Shared resource management and control method and device based on BIM system and computer equipment
By obtaining the characteristic information of the building information model and user needs, and generating model correlation maps and keywords, the problems of low retrieval efficiency and insufficient accuracy in traditional management and control methods are solved, and more efficient building information model retrieval and screening are achieved.
Patent Information
- Application Number
- CN202410985532.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-12
AI Technical Summary
The traditional building information model management method is inefficient, making it difficult for users to accurately retrieve the target model, and cannot be effectively retrieved under semantic fuzzy conditions, resulting in insufficient search accuracy and comprehensiveness.
By obtaining feature information of the building information model, generating model correlation maps and keywords, combining user needs and project information, dividing model groups and filtering target models, improving the accuracy and comprehensiveness of the search.
It improves the search efficiency and accuracy of building information models, avoids search failures caused by semantic ambiguity, and enhances the satisfaction of user needs and the comprehensiveness of model screening.
Smart Images

Figure CN118940373A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of BIM technology, and in particular to a shared resource management and control method, device and computer equipment based on a BIM system. Background Art
[0002] With the development of BIM (Building Information Modeling) technology, various building information models are constantly being constructed and generated. For enterprises, a large number of building information models can not only be used for current projects, but also can be used as reference models for other projects and other resources. Especially when ordinary construction personnel need to retrieve, review, and manage various building information models, the control effect of each building information model is particularly important. Therefore, how to improve the control effect of each building information model is the current research focus.
[0003] The traditional way to manage and control multiple building information models is to divide the building information models based on their source, classification, time and other information, so as to facilitate user retrieval and query. However, the simple division method often makes it less efficient for users to retrieve the target building information model, and when the user's retrieval semantics are vague, there are situations where retrieval cannot be performed or retrieval fails. Not only can the target building information model required by the user not be retrieved, but the retrieved target building information model may be different from the target building information model actually required by the user, resulting in low accuracy of each retrieved building information model. Summary of the invention
[0004] Based on this, it is necessary to provide a shared resource management and control method, device, computer equipment, computer-readable storage medium and computer program product based on a BIM system to address the above technical problems.
[0005] In a first aspect, the present application provides a shared resource management and control method based on a BIM system, comprising: Obtaining model introduction information of each building information model, model requirement information of the user, and current project information of the user, and extracting each model feature information of each building information model; Based on the model feature information of each building information model, a model association map between each building information model and a model keyword of each building information model are generated, and based on the model introduction information of each building information model and the model keyword of each building information model, each building information model is divided into model groups; Based on the model requirement information and the current project information, the actual requirement content of the user is generated, and based on the actual requirement content, the target building information model required by the user is screened through each of the model groups and the model association map.
[0006] Optionally, extracting each model feature information of each building information model includes: For each building information model, split the building information model into building structure information, model physical information, and model rule information; Extracting structural features from the building structure information through a three-dimensional model extraction network, and converting the physical information into physical text information, and converting the model rule information into rule text information; The physical features in the physical text information and the rule features in the rule text information are extracted respectively through a text extraction network, and the structural features, the physical features and the rule features are used as each model feature information of the building information model.
[0007] Optionally, the generating, based on the model feature information of each building information model, a model association graph between each building information model and a model keyword of each building information model comprises: For each two building information models, the similarity between each model feature information of the two building information models is calculated by a similarity recognition algorithm, and each model feature information corresponding to a similarity greater than a similarity threshold is used as association information between the two building information models; Based on the association information between the building information models, a model association map is constructed, and for each building information model, based on the model feature information of each building information model, feature content corresponding to each model feature information of the building information model is identified; The keywords corresponding to each characteristic content are extracted by a keyword extraction algorithm to obtain model keywords of the building information model.
[0008] Optionally, the dividing each building information model into model groups based on the model introduction information of each building information model and the model keywords of each building information model includes: Each model introduction information is split into sub-introduction information of each model introduction type, and each building information model is classified into the same category based on each sub-introduction information of each model introduction type to obtain each initial model group corresponding to each model introduction type; For each initial model group, clustering is performed on each building information model in the initial model group based on model keywords of each building information model in the initial model group to obtain a cluster center model in the initial model group, and a preset number of target cluster center models are screened based on the cluster center models of each initial model group corresponding to each model introduction type; Based on each target cluster center model, model clustering processing is performed on each of the building information models to obtain each model group.
