CN116186831A - Semantic structured description and compliance inspection method and system for building engineering design - Google Patents
Semantic structured description and compliance inspection method and system for building engineering design Download PDFInfo
- Publication number
- CN116186831A CN116186831A CN202211569172.1A CN202211569172A CN116186831A CN 116186831 A CN116186831 A CN 116186831A CN 202211569172 A CN202211569172 A CN 202211569172A CN 116186831 A CN116186831 A CN 116186831A
- Authority
- CN
- China
- Prior art keywords
- building
- knowledge
- description
- data
- function
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- Architecture (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Databases & Information Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of building modeling, and relates to a method and a system for semantic structural description and compliance examination of building engineering design, wherein the method comprises the following steps: formulating a unified data format, storing various building design objects and attribute fields thereof in the data format completely, and integrating model information of various types layer by layer to form an information model; knowledge extraction is carried out on Chinese natural language texts in the digitalized strips, knowledge sets which are uniformly described in multiple dimensions are combined, and the knowledge sets are stored in a database in a structured mode to form a knowledge base; adopting a knowledge base to carry out data encapsulation on the building design objects and attribute fields thereof stored in a data format, providing a description structure of building engineering design compliance semantics, formulating a descriptive rule language taking an object-oriented as a core, and carrying out compliance examination of the building engineering design; the problems of repeated redundancy, difficult maintenance and upgrading, invisible logic and the like caused by using a hard coding mode in the prior art are solved.
Description
Technical Field
The invention belongs to the technical field of building modeling, and particularly relates to a semantic structural description and compliance inspection method and system for building engineering design.
Background
The existing building engineering design mode is generally carried out based on two-dimensional drawings, and in the engineering construction approval and supervision process, drawings and other technical files are inspected by mainly relying on professional technicians, so that the professional technical requirements of the inspectors are high, the dependence on the personnel is high, the manual inspection time is long, the efficiency is low, and the accuracy of inspection results is difficult to be effectively ensured. Under the time-limited requirement, the auditing is often performed in an spot check mode, so that the auditing is incomplete. The final auditing result is easily influenced by the professional knowledge comprehensiveness and experience enrichment condition of the approver.
With development and wide application of Building Information Model (BIM) technology, the BIM technology brings strong technical support for building project refinement and informatization management, and promotes deep fusion of building design and information technology. Fully utilizing data in the BIM model, and combining with examination requirements, realizing intelligent examination, such as whether related indexes meet planning requirements, including volume rate, parking space statistics and the like; and whether the BIM design meets the specification requirements of the building design or not, including strong strip inspection of the building design fireproof specification and the like. The auditing efficiency and the auditing comprehensiveness can be greatly improved through an intelligent auditing mode.
However, for implementation of compliance intelligent examination, existing enterprises basically adopt a manner of hard-coding specification treaty and index content, and form computer executable logic codes according to a certain rule. The benefit of this hard coding is that the logic of the coding is strong and the efficiency of the execution is high, but the way of hard coding also has the following disadvantages: (1) The method needs to encode different specification texts and index contents one by one, and a plurality of repeated and redundant calculation items are often generated in the process. (2) After hard coding is finished, the maintenance and updating work has the problems of more labor investment, high time cost, poor flexibility, insufficient maintainability, high modification cost and the like. (3) Because the hard-coded logic calculation and logic judgment modes are invisible to the user, the user cannot judge whether the calculation process and the calculation formula meet the requirements of the related specification standard.
The existing structured natural language definition and description has very limited examination rule depth, a certain technical barrier exists in interdisciplinary research, and the problems of difficult combination, difficult compound judgment, difficult multiple calculation, difficult accurate translation and the like exist for rules with complex semantics and more limiting conditions.
Therefore, the rule based on BIM technology in building engineering design compliance semantic structuring description is formulated, and the technology for realizing intelligent examination has very important significance for improving traditional graph examination efficiency and BIM management accuracy.
