Building data hooking method, device, equipment and product

Abstract

The invention relates to the technical field of buildings, and discloses a building data hooking method, device, equipment and product, and the method comprises the steps: obtaining a building data knowledge graph, and a first building data source and a second building data source to be hooked; extracting first construction information corresponding to each piece of first building data in the first building data source and second construction information corresponding to each piece of second building data in the second building data source from the building data knowledge graph by using a pre-trained data hooking model; screening out a plurality of candidate construction information associated with the first target construction information from all the second construction information according to the hierarchical relationship of the building data knowledge graph; and screening out second target construction information from the multiple pieces of candidate construction information by using the data hooking model and the building data knowledge graph, and hooking the second target construction information and the first target construction information to obtain a data hooking result. By implementing the technical scheme of the invention, the building data hitching efficiency and accuracy are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of construction technologies, and particularly to a method, apparatus, device and product for attaching construction data. Background Art

[0002] In the construction field, there are various types of source data in different scenarios. These data are stored independently of each other and lack effective association and integration. In the actual project process, it is necessary to establish an attachment relationship between different data sources to achieve the connection and cooperation between different construction stages and different participants.

[0003] Currently, the commonly used method for attaching construction data usually requires experienced business personnel to read different source data throughout and manually establish an attachment relationship after analysis. This method not only requires a large number of experienced business personnel, but also the data attachment operation is cumbersome, time-consuming and laborious, and it is easy to have attachment errors, resulting in inefficient decision-making and mistakes in the construction process management, and leading to relatively low efficiency and accuracy of construction data attachment. Summary of the Invention

[0004] In view of this, the present disclosure provides a method, apparatus, device and product for attaching construction data to solve the problem of low efficiency and accuracy of construction data attachment.

[0005] In a first aspect, the present disclosure provides a method for attaching construction data, the method comprising:

[0006] Obtaining a construction data knowledge graph and a first construction data source and a second construction data source to be attached;

[0007] Using a pre-trained data attachment model to extract first construction information corresponding to each first construction data in the first construction data source and second construction information corresponding to each second construction data in the second construction data source from the construction data knowledge graph;

[0008] For any one first target construction information in each first construction information, screening out a plurality of candidate construction information associated with the first target construction information from all the second construction information according to the hierarchical relationship of the construction data knowledge graph;

[0009] Using the data attachment model and the construction data knowledge graph, screening out a second target construction information from the plurality of candidate construction information, and attaching the second target construction information to the first target construction information to obtain a data attachment result.

[0010] In the embodiments of the present disclosure, by obtaining a building data knowledge graph and first and second building data sources to be connected; using a pre-trained data connection model to extract the first construction information corresponding to each first building data in the first building data source and the second construction information corresponding to each second building data in the second building data source from the building data knowledge graph; for any first target construction information among the first construction information, screening out multiple candidate construction information associated with the first target construction information from all the second construction information according to the hierarchical relationship of the building data knowledge graph; using the data connection model and the building data knowledge graph to screen out a second target construction information from the multiple candidate construction information, and connecting the second target construction information with the first target construction information to obtain a data connection result. Since the embodiments of the present disclosure connect the building data of different building data sources through the data connection model and the knowledge graph, the efficiency and accuracy of building data connection are improved.

[0011] In an alternative embodiment, obtaining a building data knowledge graph includes:

[0012] Obtaining different types of building construction data;

[0013] Based on the construction work of the building construction data, constructing the construction priority and construction level of the construction work;

[0014] Based on the construction work of the building construction data, constructing the construction object corresponding to the construction work;

[0015] Based on the relationship between construction objects, constructing the object level of the construction objects;

[0016] Constructing a graph according to the construction priority, construction level, construction object and object level to generate a building data knowledge graph.

[0017] In the embodiments of the present disclosure, by constructing a graph based on the construction priority, construction level, construction object and object level in the building construction data, a knowledge graph with clear structure and rich information can be generated, improving the accuracy and efficiency of building data connection.

[0018] In an alternative embodiment, using a pre-trained data connection model to extract the first construction information corresponding to each first building data in the first building data source and the second construction information corresponding to each second building data in the second building data source from the building data knowledge graph includes:

[0019] Comparing the similarity of each first building data with the building data knowledge graph to obtain multiple first candidate construction information related to each first building data;

[0020] Compare the respective second building data with the building data knowledge graph to obtain multiple second candidate construction information related to each second building data;

[0021] Use the data connection model to determine the first construction information corresponding to the first building data from multiple first candidate construction information, and determine the second construction information corresponding to the second building data from multiple second candidate construction information.

[0022] In the embodiments of the present disclosure, extracting the first candidate construction information and the second candidate construction information from the building data knowledge graph through similarity comparison can ensure the accuracy and consistency of the construction information. Screening the first candidate construction information and the second candidate construction information through the data connection model can quickly and accurately determine the first construction information and the second construction information, improving the efficiency and accuracy of building data connection.

[0023] In an alternative embodiment, according to the hierarchical relationship of the building data knowledge graph, screen out multiple candidate construction information associated with the first target construction information from all the second construction information, including:

[0024] Obtain all the first construction tasks corresponding to the first target construction information, and determine the first target construction task with the highest priority from all the first construction tasks;

[0025] Decompose the first target construction task according to the building data knowledge graph to obtain the first target decomposition task;

[0026] Compare the first target decomposition task with the second construction tasks corresponding to the second construction information, and screen out multiple candidate construction information from the second construction tasks.

[0027] In the embodiments of the present disclosure, by determining the first construction task with the highest priority as the first target construction task, then decomposing the first target construction task and comparing it with the second construction task, multiple candidate construction information associated with the first target construction information can be accurately determined, improving the accuracy of building data connection.

[0028] In an alternative embodiment, compare the first target decomposition task with the second construction tasks corresponding to the second construction information, and screen out multiple candidate construction information from the second construction tasks, including:

[0029] Identify the relevance between the first construction task and the second construction task;

[0030] If the second construction task includes the first target decomposition task, and / or, the second construction task partially includes the first target decomposition task, then determine the construction information corresponding to the second construction task as the candidate construction information.

[0031] In the embodiments of the present disclosure, by screening the second construction work according to the relevance between the first construction work and the second construction work, multiple candidate construction information associated with the first target construction information can be accurately determined, improving the accuracy of building data connection.

[0032] In an alternative embodiment, it further includes:

[0033] If the second construction work has nothing to do with the first target disassembly work, the connection is rejected.

[0034] In the embodiments of the present disclosure, by rejecting the connection when the second construction work has nothing to do with the first target disassembly work, the occurrence of incorrect connection can be effectively avoided, ensuring the accuracy and rationality of the building data connection result, and enhancing the reliability of the building project management and decision-making basis.

