Fabricated building construction project risk management method and system

Abstract

The invention relates to the technical field of data processing, and provides an assembly type building construction project risk management method and system, and the method comprises the steps: building construction project risk ontology models of different assembly types through obtaining a reference knowledge file set of an assembly type building construction project, and building a risk prediction model; then, according to related information of project construction main bodies in the fabricated building construction project information, predicting the risk probability of each candidate project construction main body during building construction, and finally, based on the risk probability and project construction demand information, generating a project construction main body combination which simultaneously meets the construction deadline requirement and the construction risk requirement. Therefore, the project construction main body combination is reasonably selected by considering the influence strength between the different risk body elements and the risk consequence elements and the construction time of the different candidate project construction main bodies, the construction risk prediction accuracy of the different project construction main bodies is improved, and the overall construction period of the project is ensured.

Description

Technical Field

[0001] The present invention relates to the field of data technology, and in particular to a method and system for risk management of prefabricated building construction projects. Background Art

[0002] Prefabricated construction is a construction method that transfers a large amount of on-site work in traditional construction methods to factories, where building components and accessories (such as floor slabs, wall panels, stairs, balconies, etc.) are processed and manufactured in factories, transported to the construction site, and assembled and installed on site through reliable connection methods.

[0003] Compared with traditional buildings, prefabricated buildings reduce the amount of concrete that needs to be poured on site, and the construction site does not need too many construction workers and machinery. However, as the core participants in the construction process, contractors will face challenges different from traditional buildings, such as formulating a construction project schedule according to the project department's schedule, site management and coordination tasks, and selecting the main construction entities of the project in different construction links and arranging the construction period. Since the above factors have very strict requirements on the arrangement of construction deadlines and time, it is necessary to control the risks of each construction link of the project (including the risk of delay caused by production accidents and the deadline risk caused by the construction progress, etc.), and when selecting the main construction entities of the project in different construction links, not only the construction deadline should be considered, but also the existence of construction risks.

[0004] Therefore, how to improve the accuracy of construction risk prediction for different project construction entities, ensure the overall construction period of the project, and reasonably select the combination of project construction entities is a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present invention provides a method and system for risk management of prefabricated building construction projects, aiming to solve the above-mentioned problems in the prior art.

[0006] A first aspect of the present invention provides a method for risk management of prefabricated building construction projects, comprising: Obtain reference knowledge document sets for prefabricated building construction projects, and build risk ontology models for construction projects of different assembly types based on the reference knowledge document sets; Establish a risk prediction model based on the risk ontology model of construction projects with different assembly types; Receiving prefabricated building construction project information of a target prefabricated building construction project submitted by a user terminal, extracting project construction demand information of the target prefabricated building construction project, a list of candidate project construction entities, and relevant information of each candidate project construction entity; According to the list of candidate project construction entities and the relevant information of each candidate project construction entity, the risk probability of each candidate project construction entity is predicted using the risk prediction model; The final project construction entity combination of the target prefabricated building construction project is generated by using the project construction demand information and the risk probability.

[0007] Optionally, a reference knowledge file set of prefabricated building construction projects is obtained, and based on the reference knowledge file set, a risk ontology model of construction projects of different assembly types is constructed, specifically including: Obtain a reference knowledge file set of the prefabricated building construction project; wherein the reference knowledge file set includes a plurality of reference knowledge files and the generation time of each reference knowledge file, and the reference knowledge file includes literature, expert experience files or actual case files; Extracting the text content in each reference knowledge file, using natural language processing tools to perform semantic analysis, part-of-speech determination, non-keyword removal and word segmentation on the text content, and obtaining a number of keywords for each reference knowledge file; According to several keywords of each reference knowledge file, the reference knowledge files in the reference knowledge file set are classified into assembly types, and based on the classified reference knowledge files, construction project risk ontology models of different assembly types are constructed.

[0008] Optionally, the step of classifying the reference knowledge files in the reference knowledge file set into assembly types according to a number of keywords of each reference knowledge file, and constructing a construction project risk ontology model of different assembly types based on the classified reference knowledge files, specifically includes: Based on a number of keywords of each reference knowledge file, similarity matching is performed in keyword sets of different assembly types, and each reference knowledge file in the reference knowledge file set is classified into an assembly type with the highest similarity; Based on each reference knowledge file in each assembly type, the trained reference knowledge file analysis model is used to determine several risk ontology elements, several risk consequence elements and the association information between risk ontology elements and risk consequence elements for each assembly type, and then a risk ontology model of construction projects with different assembly types is constructed.

