Method, device and equipment for carrying out hidden danger investigation on project engineering and storage medium

Abstract

The invention discloses a method, a device, equipment and a storage medium for checking hidden dangers of project engineering, and the method comprises the steps: obtaining the basic information of a target project engineering, and inputting the basic information into a classification model, so as to obtain a target accident type corresponding to the basic information; determining each high-risk point corresponding to the target accident type by using the first mapping relationship, and determining a project stage associated with each high-risk point by using the second mapping relationship; obtaining a target year in which hidden danger checking needs to be carried out on the target project engineering, and determining a project stage in which the target year is located; according to the project stage of the target year and the project stage associated with each high risk point, determining a hidden danger investigation result; wherein the hidden danger checking result comprises a high risk point existing in a project stage in which the target year is located; according to the invention, the hidden danger investigation service in the building construction project can be formulated more professionally and accurately.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for troubleshooting hidden dangers in a project. Background Art

[0002] With the comprehensive promotion of construction safety production liability insurance, many insurance institutions and service agencies have actively participated in the promotion of construction safety production liability insurance and accident prevention services.

[0003] However, as a new thing, accident prevention services in construction safety liability insurance lack unified online information and data support. Among them, hidden danger inspection services are an important service in accident prevention services. When insurance companies formulate service plans for project parties, they consider the construction stage of the project, the risk points that are prone to accidents, and the years in which hidden danger inspection services are required within the project period. These factors directly affect the professionalism and accuracy of hidden danger inspection services.

[0004] Therefore, how to make the hidden danger investigation service of accident prevention service in construction safety liability insurance more professional, accurate and standardized has become a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0005] The purpose of the present invention is to provide a method, device, equipment and storage medium for troubleshooting project engineering, which can make the troubleshooting service in construction project engineering more professional, accurate and standardized.

[0006] According to one aspect of the present invention, a method for troubleshooting a project is provided, the method comprising: Obtaining basic information of the target project, and inputting the basic information into a pre-trained classification model to obtain a target accident type corresponding to the basic information; Using the first mapping relationship to determine each high-risk point corresponding to the target accident type, and using the second mapping relationship to respectively determine the project stage associated with each high-risk point; Obtaining a target year for potential hazards inspection of the target project, and determining the project stage in which the target year is located; The hidden danger inspection results are determined according to the project stage in which the target year is located and the project stage associated with each high-risk point; wherein the hidden danger inspection results include: high-risk points existing in the project stage in which the target year is located.

[0007] Optionally, the basic information of the target project is obtained, and the basic information is input into a pre-trained classification model to obtain a target accident type corresponding to the basic information, including: Based on the basic information of historical project engineering, a sample accident data set for model training is constructed; Using the sample accident data set to train a preset model to obtain the classification model; Inputting basic information of the target project into the classification model, and determining the target accident type according to the output of the classification model; The basic information of the target project includes at least one of the following: project type information, project deadline information, project cost information, project type information, general contractor information, and sub-item information.

[0008] Optionally, the using the first mapping relationship to determine each high-risk point corresponding to the target accident type includes: Acquire an accident fault tree constructed based on the basic information of the historical project engineering; wherein the accident fault tree includes the first mapping relationship between each node representing the accident type and each node representing the risk point, and the level of the node representing the accident type is higher than the level of the node representing the risk point; Determine, from the accident fault tree, a target node representing a risk point that has a mapping relationship with a node representing the target accident type; The hidden danger risk points represented by each target node are determined, and the high-risk risk points are determined based on the hidden danger risk points.

[0009] Optionally, determining the hidden danger risk points represented by each target node, and determining the high-risk points according to the hidden danger risk points, includes: Reversely constructing a Bayesian network model based on the accident fault tree; wherein, in the Bayesian network model, the level of the node representing the risk point is higher than the level of the node representing the accident type; Determine the associated node corresponding to the target node from the Bayesian network model; Analyze the prior probability of each target node from the accident fault tree; wherein the prior probability is used to characterize the historical probability of a certain risk point existing when a certain type of accident occurs; The posterior probability of each associated node is calculated based on the basic information of the target project and the Bayesian network model; wherein the posterior probability is used to characterize the predicted probability of a certain risk point existing when a certain type of accident occurs; Traverse each hidden danger risk point in turn, and determine whether the prior probability of the target node corresponding to the current traversed hidden danger risk point in the accident fault tree and the posterior probability of the corresponding associated node in the Bayesian network model are both greater than the preset probability threshold. If so, set the current traversed hidden danger risk point as a high-risk point.