[0009] Optionally, the generating the actual demand content of the user based on the model demand information and the current project information includes: Based on the current project information, identifying the project introduction information of the user, and based on the project introduction information, identifying a first model keyword corresponding to the current project information; Converting the model requirement information into requirement text information, and identifying text semantic information of the requirement text information through a text recognition network; Calculating the similarity between each model keyword and the text semantic information respectively, and selecting the model keyword corresponding to the similarity greater than the similarity threshold as the second model keyword; Each of the first model keywords and each of the second model keywords are used as the actual demand content of the user.
[0010] Optionally, the step of screening the target building information model required by the user through each of the model groups and the model association graph based on the actual requirement content includes: In each of the model groups, a building information model including both the first model keywords and the second model keywords is selected as a first building information model; Based on the model association map, a building information model highly associated with the first building information model is selected as a second building information model, and based on the association information between each first building information model and each second building information model, an association relationship between each first building information model and each second building information model is constructed; The first building information models, the second building information models, and the association relationships are used as target building information models required by the user.
[0011] In a second aspect, the present application also provides a shared resource management and control device based on a BIM system, comprising: An acquisition module, used to acquire model introduction information of each building information model, model requirement information of a user, and current project information of the user, and extract each model feature information of each building information model; A division module, for generating a model association map between the building information models and a model keyword of each building information model based on the model feature information of each building information model, and dividing the building information models into model groups based on the model introduction information of each building information model and the model keyword of each building information model; The screening module is used to generate the actual demand content of the user based on the model demand information and the current project information, and based on the actual demand content, screen the target building information model required by the user through each of the model groups and the model association map.
[0012] Optionally, the acquisition module is specifically used to: For each building information model, split the building information model into building structure information, model physical information, and model rule information; Extracting structural features from the building structure information through a three-dimensional model extraction network, and converting the physical information into physical text information, and converting the model rule information into rule text information; The physical features in the physical text information and the rule features in the rule text information are extracted respectively through a text extraction network, and the structural features, the physical features and the rule features are used as each model feature information of the building information model.
[0013] Optionally, the division module is specifically used to: For each two building information models, the similarity between each model feature information of the two building information models is calculated by a similarity recognition algorithm, and each model feature information corresponding to a similarity greater than a similarity threshold is used as association information between the two building information models; Based on the association information between the building information models, a model association map is constructed, and for each building information model, based on the model feature information of each building information model, feature content corresponding to each model feature information of the building information model is identified; The keywords corresponding to each characteristic content are extracted by a keyword extraction algorithm to obtain model keywords of the building information model.
[0014] Optionally, the division module is specifically used to: Each model introduction information is split into sub-introduction information of each model introduction type, and each building information model is classified into the same category based on each sub-introduction information of each model introduction type to obtain each initial model group corresponding to each model introduction type; For each initial model group, clustering is performed on each building information model in the initial model group based on model keywords of each building information model in the initial model group to obtain a cluster center model in the initial model group, and a preset number of target cluster center models are screened based on the cluster center models of each initial model group corresponding to each model introduction type; Based on each target cluster center model, model clustering processing is performed on each of the building information models to obtain each model group.
[0015] Optionally, the screening module is specifically used for: Based on the current project information, identifying the project introduction information of the user, and based on the project introduction information, identifying a first model keyword corresponding to the current project information; Converting the model requirement information into requirement text information, and identifying text semantic information of the requirement text information through a text recognition network; Calculating the similarity between each model keyword and the text semantic information respectively, and selecting the model keyword corresponding to the similarity greater than the similarity threshold as the second model keyword; Each of the first model keywords and each of the second model keywords are used as the actual demand content of the user.
[0016] Optionally, the screening module is specifically used for: In each of the model groups, a building information model including both the first model keywords and the second model keywords is selected as a first building information model; Based on the model association map, a building information model highly associated with the first building information model is selected as a second building information model, and based on the association information between each first building information model and each second building information model, an association relationship between each first building information model and each second building information model is constructed; The first building information models, the second building information models, and the association relationships are used as target building information models required by the user.
[0017] In a third aspect, the present application provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.
[0018] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.
[0019] In a fifth aspect, the present application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.