[0035] In an alternative embodiment, using a data connection model and a building data knowledge graph, the second target construction information is screened out from multiple candidate construction information, and the second target construction information is connected with the first target construction information to obtain a data connection result, including:

[0036] Obtain all candidate construction work corresponding to the candidate construction information;

[0037] Obtain the level of the first target disassembly work in the building data knowledge graph;

[0038] Based on the level relationship between the candidate construction work and the first target disassembly work, the second target construction work corresponding to the first target disassembly work is screened out from all candidate construction work;

[0039] Determine the construction information corresponding to the second target construction work as the second target construction information;

[0040] Use the data connection model to connect the second target construction information with the first target construction information to obtain a data connection result.

[0041] In the embodiments of the present disclosure, by screening out the second target construction work based on the level relationship between the candidate construction work and the first target disassembly work, and using the data connection model to connect it with the first target construction information, the data connection can be accurately screened and realized based on the hierarchical logic of the building data knowledge graph, improving the accuracy and rationality of the building data connection.

[0042] In an alternative embodiment, based on the level relationship between the candidate construction work and the first target disassembly work, screening out the second target construction work corresponding to the first target disassembly work from all candidate construction work includes:

[0043] Exclude the candidate construction works that have the same level or a superior relationship with the first target disassembly work from all candidate construction works to obtain the first remaining construction works;

[0044] Exclude the construction works that have a superior relationship with other construction works from the first remaining construction works to obtain the second remaining construction works;

[0045] Obtain the second work objects corresponding to the second remaining construction works, and screen out the third work objects that have a superior relationship with other work objects from the second work objects;

[0046] Exclude the construction works corresponding to the third work objects from the second remaining construction works to obtain the third remaining construction works, and determine the third remaining construction works as the second target construction works.

[0047] In the embodiments of the present disclosure, by performing multiple rounds of screening based on the level relationship between the candidate construction works and the first target disassembly work to obtain the second target construction works, it is possible to achieve accurate screening of construction works based on the hierarchical logic of the building data knowledge graph, ensure the accuracy and rationality of the building data hanging results, and improve the reliability of the building project management and decision-making basis.

[0048] In an alternative implementation manner, a data hanging model is used to hang the second target construction information and the first target construction information to obtain a data hanging result, including:

[0049] Obtain the prompt hanging information of the data hanging model;

[0050] Match and perform data hanging on the second target construction information and the first target construction information according to the prompt hanging information to generate a data hanging result.

[0051] In the embodiments of the present disclosure, by using a data hanging model to hang the second target construction information and the first target construction information according to the prompt hanging information to obtain a data hanging result, it is possible to reduce labor costs and improve the accuracy and standardization of data hanging.

[0052] In a second aspect, the present disclosure provides a building data hanging device, and the device includes:

[0053] An acquisition module, configured to acquire a building data knowledge graph and a first building data source and a second building data source to be hung;

[0054] An extraction module, configured to extract the first construction information corresponding to each first building data in the first building data source and the second construction information corresponding to each second building data in the second building data source from the building data knowledge graph by using a pre-trained data hanging model;

[0055] A screening module, configured to screen, according to the hierarchical relationship of the building data knowledge graph, multiple candidate construction information associated with any first target construction information from all the second construction information for each first construction information;

[0056] An attachment module, configured to screen a second target construction information from the multiple candidate construction information by using a data attachment model and the building data knowledge graph, and attach the second target construction information to the first target construction information to obtain a data attachment result.

[0057] In a third aspect, the present disclosure provides a computer device, including: a memory and a processor, which are communicatively connected to each other, wherein the memory stores computer instructions, and the processor executes the computer instructions to execute the building data attachment method according to the first aspect or any corresponding embodiment thereof.

[0058] In a fourth aspect, the present disclosure provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to cause a computer to execute the building data attachment method according to the first aspect or any corresponding embodiment thereof.

[0059] In a fifth aspect, the present disclosure provides a computer program product, including computer instructions, and the computer instructions are used to cause a computer to execute the building data attachment method according to the first aspect or any corresponding embodiment thereof. Description of the Drawings

[0060] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the following will briefly introduce the drawings required to be used in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0061] Figure 1 is a flowchart of a building data attachment method according to an embodiment of the present disclosure;

[0062] Figure 2 is a schematic diagram of a knowledge graph according to an embodiment of the present disclosure;

[0063] Figure 3 is a flowchart of a building data attachment method according to another embodiment of the present disclosure;

[0064] Figure 4 is a flowchart of a building data attachment method according to still another embodiment of the present disclosure;

[0065] Figure 5It is a schematic flowchart of a method for attaching building data according to another embodiment of the present disclosure;

[0066] Figure 6 It is a structural block diagram of a building data attachment device according to an embodiment of the present disclosure;

[0067] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present disclosure. Detailed implementation manners

[0068] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.

[0069] In the construction field, there are various types of source data in different scenarios. These data are stored independently of each other and lack effective association and integration. In the actual project process, it is necessary to establish an attachment relationship between different data sources to achieve the connection and cooperation between different construction stages and different participants.

[0070] Currently, the commonly used method for attaching building data usually requires experienced business personnel to read different source data throughout and manually establish an attachment relationship after analysis. This method not only requires a large number of experienced business personnel, but also the data attachment operation is cumbersome, time-consuming and laborious, and it is also prone to attachment errors, resulting in inefficient decision-making and mistakes in the construction process management, and the efficiency and accuracy of building data attachment are relatively low.

[0071] To solve the above problems, according to an embodiment of the present disclosure, an embodiment of a method for attaching building data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from that here.

[0072] In this embodiment, a method for attaching building data is provided, as Figure 1 shown, Figure 1 It is a schematic flowchart of a method for attaching building data according to an embodiment of the present disclosure. This process can be applied to a computer device such as a server, and includes the following steps:

[0073] Step S101, obtain a building data knowledge graph and a first building data source and a second building data source to be attached.

[0074] Construction data sources are usually some actual project data sources, including the first construction data source and the second construction data source. Usually, the construction work of the construction data in the first construction data source is at a lower level than that of the construction data in the second construction data source. For example, the first construction data source can be a construction progress plan, etc., and the second construction data source can be a cost item, etc.

[0075] Specifically, users can create corresponding styles of construction data sources in a computer device according to actual needs and save them. When it is necessary to parse the construction data source, the computer device can access the storage location of the construction data source and obtain the corresponding construction data source from this storage location. Of course, it can also be obtained in real time. For example, a fixed time point is set, and when the time reaches this fixed time point, the construction data source obtained at that time is automatically pushed to the computer device. At this time, the computer device can automatically obtain this construction data source, and no specific limitation is made here.

[0076] In addition, as Figure 2 shown, the construction data knowledge graph is a knowledge graph in the construction field constructed based on construction project data. This construction project data is usually some actual project data, such as cost list, cost item, progress plan, etc. The construction data knowledge graph can be constructed by a method based on rules and templates, or by a model architecture based on machine learning, or by integrating a method based on rules and templates and a model architecture based on machine learning. No specific limitation is made here.