[0009] Optionally, the construction project risk ontology model includes a plurality of risk ontology element nodes, a plurality of risk consequence element nodes, and connecting lines with impact strength between the risk ontology element nodes and the risk consequence element nodes, wherein the impact strength is configured as the impact level after semantic recognition and degree division of the association information between the risk ontology elements and the risk consequence elements.

[0010] Optionally, the method for risk management of prefabricated building construction projects further includes: Obtain a reference knowledge document analysis sample, and annotate a first keyword corresponding to a risk ontology element, a second keyword for a risk consequence element, and a strength keyword representing a strength relationship between the risk ontology element and the risk consequence element in the reference knowledge document analysis sample; The annotated reference knowledge document analysis samples are input into the pre-built initial BiLSTM-CRF model for training to obtain a trained knowledge document analysis model.

[0011] Optionally, the risk ontology elements include prefabricated components, construction technology and risk factors, and the risk consequence elements include risk consequence impact levels; a risk prediction model is established based on the risk ontology model of construction projects of different assembly types, specifically including: Count the cumulative sum of the product of the influence intensity of the risk ontology element node belonging to the same risk ontology element in the risk ontology model of construction projects of different assembly types and the weakening weights corresponding to the different time length paragraphs from the generation time of the reference knowledge file; The accumulated sum is used as the risk prediction weight of each risk ontology element, a risk prediction weight matrix containing all risk ontology elements is constructed, and the risk prediction weight matrix is ​​used as the calculation weight of the risk probability prediction value to establish a risk prediction model.

[0012] Optionally, the project construction demand information includes: project construction period; the candidate project construction entity list includes: several candidate project construction entities, and the relevant information of each candidate project construction entity includes: project construction duration and project construction period of each candidate project construction entity.

[0013] Optionally, based on the candidate project construction entity list and relevant information of each candidate project construction entity, the risk probability of each candidate project construction entity is predicted, specifically including: Querying the prefabricated building construction project feature set of each candidate project construction subject in the construction project subject database; wherein the prefabricated building construction project feature set includes several risk ontology elements of prefabricated components, construction technology and risk factors; The feature set of the prefabricated building construction project is input into the risk prediction model to predict the risk probability of each candidate project construction entity.

[0014] Optionally, the final project construction subject combination of the target prefabricated building construction project is generated by using the project construction demand information and the risk probability, specifically including: According to the construction duration and construction period of each candidate project construction entity, a project construction entity combination arrangement model is established; Taking the overall construction time of the target prefabricated building construction project being less than the project construction period as a constraint condition, and taking the overall risk probability of the target prefabricated building construction project being minimized as the objective function, the project construction entity combination arrangement model is solved to obtain the final project construction entity combination of the target prefabricated building construction project.

[0015] A second aspect of the present invention provides a prefabricated building construction project risk management system, comprising: A construction module is used to obtain a reference knowledge file set of prefabricated building construction projects, and to construct a risk ontology model of construction projects of different assembly types based on the reference knowledge file set; Establish a module for establishing a risk prediction model based on the risk ontology model of construction projects of different assembly types; An extraction module is used to receive the prefabricated building construction project information of the target prefabricated building construction project submitted by the user terminal, and extract the project construction demand information of the target prefabricated building construction project, the list of candidate project construction entities and the relevant information of each candidate project construction entity; A prediction module, used to predict the risk probability of each candidate project construction entity based on the candidate project construction entity list and relevant information of each candidate project construction entity; A generation module is used to generate a final project construction entity combination of a target prefabricated building construction project by using the project construction demand information and the risk probability.

[0016] The beneficial effects of the present invention are as follows: a method and system for risk management of prefabricated building construction projects are proposed, and a risk ontology model of construction projects of different assembly types is constructed by acquiring a reference knowledge file set of prefabricated building construction projects, thereby establishing a risk prediction model of different assembly types, and when the prefabricated building construction project information is received, the risk probability of each candidate project construction subject when performing construction is predicted according to the relevant information of the project construction subject in the prefabricated building construction project information, and finally, based on the risk probability and the project construction demand information, a combination of project construction subjects that simultaneously meets the construction deadline requirements and construction risk requirements is generated, thereby, using the reference knowledge file set to generate a risk prediction model, considering the influence intensity between different risk ontology elements and risk consequence elements and the construction time of different candidate project construction subjects, and reasonably selecting the project construction subject combination, thereby improving the accuracy of construction risk prediction of different project construction subjects and ensuring the overall construction deadline of the project. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flowchart of the risk management method of the prefabricated building construction project of this embodiment.

