Tunnel disease diagnosis method and system based on knowledge graph

Abstract

The invention discloses a tunnel disease diagnosis method and system based on a knowledge graph, and the method comprises the steps: collecting operation tunnel disease case data, and carrying out the preprocessing of the disease case data; based on the preprocessed operation tunnel disease case data, constructing a tunnel disease case knowledge graph, and performing data mining and analysis on the tunnel disease case knowledge graph; and performing feature matching on the to-be-diagnosed operation tunnel disease case data and the data in the tunnel disease case knowledge graph to obtain similar cases and determine disease causes and proper processing measures. According to the method, a large amount of tunnel disease related data including information such as disease types, causes, geological environment factors and processing measures are integrated by constructing a disease case knowledge graph; according to the method, historical case knowledge, correlation matching and other technologies are utilized to quickly and accurately analyze causes of operation tunnel diseases, appropriate processing measures are recommended according to empirical data in a knowledge graph, and the safety and reliability of tunnel operation are improved.

Description

Technical Field

[0001] The present invention relates to the field of tunnel engineering technology, and in particular to a tunnel disease diagnosis method and system based on a knowledge graph. Background Art

[0002] With the continuous development of transportation infrastructure, the number of operating tunnels is increasing. However, due to the complex environment in which tunnels are located, various diseases are prone to occur during operation, such as cracks, water leakage, lining peeling, etc. These diseases not only affect the service life of the tunnel, but may also pose a threat to driving safety. Therefore, timely and accurate analysis of the causes of diseases and taking effective treatment measures are of great significance to ensure the safe operation of tunnels.

[0003] Traditional tunnel disease cause analysis and treatment measures mainly rely on experience and manual judgment, lacking in systematicness and scientificity. Moreover, due to the diversity and complexity of tunnel diseases, different diseases may be caused by multiple factors, and traditional methods are difficult to comprehensively and accurately analyze the causes of diseases. In addition, the selection of treatment measures also lacks scientific basis and is often blind and arbitrary. Summary of the invention

[0004] The present invention provides a tunnel disease diagnosis method and system based on knowledge graph to solve the problems that traditional tunnel disease cause analysis and treatment measures rely on experience and manual judgment, it is difficult to comprehensively and accurately analyze the cause of the disease, there is a lack of scientific basis for the selection of treatment measures, and there are blindness and arbitrariness.

[0005] According to the first aspect, an embodiment provides a tunnel disease diagnosis method based on a knowledge graph, the method comprising:

[0006] Collect the disease case data of operating tunnels and pre-process the disease case data;

[0007] Based on the pre-processed operational tunnel disease case data, a tunnel disease case knowledge graph is constructed, and data mining and analysis are performed on the tunnel disease case knowledge graph;

[0008] The feature matching of the operational tunnel disease case data to be diagnosed is performed with the data in the tunnel disease case knowledge graph to obtain similar cases and determine the cause of the disease and appropriate treatment measures.

[0009] Furthermore, data on operational tunnel disease cases are collected, including:

[0010] The disease case data includes disease type, disease location, disease occurrence time, disease severity, and tunnel environmental parameters.

[0011] Furthermore, the disease case data is preprocessed, including:

[0012] Remove noisy data, including obvious abnormal data caused by measurement equipment failure or human error;

[0013] Correct erroneous data and amend the erroneous information that occurs during data entry;

[0014] Ensure the accuracy and completeness of data and supplement missing data.

[0015] Furthermore, based on the pre-processed operational tunnel disease case data, a tunnel disease case knowledge graph is constructed, which specifically includes:

[0016] Using ontology construction technology, we define the core concepts in the field of tunnel diseases:

[0017] Tunnel disease: A general term for various adverse conditions that occur in operating tunnels, expressed as a collection of:

[0018] T={t1,t2,t3,....}

[0019] Where T i Represents different specific disease conditions, covering all possible disease conditions;

[0020] Disease type: The specific manifestation of the disease, expressed as a collection:

[0021] D={d1,d2,d3,....}

[0022] Where D i It is a specific manifestation of the disease;

[0023] Causative factors: various possible causes of tunnel diseases, expressed as a set:

[0024] C={c1,c2,c3,....}

[0025] Treatment measures: The solutions adopted for different disease types, expressed as a set:

[0026] M={m1,m2,m3,....}

[0027] Clarify the connotation and extension of the concept:

[0028] Tunnel disease refers to the conditions that affect the normal use and safety performance of the tunnel during operation. It is quantified through evaluation indicators, including the disease severity index:

[0029]

[0030] where ω i Disease type d iThe weight of n is the total number of disease types; the extension includes various specific disease types and a series of problems caused by these diseases;

[0031] The connotation of the disease type is the specific disease manifestation classified according to the appearance characteristics and occurrence location of the disease, which is described by the feature vector; the extension includes various forms of cracks, leakage, and peeling. Each disease type has a specific manifestation and impact range;

[0032] The connotation of causal factors is the various conditions and causes that can cause tunnel diseases, which are measured by the probability of causal factors, including the probability of geological structural instability causing diseases:

[0033]

[0034] where n c1 is the number of cases caused by unstable geological structure, and N is the total number of cases; the extension includes multiple factors such as geology, hydrology, transportation, and construction, and each causal factor has a specific mechanism of action and influencing factors;

[0035] The connotation of treatment measures is the specific actions and methods taken to eliminate or alleviate tunnel diseases, which are evaluated through treatment effect indicators; the extension includes various engineering technical measures and management measures, and each treatment measure has a specific scope of application and implementation conditions;

[0036] Identify the relationships between concepts:

[0037] There is a causal relationship between disease type and causal factors, which can be expressed as a function:

[0038] f: D×C→{0, 1}

[0039] Where f(d i , c j )=1 indicates the disease type d i The causal factor c j As a result, when f(d i , c j ) = 0 means no; the relationship is determined by methods including statistical analysis and causal inference;

[0040] There is a corresponding relationship between disease types and treatment measures, which can be expressed as a function:

[0041] g: D×M→{0, 1}

[0042] Where g(d i , m j )=1 indicates the disease type d i Corresponding treatment measuresc j , when g(d i , m j)=0 indicates no correspondence; the relationship is determined by methods including experience summary and expert knowledge.

[0043] Furthermore, based on the pre-processed operational tunnel disease case data, a tunnel disease case knowledge graph is constructed, which specifically includes:

[0044] Extract key information from the preprocessed disease case data as nodes in the knowledge graph;

[0045] According to the relationships defined in the ontology, the association relationships between entities are extracted from the disease case data as edges in the knowledge graph.

[0046] Furthermore, based on the pre-processed operational tunnel disease case data, a tunnel disease case knowledge graph is constructed, which specifically includes:

[0047] The Neo4j graph database is used to store all entities involved in tunnel disease knowledge and the relationships between entities. Each entity is stored independently according to a specific attribute type. The collected corpus data is sorted out, and the disease case data that does not form a complete closed loop of disease, cause, and treatment measures are removed. Operations including entity alignment, attribute fusion, and relationship fusion are performed, and finally the data is stored in the neo4j graph database.

[0048] Furthermore, data mining and analysis are conducted on the knowledge graph of tunnel disease cases, including:

[0049] Use association rule mining algorithms to analyze a large amount of disease case data in the knowledge graph to find out the potential associations between different disease types and various treatment measures;

[0050] Cluster analysis algorithms including the K-Means algorithm are used to classify disease cases with similar characteristics; for each type of disease, common treatment measures and treatment effects are analyzed to provide a basis for subsequent treatment measure recommendations.

[0051] Furthermore, a cluster analysis algorithm including the K-Means algorithm was used to classify disease cases with similar characteristics, including:

[0052] For the crack disease case, multiple features including crack width, location, and causal factors are used as feature vectors and classified into different categories using a clustering algorithm:

[0053] Assume that the set of crack disease cases is:

[0054] C={c1,c2,c3,....}

[0055] Each case c i Represented as a feature vector where ωi represents the crack width, p i Indicates the occurrence location, f i Indicates causal factors;

[0056] Use clustering algorithm to divide C into K clusters, C = {C1, C2, C3, ..., C K}, so that the cases in each cluster have high similarity;

[0057] Clustering evaluation indicators include silhouette coefficient and Calinski-Harabasz index. Silhouette coefficient is used to measure the closeness of a sample to its cluster and the degree of separation from other clusters. Its value range is between -1 and 1. The larger the value, the better the clustering effect. Calinski-Harabasz index is used to measure the ratio of inter-cluster dispersion to intra-cluster dispersion. The larger the value, the better the clustering effect.