[0077] Step S102, use the pre-trained data connection model to extract the first construction information corresponding to each first construction data in the first construction data source and the second construction information corresponding to each second construction data in the second construction data source from the construction data knowledge graph.

[0078] The first construction data is the construction data in the first construction data source. For example, if the first construction data source is a construction progress plan, the first construction data can be civil engineering stage | Building 1 | 3rd floor | Area C | Main wall steel bars. The second construction data is the construction data in the second construction data source. For example, if the second construction data source is a cost item, the second construction data can be labor subcontracting \ main project \ steel project.

[0079] As Figure 2 shown, the construction information refers to the information corresponding to the construction work. The construction work includes sub-project level (such as decoration engineering), sub-item project level (such as exterior wall decoration project, interior wall decoration project, wall plastering), process level (such as exterior wall plastering, interior wall plastering), and practice level (such as mortar leveling at the bottom of the canopy slab, mortar leveling of the exterior wall, mortar leveling of the interior wall, mortar leveling of the interior wall).

[0080] The construction information includes first construction information and second construction information. Among them, the first construction information refers to the construction information corresponding to the first building data in the building data knowledge graph, and the second construction information refers to the construction information corresponding to the second building data in the building data knowledge graph.

[0081] The pre-trained data attachment model is used to attach construction project data for different data sources. Specifically, the data attachment model can be trained based on the model architecture of a large language model, or based on the model architecture of machine learning, or based on the model architecture of a neural network. There is no specific limitation here.

[0082] Taking the data attachment model trained based on the model architecture of a large language model as an example, the computer device first traverses each first building data in the first building data source, and inputs each first building data and a text extraction instruction (a prompt word used to describe the extraction of the first construction information in the first building data) into the data attachment model. The data attachment model is used to extract the first construction information corresponding to each first building data according to the text extraction instruction, and outputs a natural language description of the first construction information.

[0083] Then, the computer device traverses each second building data in the second building data source, and inputs each second building data and a text extraction instruction (a prompt word used to describe the extraction of the second construction information in the second building data) into the data attachment model. The data attachment model is used to extract the second construction information corresponding to each second building data according to the text extraction instruction, and outputs a natural language description of the second construction information.

[0084] Step S103, for any one of the first target construction information in each of the first construction information, according to the hierarchical relationship of the building data knowledge graph, screen out multiple candidate construction information associated with the first target construction information from all the second construction information.

[0085] The first target construction information is included in the first construction information, which refers to any one of the construction information in the first construction information. The candidate construction information is the construction information in the second construction information that is associated with the first target construction information. For example: for multiple first construction information: decoration project, exterior wall decoration project, interior wall decoration project, wall plastering, any one of the construction information can be the first target construction information.

[0086] In the construction field, building data is the specific data in the building data source, construction information is the information corresponding to the construction work in the building data, construction work is the specific work content in the building construction process, and the construction object is the specific thing or part that the construction work acts on in the building construction process.

[0087] The hierarchical relationships of the building data knowledge graph include the construction level, construction priority, and object level. For example, Figure 2 As shown, the construction level refers to the hierarchical relationships among different construction works. For example, the decoration and finishing project belongs to the civil engineering project; the ceiling project belongs to the interior decoration project; the plaster mortar plastering of the canopy slab belongs to the exterior wall plastering, etc. The construction priority refers to the priority relationships among different construction works. For example, the priority of the work related to the plastering project is higher than that of the painting project. The object level refers to the hierarchical relationships among different construction objects. For example, the wall includes the interior wall and the exterior wall.

[0088] According to the hierarchical relationships of the building data knowledge graph, the computer device first screens the first target construction information according to the construction priority, and then determines the construction levels of the screened first target construction information and all the second construction information in the building data knowledge graph. According to the relationship between the construction level of the screened first target construction information and the construction level of the second construction information, the second construction information is screened to obtain multiple candidate construction information associated with the first target construction information.

[0089] Step S104, using the data hanging model and the building data knowledge graph, screen out the second target construction information from the multiple candidate construction information, and hang the second target construction information with the first target construction information to obtain the data hanging result.

[0090] Data hanging refers to automatically matching and connecting the data with associated relationships in different source data, that is, hanging a piece of data under the first building data source to the most suitable piece of data under the second building data source. The second target construction information is included in the candidate construction information and is used for data hanging with the first target construction information. For example, for multiple candidate construction information: decoration and finishing project, exterior wall decoration project, interior wall decoration project, wall plastering, the second target construction information may be any one of the construction information.

[0091] The computer device first determines the construction levels of the multiple candidate construction information according to the hierarchical relationships of the building data knowledge graph, screens the candidate construction information according to the relationship between the construction level of the first target construction information and the construction level of the candidate construction information to obtain the screened candidate construction information, then obtains the construction objects corresponding to the screened candidate construction information according to the building data knowledge graph, determines the object levels of the construction objects corresponding to the screened candidate construction information according to the hierarchical relationships of the building data knowledge graph, and further screens the screened candidate construction information according to the relationship between the object levels of the screened candidate construction information to obtain the second target construction information.

[0092] After that, the computer device inputs the second target construction information and a preset filtering rule (a filtering rule preset according to the actual application scenario) into the data hanging model, and uses the data hanging model to filter the second target construction information according to the preset filtering rule, and outputs the filtered second target construction information.

[0093] Finally, the computer device hangs the first target construction information and the filtered second target construction information. The first target construction information and the filtered second target construction information can be integrated into a unified record, or the first target construction information and the filtered second target construction information can be quickly accessed and called by establishing data pointers, references, etc., to obtain the final data hanging result.

[0094] In the embodiment of the present disclosure, by obtaining a building data knowledge graph and a first building data source and a second building data source to be hung; using a pre-trained data hanging model to extract the first construction information corresponding to each first building data in the first building data source and the second construction information corresponding to each second building data in the second building data source from the building data knowledge graph; for any one of the first target construction information in each first construction information, according to the hierarchical relationship of the building data knowledge graph, screening out multiple candidate construction information associated with the first target construction information from all the second construction information; using the data hanging model and the building data knowledge graph, screening out the second target construction information from the multiple candidate construction information, and hanging the second target construction information with the first target construction information to obtain a data hanging result. Since the embodiment of the present disclosure hangs the building data of different building data sources through the data hanging model and the knowledge graph, the efficiency and accuracy of building data hanging are improved.

[0095] In some alternative embodiments, the present embodiment provides a method for hanging building data, as Figure 3 shown, Figure 3 is a schematic flowchart of a method for hanging building data according to another embodiment of the present disclosure. This process can be applied to a computer device, such as a server, etc., and includes the following steps:

[0096] Step S201, obtain a building data knowledge graph and a first building data source and a second building data source to be hung.

[0097] Specifically, obtaining the building data knowledge graph in the above step S201 includes:

[0098] Step S2011, obtain different types of building construction data.