[0018] Figure 2It is a schematic diagram of the structure of the prefabricated building construction project risk management system of this embodiment.

[0019] Reference numerals: 10- construction module; 20- establishment module; 30- extraction module; 40- prediction module; 50- generation module. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Embodiment 1: like Figure 1 As shown, a method for risk management of prefabricated building construction projects includes: S100: Obtain a reference knowledge file set of prefabricated building construction projects, and construct a risk ontology model of construction projects of different assembly types based on the reference knowledge file set; S200: Establish a risk prediction model based on the risk ontology model of construction projects of different assembly types; S300: receiving prefabricated building construction project information of a target prefabricated building construction project submitted by a user terminal, extracting project construction demand information of the target prefabricated building construction project, a list of candidate project construction entities, and relevant information of each candidate project construction entity; S400: predicting the risk probability of each candidate project construction entity using a risk prediction model according to the candidate project construction entity list and relevant information of each candidate project construction entity; S500: Generate a final project construction entity combination of a target prefabricated building construction project by using the project construction demand information and the risk probability.

[0022] It should be noted that, compared with traditional buildings, prefabricated buildings reduce the amount of concrete that needs to be poured on site, and the construction site does not need too many construction workers and machinery. However, as the core participant in the construction process, contractors will face challenges different from traditional buildings, such as formulating a construction project schedule according to the project department's schedule, site management and coordination tasks, and selecting the main construction entities of the project in different construction links and arranging the construction period. Since the above factors have very strict requirements on the arrangement of construction deadlines and time, it is necessary to control the risks of each construction link of the project (including the risk of delay caused by production accidents and the deadline risk caused by the construction progress, etc.), and then when selecting the main construction entities of the project in different construction links, not only the construction deadline should be considered, but also the existence of construction risks.

[0023] In order to solve the above problems, this embodiment obtains a reference knowledge file set of prefabricated building construction projects, constructs risk ontology models of construction projects of different assembly types, and thereby establishes risk prediction models of different assembly types. When receiving prefabricated building construction project information, the risk probability of each candidate project construction entity when performing construction is predicted based on the relevant information of the project construction entity in the prefabricated building construction project information. Finally, based on the risk probability and the project construction demand information, a combination of project construction entities that simultaneously meet the construction deadline requirements and construction risk requirements is generated. Thus, a risk prediction model is generated using the reference knowledge file set, and the impact intensity between different risk ontology elements and risk consequence elements and the construction time of different candidate project construction entities are considered, and a reasonable combination of project construction entities is selected, thereby improving the accuracy of construction risk prediction of different project construction entities and ensuring the overall construction deadline of the project.

[0024] In a preferred embodiment, a reference knowledge file set of prefabricated building construction projects is obtained, and a risk ontology model of construction projects of different assembly types is constructed based on the reference knowledge file set, specifically including: S110: Acquire a reference knowledge file set of the prefabricated building construction project; wherein the reference knowledge file set includes a plurality of reference knowledge files and the generation time of each reference knowledge file, and the reference knowledge files include literature materials, expert experience files or actual case files; S120: extracting text content from each reference knowledge file, using a natural language processing tool to perform semantic analysis, part-of-speech determination, non-keyword removal and word segmentation on the text content, and obtaining a number of keywords for each reference knowledge file; S130: Classifying the reference knowledge files in the reference knowledge file set into assembly types according to a number of keywords of each reference knowledge file, and constructing construction project risk ontology models of different assembly types based on the classified reference knowledge files.

[0025] On this basis, according to several keywords of each reference knowledge file, the reference knowledge files in the reference knowledge file set are classified into assembly types, and based on the classified reference knowledge files, construction project risk ontology models of different assembly types are constructed, specifically including: S133: performing similarity matching in keyword sets of different assembly types based on a number of keywords of each reference knowledge file, and classifying each reference knowledge file in the reference knowledge file set into an assembly type with the highest similarity; S134: Based on each reference knowledge file in each assembly type, using the trained reference knowledge file analysis model, determine a number of risk ontology elements, a number of risk consequence elements and the association information between the risk ontology elements and the risk consequence elements for each assembly type, and construct a construction project risk ontology model for different assembly types.

