Method and system for constructing traditional Chinese medicine knowledge graph based on AI semantic understanding

Abstract

The present invention provides a method and system for constructing a TCM knowledge graph based on AI semantic understanding, which realizes the systematic organization of TCM theoretical knowledge by efficiently extracting and constructing a TCM knowledge architecture from TCM classic literature data. Furthermore, through in-depth association analysis of each knowledge concept entity in the TCM knowledge architecture, not only the logical relationship between each knowledge entity is clarified, but also the specific TCM knowledge attribute characteristics of each associated knowledge entity are described in detail, thereby greatly enriching the content of the TCM knowledge graph. Finally, through the generation of graphical representation and visual display data flow, complex TCM knowledge becomes intuitive and easy to understand, providing data support for the inheritance, research and clinical application of TCM knowledge, and significantly improving the accessibility and practicality of TCM knowledge.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and system for constructing a traditional Chinese medicine knowledge graph based on AI semantic understanding. Background Art

[0002] Traditional Chinese Medicine (TCM) carries thousands of years of medical wisdom and practical experience. However, with the passage of time, the transmission and popularization of TCM knowledge faces unprecedented challenges. Traditional TCM learning relies primarily on master-apprentice instruction and the study of classic texts. While this approach can deeply transmit the essence of TCM, it is inefficient and, due to geographical and time constraints, hinders widespread adoption.

[0003] In recent years, the rapid development of information technology, particularly the rise of artificial intelligence (AI), has provided new opportunities for the inheritance and popularization of Traditional Chinese Medicine (TCM) knowledge. AI can mimic human intelligence and efficiently process and analyze large amounts of data, providing strong support for the systematic and structured organization of TCM knowledge. However, most TCM knowledge systems currently available remain at the level of simple information retrieval, lacking a deeper semantic understanding of TCM theory and analysis of knowledge associations.

[0004] As an effective knowledge representation method, TCM knowledge graphs can intuitively display the knowledge concept entities and their interrelationships in TCM theory in the form of graphs, helping users better understand and master TCM knowledge. However, how to construct an accurate and comprehensive TCM knowledge graph has always been an urgent problem to be solved in the field of TCM informatization. Summary of the Invention

[0005] In view of the above-mentioned problems, in combination with the first aspect of the present invention, an embodiment of the present invention provides a method for constructing a traditional Chinese medicine knowledge graph based on AI semantic understanding, the method comprising:

[0006] Acquire TCM classic literature data and construct a TCM knowledge architecture from the TCM classic literature data; the TCM classic literature data is a data source corresponding to TCM theory, the TCM knowledge architecture is a feature vector of the TCM knowledge graph to be constructed, and the TCM knowledge architecture includes one or more knowledge concept entities;

[0007] Performing association analysis on each knowledge concept entity in the TCM knowledge architecture to generate one or more associated knowledge entities corresponding to each knowledge concept entity in the TCM knowledge graph, as well as semantic relationship information and knowledge feature vector information corresponding to each of the one or more associated knowledge entities, wherein the semantic relationship information is the logical relationship between each associated knowledge entity and the knowledge concept entity, and the knowledge feature vector information is the specific TCM knowledge attribute characteristics represented by each associated knowledge entity;

[0008] Wandering through the TCM knowledge graph, based on the semantic relationship information and the knowledge feature vector information, graphically representing each associated knowledge entity, and generating a visual display data stream of the TCM knowledge graph.

[0009] On the other hand, an embodiment of the present invention also provides a system for constructing a traditional Chinese medicine knowledge graph based on AI semantic understanding, including a processor and a machine-readable storage medium, wherein the machine-readable storage medium is connected to the processor, the machine-readable storage medium is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the machine-readable storage medium to implement the above method.

[0010] Based on the above aspects, the embodiment of the present application realizes the systematic organization of TCM theoretical knowledge by efficiently extracting and constructing TCM knowledge architecture from TCM classic literature data. Furthermore, through in-depth correlation analysis of each knowledge concept entity in the TCM knowledge architecture, not only the logical relationship between each knowledge entity is clarified, but also the specific TCM knowledge attribute characteristics of each associated knowledge entity are described in detail, thereby greatly enriching the content of the TCM knowledge map. Ultimately, through the generation of graphical representation and visual display data flow, complex TCM knowledge becomes intuitive and easy to understand, providing data support for the inheritance, research and clinical application of TCM knowledge, and significantly improving the accessibility and practicality of TCM knowledge. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a schematic diagram of the execution flow of the method for constructing a traditional Chinese medicine knowledge graph based on AI semantic understanding provided by an embodiment of the present invention.

[0012] Figure 2 This is a schematic diagram of the hardware architecture of the TCM knowledge graph construction system based on AI semantic understanding provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0013] The present invention will be described in detail below with reference to the accompanying drawings. Figure 1 This is a flow chart of a method for constructing a traditional Chinese medicine knowledge graph based on AI semantic understanding provided by an embodiment of the present invention. The following is a detailed introduction to the method for constructing a traditional Chinese medicine knowledge graph based on AI semantic understanding.

[0014] Step S110: Acquire TCM classic literature data and construct a TCM knowledge architecture from the TCM classic literature data. The TCM classic literature data is the data source corresponding to TCM theory, and the TCM knowledge architecture is the feature vector of the TCM knowledge graph to be constructed, and the TCM knowledge architecture includes one or more knowledge concept entities.

[0015] In this embodiment, the server first retrieves classic TCM literature. For a TCM research institution, the server is connected to a database storing a wealth of TCM-related materials. This database contains a wide range of TCM literature sources, including digitized manuscripts or documents on traditional TCM diagnosis and treatment experience compiled over many years by TCM research and development teams. These documents contain many unique insights into TCM theory.

[0016] For example, a manuscript records a traditional treatment method for a specific disease in a mountainous area. This method involves understanding the changes in the human body's qi and blood under specific circumstances. This understanding extends and differs from the common traditional Chinese medicine theory of qi and blood. The server will also include this type of data in its acquisition scope.

[0017] After the server acquires this classical TCM literature, it begins constructing a TCM knowledge architecture. For example, suppose the server obtains a document on a regional TCM theory that mentions a unique concept of "qi" (qi), which has a unique connection to the human internal organs, differing from the commonly understood relationship between qi and internal organs in traditional TCM theory. The server extracts this unique "qi" concept as a knowledge concept entity. Meanwhile, another document mentions the relationship between a specific herbal preparation method and the human meridians. The server also extracts related elements, such as the herbal preparation method, the human meridians, and the relationship between them, as knowledge concept entities. As more literature data is analyzed, the server gradually constructs a TCM knowledge architecture. The knowledge concept entities in this architecture are interwoven, forming a complex network, like nodes in a larger network. Each node represents a knowledge concept entity. These knowledge concept entities cover various aspects, from specific illnesses and unique treatments to unique TCM theoretical concepts. Together, they constitute the feature vectors of the TCM knowledge graph to be constructed.

[0018] Step S120, performing association analysis on each knowledge concept entity in the traditional Chinese medicine knowledge architecture, generating one or more associated knowledge entities corresponding to each knowledge concept entity in the traditional Chinese medicine knowledge graph, and semantic relationship information and knowledge feature vector information corresponding to each associated knowledge entity in the one or more associated knowledge entities, wherein the semantic relationship information is the logical relationship between each associated knowledge entity and the knowledge concept entity, and the knowledge feature vector information is the specific traditional Chinese medicine knowledge attribute characteristics represented by each associated knowledge entity.

[0019] In this embodiment, the server begins to perform an association analysis on each knowledge concept entity in the constructed traditional Chinese medicine knowledge architecture. Take the previously mentioned special "qi" concept knowledge concept entity as an example. The server will first analyze the overall structure of the traditional Chinese medicine knowledge architecture. In this architecture, the special concept of "qi" has various potential connections with other knowledge concept entities. From the overall structure, the area where the concept of "qi" is located may have an indirect connection with the area of ​​some special diseases, because some documents mention that changes in this special "qi" may cause some special diseases. At the same time, there may also be a connection between the concept of "qi" and certain special acupuncture points of the human body. Although this connection is not clearly stated in traditional Chinese medicine theory, there are related hints in these unique documents.

[0020] The server then determines the initial semantic domain scope of the conceptual knowledge entity of "qi". This scope may cover aspects such as human physiological functions and the inducing factors of special diseases. Next, the server searches and filters the data of classic Chinese medicine literature based on this initial semantic domain scope. During the screening process, a collection of text descriptions related to the initial semantic domain scope will be mined. For example, in a document on the treatment of local special diseases, there is a description like this: "When this qi flows backward, the heart meridian is not smooth, and this symptom is seen in those who have a dull pain between the eyebrows." This description is included in the text description collection.

[0021] When parsing this text description set, the server analyzes the basic logical relationships between the grammatical structural elements within the sentence, as well as the Traditional Chinese Medicine (TCM) connotations of each word and phrase. In the sentence above, there's a causal relationship between "reverse flow of qi" and "sluggish heart pulse," and a causal relationship between "sluggish heart pulse" and "dull pain between the eyebrows." These are the basic logical relationships between the grammatical structural elements. From a TCM perspective, "reverse flow of qi" here means that this particular type of qi flows in the opposite direction of normal, "sluggish heart pulse" means that the flow of qi and blood in the heart's meridians is blocked, and "dull pain between the eyebrows" is a symptom of a disease. Based on these relationships and connotations, the server identifies potential associated elements related to the concept of "qi," such as "heart pulse," "brows," and "reverse flow of qi," and generates a list of these potential associated elements.