[0099] Building engineering data are usually some actual engineering data, such as: cost list, cost item, schedule plan, etc.

[0100] Specifically, users can create construction project data of corresponding styles in a computer device according to actual needs and save it. When it is necessary to parse the construction project data, the computer device can access the storage location of the construction project data and obtain the corresponding construction project data from this storage location. Of course, it can also be obtained in real time. For example, by setting a fixed time point, when the time reaches this fixed time point, the construction project data obtained at that moment is automatically pushed to the computer device, and then the computer device can automatically obtain this construction project data. There is no specific limitation here.

[0101] Step S2012: Based on the construction work of the construction data, construct the construction priority and construction level of the construction work.

[0102] As Figure 2 shown, the construction data knowledge graph contains construction work at different levels and with different priorities. The construction work includes sub-project levels (such as building decoration and fit-out, main structure, etc.), itemized project levels (such as plastering work, leveling work, wall work, ceiling work, etc.), process levels (such as wall plastering, ceiling keel installation, etc.), and practice levels (such as applying putty on walls, spraying fireproof paint on steel columns, etc.).

[0103] The construction priority refers to the priority relationship between different construction works. For example, the priority of work related to plastering work is higher than that of painting work.

[0104] The construction level refers to the hierarchical relationship between different construction works. For example, the decoration and fit-out project belongs to the civil engineering project; the ceiling project belongs to the interior decoration project; the plastering of the awning board with gypsum mortar belongs to the exterior wall plastering, etc.

[0105] Specifically, the computer device can use natural language processing technology, data mining technology, or semantic analysis technology to analyze the priority relationship and hierarchical relationship between the construction works of the construction project data, and obtain the construction priority and construction level of the construction work.

[0106] Step S2013: Based on the construction work of the construction data, construct the construction object corresponding to the construction work.

[0107] The construction object refers to the specific thing or part that the construction work acts on during the construction process. As Figure 2 shown, the construction work in the construction data knowledge graph corresponds to a construction object. For example, the construction object of applying putty on the wall is the wall.

[0108] Specifically, the computer device can use natural language processing technology, data mining technology, or semantic analysis technology to analyze the construction object corresponding to the construction work of the construction project data, and obtain the construction object corresponding to the construction work.

[0109] In step S2014, based on the relationships between construction objects, an object hierarchy of construction objects is constructed.

[0110] As Figure 2 shown, there is an object hierarchy among the construction objects in the building data knowledge graph. The object hierarchy refers to the hierarchical relationships between different construction objects. For example, a wall includes an interior wall and an exterior wall.

[0111] Specifically, the computer device can use natural language processing technology, data mining technology, or semantic analysis technology to analyze the hierarchical relationships between different construction objects in the building engineering data to obtain the object hierarchy of construction objects.

[0112] In step S2015, a knowledge graph of building data is generated by constructing a graph according to the construction priority, construction hierarchy, construction objects, and object hierarchy.

[0113] The building data knowledge graph can be constructed by a rule - and - template - based method, or by a machine - learning - based model architecture, or by integrating a rule - and - template - based method and a machine - learning - based model architecture. No specific limitation is made here.

[0114] Specifically, based on any of the above - mentioned methods or other methods, the computer device constructs corresponding nodes in the knowledge graph according to the construction work and construction objects, constructs the relationships between the corresponding construction work nodes in the knowledge graph according to the construction priority and construction hierarchy, and constructs the relationships between the corresponding construction object nodes in the knowledge graph according to the object hierarchy, and finally obtains the building data knowledge graph.

[0115] In step S202, the pre - trained data hanging model is used to extract the first construction information corresponding to each first building data in the first building data source and the second construction information corresponding to each second building data in the second building data source from the building data knowledge graph. For details, please refer to Figure 1 step S102 of the embodiment shown herein, which will not be elaborated here.

[0116] In step S203, for any one of the first target construction information in each first construction information, according to the hierarchical relationship of the building data knowledge graph, a plurality of candidate construction information associated with the first target construction information is screened out from all the second construction information. For details, please refer to Figure 1 step S103 of the embodiment shown herein, which will not be elaborated here.

[0117] In step S204, the data hanging model and the building data knowledge graph are used to screen out the second target construction information from the plurality of candidate construction information, and the second target construction information is hung up with the first target construction information to obtain a data hanging result.Figure 1 Step S104 of the illustrated embodiment will not be elaborated here.

[0118] In the embodiments of the present disclosure, by constructing a knowledge graph based on the construction priority, construction level, construction object, and object level in the construction data, a knowledge graph with clear structure and rich information can be generated, improving the accuracy and efficiency of building data attachment.

[0119] In some alternative embodiments, this embodiment provides a method for attaching building data, as Figure 4 shown, Figure 4 is a schematic flowchart of a method for attaching building data according to another embodiment of the present disclosure. This process can be applied to computer devices, such as servers, and includes the following steps:

[0120] Step S301, obtain the building data knowledge graph and the first building data source and the second building data source to be attached. For details, please refer to Figure 3 Step S201 of the illustrated embodiment will not be elaborated here.

[0121] Step S302, use the pre-trained data attachment model to extract the first construction information corresponding to each first building data in the first building data source and the second construction information corresponding to each second building data in the second building data source from the building data knowledge graph.

[0122] Specifically, the above step S302 includes:

[0123] Step S3021, compare the similarity between each first building data and the building data knowledge graph to obtain multiple first candidate construction information related to each first building data.

[0124] Among them, the first candidate construction information refers to the construction work related to the first building data in the building data knowledge graph.

[0125] Specifically, before comparing the similarity between each first building data and the building data knowledge graph, the computer device first uses a text embedding model to convert the data texts of each first building data and the building data knowledge graph into numerical vectors. Among them, the text embedding model can be traditional models such as the bag-of-words model and the term frequency-inverse document frequency model, or a model trained based on a neural network, or a pre-trained language model, and no specific limitation is made here.

[0126] Next, the computer device calculates the similarity between each first building data vector and the building data knowledge graph vector respectively, then compares the magnitudes of the similarities, and obtains multiple first candidate construction information with the highest similarity between each first building data vector and each data text in the building knowledge graph according to the magnitude relationship of the similarities. Among them, the similarity calculation method can be cosine similarity or Euclidean distance. The similarity can be character similarity or semantic similarity.

[0127] Step S3022: Compare the similarity between each second building data and the building data knowledge graph to obtain multiple second candidate construction information related to each second building data.

[0128] Among them, the second candidate construction information refers to the construction work related to the second building data in the building data knowledge graph.

[0129] Specifically, before comparing the similarity between each second building data and the building data knowledge graph, the computer device first uses a text embedding model to convert each second building data and the data text in the building data knowledge graph into numerical vectors. Among them, the text embedding model can be a traditional model such as a bag-of-words model or a term frequency-inverse document frequency model, or a model trained based on a neural network, or a pre-trained language model, and no specific limitation is made here.

