Water supply network safety evaluation system and method based on multi-dimensional data fusion

Abstract

The invention belongs to the technical field of pipe network management. The invention provides a water supply network safety evaluation system and method based on multi-dimensional data fusion. The method comprises the following steps: a data acquisition module collects static data and dynamic data of a water supply network; the data processing module is used for further processing and processing the static data and the dynamic data collected by the data acquisition module; the static data and the dynamic data processed by the data processing module are input into a model prediction module, and the safety level of the water supply network is predicted; the risk assessment module generates a safety risk assessment report of the water supply network based on the safety level of the water supply network in combination with urgency of user demands, road traffic flow intensity and geographical particularity of pipeline layout; and the decision support module formulates a priority repair and transformation strategy according to the security risk assessment report. According to the method, a more reasonable priority repair and transformation strategy can be formulated, the complexity of water supply network transformation is reduced, and the transformation effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pipe network management, and in particular to a water supply pipe network safety assessment system and method based on multi-dimensional data fusion. Background Art

[0002] Urban areas have dense underground pipeline networks, facing complex pipeline conditions and frequent road traffic pressure, which brings huge challenges to the renewal and upgrading of drinking water supply pipelines. Traditional pipeline network renovation decisions are often based only on pipe conditions, ignoring key factors such as the urgency of user needs, road traffic flow intensity, and the geographical specificity of pipeline layout, resulting in high complexity, difficulty and poor results of renovation projects.

[0003] The present invention aims to improve the above technical problems. Summary of the invention

[0004] In this regard, the present invention provides a water supply network safety assessment method, system, electronic equipment, computer storage medium and computer program product based on multi-dimensional data fusion to solve the above-mentioned technical problems.

[0005] The present invention discloses a water supply network safety assessment method based on multi-dimensional data fusion, the method comprising the following steps:

[0006] The data acquisition module collects static data and dynamic data of the water supply network; wherein the static data at least includes pipe length, pipe diameter, and pipe material characteristics, and the dynamic data at least includes historical maintenance records and causes of damage;

[0007] The data processing module further processes and handles the static data and the dynamic data collected by the data acquisition module;

[0008] The static data and the dynamic data processed by the data processing module are input into a model prediction module, and the model prediction module predicts the safety level of the water supply network; wherein the model prediction module is an XgBoost model;

[0009] The risk assessment module generates a safety risk assessment report for the water supply network based on the safety level of the water supply network predicted by the model prediction module, combined with the urgency of user needs, road traffic flow intensity, and geographical specificity of pipeline layout;

[0010] The decision support module formulates a priority repair and transformation strategy based on the safety risk assessment report generated by the risk assessment module.

[0011] Optionally, the data acquisition module collects static data and dynamic data of the water supply network, including:

[0012] The data acquisition module obtains the static data of the water supply network by means of database query, and the data acquisition module collects the dynamic data of the water supply network through multi-source approaches, wherein the multi-source approaches include sensor upload, database query and user feedback.

[0013] Optionally, the data processing module further processes and handles the static data and the dynamic data collected by the data acquisition module, including:

[0014] The data processing module includes a data preprocessing part and a feature engineering part;

[0015] The data preprocessing part is responsible for processing the missing values ​​and abnormal values ​​in the collected original static data and dynamic data to ensure the accuracy and reliability of the data;

[0016] The feature engineering part is responsible for extracting preliminary features from the static data and the dynamic data processed by the data preprocessing part, and optimizing the preliminary features by performing feature selection and feature scaling on the preliminary features to obtain target features; the target features are used to be input into the model prediction module.

[0017] Optionally, before inputting the static data and the dynamic data processed by the data processing module into the model prediction module, the method further includes:

[0018] Determine target parameters of the model prediction module, and generate training constraints based on the target parameters; wherein the target parameters include at least tree depth, subtree weight, regularization parameter and learning rate;

[0019] Under the constraints of the training constraints, the model prediction module is trained in the first stage using the first set of training data until a convergence condition is reached, so as to achieve tuning of only the target parameters of the model prediction module;

[0020] In the second stage, the model prediction module is trained in the second stage using the second set of training data until the convergence condition is reached; wherein the second stage training does not use the training constraints, that is, all parameters of the model prediction module are tuned.