[0058] Furthermore, feature matching is performed between the operational tunnel disease case data to be diagnosed and the data in the tunnel disease case knowledge graph to obtain similar cases and determine the causes of the disease and appropriate treatment measures, including:

[0059] Organize and analyze the case data of operating tunnel diseases to be diagnosed, and extract key features including disease type, location, severity, and environmental parameters;

[0060] The extracted features are matched and compared with the existing data in the knowledge graph. The similarity between the disease cases to be diagnosed and the existing cases in the knowledge graph is calculated by using a similarity calculation algorithm:

[0061] The new disease case feature vector is The feature vector of existing cases in the knowledge graph is Use cosine similarity to calculate the similarity between the two:

[0062]

[0063] in represents the dot product of vectors, and They represent the magnitude of the vector respectively;

[0064] According to the matching results and association rules, suitable treatment measures for the corresponding diseases are screened out from the knowledge graph.

[0065] According to the second aspect, an embodiment provides a tunnel disease diagnosis system based on a knowledge graph, the system comprising:

[0066] Data processing module, used to collect and pre-process the disease case data of operating tunnels;

[0067] The knowledge graph construction module is used to construct a tunnel disease case knowledge graph based on the pre-processed operational tunnel disease case data, and to perform data mining and analysis on the tunnel disease case knowledge graph;

[0068] The disease diagnosis module is used to match the features of the operational tunnel disease case data to be diagnosed with the data in the tunnel disease case knowledge graph, obtain similar cases and determine the cause of the disease and appropriate treatment measures.

[0069] According to a third aspect, an embodiment provides an electronic device, the device comprising: a processor and a memory;

[0070] The memory is used to store one or more program instructions;

[0071] The processor is used to run one or more program instructions to execute the steps of a tunnel disease diagnosis method based on a knowledge graph as described in any of the above items.

[0072] According to the fourth aspect, an embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of a tunnel disease diagnosis method based on a knowledge graph as described in any one of the above items are implemented.

[0073] The present invention provides a tunnel disease diagnosis method and system based on knowledge graph, which integrates and associates a large amount of tunnel disease-related data by constructing a knowledge graph of disease cases, and uses data mining and analysis algorithms to achieve rapid and accurate analysis of the causes of diseases and scientific recommendations for treatment measures.

[0074] Beneficial effects:

[0075] 1. Improve the accuracy and scientificity of disease cause analysis. Through the construction of knowledge graphs and the application of data analysis algorithms, it is possible to comprehensively and accurately find the correlation between disease causes and various factors.

[0076] 2. Make scientific recommendations on treatment measures, and provide reasonable treatment measures to the tunnel management department based on the empirical data in the knowledge graph to avoid blindness and arbitrariness.

[0077] 3. Improving the safety and reliability of tunnel operation, timely and accurately analyzing the causes of defects and taking effective treatment measures can extend the service life of the tunnel and ensure driving safety.

[0078] 4. It has good scalability and adaptability. With the continuous accumulation and updating of tunnel disease data, the knowledge graph can be continuously improved and optimized to adapt to the operation and management needs of tunnels of different types and scales. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 A flow chart of a tunnel disease diagnosis method based on a knowledge graph provided by an embodiment of the present invention;

[0080] Figure 2 A knowledge graph construction principle in a tunnel disease diagnosis method based on a knowledge graph provided by an embodiment of the present invention;

[0081] Figure 3 An entity and attribute relationship diagram in a knowledge graph construction process in a tunnel disease diagnosis method based on a knowledge graph provided by an embodiment of the present invention;

[0082] Figure 4 A knowledge graph display page in a tunnel disease diagnosis method based on a knowledge graph provided by an embodiment of the present invention;

[0083] Figure 5 A diagnostic logic flow chart of a tunnel disease diagnosis method based on a knowledge graph provided by an embodiment of the present invention;

[0084] Figure 6 A schematic diagram of a diagnosis use case in a tunnel disease diagnosis method based on a knowledge graph provided by an embodiment of the present invention;

[0085] Figure 7 A schematic diagram of a disease diagnosis page in a tunnel disease diagnosis method based on a knowledge graph provided by an embodiment of the present invention;

[0086] Figure 8 A schematic diagram of the logical structure of a tunnel disease diagnosis system based on a knowledge graph provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0087] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present invention better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present invention are not shown or described in the specification, this is to avoid the core part of the present invention being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0088] In addition, the features, operations or characteristics described in the specification can be combined in any appropriate manner to form various implementations. At the same time, the steps or actions in the method description can also be interchanged or adjusted in a manner that is obvious to those skilled in the art. Therefore, the various sequences in the specification and the drawings are only for the purpose of clearly describing a certain embodiment and are not meant to be a required sequence, unless otherwise specified that a certain sequence must be followed.