[0010] Optionally, the using the second mapping relationship to respectively determine the project stage associated with each high-risk point includes: Obtaining sub-item information associated with the high-risk point; Based on the preset second mapping relationship between the sub-item information and the project stage, the project stage associated with the high-risk point is determined.

[0011] Optionally, obtaining the target year for conducting hidden danger inspection on the target project includes: Obtaining the insurance period of the insurance bound to the target project engineering; wherein the insurance period includes: an effective date of the effective year, and an expiration date of the expiration year; When the insurance period is less than one year and the insurance period crosses the year, determine whether the first time period from the effective date to the last day of the effective year is greater than the second time period from the first day of the expiration year to the expiration date. If so, set the effective year to the target year; if not, set the expiration year to the target year. When the insurance period is less than one year and does not cross the year, the effective year is set as the target year.

[0012] Optionally, obtaining the target year for conducting hidden danger inspection on the target project engineering further includes: Setting the sum of the first duration and the second duration as a reference duration; When the insurance period reaches one year and the reference period is greater than the first period threshold, determine whether the reference period is greater than the second period threshold; if so, set all years covered by the insurance period as the target year; if not, set the effective year and all complete years covered by the insurance period as the target year when the first period is greater than the second period, or set the expiration year and all complete years covered by the insurance period as the target year when the first period is less than the second period; wherein the first period threshold is less than one year, and the second period threshold is greater than one year; When the insurance period reaches one year and the reference duration is less than the first duration threshold, all complete years covered by the insurance period are set as the target years.

[0013] In order to achieve the above object, the present invention also provides a device for troubleshooting hidden dangers in a project, the device comprising: A training module is used to obtain basic information of a target project and input the basic information into a pre-trained classification model to obtain a target accident type corresponding to the basic information; A mapping module, used to determine each high-risk point corresponding to the target accident type using the first mapping relationship, and to determine the project stage associated with each high-risk point using the second mapping relationship; A determination module is used to obtain a target year for the target project engineering to be inspected for hidden dangers, and to determine the project stage in which the target year is located; The processing module is used to determine the hidden danger inspection results according to the project stage in the target year and the project stage associated with each high-risk point; wherein the hidden danger inspection results include: the high-risk points existing in the project stage in the target year.

[0014] In order to achieve the above-mentioned purpose, the present invention also provides a computer device, which specifically includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of the method for troubleshooting hidden dangers in a project engineering described above are implemented.

[0015] In order to achieve the above-mentioned purpose, the present invention also 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 the method for troubleshooting hidden dangers in a project engineering described above are implemented.

[0016] The method, device, equipment and storage medium for hidden danger inspection of project engineering provided by the present invention calculate the year in which hidden danger inspection service is needed within the project period, determine the project stage corresponding to the hidden danger inspection service year and obtain the high-risk points appearing in the project stage, so that the hidden danger inspection service in the construction project engineering can be formulated more professionally, accurately and standardized. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 An optional flow chart of a method for troubleshooting hidden dangers in a project provided in Example 1; Figure 2A schematic diagram of the process of training a classification model provided in Example 1; Figure 3 A schematic diagram of a process for calculating high-risk points provided in Example 1; Figure 4 A schematic diagram of a process for matching risk points with project stages provided in Example 1; Figure 5 A schematic diagram of a process for determining a target year provided in Example 1; Figure 6 Another schematic diagram of a process for troubleshooting a project project provided in Example 1; Figure 7 A schematic diagram of the flow of mini-program implementation services provided in Example 1; Figure 8 A schematic diagram of the mini-program display effect provided in Example 1; Fig. 9 A schematic diagram of an optional composition structure of a device for troubleshooting hidden dangers in a project provided in Example 2; Fig.10 A schematic diagram of an optional hardware architecture of a computer device provided in Example 3. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0019] Embodiment 1 The embodiment of the present invention provides a method for troubleshooting a project. Figure 1 As shown, the method specifically comprises the following steps: Step S101: acquiring basic information of a target project, and inputting the basic information into a pre-trained classification model to obtain a target accident type corresponding to the basic information.

