Disease prediction device, equipment and readable storage medium based on TCM diagnostic atlas

Abstract

The embodiment of the present application belongs to artificial intelligence technology and can be applied to the field of digital medicine. It relates to a disease prediction device based on a TCM diagnosis knowledge graph, including a construction module for constructing a TCM diagnosis knowledge graph based on disease symptoms, eight-category syndrome differentiation diagnosis graph, disease nature syndrome differentiation diagnosis graph, and disease location syndrome differentiation diagnosis graph; a first acquisition module for acquiring the user's four diagnostic information, which includes at least symptom information; an inference module for inferring candidate syndrome types corresponding to the symptom information based on the TCM diagnosis knowledge graph; and an integration module for integrating candidate syndrome types to obtain syndrome type diagnosis results. The present application also provides a computer-readable storage medium. In addition, the present application also relates to blockchain technology, and the TCM diagnosis knowledge graph can be stored in a blockchain. The present application can improve the generalization and accuracy of TCM disease diagnosis.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence technology and digital medical technology, and in particular to a disease prediction device, equipment and readable storage medium based on a traditional Chinese medicine diagnosis atlas. Background Art

[0002] The existing methods of TCM disease syndrome diagnosis generally diagnose the final disease by performing reverse matching, sorting or simple knowledge reasoning on the user's symptoms and disease library, which can obtain the results of TCM disease syndrome diagnosis to a certain extent. However, these methods only diagnose diseases through knowledge graphs compiled from existing cases, and do not refer to professional books to build graphs that conform to the logic of TCM theory. The reasoning knowledge base compiled from the existing TCM knowledge diagnosis graph is only effective under the data set of the current case, and the generalization is not strong, and the reasoning knowledge base cannot be well applied to actual diagnosis. Summary of the invention

[0003] The purpose of the embodiments of the present application is to propose a disease prediction device, equipment and readable storage medium based on the TCM diagnostic map, so as to solve the problem that the reasoning knowledge base of TCM disease syndrome diagnosis in the prior art is only effective under the data set of the current case and has poor generalization.

[0004] In order to solve the above technical problems, an embodiment of the present application provides a disease prediction device based on a traditional Chinese medicine diagnosis map, and the disease prediction device includes: a construction module, which is used to construct a traditional Chinese medicine diagnosis knowledge map based on disease symptoms, an eight-category syndrome differentiation diagnosis map, a disease nature syndrome differentiation diagnosis map, and a disease location syndrome differentiation diagnosis map; a first acquisition module, which is used to obtain the user's four diagnostic information, and the four diagnostic information at least includes symptom information; a matching module, which is used to match the candidate syndrome types corresponding to the symptom information in the traditional Chinese medicine diagnosis knowledge map; and an integration module, which is used to integrate the candidate syndrome types to obtain syndrome type diagnosis results.

[0005] Furthermore, the construction module includes: an initialization submodule, which is used to initialize the path weights between each symptom information and the dialectical nodes in the eight-category syndrome differentiation diagnosis map, the dialectical nodes in the disease nature syndrome differentiation diagnosis map, the dialectical nodes in the disease location syndrome differentiation diagnosis map, and the diseases, so as to obtain the general TCM diagnosis knowledge graph; an adjustment submodule, which is used to adjust the path weights according to the probability of correspondence between each symptom information in the existing medical records, the dialectical nodes in the eight-category syndrome differentiation diagnosis map, the dialectical nodes in the disease nature syndrome differentiation diagnosis map, the dialectical nodes in the disease location syndrome differentiation diagnosis map, and the diseases, so as to obtain the TCM diagnosis knowledge graph.

[0006] Furthermore, the matching module includes: an acquisition submodule, used to acquire candidate diseases corresponding to the symptom information according to the disease identification symptom path; a first matching submodule, used to match the first candidate syndrome type corresponding to the candidate disease in the existing medical records; and a second matching submodule, used to match the second candidate syndrome type corresponding to the symptom information in the eight-category syndrome differentiation diagnosis map, the disease nature syndrome differentiation diagnosis map and the disease location syndrome differentiation diagnosis map.

[0007] Furthermore, the acquisition submodule includes: a calculation unit, used to calculate the number of matches between the symptom information and the disease identification symptom path to obtain the disease corresponding to the symptom information; a sorting unit, used to sort the diseases according to the number of matches; and a selection unit, used to select the disease whose matching number is greater than a threshold matching number as a candidate disease.

[0008] Furthermore, the integration module includes an acquisition submodule for acquiring the intersection of the first candidate syndrome type and the second candidate syndrome type; and a processing submodule for processing the candidate syndrome type in the intersection to obtain the syndrome type diagnosis result.

[0009] Furthermore, the processing submodule includes: a judgment unit, used to judge whether the matching numbers of the paths of the candidate syndromes in the intersection are equal; a first calculation unit, used to calculate the correlation between the candidate syndrome and each of the symptom information when judging that the matching numbers of the paths of the candidate syndromes in the intersection are equal; an accumulation unit, used to accumulate the sum of the correlations of all the symptom information in the candidate syndrome; and a first selection unit, selecting the candidate syndrome with the largest sum of correlations as the syndrome diagnosis result.