Disclosure of Invention
In order to solve the defects existing in the prior art, the invention aims to provide a semantic structural description and compliance inspection method and system for building engineering design, which are used for constructing unified description and structural storage of a multi-source heterogeneous building BIM model, constructing a descriptive rule language structure with nested inside and outside, male-female inclusion and multiplexing, carrying out visual configuration on the rule language and solving the problems of repeated redundancy, poor flexibility, difficult maintenance and upgrading, invisible logic and the like caused by using a hard-coded implementation mode in the intelligent inspection process based on BIM technology.
The method is realized by the following technical scheme: the method for semantic structural description and compliance inspection of the building engineering design comprises the following steps:
adopting a building design specification expression mode based on an object-oriented thought to formulate a unified data format, integrally storing various building design objects and attribute fields thereof in the data format, and integrating model information of various types layer by layer to form an information model;
removing the digitalized treaty content in the constructional engineering design specification strip, extracting knowledge from the Chinese natural language text in the digitalized strip, combining the knowledge sets into a multi-dimensional unified description knowledge set, and storing the knowledge set in a database in a structured form to form a knowledge base;
and adopting the formed knowledge base to carry out data encapsulation on the building design objects and attribute fields thereof stored in the data format, providing a description structure of building engineering design compliance semantics, formulating a descriptive rule language taking the object as a core, and carrying out compliance examination of the building engineering design.
In a preferred embodiment, the data format is a data format adopted when data is exchanged between different information systems, and the data format not only contains geometric form information of the model itself, but also stores interrelation information of the model and data information required by quality inspection.
Further, the data format covers the definition of non-geometric information of a specific building design object and service data required by application at each stage of building engineering; various building design objects stored in the data format comprise walls, columns, doors and windows, floors, stairs, elevators and various functional rooms.
In a preferred embodiment, knowledge extraction is carried out on the Chinese natural language text in the digitalized strip, and the knowledge extraction is decomposed into Chinese segmentation words, chinese part-of-speech labels, chinese named entity recognition and named entity relations; and then combining the four dimensions of the building components/building space, the component attribute/space attribute, the comparison word and the target value into a unified description knowledge set.
In a preferred embodiment, the main content of the descriptive rule language is a descriptive function and attribute; wherein the attribute is a common data type including character type, integer type, decimal type and Boolean type; the description functions are logical functions for achieving purposes, functions or effects, and are composed of any legal identifier and marked with 'prefix to' prefix, each description function is provided with parameters, and each description function has a return value.
In a preferred embodiment, compliance review of a building engineering design includes a work sheet review, which is performed in logical order of:
executing a description function for acquiring elements by combining a data format to obtain an element group of entity data;
defining an element group as a first parameter, a parameter name as a second parameter, a comparator as a third parameter and a target value as a fourth parameter in a description function for judging whether the parameters of all elements in the element group meet the numerical requirement; the obtained element group of the entity data is used as a first parameter to be transmitted into a description function for judging whether the parameters of all elements in the element group meet the numerical requirement or not, and definition of the first parameter is completed; according to the description of the knowledge set, the second parameter is the specification of the digitalized treaty content, the third parameter is a comparer "=", the fourth parameter is a target value "yes", and a rule language formed by nesting the description function inside and outside is formulated;
and configuring the knowledge set into a multiple composite form of the description function according to the condition to be satisfied simultaneously to obtain the final inside-outside nested multiple composite descriptive rule language.
The system of the invention is realized by the following technical scheme: the semantic structural description and compliance inspection system for the building engineering design comprises the following modules:
the data format formulating module adopts a building design specification expression mode based on an object-oriented idea to formulate a unified data format, and stores various building design objects and attribute fields thereof in the data format completely, integrates model information of various types layer by layer to form an information model;
the knowledge base forming module is used for dismantling the digitalized text content in the building engineering design specification strip, extracting knowledge from the Chinese natural language text in the digitalized strip, combining the knowledge sets into a multi-dimensional unified description knowledge set, and storing the knowledge set in a structured form in a database to form a knowledge base;
the rule language formulation module adopts the formed knowledge base to carry out data encapsulation on the building design objects and attribute fields thereof stored in the data format, provides a description structure of building engineering design compliance semantics, and formulates a descriptive rule language taking an object-oriented core to carry out compliance examination of the building engineering design;
the data format is used for realizing data bidirectional exchange between different information systems, not only comprises geometric form information of a model, but also stores interrelated information of the model and data information required by quality inspection, and covers non-geometric information definition of a specific building design object and service data required by application of each stage of building engineering;
the knowledge base forming module extracts knowledge of the Chinese natural language text in the digitalized strip, and then decomposes the knowledge into Chinese word segmentation, chinese part-of-speech labeling, chinese named entity recognition and named entity relation; then combining the four dimensions of the building components/building space, the component attribute/space attribute, the comparison word and the target value into a knowledge set which is uniformly described according to the four dimensions;
the main content of the descriptive rule language is a description function and attribute; wherein the attribute is a common data type including character type, integer type, decimal type and Boolean type; the description functions are logical functions for achieving purposes, functions or effects, and are composed of any legal identifier and marked with 'prefix to' prefix, each description function is provided with parameters, and each description function has a return value.