[0020] Among them, the target project engineering refers to the project engineering for which the project party has purchased construction safety production liability insurance and needs to do hidden danger investigation services in accident prevention services. Specifically, construction safety production liability insurance refers to commercial insurance that provides compensation for casualties and related economic losses caused by production safety accidents in the insured production and operation units by insurance institutions, and provides accident prevention services to the insured production and operation units. Hidden danger investigation refers to a comprehensive and systematic inspection of production safety hidden dangers in enterprises or organizations, discovering existing potential dangers and safety hazards, taking preventive measures, and eliminating hidden dangers to ensure the safety of the production process and workplace. The basic information of the target project engineering may include one or more of the following information: project type information, project type information, project deadline information, project cost information, sub-item information and general contractor information.

[0021] In this embodiment, model training can be performed through historical data of various historical project engineering collected in advance to obtain a classification model for classifying accident types. When service agency personnel are required to go to the site of the target project engineering to provide special services for hidden danger inspection, basic information of the target project engineering is collected and extracted from the construction site, and the basic information is input into the pre-trained classification model to obtain the accident type corresponding to the basic information of the project engineering. In addition, the target accident type is the type of hidden danger accident existing in the target project engineering.

[0022] Step S102: using the first mapping relationship to determine each high-risk point corresponding to the target accident type, and using the second mapping relationship to respectively determine the project stage associated with each high-risk point.

[0023] Among them, the high-risk points are matters that lead to hidden dangers and accidents, and the target project engineering includes multiple project stages.

[0024] The first mapping relationship is a mapping relationship established in advance to characterize various accident types and various risk points, wherein the risk point is the cause of the engineering accident, and one accident type may correspond to one risk point or may correspond to multiple risk points. It should also be noted that in this embodiment, the risk point corresponding to the target accident type can be directly used as a high-risk risk point, or the risk point corresponding to the target accident type can be processed to further screen out the high-risk risk point, which is not specifically limited here.

[0025] The second mapping relationship is a mapping relationship established in advance to characterize various risk points and various project stages; among them, the construction project includes multiple project stages, for example, the project stages include: foundation pit, main construction and decoration and renovation, and there are corresponding risk points in each project stage. That is, different risk points exist in different project stages, and different risk points can lead to different types of engineering accidents.

[0026] In this embodiment, the service agency personnel first compare the obtained target accident type with the first mapping relationship to obtain high-risk points, and then obtain the construction project stage corresponding to each high-risk point according to the second mapping relationship.

[0027] Step S103: obtaining a target year for troubleshooting the target project, and determining the project stage in which the target year is located.

[0028] The target year is the year in which the hidden danger inspection service is required within the entire project insurance period. In this embodiment, the year in which the hidden danger inspection service is required within the entire project engineering period is obtained, and the project stage of the target project engineering in the current year is determined according to the year.

[0029] Step S104: Determine the hidden danger inspection result according to the project stage in the target year and the project stage associated with each high-risk point; wherein the hidden danger inspection result includes: the high-risk points existing in the project stage in the target year.

[0030] In this embodiment, the connection between the target year and the high-risk points is established through the project stage, so as to determine the hidden danger inspection results. When the service agency formulates a service plan for the project party, it can first determine the target years for the project engineering to be inspected for hidden dangers, then determine the project stage in which each target year is located, and finally determine the high-risk points that may cause engineering accidents in different project stages, so as to remind the project party of safety hazards from the three dimensions of year, project stage, and high-risk points, thereby specifying a professional, accurate, and standard hidden danger inspection service plan for the project party.

[0031] Specifically, the step of obtaining basic information of the target project in step S101 and inputting the basic information into a pre-trained classification model to obtain a target accident type corresponding to the basic information includes the following steps: Step A1: construct a sample accident data set for model training based on the basic information of historical project engineering; The sample accident data set includes a plurality of sample accident data, and each sample accident data includes: project type information, project deadline information, project cost information, project type information, general contractor information, sub-item information and accident type information.

[0032] Step A2: training a preset model using the sample accident data set to obtain the classification model; Among them, the preset model adopts a neural network multi-classification model. Common neural network multi-classification models include feedforward neural network, convolutional neural network, and recursive neural network.

[0033] Step A3: inputting the basic information of the target project into the classification model, and determining the target accident type according to the output of the classification model; The basic information of the target project includes: project type information, project deadline information, project cost information, project type information, general contractor information, and sub-item information.