[0022] The server categorizes this list of potentially related elements based on the logic and classification criteria of the Traditional Chinese Medicine (TCM) knowledge system. The element "heart meridian" falls into the category of human meridians; "brow center" falls into the category of body parts; and "reverse qi" falls into the category of specific qi states. Then, for each category, the server evaluates the closeness of the element's association with the knowledge concept entity "qi." When evaluating the closeness of the association between "heart meridian" and "qi," based on the causal relationship in TCM theory (since reverse qi can cause heart meridian obstruction), it is determined that the two are closely related and consistent with TCM knowledge logic. As for "brow center," since it is the site of symptoms caused by reverse qi leading to heart meridian obstruction, it also has a certain association with "qi." After screening, these elements are all deemed to be closely related and consistent with TCM knowledge logic, thus generating a subset of valid related elements.

[0023] Each valid associated element in the valid associated element subset is determined as an associated knowledge entity. For example, "heart pulse", "eyebrow center", and "retrograde qi" all become associated knowledge entities associated with the conceptual knowledge entity of "qi". According to the basic logical relationship between the grammatical structure components in the text description set, the semantic relationship information between each associated knowledge entity and the knowledge concept entity is constructed. The semantic relationship information between "heart pulse" and "qi" is "retrograde qi will cause poor heart pulse", which is a causal relationship; the semantic relationship information between "eyebrow center" and "qi" is "retrograde qi will cause poor heart pulse and then cause dull pain in the eyebrow center", which is an indirect causal relationship; the semantic relationship information between "retrograde qi" and "qi" itself is "it is a special state of qi". At the same time, for each associated knowledge entity, the knowledge feature vector information of the associated knowledge entity is extracted based on the attribute feature definition in the traditional Chinese medicine knowledge system. For the "heart meridian", its knowledge feature vector information may include the meridian system to which it belongs, the characteristics of the circulation of qi and blood, etc.; for the "eyebrow center", its knowledge feature vector information may include its position characteristics on the human head, its relationship with the surrounding meridian acupoints, etc.; for the "retrograde qi", its knowledge feature vector information may include the factors that cause its retrograde movement, the impact of retrograde movement on other aspects of the human body, etc.

[0024] The server also performs similar association analysis for other knowledge concept entities within the TCM knowledge architecture, such as the previously mentioned herbal preparation method knowledge concept entity. Assume that this herbal preparation method involves a unique combination of steaming and boiling, with a special connection to the human meridians. By analyzing the overall architecture structure and contextual relationships, the server determines that its initial semantic domain likely involves aspects such as the transformation of herbal medicinal properties and their effects on the human meridians. By searching and filtering literature data, a collection of text descriptions containing statements such as "This preparation method allows the medicinal properties of the herb to enter the kidney meridian and open up the lower Jiao meridians" is obtained. These sentences are parsed to identify potential association elements such as "kidney meridian," "lower Jiao meridian," and "herbal medicinal property transformation." After classifying and evaluating the closeness of the associations, a subset of valid association elements is obtained. "Kidney Meridian", "Lower Burner Meridian", and "Transformation of Herbal Medicinal Properties" are identified as associated knowledge entities, and semantic relationship information is constructed (such as "This preparation method transforms the medicinal properties of herbs and allows them to enter the kidney meridian and open the lower burner meridians"), and knowledge feature vector information of each associated knowledge entity is extracted (such as the meridian direction of the "Kidney Meridian" and its connection with the internal organs, the scope and functional characteristics of the "Lower Burner Meridian", the transformation conditions of the "Transformation of Herbal Medicinal Properties", and the characteristics of the medicinal properties after transformation).

[0025] Step S130, walk the TCM knowledge graph, and based on the semantic relationship information and the knowledge feature vector information, perform a graphical representation of each associated knowledge entity to generate a visual display data stream of the TCM knowledge graph.

[0026] In this embodiment, the server starts to walk through the constructed TCM knowledge graph. Assume that the walk starts from the special concept knowledge entity of "qi" and its associated knowledge entities in the previously constructed TCM knowledge graph. First, based on the semantic relationship information in each associated knowledge entity, the associated knowledge concept entity is determined. Taking the associated knowledge entity "qi retrograde" as an example, according to its semantic relationship information with "qi" "is a special state of qi", it can be determined that its associated knowledge concept entity is "qi". Then, the basic information of traditional Chinese medicine corresponding to the associated knowledge concept entity is obtained. For the knowledge concept entity "qi", its basic information of traditional Chinese medicine may include the normal operation law of qi in the human body, the source of qi, etc.

[0027] Based on the knowledge feature vector information and the basic Traditional Chinese Medicine information corresponding to the associated knowledge concept entities, the feature vector corresponding to the current display node in each associated knowledge entity is graphically represented to generate the current Traditional Chinese Medicine knowledge display node. For the associated knowledge entity "Qi Retrograde," combining its knowledge feature vector information (factors causing retrograde movement, its impact on other aspects of the human body, etc.) with the basic Traditional Chinese Medicine information about "Qi" (the normal operating rules of Qi in the human body, etc.), the relevant features of the "Qi Retrograde" node can be represented in the graph. For example, in the graph, this node may be displayed with a specific color (indicating an abnormal state), a specific shape (indicating its relationship to Qi), and some text description (such as the factors causing retrograde movement, etc.). This generates the current Traditional Chinese Medicine knowledge display node, which is part of the visual display data stream of the Traditional Chinese Medicine knowledge graph.

[0028] Next, the server continues to navigate the TCM knowledge graph, graphically representing the feature vector corresponding to the next display node. For example, upon reaching the associated knowledge entity "heart meridian," based on its semantic relationship with "qi" ("reverse flow of qi can cause poor heart meridian flow"), it determines its associated knowledge concept entity as "qi" and obtains basic TCM information about "qi." Then, combining the knowledge feature vector information of "heart meridian" (its meridian system, the characteristics of qi and blood circulation, etc.) with the basic TCM information about "qi," it represents the relevant features of the "heart meridian" node in the graph, such as using different line colors to indicate the state of qi and blood circulation (a lighter color might indicate weak qi and blood circulation due to reverse flow of qi), or using a specific line thickness to indicate its importance within the meridian system. This generates a new TCM knowledge display node. In this manner, the server continuously navigates the TCM knowledge graph, graphically representing the feature vectors corresponding to each display node. This completes the graphical representation of the feature vectors corresponding to each display node, generating a visual display data stream for the TCM knowledge graph. This visual display of the data stream is like a dynamic TCM knowledge map, showing the complex relationships and characteristics between TCM knowledge concept entities and their related knowledge entities from different perspectives, providing TCM researchers, practitioners, etc. with an intuitive and comprehensive display of the TCM knowledge system.

[0029] The process of walking from the herbal preparation method knowledge concept entity and its associated knowledge entities is similar. For example, starting from the associated knowledge entity "herbal medicinal property transformation," based on its semantic relationship information with herbal preparation methods, the associated knowledge concept entity is determined to be herbal preparation methods. Basic Traditional Chinese Medicine information about herbal preparation methods (such as the purpose of preparation and traditional operating procedures) is obtained. Combined with the knowledge feature vector information of "herbal medicinal property transformation" (such as the transformation conditions and the characteristics of the transformed medicinal properties), the characteristics of the "herbal medicinal property transformation" node are represented in the graph, such as using a specific icon to represent the transformation process and different colors to represent the type of medicinal property after transformation. Next, walking to the associated knowledge entity "kidney meridian," similarly determines the associated knowledge concept entity based on the semantic relationship information, obtains relevant basic Traditional Chinese Medicine information, and combines the knowledge feature vector information of the "kidney meridian" (such as the meridian direction and the connection with the internal organs) to represent the characteristics of the "kidney meridian" node in the graph, such as using a line to represent the meridian direction and the size of the node to indicate the closeness of the connection with the internal organs. This process is repeated repeatedly, ultimately completing the generation of the data stream for the visualization of the entire TCM knowledge graph.

[0030] Based on the above steps, the embodiment of the present application realizes the systematic organization of TCM theoretical knowledge by efficiently extracting and constructing TCM knowledge architecture from TCM classic literature data. Furthermore, through in-depth correlation analysis of each knowledge concept entity in the TCM knowledge architecture, not only the logical relationship between each knowledge entity is clarified, but also the specific TCM knowledge attribute characteristics of each associated knowledge entity are described in detail, thereby greatly enriching the content of the TCM knowledge map. Finally, through the generation of graphical representation and visual display data flow, complex TCM knowledge becomes intuitive and easy to understand, providing data support for the inheritance, research and clinical application of TCM knowledge, and significantly improving the accessibility and practicality of TCM knowledge.

[0031] In a possible implementation, before step S130, the method further includes:

[0032] Step A110: Acquire an adjustment instruction for the TCM knowledge graph. The adjustment instruction is instruction information for adjusting the TCM knowledge graph.

[0033] Step A120: Adjust the TCM knowledge graph based on the adjustment instruction to generate a target TCM knowledge graph.

[0034] Wherein, step S130 includes:

[0035] The target TCM knowledge graph is traversed, and each target-related knowledge entity in the target TCM knowledge graph is graphically represented based on target semantic relationship information and target knowledge feature vector information, thereby generating a visual display data stream of the TCM knowledge graph. The target semantic relationship information and target knowledge feature vector information correspond to each target-related knowledge entity.

[0036] In this embodiment, the server system of a TCM research institution receives adjustment instructions for the TCM knowledge graph from various sources. For example, a team of experts researching the TCM knowledge graph may send adjustment instructions to the server based on their research needs or new research findings. This adjustment instruction is intended to adjust the constructed TCM knowledge graph to better reflect the accuracy of TCM knowledge or to better align with specific research directions.