[0021] Optionally, the risk assessment module generates a safety risk assessment report for the water supply network based on the safety level of the water supply network predicted by the model prediction module, combined with the urgency of user needs, road traffic flow intensity, and geographical specificity of pipeline layout, including:

[0022] Obtain the urgency of the user demand, the road traffic flow intensity, and the geographical specificity of the pipeline layout related to the water supply network to be renovated, and use the semantic analysis plug-in to extract semantic features from these related information;

[0023] The extracted semantic features and the safety level of the water supply network are input into the risk assessment module, and the risk assessment module predicts the necessary value for transformation; wherein the risk assessment module is constructed based on a large language model;

[0024] The safety risk assessment report is generated based on the necessary transformation value, the urgency of the user needs, the road traffic flow intensity, the geographical specificity of the pipeline layout and the safety level of the water supply network, as well as a preset report template.

[0025] Optionally, the decision support module formulates a priority repair and transformation strategy according to the safety risk assessment report generated by the risk assessment module, including:

[0026] The decision support module selects key information from the safety risk assessment report, the key information including the necessary value for transformation and the safety level of the water supply network, and determines the water supply network segment to be repaired first by combining the static data and the dynamic data;

[0027] The decision support module screens the road traffic flow intensity and the geographical specificity of the pipeline layout from the safety risk assessment report, and determines the reconstruction strategy for the water supply network section that needs to be repaired first based on the road traffic flow intensity and the geographical specificity of the pipeline layout.

[0028] The present invention also discloses a water supply network safety assessment system based on multi-dimensional data fusion, the system comprising a data acquisition module, a data processing module, a model prediction module, a risk assessment module, and a decision support module; wherein,

[0029] The data acquisition module is used to collect static data and dynamic data of the water supply network; wherein the static data at least includes pipe length, pipe diameter, and pipe material characteristics, and the dynamic data at least includes historical maintenance records and causes of damage;

[0030] The data processing module is used to further process and handle the static data and the dynamic data collected by the data acquisition module;

[0031] The model prediction module is used to predict the safety level of the water supply network based on the static data and the dynamic data processed by the data processing module; wherein the model prediction module is an XgBoost model;

[0032] The risk assessment module is used to generate a safety risk assessment report for the water supply network based on the safety level of the water supply network predicted by the model prediction module, combined with the urgency of user needs, road traffic flow intensity, and geographical specificity of pipeline layout;

[0033] The decision support module is used to formulate a priority repair and transformation strategy based on the safety risk assessment report generated by the risk assessment module.

[0034] The present invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement any of the above methods.

[0035] The present invention also discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0036] The present invention also discloses a computer program product, wherein the computer program product includes a computer program, and the computer program is executed by a processor of an electronic device to implement any of the above methods.

[0037] The beneficial effects of the present invention are at least:

[0038] The present invention uses the XgBoost model to accurately predict the safety level of the water supply network. It also combines the urgency of user needs, road traffic flow intensity, and the geographical specificity of pipeline layout to generate a safety risk assessment report for the water supply network, thereby formulating a more reasonable priority repair and renovation strategy, reducing the complexity of water supply network renovation and improving the renovation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 It is a flow chart of a water supply network safety assessment method based on multi-dimensional data fusion disclosed in an embodiment of the present invention;

[0041] Figure 2 It is a structural schematic diagram of a water supply network safety assessment system based on multi-dimensional data fusion disclosed in an embodiment of the present invention;

[0042] Figure 3It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0044] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0045] like Figure 1 As shown, an embodiment of the present invention discloses a water supply network safety assessment method based on multi-dimensional data fusion, the method comprising the following steps:

[0046] The data acquisition module collects static data and dynamic data of the water supply network; wherein the static data at least includes pipe length, pipe diameter, and pipe material characteristics, and the dynamic data at least includes historical maintenance records and causes of damage;