[0034] In this embodiment, if Figure 2 As shown, before establishing a classification model for predicting accident types, an original database is first established based on the national construction accident report and the claims cases of construction safety production liability insurance to obtain the basic information of the historical project engineering, and the keywords in the accident report and the claims cases are identified. The report is structured and revised twice by the safety service expert, and the original database is established to obtain the sample accident data set. The sample accident data set is divided into a test data set and a training data set at a ratio of 2:8, and the training data set is input into the neural network multi-classification model for training, and the obtained training results are evaluated with the test data set. After repeated training, the classification model is determined, and the basic information of the target project engineering is input into the classification model to determine the target accident type. The classification model constructed by the basic information of the historical project engineering predicts the basic information of the target project engineering, and the predicted accident type is more accurate.

[0035] Specifically, the step of determining each high-risk point corresponding to the target accident type by using the first mapping relationship in step S102 includes the following steps: Step B1: obtaining an accident fault tree constructed based on the basic information of the historical project engineering; wherein the accident fault tree includes the first mapping relationship between each node representing the accident type and each node representing the risk point, and the level of the node representing the accident type is higher than the level of the node representing the risk point; Step B2: determining, from the accident fault tree, a target node representing a risk point that has a mapping relationship with a node representing the target accident type; Step B3: determine the hidden danger risk points represented by each target node, and determine the high-risk points based on the hidden danger risk points.

[0036] In this embodiment, if Figure 3 As shown, an accident fault tree is constructed based on the basic information of the historical project engineering obtained; wherein the root node of the accident fault tree is the occurrence of the accident, the second-level node represents each accident type, the third-level node represents each cause factor leading to each type of accident, and the fourth-level node represents one or more risk points contained in each cause factor.

[0037] Furthermore, the step of determining the hidden danger risk points represented by each target node in step B3, and determining the high-risk points according to the hidden danger risk points, specifically includes: Step C1: reversely constructing a Bayesian network model based on the accident fault tree; wherein, in the Bayesian network model, the level of the node representing the risk point is higher than the level of the node representing the accident type; Step C2: determining the associated nodes corresponding to the target node from the Bayesian network model; Step C3: parse the prior probability of each target node from the accident fault tree; wherein the prior probability is used to characterize the historical probability of a certain risk point existing when a certain type of accident occurs; Step C4: Calculate the posterior probability of each associated node based on the basic information of the target project and the Bayesian network model; wherein the posterior probability is used to characterize the predicted probability of a certain risk point existing when a certain type of accident occurs; Step C5: traverse each hidden danger risk point in turn, and determine whether the prior probability of the target node corresponding to the current traversed hidden danger risk point in the accident fault tree and the posterior probability of the corresponding associated node in the Bayesian network model are both greater than the preset probability threshold. If so, set the current traversed hidden danger risk point as a high-risk point.

[0038] In this embodiment, a Bayesian network model is reversely constructed based on the accident fault tree; wherein the root node of the Bayesian network model represents one or more risk points contained in each cause factor, the second-level node represents each cause factor leading to each type of accident, the third-level node represents each accident type, and the fourth-level node represents the occurrence of the accident.

[0039] like Figure 3As shown in the figure, based on the established accident database, an accident fault tree is established, with "accident" as the root node, the second-level node as the accident type, the third-level node classifies the human factors, material factors, and environmental factors (i.e., cause factors) according to each accident type, and the fourth-level node is the risk point that causes the accident. The prior probability of each risk point is obtained according to the frequency of occurrence of the risk point under each accident type; according to the established fault tree model, a Bayesian network model is reversely established, with the accident as the fourth-level node and the risk point that causes the accident as the root node, and the posterior probability corresponding to the risk point under the condition of the accident is calculated. The high-risk risk point that is most likely to cause an accident is obtained by comparing the prior probability and the posterior probability. For example, the prior probability of a risk point obtained by the analysis of the accident fault tree is 70%, and the posterior probability obtained after the calculation of the Bayesian network model is 60%. Then the prior probability and posterior probability of the risk point are both greater than 50%, and it is determined that this risk point is a high-risk risk point.

[0040] In addition, Fault Tree Analysis (FTA) and Bayesian Network (BN) are two commonly used models in system reliability analysis and safety risk assessment. There is a close relationship between them, and they can be converted and complemented with each other. Specifically, the fault tree is a top-down analysis method, which starts from the most undesirable event (top event) and gradually searches for all possible causes of the event. The Bayesian network is a probabilistic graphical model that expresses the dependency and independence relationship between variables through a directed acyclic graph. The fault tree can be converted into a Bayesian network, in which the basic events, intermediate events and top events of the fault tree correspond to the root nodes, intermediate nodes and leaf nodes in the Bayesian network one by one, and the connection method of the nodes is the same as the connection method of the corresponding events of the fault tree. Through the direct connection between the fault tree and the Bayesian network model, the fault tree can be converted into a Bayesian network, and the probabilistic reasoning ability of the Bayesian network is used to supplement the fault tree analysis, providing a more comprehensive reliability analysis and a more accurate risk point assessment.