[0130] Next, the computer device calculates the similarity between each second building data vector and the building data knowledge graph vector respectively, then compares the magnitudes of the similarities, and obtains multiple second candidate construction information with the highest similarity between each second building data vector and each data text in the building knowledge graph according to the magnitude relationship of the similarities. Among them, the similarity calculation method can be cosine similarity or Euclidean distance. The similarity can be character similarity or semantic similarity.

[0131] In a specific example, for the second building data: "labor subcontracting\main project\steel project", the computer device can obtain multiple second candidate construction information most similar to the construction work in the building data knowledge graph through similarity comparison: "main project", "civil engineering", "steel structure construction project", "steel structure plastering project", "main steel project", etc.

[0132] Step S3023: Use a data hanging model to determine the first construction information corresponding to the first building data from multiple first candidate construction information, and determine the second construction information corresponding to the second building data from multiple second candidate construction information.

[0133] Among them, the first construction information is included in the first candidate construction information, which refers to the construction work corresponding to the first building data in the building data knowledge graph. The second construction information is included in the second candidate construction information, which refers to the construction work corresponding to the second building data in the building data knowledge graph.

[0134] Specifically, the computer device first traverses each first candidate construction information, and inputs each first candidate construction information and a text screening instruction (a prompt word used to describe the screening of multiple first candidate construction information) into the data connection model. The data connection model is used to screen multiple first candidate construction information according to the text screening instruction, and output the first construction information.

[0135] Then, the computer device traverses each second candidate construction information, and inputs each second candidate construction information and a text screening instruction (a prompt word used to describe the screening of multiple second candidate construction information) into the data connection model. The data connection model is used to screen multiple second candidate construction information according to the text screening instruction, and output the second construction information.

[0136] In a specific example, for multiple second candidate construction information: "main project", "civil engineering", "steel structure construction project", "steel structure plastering project", "main body steel bar project", the computer device screens multiple second candidate construction information through the data connection model, and can obtain the second construction information corresponding to the second building data: "main body steel bar project".

[0137] Step S303, for any first target construction information in each first construction information, according to the hierarchical relationship of the building data knowledge graph, screen out multiple candidate construction information associated with the first target construction information from all the second construction information. For details, please refer to Figure 3 Step S203 of the illustrated embodiment, which will not be elaborated here.

[0138] Step S304, using the data connection model and the building data knowledge graph, screen out the second target construction information from multiple candidate construction information, and connect the second target construction information with the first target construction information to obtain a data connection result. For details, please refer to Figure 3 Step S204 of the illustrated embodiment, which will not be elaborated here.

[0139] In the embodiments of the present disclosure, the first candidate construction information and the second candidate construction information are extracted from the building data knowledge graph through similarity comparison, which can ensure the accuracy and consistency of the construction information. By screening the first candidate construction information and the second candidate construction information through the data connection model, the first construction information and the second construction information can be quickly and accurately determined, improving the efficiency and accuracy of building data connection.

[0140] In some alternative embodiments, the present embodiment provides a method for attaching building data, as Figure 5 shown Figure 5 is a schematic flowchart of a method for attaching building data according to another embodiment of the present disclosure. This process can be applied to computer devices, such as servers, etc., and includes the following steps:

[0141] Step S401, obtain the building data knowledge graph and the first building data source and the second building data source to be attached. For details, please refer to Figure 4 Step S301 of the embodiment shown, which will not be elaborated here.

[0142] Step S402, use the pre-trained data attachment model to extract the first construction information corresponding to each first building data in the first building data source, and the second construction information corresponding to each second building data in the second building data source. For details, please refer to Figure 4 Step S302 of the embodiment shown, which will not be elaborated here.

[0143] Step S403, for any one of the first target construction information in each first construction information, screen out multiple candidate construction information associated with the first target construction information from all the second construction information according to the hierarchical relationship of the building data knowledge graph.

[0144] Specifically, the above step S403 includes:

[0145] Step S4031, obtain all the first construction tasks corresponding to the first target construction information, and determine the first target construction task with the highest priority from all the first construction tasks.

[0146] Among them, the first target construction task is included in the first construction tasks, referring to the construction task with the highest priority among the first construction tasks.

[0147] Specifically, the computer device determines the construction priorities of all the first construction tasks according to the hierarchical relationship of the building data knowledge graph, and screens out the construction task with the highest priority among the first construction tasks according to the relationship between the construction priorities of all the first construction tasks to obtain the first target construction task.

[0148] Step S4032, disassemble the first target construction task according to the building data knowledge graph to obtain the first target disassembly task.

[0149] Among them, the first target disassembly task refers to the construction task with the lowest level obtained after disassembling the first target construction task.

[0150] Specifically, the computer device determines the construction level of the first target construction work according to the hierarchical relationship of the building data knowledge graph, and obtains the construction work with the lowest level subordinate to the first target construction work, thereby obtaining the first target disassembly work.

[0151] In a specific example, for the first target construction work of "wall plastering", it includes "interior wall plastering" and "exterior wall plastering". "Interior wall plastering" includes "interior wall mortar leveling" and "interior wall cement mortar surface layer", and "exterior wall plastering" includes "exterior wall mortar leveling" and "exterior wall cement mortar surface layer". Then, the first target disassembly work corresponding to the first target construction work of "wall plastering" includes: "interior wall mortar leveling", "interior wall cement mortar surface layer", "exterior wall mortar leveling", and "exterior wall cement mortar surface layer".

[0152] Step S4033: Compare the first target disassembly work with the second construction work corresponding to the second construction information, and screen out multiple candidate construction information from the second construction work.

[0153] Specifically, the computer device compares the first target disassembly work with all the second construction works, determines the relationship between the first target disassembly work and all the second construction works, and screens out multiple candidate construction information from the second construction works according to this relationship.

[0154] In some optional implementation manners, the above step S4033 includes:

[0155] Step a1: Identify the relevance between the first construction work and the second construction work.

[0156] Step a2: If the second construction work includes the first target disassembly work, and / or, the second construction work partially includes the first target disassembly work, then determine the construction information corresponding to the second construction work as candidate construction information.

[0157] Step a3: If the second construction work has no relation with the first target disassembly work, then reject the hanging connection.

[0158] Specifically, if the second construction work completely includes or partially includes the first target disassembly work, then there is a relevance between the first construction work and the second construction work; if the second construction work completely does not include the first target disassembly work, then there is no relevance between the first construction work and the second construction work.

[0159] The computer device identifies the relevance between the first construction work and all the second construction works. If there is a second construction work that completely contains the first target disassembly work, then this second construction work is determined as candidate construction information; if there is no second construction work that completely contains the first target disassembly work, and there is a second construction work that partially contains the first target disassembly work, then this second construction work is determined as candidate construction information; if there is no second construction work that completely contains the first target disassembly work, and there is no second construction work that partially contains the first target disassembly work, that is, the second construction work has no relation with the first target disassembly work, then the hanging connection is rejected.