[0026] In a preferred embodiment, the construction project risk ontology model includes a plurality of risk ontology element nodes, a plurality of risk consequence element nodes, and connecting lines with impact strength between the risk ontology element nodes and the risk consequence element nodes, wherein the impact strength is configured as the impact level after semantic recognition and degree division of the association information between the risk ontology elements and the risk consequence elements.

[0027] In this embodiment, the reference knowledge file records the relevant construction content of the prefabricated building construction projects of different assembly types (such as prefabricated concrete structures, steel structure prefabricated buildings, wooden structure prefabricated buildings, etc.), and the natural language processing tool can be used to extract keywords and classify the assembly types based on keyword set matching, so as to obtain reference knowledge files of different assembly types. After that, the reference knowledge file analysis model is used to extract several risk ontology elements, several risk consequence elements, and the association information between risk ontology elements and risk consequence elements, and then construct the risk ontology model of construction projects of different assembly types. Therefore, by generating the risk ontology model of the construction project, the risk ontology model of the construction project is used to save the risk ontology elements, risk consequence elements, and the association information between risk ontology elements and risk consequence elements in different assembly types, so as to provide data support for the subsequent risk prediction of the construction subject of the candidate project for a certain construction link and the overall risk prediction of the entire project.

[0028] In a preferred embodiment, the method for risk management of prefabricated building construction projects further includes: S131: Obtain a reference knowledge document analysis sample, and annotate the first keyword corresponding to the risk ontology element, the second keyword of the risk consequence element, and the strength keyword representing the strength relationship between the risk ontology element and the risk consequence element in the reference knowledge document analysis sample; S132: Input the annotated reference knowledge document analysis samples into the pre-built initial BiLSTM-CRF model for training to obtain a trained knowledge document analysis model.

[0029] In this embodiment, the reference knowledge document analysis samples are labeled and input into a pre-built initial BiLSTM-CRF model for training, thereby giving the knowledge document analysis model the ability to extract risk ontology elements, risk consequence elements, and the association information between risk ontology elements and risk consequence elements in the reference knowledge document.

[0030] In a preferred embodiment, the risk ontology elements include prefabricated components, construction technology and risk factors, and the risk consequence elements include risk consequence impact levels; a risk prediction model is established based on the risk ontology model of construction projects of different assembly types, specifically including: S210: Counting the cumulative sum of the product of the influence intensity of the risk ontology element node belonging to the same risk ontology element in the risk ontology model of the construction project of different assembly types and the weakening weight corresponding to the different time length paragraphs of the generation time of the reference knowledge file; S220: Using the accumulated sum as the risk prediction weight of each risk ontology element, constructing a risk prediction weight matrix including all risk ontology elements, using the risk prediction weight matrix as the calculation weight of the risk probability prediction value, and establishing a risk prediction model.

[0031] In this embodiment, the cumulative sum of the products of the influence strength of the risk ontology element node of the same risk ontology element and the weakened weights corresponding to the different time length paragraphs of the generation time of the reference knowledge file is statistically calculated, and this is used as a measure of the impact of different risk ontology elements on the occurrence of risks in the risk prediction model, thereby establishing a risk prediction model. For the risk probability value, the risk probability can be generated by the ratio of the cumulative sum of the products of the quantified values ​​converted from different risk ontology elements and the corresponding weights to the standard value.

[0032] In a preferred embodiment, the project construction demand information includes: project construction period; the candidate project construction entity list includes: several candidate project construction entities, and the relevant information of each candidate project construction entity includes: project construction duration and project construction period of each candidate project construction entity.

[0033] On this basis, according to the list of candidate project construction entities and the relevant information of each candidate project construction entity, the risk probability of each candidate project construction entity is predicted, including: S410: querying the prefabricated building construction project feature set of each candidate project construction subject in the construction project subject database; wherein the prefabricated building construction project feature set includes several risk ontology elements of prefabricated components, construction technology and risk factors; S420: Input the feature set of the prefabricated building construction project into the risk prediction model to predict the risk probability of each candidate project construction entity.

[0034] On this basis, the final project construction subject combination of the target prefabricated building construction project is generated by using the project construction demand information and the risk probability, specifically including: S510: Establishing a project construction entity combination arrangement model according to the project construction duration and project construction period of each candidate project construction entity; S520: Taking the overall construction time of the target prefabricated building construction project being less than the project construction period as a constraint condition and taking the overall risk probability of the target prefabricated building construction project being minimized as an objective function, solving the project construction subject combination arrangement model to obtain the final project construction subject combination of the target prefabricated building construction project.

