display mode, an English-Chinese display mode, and a Chinese-English display mode.

8. The method of construction and use according to claim 6, characterized in that: The construction and use methods further include: In the case where the natural medicinal material systematic nomenclature is constructed successfully, presenting a natural medicinal material information input box to the user on the interactive interface so that the user can fill in and submit the natural medicinal material information associated with the natural medicinal material systematic nomenclature in text form or according to the first grammatical rule; and Review the natural medicinal materials information submitted by the user.

9. The method of construction and use according to claim 6, characterized in that: The construction and use method further includes, when the natural medicinal material systematic nomenclature is successfully constructed and has been included in the natural medicinal material domain-specific knowledge base: Presenting a knowledge page summary associated with the natural medicinal material systematic nomenclature to the user on the interactive interface, so that the user can view detailed information of the natural medicinal material systematic nomenclature by clicking on the knowledge page summary; On the interactive interface and / or on the knowledge page corresponding to the natural medicinal material systematic nomenclature, a natural medicinal material information input box is presented to the user so that the user can fill in and submit the natural medicinal material information associated with the natural medicinal material systematic nomenclature in text form or according to the first grammatical rule; and Review the natural medicinal materials information submitted by the user.

10. The construction and use method according to claim 8 or 9, characterized in that: Reviewing the natural medicinal material information submitted by the user further includes: If it is determined that the natural medicinal material systematic nomenclature has not been included in the natural medicinal material domain-specific knowledge base and has passed manual review, the natural medicinal material information is included in the natural medicinal material domain-specific knowledge base in association with the natural medicinal material systematic nomenclature; or When it is determined that the natural medicinal material systematic nomenclature is already included in the natural medicinal material specific domain knowledge base, it is determined whether the natural medicinal material information contains new information that has not yet been included in the natural medicinal material specific domain knowledge base; after the new information that has not yet been included passes manual review, the natural medicinal material information is associated with the natural medicinal material systematic nomenclature and is included in the natural medicinal material specific domain knowledge base.

11. The method of construction and use according to claim 10, characterized in that: The construction and use method further includes, in the case where the new information that has not yet been included fails to pass manual review; Providing review opinions to the user on the interactive interface; or The user is provided with review opinions on the interactive interface and the natural medicinal material information is returned to the user so that the user can modify the natural medicinal material information and submit it again.

12. The method of construction and use according to claim 10, characterized in that: Incorporating the natural medicinal material information and the natural medicinal material systematic nomenclature into the natural medicinal material domain-specific knowledge base in association with each other further includes: The natural medicinal material information is converted into structured and standardized natural medicinal material knowledge, and the structured and standardized natural medicinal material knowledge is associated with the natural medicinal material systematic nomenclature and included in the natural medicinal material domain-specific knowledge base.

13. The method of construction and use according to claim 12, characterized in that: Converting the natural medicinal material information into structured and standardized natural medicinal material knowledge further includes: The natural medicinal material information is converted into natural medicinal material knowledge in a customized multilingual Markdown format, wherein the natural medicinal material professional extended terms in the natural medicinal material knowledge in the multilingual Markdown format are co-referenced and annotated with their corresponding co-referential subjects.

14. The method of construction and use according to claim 13, characterized in that: The co-referential subject of the natural medicinal material professional extended term corresponding to each natural medicinal material is the natural medicinal material ID of the natural medicinal material.

15. The method of construction and use according to claim 7, characterized in that: The natural medicinal material system naming rules include at least one rule for generating items to be noted, and the construction and use method further includes: In the case that the natural medicinal material systematic naming is successfully constructed but contains items requiring attention, the items requiring attention are presented to the user on the interactive interface.

16. The method of construction and use according to claim 7, characterized in that: The webpage provides collection, download and citation options so that the user can add the natural medicinal material knowledge presented on the webpage to the user's private profile, or download the original data associated with the natural medicinal material knowledge, or cite the page of natural medicinal material knowledge presented on the webpage.

17. The method of construction and use according to any one of claims 1 to 3, characterized in that: The natural medicinal material relationships in the natural medicinal material relationship set are represented as manually annotated [source object, relationship, target object] triples, wherein the relationship includes at least one of a synonym relationship, a containment relationship, a derived / superior relationship, a derived / subordinate relationship, and a peer relationship.

Images