Compared with the prior art, the invention has the following advantages:
1. the method comprises the steps of constructing unified description and structured storage of a multi-source heterogeneous building BIM model, solving the problems of nonstandard, incomplete and nonstandard data and the like, laying a data foundation for quality inspection in the field of building engineering design, and realizing intelligent inspection of rules, accurate calculation of application indexes and the like.
2. The method has the advantages that the method constructs a descriptive rule language structure with complex semantics and more limiting conditions, including inner and outer nesting, father and son inclusion and multiplexing, can solve the problems of lack of expandability, difficult logic deep combination and insufficient nesting depth of the conventional rule description, is convenient for users to freely combine according to various logic requirements by using a custom rule language, and realizes various application requirements, including intelligent examination, index calculation, integrity detection, pattern consistency detection and the like.
3. The rule language is subjected to visual configuration, rule logic is presented in detail, soft coding and low code operation are realized, a user can see the logic configuration, the calculation process and the calculation formula at a glance, the problem can be quickly found and quick correction is supported, and the problems of repeated redundancy, poor flexibility, difficult maintenance and upgrading, invisible logic (namely a logic black box) and the like of the conventional hard coding are solved; and the post maintenance and update workload is less, the time cost is less, the modification work is highly flexible, the maintainability of the rule base is high, and the modification cost is low.
Drawings
FIG. 1 is a flow chart of a structural description of architectural engineering design semantics and compliance review method in an embodiment of the present invention;
FIG. 2 is a schematic diagram of a configuration and execution flow of a descriptive rule language in an embodiment of the present invention.
Detailed Description
The present invention will be further described with reference to the drawings and examples, but the embodiments of the present invention are not limited thereto.
Example 1
The embodiment provides a semantic structural description and compliance inspection method for building engineering design, which can provide technical support for application scenes such as building planning BIM report construction, construction drawing BIM inspection and the like, and specifically comprises the following steps as shown in fig. 1:
s1, adopting a building design specification expression mode based on an object-oriented idea to formulate a unified BIM structured data format agm, integrally storing various building design objects and attribute fields thereof in the data format agm, and integrating model information of various types layer by layer to form an information model.
The data format agm is a data format adopted by the embodiment for realizing bidirectional data exchange between different BIM information systems, is a light-weight storage form compatible with conventional three-dimensional model data, and can be used for data conversion and sharing between different BIM information systems.
The data format agm not only contains geometric form information of the model, but also stores interrelated information of the model and data information required by quality inspection; therefore, the model information can be uniformly called and reused without secondary modeling and normalization, and rule examination is realized.
In this embodiment, the data format agm expresses complete architectural engineering design information and also covers non-geometric information definition of specific architectural design objects such as projects, floors, components, spaces and the like, and service data required by application at each stage of architectural engineering.
The data format agm of the step adopts a building standard expression mode based on an object-oriented idea, various building design objects (such as walls, columns, doors and windows, floors, stairs, elevators and various functional rooms) and attribute fields thereof are completely stored, model information of various types is integrated layer by layer to form an information model, the information model becomes a BIM data structured storage standard, and a data foundation is laid for quality inspection, intelligent examination and the like.