[0047] The data processing module further processes and handles the static data and the dynamic data collected by the data acquisition module;

[0048] The static data and the dynamic data processed by the data processing module are input into a model prediction module, and the model prediction module predicts the safety level of the water supply network; wherein the model prediction module is an XgBoost model;

[0049] The risk assessment module generates a safety risk assessment report for the water supply network based on the safety level of the water supply network predicted by the model prediction module, combined with the urgency of user needs, road traffic flow intensity, and geographical specificity of pipeline layout;

[0050] The decision support module formulates a priority repair and transformation strategy based on the safety risk assessment report generated by the risk assessment module.

[0051] The present invention uses the XgBoost model to accurately predict the safety level of the water supply network. It also combines the urgency of user needs, road traffic flow intensity, and the geographical specificity of pipeline layout to generate a safety risk assessment report for the water supply network, thereby formulating a more reasonable priority repair and renovation strategy, reducing the complexity of water supply network renovation and improving the renovation effect.

[0052] Optionally, the data acquisition module collects static data and dynamic data of the water supply network, including:

[0053] The data acquisition module obtains the static data of the water supply network by means of database query, and the data acquisition module collects the dynamic data of the water supply network through multi-source approaches, wherein the multi-source approaches include sensor upload, database query and user feedback.

[0054] In this embodiment, the data acquisition module can collect static data and dynamic data of the water supply network through various channels and perform preliminary processing to provide a basis for subsequent data processing and model prediction.

[0055] Optionally, the data processing module further processes and handles the static data and the dynamic data collected by the data acquisition module, including:

[0056] The data processing module includes a data preprocessing part and a feature engineering part;

[0057] The data preprocessing part is responsible for processing the missing values ​​and abnormal values ​​in the collected original static data and dynamic data to ensure the accuracy and reliability of the data;

[0058] The feature engineering part is responsible for extracting preliminary features from the static data and the dynamic data processed by the data preprocessing part, and optimizing the preliminary features by performing feature selection and feature scaling on the preliminary features to obtain target features; the target features are used to be input into the model prediction module.

[0059] In this embodiment, the data preprocessing part removes data quality problems such as missing values ​​and outliers in the original data, which can ensure the accuracy and reliability of the data. The feature engineering part preprocesses the original data to ensure the accuracy and reliability of the data, thereby improving the prediction accuracy of the model prediction module; and when the model prediction module is pre-trained using the preprocessed original data, the efficiency of model training can also be improved.

[0060] Among them, the target features extracted by the feature engineering part are used to be input into the model prediction module, so there is no need to input static data and dynamic data into the model prediction module.

[0061] Optionally, before inputting the static data and the dynamic data processed by the data processing module into the model prediction module, the method further includes:

[0062] Determine target parameters of the model prediction module, and generate training constraints based on the target parameters; wherein the target parameters include at least tree depth, subtree weight, regularization parameter and learning rate;

[0063] Under the constraints of the training constraints, the model prediction module is trained in the first stage using the first set of training data until a convergence condition is reached, so as to achieve tuning of only the target parameters of the model prediction module;

[0064] In the second stage, the model prediction module is trained in the second stage using the second set of training data until the convergence condition is reached; wherein the second stage training does not use the training constraints, that is, all parameters of the model prediction module are tuned.

[0065] In this embodiment, the model prediction module needs to be pre-trained before being used. Different from the traditional full parameter tuning training method, the present invention divides the training process into two stages, namely:

[0066] Phase 1: During the training process, multiple parameters of the model prediction module are tuned, and the tree depth, subtree weight, regularization parameter, and learning rate are selected as target parameters to form training constraints. During the training process of this phase, the training constraints need to be used to limit the tuning of the above target parameters of the model prediction module, without tuning other parameters.

[0067] The second stage: Use the second set of training data to perform regular training on the model prediction module, that is, cancel the training constraints and use the second set of training data to tune all tunable parameters of the model prediction module.

[0068] The advantage of setting up the above two-stage training method is that, under the constraints of training constraints, the training speed of the model prediction module can be significantly improved, so that it can quickly have acceptable prediction capabilities, and then the conventional training method is used to perform secondary training on the quickly trained model prediction model to achieve overall optimization of the model parameters, so that it has better prediction capabilities.

[0069] It should be noted that, in the first stage, the parameters of the model prediction module other than the target parameters can be set to preset fixed values ​​using the above training constraints, so that these parameters are not tuned in the first stage of training. Also, the data volume of the first set of training data in the first stage depends on the number of parameters of the target parameters. Specifically, the data volume of the first set of training data is positively correlated with the number of parameters.

[0070] In addition, the model prediction module in the present invention adopts the XgBoost model. XgBoost (eXtreme Gradient Boosting) is an efficient, flexible and scalable machine learning algorithm based on gradient boosting. It performs very well in dealing with regression and classification problems and is widely used in various data competitions and practical applications. The following is a detailed introduction to the XGBoost model:

[0071] Loss function optimization: XGBoost uses Taylor expansion to approximate the loss function to better estimate the loss of each sample. The loss function includes the difference between the predicted value and the actual value, as well as a regularization term to control the complexity of the model.

[0072] Tree model construction: XGBoost iteratively trains multiple decision tree models and combines them into a powerful ensemble model. In each iteration, a new tree model is learned to fit the residuals of the current model, thereby gradually optimizing the model's predictive power.

[0073] Regularization term: XGBoost introduces regularization terms to control the complexity of the model and prevent overfitting. Regularization terms include the number of leaf nodes, the score of leaf nodes, etc., which can be adjusted through parameters.

[0074] Objective function: The objective function of XGBoost is the weighted sum of the loss function and the regularization term. In each iteration, an attempt is made to find a new tree model that minimizes the objective function.

[0075] Model update: XGBoost uses a greedy algorithm to gradually build a tree model. Each iteration will learn a new tree model to reduce the objective function. Model update includes leaf node splitting and leaf node weight update.

[0076] Optionally, the risk assessment module generates a safety risk assessment report for the water supply network based on the safety level of the water supply network predicted by the model prediction module, combined with the urgency of user needs, road traffic flow intensity, and geographical specificity of pipeline layout, including:

[0077] Obtain the urgency of the user demand, the road traffic flow intensity, and the geographical specificity of the pipeline layout related to the water supply network to be renovated, and use the semantic analysis plug-in to extract semantic features from these related information;

[0078] The extracted semantic features and the safety level of the water supply network are input into the risk assessment module, and the risk assessment module predicts the necessary value for transformation; wherein the risk assessment module is constructed based on a large language model;

[0079] The safety risk assessment report is generated based on the necessary transformation value, the urgency of the user needs, the road traffic flow intensity, the geographical specificity of the pipeline layout and the safety level of the water supply network, as well as a preset report template.

[0080] In this embodiment, after obtaining relevant information such as the urgency of user needs related to the water supply network to be renovated, the intensity of road traffic flow, and the geographical specificity of the pipeline layout, since these information contain a lot of unstructured data, it is necessary to first use a semantic analysis plug-in to extract semantic features from them, and then use a risk assessment module to conduct an in-depth analysis of the semantic features and the safety level of the water supply network determined above to obtain the predicted necessary value for renovation. Among them, the risk assessment module is constructed based on a large language model, such as a BERT model. The BERT model can conduct a comprehensive analysis of the simplified semantic features and the safety level of the water supply network to obtain the necessary value for renovation. The necessary value for renovation is used to characterize the estimated necessity for renovation of the water supply network to be renovated. Obviously, the higher the necessary value for renovation, the higher the corresponding necessity for renovation.

[0081] Then, the necessary transformation value, the urgency of user demand, the road traffic flow intensity, the geographical specificity of pipeline layout and the safety level of the water supply network are filled into the corresponding positions of the preset report template to generate a safety risk assessment report. Among them, the urgency of user demand, the road traffic flow intensity and the geographical specificity of pipeline layout are used to discuss the necessary transformation value.

[0082] Optionally, the decision support module formulates a priority repair and transformation strategy according to the safety risk assessment report generated by the risk assessment module, including:

[0083] The decision support module selects key information from the safety risk assessment report, the key information including the necessary value for transformation and the safety level of the water supply network, and determines the water supply network segment to be repaired first by combining the static data and the dynamic data;

[0084] The decision support module screens the road traffic flow intensity and the geographical specificity of the pipeline layout from the safety risk assessment report, and determines the reconstruction strategy for the water supply network section that needs to be repaired first based on the road traffic flow intensity and the geographical specificity of the pipeline layout.

[0085] In this embodiment, the decision support module determines the water supply network segment that should be repaired first based on the necessary renovation value in the safety risk assessment report, the safety level of the water supply network, and the static data and dynamic data of each water supply network segment. Then, based on the road traffic flow intensity of the water supply network segment and the geographical characteristics of the pipeline layout, a suitable renovation strategy is determined to reduce the impact on road traffic and reduce the difficulty and cost of renovation.

[0086] Among them, a variety of transformation strategies are preset. These transformation strategies are extracted from other water supply network transformation examples. They correspond to various road traffic flow intensities and geographical characteristics of pipeline layouts. Appropriate transformation strategies can be obtained through matching and screening.

[0087] like Figure 2 As shown, the embodiment of the present invention also discloses a water supply network safety assessment system based on multi-dimensional data fusion, the system includes a data acquisition module, a data processing module, a model prediction module, a risk assessment module, and a decision support module; wherein,

[0088] The data acquisition module is used to collect static data and dynamic data of the water supply network; wherein the static data at least includes pipe length, pipe diameter, and pipe material characteristics, and the dynamic data at least includes historical maintenance records and causes of damage;

[0089] The data processing module is used to further process and handle the static data and the dynamic data collected by the data acquisition module;

[0090] The model prediction module is used to predict the safety level of the water supply network based on the static data and the dynamic data processed by the data processing module; wherein the model prediction module is an XgBoost model;

[0091] The risk assessment module is used to generate a safety risk assessment report for the water supply network based on the safety level of the water supply network predicted by the model prediction module, combined with the urgency of user needs, road traffic flow intensity, and geographical specificity of pipeline layout;

[0092] The decision support module is used to formulate a priority repair and transformation strategy based on the safety risk assessment report generated by the risk assessment module.

[0093] like Figure 3 As shown, an embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in the aforementioned embodiment.

[0094] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the above embodiment.

[0095] An embodiment of the present invention further discloses a computer program product, wherein the computer program product includes a computer program, and the computer program is executed by a processor of an electronic device to implement any of the above methods.

[0096] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0097] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be electrical, mechanical or other forms of connection.

[0098] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0099] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0100] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-On l yMemory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0101] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A water supply network safety assessment method based on multi-dimensional data fusion, characterized by: The method comprises the following steps: The data acquisition module collects static data and dynamic data of the water supply network; wherein the static data at least includes pipe length, pipe diameter, and pipe material characteristics, and the dynamic data at least includes historical maintenance records and causes of damage; The data processing module further processes and handles the static data and the dynamic data collected by the data acquisition module; The static data and the dynamic data processed by the data processing module are input into a model prediction module, and the model prediction module predicts the safety level of the water supply network; wherein the model prediction module is an XgBoost model; The risk assessment module generates a safety risk assessment report for the water supply network based on the safety level of the water supply network predicted by the model prediction module, combined with the urgency of user needs, road traffic flow intensity, and geographical specificity of pipeline layout; The decision support module formulates a priority repair and transformation strategy based on the safety risk assessment report generated by the risk assessment module.

2. The water supply network safety assessment method based on multi-dimensional data fusion according to claim 1 is characterized in that: The data acquisition module collects static and dynamic data of the water supply network, including: The data acquisition module obtains the static data of the water supply network by means of database query, and the data acquisition module collects the dynamic data of the water supply network through multi-source approaches, wherein the multi-source approaches include sensor upload, database query and user feedback.

3. The water supply network safety assessment method based on multi-dimensional data fusion according to claim 2 is characterized in that: The data processing module further processes and handles the static data and the dynamic data collected by the data acquisition module, including: The data processing module includes a data preprocessing part and a feature engineering part; The data preprocessing part is responsible for processing the missing values ​​and abnormal values ​​in the collected original static data and dynamic data to ensure the accuracy and reliability of the data; The feature engineering part is responsible for extracting preliminary features from the static data and the dynamic data processed by the data preprocessing part, and optimizing the preliminary features by performing feature selection and feature scaling on the preliminary features to obtain target features; the target features are used to be input into the model prediction module.

4. The water supply network safety assessment method based on multi-dimensional data fusion according to claim 3 is characterized by: Before inputting the static data and the dynamic data processed by the data processing module into a model prediction module, the method further includes: Determine target parameters of the model prediction module, and generate training constraints based on the target parameters; wherein the target parameters include at least tree depth, subtree weight, regularization parameter and learning rate; Under the constraints of the training constraints, the model prediction module is trained in the first stage using the first set of training data until a convergence condition is reached, so as to achieve tuning of only the target parameters of the model prediction module; In the second stage, the model prediction module is trained in the second stage using the second set of training data until the convergence condition is reached; wherein the second stage training does not use the training constraints, that is, all parameters of the model prediction module are tuned.

5. The water supply network safety assessment method based on multi-dimensional data fusion according to claim 4 is characterized in that: The risk assessment module generates a safety risk assessment report of the water supply network based on the safety level of the water supply network predicted by the model prediction module, combined with the urgency of user needs, road traffic flow intensity, and geographical specificity of pipeline layout, including: Obtain the urgency of the user demand, the road traffic flow intensity, and the geographical specificity of the pipeline layout related to the water supply network to be renovated, and use the semantic analysis plug-in to extract semantic features from these related information; The extracted semantic features and the safety level of the water supply network are input into the risk assessment module, and the risk assessment module predicts the necessary value for transformation; wherein the risk assessment module is constructed based on a large language model; The safety risk assessment report is generated based on the necessary transformation value, the urgency of the user needs, the road traffic flow intensity, the geographical specificity of the pipeline layout and the safety level of the water supply network, as well as a preset report template.

6. The water supply network safety assessment method based on multi-dimensional data fusion according to claim 5 is characterized by: The decision support module formulates priority repair and transformation strategies based on the safety risk assessment report generated by the risk assessment module, including: The decision support module selects key information from the safety risk assessment report, the key information including the necessary value for transformation and the safety level of the water supply network, and determines the water supply network segment to be repaired first by combining the static data and the dynamic data; The decision support module selects the road traffic flow intensity and the geographical specificity of the pipeline layout from the safety risk assessment report, and determines the reconstruction strategy for the water supply network section that needs to be repaired first based on the road traffic flow intensity and the geographical specificity of the pipeline layout.

7. A water supply network safety assessment system based on multi-dimensional data fusion, characterized by: The system includes a data acquisition module, a data processing module, a model prediction module, a risk assessment module, and a decision support module; wherein, The data acquisition module is used to collect static data and dynamic data of the water supply network; wherein the static data at least includes pipe length, pipe diameter, and pipe material characteristics, and the dynamic data at least includes historical maintenance records and causes of damage; The data processing module is used to further process and handle the static data and the dynamic data collected by the data acquisition module; The model prediction module is used to predict the safety level of the water supply network based on the static data and the dynamic data processed by the data processing module; wherein the model prediction module is an XgBoost model; The risk assessment module is used to generate a safety risk assessment report for the water supply network based on the safety level of the water supply network predicted by the model prediction module, combined with the urgency of user needs, road traffic flow intensity, and geographical specificity of pipeline layout; The decision support module is used to formulate a priority repair and transformation strategy based on the safety risk assessment report generated by the risk assessment module.

8. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 6.

9. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that: The computer program is executed by a processor of an electronic device to implement the method according to any one of claims 1 to 6.

Images