[0020] The above-mentioned shared resource management and control method, device and computer equipment based on the BIM system obtains each building information model, the model introduction information of each building information model, the model requirement information of the user, and the current project information of the user, and extracts each model feature information of each building information model; based on each model feature information of each building information model, generates a model association map between each building information model and the model keywords of each building information model, and divides each building information model into each model group based on the model introduction information of each building information model and the model keywords of each building information model; based on the model requirement information and the current project information, generates the actual demand content of the user, and based on the actual demand content, through each model group and the model association map, screens the target building information model required by the user. This solution extracts each model feature information of the building information model, thereby constructing a model association map between each building information model, so that when the user searches for a model, the user can be provided with each building information model required by the user and the building information model that the user may require, thereby improving the comprehensiveness of the building information model fed back to the user for retrieval. Then, this solution extracts the keywords of each model and the model introduction information of the building information model, thereby dividing each building information model into multiple model groups. Compared with the traditional model grouping method, this solution is not limited to the model classification of each model by model category, but classifies each model by combining the model keywords and model introduction information of each model (including the model source and the sub-introduction information corresponding to each model introduction type of the model category), thereby improving the accuracy of classification. After that, this solution extracts the user's demand text information and model demand information, as well as the current project information, thereby determining the user's actual demand content, avoiding the problem that the user's search semantics are ambiguous and cannot be directly retrieved, and improving the accuracy of identifying the user's actual demand content. Finally, through the actual demand content, model group, and model association map, the target building information model required by the user and the target building information model of potential demand are comprehensively screened, thereby improving the comprehensiveness and accuracy of the screened target building information model. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0022] Figure 1 A flow chart of a shared resource management and control method based on a BIM system in one embodiment; Figure 2 A schematic diagram of a process of a shared resource management and control example based on a BIM system in one embodiment; Figure 3 It is a structural block diagram of a shared resource management and control device based on a BIM system in one embodiment; Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0023] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0024] The shared resource management and control method based on the BIM system provided in the embodiment of the present application can be applied to the application environment corresponding to the shared resource management platform of the BIM system. The method can be applied to a terminal, a server, or a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc. Among them, the terminal extracts the feature information of each model of the building information model to construct a model association map between each building information model, so that when the user retrieves the model, the user can be provided with each building information model required by the user and the building information model that the user may require, thereby improving the comprehensiveness of the building information model fed back to the user for retrieval. Then, this scheme extracts the model keywords of each building information model and the model introduction information, thereby dividing each building information model into multiple model groups. Compared with the traditional model grouping method, this scheme is not only limited to the model classification of each model category, but also classifies each model by combining the model keywords and model introduction information of each model (including the model source and the sub-introduction information corresponding to each model introduction type of the model category), thereby improving the accuracy of classification. Then, this solution extracts the user's demand text information and model demand information, as well as the current project information, to determine the user's actual demand content, avoiding the problem that the user's search semantics are ambiguous and cannot be directly searched, and improving the accuracy of identifying the user's actual demand content. Finally, through the actual demand content, model group, and model association map, the target building information model required by the user and the target building information model of potential demand are comprehensively screened, improving the comprehensiveness and accuracy of the screened target building information model.
[0025] In an exemplary embodiment, Figure 1 As shown, a shared resource management and control method based on a BIM system is provided, and the method is applied to a terminal as an example for explanation, including the following steps S102 to S103. Among them: Step S101, obtaining model introduction information of each building information model, model requirement information of the user, and current project information of the user, and extracting each model feature information of each building information model.
[0026] In this embodiment, the terminal collects the model introduction information of each building information model and the model data of each building information model in the shared resource platform of the BIM system. Then, the terminal responds to the model retrieval request of the user, obtains the model requirement information of the user, and obtains the user information of the user in the BIM system. Among them, the model introduction information is the introduction information of each model introduction type contained in the introduction page of the model, wherein the model introduction type includes the model creator type, the model company type, the model project type, the model use type, and the model scoring type. The terminal extracts the project-related information from the user information of the user and obtains the current project information, wherein the user information includes the user name, company name, department, position, current execution project name, current execution project number, current execution project category, and current project responsible content, wherein the project-related information includes the current execution project name, current execution project number, current execution project category, and current project responsible content. Among them, the model requirement information can be a search text, a search voice, a plurality of search words, and other search methods to input the search information of the terminal. Then, the terminal extracts each model feature information of each building information model, wherein the model feature information includes structural features corresponding to the structural model of the building information model, physical features corresponding to the physical information, and rule features corresponding to the rule information. The specific extraction process will be described in detail later.
[0027] Step S102, based on the model feature information of each building information model, a model association map between each building information model and a model keyword of each building information model are generated, and based on the model introduction information of each building information model and the model keyword of each building information model, each building information model is divided into model groups.