S2, removing the digitalized treaty content in the constructional engineering design specification treaty, extracting knowledge from the Chinese natural language text in the digitalized treaty, combining the knowledge sets into a multi-dimensional unified description knowledge set, and storing the knowledge set in a structured form in a database to form a knowledge base.
The building engineering design specification mainly includes digitalized and non-digitalized texts, which can be translated into computer identification and execution languages to establish corresponding knowledge sets.
The method comprises the steps of dismantling digitalized strip text content in building design standard strips covered by a project, extracting knowledge from Chinese natural language text contained in the digitalized strip text, and decomposing the knowledge into Chinese segmentation words, chinese part-of-speech labels, chinese named entity identification, named entity relation and the like, wherein knowledge extraction modes comprise identification, understanding, screening and the like; and then combining the knowledge sets into a knowledge set which is uniformly described according to four dimensions of building components/building space, component attributes/space attributes, comparison words and target values, and storing the knowledge set in a database in a structured form to form a knowledge base. For example, the digitalisable treaty "concrete retaining wall crown width is not preferably less than 200mm", can be structured to describe a knowledge set: "building element: concrete retaining wall "," building element properties: wall top width "," comparator: less than "," target value: 200 mm).
S3, adopting the knowledge base formed in the step S2 to package data materials (namely building design objects and attribute fields thereof) stored in the BIM structured data format agm, providing a description structure of building engineering design compliance semantics based on BIM technology, formulating a descriptive rule language taking an object as a core, and carrying out compliance examination of the building engineering design, as shown in figure 2.
The main content of the descriptive rule language is mainly descriptive functions and attributes; wherein the attribute is a common data type, including character type, integer type, decimal type, boolean type, etc.; the description functions are logical functions for realizing a specific purpose, function or effect, and are composed of any legal identifier and marked with 'to' prefixes, each description function is provided with parameters, and each description function has a return value.
In this embodiment, some commonly used function modules are written into description functions, which are used to package the acquired building element data, building element data attributes and other data, and put them in a function library for public selection. The description function can be called for a plurality of times at will, so that the function utilization rate is improved, and the workload of repeatedly writing the program segments is reduced. The sub-functions are generally called by the main function, and the sub-functions can also be called by each other.
The descriptive rule language structure is characterized in that the descriptive rule language structure is formed by inner and outer nesting and multiple compounding of descriptive functions, an execution result of a child function is used as an input parameter of a parent function, the execution and calculation of the parent function are supported, and the execution result of the parent function can be collected upwards as the input parameter of the parent function, so that the descriptive rule language structure with the functions of father-son inclusion, inner and outer nesting and multiple compounding is formed.
The logic sequence of execution is from inside to outside, that is, the sub-functions at the innermost layer are sequentially executed outwards, the parameters are continuously transferred to the outer layer, the function execution result is continuously used as the parameter entering parameter of the function at the upper level, the logic flow is continuously recursion, and finally the calculation result of the whole description function is obtained. Of particular note is that the attribute may also be invoked as a function, returning the attribute value itself.
In this step, according to the knowledge base formed in step S2, the corresponding description function and attribute are selected, and the BIM structured data format agm stored with various architectural design objects and attribute fields thereof in step S1 is further packaged. The description function is further data encapsulation after pretreatment such as query, screening, calculation and the like on BIM structured data agm. For example, section 7.3.8 of the building design fire Specification GB 50016-2014 (2018 edition) specifies: "1 should be able to dock at each level; the loading capacity of the 2 elevators should not be less than 800kg ", the knowledge set is" building element: fire elevator "," building element properties: each layer of dock "," comparator: equal to "," target value: is "and" building element: fire elevator "," building element properties: load weight "," comparator: greater than or equal to "," target value: 800 kg). In order to obtain the correct inspection result of the construction diagram corresponding to the regulation, the description function can select 'GetElementsByName' (meaning of the description function: acquiring elements) 'Chec kParamall' (meaning of the description function: judging whether parameters of all elements in the element group meet a certain numerical requirement).
In this embodiment, the description functions include a description function "GetElementsByName" for obtaining an element, a description function "CheckParamAll" for determining whether parameters of all elements in an element group meet numerical requirements, a description function "Count" for calculating a total number of element sets, a description function "superramvalus" for accumulating values of a certain parameter in an element set, and the like.