[0041] Furthermore, the step of using the second mapping relationship to determine the project stage associated with each high-risk point in step S102 specifically includes: Step D1: Obtain sub-item information associated with the high-risk point; Among them, when establishing the sample accident data set, the correlation between the accident type and the sub-items will be established, and then the correlation between the risk points under the accident type and the distribution sub-items will be obtained.

[0042] Step D2: Based on the preset second mapping relationship between the sub-item information and the project stage, determine the project stage associated with the high-risk point.

[0043] In this embodiment, if Figure 4 As shown, in this embodiment, the project phase is divided into three phases: foundation pit, main construction, and decoration and renovation. The accident database includes the sub-items where the risk points are located. According to the mapping relationship between the sub-items and the project phases, the high-risk points are matched with the project phases. At the same time, according to the hidden danger investigation database established by the platform, the data in the database includes the high-risk points checked by the service experts when providing services at the project site and the actual stage of the project. Finally, after being revised by the safety service experts, a matching relationship between the high-risk points and the project phases is established.

[0044] Specifically, Figure 5 As shown, the step of obtaining the target year for which hidden danger inspection of the target project is required in step S103 includes the following steps: Obtaining the insurance period of the insurance bound to the target project engineering; wherein the insurance period includes: an effective date of the effective year, and an expiration date of the expiration year; When the insurance period is less than one year and the insurance period crosses the year, determine whether the first time period from the effective date to the last day of the effective year is greater than the second time period from the first day of the expiration year to the expiration date. If so, set the effective year to the target year; if not, set the expiration year to the target year. When the insurance period is less than one year and does not cross the year, the effective year is set as the target year.

[0045] Further, such as Figure 5 As shown, the step of obtaining the target year for which the target project engineering needs to be inspected for hidden dangers in step S103 further includes the following steps: Setting the sum of the first duration and the second duration as a reference duration; When the insurance period reaches one year and the reference period is greater than the first period threshold, determine whether the reference period is greater than the second period threshold; if so, set all years covered by the insurance period as the target year; if not, set the effective year and all complete years covered by the insurance period as the target year when the first period is greater than the second period, or set the expiration year and all complete years covered by the insurance period as the target year when the first period is less than the second period; wherein the first period threshold is less than one year, and the second period threshold is greater than one year; When the insurance period reaches one year and the reference duration is less than the first duration threshold, all complete years covered by the insurance period are set as the target years.

[0046] Preferably, the first duration threshold plus one year equals the second duration threshold, and the first duration threshold is less than half a year; for example, the first duration threshold is 90 days, and the second duration threshold is 455 days.

[0047] Furthermore, the step of determining the project stage of the target year in step S103 includes the following steps: Step E1: Obtain basic information of the target project; Step E2: Input the basic information of the target project into the project virtual progress matching algorithm to obtain the project stage in the target year.

[0048] In this embodiment, according to the basic information of the target project, based on a pre-built project virtual schedule matching algorithm, the basic information of the target project is input into the project virtual schedule matching algorithm, and the project stage of the target year is output.

[0049] In this embodiment, if Figure 6 As shown, the basic information of the target project, including the project type, project period, project cost, general contractor and sub-items, is input into the accident prevention service platform. The platform uses calculation rules to check hidden dangers, obtains the target accident type that may exist in the project, the high-risk points that cause accidents, the project stage where the high-risk points are located, the target year for the target project to check hidden dangers, the project stage where the target year is located, and obtains the hidden danger inspection results. Finally, the hidden danger inspection results are displayed, that is, the target year, project stage and the high-risk points in the project stage are displayed.

[0050] In addition, after step S104, the method further includes: Step F1: Input the basic information of the target project into the mini program; Step F2: The mini-program performs summary calculation to obtain the target accident type, the high-risk points corresponding to the target accident type, the project stage associated with each high-risk point, the target year for the target project to conduct hidden danger inspection, and the project stage in the target year, and obtains the hidden danger inspection result; Step F3: Display the hidden danger investigation results.