[0037] For example, if the expert team discovers new research on the relationship between this unique concept of "qi" and other elements, they will send adjustment instructions. For example, if they discover that a specific environmental factor has a previously undiscovered impact on the state of this "qi," and this impact involves a new human physiological reaction, this information will be compiled into adjustment instructions and sent to the server.

[0038] After receiving this adjustment instruction, the server begins to adjust the TCM knowledge graph based on this instruction, thereby generating a target TCM knowledge graph. If the adjustment instruction is a category knowledge adjustment instruction, for example, it is to adjust the TCM knowledge attribute characteristics corresponding to the previously mentioned "Qi Retrograde" associated knowledge entity. The server will obtain the target associated knowledge entity "Qi Retrograde" and the knowledge feature vector information to be adjusted from this category knowledge adjustment instruction. This knowledge feature vector information to be adjusted may be about the new conditions or impact results of "Qi Retrograde" under the influence of this special environmental factor. The server then obtains the target knowledge feature vector information corresponding to "Qi Retrograde" and updates the target knowledge feature vector information based on the knowledge feature vector information to be adjusted. For example, the original knowledge feature vector information about "Qi Retrograde" did not include the impact of special environmental factors. Now this new influencing factor and its related results are added to the knowledge feature vector information, thus completing the adjustment of this part of the TCM knowledge graph and generating the target TCM knowledge graph.

[0039] If the adjustment instruction is an architecture adjustment instruction, for example, an adjustment to the architecture of the traditional Chinese medicine knowledge graph, this architecture adjustment instruction may include at least one of associated knowledge entity expansion information, associated knowledge entity destruction information, and associated knowledge entity migration information.

[0040] If the architecture adjustment instruction includes associated knowledge entity expansion information, a first target associated knowledge entity is obtained from this associated knowledge entity expansion information. This is assuming it is a group associated knowledge entity within the knowledge section related to "qi," for example, a group associated knowledge entity related to a specific type of human physiological reaction related to "qi," as well as a target associated knowledge entity to be expanded. This target associated knowledge entity to be expanded may be the human body's reaction to a newly discovered specific substance related to this physiological reaction. Based on the logical relationship between the target associated knowledge entity to be expanded and the knowledge concept entity, the server determines the target knowledge concept entity to be expanded. This may be a human physiological regulation concept entity related to the specific concept of "qi." The server then performs association analysis on this target knowledge concept entity to generate a target associated knowledge entity to be expanded, for example, a new associated knowledge entity related to the human physiological regulation process related to the reaction of a specific substance. Finally, this target associated knowledge entity to be expanded is loaded into the first target associated knowledge entity of the TCM knowledge graph. After the adjustment, the category of the first target associated knowledge entity, if originally a category associated knowledge entity, may now be a group associated knowledge entity category. This completes the architecture adjustment of the TCM knowledge graph, generating the target TCM knowledge graph.

[0041] If the architecture adjustment instruction includes associated knowledge entity destruction information, a second target associated knowledge entity is retrieved from this associated knowledge entity destruction information. This second target associated knowledge entity is assumed to be a previously identified knowledge entity related to the concept of "qi" that was proven to be incorrectly associated, such as a knowledge entity associated with a non-existent physiological phenomenon that was mistakenly believed to be directly related to "qi." The server then destroys this second target associated knowledge entity from the TCM knowledge graph, thereby completing the architecture adjustment of the TCM knowledge graph and generating the target TCM knowledge graph.

[0042] If the architecture adjustment instruction includes associated knowledge entity migration information, the third target associated knowledge entity and the fourth target associated knowledge entity are obtained from this associated knowledge entity migration information. It is assumed that the third target associated knowledge entity is an associated knowledge entity related to the special "qi" in a certain local theory, and the fourth target associated knowledge entity is an associated knowledge entity in another related but different theory, and they are determined by the knowledge section corresponding to the traditional Chinese medicine knowledge graph. There is no derivative relationship between these two associated knowledge entities. The server migrates these two associated knowledge entities in the traditional Chinese medicine knowledge graph, such as adjusting their positions in the graph to make them more consistent with the logical relationship of traditional Chinese medicine knowledge, completing the architecture adjustment of the traditional Chinese medicine knowledge graph and generating the target traditional Chinese medicine knowledge graph.

[0043] After completing these adjustments, the server begins to roam the target TCM knowledge graph, and based on the target semantic relationship information and target knowledge feature vector information, it graphically represents each target-related knowledge entity in the target TCM knowledge graph, and generates a visual display data stream of the TCM knowledge graph.

[0044] Starting with the previously adjusted, specialized portion of the knowledge graph related to "qi," the walk begins. Taking the target associated knowledge entity "qi nixing" as an example, based on its corresponding target semantic relationship information (such as its newly adjusted relationships with other elements) and target knowledge feature vector information (including updated information such as new influencing factors), the walk identifies the associated knowledge concept entity as "qi." The corresponding basic Traditional Chinese Medicine information for "qi" is then obtained. This information is then combined to graphically represent the feature vector corresponding to the current display node in the target associated knowledge entity "qi nixing," generating the current TCM knowledge display node. This node is part of the TCM knowledge graph visualization data stream. The walk continues in this manner, graphically representing the feature vector corresponding to the next display node, until all feature vectors corresponding to each display node are graphically represented. This completes the graphical representation and generates the TCM knowledge graph visualization data stream. This process is like touring a newly constructed and adjusted TCM knowledge building, accurately displaying each knowledge entity according to the new rules and information, forming an accurate, comprehensive, and responsive TCM knowledge graph visualization data stream.

[0045] In a possible implementation, the adjustment instruction is a category knowledge adjustment instruction, which is instruction information for adjusting the TCM knowledge attribute features corresponding to the associated knowledge entities in the TCM knowledge graph.

[0046] Step A120 includes:

[0047] From the category knowledge adjustment instruction, target associated knowledge entity and knowledge feature vector information to be adjusted are obtained. The target associated knowledge entity is the associated knowledge entity in the TCM knowledge graph whose knowledge feature is to be adjusted.

[0048] Obtain target knowledge feature vector information corresponding to the target associated knowledge entity.

[0049] Based on the knowledge feature vector information to be adjusted, the target knowledge feature vector information is updated, thereby completing the adjustment of the TCM knowledge graph and generating the target TCM knowledge graph.

[0050] In this embodiment, in a TCM research institution, the server is responsible for maintaining and adjusting the TCM knowledge graph. When the received adjustment instruction is a category knowledge adjustment instruction, it means that the TCM knowledge attribute features corresponding to the associated knowledge entities in the TCM knowledge graph need to be adjusted.

[0051] Taking the previously mentioned special "Qi"-related TCM knowledge graph as an example, suppose new research results or deeper excavation of ancient texts lead to the discovery of new information about the associated knowledge entity "Qi Retrograde." In this case, the server retrieves the target associated knowledge entity "Qi Retrograde" and the feature vector information of the knowledge to be adjusted from the category knowledge adjustment instruction. This feature vector information may stem from new research findings, such as the discovery that under a certain dietary structure, "Qi Retrograde" will manifest differently and have different effects on other human functions. These new manifestations and effects are the feature vector information of the knowledge to be adjusted.

[0052] The server then retrieves the target knowledge feature vector information corresponding to "Qi Retrograde." This target knowledge feature vector information is the knowledge attribute characteristics of "Qi Retrograde" that already exist in the current TCM knowledge graph, such as the previously recorded information on the impact of "Qi Retrograde" on the circulation of Qi and blood, and the function of internal organs.

[0053] Next, based on the knowledge feature vector information to be adjusted, the target knowledge feature vector information is updated. The server integrates the newly discovered different manifestations and effects of "Qi Retrograde" under a special diet structure into the original target knowledge feature vector information. For example, the original target knowledge feature vector information only mentioned that "Qi Retrograde" can cause poor heart circulation, but now it has been added that under a special diet structure, "Qi Retrograde" will also affect the spleen and stomach transportation and transformation functions. At the same time, new content has been added to the manifestations of "Qi Retrograde", such as the possibility of new manifestations such as abdominal distension. Through such an update, the adjustment of the knowledge feature vector information of the associated knowledge entity "Qi Retrograde" is completed, thereby completing the adjustment of this part of the TCM knowledge graph and generating the target TCM knowledge graph.

[0054] For another example, for the associated knowledge entity "herbal medicinal property conversion" related to a special herbal preparation method, if a category knowledge adjustment instruction is received, the target associated knowledge entity "herbal medicinal property conversion" and the knowledge feature vector information to be adjusted are obtained from the instruction. Suppose new research finds that different storage environments have special effects on herbal medicinal property conversion, and the information related to this effect is the knowledge feature vector information to be adjusted. The server obtains the existing target knowledge feature vector information of "herbal medicinal property conversion", including the currently recorded conversion conditions, the medicinal property characteristics after conversion, etc. Then, based on the new knowledge feature vector information to be adjusted, the special effects of different storage environments on herbal medicinal property conversion are added to the target knowledge feature vector information. For example, the special changes that may occur in the medicinal property conversion of herbs stored in a humid environment during preparation are added. After the adjustment is completed, the target traditional Chinese medicine knowledge graph is generated.

[0055] This adjustment process based on category knowledge adjustment instructions enables the TCM knowledge graph to continuously absorb new knowledge content, more accurately reflect the connotation and extension of TCM knowledge, and provide more precise knowledge basis for TCM research, teaching, clinical practice and other aspects.

[0056] In a possible implementation, the adjustment instruction is an architecture adjustment instruction. The architecture adjustment instruction is instruction information for adjusting the architecture of the TCM knowledge graph.