In this embodiment, the execution logic sequence of the construction drawing inspection is specifically:
s31, combining with the BIM structured data format agm, executing a description function (GetElementsBy Name ('fire elevator') for acquiring the elements to obtain an element group of the entity data of the fire elevator.
S32, 4 parameters are defined in total by a description function 'checkParamall' for judging whether the parameters of all elements in the element group meet the numerical requirement, wherein the parameters are respectively an element group, a parameter name, a comparator and a target value, and the return value is of a Boolean type. The element group of the entity data about the fire elevator obtained in the step S31 is used as a first parameter to be transmitted into a description function 'CheckParamall', so that the definition of the description function 'CheckParamall' on the first parameter is completed; the second parameter is a prescribed "stop per layer" of the digitized textual content, based on the description of the knowledge set; the third parameter is a comparator "= ="; the fourth parameter is the target value "yes"; thus, formulating a rule language formed by nesting inside and outside descriptive functions can be expressed as: "-CheckPa ramAll (-GetElementsByName ('firefighting elevator')", "per floor parking '," =', 'is') "".
S33, since the knowledge set needs to meet the conditions that the elevator should stop at each floor and the carrying capacity of the elevator should not be less than 800kg, the knowledge set needs to be configured into a form of multiple complex of the description functions of 'A & B', and the complete rule language can be expressed as follows: "a descriptive rule language of nested and multiple-composite inside and outside" (-CheckParamAll (-GetElementsByName ('firefighting elevator') "," each floor stop ', = =', 'is') + (-CheckParamAll (-GetElementsByName ('firefighting elevator') "," carrying capacity ', > =', '800')) ").
After the computer automatically runs the descriptive rule language, an execution result is obtained, and the data type of the execution result is Boolean; if the execution result is true, representing that all firefighting elevators in BIM structural data agm can stop at each layer and the carrying capacity is not less than 800kg; if the execution result is false, at least one firefighting elevator in BIM structured data agm can not stop at each floor or has a load capacity of less than 800kg.
In addition to construction map review, descriptive functions based on BIM technique semantic structuring can also be used to check the integrity of BIM data and to perform index calculations.
For example, to perform an engineering calculation, such as calculating the number of BIM data with respect to the structural columns, a description function of "Count" (description function meaning: calculating element set total number) and a description function of "GetElementsByName" (description function meaning: obtaining element) may be used. The complete descriptive rule language is "Count (GetElementsByName ('constructional column'))", and the total number of constructional columns can be obtained after the computer runs the execution logic of the above description function.
For example, to calculate the building area of the BIM, a description function of "about suramvalues" (meaning of description function: value of a certain parameter of cumulative element set) and a description function of "about GetElementsByName" (meaning of description function: acquiring element) may be used, and the complete descriptive rule language is "about suramvalues" (about GetElementsByName (' floor '), (building area ')) ", and after the computer runs the execution logic of the description function, the value about the building area may be obtained.
According to the embodiment, corresponding rule languages are visually configured according to each rule or each application requirement, so that building engineering design compliance semantic structural description based on BIM technology, automatic operation and intelligent examination are completed. Particularly, if the examination result does not accord with the standard value, the intelligent examination can be executed again after the delivery standard is reached by re-ordering the BIM model; or adjusting the rule language, finishing the modification of the corresponding rule through a configuration interface of the visual language, and then running the latest rule language by the computer to finish the corresponding quality inspection and intelligent examination. The method for building engineering design compliance semantic structural description and intelligent examination based on BIM technology finally achieves the effects of rule language visualization, modifiable operation logic, flexible rule configuration, credible calculation result and greatly improved graph examination efficiency.