[0160] In the above embodiment, by screening the second construction works according to the relevance between the first construction work and the second construction works, multiple candidate construction information associated with the first target construction information can be accurately determined, improving the accuracy of building data hanging connection. By rejecting the hanging connection when the second construction work has no relation with the first target disassembly work, the occurrence of incorrect hanging connection can be effectively avoided, ensuring the accuracy and rationality of the building data hanging connection result, and enhancing the reliability of the building engineering management and decision-making basis.

[0161] Step S404: Using the data hanging connection model and the building data knowledge graph, screen out the second target construction information from multiple candidate construction information, and hang connect the second target construction information with the first target construction information to obtain the data hanging connection result.

[0162] In some optional embodiments, the above step S404 includes:

[0163] Step S4041: Obtain all candidate construction works corresponding to the candidate construction information.

[0164] Specifically, the computer device obtains all candidate construction works corresponding to multiple candidate construction information screened out from the second construction works.

[0165] Step S4042: Obtain the level of the first target disassembly work in the building data knowledge graph.

[0166] Specifically, the computer device determines the construction level of the first target disassembly work in the building data knowledge graph according to the hierarchical relationship of the building data knowledge graph.

[0167] Step S4043: Based on the level relationship between the candidate construction works and the first target disassembly work, screen out the second target construction work corresponding to the first target disassembly work from all candidate construction works.

[0168] Specifically, after the computer device determines the construction level of the candidate construction work and the construction level of the first target disassembly work, it performs multiple rounds of screening on all candidate construction works according to the relationship between the construction level of the candidate construction work and the construction level of the first target disassembly work, and obtains the second target construction work corresponding to the first target disassembly work.

[0169] In some alternative embodiments, the above step S4043 includes:

[0170] Step b1, excluding the candidate construction works that have the same level or a superior relationship with the first target disassembly work from all candidate construction works, to obtain the first remaining construction works.

[0171] Step b2, excluding the construction works that have a superior relationship with other construction works from the first remaining construction works, to obtain the second remaining construction works.

[0172] Step b3, obtaining the second work object corresponding to the second remaining construction works, and screening out the third work object that has a superior relationship with other work objects from the second work objects.

[0173] Step b4, excluding the construction works corresponding to the third work object from the second remaining construction works, to obtain the third remaining construction works, and determining the third remaining construction works as the second target construction work.

[0174] Specifically, according to the hierarchical relationship of the building data knowledge graph, the computer device first excludes the candidate construction works that have the same level or a superior relationship with the first target disassembly work from all candidate construction works, to obtain the first remaining construction works, and then excludes the construction works that have a superior relationship with other construction works from the first remaining construction works, to obtain the second remaining construction works.

[0175] After that, the computer device obtains the second construction object corresponding to the second remaining construction works according to the building data knowledge graph, and then, according to the hierarchical relationship of the building data knowledge graph, screens out the third work object that has a superior relationship with other work objects from the second work objects, and finally excludes the construction works corresponding to the third work object from the second remaining construction works, to obtain the third remaining construction works, and determines the third remaining construction works as the second target construction work.

[0176] In a specific example, for the first target decomposition task: the mortar surface layer of the interior wall, and the candidate construction tasks: building decoration, mortar surface layer of the wall, and plastering of the interior wall. Since building decoration is the superior of the mortar surface layer of the wall, building decoration is excluded. Since the construction object of the mortar surface layer of the wall is the wall, and the construction object of the plastering of the interior wall is the interior wall, and the wall is the superior of the interior wall, the plastering of the interior wall is excluded. Since only the plastering of the interior wall remains among the candidate construction tasks, the plastering of the interior wall is the final second target construction task.

[0177] In the above implementation, by performing multiple rounds of screening based on the hierarchical relationship between the candidate construction tasks and the first target decomposition task to obtain the second target construction task, it is possible to achieve accurate screening of construction tasks based on the hierarchical logic of the building data knowledge graph, ensure the accuracy and rationality of the building data hanging results, and improve the reliability of the building project management and decision-making basis.

[0178] Step S4044: Determine the construction information corresponding to the second target construction task as the second target construction information.

[0179] Specifically, after the computer device performs multiple rounds of screening on all candidate construction tasks to obtain the second target construction task corresponding to the first target decomposition task, it determines the construction information corresponding to the second target construction task as the second target construction information.

[0180] Step S4045: Use the data hanging model to hang the second target construction information with the first target construction information to obtain the data hanging result.

[0181] Specifically, the computer device inputs the second target construction information and a preset filtering rule (a filtering rule preset according to the actual application scenario) into the data hanging model, and uses the data hanging model to filter the second target construction information according to the preset filtering rule, and outputs the filtered second target construction information.

[0182] Then, the computer device hangs the first target construction information with the filtered second target construction information. It can fuse the first target construction information and the filtered second target construction information in a unified record, or achieve fast access and call between the first target construction information and the filtered second target construction information by establishing data pointers, references, etc., to obtain the final data hanging result.

[0183] In some optional implementation manners, the above step S4045 includes:

[0184] Step c1: Obtain the prompt hanging information of the data hanging model.

[0185] Step c2: Match and perform data attachment on the second target construction information and the first target construction information according to the prompt attachment information to generate a data attachment result.

[0186] Specifically, the computer device first obtains the prompt attachment information of the data attachment model, that is, the prompt words used to filter the second target construction information. The prompt attachment information can be a part matching rule (a rule for determining whether the construction area matches), or other attachment rules not covered by other knowledge graphs (data attachment rules that meet business requirements).

[0187] In a specific example, the prompt attachment information input by the computer device to the data attachment model can be:

[0188] "1. Understand the construction area of the first target construction information.

[0189] 2. Traverse each second target construction information and exclude the specified data below:

[0190] (1) Part matching rule: Exclude the second target construction information that has an obvious contradiction with the construction area of the first target construction information:

[0191] Contradiction type 1 (above ground and underground): Above ground and underground;

[0192] Contradiction type 2 (single building): Building 1 and Building 2;

[0193] Contradiction type 3 (floor): Floor 2 and Floor 5;

[0194] Contradiction type 4 (functional space type): Kitchen and bathroom;

[0195] It is necessary to clearly indicate which of the above contradiction types the contradiction belongs to, and no contradiction types other than above ground and underground, single building, floor, and functional space type shall be fabricated.

[0196] (2) Attachment rules not covered by other knowledge graphs: Exclude the second target construction information related to material costs.

[0197] 3. From the remaining second target construction information in Step 2, select the only second target construction information with the highest matching degree with the first target construction information:

[0198] If there is no remaining second target construction information, one must be selected from the second target construction information input by the user and output;

[0199] Preferably select the second target construction information that is closest to the first target construction information in terms of the construction object description;

[0200] The output second target construction information must be the same as the original text of the candidate second target construction information, and the second target construction information shall not be rewritten or fabricated.