[0010] Furthermore, the first calculation unit includes: a first calculation subunit, used to respectively calculate the first frequency of occurrence of each symptom information in the intersection, the second frequency of occurrence of each syndrome type, and the third frequency of co-occurrence of the symptom information and the syndrome type; a second calculation subunit, used to calculate the correlation between the syndrome type and the symptom information based on the first frequency, the second frequency and the third frequency.

[0011] Furthermore, the processing submodule also includes: a second selection unit, which is used to select the candidate symptom with the largest number of matches in the symptom path as the syndrome diagnosis result when it is determined that the matching numbers of the candidate syndrome symptom paths in the intersection are not equal.

[0012] In order to solve the above technical problems, the embodiment of the present application also provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the functions of each unit and / or module in the disease prediction device based on the TCM diagnostic map described in any of the above items are realized.

[0013] In order to solve the above-mentioned technical problems, an embodiment of the present application also provides a computer-readable storage medium, which adopts the technical solution described below: computer-readable instructions are stored on the computer-readable storage medium, and when the computer-readable instructions are executed by the processor, the functions of each unit and / or module in the disease prediction device based on the traditional Chinese medicine diagnostic map as described above are realized.

[0014] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0015] The present application provides a disease prediction device, equipment and readable storage medium based on a TCM diagnosis map. By constructing a TCM diagnosis knowledge map based on disease symptoms, an eight-category syndrome differentiation diagnosis map, a disease nature syndrome differentiation diagnosis map and a disease location syndrome differentiation diagnosis map, the user's four diagnostic information is obtained. According to the four diagnostic information, the candidate syndrome types corresponding to the symptom information in the four diagnostic information are matched in the TCM diagnosis knowledge map, and the candidate syndrome types are further integrated to obtain the syndrome type diagnosis result. The present application fully introduces TCM syndrome differentiation knowledge, so that TCM disease diagnosis has complete knowledge reasoning support, and the generalization and accuracy are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0018] Figure 2 It is a schematic diagram of the structure of a disease prediction device based on a TCM diagnostic map;

[0019] Figure 3 is a schematic diagram of a construction module 210 in an embodiment of the present application

[0020] Figure 4 It is a schematic diagram of an implementation method of the eight-category syndrome differentiation diagnosis atlas of the present application;

[0021] Figure 5 It is a schematic diagram of an implementation method of the disease differentiation and diagnosis atlas of the present application;

[0022] Figure 6 It is a schematic diagram of an implementation method of the disease location syndrome differentiation diagnosis atlas of the present application;

[0023] Figure 7 is a schematic diagram of a matching module 230 in an embodiment of the present application;

[0024] Figure 8 It is a matching diagram of the disease diagnosis symptom pathway and candidate diseases in this application;

[0025] Fig. 9 is a schematic diagram of an integration module 240 in an embodiment of the present application;

[0026] Fig.10 is a schematic diagram of a processing submodule 242 in an embodiment of the present application;

[0027] Fig.11 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0029] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0031] In order to solve the problem that the reasoning knowledge base of TCM disease syndrome diagnosis is only effective under the data set of the current case, the generalization is not strong, and the application of the existing TCM knowledge graph does not take into account the problem of path screening and sorting when there are multiple matching paths, this application provides a disease prediction device based on TCM diagnosis graph, involving artificial intelligence and digital medicine, which can be applied to Figure 1In the system architecture 100 shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0032] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0033] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0034] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0035] It should be noted that the disease prediction device based on the TCM diagnostic map provided in the embodiment of the present application is generally arranged in a terminal device.

[0036] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0037] The server can be a stand-alone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), as well as big data and artificial intelligence platforms.

[0038] Continue to refer Figure 2, shows a schematic structural diagram of a disease prediction device based on a TCM diagnostic map according to the present application, including a sampling and construction module 210, a first acquisition module 220, a matching module 230 and an integration module 240.

[0039] Among them, the construction module 210 is used to construct a traditional Chinese medicine diagnosis knowledge map based on disease symptoms, eight-category syndrome differentiation diagnosis map, disease nature syndrome differentiation diagnosis map and disease location syndrome differentiation diagnosis map.

[0040] Please further combine Figure 3 , Figure 3 FIG. 2 is a schematic diagram of a construction module 210 in an embodiment of the present application.

[0041] In some optional implementations of this embodiment, the construction module 210 includes an initialization submodule 211 and an adjustment submodule 212 .

[0042] Among them, in the embodiment of the present application, a Chinese medicine diagnosis knowledge graph is constructed based on disease symptoms, eight-category syndrome differentiation diagnosis graph, disease nature syndrome differentiation diagnosis graph, and disease location syndrome differentiation diagnosis graph.

[0043] Optionally, the entities and relationships of the TCM diagnosis knowledge map are mainly referenced from "Chinese Medicine Diagnosis", "Syndrome Differentiation of Syndrome Elements" and the guidance of TCM experts' knowledge. In the specific implementation of the present application, the TCM diagnosis knowledge map is constructed by drawing on the knowledge of TCM diagnosis such as disease symptoms, eight-category syndrome differentiation diagnosis map, disease nature syndrome differentiation diagnosis map and disease location syndrome differentiation diagnosis map.