Example 2
Based on the same inventive concept as embodiment 1, this embodiment provides a semantic structural description and compliance review system for architectural engineering design, including the following modules:
the data format formulating module adopts a building design specification expression mode based on an object-oriented idea to formulate a unified data format, and stores various building design objects and attribute fields thereof in the data format completely, integrates model information of various types layer by layer to form an information model;
the knowledge base forming module is used for dismantling the digitalized text content in the building engineering design specification strip, extracting knowledge from the Chinese natural language text in the digitalized strip, combining the knowledge sets into a multi-dimensional unified description knowledge set, and storing the knowledge set in a structured form in a database to form a knowledge base;
and the rule language making module adopts the formed knowledge base to carry out data encapsulation on the building design objects and attribute fields thereof stored in the data format, provides a description structure of building engineering design compliance semantics, makes a descriptive rule language with an object oriented core, and carries out compliance examination of the building engineering design.
The data format is used for realizing data bidirectional exchange between different information systems, not only comprises geometric form information of the model, but also stores interrelated information of the model and data information required by quality inspection, and covers non-geometric information definition of specific building design objects and service data required by application of each stage of building engineering.
The knowledge base forming module extracts knowledge of the Chinese natural language text in the digitalized strip, and then decomposes the knowledge into Chinese word segmentation, chinese part-of-speech labeling, chinese named entity recognition and named entity relation; and then combining the four dimensions of the building components/building space, the component attribute/space attribute, the comparison word and the target value into a unified description knowledge set.
The main content of the descriptive rule language is a description function and attribute; wherein the attribute is a common data type including character type, integer type, decimal type and Boolean type; the description functions are logical functions for achieving purposes, functions or effects, and are composed of any legal identifier and marked with 'prefix to' prefix, each description function is provided with parameters, and each description function has a return value.
The above modules in this embodiment are used to execute the steps in embodiment 1, and the detailed execution process thereof is referred to embodiment 1 and is not repeated herein.
The foregoing is only illustrative of the preferred embodiments of the present invention, but the scope of the invention is not limited thereto, and any other changes, modifications, substitutions, combinations, and simplifications that do not depart from the spirit and principles of the present invention should be made therein and are intended to be equivalent substitutes.
Claims (10)
1. The method for semantic structural description and compliance inspection of the building engineering design is characterized by comprising the following steps of:
adopting a building design specification expression mode based on an object-oriented thought to formulate a unified data format, integrally storing various building design objects and attribute fields thereof in the data format, and integrating model information of various types layer by layer to form an information model;
removing the digitalized treaty content in the constructional engineering design specification strip, extracting knowledge from the Chinese natural language text in the digitalized strip, combining the knowledge sets into a multi-dimensional unified description knowledge set, and storing the knowledge set in a database in a structured form to form a knowledge base;
and adopting the formed knowledge base to carry out data encapsulation on the building design objects and attribute fields thereof stored in the data format, providing a description structure of building engineering design compliance semantics, formulating a descriptive rule language taking the object as a core, and carrying out compliance examination of the building engineering design.
2. The method according to claim 1, wherein the data format used for bidirectional data exchange between different information systems includes not only geometric information of the model itself, but also interrelated information of the model and data information required for quality inspection.
3. The method of claim 1, wherein the data format covers non-geometric information definitions of specific architectural design objects, and business data required for various phases of application of the architectural engineering; various building design objects stored in the data format comprise walls, columns, doors and windows, floors, stairs, elevators and various functional rooms.
4. The method of claim 1, wherein knowledge extraction is performed on the chinese natural language text in the digitized strips, and the knowledge extraction is decomposed into chinese segmentation, chinese part-of-speech tagging, chinese named entity recognition, and named entity relationships; and then combining the four dimensions of the building components/building space, the component attribute/space attribute, the comparison word and the target value into a unified description knowledge set.
5. The method of claim 1, wherein the subject content of the descriptive rule language is descriptive functions and attributes; wherein the attribute is a common data type including character type, integer type, decimal type and Boolean type; the description functions are logical functions for achieving purposes, functions or effects, and are composed of any legal identifier and marked with 'prefix to' prefix, each description function is provided with parameters, and each description function has a return value.
6. The method according to claim 5, wherein the internal and external nesting and multiple compounding of functions are described, the execution result of the child function is used as the parameter entering parameter of the parent function, the execution and calculation of the parent function are supported, the execution result of the parent function is further gathered up to the parameter entering parameter of the parent function, and the descriptive rule language structure of the parent-child inclusion, the internal and external nesting and multiple compounding is formed;
when the formed knowledge base is adopted to carry out data encapsulation on the architectural design objects and attribute fields thereof stored in the data format, corresponding description functions and attributes are selected according to the formed knowledge base, and the data formats stored with various architectural design objects and attribute fields thereof are further encapsulated.