[0051] In this embodiment, if Figure 7 , Figure 8As shown, the mini program marks high-risk points according to the recommended service plan. The mini program establishes a hidden danger investigation database based on the accident data set formed by historical data and the hidden danger investigation specifications for construction projects, and then matches the hidden danger checkpoints associated with high-risk points based on the hidden danger investigation database. Finally, the high-risk points and the associated hidden danger checkpoints are displayed through the mini program interface, where the items marked with exclamation marks are high-risk points, and the rest are standard risk points for hidden danger investigation.

[0052] In this embodiment, by calculating the years during which hidden danger inspection services are needed within the project period, determining the project stages corresponding to the hidden danger inspection service years, and obtaining high-risk points that appear during the project stages, hidden danger inspection services in construction projects can be formulated more professionally, accurately, and in a standardized manner.

[0053] Embodiment 2 The embodiment of the present invention provides a device for troubleshooting project engineering hazards, such as Fig. 9 The device specifically comprises the following components: The training module 901 is used to obtain basic information of a target project and input the basic information into a pre-trained classification model to obtain a target accident type corresponding to the basic information; A mapping module 902 is used to determine each high-risk point corresponding to the target accident type using the first mapping relationship, and to determine the project stage associated with each high-risk point using the second mapping relationship; The determination module 903 is used to obtain the target year for which the target project needs to be checked for hidden dangers, and determine the project stage in which the target year is located; Processing module 904 is used to determine the hidden danger inspection results according to the project stage in the target year and the project stage associated with each high-risk point; wherein the hidden danger inspection results include: high-risk points existing in the project stage in the target year.

[0054] Specifically, the training module 901 is used to: Based on the basic information of historical project engineering, a sample accident data set for model training is constructed; Using the sample accident data set to train a preset model to obtain the classification model; Inputting basic information of the target project into the classification model, and determining the target accident type according to the output of the classification model; The basic information of the target project includes at least one of the following: project type information, project deadline information, project cost information, project type information, general contractor information, and sub-item information.

[0055] Specifically, the mapping module 902 includes: An acquisition unit, used for acquiring an accident fault tree constructed based on the basic information of the historical project engineering; wherein the accident fault tree includes the first mapping relationship between each node representing the accident type and each node representing the risk point, and the level of the node representing the accident type is higher than the level of the node representing the risk point; A mapping unit, used to determine, from the accident fault tree, a target node representing a risk point having a mapping relationship with a node representing the target accident type; The determination unit is used to determine the hidden danger risk points represented by each target node, and determine the high-risk points based on the hidden danger risk points.

[0056] Furthermore, the determining unit is specifically configured to: Reversely constructing a Bayesian network model based on the accident fault tree; wherein, in the Bayesian network model, the level of the node representing the risk point is higher than the level of the node representing the accident type; Determine the associated node corresponding to the target node from the Bayesian network model; Analyze the prior probability of each target node from the accident fault tree; wherein the prior probability is used to characterize the historical probability of a certain risk point existing when a certain type of accident occurs; The posterior probability of each associated node is calculated based on the basic information of the target project and the Bayesian network model; wherein the posterior probability is used to characterize the predicted probability of a certain risk point existing when a certain type of accident occurs; Traverse each hidden danger risk point in turn, and determine whether the prior probability of the target node corresponding to the current traversed hidden danger risk point in the accident fault tree and the posterior probability of the corresponding associated node in the Bayesian network model are both greater than the preset probability threshold. If so, set the current traversed hidden danger risk point as a high-risk point.

[0057] Furthermore, the mapping module 902 further includes: The association unit is used to obtain the sub-item information associated with the high-risk point; based on the second mapping relationship between the preset sub-item information and the project stage, determine the project stage associated with the high-risk point.

[0058] Specifically, the determining module 903 is used to: Obtaining the insurance period of the insurance bound to the target project engineering; wherein the insurance period includes: an effective date of the effective year, and an expiration date of the expiration year; When the insurance period is less than one year and the insurance period crosses the year, determine whether the first time period from the effective date to the last day of the effective year is greater than the second time period from the first day of the expiration year to the expiration date. If so, set the effective year to the target year; if not, set the expiration year to the target year. When the insurance period is less than one year and does not cross the year, the effective year is set as the target year.