[0089] The first embodiment of the present invention provides a tunnel disease diagnosis method based on knowledge graph. Figure 1 Provide detailed explanation.

[0090] like Figure 1 As shown, in step S100, operating tunnel disease case data is collected and pre-processed.

[0091] (1) Extensive collection of operational tunnel disease case data

[0092] Information on the types of defects includes common cracks (including longitudinal cracks, transverse cracks, mesh cracks and other cracks of different forms), water leakage (such as point leakage, line leakage, surface leakage, etc.), lining spalling (small piece spalling, large area spalling, etc.) and other detailed records of various types of defects such as tunnel deformation, anchor failure, etc.

[0093] The defect location data is accurate to the specific mileage pile number of the tunnel, the location in the tunnel cross section (top, side wall, bottom, etc.) and the location range in the longitudinal section.

[0094] The time of disease occurrence is recorded, including year, month, day and even accurate to the hour, so as to analyze the development trend of the disease over time.

[0095] Assessment data of the severity of the disease, such as the width of the crack (the actual width value measured by high-precision measuring tools), the flow rate of leaking water (data obtained by professional flow monitoring equipment), the area of ​​lining peeling (the area value obtained by using image recognition technology or actual on-site measurement), etc.

[0096] Tunnel environmental parameters, such as the geological conditions of the area where the tunnel is located (including rock type, geological structure, soil properties, etc.), climatic conditions (temperature, humidity, rainfall and other meteorological data), and the final organized disease case data are shown in Tables 1, 2, 3 and 4 below.

[0097] Table 1 Tunnel information table

[0098]

[0099] Table 2 Disease information table

[0100]

[0101] Table 3 Disease cause information table

[0102]

[0103] Table 4 Disease control measures

[0104]

[0105] (2) Clean and organize the collected data

[0106] Remove noise data, such as obvious abnormal data caused by measurement equipment failure or human error. For example, the leakage flow recorded at a certain moment is far beyond the normal range and is very different from the data in the previous and next time periods. After analysis, it is determined to be abnormal data and then removed.

[0107] Correct the wrong data and correct the wrong information that may appear during the data entry process. For example, if the mileage pile number of the diseased location is recorded incorrectly, it will be corrected after comparing it with the actual tunnel drawings and on-site investigations.

[0108] Ensure the accuracy and completeness of the data and supplement the missing data. For example, in some disease cases, the temperature data of environmental parameters is missing, and supplementary data can be collected by querying local meteorological records or installing temporary temperature monitoring equipment in the tunnel.

[0109] like Figure 1 As shown, in step S200, a tunnel disease case knowledge graph is constructed based on the pre-processed operating tunnel disease case data, and data mining and analysis are performed on the tunnel disease case knowledge graph.

[0110] The construction principle of knowledge graph is as follows Figure 2 shown.

[0111] Adopting ontology construction technology:

[0112] Define the core concepts in the field of tunnel diseases, such as "tunnel disease", "disease type", "cause factor", "treatment measures", etc. Clarify the connotation and extension of these concepts. For example, "tunnel disease" includes all kinds of adverse conditions that may occur in operating tunnels; "disease type" covers specific disease manifestations such as cracks, water leakage, lining peeling, etc. Determine the relationship between concepts, such as the "cause" relationship between "disease type" and "cause factor", and the "correspondence" relationship between "disease type" and "treatment measures". Construct an ontology model with clear hierarchy and relationship to lay the foundation for the construction of knowledge graph.

[0113] (1) Define core concepts:

[0114] Tunnel disease: A general term for various adverse conditions that occur in operating tunnels, expressed as a collection of:

[0115] T={t1,t2,t3,....}

[0116] Where T i Represents different specific disease conditions, covering all possible disease conditions;

[0117] Defect type: Specific manifestations of defects, such as cracks, water leakage, lining peeling, etc., expressed as a collection:

[0118] D={d1,d2,d3,....}

[0119] Where D i It is the specific manifestation of horizontal cracks, vertical cracks, point leakage, surface leakage, lining peeling and other specific diseases:

[0120] Causes: Various possible causes of tunnel diseases, such as unstable geological structure, groundwater erosion, construction quality problems, etc., expressed as a set:

[0121] C={c1,c2,c3,....}

[0122] Treatment measures: The solutions adopted for different types of diseases, such as grouting reinforcement, spraying waterproof materials, replacement of lining, etc., are expressed as a set:

[0123] M={m1,m2,m3,....}

[0124] (2) Clarify the connotation and extension of the concept:

[0125] Tunnel disease refers to the conditions that affect the normal use and safety performance of the tunnel during operation, which can be quantified by some evaluation indicators, such as the disease severity index:

[0126]

[0127] where ω i Disease type d i The weight of n is the total number of disease types; the extension includes various specific disease types and a series of problems caused by these diseases, such as traffic congestion, safety risks, etc.

[0128] The connotation of the disease type is the specific manifestation of the disease classified according to the appearance characteristics of the disease, the location of occurrence, etc., which can be described by a feature vector. For example, for cracks, it can be represented by a vector composed of crack length, width, depth and other features. The extension includes various forms of cracks, leakage, peeling, etc. Each disease type has its specific manifestation and impact range;

[0129] The connotation of causal factors is the various conditions and causes that can cause tunnel diseases, which can be measured by the probability of causal factors, such as the probability of geological structural instability leading to diseases:

[0130]

[0131] where n c1 is the number of cases of diseases caused by unstable geological structure, and N is the total number of cases; the extension includes factors such as geology, hydrology, transportation, and construction. Each causal factor has its specific mechanism of action and influencing factors;

[0132] The connotation of treatment measures is the specific actions and methods taken to eliminate or alleviate tunnel diseases, which can be evaluated through treatment effect indicators, such as the recurrence rate of diseases after treatment, treatment costs, etc. The extension includes various engineering technical measures and management measures, and each treatment measure has its specific scope of application and implementation conditions.

[0133] (3) Determine the relationship between concepts:

[0134] There is a causal relationship between disease type and causal factors, which can be expressed as a function:

[0135] f: D×C→{0, 1}

[0136] Where f(d i , c j )=1 indicates the disease type d i The causal factor c j As a result, when f(d i , c j )=0 means no; this relationship can be determined by statistical analysis, causal inference and other methods;

[0137] There is a corresponding relationship between disease types and treatment measures, which can be expressed as a function:

[0138] g: D×M→{0, 1}

[0139] Where g(d i , m j )=1 indicates the disease type d i Corresponding treatment measuresc j , when g(d i , m j )=0 indicates no correspondence; this relationship can be determined through experience summary, expert knowledge and other methods.

[0140] like Figure 3 As shown, using entity recognition and relationship extraction technology:

[0141] (1) Entity recognition: Extract key information from the organized disease case data as nodes in the knowledge graph. For example, each disease type (such as "horizontal cracks", "point leakage", etc.), each specific disease location (such as "side wall at K10+500"), and each environmental parameter value (such as "temperature 25℃", "humidity 70%", etc.) are identified as independent entity nodes.

[0142] (2) Relationship extraction: Based on the relationships defined in the ontology, the associations between entities are extracted from the damage case data as edges in the knowledge graph. For example, if it is analyzed from a damage case that "the transverse cracks on the side wall at K10+500 are caused by the unstable geological structure in the area and the long-term impact of large vehicle vibrations, and the treatment measures are to use grouting reinforcement and add shock-absorbing devices", then the "cause" relationship edge between the "transverse cracks on the side wall at K10+500" node and the cause factor nodes such as "unstable geological structure" and "long-term impact of large vehicle vibrations" can be extracted, as well as the "corresponding" relationship edge between the treatment measure node "grouting reinforcement and adding shock-absorbing devices" can be extracted.

[0143] The knowledge graph display page constructed is as follows Figure 4 shown.

[0144] Data mining and analysis based on knowledge graph:

[0145] (1) Use association rule mining algorithms to analyze a large amount of disease case data in the knowledge graph to find out the potential associations between different disease types and various treatment measures. For example, through analysis, it is found that when a certain type of crack appears and its width is within a certain range, and the humidity in the area where the tunnel is located is high, the success rate of using a certain grouting material and construction process for treatment is higher. In this way, association rules between disease characteristics and treatment measures can be established.

[0146] (2) Use cluster analysis algorithms to classify disease cases with similar characteristics. For example, crack disease cases with similar crack widths, similar locations, and similar causes are grouped together. For each type of disease, analyze its commonly used treatment measures and treatment effects to provide a basis for subsequent treatment measure recommendations.