[0035] In this embodiment, a risk prediction model is generated by using a reference knowledge file set, and the influence intensity between different risk ontology elements and risk consequence elements and the construction time of different candidate project construction entities are considered. The overall construction time of the target prefabricated building construction project is less than the project construction period as a constraint condition, and the overall risk probability of the target prefabricated building construction project is minimized as the objective function to reasonably select the project construction entity combination, thereby improving the accuracy of construction risk prediction of different project construction entities and ensuring the overall construction period of the project.

[0036] Embodiment 2: Reference Figure 2 , Figure 2 A schematic structural diagram of a prefabricated building construction project risk management system provided by an embodiment of the present invention.

[0037] like Figure 2 As shown, a prefabricated building construction project risk management system is used for the prefabricated building construction project risk management method as described above, comprising: A construction module 10 is used to obtain a reference knowledge file set of prefabricated building construction projects, and to construct a risk ontology model of construction projects of different assembly types based on the reference knowledge file set; Establishing module 20, for establishing a risk prediction model according to the risk ontology model of construction projects of different assembly types; The extraction module 30 is used to receive the prefabricated building construction project information of the target prefabricated building construction project submitted by the user terminal, and extract the project construction demand information of the target prefabricated building construction project, the list of candidate project construction entities and the relevant information of each candidate project construction entity; A prediction module 40 is used to predict the risk probability of each candidate project construction entity based on the candidate project construction entity list and relevant information of each candidate project construction entity; The generation module 50 is used to generate a final project construction entity combination of the target prefabricated building construction project by using the project construction demand information and the risk probability.

[0038] The specific implementation method of the prefabricated building construction project risk management system of the present application is basically the same as the above-mentioned prefabricated building construction project risk management method embodiment, and will not be repeated here.

[0039] In the description of the embodiments of the present invention, it should be understood that the terms "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "center", "top", "bottom", "top", "bottom", "inside", "outside", "inner side", "outer side" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Among them, "inside" refers to an internal or enclosed area or space. "Periphery" refers to the area surrounding a specific component or a specific area.

[0040] In the description of the embodiments of the present invention, the terms "first", "second", "third", and "fourth" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", and "fourth" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0041] In the description of the embodiments of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "install", "connect", "connect", and "assemble" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0042] In the description of the embodiments of the present invention, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0043] In the description of the embodiments of the present invention, it should be understood that "-" and "~" represent a range between two values, and the range includes the endpoints. For example: "AB" represents a range greater than or equal to A and less than or equal to B. "A~B" represents a range greater than or equal to A and less than or equal to B.

[0044] In the description of the embodiments of the present invention, the term "and / or" herein is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " herein generally indicates that the associated objects before and after are in an "or" relationship.

[0045] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for risk management of prefabricated building construction projects, characterized in that: include: Obtain reference knowledge document sets for prefabricated building construction projects, and build risk ontology models for construction projects of different assembly types based on the reference knowledge document sets; Establish a risk prediction model based on the risk ontology model of construction projects with different assembly types; Receiving prefabricated building construction project information of a target prefabricated building construction project submitted by a user terminal, extracting project construction demand information of the target prefabricated building construction project, a list of candidate project construction entities, and relevant information of each candidate project construction entity; According to the list of candidate project construction entities and the relevant information of each candidate project construction entity, the risk probability of each candidate project construction entity is predicted using the risk prediction model; The final project construction entity combination of the target prefabricated building construction project is generated by using the project construction demand information and the risk probability.

2. The method for risk management of prefabricated building construction projects according to claim 1, characterized in that: Obtain reference knowledge files of prefabricated building construction projects, and build risk ontology models of construction projects of different assembly types based on the reference knowledge files, including: Obtain a reference knowledge file set of the prefabricated building construction project; wherein the reference knowledge file set includes a plurality of reference knowledge files and the generation time of each reference knowledge file, and the reference knowledge file includes literature, expert experience files or actual case files; Extracting the text content in each reference knowledge file, using natural language processing tools to perform semantic analysis, part-of-speech determination, non-keyword removal and word segmentation on the text content, and obtaining a number of keywords for each reference knowledge file; According to several keywords of each reference knowledge file, the reference knowledge files in the reference knowledge file set are classified into assembly types, and based on the classified reference knowledge files, construction project risk ontology models of different assembly types are constructed.