[0057] Step A120 includes:

[0058] Based on the architecture adjustment instruction, the architecture of the TCM knowledge graph is adjusted to generate the target TCM knowledge graph. The architecture adjustment instruction includes at least one of associated knowledge entity expansion information, associated knowledge entity destruction information, and associated knowledge entity migration information.

[0059] Among them, the associated knowledge entity extension information is the feature vector for expanding the associated knowledge entity into the traditional Chinese medicine knowledge graph, the associated knowledge entity destruction information is the feature vector for destroying the associated knowledge entity from the traditional Chinese medicine knowledge graph, and the associated knowledge entity migration information is the feature vector for migrating the associated knowledge entity in the traditional Chinese medicine knowledge graph.

[0060] In this embodiment, taking the TCM knowledge graph portion related to the special "qi" as an example, if the architecture adjustment instruction includes associated knowledge entity expansion information, suppose that further research into ancient TCM texts discovers a new health-preserving exercise related to the special "qi." This exercise is closely linked to the flow of the special "qi" in the human body and is also associated with certain human meridian knowledge entities previously described in the graph. From the associated knowledge entity expansion information, the server retrieves a first target associated knowledge entity, such as a knowledge section on health-preserving exercises related to the special "qi" (this section can be considered a group associated knowledge entity), and a target associated knowledge entity to be expanded, i.e., a knowledge entity related to the newly discovered health-preserving exercise. Based on the logical relationship between the target associated knowledge entity and the knowledge concept entity (here, the special "qi"), the server determines the target associated knowledge entity to be expanded, such as a concept entity of the human body's essence, qi, and spirit that interacts with the special "qi" in the health-preserving exercise. The server then performs association analysis on this target associated knowledge entity to generate a target associated knowledge entity to be expanded, such as an associated knowledge entity related to the specific flow and changes of the essence, qi, and spirit in the new health-preserving exercise. Finally, the target-associated knowledge entity to be expanded is loaded into the first target-associated knowledge entity of the TCM knowledge graph. If the first target-associated knowledge entity was originally a category-associated knowledge entity, its category may become a group-associated knowledge entity category after loading, thus completing the expansion and adjustment of this part of the architecture.

[0061] If the architecture adjustment instruction includes information about the destruction of related knowledge entities, for example, in the knowledge graph related to a specific concept of "qi," if, after more rigorous verification, it is discovered that a related knowledge entity in the graph related to an ancient legend related to a specific concept of "qi" (for example, a related knowledge entity related to the influence of a specific "qi" on the human body by a mythical creature) does not conform to the scientific logic of Traditional Chinese Medicine (TCM), the server will retrieve the second target related knowledge entity from the related knowledge entity destruction information, namely the related knowledge entity related to the ancient legend, and then destroy this second target related knowledge entity from the TCM knowledge graph, thereby adjusting this part of the architecture.

[0062] If the architecture adjustment instruction includes related knowledge entity migration information, for example, in the knowledge graph section related to the special concept of "qi," there is a related knowledge entity about the special concept of "qi" in local folk remedies, and another related knowledge entity about the concept in orthodox Chinese medicine theory. These two related knowledge entities do not have a derivative relationship, but are both in the corresponding knowledge sections of the Chinese medicine knowledge graph. The server obtains the third target related knowledge entity (the related knowledge entity in folk remedies) and the fourth target related knowledge entity (the related knowledge entity in orthodox Chinese medicine theory) from the related knowledge entity migration information, and then migrates these two related knowledge entities in the Chinese medicine knowledge graph. For example, the related knowledge entity in folk remedies is migrated to a more logical knowledge section related to folk medicine, and the related knowledge entity in orthodox Chinese medicine theory is migrated to a section that better reflects its theoretical core, making the architecture of the Chinese medicine knowledge graph more reasonable.

[0063] Similar operations are used to adjust the architecture of other parts of the TCM knowledge graph, such as herbal preparation methods. For example, in the knowledge graph related to herbal preparation methods, if new herbal preparation tools are found to be associated with existing preparation methods and herbal knowledge entities, the architecture can be expanded by expanding the associated knowledge entity information; if an incorrect preparation-related knowledge entity is found in the previous graph (such as a knowledge entity that mistakenly believes that an irrelevant substance is involved in the preparation process), the architecture can be adjusted by destroying the associated knowledge entity information; if the location of the associated knowledge entities of the preparation methods in different regional theories is unreasonable, adjustments can be made by migrating the associated knowledge entity information. Through these operations, the architecture of the TCM knowledge graph is adjusted based on the architecture adjustment instructions, and the target TCM knowledge graph is generated, so that the architecture of the TCM knowledge graph reflects the TCM knowledge system more scientifically, reasonably, and accurately.

[0064] In a possible implementation, when the architecture adjustment instruction includes the associated knowledge entity extension information, adjusting the architecture of the TCM knowledge graph based on the architecture adjustment instruction to generate the target TCM knowledge graph includes:

[0065] A first target associated knowledge entity and a to-be-expanded associated knowledge entity are obtained from the associated knowledge entity extension information, wherein the first target associated knowledge entity is a category associated knowledge entity or a group associated knowledge entity in the TCM knowledge graph for which feature vector expansion is to be performed. The to-be-expanded associated knowledge entity is an initial associated knowledge entity to be loaded into the first target associated knowledge entity.

[0066] Based on the logical relationship between the associated knowledge entity to be expanded and the knowledge concept entity, the knowledge concept entity to be expanded is determined.

[0067] Perform association analysis on the knowledge concept entity to be expanded to generate a target associated knowledge entity to be expanded.

[0068] The target associated knowledge entity to be expanded is loaded into the first target associated knowledge entity of the traditional Chinese medicine knowledge graph, the structural adjustment of the traditional Chinese medicine knowledge graph is completed, and the target traditional Chinese medicine knowledge graph is generated. The first target associated knowledge entity and the target associated knowledge entity to be expanded are same-level associated knowledge entities or hierarchical associated knowledge entities, and when the first target associated knowledge entity is a category associated knowledge entity, and the first target associated knowledge entity and the target associated knowledge entity to be expanded are hierarchical associated knowledge entities, the category of the first target associated knowledge entity after adjustment is a group associated knowledge entity category.

[0069] In this embodiment, when the architecture adjustment instruction includes associated knowledge entity extension information, the server starts to perform a series of operations to adjust the architecture of the TCM knowledge graph to generate a target TCM knowledge graph.

[0070] Taking the specific TCM knowledge graph related to "qi" as an example, suppose that after studying some newly unearthed fragments of ancient TCM texts, new knowledge content is discovered that needs to be expanded into the graph. The server retrieves the first target related knowledge entity and the related knowledge entity to be expanded from the related knowledge entity expansion information. For example, the first target related knowledge entity is the health-preserving exercise knowledge section related to the specific "qi". This section is currently a category-related knowledge entity in the graph and contains some basic health-preserving exercise knowledge related to "qi". The related knowledge entity to be expanded is a knowledge entity related to the specific movements of an ancient health-preserving exercise discovered in the newly unearthed ancient texts and its special connection with the specific "qi". This entity is the initial related knowledge entity to be loaded into the health-preserving exercise knowledge section (the first target related knowledge entity).

[0071] Based on the logical relationship between this associated knowledge entity to be expanded and the knowledge concept entity (the special "qi"), the server determines the knowledge concept entity to be expanded. In this example, because the specific movements of the ancient health-preserving exercises are closely related to the circulation and regulation of the special "qi" within the human body, the knowledge concept entity to be expanded may be a concept entity related to the specific circulation trajectory and regulatory mechanism of qi and blood in the human meridians during health-preserving exercises.

[0072] The server then performs an association analysis on the knowledge concept entity to be expanded. The server examines the structure of the entire TCM knowledge graph and analyzes the relationship between the knowledge concept entity to be expanded and other knowledge entities. For example, it analyzes its relationship with other organs, emotions, and other aspects of the human body. During the analysis process, the server explores potential associated elements related to the knowledge concept entity to be expanded and, after screening, generates target-associated knowledge entities to be expanded. For example, knowledge entities such as the association between certain movements in a new health-preserving exercise and specific meridian acupoints, as well as the association between these movements and changes in emotions after regulating qi and blood, are identified as target-associated knowledge entities to be expanded.

[0073] Finally, the server loads these target-related knowledge entities to be expanded into the first target-related knowledge entity (the health-preserving exercises knowledge section) of the TCM knowledge graph. If the first target-related knowledge entity is a category-related knowledge entity, like the health-preserving exercises knowledge section here, it was originally a simple category-related knowledge entity. After loading these target-related knowledge entities, its internal hierarchical structure becomes more complex, so the category of the first target-related knowledge entity is adjusted to a group-related knowledge entity category. This completes the adjustment to this part of the TCM knowledge graph architecture, making the TCM knowledge graph more rich and accurate in reflecting TCM knowledge.

[0074] Taking the knowledge graph related to herbal preparation methods as an example, the first target associated knowledge entity might be a knowledge block related to temperature control during the preparation of a certain type of herbal medicine (a category-related knowledge entity). The associated knowledge entity to be expanded is a knowledge entity related to the special temperature adjustment required for the preparation of a newly discovered herbal medicine under unique geographical conditions. Based on the logical relationship between the associated knowledge entity to be expanded and the knowledge concept entity (temperature control for herbal preparation), the concept entity to be expanded is determined to be a concept entity related to the relationship between the effects of unique geographical factors on herbal properties and temperature during preparation. Association analysis is performed on this knowledge concept entity to generate target associated knowledge entities to be expanded, such as the relationship between changes in herbal composition under unique geographical conditions and temperature adjustment. These target associated knowledge entities to be expanded are then loaded into the temperature control knowledge block. If they meet the criteria for hierarchical association, the temperature control knowledge block's category becomes a group-related knowledge entity category, thus completing the adjustment of this portion of the TCM knowledge graph architecture and generating the target TCM knowledge graph.