[0059] Furthermore, the determining module 903 is further configured to: Setting the sum of the first duration and the second duration as a reference duration; When the insurance period reaches one year and the reference period is greater than the first period threshold, determine whether the reference period is greater than the second period threshold; if so, set all years covered by the insurance period as the target year; if not, set the effective year and all complete years covered by the insurance period as the target year when the first period is greater than the second period, or set the expiration year and all complete years covered by the insurance period as the target year when the first period is less than the second period; wherein the first period threshold is less than one year, and the second period threshold is greater than one year; When the insurance period reaches one year and the reference duration is less than the first duration threshold, all complete years covered by the insurance period are set as the target years.

[0060] Embodiment 3 This embodiment also provides a computer device, such as a smart phone, tablet computer, laptop computer, desktop computer, rack server, blade server, tower server or cabinet server (including an independent server or a server cluster composed of multiple servers) that can execute programs. Fig.10 As shown, the computer device 100 of this embodiment includes at least but not limited to: a memory 1001 and a processor 1002 that can communicate with each other via a system bus. It should be noted that Fig.10 The computer device 100 is shown only with components 1001 - 1002 , but it should be understood that implementing all of the components shown is not a requirement, and more or fewer components may alternatively be implemented.

[0061] In this embodiment, the memory 1001 (i.e., readable storage medium) includes flash memory, hard disk, multimedia card, card-type memory (e.g., 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, magnetic disk, optical disk, etc. In some embodiments, the memory 1001 may be an internal storage unit of the computer device 100, such as a hard disk or memory of the computer device 100. In other embodiments, the memory 1001 may also be an external storage device of the computer device 100, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 100. Of course, the memory 1001 may also include both the internal storage unit of the computer device 100 and its external storage device. In this embodiment, the memory 1001 is generally used to store the operating system and various application software installed on the computer device 100. In addition, the memory 1001 can also be used to temporarily store various types of data that have been output or are to be output.

[0062] In some embodiments, the processor 1002 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 1002 is generally used to control the overall operation of the computer device 100 .

[0063] Specifically, in this embodiment, the processor 1002 is used to execute the program for troubleshooting hidden dangers in the project engineering stored in the memory 1001. When the program for troubleshooting hidden dangers in the project engineering is executed, the following steps are implemented: Obtaining basic information of the target project, and inputting the basic information into a pre-trained classification model to obtain a target accident type corresponding to the basic information; Using the first mapping relationship to determine each high-risk point corresponding to the target accident type, and using the second mapping relationship to respectively determine the project stage associated with each high-risk point; Obtaining a target year for potential hazards inspection of the target project, and determining the project stage in which the target year is located; The hidden danger inspection results are determined according to the project stage in which the target year is located and the project stage associated with each high-risk point; wherein the hidden danger inspection results include: high-risk points existing in the project stage in which the target year is located.

[0064] The specific implementation process of the above method steps can be found in Example 1, and this embodiment will not be repeated here.

[0065] Embodiment 4 This embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, a server, an App application store, etc., on which a computer program is stored. When the computer program is executed by a processor, the following method steps are implemented: Obtaining basic information of the target project, and inputting the basic information into a pre-trained classification model to obtain a target accident type corresponding to the basic information; Using the first mapping relationship to determine each high-risk point corresponding to the target accident type, and using the second mapping relationship to respectively determine the project stage associated with each high-risk point; Obtaining a target year for potential hazards inspection of the target project, and determining the project stage in which the target year is located; The hidden danger inspection results are determined according to the project stage in which the target year is located and the project stage associated with each high-risk point; wherein the hidden danger inspection results include: high-risk points existing in the project stage in which the target year is located.

[0066] The specific implementation process of the above method steps can be found in Example 1, and this embodiment will not be repeated here.

[0067] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0068] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0069] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above 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.

[0070] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for troubleshooting a project, characterized in that: The method comprises: Obtaining basic information of the target project, and inputting the basic information into a pre-trained classification model to obtain a target accident type corresponding to the basic information; Using the first mapping relationship to determine each high-risk point corresponding to the target accident type, and using the second mapping relationship to respectively determine the project stage associated with each high-risk point; Obtaining a target year for potential hazards inspection of the target project, and determining the project stage in which the target year is located; The hidden danger inspection results are determined according to the project stage in the target year and the project stage associated with each high-risk point; wherein the hidden danger inspection results include: the high-risk points existing in the project stage in the target year.

2. The method for troubleshooting a project according to claim 1, characterized in that: The basic information of the target project is obtained, and the basic information is input into a pre-trained classification model to obtain a target accident type corresponding to the basic information, including: Based on the basic information of historical project engineering, a sample accident data set for model training is constructed; Using the sample accident data set to train a preset model to obtain the classification model; Inputting basic information of the target project into the classification model, and determining the target accident type according to the output of the classification model; The basic information of the target project includes at least one of the following: project type information, project deadline information, project cost information, project type information, general contractor information, and sub-item information.

3. The method for troubleshooting a project according to claim 2, characterized in that: The using the first mapping relationship to determine each high-risk point corresponding to the target accident type includes: Acquire an accident fault tree constructed based on the basic information of the historical project engineering; wherein the accident fault tree includes the first mapping relationship between each node representing the accident type and each node representing the risk point, and the level of the node representing the accident type is higher than the level of the node representing the risk point; Determine, from the accident fault tree, a target node representing a risk point that has a mapping relationship with a node representing the target accident type; The hidden danger risk points represented by each target node are determined, and the high-risk risk points are determined based on the hidden danger risk points.

4. The method for troubleshooting a project according to claim 3, characterized in that: The step of determining the hidden danger risk points represented by each target node, and determining the high-risk risk points according to the hidden danger risk points, includes: Reversely constructing a Bayesian network model based on the accident fault tree; wherein, in the Bayesian network model, the level of the node representing the risk point is higher than the level of the node representing the accident type; Determine the associated node corresponding to the target node from the Bayesian network model; Analyze the prior probability of each target node from the accident fault tree; wherein the prior probability is used to characterize the historical probability of a certain risk point existing when a certain type of accident occurs; The posterior probability of each associated node is calculated based on the basic information of the target project and the Bayesian network model; wherein the posterior probability is used to characterize the predicted probability of a certain risk point existing when a certain type of accident occurs; Traverse each hidden danger risk point in turn, and determine whether the prior probability of the target node corresponding to the current traversed hidden danger risk point in the accident fault tree and the posterior probability of the corresponding associated node in the Bayesian network model are both greater than the preset probability threshold. If so, set the current traversed hidden danger risk point as a high-risk point.

5. The method for troubleshooting a project according to claim 1, characterized in that: The method of using the second mapping relationship to respectively determine the project stage associated with each high-risk point includes: Obtaining sub-item information associated with the high-risk point; Based on the preset second mapping relationship between the sub-item information and the project stage, the project stage associated with the high-risk point is determined.

6. The method for troubleshooting a project according to claim 1, characterized in that: The target year for obtaining the target project engineering for potential hazards inspection includes: Obtaining the insurance period of the insurance bound to the target project engineering; wherein the insurance period includes: an effective date of the effective year, and an expiration date of the expiration year; When the insurance period is less than one year and the insurance period crosses the year, determine whether the first time period from the effective date to the last day of the effective year is greater than the second time period from the first day of the expiration year to the expiration date. If so, set the effective year to the target year; if not, set the expiration year to the target year. When the insurance period is less than one year and does not cross the year, the effective year is set as the target year.

7. The method for troubleshooting a project according to claim 6, characterized in that: The obtaining of the target year for the target project engineering to be inspected for hidden dangers also includes: Setting the sum of the first duration and the second duration as a reference duration; When the insurance period reaches one year and the reference period is greater than the first period threshold, determine whether the reference period is greater than the second period threshold; if so, set all years covered by the insurance period as the target year; if not, set the effective year and all complete years covered by the insurance period as the target year when the first period is greater than the second period, or set the expiration year and all complete years covered by the insurance period as the target year when the first period is less than the second period; wherein the first period threshold is less than one year, and the second period threshold is greater than one year; When the insurance period reaches one year and the reference duration is less than the first duration threshold, all complete years covered by the insurance period are set as the target years.

8. A device for troubleshooting project engineering, characterized in that: The device comprises: A training module is used to obtain basic information of a target project and input the basic information into a pre-trained classification model to obtain a target accident type corresponding to the basic information; A mapping module, used to determine each high-risk point corresponding to the target accident type using the first mapping relationship, and to determine the project stage associated with each high-risk point using the second mapping relationship; A determination module is used to obtain a target year for the target project engineering to be inspected for hidden dangers, and to determine the project stage in which the target year is located; The processing module is used to determine the hidden danger inspection results according to the project stage in the target year and the project stage associated with each high-risk point; wherein the hidden danger inspection results include: the high-risk points existing in the project stage in the target year.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images