[0147] For crack disease cases, the crack width, location, and causal factors are used as feature vectors and classified into different categories using a clustering algorithm:

[0148] Assume that the set of crack disease cases is:

[0149] C={c1,c2,c3,....}

[0150] Each case c iRepresented as a feature vector where ω i represents the crack width, p i Indicates the occurrence location, f i Indicates causal factors;

[0151] Use clustering algorithm to divide C into K clusters, C = {C1, C2, C3, ..., C K}, so that the cases in each cluster have high similarity;

[0152] Commonly used clustering evaluation indicators include silhouette coefficient and Calinski-Harabasz index. Silhouette coefficient is used to measure the closeness of a sample to its cluster and the degree of separation from other clusters. Its value range is between -1 and 1. The larger the value, the better the clustering effect. Calinski-Harabasz index is used to measure the ratio of inter-cluster dispersion to intra-cluster dispersion. The larger the value, the better the clustering effect.

[0153] Based on the analysis results, a cause analysis report can also be provided for operating tunnel diseases. The cause analysis report includes a detailed description of the cause of the disease, the degree of influence of related factors and other information.

[0154] like Figure 1 As shown, in step S300, feature matching is performed between the operational tunnel disease case data to be diagnosed and the data in the tunnel disease case knowledge graph to obtain similar cases and determine the cause of the disease and appropriate treatment measures.

[0155] Organize and analyze the case data of operating tunnel diseases to be diagnosed, and extract key features including disease type, location, severity, and environmental parameters;

[0156] The extracted features are matched and compared with the existing data in the knowledge graph. The similarity between the disease cases to be diagnosed and the existing cases in the knowledge graph is calculated by using a similarity calculation algorithm:

[0157] The new disease case feature vector is The feature vector of existing cases in the knowledge graph is Use cosine similarity to calculate the similarity between the two:

[0158]

[0159] in represents the dot product of vectors, and They represent the magnitude of the vector respectively;

[0160] According to the matching results, suitable treatment measures for the corresponding diseases are screened from the knowledge graph. The treatment measures recommended include but are not limited to suggestions on maintenance methods, construction technology, material selection, etc. For example, based on the experience of similar cases, it is recommended to use a certain waterproof material to seal the cracks and add drainage facilities on the top of the tunnel to reduce the impact of rainwater penetration. The diagnostic logic is as follows: Figure 5 Diagnostic examples include Figure 6 The disease diagnosis page is as shown. Figure 7 shown.

[0161] At the same time, considering the complexity and diversity of the actual situation, a variety of alternative treatment measures can be provided, and the advantages and disadvantages of each measure can be analyzed and explained. For example, in addition to the above recommended treatment measures, another solution can be provided to use reinforcement materials to strengthen the top of the tunnel as a whole, and explain the characteristics of this solution, such as higher cost but more lasting effect, so that the tunnel management department can choose according to the actual situation.

[0162] Corresponding to the above-disclosed tunnel disease diagnosis method based on knowledge graph, the embodiment of the present invention also discloses a tunnel disease diagnosis system based on knowledge graph, such as Figure 8 As shown, it specifically includes:

[0163] Data processing module, used to collect and pre-process the disease case data of operating tunnels;

[0164] The knowledge graph construction module is used to construct a tunnel disease case knowledge graph based on the pre-processed operational tunnel disease case data, and to perform data mining and analysis on the tunnel disease case knowledge graph;

[0165] The disease diagnosis module is used to match the features of the operational tunnel disease case data to be diagnosed with the data in the tunnel disease case knowledge graph, obtain similar cases and determine the cause of the disease and appropriate treatment measures.

[0166] It should be noted that, for the detailed description of a tunnel disease diagnosis system based on a knowledge graph provided in an embodiment of the present invention, reference can be made to the relevant description of a tunnel disease diagnosis method based on a knowledge graph provided in an embodiment of the present invention, which will not be repeated here.

[0167] In addition, an embodiment of the present invention also provides an electronic device, comprising: a processor and a memory; the memory is used to store one or more program instructions; the processor is used to run one or more program instructions to execute the steps of a tunnel disease diagnosis method based on a knowledge graph as described in any of the above items.

[0168] It should be noted that, for the detailed description of an electronic device provided in an embodiment of the present invention, reference can be made to the relevant description of a tunnel disease diagnosis method based on a knowledge graph provided in an embodiment of the present invention, which will not be repeated here.

[0169] In addition, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of a tunnel disease diagnosis method based on a knowledge graph as described in any of the above items are implemented.

[0170] It should be noted that, for a detailed description of a computer-readable storage medium provided in an embodiment of the present invention, reference can be made to the relevant description of a tunnel disease diagnosis method based on a knowledge graph provided in an embodiment of the present invention, which will not be repeated here.

[0171] Those skilled in the art will appreciate that all or part of the functions of the various methods in the above-mentioned embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to implement the above-mentioned functions. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the above-mentioned functions can be implemented. In addition, when all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can also be stored in a storage medium such as a server, another computer, disk, optical disk, flash disk or mobile hard disk, and can be downloaded or copied and saved in the memory of the local device, or the system of the local device is updated, and when the program in the memory is executed by the processor, all or part of the functions in the above-mentioned embodiments can be implemented.

[0172] The above specific examples are used to illustrate the present invention, which is only used to help understand the present invention and is not intended to limit the present invention. For those skilled in the art, according to the concept of the present invention, some simple deductions, modifications or substitutions can be made.

Claims

1. A tunnel disease diagnosis method based on knowledge graph, characterized in that: The method comprises: Collect the disease case data of operating tunnels and pre-process the disease case data; Based on the pre-processed operational tunnel disease case data, a tunnel disease case knowledge graph is constructed, and data mining and analysis are performed on the tunnel disease case knowledge graph; The feature matching of the operational tunnel disease case data to be diagnosed is performed with the data in the tunnel disease case knowledge graph to obtain similar cases and determine the cause of the disease and appropriate treatment measures.

2. A tunnel disease diagnosis method based on knowledge graph according to claim 1, characterized in that: Collect data on operational tunnel disease cases, including: The disease case data includes disease type, disease location, disease occurrence time, disease severity, and tunnel environmental parameters.

3. The tunnel disease diagnosis method based on knowledge graph according to claim 1, characterized in that: Preprocess the disease case data, including: Remove noisy data, including obvious abnormal data caused by measurement equipment failure or human error; Correct erroneous data and amend the erroneous information that occurs during data entry; Ensure the accuracy and completeness of data and supplement missing data.

4. The tunnel disease diagnosis method based on knowledge graph according to claim 1, characterized in that: Based on the pre-processed operational tunnel disease case data, a tunnel disease case knowledge graph is constructed, including: Using ontology construction technology, we define the core concepts in the field of tunnel diseases: Tunnel disease: A general term for various adverse conditions that occur in operating tunnels, expressed as a collection of: T={t1,t2,t3,....} Where T i Represents different specific disease conditions, covering all possible disease conditions; Disease type: The specific manifestation of the disease, expressed as a collection: D={d1,d2,d3,....} Where D i It is a specific manifestation of the disease; Causative factors: various possible causes of tunnel diseases, expressed as a set: C={c1,c2,c3,....} Treatment measures: The solutions adopted for different disease types, expressed as a set: M={m1,m2,m3,....} Clarify the connotation and extension of the concept: Tunnel disease refers to the conditions that affect the normal use and safety performance of the tunnel during operation. It is quantified through evaluation indicators, including the disease severity index: where ω i Disease type d i The weight of n is the total number of disease types; the extension includes various specific disease types and a series of problems caused by these diseases; The connotation of the disease type is the specific disease manifestation classified according to the appearance characteristics and occurrence location of the disease, which is described by the feature vector; the extension includes various forms of cracks, leakage, and peeling. Each disease type has a specific manifestation and impact range; The connotation of causal factors is the various conditions and causes that can cause tunnel diseases, which are measured by the probability of causal factors, including the probability of geological structural instability causing diseases: where n c1 is the number of cases caused by unstable geological structure, and N is the total number of cases; the extension includes multiple factors such as geology, hydrology, transportation, and construction, and each causal factor has a specific mechanism of action and influencing factors; The connotation of treatment measures is the specific actions and methods taken to eliminate or alleviate tunnel diseases, which are evaluated through treatment effect indicators; the extension includes various engineering technical measures and management measures, and each treatment measure has a specific scope of application and implementation conditions; Identify the relationships between concepts: There is a causal relationship between disease type and causal factors, which can be expressed as a function: f: D×C→{0, 1} Where f(d i , c j )=1 indicates the disease type d i The causal factor c j As a result, when f(d i , c j ) = 0 means no; the relationship is determined by methods including statistical analysis and causal inference; There is a corresponding relationship between disease types and treatment measures, which can be expressed as a function: g: D×M→{0, 1} Where g(d i , m j )=1 indicates the disease type d i Corresponding treatment measuresc j , when g(d i , m j )=0 indicates no correspondence; the relationship is determined by methods including experience summary and expert knowledge.

5. A tunnel disease diagnosis method based on knowledge graph as claimed in claim 4, characterized in that: Based on the pre-processed operational tunnel disease case data, a tunnel disease case knowledge graph is constructed, including: Extract key information from the preprocessed disease case data as nodes in the knowledge graph; According to the relationships defined in the ontology, the association relationships between entities are extracted from the disease case data as Edges in the knowledge graph.

6. A tunnel disease diagnosis method based on knowledge graph as claimed in claim 5, characterized in that: Based on the pre-processed operational tunnel disease case data, a tunnel disease case knowledge graph is constructed, including: The Neo4j graph database is used to store all entities involved in tunnel disease knowledge and the relationships between entities. Each entity is stored independently according to a specific attribute type. The collected corpus data is sorted out, and the disease case data that does not form a complete closed loop of disease, cause, and treatment measures are removed. Operations including entity alignment, attribute fusion, and relationship fusion are performed, and finally the data is stored in the neo4j graph database.

7. The tunnel disease diagnosis method based on knowledge graph according to claim 1, characterized in that: Data mining and analysis of the knowledge graph of tunnel disease cases, including: Use association rule mining algorithms to analyze a large amount of disease case data in the knowledge graph to find out the potential associations between different disease types and various treatment measures; Cluster analysis algorithms including the K-Means algorithm are used to classify disease cases with similar characteristics; for each type of disease, common treatment measures and treatment effects are analyzed to provide a basis for subsequent treatment measure recommendations.

8. The tunnel disease diagnosis method based on knowledge graph according to claim 7, characterized in that: Cluster analysis algorithms including the K-Means algorithm were used to classify disease cases with similar characteristics, including: For the crack disease case, multiple features including crack width, location, and causal factors are used as feature vectors and classified into different categories using a clustering algorithm: Assume that the set of crack disease cases is: C = {c1, c2, c3, ...} Each case c i Represented as a feature vector where ω i represents the crack width, p i Indicates the occurrence location, f i Indicates causal factors; Using clustering algorithm, C is divided into K clusters, C = {C1, C2, C3, ..., C K }, so that the cases in each cluster have high similarity; Clustering evaluation indicators include silhouette coefficient and Calinski-Harabasz index; silhouette coefficient is used to measure the closeness of a sample to its cluster and the degree of separation from other clusters. The value range is between -1 and 1. The larger the value, the better the clustering effect. Calinski-Harabasz index is used to measure the ratio of inter-cluster dispersion to intra-cluster dispersion. The larger the value, the better the clustering effect.

9. The tunnel disease diagnosis method based on knowledge graph according to claim 1, characterized in that: The data of the operating tunnel disease cases to be diagnosed are matched with the data in the tunnel disease case knowledge graph to obtain similar cases and determine the causes of the disease and appropriate treatment measures, including: Organize and analyze the case data of operating tunnel diseases to be diagnosed, and extract key features including disease type, location, severity, and environmental parameters; The extracted features are matched and compared with the existing data in the knowledge graph. The similarity between the disease cases to be diagnosed and the existing cases in the knowledge graph is calculated by using a similarity calculation algorithm: The new disease case feature vector is The feature vector of existing cases in the knowledge graph is Use cosine similarity to calculate the similarity between the two: in represents the dot product of vectors, and They represent the magnitude of the vector respectively; According to the matching results and association rules, suitable treatment measures for the corresponding diseases are screened out from the knowledge graph.

10. A tunnel disease diagnosis system based on knowledge graph, characterized in that: The system comprises: Data processing module, used to collect and pre-process the disease case data of operating tunnels; The knowledge graph construction module is used to construct a tunnel disease case knowledge graph based on the pre-processed operational tunnel disease case data, and to perform data mining and analysis on the tunnel disease case knowledge graph; The disease diagnosis module is used to match the features of the operational tunnel disease case data to be diagnosed with the data in the tunnel disease case knowledge graph, obtain similar cases and determine the cause of the disease and appropriate treatment measures.

Images