[0075] In a possible implementation, when the architecture adjustment instruction includes the associated knowledge entity destruction information, adjusting the architecture of the TCM knowledge graph based on the architecture adjustment instruction to generate the target TCM knowledge graph includes:

[0076] A second target associated knowledge entity is obtained from the associated knowledge entity destruction information, wherein the second target associated knowledge entity is an associated knowledge entity to be destroyed in the traditional Chinese medicine knowledge graph.

[0077] From the TCM knowledge graph, the second target associated knowledge entity is destroyed, the structural adjustment of the TCM knowledge graph is completed, and the target TCM knowledge graph is generated.

[0078] In a possible implementation, when the architecture adjustment instruction includes the associated knowledge entity migration information, adjusting the architecture of the TCM knowledge graph based on the architecture adjustment instruction to generate the target TCM knowledge graph includes:

[0079] A third target associated knowledge entity and a fourth target associated knowledge entity are obtained from the associated knowledge entity migration information. The third target associated knowledge entity and the fourth target associated knowledge entity are associated knowledge entities that do not have a derivative relationship in the traditional Chinese medicine knowledge graph, and the third target associated knowledge entity and the fourth target associated knowledge entity are determined by a knowledge section corresponding to the traditional Chinese medicine knowledge graph.

[0080] In the TCM knowledge graph, the third target-related knowledge entity and the fourth target-related knowledge entity are migrated, the structural adjustment of the TCM knowledge graph is completed, and the target TCM knowledge graph is generated.

[0081] In this embodiment, when the architecture adjustment instruction includes information about the destruction of associated knowledge entities, the server will perform specific operations based on the instruction. For example, taking the specific "qi"-related portion of the TCM knowledge graph as an example, as TCM research deepens, it may be discovered that certain associated knowledge entities in the previous graph contain errors or are inconsistent with current TCM theoretical frameworks. In this case, the server retrieves a second target associated knowledge entity from the associated knowledge entity destruction information. This second target associated knowledge entity is the associated knowledge entity in the TCM knowledge graph to be destroyed. For example, within the specific "qi"-related knowledge, a previous associated knowledge entity claimed that wearing a certain special stone could directly regulate this special "qi" in the human body. However, rigorous TCM theoretical research and practical verification have revealed that this claim is unfounded. This associated knowledge entity concerning the special stone and the special "qi" is then identified as the second target associated knowledge entity. The server then directly destroys this second target associated knowledge entity from the TCM knowledge graph. During the destruction process, the server adjusts the relevant connections to ensure the graph's coherence and logic. Upon completion of this operation, the architecture adjustment of the TCM knowledge graph is completed, thereby generating the target TCM knowledge graph.

[0082] Let's consider the case where the architecture adjustment directive includes associated knowledge entity migration information. Continuing with the example of the knowledge graph related to the concept of "qi," let's assume the graph contains associated knowledge entities related to this concept in traditional folk health practices, as well as associated knowledge entities in orthodox TCM theory. These two associated knowledge entities are the third target associated knowledge entity and the fourth target associated knowledge entity. These are associated knowledge entities in the TCM knowledge graph that do not have a derivative relationship and are determined by the corresponding knowledge sections in the TCM knowledge graph. In traditional folk health practices, this concept of "qi" may have a special connection to specific folk customs, while in orthodox TCM theory, it is more closely related to theories of the human body's internal organs and meridians. With the need to integrate the TCM knowledge system, the server retrieves these two target associated knowledge entities from the associated knowledge entity migration information and performs the migration operation within the TCM knowledge graph. For example, we migrated the unique "qi"-related knowledge entities in traditional folk health preservation concepts to a more appropriate knowledge section that integrates folk culture and traditional Chinese medicine. We also migrated the unique "qi"-related knowledge entities in orthodox traditional Chinese medicine theory to the viscera and meridians-related knowledge section that better reflects the core of traditional Chinese medicine theory. This allows for more rational knowledge classification. During the migration process, the server reconstructs the relationships between these entities and the surrounding knowledge entities to ensure the integrity of the graph structure. Once the migration is complete, the structural adjustment of the TCM knowledge graph is completed, and the target TCM knowledge graph is generated.

[0083] Similarly, similar operations are followed for the knowledge graph related to herbal preparation methods. If there is an associated knowledge entity that claims that a certain herb has magical effects after preparation that are inconsistent with traditional Chinese medicine theory, this associated knowledge entity is determined to be the second target associated knowledge entity that needs to be destroyed, and the server will destroy it from the graph. If there are associated knowledge entities of herbal preparation methods in different regional theories that need to be repositioned, these associated knowledge entities are determined to be the third target associated knowledge entities and the fourth target associated knowledge entities. The server will migrate them to the appropriate knowledge sections, thereby completing the structural adjustment and generating the target traditional Chinese medicine knowledge graph.

[0084] In a possible implementation, after step S120, the method further includes:

[0085] Step B110: Obtain source-related knowledge entities from the TCM knowledge graph. The source-related knowledge entities are related knowledge entities in the TCM knowledge graph that are used to trigger graphical representation.

[0086] Step B120: determining adjustment restriction information based on the source-related knowledge entity.

[0087] Step B130, loading the adjustment restriction information into each associated knowledge entity in the TCM knowledge graph, thereby ending the restriction on the TCM knowledge graph and generating a restricted TCM knowledge graph.

[0088] Step A120 includes:

[0089] When the adjustment restriction information is in an open state, the restricted TCM knowledge graph is adjusted based on the adjustment instruction, and the adjustment restriction information is configured to be in an adjustment state.

[0090] When the adjustment of the restricted TCM knowledge graph is completed, the target TCM knowledge graph is generated, and the adjustment restriction information is configured to be in the open state.

[0091] In this embodiment, after completing the association analysis of each knowledge concept entity in the traditional Chinese medicine knowledge architecture and obtaining the associated knowledge entity, semantic relationship information and knowledge feature vector information corresponding to each knowledge concept entity, the server starts a new operation process.

[0092] The server retrieves source-related knowledge entities from the TCM knowledge graph. For example, let's consider the TCM knowledge graph related to "qi," assuming the source-related knowledge entity is "qi nixing." This "qi nixing" holds a unique position within the TCM knowledge graph, possessing complex connections with numerous other knowledge entities. Due to its key role in TCM theory (e.g., its close connection to human symptoms and the circulation of qi and blood through meridians), it is identified as a related knowledge entity to trigger the graphical representation.

[0093] Based on this source-associated knowledge entity, "Qi Nixing," the server determines adjustment restriction information. For example, because "Qi Nixing" primarily involves knowledge related to the circulation of Qi and blood in the human body and meridians, the server will determine relevant adjustment restriction information based on relevant classical Chinese medicine theories, existing research results, and actual clinical experience. This adjustment restriction information may stipulate that when adjusting knowledge entities directly related to "Qi Nixing" (such as knowledge entities related to Qi Nixing's symptoms and conditioning methods), specific principles of Chinese medicine Qi and blood theory must be followed, and their core semantic relationship information and knowledge feature vector information cannot be arbitrarily modified.

[0094] The server then loads this adjustment restriction information into each associated knowledge entity in the TCM knowledge graph. For example, for the symptom knowledge entity "heart meridian stagnation" related to "qi retrograde flow," after loading the adjustment restriction information, subsequent graph adjustments to adjust "heart meridian stagnation" will require reference to this adjustment restriction information. This completes the restriction of the TCM knowledge graph and generates a restricted TCM knowledge graph.

[0095] When there is an adjustment instruction to adjust the TCM knowledge graph to generate the target TCM knowledge graph, if the adjustment restriction information is in an open state, the server can adjust the restricted TCM knowledge graph based on the adjustment instruction, and configure the adjustment restriction information to the adjustment state. For example, suppose the adjustment instruction is to update a certain conditioning method knowledge entity related to "Qi Nixing". Since the adjustment restriction information is in an open state, the server can adjust this conditioning method knowledge entity based on new research results or clinical experience. During the adjustment process, the adjustment restriction information is in an adjustment state, which means that the server must follow the basic principles of the previously determined restriction information when operating, such as not violating the TCM Qi and blood theory.

[0096] When adjustments to the restricted TCM knowledge graph are complete, the server generates a target TCM knowledge graph and reconfigures the adjustment restriction information to an open state. For example, after updating the knowledge entities related to "Qi Ni Xing" conditioning methods, the entire graph is adjusted. The generated target TCM knowledge graph now reflects the latest TCM knowledge state, and the adjustment restriction information is restored to an open state to facilitate possible future adjustments.

[0097] The same situation applies to the knowledge graph related to herbal preparation methods. If the source associated knowledge entity is a key step in the preparation process of a certain herbal medicine, the adjustment restriction information is determined based on this key step (such as following a specific herbal medicinal property conversion theory, etc.), and it is loaded into each associated knowledge entity to form a restricted knowledge graph. When there is an adjustment instruction and the adjustment restriction information is in an open state, the restricted graph is adjusted (such as updating the relationship with other knowledge entities in the preparation process, etc.). After the adjustment is completed, the target knowledge graph is generated and the adjustment restriction information is restored to an open state.

[0098] In a possible implementation, the knowledge concept entities in the TCM knowledge architecture include basic information of traditional Chinese medicine.