3. The method for risk management of prefabricated building construction projects according to claim 2, characterized in that: The method of classifying the reference knowledge files in the reference knowledge file set into assembly types according to a number of keywords of each reference knowledge file, and constructing a construction project risk ontology model of different assembly types based on the classified reference knowledge files, specifically includes: Based on a number of keywords of each reference knowledge file, similarity matching is performed in keyword sets of different assembly types, and each reference knowledge file in the reference knowledge file set is classified into an assembly type with the highest similarity; Based on each reference knowledge file in each assembly type, the trained reference knowledge file analysis model is used to determine several risk ontology elements, several risk consequence elements and the association information between risk ontology elements and risk consequence elements for each assembly type, and then a risk ontology model of construction projects with different assembly types is constructed.

4. The method for risk management of prefabricated building construction projects according to claim 3 is characterized in that: The construction project risk ontology model includes a plurality of risk ontology element nodes, a plurality of risk consequence element nodes, and connection lines with impact strength between the risk ontology element nodes and the risk consequence element nodes. The impact strength is configured as the impact level after semantic recognition and degree division of the association information between the risk ontology elements and the risk consequence elements.

5. The method for risk management of prefabricated building construction projects according to claim 3, characterized in that: Also includes: Obtain a reference knowledge document analysis sample, and annotate a first keyword corresponding to a risk ontology element, a second keyword for a risk consequence element, and a strength keyword representing a strength relationship between the risk ontology element and the risk consequence element in the reference knowledge document analysis sample; The annotated reference knowledge document analysis samples are input into the pre-built initial BiLSTM-CRF model for training to obtain a trained knowledge document analysis model.

6. The method for risk management of prefabricated building construction projects according to claim 4, characterized in that: The risk ontology elements include prefabricated components, construction technology and risk factors, and the risk consequence elements include risk consequence impact level; According to the risk ontology model of construction projects with different assembly types, a risk prediction model is established, including: Count the cumulative sum of the product of the influence intensity of the risk ontology element node belonging to the same risk ontology element in the risk ontology model of construction projects of different assembly types and the weakening weights corresponding to the different time length paragraphs from the generation time of the reference knowledge file; The accumulated sum is used as the risk prediction weight of each risk ontology element, a risk prediction weight matrix containing all risk ontology elements is constructed, and the risk prediction weight matrix is ​​used as the calculation weight of the risk probability prediction value to establish a risk prediction model.

7. The method for risk management of prefabricated building construction projects according to claim 1, characterized in that: The project construction demand information includes: the project construction period; the candidate project construction entity list includes: a number of candidate project construction entities, and the relevant information of each candidate project construction entity includes: the project construction duration and project construction period of each candidate project construction entity.

8. The method for risk management of prefabricated building construction projects according to claim 7, characterized in that: Based on the list of candidate project construction entities and the relevant information of each candidate project construction entity, the risk probability of each candidate project construction entity is predicted, including: Querying the prefabricated building construction project feature set of each candidate project construction subject in the construction project subject database; wherein the prefabricated building construction project feature set includes several risk ontology elements of prefabricated components, construction technology and risk factors; The feature set of the prefabricated building construction project is input into the risk prediction model to predict the risk probability of each candidate project construction entity.

9. The method for risk management of prefabricated building construction projects according to claim 7, characterized in that: Using the project construction demand information and the risk probability, the final project construction subject combination of the target prefabricated building construction project is generated, specifically including: According to the construction duration and construction period of each candidate project construction entity, a combination arrangement model of the project construction entity is established; Taking the overall construction time of the target prefabricated building construction project being less than the project construction period as a constraint condition, and taking the overall risk probability of the target prefabricated building construction project being minimized as the objective function, the project construction entity combination arrangement model is solved to obtain the final project construction entity combination of the target prefabricated building construction project.

10. A risk management system for prefabricated building construction projects, characterized in that: include: A construction module is used to obtain a reference knowledge file set of prefabricated building construction projects, and to construct a risk ontology model of construction projects of different assembly types based on the reference knowledge file set; Establish a module for establishing a risk prediction model based on the risk ontology model of construction projects of different assembly types; An extraction module is used to receive the prefabricated building construction project information of the target prefabricated building construction project submitted by the user terminal, and extract the project construction demand information of the target prefabricated building construction project, the list of candidate project construction entities and the relevant information of each candidate project construction entity; A prediction module, used to predict the risk probability of each candidate project construction entity based on the candidate project construction entity list and relevant information of each candidate project construction entity; A generation module is used to generate a final project construction entity combination of a target prefabricated building construction project by using the project construction demand information and the risk probability.

Images