[0044] Further, the TCM diagnosis knowledge map of the present application is divided into three levels, namely, symptom layer nodes, syndrome differentiation theory layer nodes, and syndrome type layer nodes. Among them, the symptom layer nodes may include disease differentiation symptom entities and common symptom entities, the syndrome differentiation theory layer nodes may include eight-category entities, pathological entities, and disease location entities, and the syndrome type layer nodes may include syndrome type entities and disease entities. Further, 50 disease entities commonly used in the embodiments of the present application correspond to 226 syndrome type entities, more than 800 symptom entities, 77 disease differentiation symptom entities, 4 eight-category entities, 33 pathological entities, and 20 disease location entities. Of course, in other embodiments, the number of disease entities and the corresponding syndrome type entities, symptom entities, disease differentiation symptom entities, eight-category entities, pathological entities, and disease location entities can also be other numbers, which are not specifically limited here.

[0045] Further, combined with Figure 4 , Figure 4This is a schematic diagram of an implementation method of the Eight-Principle Syndrome Differentiation Diagnosis Atlas of this application. The Eight-Principle Syndrome Differentiation Diagnosis Atlas in this application refers to the eight principle elements of exterior, interior, cold, heat, deficiency, excess, yin, and yang. The eight principles are common principles abstracted from various specific symptoms. Among them, exterior and interior are the basic principles for distinguishing the depth of the disease, and cold, heat, deficiency, and excess are the basic principles for distinguishing the nature of the disease; yin and yang are the general principles for distinguishing disease categories and summarizing disease syndromes, and can cover the six principles of exterior, interior, cold, heat, deficiency, and excess.

[0046] The eight-category syndrome differentiation diagnosis map in the embodiment of the present application is firstly the nodes of each symptom layer, for example Figure 4 The nasal congestion and fever in the symptom differentiation theory layer are shown in the present embodiment. In actual application, the eight-category syndrome differentiation diagnosis map contains eight category elements: exterior, interior, cold, heat, deficiency, excess, yin, and yang. The last layer is the syndrome type layer node corresponding to each category, such as wind-heat cold.

[0047] It is understandable that the eight-category syndrome differentiation and diagnosis charts are both different from each other and interconnected, and there are relationships such as concurrence, confusion, and transformation. Therefore, in the eight-category syndrome differentiation and diagnosis chart, there will be a situation where a symptom corresponds to multiple categories. For example, two concurring symptoms, such as cold syndrome of exterior and interior, cold syndrome of interior deficiency, etc., are concurring syndromes composed of any three categories other than the corresponding two categories (exterior and interior, cold and heat, deficiency and excess). For example, two concurring symptoms refer to the simultaneous existence of two opposite categories of syndromes in the eight categories at a certain stage of the real disease, such as cold exterior and interior, heat above and cold below, etc. Another example is the transformation between two symptoms. In the process of disease development and change, the opposite syndromes in the eight categories can be transformed into each other under certain conditions, but the transformation of syndromes is generally a process of quantitative change to qualitative change. Therefore, before the transformation of syndromes, the phenomenon of concurrence or confusion of syndromes can be presented, that is, the transition from exterior to interior, cold to heat, etc.

[0048] Further integration Figure 5 , Figure 5 This is a schematic diagram of an implementation method of the disease differentiation and diagnosis atlas of the present application, as shown in Figure 5 In this application, the disease differentiation and diagnosis chart is used to differentiate diseases through the essential attributes of the current pathological changes of the disease. Among them, the disease differentiation and diagnosis chart is mainly divided into the six pathogenic factors differentiation (wind pathogenic factors, cold pathogenic factors, heat pathogenic factors, damp pathogenic factors, dry pathogenic factors, and fire pathogenic factors), yin and yang deficiency syndrome differentiation (yang deficiency, yin deficiency and loss of yang, loss of yin), qi and blood syndrome differentiation (qi disease, blood disease, qi and blood co-disease), and body fluid syndrome differentiation. Optionally, combined with Figure 5 The disease differentiation diagnosis map of the present application also includes symptom layer nodes, differentiation theory layer nodes and syndrome type layer nodes. Among them, nasal congestion, fever and chest pain belong to symptom layer nodes, wind and fire belong to differentiation theory layer nodes and wind-heat cold belongs to syndrome type layer nodes.

[0049] Further integration Figure 6 , Figure 6This is a schematic diagram of an implementation method of the disease location syndrome differentiation diagnosis atlas of the present application, as shown in Figure 6 In this application, the diagnosis of the disease location must be combined with the diagnosis of the disease symptoms to form a complete syndrome diagnosis. Therefore, the "Disease Location Syndrome Diagnosis Atlas" in the embodiment of this application is actually a syndrome differentiation method based on the disease location, combining the disease location and the disease nature, specifically including viscera syndrome differentiation, six meridian syndrome differentiation, Wei Qi Ying Xue syndrome differentiation, triple burner syndrome differentiation and meridian syndrome differentiation. Figure 6 , the disease location syndrome differentiation diagnosis map in this application also includes symptom layer nodes, syndrome differentiation theory layer nodes and syndrome type layer nodes. Among them, nasal congestion, fever and chest pain belong to symptom layer nodes, lung belongs to syndrome differentiation theory layer node and wind-heat cold belongs to syndrome type layer node. It can be understood that the disease location syndrome differentiation diagnosis map, disease nature syndrome differentiation diagnosis map and eight-category syndrome differentiation diagnosis map in this application can share symptom layer nodes and syndrome type layer nodes. For example, in an embodiment of the present application, the fever symptom in the symptom layer node can be subordinate to the eight-category or to the disease location and disease location syndrome differentiation, and the same syndrome type layer node, i.e., wind-heat cold, can be inferred through different syndrome differentiation theory layer nodes.