[0099] Step S130 includes:

[0100] Step S131 , walking the TCM knowledge graph, and determining associated knowledge concept entities based on the semantic relationship information in each associated knowledge entity.

[0101] Step S132: Acquire the basic information of traditional Chinese medicine corresponding to the associated knowledge concept entity.

[0102] Step S133: Based on the knowledge feature vector information and the basic traditional Chinese medicine information corresponding to the associated knowledge concept entity, a feature vector corresponding to the current display node in each associated knowledge entity is graphically represented to generate a current traditional Chinese medicine knowledge display node. The current traditional Chinese medicine knowledge display node belongs to the visual display data stream of the traditional Chinese medicine knowledge graph.

[0103] Step S134, continue to walk the TCM knowledge graph, and perform graphical representation on the feature vector corresponding to the next display node until the graphical representation of the feature vectors corresponding to each display node is completed, thereby completing the graphical representation and generating a visual display data stream of the TCM knowledge graph.

[0104] In this embodiment, since the knowledge concept entities in the traditional Chinese medicine knowledge architecture contain basic information of traditional Chinese medicine, the server begins to traverse the traditional Chinese medicine knowledge graph for graphical representation to generate a visual display data stream.

[0105] Taking the specific knowledge related to "qi" as an example, the server begins to traverse the Traditional Chinese Medicine (TCM) knowledge graph and identifies associated knowledge concept entities based on the semantic relationship information within each associated knowledge entity. For example, for the associated knowledge entity "qi retrograde," based on its semantic relationship information (e.g., "qi retrograde" affects the circulation of qi and blood in the heart meridians), the associated knowledge concept entity can be determined to be "qi." This is because in TCM theory, "qi" is a fundamental concept, and "qi retrograde" is a special state of "qi," and the two have a close semantic connection.

[0106] The server then retrieves the basic Traditional Chinese Medicine information corresponding to the associated knowledge concept entity. For the associated knowledge concept entity "Qi," this basic Traditional Chinese Medicine information includes the source of Qi (e.g., innate Qi originates from parents, acquired Qi originates from diet and breathing), the classification of Qi (e.g., Yuan Qi, Zong Qi, Ying Qi, Wei Qi), and the basic principles of Qi's operation in the human body (e.g., Qi flows along the meridians and interacts with the internal organs).

[0107] Based on the knowledge feature vector information and the basic Traditional Chinese Medicine information corresponding to the associated knowledge concept entities, the feature vector corresponding to the current display node in each associated knowledge entity is graphically represented to generate the current Traditional Chinese Medicine knowledge display node. For the associated knowledge entity "Qi Retrograde," its knowledge feature vector information may include the triggering factors of Qi retrograde (such as emotional overreaction and invasion of external pathogens) and the effects of Qi retrograde on the human body (such as poor heart circulation and organ dysfunction). Combined with the basic Traditional Chinese Medicine information about "Qi," this is represented in the graph. For example, in the visual display data stream, the "Qi Retrograde" node can be represented by a specific icon (such as a red arrow indicating the retrograde direction) and connected to the "Qi" node by a line. The line indicates the interference of Qi retrograde on the normal operation of Qi. Textual information such as the triggering factors and effects of Qi retrograde are displayed around the "Qi Retrograde" node. This generates the current Traditional Chinese Medicine knowledge display node, which belongs to the visual display data stream of the Traditional Chinese Medicine knowledge graph.

[0108] Next, the server continues to traverse the TCM knowledge graph, graphically representing the feature vector corresponding to the next display node. Assuming the next associated knowledge entity is "heart pulse obstruction," based on its semantic relationship information (reverse flow of Qi causes heart pulse obstruction), the associated knowledge concept entity is determined to be "heart pulse." Basic Traditional Chinese Medicine information corresponding to "heart pulse" is obtained, including the direction of the heart meridian (originating in the heart, belonging to the heart system, etc.), the intersection of the heart meridian with other meridians, and the characteristics of the heart meridian's Qi and blood circulation. Based on the knowledge feature vector information of "heart pulse obstruction" (such as symptoms such as chest tightness and palpitations, and the specific conditions of Qi and blood stasis) and the basic Traditional Chinese Medicine information about "heart pulse," the "heart pulse obstruction" node is represented in the graph. For example, a lighter line is used to represent the state of Qi and blood obstruction in the heart meridian, and specific symptoms are listed at the node, generating a new TCM knowledge display node.

[0109] In this way, the server continuously traverses the TCM knowledge graph, graphically representing the feature vectors corresponding to each display node until the graphical representation of each feature vector is completed, generating a complete visual display data stream of the TCM knowledge graph. This data stream is like a dynamic TCM knowledge map, comprehensively displaying the complex relationships and characteristics between various knowledge entities in the TCM knowledge system.

[0110] The same applies to knowledge related to herbal preparation methods. For example, for the associated knowledge entity "herbal property transformation," the semantic relationship information is used to determine that the associated knowledge concept entity is the herb itself. The basic traditional Chinese medicine information of the herb (such as the nature, flavor, meridians, and efficacy) is obtained. Combined with the knowledge feature vector information of "herbal property transformation" (such as the conditions for transformation and changes in the medicinal properties after transformation), the node "herbal property transformation" is graphically represented to generate a display node. The graph is then continued to navigate, and similar operations are performed on the next display node related to herbal preparation, until the generation of the visual display data stream of the entire herbal preparation-related knowledge in the TCM knowledge graph is completed.

[0111] For example, in one possible implementation, step S120 includes:

[0112] Step S121 , analyzing the overall structure of the TCM knowledge architecture and the contextual relationship of each knowledge concept entity in the overall structure, and determining the initial semantic domain scope involved by each knowledge concept entity.

[0113] In step S122, based on the determined initial semantic domain, the TCM classic literature data is searched and screened to mine a text description set related to the initial semantic domain.

[0114] Step S123, parse the text description set, analyze the basic logical relationship between the grammatical structure components in the sentence, and the traditional Chinese medicine connotation of each word and phrase, identify the potential associated elements related to the knowledge concept entity based on the basic logical relationship between the grammatical structure components and the traditional Chinese medicine connotation of each word and phrase, and generate a list of potential associated elements.

[0115] Step S124: classify the list of potential associated elements according to the logic and classification standards of the traditional Chinese medicine knowledge system. For each classification category, evaluate the degree of association between the elements and the knowledge concept entities, screen out elements that are closely associated and conform to the logic of traditional Chinese medicine knowledge, and generate a subset of valid associated elements. The evaluation of the degree of association is based on the causal relationship and functional connection in traditional Chinese medicine theory.

[0116] Step S125: Determine each valid associated element in the valid associated element subset as an associated knowledge entity, and construct semantic relationship information between each associated knowledge entity and the knowledge concept entity based on the basic logical relationship between the grammatical structure component elements in the text description set, and generate one or more associated knowledge entities corresponding to the knowledge concept entity and the semantic relationship information between the associated knowledge entity and the knowledge concept entity.

[0117] Step S126 : for each associated knowledge entity, extract the knowledge feature vector information of the associated knowledge entity according to the attribute feature definition in the traditional Chinese medicine knowledge system.

[0118] In this example, continuing with the specific knowledge concept entity "qi," the server first analyzes the overall structure of the TCM knowledge architecture and the contextual relationships of "qi" within this overall structure. Within the TCM knowledge architecture, the overall structure encompasses multiple components, such as the human physiological structure (viscera, meridians, etc.), pathological phenomena, health preservation, and medication. The concept entity "qi" occupies a central position within this framework, closely connected to the internal organs. For example, "qi" is the fundamental substance that maintains the functional activities of the organs. It is even more closely associated with the meridians, serving as the crucial material foundation for their circulation. In terms of pathological phenomena, imbalances in "qi" (such as qi deficiency and qi reversal) are often a major contributing factor to disease. In terms of health preservation, many principles of various health-preserving exercises (such as Tai Chi) are based on regulating "qi." In medication, the efficacy of medications is often related to regulating "qi" (e.g., qi-tonifying and qi-promoting drugs). Through this overall structural analysis and analysis of the contextual relationships of "qi," the initial semantic domain of the knowledge concept entity "qi" is determined. This scope covers the generation of Qi (both innate and acquired), the movement patterns of Qi (such as the path and direction of Qi between the meridians and internal organs), the functions of Qi (such as promotion, warmth, defense, etc.), the abnormal manifestations of Qi (such as Qi deficiency, Qi disorder, etc.), and the relationship with other physiological and pathological factors.

[0119] Next, based on the determined initial semantic scope of "qi," the server searches and filters classical TCM literature. This classical TCM literature comes from a wide range of sources, including ancient TCM texts and local TCM traditions. During the search, the server searches for text fragments containing content related to the generation, operation, function, abnormal manifestations, and interrelationships of "qi." For example, from the Yellow Emperor's Classic of Internal Medicine, the server selects the following sentence describing the generation and relationship between qi and the internal organs: "Humans receive qi from food. Food enters the stomach and is transmitted to the lungs. The five internal organs and six bowels all receive qi." From the Difficult Classic, the server also finds relevant descriptions of qi's path: "The movement of qi is like the flow of water, without being able to rest." Through this search and screening process, a collection of text descriptions relevant to the initial semantic scope of "qi" is discovered.