[0028] In this embodiment, the terminal generates a model association map between each building information model and a model keyword of each building information model based on the model feature information of each building information model, and divides each building information model into model groups based on the model introduction information of each building information model and the model keyword of each building information model. The model association map contains the association information between each building information model, and the association information includes highly associated information and ordinary associated information. The specific association information generation process will be described in detail later. The model keyword of each building information model is the keyword in the feature content corresponding to the model feature information of each building information model, for example, the physical content corresponding to the object feature in the physical information, and the rule content corresponding to the rule feature in the rule information. The specific identification process of each feature content will be described in detail later. The keyword is extracted by a keyword extraction algorithm, for example, by a keyword extraction algorithm in a trained supervised support vector machine (SVM) model. Each model group divided by the terminal based on model introduction information and model keywords can contain repeated building information models, that is, the same building information model can belong to multiple model groups, thereby improving the classification accuracy and comprehensiveness of the model.
[0029] Step S103, based on the model requirement information and the current project information, the actual requirement content of the user is generated, and based on the actual requirement content, the target building information model required by the user is screened through each model group and the model association map.
[0030] In this embodiment, the terminal generates the actual demand content of the user based on the model demand information and the current project information, and based on the actual demand content, screens the target building information model required by the user through each model group and the model association map. The specific generation process will be described in detail later. The target building information model includes a plurality of first building information models directly required by the user and second building information models that are highly associated with each first building information model. The specific screening process will be described in detail later.
[0031] Based on the above scheme, by extracting the feature information of each model of the building information model, a model association map between each building information model is constructed, so that when the user searches for a model, the user can be provided with each building information model that the user needs and the user may need, thereby improving the comprehensiveness of the building information model fed back to the user for retrieval. Then, this scheme extracts the keywords of each model of the building information model and the model introduction information, thereby dividing each building information model into multiple model groups. Compared with the traditional model grouping method, this scheme is not limited to the model classification of each model by the model category, but by combining the model keywords and model introduction information of each model (including the model source, the sub-introduction information corresponding to each model introduction type of the model category), so as to classify each model, thereby improving the accuracy of classification. Afterwards, this scheme extracts the user's demand text information and model demand information, as well as the current project information, thereby determining the user's actual demand content, avoiding the problem that the user's search semantics are ambiguous and cannot be directly retrieved, and improving the accuracy of identifying the user's actual demand content. Finally, through the actual demand content, model groups, and model association maps, the target building information models required by users and the target building information models of potential needs are comprehensively screened, thereby improving the comprehensiveness and accuracy of the screened target building information models.
[0032] Optionally, extracting each model feature information of each building information model, including: for each building information model, splitting the building information model into building structure information, model physical information, and model rule information; extracting structural features in the building structure information through a three-dimensional model extraction network, and converting the physical information into physical text information, and converting the model rule information into rule text information; extracting physical features in the physical text information and rule features in the rule text information through a text extraction network, and using the structural features, physical features, and rule features as each model feature information of the building information model.
[0033] In this embodiment, the terminal splits each building information model into building structure information, model physical information, and model rule information for each building information model. Each building information model includes geometric information, physical information, rule information of the building structure, and actual existing structural information after the building changes. The terminal uses the geometric information and structural information as building structure information, the physical information as model physical information, and the rule information as model rule information. The physical information is the physical properties of the building structure information, such as compressive properties, deformation properties, load-bearing properties and other physical properties. The geometric information includes the geometric shape of the building, and the rule information includes the rules and information of the building during the design, construction, and operation processes.
[0034] Then, the terminal extracts the structural features in the building structure information through the three-dimensional model extraction network, and converts the physical information into physical text information and the model rule information into rule text information. When the physical information and the rule information are text information, this step does not need to be performed; when the physical information and the rule information are not text information, the terminal first identifies the information mode corresponding to each information, such as the picture mode, the audio mode, and the video mode, and then the terminal converts the information of each mode into the text mode through the conversion network preset in the terminal to obtain the physical text information and the rule text information.
[0035] Then, the terminal extracts the physical features in the physical text information and the rule features in the rule text information through the text extraction network, and uses the structural features, physical features, and rule features as the model feature information of the building information model. The text extraction network is a neural network based on natural language processing technology (Neuro-Linguistic Programming, NLP).
[0036] Based on the above scheme, by extracting structural features, physical features, and rule features respectively, the model feature information of the building information model is obtained, thereby improving the accuracy of extracting the model feature information.
[0037] Optionally, based on the model feature information of each building information model, a model association map between each building information model and a model keyword of each building information model are generated, including: for every two building information models, using a similarity recognition algorithm, respectively calculating the similarity between the model feature information of the two building information models, and taking the model feature information corresponding to the similarity greater than the similarity threshold as the association information between the two building information models; based on the association information between the building information models, a model association map is constructed, and for each building information model, based on the model feature information of the building information model, the feature content corresponding to the model feature information of the building information model is identified; and using a keyword extraction algorithm, the keywords corresponding to each feature content are extracted to obtain the model keywords of the building information model.