[0201] 4. Output the JSON result in the format:

[0202] Note that there should be no single backslash ('\') in the JSON result to meet the parsing requirements.

[0203] Then, the computer device attaches the first target construction information and the filtered second target construction information, which can either fuse the first target construction information and the filtered second target construction information in a unified record or achieve fast access and invocation between the first target construction information and the filtered second target construction information by establishing data pointers, references, etc., to obtain the final data attachment result.

[0204] In the above embodiment, by adopting the data attachment model and attaching the second target construction information to the first target construction information according to the prompted attachment information to obtain the data attachment result, the labor cost can be reduced and the accuracy and standardization of data attachment can be improved.

[0205] In the embodiments of the present disclosure, by determining the first construction work with the highest priority as the first target construction work, then disassembling the first target construction work and comparing it with the second construction work, multiple candidate construction information associated with the first target construction information can be accurately determined, improving the accuracy of building data attachment. By screening out the second target construction work based on the level relationship between the candidate construction work and the first target disassembly work and attaching it to the first target construction information using the data attachment model, accurate screening and data attachment can be achieved based on the hierarchical logic of the building data knowledge graph, improving the accuracy and rationality of building data attachment.

[0206] In this embodiment, a building data attachment device is also provided. This device is used to implement the above embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0207] This embodiment provides a building data attachment device, as Figure 6 shown, including:

[0208] An acquisition module 601, configured to acquire a building data knowledge graph and a first building data source and a second building data source to be attached;

[0209] An extraction module 602, configured to extract the first construction information corresponding to each first construction data in the first construction data source and the second construction information corresponding to each second construction data in the second construction data source from the construction data knowledge graph by using a pre-trained data connection model;

[0210] A screening module 603, configured to, for any first target construction information among each first construction information, screen out multiple candidate construction information associated with the first target construction information from all the second construction information according to the hierarchical relationship of the construction data knowledge graph;

[0211] A connection module 604, configured to screen out a second target construction information from the multiple candidate construction information by using the data connection model and the construction data knowledge graph, and connect the second target construction information with the first target construction information to obtain a data connection result.

[0212] In the embodiments of the present disclosure, by obtaining a construction data knowledge graph and a first construction data source and a second construction data source to be connected; using a pre-trained data connection model to extract the first construction information corresponding to each first construction data in the first construction data source and the second construction information corresponding to each second construction data in the second construction data source from the construction data knowledge graph; for any first target construction information among each first construction information, screening out multiple candidate construction information associated with the first target construction information from all the second construction information according to the hierarchical relationship of the construction data knowledge graph; using the data connection model and the construction data knowledge graph to screen out a second target construction information from the multiple candidate construction information, and connecting the second target construction information with the first target construction information to obtain a data connection result. Since the embodiments of the present disclosure connect the construction data of different construction data sources through the data connection model and the knowledge graph, the efficiency and accuracy of construction data connection are improved.

[0213] In some optional embodiments, the obtaining module 601 includes:

[0214] A first obtaining sub-module, configured to obtain different types of construction data;

[0215] A first constructing sub-module, configured to construct the construction priority and construction level of the construction work based on the construction work of the construction data;

[0216] A second constructing sub-module, configured to construct the construction object corresponding to the construction work based on the construction work of the construction data;

[0217] A third constructing sub-module, configured to construct the object level of the construction object based on the relationship between the construction objects;

[0218] A generation sub-module, configured to construct a graph according to the construction priority, construction level, construction object, and object level, and generate a building data knowledge graph.

[0219] In some alternative embodiments, the extraction module 602 includes:

[0220] A first comparison sub-module, configured to compare the similarity between each first building data and the building data knowledge graph to obtain a plurality of first candidate construction information related to each first building data;

[0221] A second comparison sub-module, configured to compare the similarity between each second building data and the building data knowledge graph to obtain a plurality of second candidate construction information related to each second building data;

[0222] A first determination sub-module, configured to use a data hanging model to determine the first construction information corresponding to the first building data from the plurality of first candidate construction information, and determine the second construction information corresponding to the second building data from the plurality of second candidate construction information.

[0223] In some alternative embodiments, the screening module 603 includes:

[0224] A second determination sub-module, configured to obtain all first construction tasks corresponding to the first target construction information, and determine the first target construction task with the highest priority from all the first construction tasks;

[0225] A disassembly sub-module, configured to disassemble the first target construction task according to the building data knowledge graph to obtain a first target disassembly task;

[0226] A first screening sub-module, configured to compare the first target disassembly task with the second construction tasks corresponding to the second construction information, and screen out a plurality of candidate construction information from the second construction tasks.

[0227] In some alternative embodiments, the screening sub-module includes:

[0228] An identification unit, configured to identify the relevance between the first construction task and the second construction task;

[0229] A first determination unit, configured to, if the second construction task includes the first target disassembly task, and / or, the second construction task partially includes the first target disassembly task, determine the construction information corresponding to the second construction task as candidate construction information;

[0230] A rejection unit, configured to reject hanging if the second construction task has no relation to the first target disassembly task.

[0231] In some alternative embodiments, the hanging module 604 includes:

[0232] A second acquisition sub-module, configured to acquire all candidate construction tasks corresponding to the candidate construction information;

[0233] A third acquisition sub-module, configured to acquire the level of the first target disassembly task in the building data knowledge graph;

[0234] A second screening sub-module, configured to screen out a second target construction task corresponding to the first target disassembly task from all candidate construction tasks based on the level relationship between the candidate construction tasks and the first target disassembly task;

[0235] A third determination sub-module, configured to determine the construction information corresponding to the second target construction task as the second target construction information;

[0236] A hanging connection sub-module, configured to hang-connect the second target construction information and the first target construction information by using a data hanging connection model to obtain a data hanging connection result.

[0237] In some alternative embodiments, the second screening sub-module includes:

[0238] A first exclusion unit, configured to exclude candidate construction tasks that have the same level or a superior relationship with the first target disassembly task from all candidate construction tasks to obtain first remaining construction tasks;

[0239] A second exclusion unit, configured to exclude construction tasks that have a superior relationship with other construction tasks from the first remaining construction tasks to obtain second remaining construction tasks;

[0240] A screening unit, configured to obtain second work objects corresponding to the second remaining construction tasks, and screen out third work objects that have a superior relationship with other work objects from the second work objects;

[0241] A second determination unit, configured to exclude the construction tasks corresponding to the third work objects from the second remaining construction tasks to obtain third remaining construction tasks, and determine the third remaining construction tasks as the second target construction tasks.

[0242] In some alternative embodiments, the hanging connection sub-module includes:

[0243] An acquisition unit, configured to acquire the prompt hanging connection information of the data hanging connection model;

[0244] A generation unit, configured to match and perform data hanging connection on the second target construction information and the first target construction information according to the prompt hanging connection information to generate a data hanging connection result.

[0245] The further function descriptions of the above-mentioned various modules and units are the same as those in the corresponding foregoing embodiments, and will not be elaborated herein.

[0246] The building data attachment device in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0247] This embodiment of the disclosure also provides a computer device having the above Figure 6 shown building data attachment device.

[0248] Please refer to Figure 7 , Figure 7 which is a schematic structural diagram of a computer device provided by an alternative embodiment of the disclosure. As Figure 7 shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. Each component communicates with each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some alternative embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (such as an array of servers, a set of blade servers, or a multi-processor system). Figure 7 In

[0249] FIG. 15, a processor 10 is taken as an example.

[0250] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0251] The memory 20 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the computer device and the like. In addition, the memory 20 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 may optionally include a memory remotely disposed relative to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0252] The memory 20 may include volatile memory, for example, random access memory; the memory may also include non-volatile memory, for example, flash memory, a hard disk, or a solid-state drive; the memory 20 may further include a combination of the above types of memories.

[0253] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0254] The embodiments of the present disclosure also provide a computer-readable storage medium. The methods according to the embodiments of the present disclosure can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and to be stored in a local storage medium, so that the methods described herein can be stored in such software processes on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the methods shown in the above embodiments are implemented.

[0255] A part of the present disclosure can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can call or provide the methods and / or technical solutions according to the present disclosure through the operations of the computer. Those skilled in the art should understand that the forms of existence of computer program instructions in a computer-readable medium include but are not limited to source files, executable files, installation package files, etc. Correspondingly, the ways for a computer to execute computer program instructions include but are not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Herein, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0256] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A building data connection method, characterized in that, The method includes: Obtaining a building data knowledge graph, a first building data source and a second building data source to be attached; Using a pre-trained data attachment model to extract the first construction information corresponding to each first building data in the first building data source and the second construction information corresponding to each second building data in the second building data source from the building data knowledge graph; For any first target construction information among each of the first construction information, according to the hierarchical relationship of the building data knowledge graph, screening out a plurality of candidate construction information associated with the first target construction information from all the second construction information; Using the data attachment model and the building data knowledge graph, screening out a second target construction information from the plurality of candidate construction information, and attaching the second target construction information to the first target construction information to obtain a data attachment result.

2. The method according to claim 1, wherein Obtaining the building data knowledge graph includes: Obtaining different types of building construction data; Based on the construction work of the building construction data, constructing the construction priority and construction level of the construction work; Based on the construction work of the building construction data, constructing the construction object corresponding to the construction work; Based on the relationship between the construction objects, constructing the object level of the construction objects; Constructing a graph according to the construction priority, the construction level, the construction object and the object level to generate the building data knowledge graph.

3. The method according to claim 1, wherein The step of using a pre-trained data attachment model to extract the first construction information corresponding to each first building data in the first building data source and the second construction information corresponding to each second building data in the second building data source from the building data knowledge graph includes: Comparing the similarity of each of the first building data with the building data knowledge graph to obtain a plurality of first candidate construction information related to each of the first building data; Comparing the similarity of each of the second building data with the building data knowledge graph to obtain a plurality of second candidate construction information related to each of the second building data; Using the data attachment model to determine the first construction information corresponding to the first building data from the plurality of first candidate construction information and determine the second construction information corresponding to the second building data from the plurality of second candidate construction information.

4. The method according to claim 1, wherein The step of screening out a plurality of candidate construction information associated with the first target construction information from all the second construction information according to the hierarchical relationship of the building data knowledge graph includes: Obtaining all the first construction work corresponding to the first target construction information, and determining the first target construction work with the highest priority from all the first construction work; Decomposing the first target construction work according to the building data knowledge graph to obtain a first target decomposition work; Comparing the first target decomposition work with the second construction work corresponding to the second construction information, and screening out a plurality of the candidate construction information from the second construction work.

5. The method according to claim 4, characterized in that, Comparing the first target disassembly work with the second construction work corresponding to the second construction information, and screening out a plurality of the candidate construction information from the second construction work, including: Identifying the relevance between the first construction work and the second construction work; If the second construction work includes the first target disassembly work, and / or, the second construction work partially includes the first target disassembly work, determining the construction information corresponding to the second construction work as the candidate construction information.

6. The method according to claim 5, characterized in that, It further includes: If the second construction work has no relation with the first target disassembly work, rejecting the hanging connection.

7. The method according to claim 4, characterized in that, Using the data hanging connection model and the building data knowledge graph to screen out the second target construction information from the plurality of candidate construction information, and hanging the second target construction information with the first target construction information to obtain a data hanging connection result, including: Obtaining all candidate construction works corresponding to the candidate construction information; Obtaining the level of the first target disassembly work in the building data knowledge graph; Based on the level relationship between the candidate construction work and the first target disassembly work, screening out the second target construction work corresponding to the first target disassembly work from all the candidate construction works; Determining the construction information corresponding to the second target construction work as the second target construction information; Using the data hanging connection model to hang the second target construction information with the first target construction information to obtain the data hanging connection result.

8. The method according to claim 7, characterized in that, The screening out the second target construction work corresponding to the first target disassembly work from all the candidate construction works based on the level relationship between the candidate construction work and the first target disassembly work includes: Excluding the candidate construction works having the same level or a superior relationship with the first target disassembly work from all the candidate construction works to obtain the first remaining construction works; Excluding the construction works having a superior relationship with other construction works from the first remaining construction works to obtain the second remaining construction works; Obtaining the second work objects corresponding to the second remaining construction works, and screening out the third work objects having a superior relationship with other work objects from the second work objects; Excluding the construction works corresponding to the third work objects from the second remaining construction works to obtain the third remaining construction works, and determining the third remaining construction works as the second target construction work.

9. The method according to claim 7, wherein The using the data hanging connection model to hang the second target construction information with the first target construction information to obtain the data hanging connection result includes: Obtaining the prompt hanging connection information of the data hanging connection model; Matching and performing data hanging connection on the second target construction information and the first target construction information according to the prompt hanging connection information to generate the data hanging connection result.

10. A building data connection device, characterized in that, The device includes: An obtaining module, configured to obtain a building data knowledge graph and a first building data source and a second building data source to be hung. An extraction module, configured to extract the first construction information corresponding to each first construction data in the first construction data source and the second construction information corresponding to each second construction data in the second construction data source from the construction data knowledge graph by using a pre-trained data connection model; A screening module, configured to, for any first target construction information among each of the first construction information, screen out a plurality of candidate construction information associated with the first target construction information from all the second construction information according to the hierarchical relationship of the construction data knowledge graph; A connection module, configured to use the data connection model and the construction data knowledge graph to screen out a second target construction information from the plurality of candidate construction information, and connect the second target construction information with the first target construction information to obtain a data connection result.

11. A computer device, characterized in that, Comprising: A memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the construction data connection method according to any one of claims 1 to 9.

12. A computer program product, characterized in that, Comprising computer instructions for causing a computer to execute the construction data connection method according to any one of claims 1 to 9.

Images