7. The method of claim 5, wherein compliance review of a building engineering design includes a work sheet review, the work sheet review being performed in logical order of:
executing a description function for acquiring elements by combining a data format to obtain an element group of entity data;
defining an element group as a first parameter, a parameter name as a second parameter, a comparator as a third parameter and a target value as a fourth parameter in a description function for judging whether the parameters of all elements in the element group meet the numerical requirement; the obtained element group of the entity data is used as a first parameter to be transmitted into a description function for judging whether the parameters of all elements in the element group meet the numerical requirement or not, and definition of the first parameter is completed; according to the description of the knowledge set, the second parameter is the specification of the digitalized treaty content, the third parameter is a comparer "=", the fourth parameter is a target value "yes", and a rule language formed by nesting the description function inside and outside is formulated;
and configuring the knowledge set into a multiple composite form of the description function according to the condition to be satisfied simultaneously to obtain the final inside-outside nested multiple composite descriptive rule language.
8. The method of claim 5, wherein the compliance review of the architectural engineering design includes a review of the engineering volume, and wherein the complete descriptive rule language is formulated using the descriptive function for counting the total number of sets of elements and the descriptive function for obtaining the elements when the review of the engineering volume is performed.
9. The method of claim 5, wherein compliance review of the architectural design includes review of the calculated architectural area, and wherein the complete descriptive rule language is formulated using the descriptive function for accumulating values of a parameter of the set of elements and the descriptive function for obtaining the elements when the review of the calculated architectural area is performed.
10. The semantic structural description and compliance inspection system for the building engineering design is characterized by comprising the following modules:
the data format formulating module adopts a building design specification expression mode based on an object-oriented idea to formulate a unified data format, and stores various building design objects and attribute fields thereof in the data format completely, integrates model information of various types layer by layer to form an information model;
the knowledge base forming module is used for dismantling the digitalized text content in the building engineering design specification strip, extracting knowledge from the Chinese natural language text in the digitalized strip, combining the knowledge sets into a multi-dimensional unified description knowledge set, and storing the knowledge set in a structured form in a database to form a knowledge base;
the rule language formulation module adopts the formed knowledge base to carry out data encapsulation on the building design objects and attribute fields thereof stored in the data format, provides a description structure of building engineering design compliance semantics, and formulates a descriptive rule language taking an object-oriented core to carry out compliance examination of the building engineering design;
the data format is used for realizing data bidirectional exchange between different information systems, not only comprises geometric form information of a model, but also stores interrelated information of the model and data information required by quality inspection, and covers non-geometric information definition of a specific building design object and service data required by application of each stage of building engineering;
the knowledge base forming module extracts knowledge of the Chinese natural language text in the digitalized strip, and then decomposes the knowledge into Chinese word segmentation, chinese part-of-speech labeling, chinese named entity recognition and named entity relation; then combining the four dimensions of the building components/building space, the component attribute/space attribute, the comparison word and the target value into a knowledge set which is uniformly described according to the four dimensions;
the main content of the descriptive rule language is a description function and attribute; wherein the attribute is a common data type including character type, integer type, decimal type and Boolean type; the description functions are logical functions for achieving purposes, functions or effects, and are composed of any legal identifier and marked with 'prefix to' prefix, each description function is provided with parameters, and each description function has a return value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211569172.1A CN116186831A (en) | 2022-12-08 | 2022-12-08 | Semantic structured description and compliance inspection method and system for building engineering design |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211569172.1A CN116186831A (en) | 2022-12-08 | 2022-12-08 | Semantic structured description and compliance inspection method and system for building engineering design |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116186831A true CN116186831A (en) | 2023-05-30 |