[0050] Furthermore, in the present application, the initialization submodule 211 is used to initialize each symptom information and the eight-category syndrome differentiation diagnosis map, the disease nature syndrome differentiation diagnosis map, the disease location syndrome differentiation diagnosis map and the path weights between the diseases to obtain a general TCM diagnostic knowledge map.

[0051] The adjustment submodule 212 is used to adjust the path weight according to the corresponding probability between each symptom information in the existing medical records and the dialectical nodes in the eight-category syndrome differentiation diagnosis map, the dialectical nodes in the disease nature syndrome differentiation diagnosis map, the dialectical nodes in the disease location syndrome differentiation diagnosis map and the disease, so as to obtain a general TCM diagnostic knowledge map.

[0052] Optionally, the existing medical records in the present application can be obtained through medical record data of online consultations. By counting and sorting out the probabilities between the dialectical nodes in the Eight-Principle Syndrome Differentiation Diagnosis Graph, the dialectical nodes in the Pathology Syndrome Differentiation Diagnosis Graph, the dialectical nodes in the Disease Location Syndrome Differentiation Diagnosis Graph, and the diseases corresponding to each symptom information in the online consultation medical records, the dialectical nodes in the Eight-Principle Syndrome Differentiation Diagnosis Graph, the dialectical nodes in the Pathology Syndrome Differentiation Diagnosis Graph, the dialectical nodes in the Disease Location Syndrome Differentiation Diagnosis Graph, and the path weights between the diseases in the general TCM diagnostic knowledge graph are learned and adjusted, thereby providing TCM theoretical reasoning knowledge for disease diagnosis and improving the generalization of the TCM diagnostic graph.

[0053] In the above implementation, by drawing on the knowledge of TCM diagnosis such as disease symptoms, eight-category syndrome differentiation diagnosis map, disease nature syndrome differentiation diagnosis map and disease location syndrome differentiation diagnosis map, a TCM diagnosis knowledge graph is constructed, and the path weights between each symptom and the dialectical nodes in the eight-category syndrome differentiation diagnosis map, the dialectical nodes in the disease nature syndrome differentiation diagnosis map, the dialectical nodes in the disease location syndrome differentiation diagnosis map and the disease are initialized to obtain a general TCM diagnosis knowledge graph, and then the path weights are adjusted through the frequency between each symptom and the eight categories, disease nature, disease location and disease in the existing online consultation medical records, to obtain a TCM diagnosis knowledge graph that is more suitable for the current medical records, thereby improving the generalization of the TCM diagnosis map.

[0054] The first acquisition module 220 is used to acquire the user's four diagnostic information, which at least includes symptom information.

[0055] Specifically, the user's four diagnostic information in this application can be obtained through existing clinical data and / or disease databases, or through a combination of software and hardware, such as obtaining the patient's facial image and tongue image, and performing facial and tongue diagnosis based on the facial image and tongue image to determine the diagnostic result of inspection; determining the diagnostic result of auscultation by collecting image information of the patient's site and sound information of the heart, stomach, and lungs; extracting the user's symptom information from the voice information through voice recognition of the user's voice intention, thereby achieving the diagnostic result of the interview; obtaining the patient's wrist pulse phase information through, for example, a Bluetooth pulse vibration wristband, thereby achieving the diagnostic result of palpation. Of course, the acquisition of the above-mentioned four diagnostic information is only an illustrative example, and other methods can also be used to obtain it in other embodiments, which is not specifically limited here.

[0056] The matching module 230 is used to infer candidate syndrome types corresponding to the symptom information based on the TCM diagnosis knowledge graph.

[0057] Please further combine Figure 7 , Figure 7 FIG. 2 is a schematic diagram of a matching module 230 in an embodiment of the present application.

[0058] In some optional implementations of this embodiment, the matching module 230 further includes an acquisition submodule 231 , a first matching submodule 232 , and a second matching submodule 233 .

[0059] The acquisition submodule 231 is used to acquire candidate diseases corresponding to the symptom information according to the disease identification symptom path. It can be understood that the acquisition submodule 231 in the present application further includes a calculation unit, a sorting unit and a selection unit.

[0060] The calculation unit is used to calculate the matching number of the symptom information and the disease identification symptom path to obtain the disease corresponding to the symptom information. The sorting unit is used to sort the diseases according to the matching number. The selection unit is used to select the disease with a matching number greater than the threshold matching number as a candidate disease.

[0061] It can be understood that if there are multiple calculated matching numbers between symptom information and disease identification symptom paths, the diseases are sorted according to the calculated matching numbers, and the diseases with matching numbers greater than the threshold matching number are selected as candidate diseases.

[0062] Please further combine Figure 8 , Figure 8 This is a schematic diagram of the matching of disease diagnosis symptom pathways and candidate diseases for this application.

[0063] Specifically, disease reasoning mainly obtains the corresponding disease by calculating the matching degree between the user's symptoms and the disease diagnosis symptom path, and sorts the diseases according to the number of matching paths. Figure 8 As shown, in a specific application scenario of the present application, the patient has four symptoms of "nasal congestion", "fever", "aversion to wind", and "sputum". Among them, the three symptoms of "nasal congestion", "fever", and "aversion to wind" are inferred as "cold" through the disease identification symptom path reasoning, and "sputum" is inferred as "cough" through the disease identification symptom path reasoning. The number of paths matched according to all symptoms is 3 and 1 respectively, so the diseases inferred by the current patient's symptoms are "cold" and "cough" respectively. Of course, if the number of matches of the paths calculated according to all symptoms is multiple, for example, the number of matches of the path matching disease A is 5, the number of matches of the path matching disease B is 4, the number of matches of the path matching disease C is 3, and the number of matches of the path matching disease D is 2, then the diseases are sorted according to the number of matches of the path, and then a threshold matching number is set, and the diseases whose path matching number is greater than the threshold matching number are selected as candidate diseases. In combination with this embodiment, if the threshold matching number is set to 3, the diseases whose path matching number is greater than 3 are selected as candidate diseases, that is, disease A, disease B and disease C are candidate diseases.

[0064] The first matching submodule 232 is used to match the first candidate syndrome type corresponding to the candidate disease in the existing medical records. Specifically, the embodiment of the present application can obtain the disease type through the disease symptom path, and then obtain the syndrome type information corresponding to the disease type based on the existing medical records or data, so as to obtain the corresponding syndrome type of the disease.

[0065] Furthermore, according to the candidate diseases, first candidate syndrome types S1, S2, S3 corresponding to the candidate diseases can be obtained.

[0066] The second matching submodule 233 is used to match the second candidate syndrome type corresponding to the symptom information in the eight-category syndrome differentiation diagnosis map, the disease nature syndrome differentiation diagnosis map and the disease location syndrome differentiation diagnosis map.

[0067] Specifically, the user's four diagnostic information is inferred through the eight-category syndrome differentiation diagnosis map, the disease nature syndrome differentiation diagnosis map and the disease location syndrome differentiation diagnosis map to obtain the second candidate syndrome types S1, S2, S4 corresponding to the symptom information in the four diagnostic information.

[0068] The integration module 240 is used to integrate the candidate syndromes to obtain the syndrome diagnosis result. Further, the integration module 240 of the present application is used to integrate the first candidate syndrome and the second candidate syndrome to obtain the syndrome diagnosis result. Fig. 9 , Fig. 9 FIG. 2 is a schematic diagram of an integration module 240 in an embodiment of the present application.

[0069] In some optional implementations of this embodiment, the integration module 240 further includes an acquisition submodule 241 and a processing submodule 242. The acquisition submodule 241 is used to acquire the intersection of the first candidate syndrome type and the second candidate syndrome type.

[0070] Optionally, the first candidate syndrome type S1, S2, S3 and the second candidate syndrome type S1, S2, S4 are intersected to obtain candidate syndromes inferred by using the Eight-Principle Syndrome Differentiation Diagnosis Atlas, the Disease Nature Syndrome Differentiation Diagnosis Atlas and the Disease Location Syndrome Differentiation Diagnosis Atlas and the overlapping parts of the candidate syndromes inferred by using the candidate diseases, i.e., candidate syndromes S1 and S2.

[0071] S=S1∩S2∩S3S1∩S2∩S4=S1 and S2

[0072] Optionally, if the first candidate syndrome type and the second candidate syndrome type do not have an intersection, that is, there is no overlapping between the candidate syndrome types inferred by the Eight-Principle Syndrome Differentiation Diagnosis Chart, the Disease Nature Syndrome Differentiation Diagnosis Chart, and the Disease Location Syndrome Differentiation Diagnosis Chart and the candidate syndrome types inferred by the candidate diseases, then the process ends.

[0073] The processing submodule 242 is used to process the candidate syndrome types in the intersection to obtain the syndrome type diagnosis result. Fig.10 , Fig.10 Schematic diagram of the processing submodule 242 in an embodiment of the present application. In some optional implementations of the present embodiment, the processing submodule 242 further includes a judgment unit 2421, a first calculation unit 2422, an accumulation unit 2423 and a first selection unit 2424.

[0074] The judging unit 2421 is used to judge whether the matching numbers of candidate syndrome paths in the intersection are equal. Specifically, it is judged whether the matching numbers of candidate syndrome paths in the intersection are equal. If they are equal, the correlation between the candidate syndrome and each corresponding symptom information is calculated. Otherwise, if they are not equal, the candidate symptom with the largest number of matching paths is selected as the syndrome diagnosis result.

[0075] The first calculation unit 2422 is used to calculate the correlation between the syndrome and each symptom information when the matching numbers of the paths of the candidate syndromes in the intersection are equal. Optionally, when the matching numbers of the paths of the two candidate syndromes in the intersection are equal, the information entropy score of the symptom corresponding to the syndrome can be constructed through the real medical case data to evaluate the correlation between the syndrome and the symptoms. For example, if the matching number of the path of candidate syndrome A is 3 (that is, there are 3 symptom information through the disease identification symptom path reasoning to obtain syndrome A), and the matching number of the path corresponding to candidate syndrome B is also 3 (that is, there are 3 symptom information through the disease identification symptom path reasoning to obtain syndrome B), it is necessary to construct the information entropy score of the symptom corresponding to the syndrome through the existing medical case data to evaluate the correlation between the syndrome and the symptoms.

[0076] Specifically, in the present application, the first computing unit 2422 further includes a first computing subunit and a second computing subunit.

[0077] The first calculation subunit is used to respectively calculate the first frequency of occurrence of each symptom information in the intersection, the second frequency of occurrence of each candidate syndrome type, and the third frequency of co-occurrence of symptom information and candidate syndrome types.

[0078] Specifically, the first frequency of occurrence of each symptom information is:

[0079]

[0080] The second frequency of each candidate syndrome is:

[0081]

[0082] The third frequency of co-occurrence of symptom information and candidate syndrome is:

[0083]

[0084] Among them, symptom is symptom information, and disease is the candidate syndrome type.

[0085] Specifically in the specific embodiment of the present application, it is necessary to calculate the first frequency of occurrence of each symptom information corresponding to candidate syndrome type A, the second frequency of occurrence of candidate syndrome type A, and the third frequency of co-occurrence of each symptom information and candidate syndrome type A. Similarly, it is also necessary to calculate the first frequency of occurrence of each symptom information corresponding to candidate syndrome type B, the second frequency of occurrence of candidate syndrome type B, and the third frequency of co-occurrence of each symptom information and candidate syndrome type B.

[0086] The second calculation subunit is used to calculate the correlation between the candidate syndrome type and the symptom information according to the first frequency, the second frequency and the third frequency.

[0087] Furthermore, the correlation between the candidate syndrome and the symptom information is calculated based on the first frequency, the second frequency, and the third frequency, which is expressed as:

[0088]

[0089] Among them, corr score It is the correlation between syndrome type and symptoms. Specifically in the embodiment of the present application, it is necessary to calculate the correlation between candidate syndrome type A and candidate syndrome type B and each corresponding symptom information. For example, if the number of matching paths of candidate syndrome type A is 3, that is, there are 3 symptom information (such as symptom a, symptom b, symptom c) that are inferred through the disease identification symptom path to obtain syndrome type A, then it is necessary to calculate the correlations C1, C2 and C3 between symptom a, symptom b, symptom c and candidate syndrome type A respectively.

[0090] Similarly, if candidate syndrome type B also corresponds to the matching number of 3 paths, that is, there are 3 symptom information (such as symptom d, symptom e, symptom f) and syndrome type B is obtained through disease diagnosis symptom path reasoning, then it is necessary to calculate the correlation C4, C5 and C6 between symptom d, symptom e, symptom f and candidate syndrome type B respectively.

[0091] Furthermore, the accumulating unit 2423 is used to accumulate the sum of the correlations of all symptom information in the candidate syndrome type. Specifically, the sum of the correlations of all symptom information in the candidate syndrome type A and the candidate syndrome type B is calculated respectively, that is, the sum of the correlations of all symptom information in the candidate syndrome type A is C1+C2+C3, and the sum of the correlations of all symptom information in the candidate syndrome type B is C4+C5+C6, and the calculated sums of the correlations are sorted.

[0092] The first selection unit 2424 is used to select the candidate syndrome type with the largest sum of correlations as the syndrome type diagnosis result, that is, select the largest one among C1+C2+C3 and C4+C5+C6 as the candidate syndrome type as the syndrome type diagnosis result. It can be understood that the examples in the present application are only illustrative examples. In other implementations, there can also be 3, 4 or 5 candidate syndrome types, and the number of path matching can also be 4, 5, etc., which are not specifically limited here.

[0093] It is understandable that the processing submodule 242 in the present application further includes a second selection unit 2425, which is used to select the candidate symptom with the largest number of path matches as the syndrome diagnosis result when the matching numbers of the candidate syndrome paths in the judgment intersection are not equal. Specifically, if the matching number of the disease identification symptom path corresponding to candidate syndrome A is 4, the matching number of the disease identification symptom path corresponding to candidate syndrome B is 2, and the matching number of the disease identification symptom path corresponding to candidate syndrome C is 3, then candidate syndrome A with 4 matching numbers of disease identification symptom paths is selected as the syndrome diagnosis result.

[0094] In the above implementation, by constructing a TCM diagnosis knowledge graph based on disease symptom identification, eight-category syndrome differentiation diagnosis graph, disease nature syndrome differentiation diagnosis graph, and disease location syndrome differentiation diagnosis graph, the user's four diagnostic information is obtained, and the candidate syndrome types corresponding to the symptom information in the four diagnostic information are matched in the TCM diagnosis knowledge graph according to the four diagnostic information, and the candidate syndrome types are further integrated to obtain the syndrome type diagnosis results. This application fully introduces TCM syndrome differentiation knowledge, so that TCM disease diagnosis has complete knowledge reasoning support, and the generalization and accuracy are improved.

[0095] It should be emphasized that in order to further ensure the privacy and security of the TCM diagnostic map, the above-mentioned TCM diagnostic map can also be stored in a blockchain node.

[0096] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0097] Optionally, the present application provides an embodiment of a disease prediction method based on a TCM diagnostic map. Figure 2 Corresponding to the device embodiment shown, the method can be specifically applied to various computer devices and computer-readable storage media. The specific steps of the disease prediction method based on the TCM diagnosis atlas are as follows:

[0098] A TCM diagnosis knowledge graph is constructed based on disease symptoms, the Eight-Principle Syndrome Differentiation Diagnosis Graph, the Pathology Syndrome Differentiation Diagnosis Graph and the Disease Location Syndrome Differentiation Diagnosis Graph, and each symptom information is initialized with the path weights between the dialectical nodes in the Eight-Principle Syndrome Differentiation Diagnosis Graph, the dialectical nodes in the Pathology Syndrome Differentiation Diagnosis Graph, the dialectical nodes in the Disease Location Syndrome Differentiation Diagnosis Graph and the diseases to obtain a general TCM diagnosis knowledge graph; an adjustment submodule is used to adjust the path weights according to the probability of correspondence between each symptom information in the existing medical records and the dialectical nodes in the Eight-Principle Syndrome Differentiation Diagnosis Graph, the dialectical nodes in the Pathology Syndrome Differentiation Diagnosis Graph, the dialectical nodes in the Disease Location Syndrome Differentiation Diagnosis Graph and the diseases to obtain the TCM diagnosis knowledge graph.

[0099] The user's four diagnostic information is obtained, and the four diagnostic information includes at least symptom information. The user's four diagnostic information can be obtained through existing clinical data and / or disease databases, or through a combination of software and hardware. For example, the patient's facial image and tongue image are obtained, and facial and tongue diagnosis are performed based on the facial image and tongue image to determine the diagnosis result of inspection; the diagnosis result of auscultation is determined by collecting image information of the patient's site and sound information of the heart, stomach, and lungs; the user's voice intention is recognized through voice recognition, and the user's symptom information in the voice information is extracted to achieve the diagnosis result of the interview; the patient's wrist pulse phase information is obtained through, for example, a Bluetooth pulse vibration wristband, so as to achieve the diagnosis result of palpation.

[0100] Match the candidate syndrome type corresponding to the symptom information in the TCM diagnosis knowledge graph. Specifically, obtain the candidate disease corresponding to the symptom information according to the disease identification symptom path, and match the first candidate syndrome type corresponding to the candidate disease in the existing medical records. Match the second candidate syndrome type corresponding to the symptom information in the eight-category syndrome differentiation diagnosis graph, the disease nature syndrome differentiation diagnosis graph, and the disease location syndrome differentiation diagnosis graph.

[0101] Integrate the candidate syndromes to obtain a syndrome diagnosis result, specifically, obtain the intersection of the first candidate syndrome and the second candidate syndrome; process the candidate syndromes in the intersection to obtain the syndrome diagnosis result. Wherein, processing the candidate syndromes in the intersection to obtain the syndrome diagnosis result further includes: obtaining the intersection of the first candidate syndrome and the second candidate syndrome, judging whether the matching numbers of the paths of the candidate syndromes in the intersection are equal, and when judging that the matching numbers of the paths of the candidate syndromes in the intersection are equal, calculating the correlation between the candidate syndromes and the symptom information, sorting the candidate syndromes according to the correlation, and selecting the candidate syndromes with a correlation greater than a threshold correlation as the syndrome diagnosis result.

[0102] In the above implementation, by constructing a TCM diagnosis knowledge graph based on disease symptom identification, eight-category syndrome differentiation diagnosis graph, disease nature syndrome differentiation diagnosis graph, and disease location syndrome differentiation diagnosis graph, the user's four diagnostic information is obtained, and the candidate syndrome types corresponding to the symptom information in the four diagnostic information are matched in the TCM diagnosis knowledge graph according to the four diagnostic information, and the candidate syndrome types are further integrated to obtain the syndrome type diagnosis results. This application fully introduces TCM syndrome differentiation knowledge, so that TCM disease diagnosis has complete knowledge reasoning support, and the generalization and accuracy are improved.

[0103] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0104] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0105] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0106] To solve the above technical problems, the present application also provides a computer device. Fig.10 , Fig.10 This is a basic structural block diagram of the computer device in this embodiment.

[0107] The computer device 10 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0108] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0109] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of a disease prediction method based on a Chinese medicine diagnosis spectrum, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0110] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run the computer-readable instructions or process data stored in the memory 41, such as computer-readable instructions for running the disease prediction method based on the TCM diagnostic map.

[0111] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0112] This embodiment implements the functions of each unit and / or module in the disease prediction device based on the TCM diagnosis map as in the above-mentioned embodiment when the processor executes computer-readable instructions stored in the memory. By constructing a TCM diagnosis knowledge map, the user's four diagnostic information is obtained, and the candidate syndrome types corresponding to the symptom information in the four diagnostic information are matched in the TCM diagnosis knowledge map according to the four diagnostic information. The candidate syndrome types are further integrated to obtain the syndrome type diagnosis results. This application fully introduces TCM syndrome differentiation knowledge, so that there is complete knowledge reasoning support in TCM disease diagnosis, and the generalization and accuracy are improved.

[0113] The present application also provides another implementation mode, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor, so that the at least one processor executes the functions of each unit and / or module in the disease prediction device based on the TCM diagnostic map as described above, obtains the user's four diagnostic information by constructing a TCM diagnostic knowledge map, and obtains candidate syndrome types corresponding to the symptom information in the four diagnostic information in the TCM diagnostic knowledge map according to the four diagnostic information, and further integrates the candidate syndrome types to obtain syndrome type diagnosis results. The present application fully introduces TCM syndrome differentiation knowledge, so that TCM disease diagnosis has complete knowledge reasoning support, and the generalization and accuracy are improved.

[0114] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0115] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A disease prediction device based on TCM diagnostic atlas, characterized in that: The disease prediction device comprises: A construction module is used to construct a TCM diagnosis knowledge map based on disease symptoms, eight-category syndrome differentiation diagnosis map, disease nature syndrome differentiation diagnosis map and disease location syndrome differentiation diagnosis map; wherein the TCM diagnosis knowledge map is divided into three levels, namely, symptom layer nodes, syndrome differentiation theory layer nodes and syndrome type layer nodes; the disease location syndrome differentiation diagnosis map, disease nature syndrome differentiation diagnosis map and eight-category syndrome differentiation diagnosis map share symptom layer nodes and syndrome type layer nodes; A first acquisition module is used to acquire the user's four diagnostic information, wherein the four diagnostic information at least includes symptom information; A matching module, used for matching candidate syndrome types corresponding to the symptom information in the TCM diagnosis knowledge graph; An integration module, used for integrating the candidate syndromes to obtain syndrome diagnosis results; Wherein, the building blocks include: An initialization submodule is used to initialize each symptom information and the dialectical nodes in the eight-category syndrome differentiation diagnosis map, the dialectical nodes in the disease nature syndrome differentiation diagnosis map, the dialectical nodes in the disease location syndrome differentiation diagnosis map, and the path weights between the diseases to obtain a general TCM diagnosis knowledge map; The adjustment submodule is used to adjust the path weight according to the corresponding probabilities between the dialectical nodes in the eight-category syndrome differentiation diagnosis map, the dialectical nodes in the disease nature syndrome differentiation diagnosis map, the dialectical nodes in the disease location syndrome differentiation diagnosis map, and the diseases, so as to obtain the TCM diagnosis knowledge map.

2. The disease prediction device according to claim 1, characterized in that: The matching module comprises: An acquisition submodule, used for acquiring candidate diseases corresponding to the symptom information according to the disease identification symptom path; A first matching submodule, used for matching a first candidate syndrome type corresponding to the candidate disease in the existing medical records; The second matching submodule is used to match the second candidate syndrome type corresponding to the symptom information in the eight-category syndrome differentiation diagnosis map, the disease nature syndrome differentiation diagnosis map and the disease location syndrome differentiation diagnosis map.

3. The disease prediction device according to claim 2, characterized in that: The acquisition submodule includes: A calculation unit, used for calculating the number of matches between the symptom information and the disease identification symptom path, so as to obtain the disease corresponding to the symptom information; A sorting unit, used for sorting the diseases according to the matching number; A selection unit is used to select the disease whose matching number is greater than the threshold matching number as a candidate disease.

4. The disease prediction device according to claim 2, characterized in that: The integration module includes: An acquisition submodule, used for acquiring the intersection of the first candidate syndrome type and the second candidate syndrome type; A processing submodule is used to process the candidate syndrome types in the intersection to obtain the syndrome type diagnosis result.

5. The disease prediction device according to claim 4, characterized in that: The processing submodule comprises: A judging unit, used to judge whether the matching numbers of the paths of the candidate syndrome types in the intersection are equal; A first calculation unit, configured to respectively calculate the correlation between the candidate syndrome and each of the symptom information when it is determined that the matching numbers of the paths of the candidate syndrome in the intersection are equal; An accumulation unit, used for accumulating the sum of the relevance of all the symptom information in the candidate syndrome type; The first selection unit selects the candidate syndrome with the largest sum of correlations as the syndrome diagnosis result.

6. The disease prediction device according to claim 5, characterized in that: The first computing unit comprises: A first calculation subunit is used to respectively calculate a first frequency of occurrence of each symptom information, a second frequency of occurrence of each syndrome type, and a third frequency of co-occurrence of the symptom information and the syndrome type in the intersection; The second calculation subunit is used to calculate the correlation between the syndrome type and the symptom information according to the first frequency, the second frequency and the third frequency.

7. The disease prediction device according to claim 5, characterized in that: The processing submodule also includes: The second selection unit is used to select the candidate symptom with the largest number of matches in the symptom path as the syndrome diagnosis result when it is determined that the matching numbers of the candidate syndrome symptom paths in the intersection are not equal.

8. A computer device comprising a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, it implements the functions of each unit and / or module in the disease prediction device based on the traditional Chinese medicine diagnostic map as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the functions of each unit and / or module in the disease prediction device based on the traditional Chinese medicine diagnostic map as described in any one of claims 1 to 7.

Images