[0038] In this embodiment, the terminal calculates the similarity between each model feature information of the two building information models through a similarity recognition algorithm for each two building information models. The similarity recognition algorithm is a cosine similarity algorithm, which calculates the similarity between the same model feature information of two building information models. For example, each model feature information of building information model A includes a structural feature, a physical feature, and a regular feature; each model feature information of building information model B includes b structural feature, b physical feature, and b regular feature; then the method of calculating the similarity between each model feature information of the two building information models is to calculate the similarity between a structural feature and b structural feature, the similarity between a physical feature and b physical feature, and the similarity between a regular feature and b regular feature of building information model A and building information model B, respectively.
[0039] Finally, the terminal uses the model feature information corresponding to the similarity greater than the similarity threshold preset in the terminal as the association information between the two building information models. The association information includes association information of each feature type, and the feature type includes a structural feature type (the type corresponds to a structural feature), a physical feature type (the type corresponds to a physical feature), and a rule feature type (the type corresponds to a rule feature). When the number of feature types included in the association information is greater than two, it indicates that the two building information are highly associated; when the number of feature types included in the association information is less than or equal to two, it indicates that the two building information are generally associated.
[0040] Finally, the terminal constructs a model association map based on the association information between the building information models, wherein each connection line in the model association map represents the association information between two building information models.
[0041] For each building information model, the terminal locates the text content corresponding to each model feature information in the text information corresponding to each model feature information based on each model feature information of the building information model, and uses the text content as the feature content corresponding to each model feature information of the building information model. The positioning method is to identify the text content corresponding to each model feature information, and search for the text content containing the text content in the text information corresponding to each model feature information to obtain the text content corresponding to each model feature information.
[0042] Finally, the terminal extracts the keywords corresponding to each feature content through a keyword extraction algorithm to obtain the model keywords of the building information model.
[0043] Based on the above scheme, a model association graph is constructed through feature similarity, and the keywords corresponding to each feature content are extracted through a keyword extraction algorithm to obtain the model keywords of the building information model, thereby improving the accuracy of the constructed model association graph and the extracted model keywords.
[0044] Optionally, based on the model introduction information of each building information model and the model keywords of each building information model, each building information model is divided into model groups, including: splitting each model introduction information into sub-introduction information of each model introduction type, and classifying each building information model into the same category based on each sub-introduction information of each model introduction type to obtain initial model groups corresponding to each model introduction type; for each initial model group, clustering each building information model based on the model keywords of each building information model in the initial model group to obtain a cluster center model in the initial model group, and screening a preset number of target cluster center models based on the cluster center models of each initial model group corresponding to each model introduction type; and clustering each building information model based on each target cluster center model to obtain model groups.
[0045] In this embodiment, the terminal divides each model introduction information into sub-introduction information of each model introduction type, and classifies each building information model into the same category based on each sub-introduction information of each model introduction type, and obtains each initial model group corresponding to each model introduction type. Among them, for each model introduction type, the terminal classifies the building information models with the same sub-introduction information into the same group based on each sub-introduction information of the model introduction type, and obtains each initial model group corresponding to each model introduction type.
[0046] For each initial model group, the terminal performs clustering processing on each building information model based on the model keywords of each building information model in the initial model group to obtain a cluster center model in the initial model group. Specifically, the terminal identifies the number of identical keywords in each building information model based on the model keywords of each building information model, and performs clustering processing on each building information model according to the number of identical keywords to obtain multiple initial cluster center models, wherein each initial cluster center model is a building information model having the highest average number of identical keywords with each building information model in the cluster set.
[0047] The terminal screens a preset number of target cluster center models based on the cluster center models of each initial model group corresponding to each model introduction type. Specifically, the screening method is that the terminal presets weight values for different model introduction types, and based on the weight values of each model introduction type, performs weighted processing on each target cluster center model of each model introduction type to obtain the cluster weight of each cluster center model. Then, the terminal sums up the cluster weights of the same cluster center model to obtain the target cluster weight of each cluster center model, and sorts the cluster center models in order from large to small according to the target cluster weight to obtain a model sequence. Finally, the terminal screens a preset number of cluster center models as the target cluster center model in the order of the model sequence from front to back.
[0048] The terminal performs model clustering processing on each building information model based on each target cluster center model to obtain each model group. The clustering method is to perform clustering processing based on the number of identical keywords between each building information model and each target cluster center model. When there is a building information model with the same number of identical keywords as multiple target cluster center models, the building information model is divided into different model groups.
[0049] Based on the above scheme, after clustering the models by each model introduction type, the target cluster center model is screened, and then each model group is obtained by re-clustering. In this way, when dividing each model group, the introduction type of each model and the similarity of keywords are comprehensively considered, thereby improving the accuracy of the divided model groups.
[0050] Optionally, based on the model requirement information and the current project information, the user's actual requirement content is generated, including: based on the current project information, identifying the user's project introduction information, and based on the project introduction information, identifying the first model keyword corresponding to the current project information; converting the model requirement information into requirement text information, and identifying the text semantic information of the requirement text information through a text recognition network; calculating the similarity between each model keyword and the text semantic information, and screening the model keywords corresponding to the similarity greater than the similarity threshold as the second model keywords; and using each first model keyword and each second model keyword as the user's actual requirement content.
[0051] In this embodiment, the terminal identifies the user's project introduction information based on the current project information, and identifies the first model keyword corresponding to the current project information based on the project introduction information. Specifically, the terminal extracts the keywords of each information from the information related to each project in the project introduction information through the above-mentioned keyword extraction algorithm, and then the terminal identifies the model keyword similar to the keyword of each information through the text classification network as the first model keyword corresponding to the project introduction information.
[0052] The terminal converts the model demand information into demand text information, and identifies the text semantic information of the demand text information through the text recognition network. The text recognition network is a large language model. Then, the terminal calculates the similarity between each model keyword and the text semantic information respectively. The similarity algorithm is the same as the keyword similarity algorithm described above, and no redundant description is given here. Then, the terminal selects the model keyword corresponding to the similarity greater than the similarity threshold as the second model keyword. Finally, the terminal uses each first model keyword and each second model keyword as the actual demand content of the user.
[0053] Based on the above solution, by respectively identifying the first model keywords corresponding to the project introduction information and the second model keywords corresponding to the demand text information, the accuracy and comprehensiveness of obtaining the user's actual demand content are improved.
[0054] Optionally, based on actual demand content, the target building information model of the user's demand is screened through each model group and the model association map, including: in each model group, a building information model that contains both the first model keywords and the second model keywords is screened as the first building information model; based on the model association map, a building information model that is highly associated with the first building information model is screened as the second building information model, and based on the association information between each first building information model and each second building information model, an association relationship between each first building information model and each second building information model is constructed; each first building information model, each second building information model, and each association relationship are used as the target building information model of the user's demand.
[0055] In this embodiment, the terminal selects a building information model that contains both the first model keywords and the second model keywords in each model group as the first building information model. Then, based on the model association map, the terminal selects a building information model that is highly associated with the first building information model as the second building information model, and constructs an association relationship between each first building information model and each second building information model based on the association information between each first building information model and each second building information model. The association relationship is the association introduction information corresponding to the association information between the second building information model and the first building information model. For example, if the association information between model A and model B is that both apply the c rule feature, then the association relationship is that model B is associated with model A at the c rule feature. If the model of the user's potential needs is more inclined to rule information, the user can filter out model B that is highly associated with the rule information of model A, so that the target building information model for identifying user needs is more comprehensive.
[0056] Finally, the terminal uses the first building information models, the second building information models, and the association relationships as target building information models required by the user.
[0057] Based on the above solution, through keyword query and model association graph screening, the building information model required by the user is accurately obtained, and the building information model that the user may require is provided, which improves the comprehensiveness and accuracy of the building information model fed back to the user.
[0058] This application also provides an example of shared resource management and control based on the BIM system, such as Figure 2 As shown, the specific processing process includes the following steps: Step S201, obtaining model introduction information of each building information model, model requirement information of the user, and current project information of the user.
[0059] Step S202: for each building information model, split the building information model into building structure information, model physical information, and model rule information.
[0060] Step S203, extracting the structural features in the building structure information through the three-dimensional model extraction network, and converting the physical information into physical text information, and converting the model rule information into rule text information.
[0061] Step S204, extracting physical features from the physical text information and rule features from the rule text information respectively through a text extraction network, and using the structural features, physical features, and rule features as each model feature information of the building information model.
[0062] Step S205: for every two building information models, the similarity between each model feature information of the two building information models is calculated by a similarity recognition algorithm, and each model feature information corresponding to a similarity greater than a similarity threshold is used as association information between the two building information models.
[0063] Step S206: construct a model association map based on the association information between the building information models, and for each building information model, identify the feature content corresponding to each model feature information of the building information model based on the model feature information of the building information model.
[0064] Step S207: extract keywords corresponding to each feature content through a keyword extraction algorithm to obtain model keywords of the building information model.
[0065] Step S208, split each model introduction information into sub-introduction information of each model introduction type, and classify each building information model into the same category based on each sub-introduction information of each model introduction type to obtain each initial model group corresponding to each model introduction type.
[0066] Step S209: for each initial model group, clustering processing is performed on each building information model based on the model keywords of each building information model in the initial model group to obtain the cluster center model in the initial model group, and based on the cluster center model of each initial model group corresponding to each model introduction type, a preset number of target cluster center models are screened.
[0067] Step S210: Based on each target cluster center model, model clustering processing is performed on each building information model to obtain each model group.
[0068] Step S211, based on the current project information, identifying the user's project introduction information, and based on the project introduction information, identifying the first model keyword corresponding to the current project information.
[0069] Step S212, converting the model requirement information into requirement text information, and identifying the text semantic information of the requirement text information through a text recognition network.
[0070] Step S213, respectively calculating the similarity between each model keyword and the text semantic information, and selecting the model keywords corresponding to the similarity greater than the similarity threshold as the second model keywords.
[0071] Step S214: taking each first model keyword and each second model keyword as the actual demand content of the user.
[0072] Step S215: In each model group, a building information model that contains both the first model keywords and the second model keywords is selected as the first building information model.
[0073] Step S216: Based on the model association graph, a building information model that is highly associated with the first building information model is screened as the second building information model, and based on the association information between each first building information model and each second building information model, an association relationship between each first building information model and each second building information model is constructed.
[0074] Step S217: taking each first building information model, each second building information model, and each association relationship as a target building information model required by the user.
[0075] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0076] Based on the same inventive concept, the embodiment of the present application also provides a BIM system-based shared resource control device for implementing the BIM system-based shared resource control method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more BIM system-based shared resource control device embodiments provided below can refer to the above limitations on the BIM system-based shared resource control method, which will not be repeated here.
[0077] In an exemplary embodiment, Figure 3 As shown, a shared resource management and control device based on a BIM system is provided, including: an acquisition module 310, a division module 320 and a screening module 330, wherein: The acquisition module 310 is used to acquire model introduction information of each building information model, model requirement information of the user, and current project information of the user, and extract each model feature information of each building information model; A division module 320 is used to generate a model association map between the building information models and a model keyword of each building information model based on the model feature information of each building information model, and divide the building information models into model groups based on the model introduction information of each building information model and the model keyword of each building information model; The screening module 330 is used to generate the actual demand content of the user based on the model demand information and the current project information, and based on the actual demand content, screen the target building information model required by the user through each of the model groups and the model association map.
[0078] Optionally, the acquisition module 310 is specifically configured to: For each building information model, split the building information model into building structure information, model physical information, and model rule information; Extracting structural features from the building structure information through a three-dimensional model extraction network, and converting the physical information into physical text information, and converting the model rule information into rule text information; The physical features in the physical text information and the rule features in the rule text information are extracted respectively through a text extraction network, and the structural features, the physical features and the rule features are used as each model feature information of the building information model.
[0079] Optionally, the division module 320 is specifically configured to: For each two building information models, the similarity between each model feature information of the two building information models is calculated by a similarity recognition algorithm, and each model feature information corresponding to a similarity greater than a similarity threshold is used as association information between the two building information models; Based on the association information between the building information models, a model association map is constructed, and for each building information model, based on the model feature information of each building information model, feature content corresponding to each model feature information of the building information model is identified; The keywords corresponding to each characteristic content are extracted by a keyword extraction algorithm to obtain model keywords of the building information model.
[0080] Optionally, the division module 320 is specifically configured to: Each model introduction information is split into sub-introduction information of each model introduction type, and each building information model is classified into the same category based on each sub-introduction information of each model introduction type to obtain each initial model group corresponding to each model introduction type; For each initial model group, clustering is performed on each building information model in the initial model group based on model keywords of each building information model in the initial model group to obtain a cluster center model in the initial model group, and a preset number of target cluster center models are screened based on the cluster center models of each initial model group corresponding to each model introduction type; Based on each target cluster center model, model clustering processing is performed on each of the building information models to obtain each model group.
[0081] Optionally, the screening module 330 is specifically used to: Based on the current project information, identifying the project introduction information of the user, and based on the project introduction information, identifying a first model keyword corresponding to the current project information; Converting the model requirement information into requirement text information, and identifying text semantic information of the requirement text information through a text recognition network; Calculating the similarity between each model keyword and the text semantic information respectively, and selecting the model keyword corresponding to the similarity greater than the similarity threshold as the second model keyword; Each of the first model keywords and each of the second model keywords are used as the actual demand content of the user.
[0082] Optionally, the screening module 330 is specifically used to: In each of the model groups, a building information model including both the first model keywords and the second model keywords is selected as a first building information model; Based on the model association map, a building information model highly associated with the first building information model is selected as a second building information model, and based on the association information between each first building information model and each second building information model, an association relationship between each first building information model and each second building information model is constructed; The first building information models, the second building information models, and the association relationships are used as target building information models required by the user.
[0083] Each module in the shared resource control device based on the BIM system can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.
[0084] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store XX data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a shared resource management and control method based on a BIM system is implemented.
[0085] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0086] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.
[0087] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.
[0088] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.
[0089] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0090] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0091] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0092] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A shared resource management and control method based on BIM system, characterized in that: The method comprises: Obtaining model introduction information of each building information model, model requirement information of the user, and current project information of the user, and extracting each model feature information of each building information model; Based on the model feature information of each building information model, a model association map between each building information model and a model keyword of each building information model are generated, and based on the model introduction information of each building information model and the model keyword of each building information model, each building information model is divided into model groups; Based on the model requirement information and the current project information, the actual requirement content of the user is generated, and based on the actual requirement content, the target building information model required by the user is screened through each of the model groups and the model association map.
2. The method according to claim 1, characterized in that The step of extracting the model feature information of each building information model comprises: For each building information model, split the building information model into building structure information, model physical information, and model rule information; Extracting structural features from the building structure information through a three-dimensional model extraction network, and converting the physical information into physical text information, and converting the model rule information into rule text information; The physical features in the physical text information and the rule features in the rule text information are extracted respectively through a text extraction network, and the structural features, the physical features and the rule features are used as each model feature information of the building information model.
3. The method according to claim 1, characterized in that The generating of a model association graph between the building information models and a model keyword of each building information model based on the model feature information of each building information model comprises: For each two building information models, the similarity between each model feature information of the two building information models is calculated by a similarity recognition algorithm, and each model feature information corresponding to a similarity greater than a similarity threshold is used as association information between the two building information models; Based on the association information between the building information models, a model association map is constructed, and for each building information model, based on the model feature information of each building information model, feature content corresponding to each model feature information of the building information model is identified; The keywords corresponding to each characteristic content are extracted by a keyword extraction algorithm to obtain model keywords of the building information model.
4. The method according to claim 1, characterized in that Based on the model introduction information of each building information model and the model keywords of each building information model, each building information model is divided into model groups, including: Each model introduction information is split into sub-introduction information of each model introduction type, and each building information model is classified into the same category based on each sub-introduction information of each model introduction type to obtain each initial model group corresponding to each model introduction type; For each initial model group, clustering is performed on each building information model in the initial model group based on model keywords of each building information model in the initial model group to obtain a cluster center model in the initial model group, and a preset number of target cluster center models are screened based on the cluster center models of each initial model group corresponding to each model introduction type; Based on each target cluster center model, model clustering processing is performed on each of the building information models to obtain each model group.
5. The method according to claim 1, characterized in that The generating the actual demand content of the user based on the model demand information and the current project information includes: Based on the current project information, identifying the project introduction information of the user, and based on the project introduction information, identifying a first model keyword corresponding to the current project information; Converting the model requirement information into requirement text information, and identifying text semantic information of the requirement text information through a text recognition network; Calculating the similarity between each model keyword and the text semantic information respectively, and selecting the model keyword corresponding to the similarity greater than the similarity threshold as the second model keyword; Each of the first model keywords and each of the second model keywords are used as the actual demand content of the user.
6. The method according to claim 5, characterized in that The method of screening the target building information model required by the user based on the actual demand content through each of the model groups and the model association map includes: In each of the model groups, a building information model including both the first model keywords and the second model keywords is selected as a first building information model; Based on the model association map, a building information model highly associated with the first building information model is selected as a second building information model, and based on the association information between each first building information model and each second building information model, an association relationship between each first building information model and each second building information model is constructed; The first building information models, the second building information models, and the association relationships are used as target building information models required by the user.
7. A shared resource management and control device based on a BIM system, characterized in that: The device comprises: An acquisition module, used to acquire model introduction information of each building information model, model requirement information of a user, and current project information of the user, and extract each model feature information of each building information model; A division module, for generating a model association map between the building information models and a model keyword of each building information model based on the model feature information of each building information model, and dividing the building information models into model groups based on the model introduction information of each building information model and the model keyword of each building information model; The screening module is used to generate the actual demand content of the user based on the model demand information and the current project information, and based on the actual demand content, screen the target building information model required by the user through each of the model groups and the model association map.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