[0120] The server then parses this text description. For example, the sentence "People receive Qi from food. Food enters the stomach and is transmitted to the lungs. The five internal organs and six bowels all receive Qi." The server analyzes the basic logical relationships between the grammatical structural elements within the sentence. In this sentence, "People receive Qi from food" is a declarative relationship, indicating that food is the source of Qi; "food enters the stomach" is an action relationship, describing the process of food entering the stomach; "is transmitted to the lungs" indicates a transfer relationship, where Qi transformed from food is transmitted from the stomach to the lungs; and "the five internal organs and six bowels all receive Qi" is a whole-part relationship, indicating that the five internal organs receive Qi through this transfer process. The server also analyzes the Traditional Chinese Medicine connotations of each word and phrase. In Traditional Chinese Medicine (TCM), "gu" (gu) is more than just ordinary food. It possesses five flavors (sour, bitter, sweet, pungent, and salty). Different flavors have specific affinities with the five internal organs, such as sweetness affecting the spleen. These relationships influence the generation and transformation of qi (qi). The "stomach" (gu) is a crucial organ in TCM, serving as the center of food and water, and the site of initial digestion and conversion of food into qi. Besides its respiratory function, the "lungs" (lungs) play a key role in the transmission and distribution of qi. Based on the basic logical relationships between these grammatical structural elements and the TCM connotations of each word and phrase, the server identifies potential related elements associated with the knowledge concept entity "qi." Here, "gu," "stomach," "lungs," and "the five internal organs and six fu organs" are all potential related elements, and a list of these elements is generated.

[0121] The server then categorizes this list of potentially related elements according to the logic and classification standards of the TCM knowledge system. For example, "grain" belongs to the diet and nutrition category, "stomach" and "lungs" belong to the viscera category, and "five internal organs and six bowels" belong to the viscera system category. For each category, the server assesses the closeness of the connection between the element and the knowledge concept entity "qi." This evaluation is based on the causal and functional relationships in TCM theory. Taking the "stomach" as an example, from a causal perspective, the normal digestive function of the stomach directly affects the generation of qi. Only when the stomach properly digests food and water can qi be sufficient, so the close connection is very high. From a functional perspective, the stomach is one of the sources of qi generation and has a clear functional connection with qi. Grain is the material basis for qi generation; without grain, there is no source of qi, thus having a strong causal relationship with qi. As for the overall concept of the "five internal organs and six bowels," from a functional perspective, they are both recipients and users of qi. Qi performs functions such as propulsion and warmth within the five internal organs, thus also having a close connection. After such an evaluation, elements that are closely related and conform to the logic of traditional Chinese medicine knowledge, such as "grain", "stomach", "lungs", "five internal organs", etc., are screened out to generate a subset of valid related elements.

[0122] Each valid associated element in the valid associated element subset is then identified as an associated knowledge entity. For example, "gu," "stomach," "lung," and "five zang-fu organs" all become associated knowledge entities associated with the knowledge concept entity "qi." Then, based on the basic logical relationships between the grammatical structural elements in the text description set, semantic relationship information is constructed between each associated knowledge entity and the knowledge concept entity. For "gu" and "qi," the semantic relationship information is that gu is the source of qi; for "stomach" and "qi," the semantic relationship information is that the stomach is an important site for qi generation; for "lung" and "qi," the semantic relationship information is that the lungs are a key organ for qi transmission and distribution; and for "five zang-fu organs" and "qi," the semantic relationship information is that the five zang-fu organs are the site where qi functions. This generates multiple associated knowledge entities corresponding to the knowledge concept entity "qi," along with their semantic relationship information with "qi."

[0123] Finally, for each associated knowledge entity, the knowledge feature vector information of that associated knowledge entity is extracted based on the attribute feature definitions in the TCM knowledge system. For the associated knowledge entity "gu," its knowledge feature vector information includes the type of grain (such as japonica rice, wheat, etc.), the five flavors of grains (different grains have different flavors, such as japonica rice being sweet), and the benefits of grains (such as some grains have the effect of strengthening the spleen and replenishing qi). For the associated knowledge entity "stomach," its knowledge feature vector information covers the physiological structural characteristics of the stomach (such as the upper opening of the stomach is the cardia and the lower opening is the pylorus), the functional characteristics of the stomach (such as the main function of receiving and digesting food), and the pathological manifestations of the stomach (such as epigastric pain and vomiting). For the associated knowledge entity "lung," its knowledge feature vector information includes the anatomical structure of the lungs (such as the lungs' location in the chest cavity), the physiological functions of the lungs (controlling qi and respiration, dispersing and descending qi), and the pathological changes of the lungs (such as coughing and asthma). For the associated knowledge entity "five internal organs and six bowels", the knowledge feature vector information includes the names, functions, and mutual relationships of the five internal organs (such as the mutual generation and mutual restraint relationship between the five internal organs), as well as their specific manifestations in the circulation of qi and the performance of functions.

[0124] Taking the knowledge concept entity "herbal preparation methods" as an example, the server analyzed the overall structure of the TCM knowledge architecture and discovered that herbal preparation methods are linked to the properties and efficacy of the herbs themselves, as well as the body's acceptability of the processed herbs. The server determined the initial semantic domain scope, including the types of preparation methods, the changes in herbal properties caused by preparation, and the connection between preparation and TCM theory (such as the five flavors and meridians). Based on this scope, classic TCM literature was then searched and screened, revealing a collection of relevant text descriptions, such as "When using croton, remove the skin and pericarp, and take the frost." These sentences were parsed, analyzing their grammatical structure and lexical TCM connotations, identifying potential associated elements (such as croton, pericarp, and frost) and generating a list. These elements were then classified according to TCM knowledge logic, their closeness to "herbal preparation methods" was assessed, and a subset of valid associated elements (such as croton, frost, etc.) was selected. The subset elements are identified as associated knowledge entities, and semantic relationship information is constructed (for example, the relationship between croton and the processing method is that it is the processed object, and frost is the product after processing, etc.). Finally, the knowledge feature vector information of each associated knowledge entity is extracted (for example, the toxicity and meridians of croton, the medicinal properties of frost, etc.).

[0125] Figure 2 The hardware structure of the TCM knowledge graph construction system 100 based on AI semantic understanding for implementing the above-mentioned TCM knowledge graph construction method based on AI semantic understanding provided by an embodiment of the present invention is shown as follows: Figure 2 As shown, the TCM knowledge graph construction system 100 based on AI semantic understanding may include a processor 110 , a machine-readable storage medium 120 , a bus 130 , and a communication unit 140 .

[0126] The machine-readable storage medium 120 can store data and / or instructions. In some embodiments, the machine-readable storage medium 120 can store data obtained from an external terminal. In some embodiments, the machine-readable storage medium 120 can store data and / or instructions used by the AI ​​semantic understanding-based TCM knowledge graph construction system 100 to execute or use to complete the exemplary methods described in the present invention.

[0127] During the specific implementation process, one or more processors 110 execute computer executable instructions stored in the machine-readable storage medium 120, so that the processor 110 can execute the method for constructing a traditional Chinese medicine knowledge graph based on AI semantic understanding as described in the above method embodiment. The processor 110, the machine-readable storage medium 120 and the communication unit 140 are connected through the bus 130, and the processor 110 can be used to control the sending and receiving actions of the communication unit 140.

[0128] The specific implementation process of the processor 110 can be found in the various method embodiments executed by the above-mentioned TCM knowledge graph construction system 100 based on AI semantic understanding. The implementation principles and technical effects are similar and will not be repeated here in this embodiment.

[0129] In addition, an embodiment of the present invention also provides a readable storage medium, which has computer-executable instructions preset in the readable storage medium. When the processor executes the computer-executable instructions, the above-mentioned method for constructing a traditional Chinese medicine knowledge graph based on AI semantic understanding is implemented.

[0130] It should be noted that in order to simplify the description of the present invention and facilitate understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of the invention, various features may sometimes be combined into one embodiment, figure, or description thereof.

Claims

1. A method for constructing a traditional Chinese medicine knowledge graph based on AI semantic understanding, characterized in that: The method comprises: Acquire TCM classic literature data and construct a TCM knowledge architecture from the TCM classic literature data; the TCM classic literature data is a data source corresponding to TCM theory, the TCM knowledge architecture is a feature vector of the TCM knowledge graph to be constructed, and the TCM knowledge architecture includes one or more knowledge concept entities; Performing association analysis on each knowledge concept entity in the TCM knowledge architecture to generate one or more associated knowledge entities corresponding to each knowledge concept entity in the TCM knowledge graph, as well as semantic relationship information and knowledge feature vector information corresponding to each of the one or more associated knowledge entities, wherein the semantic relationship information is the logical relationship between each associated knowledge entity and the knowledge concept entity, and the knowledge feature vector information is the specific TCM knowledge attribute characteristics represented by each associated knowledge entity; Wandering the TCM knowledge graph, graphically representing each associated knowledge entity based on the semantic relationship information and the knowledge feature vector information, and generating a visual display data stream of the TCM knowledge graph; The performing of association analysis on each knowledge concept entity in the TCM knowledge architecture to generate one or more associated knowledge entities corresponding to each knowledge concept entity in the TCM knowledge graph, as well as semantic relationship information and knowledge feature vector information corresponding to each of the one or more associated knowledge entities, includes: Analyze the overall structure of the TCM knowledge framework and the contextual relationship of each knowledge concept entity in the overall structure, and determine the initial semantic domain scope involved in each knowledge concept entity; Based on the determined initial semantic domain, the data of traditional Chinese medicine classic literature is searched and screened to mine a collection of text descriptions related to the initial semantic domain. Parsing the text description set, analyzing the basic logical relationships between grammatical structural elements in the sentence, and the TCM connotation of each word and phrase, identifying potential associated elements related to the knowledge concept entity based on the basic logical relationships between the grammatical structural elements and the TCM connotation of each word and phrase, and generating a list of potential associated elements; According to the logic and classification standards of the TCM knowledge system, the list of potential associated elements is classified. For each classification category, the degree of association between the elements and the knowledge concept entities is evaluated. Elements that are closely associated and conform to the logic of TCM knowledge are screened out to generate a subset of valid associated elements. The evaluation of the degree of association is based on the causal relationship and functional connection in TCM theory. Determining each valid associated element in the valid associated element subset as an associated knowledge entity, and constructing semantic relationship information between each associated knowledge entity and a knowledge concept entity based on the basic logical relationship between the grammatical structure component elements in the text description set, and generating one or more associated knowledge entities corresponding to the knowledge concept entity and semantic relationship information between the associated knowledge entity and the knowledge concept entity; For each associated knowledge entity, the knowledge feature vector information of the associated knowledge entity is extracted according to the attribute feature definition in the traditional Chinese medicine knowledge system.

2. The method for constructing a TCM knowledge graph based on AI semantic understanding according to claim 1, characterized in that: Before walking the TCM knowledge graph and graphically representing each associated knowledge entity based on the semantic relationship information and the knowledge feature vector information to generate a visual display data stream of the TCM knowledge graph, the method further includes: Obtaining an adjustment instruction for the TCM knowledge graph; the adjustment instruction is instruction information for adjusting the TCM knowledge graph; Adjusting the TCM knowledge graph based on the adjustment instruction to generate a target TCM knowledge graph; The walking of the TCM knowledge graph, based on the semantic relationship information and the knowledge feature vector information, performs a graph representation on each associated knowledge entity to generate a visual display data stream of the TCM knowledge graph, including: Wander through the target TCM knowledge graph, and based on the target semantic relationship information and the target knowledge feature vector information, graphically represent each target-related knowledge entity in the target TCM knowledge graph to generate a visual display data stream of the TCM knowledge graph; the target semantic relationship information and the target knowledge feature vector information correspond to each target-related knowledge entity.

3. The method for constructing a TCM knowledge graph based on AI semantic understanding according to claim 2, characterized in that: The adjustment instruction is a category knowledge adjustment instruction; the category knowledge adjustment instruction is instruction information for adjusting the TCM knowledge attribute characteristics corresponding to the associated knowledge entity in the TCM knowledge graph; The adjusting the TCM knowledge graph based on the adjustment instruction to generate a target TCM knowledge graph includes: Obtaining target associated knowledge entities and knowledge feature vector information to be adjusted from the category knowledge adjustment instruction; the target associated knowledge entity is an associated knowledge entity in the TCM knowledge graph whose knowledge feature is to be adjusted; Obtaining target knowledge feature vector information corresponding to the target associated knowledge entity; Based on the knowledge feature vector information to be adjusted, the target knowledge feature vector information is updated, thereby completing the adjustment of the TCM knowledge graph and generating the target TCM knowledge graph.

4. The method for constructing a TCM knowledge graph based on AI semantic understanding according to claim 2, characterized in that: The adjustment instruction is an architecture adjustment instruction; the architecture adjustment instruction is instruction information for adjusting the architecture of the TCM knowledge graph; The adjusting the TCM knowledge graph based on the adjustment instruction to generate a target TCM knowledge graph includes: Based on the architecture adjustment instruction, the architecture of the TCM knowledge graph is adjusted to generate the target TCM knowledge graph; the architecture adjustment instruction includes at least one of associated knowledge entity expansion information, associated knowledge entity destruction information, and associated knowledge entity migration information; Among them, the associated knowledge entity extension information is the feature vector for expanding the associated knowledge entity into the traditional Chinese medicine knowledge graph, the associated knowledge entity destruction information is the feature vector for destroying the associated knowledge entity from the traditional Chinese medicine knowledge graph, and the associated knowledge entity migration information is the feature vector for migrating the associated knowledge entity in the traditional Chinese medicine knowledge graph.

5. The method for constructing a TCM knowledge graph based on AI semantic understanding according to claim 4, characterized in that: When the architecture adjustment instruction includes the associated knowledge entity extension information, adjusting the architecture of the TCM knowledge graph based on the architecture adjustment instruction to generate the target TCM knowledge graph includes: Acquire a first target associated knowledge entity and an associated knowledge entity to be expanded from the associated knowledge entity extension information, wherein the first target associated knowledge entity is a category associated knowledge entity or a group associated knowledge entity in the TCM knowledge graph for which feature vector expansion is to be performed; and the associated knowledge entity to be expanded is an initial associated knowledge entity to be loaded into the first target associated knowledge entity; Determining the knowledge concept entity to be expanded based on the logical relationship between the associated knowledge entity to be expanded and the knowledge concept entity; Performing association analysis on the knowledge concept entity to be expanded to generate a target associated knowledge entity to be expanded; The target associated knowledge entity to be expanded is loaded into the first target associated knowledge entity of the traditional Chinese medicine knowledge graph, the structural adjustment of the traditional Chinese medicine knowledge graph is completed, and the target traditional Chinese medicine knowledge graph is generated. The first target associated knowledge entity and the target associated knowledge entity to be expanded are same-level associated knowledge entities or hierarchical associated knowledge entities, and when the first target associated knowledge entity is a category associated knowledge entity, and the first target associated knowledge entity and the target associated knowledge entity to be expanded are hierarchical associated knowledge entities, the category of the first target associated knowledge entity after adjustment is a group associated knowledge entity category.

6. The method for constructing a TCM knowledge graph based on AI semantic understanding according to claim 4, characterized in that: When the architecture adjustment instruction includes the associated knowledge entity destruction information, adjusting the architecture of the TCM knowledge graph based on the architecture adjustment instruction to generate the target TCM knowledge graph includes: Acquire a second target associated knowledge entity from the associated knowledge entity destruction information; the second target associated knowledge entity is the associated knowledge entity to be destroyed in the traditional Chinese medicine knowledge graph; From the TCM knowledge graph, the second target associated knowledge entity is destroyed, the structural adjustment of the TCM knowledge graph is completed, and the target TCM knowledge graph is generated.

7. The method for constructing a TCM knowledge graph based on AI semantic understanding according to claim 4, characterized in that: When the architecture adjustment instruction includes the associated knowledge entity migration information, adjusting the architecture of the TCM knowledge graph based on the architecture adjustment instruction to generate the target TCM knowledge graph includes: Obtaining a third target associated knowledge entity and a fourth target associated knowledge entity from the associated knowledge entity migration information; the third target associated knowledge entity and the fourth target associated knowledge entity are associated knowledge entities that do not have a derivative relationship in the traditional Chinese medicine knowledge graph, and the third target associated knowledge entity and the fourth target associated knowledge entity are determined by the knowledge section corresponding to the traditional Chinese medicine knowledge graph; In the TCM knowledge graph, the third target-related knowledge entity and the fourth target-related knowledge entity are migrated, the structural adjustment of the TCM knowledge graph is completed, and the target TCM knowledge graph is generated.

8. The method for constructing a TCM knowledge graph based on AI semantic understanding according to any one of claims 2 to 7, characterized in that: After performing association analysis on each knowledge concept entity in the TCM knowledge architecture to generate one or more associated knowledge entities corresponding to each knowledge concept entity in the TCM knowledge graph, as well as semantic relationship information and knowledge feature vector information corresponding to each of the one or more associated knowledge entities, the method further includes: Obtaining a source associated knowledge entity from the TCM knowledge graph; the source associated knowledge entity is an associated knowledge entity in the TCM knowledge graph used to trigger a graphical representation; determining adjustment restriction information based on the source-related knowledge entity; Loading the adjustment restriction information into each associated knowledge entity in the TCM knowledge graph, thereby ending the restriction on the TCM knowledge graph and generating a restricted TCM knowledge graph; The step of adjusting the TCM knowledge graph based on the adjustment instruction to generate a target TCM knowledge graph includes: When the adjustment restriction information is in an open state, adjusting the restricted TCM knowledge graph based on the adjustment instruction, and configuring the adjustment restriction information to be in an adjustment state; When the adjustment of the restricted TCM knowledge graph is completed, the target TCM knowledge graph is generated, and the adjustment restriction information is configured to be in the open state.

9. The method for constructing a TCM knowledge graph based on AI semantic understanding according to any one of claims 2 to 7, characterized in that: The knowledge concept entities in the TCM knowledge architecture include basic information of traditional Chinese medicine; The walking the TCM knowledge graph, graphically representing each associated knowledge entity based on the semantic relationship information and the knowledge feature vector information, and generating a visual display data stream of the TCM knowledge graph, includes: Walking the TCM knowledge graph, and determining associated knowledge concept entities based on the semantic relationship information in each associated knowledge entity; Acquire the traditional Chinese medicine basic information corresponding to the associated knowledge concept entity; Based on the knowledge feature vector information and the traditional Chinese medicine basic information corresponding to the associated knowledge concept entity, the feature vector corresponding to the current display node in each associated knowledge entity is graphically represented to generate a current Chinese medicine knowledge display node; the current Chinese medicine knowledge display node belongs to the visual display data stream of the Chinese medicine knowledge graph; Continue to walk the TCM knowledge graph, and perform graphical representation of the feature vector corresponding to the next display node until the graphical representation of the feature vectors corresponding to each display node is completed, and the graphical representation is completed to generate a visual display data stream of the TCM knowledge graph.

10. A TCM knowledge graph construction system based on AI semantic understanding, characterized by: The system for constructing a traditional Chinese medicine knowledge graph based on AI semantic understanding includes a processor and a memory, the memory is connected to the processor, the memory is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the memory to implement the method for constructing a traditional Chinese medicine knowledge graph based on AI semantic understanding as described in any one of claims 1 to 9 above.

Images