Family
ID=86437312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211569172.1A Pending CN116186831A (en) | 2022-12-08 | 2022-12-08 | Semantic structured description and compliance inspection method and system for building engineering design |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116186831A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116595620A (en) * | 2023-06-02 | 2023-08-15 | 中设数字技术有限公司 | Firewall judging method, device, equipment and storage medium |
| CN117011814A (en) * | 2023-10-07 | 2023-11-07 | 山东铁路投资控股集团有限公司 | Method and system for extracting railway station line structure data |
| CN118133816A (en) * | 2024-05-07 | 2024-06-04 | 浙江华东工程数字技术有限公司 | BIM derivation rule automatic structuring method and system based on large model |
| CN118643168A (en) * | 2024-08-12 | 2024-09-13 | 中交第二航务工程局有限公司 | Construction scheme compliance auditing system and method based on knowledge graph and large model |
-
2022
- 2022-12-08 CN CN202211569172.1A patent/CN116186831A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116595620A (en) * | 2023-06-02 | 2023-08-15 | 中设数字技术有限公司 | Firewall judging method, device, equipment and storage medium |
| CN116595620B (en) * | 2023-06-02 | 2024-10-18 | 中设数字技术有限公司 | Firewall judging method, device, equipment and storage medium |
| CN117011814A (en) * | 2023-10-07 | 2023-11-07 | 山东铁路投资控股集团有限公司 | Method and system for extracting railway station line structure data |
| CN117011814B (en) * | 2023-10-07 | 2023-12-15 | 山东铁路投资控股集团有限公司 | Method and system for extracting railway station line structure data |
| CN118133816A (en) * | 2024-05-07 | 2024-06-04 | 浙江华东工程数字技术有限公司 | BIM derivation rule automatic structuring method and system based on large model |
| CN118643168A (en) * | 2024-08-12 | 2024-09-13 | 中交第二航务工程局有限公司 | Construction scheme compliance auditing system and method based on knowledge graph and large model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116186831A (en) | Semantic structured description and compliance inspection method and system for building engineering design | |
| WO2022257099A1 (en) | Prefabricated building intelligent drawing output method based on bim | |
| Zhu et al. | Integration of BIM and GIS: IFC geometry transformation to shapefile using enhanced open-source approach | |
| Wu et al. | Natural-language-based intelligent retrieval engine for BIM object database | |
| Akanbi et al. | Design information extraction from construction specifications to support cost estimation | |
| CN115713161B (en) | Building information management system based on BIM technology | |
| Luo et al. | A BIM-based code compliance checking process of deep foundation construction plans | |
| CN107679221B (en) | Time-space data acquisition and service combination scheme generation method for disaster reduction task | |
| CN113987199B (en) | BIM intelligent image examination method, system and medium with standard automatic interpretation | |
| CN113408035A (en) | BIM-based wooden structure historic building structure health monitoring method | |
| CN110968713A (en) | BIM multi-scale information retrieval method and device | |
| WO2024108580A1 (en) | Multi-dimensional parameterized city information model construction method and system, and computer device | |
| CN115099315A (en) | Multi-source heterogeneous geographic information data semantic fusion conversion method based on CityGML | |
| CN112364404A (en) | Three-dimensional digital design intelligent mold overturning and picture examining method | |
| CN115687649A (en) | Automatic image examination system based on BIM and knowledge graph | |
| CN108170855A (en) | A kind of CityGML and IFC data unified query and data pick-up method | |
| Chatzinikolaou et al. | A semantically enriched and web-based 3D energy model visualization and retrieval for smart building implementation using citygml and dynamizer ade | |
| CN110162731B (en) | Method for displaying IFC model component space information on Web | |
| CN115577526B (en) | Customized building information model construction method for pedestrian traffic modeling | |
| CN115271683B (en) | BIM automatic standard checking system based on standard knowledge map element structure | |
| CN111784192A (en) | Industrial park emergency plan executable system based on dynamic evolution | |
| Zhaoguo et al. | Traditional village protection based on big data under the impact of covid-19 | |
| CN116152451A (en) | Multidimensional parameterized city information model construction method, system and computer equipment | |
| CN115934969A (en) | Construction method of immovable cultural relic risk assessment knowledge graph | |
| CN115422193A (en) | Method, system and medium for storing multi-source data of urban information model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |