Architectural design data processing flow and system based on graph structure

Abstract

The invention discloses an architectural design data processing flow and system based on a graph structure, and the method comprises the steps: firstly, extracting design component type information of each specialty from target architectural design data, converting the information into triple information through a semantic analysis model, and constructing an architectural knowledge graph; the interaction data is collected in the design system, the first design content is marked according to the high-frequency interaction content, the associated data is generated according to the first design content in combination with the atlas, the associated data and the first design content are subjected to data structuring to obtain the design intermediate data, and design interaction is performed through the design intermediate data, so that the data interaction efficiency is improved. According to the invention, the data processing flow can be effectively optimized, the interaction efficiency between the user and the design platform is improved, and the intelligent management of the design process is realized.

Description

Technical Field

[0001] The present invention relates to the field of architectural design and data processing, and more specifically, to a graph-based architectural design data processing flow and system. Background Art

[0002] In the field of architectural design and development, the design of the target building often requires the participation of multiple designers, and collaborative design is required to generate corresponding architectural design data. This results in the design platform needing to process a large amount of architectural design data, including building information model (BIM) data, architectural drawing data, architectural point cloud data, various professional model data, etc. For multi-user collaborative design platforms, due to the large amount of architectural design data, traditional architectural design data processing methods have problems such as low data sharing efficiency and insufficient data processing capabilities, which often leads to low efficiency in users' editing, correction, updating, and uploading of content. Therefore, the target urgently needs an architectural design data processing process and system. Summary of the invention

[0003] The present invention overcomes the defects of the prior art and proposes a graph-structure-based architectural design data processing flow and system.

[0004] A first aspect of the present invention provides a graph-based architectural design data processing process, comprising: Obtain design data of each discipline in the target building design data, and obtain type information of design components through the design data of each discipline; The category information is converted into text and imported into the semantic analysis model. Combined with the relationship between the building models, the entity, attribute and relationship data of the category information are extracted to form triple information, and the building knowledge graph is constructed through the triple information. In the design system, the interaction data of the user design client is collected, and the design content, design components, and interaction frequency are counted based on the interaction data, and real-time design interaction statistics are generated; By designing interactive statistics in real time, high-frequency interactive content is marked to obtain the first design content; Extracting type information of design components according to the first design content and extracting first entity data through a semantic analysis model, importing the first entity data into an architectural knowledge graph, locating a graph structure position of the first entity data in the architectural knowledge graph, and acquiring associated entity data based on a preset distance range of the graph structure and taking the first entity data as a center point, retrieving design content based on the associated entity data and the first entity data, wherein the retrieval is performed based on the target architectural design data, and obtaining retrieved design content; Based on the knowledge graph structure, the retrieved design content is structured and the graph-based design intermediate data is generated; The user sends interactive instructions through the design client, the design system receives the instructions, and makes real-time corrections, updates and uploads to the design intermediate data. During the interaction process, the changes to the design intermediate data are recorded in the form of a graph structure, and the design update record is obtained and stored in the system database.

[0005] In this solution, the design data of each discipline in the target building design data is obtained, and the type information of the design components is obtained through the design data of each discipline. Each discipline includes architectural, structural, water supply and drainage, HVAC, and electrical professional models. The type information is specifically the attribute information of the design components in different professional models.

[0006] In this solution, the category information is converted into text and imported into the semantic analysis model. Combined with the building model relationship, the entity, attribute, and relationship data of the category information are extracted to form triple information. The building knowledge graph is constructed through the triple information, specifically: Build a semantic analysis model based on word embedding; The category information is converted into text and imported into the semantic analysis model. Combined with the relationship of the building model, the category information is subjected to entity recognition, labeling, entity relationship recognition and entity attribute acquisition, and triple information is obtained; Construct an architectural knowledge graph based on the target building through triple information.

[0007] In this solution, in the design system, the interaction data of the user design client is collected, and the design interaction statistics of the design content, design components, and interaction frequency are performed based on the interaction data, and real-time design interaction statistical information is generated, specifically: Based on a design cycle, the design system collects the interaction data of multiple user design clients; Interactive data includes the addition, correction, and update information of design data, design content, and design component information; By conducting design interaction statistics on design content, design components, and interaction frequency based on interaction data, real-time design interaction statistical information is generated.

[0008] In this solution, the high-frequency interaction content is marked by designing the interaction statistical information in real time, and the high-frequency interaction content in the first design content is selected based on the comparison between the corresponding interaction frequency and the preset frequency.

[0009] In this solution, the type information of the design component is extracted according to the first design content and the first entity data is extracted through the semantic analysis model, the first entity data is imported into the architectural knowledge graph, the graph structure position where the first entity data is located is located in the architectural knowledge graph, and based on the preset distance range of the graph structure, the first entity data is used as the center point to obtain the associated entity data, and the design content is retrieved based on the associated entity data and the first entity data. The retrieval is performed based on the target architectural design data, and the retrieved design content is obtained, specifically: Extracting type information of design components and converting text according to the first design content, and importing a semantic analysis model to perform design entity analysis, and extracting first entity data; Importing the first entity data into the architectural knowledge graph to perform entity data retrieval and positioning, wherein the retrieval and positioning are achieved by comparing nodes in the knowledge graph, and obtaining graph positioning based on the first entity data; Based on graph positioning, the entity data and the corresponding nodes are determined in the architectural knowledge graph, and the corresponding nodes are used as the center points. A preset distance range is set in the knowledge graph. Based on the graph structure characteristics of the knowledge graph, the entity data within the preset distance range is retrieved to obtain the associated entity data; The design content is retrieved and extracted by associating the entity data with the first entity data. The retrieval is performed based on the target building design data, and the retrieved design content is obtained.

[0010] In this solution, based on the knowledge graph structure, the retrieved design content is data structured and the graph-structured design intermediate data is generated, specifically: Through the first entity data and the associated entity data, entity attributes and relationship data are extracted in the architectural knowledge graph to form attribute and relationship data; Constructing a storage model based on a graph structure, setting a plurality of nodes in the storage model through the first entity data and the associated entity data, and importing the attribute and relationship data into the storage model to fill the graph structure data; The retrieved design content is imported into the storage model, and the node content data is filled according to the node to which the design content belongs, and the obtained storage model is used as the design intermediate data.

[0011] In this solution, the user designs the client to send the interactive instruction, and the design system receives the instruction, which includes: In the design system, a cache area is expanded to store the intermediate design data; In real-time design interaction, users interact through user design clients, which generate interaction instructions and send them to the design system; The design system determines whether the design content in the interactive instruction belongs to the design intermediate data. If so, the design intermediate data is corrected, updated and uploaded in real time.

[0012] The second aspect of the present invention further provides a graph-based architectural design data processing system, the system comprising: a memory, a processor, the memory comprising a graph-based architectural design data processing program, the graph-based architectural design data processing program implementing the following steps when executed by the processor: Obtain design data of each discipline in the target building design data, and obtain type information of design components through the design data of each discipline; The category information is converted into text and imported into the semantic analysis model. Combined with the relationship between the building models, the entity, attribute and relationship data of the category information are extracted to form triple information, and the building knowledge graph is constructed through the triple information. In the design system, the interaction data of the user design client is collected, and the design content, design components, and interaction frequency are counted based on the interaction data, and real-time design interaction statistics are generated; By designing interactive statistics in real time, high-frequency interactive content is marked to obtain the first design content; Extracting type information of design components according to the first design content and extracting first entity data through a semantic analysis model, importing the first entity data into an architectural knowledge graph, locating a graph structure position of the first entity data in the architectural knowledge graph, and acquiring associated entity data based on a preset distance range of the graph structure and taking the first entity data as a center point, retrieving design content based on the associated entity data and the first entity data, wherein the retrieval is performed based on the target architectural design data, and obtaining retrieved design content; Based on the knowledge graph structure, the retrieved design content is structured and the graph-based design intermediate data is generated; The user sends interactive instructions through the design client, the design system receives the instructions, and makes real-time corrections, updates and uploads to the design intermediate data. During the interaction process, the changes to the design intermediate data are recorded in the form of a graph structure, and the design update record is obtained and stored in the system database.

[0013] The third aspect of the present invention also provides a computer-readable storage medium, which includes a graph-structured architectural design data processing program. When the graph-structured architectural design data processing program is executed by a processor, it implements the steps of the graph-structured architectural design data processing flow as described in any one of the above items.

[0014] The present invention discloses a graph-based architectural design data processing process and system. First, the design component type information of each profession is extracted from the target architectural design data, and converted into triple information through a semantic analysis model to construct an architectural knowledge graph. Interaction data is collected in the design system, and the first design content is marked according to the high-frequency interaction content. Associated data is generated according to the first design content combined with the graph, and the associated data and the first design content are data structured to obtain design intermediate data. Design interaction is performed through the design intermediate data, thereby improving data interaction efficiency. Through the present invention, the data processing process can be effectively optimized and the interaction efficiency between users and the design platform can be improved, realizing intelligent management of the design process. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A flowchart showing a process of architectural design data processing based on a graph structure of the present invention is shown; Figure 2 A block diagram of a graph-structure-based architectural design data processing system of the present invention is shown. DETAILED DESCRIPTION

[0016] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0017] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0018] Figure 1 A flow chart of a graph-structure-based architectural design data processing process of the present invention is shown.

[0019] like Figure 1 As shown, the first aspect of the present invention provides a graph-based architectural design data processing process, including: S102, obtaining design data of each discipline in the target building design data, and obtaining type information of design components through the design data of each discipline; S104, converting the category information into text and importing it into a semantic analysis model, extracting entity, attribute, and relationship data from the category information in combination with the building model relationship to form triple information, and constructing a building knowledge graph through the triple information; S106, in the design system, collecting interaction data of the user design client, performing design interaction statistics on the design content, design components, and interaction frequency based on the interaction data, and generating real-time design interaction statistical information; S108, marking high-frequency interactive content by real-time design interaction statistical information to obtain first design content; S110, extracting type information of design components according to the first design content and extracting first entity data through a semantic analysis model, importing the first entity data into an architectural knowledge graph, locating a graph structure position where the first entity data is located in the architectural knowledge graph, and acquiring associated entity data based on a preset distance range of the graph structure with the first entity data as a center point, retrieving design content based on the associated entity data and the first entity data, wherein the retrieval is performed based on the target architectural design data, and obtaining retrieved design content; S112, based on the knowledge graph structure, structuring the retrieved design content and generating graph-structured design intermediate data; S114, the user sends interactive instructions through the design client, the design system receives the instructions, and performs real-time correction, update and upload of the design content of the intermediate design data. During the interaction process, the changes to the intermediate design data are recorded in the form of a graph structure, and the design update record is obtained, and the design update record is stored in the system database.

[0020] According to an embodiment of the present invention, the design data of each discipline in the target building design data is obtained, and the type information of the design components is obtained through the design data of each discipline. Each discipline includes architectural, structural, water supply and drainage, HVAC, and electrical professional models, and the type information is specifically the attribute information of the design components in different professional models.

[0021] It should be noted that the category information can be used to perform semantic analysis on the model units of architectural design in the form of information text, and subsequently construct a knowledge graph.

[0022] According to an embodiment of the present invention, the text conversion of the category information is carried out and imported into the semantic analysis model, and the entity, attribute and relationship data of the category information are extracted in combination with the building model relationship to form triple information, and the building knowledge graph is constructed through the triple information, specifically: Build a semantic analysis model based on word embedding; The category information is converted into text and imported into the semantic analysis model. Combined with the relationship of the building model, the category information is subjected to entity recognition, labeling, entity relationship recognition and entity attribute acquisition, and triple information is obtained; Construct an architectural knowledge graph based on the target building through triple information.

[0023] It should be noted that the target building design data includes architectural design data of various disciplines, and there is a certain relationship between different design data. On the whole, they all belong to the overall target building, but based on different professional models, the corresponding designers are also different. For example, the building fire protection design model and the pipeline design model belong to different professional levels, but there is a certain relationship between the models designed by the user, such as spatial association, functionality, and role association. Therefore, multi-user collaborative analysis is required during the user's design, modification, and correction process. In the present invention, by performing informatization and semantic analysis on different building models and components, extracting triple information in the form of semantic information, and constructing a knowledge graph belonging to the target building, it is helpful to understand the role of each building component for the entire target building and the relationship and attributes between the design building components through informatization. For example, in the knowledge graph, there are two entity information of the first component and the second component. The two components belong to different professional models respectively, and the components have certain design parameters. This information can be stored in the attributes, and the architectural relationship and correlation between the components can be stored through the relationship in the graph, so as to grasp the relationship between different design components and provide data support for subsequent user collaborative design and data interaction. Entities in the knowledge graph are nodes in the graph structure.

[0024] According to an embodiment of the present invention, in the design system, the interaction data of the user design client is collected, and design interaction statistics are performed on the design content, design components, and interaction frequency based on the interaction data, and real-time design interaction statistical information is generated, specifically: Based on a design cycle, the design system collects the interaction data of multiple user design clients; Interactive data includes the addition, correction, and update information of design data, design content, and design component information; By conducting design interaction statistics on design content, design components, and interaction frequency based on interaction data, real-time design interaction statistical information is generated.

[0025] It should be noted that the real-time design interaction statistical information includes information such as design frequency, number of interactions, number of revisions, etc. corresponding to different building components in the overall target building design among multiple users, which is used for subsequent evaluation of high-frequency design components.

[0026] According to an embodiment of the present invention, by designing interactive statistical information in real time, high-frequency interactive content is marked, and in the first design content, high-frequency interactive content is screened based on a comparison between the corresponding interaction frequency and the preset frequency.

[0027] It should be noted that in the process of designing the interaction between users and systems, marking the components that are used frequently can further screen out related components (i.e., related design content) with research value in the future. In the present invention, the design system is a cloud platform that is interconnected with the user design client through the Internet, and the architectural design data is stored in the cloud platform.

[0028] According to an embodiment of the present invention, the type information of the design component is extracted according to the first design content and the first entity data is extracted through the semantic analysis model, the first entity data is imported into the architectural knowledge graph, the graph structure position where the first entity data is located is located in the architectural knowledge graph, and based on a preset distance range of the graph structure, the associated entity data is obtained with the first entity data as the center point, and the design content is retrieved based on the associated entity data and the first entity data. The retrieval is performed based on the target architectural design data, and the retrieved design content is obtained, specifically: Extracting type information of design components and converting text according to the first design content, and importing a semantic analysis model to perform design entity analysis, and extracting first entity data; Importing the first entity data into the architectural knowledge graph to perform entity data retrieval and positioning, wherein the retrieval and positioning are achieved by comparing nodes in the knowledge graph, and obtaining graph positioning based on the first entity data; Based on graph positioning, the entity data and the corresponding nodes are determined in the architectural knowledge graph, and the corresponding nodes are used as the center points. A preset distance range is set in the knowledge graph. Based on the graph structure characteristics of the knowledge graph, the entity data within the preset distance range is retrieved to obtain the associated entity data; The design content is retrieved and extracted by associating the entity data with the first entity data. The retrieval is performed based on the target building design data, and the retrieved design content is obtained.

[0029] It should be noted that the graph location (graph structure location) is the entity node location of the first entity data in the knowledge graph. The first entity data is used as the center point to obtain the associated entity data, that is, the corresponding node is used as the center point. In the knowledge graph, entity data is node data.

[0030] It is worth mentioning that in the existing large-scale architectural design tasks, it generally involves multi-user, multi-professional model design, and the amount of collaborative interaction tasks is huge, such as the BIM collaborative design system. In the case of a large number of user clients, the network requirements and interaction process of the design system will become extremely complex. Multiple users design at the same time, which causes excessive resource consumption during the platform transmission process. The overall file of the building is generally large, which can easily lead to shared servers not transmitting data in a timely manner, data loss, poor real-time performance, etc. The interaction process is more sensitive to hardware and network resources.

[0031] Based on this, the present invention fully considers the situation that multiple users have a high frequency of design changes of specific models and components in the process of architectural design. The present invention constructs an architectural knowledge graph, establishes entity relationships and related attributes between various design components (design elements) in the target building in the graph, analyzes the relationship between architectural design contents in a semantic form, extracts design data with high frequency of user interaction based on a certain period, converts the design data into entity data, extracts associated data (associated entity data) from the knowledge graph, and screens out associated components. Through this screening process, the user's design modification needs can be predicted. There is a certain correlation and association between the associated components and the user's high-frequency interactive design content, and intermediate data based on the graph structure is built based on the screened retrieval design content. Subsequently, design interaction is performed in the form of intermediate data, which effectively improves the data transmission efficiency between the user client and the design system, greatly reduces the server pressure during the interaction process, and can improve the design interaction efficiency of users for most of the time in multiple design cycles.

[0032] At the same time, since the intermediate data is extracted through correlation analysis, the design content modified, updated and uploaded by users in real time is likely to belong to the intermediate data.

[0033] According to an embodiment of the present invention, based on the knowledge graph structure, the retrieved design content is data structured and the design intermediate data based on the graph structure is generated, specifically: Through the first entity data and the associated entity data, entity attributes and relationship data are extracted in the architectural knowledge graph to form attribute and relationship data; Constructing a storage model based on a graph structure, setting a plurality of nodes in the storage model through the first entity data and the associated entity data, and importing the attribute and relationship data into the storage model to fill the graph structure data; The retrieved design content is imported into the storage model, and the node content data is filled according to the node to which the design content belongs, and the obtained storage model is used as the design intermediate data.

[0034] It should be noted that the design intermediate data is a storage model used as a container for intermediate storage. In this container, high-frequency design content and design content related to architectural design are stored. During real-time design analysis, the intermediate data is generated based on dynamic analysis and extracted to a specific database for storage. When the user interacts in a certain design cycle, the design intermediate data can be directly modified and changed, greatly improving the interaction efficiency.

[0035] In particular, the design intermediate data is stored based on a graph structure, which saves the actual design content data (i.e., architectural design data) and sorts and stores the design content data in a graph structure. Its data is a part of the data extracted from the target architectural design data, while the architectural knowledge graph only has entity relationship attribute data such as information type, and does not include actual design data. It is used to describe and analyze the relationship between entity contents such as building components and design content.

[0036] According to an embodiment of the present invention, the user designing a client to send an interaction instruction, and the designing system receiving the instruction, includes: In the design system, a cache area is expanded to store the intermediate design data; In real-time design interaction, users interact through user design clients, which generate interaction instructions and send them to the design system; The design system determines whether the design content in the interactive instruction belongs to the design intermediate data. If so, the design intermediate data is corrected, updated and uploaded in real time.

[0037] According to an embodiment of the present invention, the user design client sends an interactive instruction, the design system receives the instruction, and performs real-time modification, update and upload of the design content of the design intermediate data, and records the changes of the design intermediate data in the form of a graph structure during the interaction process, and obtains a design update record, and stores the design update record in the system database, and also includes: Generate a structured information table according to the storage structure of the intermediate data, wherein the structured information table stores the number of nodes, node relationships, node attributes, file size, and the number of edges of each node; During the interaction, the changes in the intermediate design data are marked, and based on the storage structure of the intermediate design data, the changes in the entity nodes, relationships, and attributes involved in the changes are determined, and each change is recorded and updated in the structured information table. The structured information table stores the original structure of the design intermediate data and the graph structure change information of each modification; According to user needs, when querying the revision records of design content and reviewing design data, historical design revisions are reviewed through structured information tables and design intermediate data; Store structured information tables in the system database.

[0038] It should be noted that the node relationship is stored in the graph structure through the edges between the nodes.

[0039] It is worth mentioning that in traditional technologies, the modification and uploading of design data often stores and uploads the entire user operation and the parts before and after the file modification to the cloud. The review efficiency is low and the storage volume is large. It may encounter problems such as platform upload jams, affecting work efficiency. Therefore, the present invention uses the graph-structured characteristics of dynamically generated design intermediate data to store each modification and update of the design content through a structured information table. When reviewing the modified design content, it can be viewed through the structured information table. The structured information table records the changes in information such as nodes, relationships (edges), attributes, etc. in the graph structure, thereby realizing a rapid review of the design content modification records. In addition, each time the design content is modified, the associated design components (through the design intermediate data) can be viewed through the modification record, which helps to assist designers in checking the associated components for each design modification, thereby improving the intelligence of the design system and efficient office work.

[0040] According to an embodiment of the present invention, it also includes: In the next design cycle, second design interaction statistical information is obtained through the design system; Using the second design interaction statistical information, high-frequency interaction content is marked to obtain the second design content; extracting second entity data through the second design content; In the architectural knowledge graph, the distance between nodes of the first entity data and the second entity data is calculated, and the similarity between the first entity data and the second entity data is reflected by the distance between nodes. If the similarity is lower than the expected value, the current design intermediate data is imported into the design system and the original design data is overwritten; Based on the architectural knowledge graph, related design content is retrieved through the second entity data, and second design intermediate data is generated; Import the second design intermediate data into the cache area.

[0041] It should be noted that the distance calculation between the nodes of the first entity data and the second entity data is used to reflect the difference between the entity data of the two through the knowledge graph. If the difference is high, it means that the current user's design focus area and key design content are deviated, and the intermediate data needs to be reset to improve the interaction efficiency of the system. The expected value is the similarity value set by the user. The distance calculation between nodes can be performed through the graph structure characteristics and the edge information between nodes.

[0042] The present invention realizes dynamic adjustment of design intermediate data by analyzing the user's high-frequency design data and judging the transfer of design focus, so that the cache area can store the most practical and efficient intermediate data for the current user, thereby improving the adaptability of the design system.

[0043] Figure 2A block diagram of a graph-structure-based architectural design data processing system of the present invention is shown.

[0044] The second aspect of the present invention further provides a graph-based architectural design data processing system 2, the system comprising: a memory 21, a processor 22, the memory 21 comprising a graph-based architectural design data processing program, the graph-based architectural design data processing program being executed by the processor 22 to implement the following steps: Obtain design data of each discipline in the target building design data, and obtain type information of design components through the design data of each discipline; The category information is converted into text and imported into the semantic analysis model. Combined with the relationship between the building models, the entity, attribute and relationship data of the category information are extracted to form triple information, and the building knowledge graph is constructed through the triple information. In the design system, the interaction data of the user design client is collected, and the design content, design components, and interaction frequency are counted based on the interaction data, and real-time design interaction statistics are generated; By designing interactive statistics in real time, high-frequency interactive content is marked to obtain the first design content; Extracting type information of design components according to the first design content and extracting first entity data through a semantic analysis model, importing the first entity data into an architectural knowledge graph, locating a graph structure position of the first entity data in the architectural knowledge graph, and acquiring associated entity data based on a preset distance range of the graph structure and taking the first entity data as a center point, retrieving design content based on the associated entity data and the first entity data, wherein the retrieval is performed based on the target architectural design data, and obtaining retrieved design content; Based on the knowledge graph structure, the retrieved design content is structured and the graph-based design intermediate data is generated; The user sends interactive instructions through the design client, the design system receives the instructions, and makes real-time corrections, updates and uploads to the design intermediate data. During the interaction process, the changes to the design intermediate data are recorded in the form of a graph structure, and the design update record is obtained and stored in the system database.

[0045] According to an embodiment of the present invention, the design data of each discipline in the target building design data is obtained, and the type information of the design components is obtained through the design data of each discipline. Each discipline includes architectural, structural, water supply and drainage, HVAC, and electrical professional models, and the type information is specifically the attribute information of the design components in different professional models.

[0046] It should be noted that the category information can be used to perform semantic analysis on the model units of architectural design in the form of information text, and subsequently construct a knowledge graph.

[0047] According to an embodiment of the present invention, the text conversion of the category information is carried out and imported into the semantic analysis model, and the entity, attribute and relationship data of the category information are extracted in combination with the building model relationship to form triple information, and the building knowledge graph is constructed through the triple information, specifically: Build a semantic analysis model based on word embedding; The category information is converted into text and imported into the semantic analysis model. Combined with the relationship of the building model, the category information is subjected to entity recognition, labeling, entity relationship recognition and entity attribute acquisition, and triple information is obtained; Construct an architectural knowledge graph based on the target building through triple information.

[0048] It should be noted that the target building design data includes architectural design data of various disciplines, and there is a certain relationship between different design data. On the whole, they all belong to the overall target building, but based on different professional models, the corresponding designers are also different. For example, the building fire protection design model and the pipeline design model belong to different professional levels, but there is a certain relationship between the models designed by the user, such as spatial association, functionality, and role association. Therefore, multi-user collaborative analysis is required during the user's design, modification, and correction process. In the present invention, by performing informatization and semantic analysis on different building models and components, extracting triple information in the form of semantic information, and constructing a knowledge graph belonging to the target building, it is helpful to understand the role of each building component for the entire target building and the relationship and attributes between the design building components through informatization. For example, in the knowledge graph, there are two entity information of the first component and the second component. The two components belong to different professional models respectively, and the components have certain design parameters. This information can be stored in the attributes, and the architectural relationship and correlation between the components can be stored through the relationship in the graph, so as to grasp the relationship between different design components and provide data support for subsequent user collaborative design and data interaction. Entities in the knowledge graph are nodes in the graph structure.

[0049] According to an embodiment of the present invention, in the design system, the interaction data of the user design client is collected, and design interaction statistics are performed on the design content, design components, and interaction frequency based on the interaction data, and real-time design interaction statistical information is generated, specifically: Based on a design cycle, the design system collects the interaction data of multiple user design clients; Interactive data includes the addition, correction, and update information of design data, design content, and design component information; By conducting design interaction statistics on design content, design components, and interaction frequency based on interaction data, real-time design interaction statistical information is generated.

[0050] It should be noted that the real-time design interaction statistical information includes information such as design frequency, number of interactions, number of revisions, etc. corresponding to different building components in the overall target building design among multiple users, which is used for subsequent evaluation of high-frequency design components.

[0051] According to an embodiment of the present invention, by designing interactive statistical information in real time, high-frequency interactive content is marked, and in the first design content, high-frequency interactive content is screened based on a comparison between the corresponding interaction frequency and the preset frequency.

[0052] It should be noted that in the process of designing the interaction between users and systems, marking the components that are used frequently can further screen out related components (i.e., related design content) with research value in the future. In the present invention, the design system is a cloud platform that is interconnected with the user design client through the Internet, and the architectural design data is stored in the cloud platform.

[0053] According to an embodiment of the present invention, the type information of the design component is extracted according to the first design content and the first entity data is extracted through the semantic analysis model, the first entity data is imported into the architectural knowledge graph, the graph structure position where the first entity data is located is located in the architectural knowledge graph, and based on a preset distance range of the graph structure, the associated entity data is obtained with the first entity data as the center point, and the design content is retrieved based on the associated entity data and the first entity data. The retrieval is performed based on the target architectural design data, and the retrieved design content is obtained, specifically: Extracting type information of design components and converting text according to the first design content, and importing a semantic analysis model to perform design entity analysis, and extracting first entity data; Importing the first entity data into the architectural knowledge graph to perform entity data retrieval and positioning, wherein the retrieval and positioning are achieved by comparing nodes in the knowledge graph, and obtaining graph positioning based on the first entity data; Based on graph positioning, the entity data and the corresponding nodes are determined in the architectural knowledge graph, and the corresponding nodes are used as the center points. A preset distance range is set in the knowledge graph. Based on the graph structure characteristics of the knowledge graph, the entity data within the preset distance range is retrieved to obtain the associated entity data; The design content is retrieved and extracted by associating the entity data with the first entity data. The retrieval is performed based on the target building design data, and the retrieved design content is obtained.

[0054] It should be noted that the graph location (graph structure location) is the entity node location of the first entity data in the knowledge graph. The first entity data is used as the center point to obtain the associated entity data, that is, the corresponding node is used as the center point. In the knowledge graph, entity data is node data.

[0055] It is worth mentioning that in the existing large-scale architectural design tasks, it generally involves multi-user, multi-professional model design, and the amount of collaborative interaction tasks is huge, such as the BIM collaborative design system. In the case of a large number of user clients, the network requirements and interaction process of the design system will become extremely complex. Multiple users design at the same time, which causes excessive resource consumption during the platform transmission process. The overall file of the building is generally large, which can easily lead to shared servers not transmitting data in a timely manner, data loss, poor real-time performance, etc. The interaction process is more sensitive to hardware and network resources.

[0056] Based on this, the present invention fully considers the situation that multiple users have a high frequency of design changes of specific models and components in the process of architectural design. The present invention constructs an architectural knowledge graph, establishes entity relationships and related attributes between various design components (design elements) in the target building in the graph, analyzes the relationship between architectural design contents in a semantic form, extracts design data with high frequency of user interaction based on a certain period, converts the design data into entity data, extracts associated data (associated entity data) from the knowledge graph, and screens out associated components. Through this screening process, the user's design modification needs can be predicted. There is a certain correlation and association between the associated components and the user's high-frequency interactive design content, and intermediate data based on the graph structure is built based on the screened retrieval design content. Subsequently, design interaction is performed in the form of intermediate data, which effectively improves the data transmission efficiency between the user client and the design system, greatly reduces the server pressure during the interaction process, and can improve the design interaction efficiency of users for most of the time in multiple design cycles.

[0057] At the same time, since the intermediate data is extracted through correlation analysis, the design content modified, updated and uploaded by users in real time is likely to belong to the intermediate data.

[0058] According to an embodiment of the present invention, based on the knowledge graph structure, the retrieved design content is data structured and the design intermediate data based on the graph structure is generated, specifically: Through the first entity data and the associated entity data, entity attributes and relationship data are extracted in the architectural knowledge graph to form attribute and relationship data; Constructing a storage model based on a graph structure, setting a plurality of nodes in the storage model through the first entity data and the associated entity data, and importing the attribute and relationship data into the storage model to fill the graph structure data; The retrieved design content is imported into the storage model, and the node content data is filled according to the node to which the design content belongs, and the obtained storage model is used as the design intermediate data.

[0059] It should be noted that the design intermediate data is a storage model used as a container for intermediate storage. In this container, high-frequency design content and design content related to architectural design are stored. During real-time design analysis, the intermediate data is generated based on dynamic analysis and extracted to a specific database for storage. When the user interacts in a certain design cycle, the design intermediate data can be directly modified and changed, greatly improving the interaction efficiency.

[0060] In particular, the design intermediate data is stored based on a graph structure, which saves the actual design content data (i.e., architectural design data) and sorts and stores the design content data in a graph structure. Its data is a part of the data extracted from the target architectural design data, while the architectural knowledge graph only has entity relationship attribute data such as information type, and does not include actual design data. It is used to describe and analyze the relationship between entity contents such as building components and design content.

[0061] According to an embodiment of the present invention, the user designing a client to send an interaction instruction, and the designing system receiving the instruction, includes: In the design system, a cache area is expanded to store the intermediate design data; In real-time design interaction, users interact through user design clients, which generate interaction instructions and send them to the design system; The design system determines whether the design content in the interactive instruction belongs to the design intermediate data. If so, the design intermediate data is corrected, updated and uploaded in real time.

[0062] The third aspect of the present invention also provides a computer-readable storage medium, which includes a graph-structured architectural design data processing program. When the graph-structured architectural design data processing program is executed by a processor, it implements the steps of the graph-structured architectural design data processing flow as described in any one of the above items.

[0063] The present invention discloses a graph-based architectural design data processing process and system. First, the design component type information of each profession is extracted from the target architectural design data, and converted into triple information through a semantic analysis model to construct an architectural knowledge graph. Interaction data is collected in the design system, and the first design content is marked according to the high-frequency interaction content. Associated data is generated according to the first design content combined with the graph, and the associated data and the first design content are data structured to obtain design intermediate data. Design interaction is performed through the design intermediate data, thereby improving data interaction efficiency. Through the present invention, the data processing process can be effectively optimized and the interaction efficiency between users and the design platform can be improved, realizing intelligent management of the design process.

[0064] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0065] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0066] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0067] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0068] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0069] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A graph-based architectural design data processing process, characterized in that: include: Obtain design data of each discipline in the target building design data, and obtain type information of design components through the design data of each discipline; The category information is converted into text and imported into the semantic analysis model. Combined with the relationship between the building models, the entity, attribute and relationship data of the category information are extracted to form triple information, and the building knowledge graph is constructed through the triple information. In the design system, the interaction data of the user design client is collected, and the design content, design components, and interaction frequency are counted based on the interaction data, and real-time design interaction statistics are generated; By designing interactive statistics in real time, high-frequency interactive content is marked to obtain the first design content; Extracting type information of design components according to the first design content and extracting first entity data through a semantic analysis model, importing the first entity data into an architectural knowledge graph, locating a graph structure position of the first entity data in the architectural knowledge graph, and acquiring associated entity data based on a preset distance range of the graph structure and taking the first entity data as a center point, retrieving design content based on the associated entity data and the first entity data, wherein the retrieval is performed based on the target architectural design data, and obtaining retrieved design content; Based on the knowledge graph structure, the retrieved design content is structured and the graph-based design intermediate data is generated; The user sends interactive instructions through the design client, the design system receives the instructions, and makes real-time corrections, updates and uploads to the design intermediate data. During the interaction process, the changes to the design intermediate data are recorded in the form of a graph structure, and the design update record is obtained and stored in the system database.

2. The architectural design data processing flow based on graph structure according to claim 1 is characterized in that: The method of obtaining the design data of each discipline in the target building design data and obtaining the type information of the design components through the design data of each discipline includes architectural, structural, water supply and drainage, HVAC, and electrical professional models. The type information is specifically the attribute information of the design components in different professional models.

3. The architectural design data processing flow based on graph structure according to claim 1 is characterized in that: The text conversion of the category information is carried out and imported into the semantic analysis model, and the entity, attribute and relationship data of the category information are extracted in combination with the building model relationship to form triple information, and the building knowledge graph is constructed through the triple information, specifically: Build a semantic analysis model based on word embedding; The category information is converted into text and imported into the semantic analysis model. Combined with the relationship of the building model, the category information is subjected to entity recognition, labeling, entity relationship recognition and entity attribute acquisition, and triple information is obtained; Construct an architectural knowledge graph based on the target building through triple information.

4. The architectural design data processing flow based on graph structure according to claim 3 is characterized in that: In the design system, the interaction data of the user design client is collected, and the design interaction statistics are performed on the design content, design components, and interaction frequency based on the interaction data, and real-time design interaction statistical information is generated, specifically: Based on a design cycle, the design system collects the interaction data of multiple user design clients; Interactive data includes the addition, correction, and update information of design data, design content, and design component information; By conducting design interaction statistics on design content, design components, and interaction frequency based on interaction data, real-time design interaction statistical information is generated.

5. The architectural design data processing flow based on graph structure according to claim 4 is characterized in that: The high-frequency interaction content is marked by designing the interaction statistical information in real time, and the high-frequency interaction content in the first design content is selected based on the comparison between the corresponding interaction frequency and the preset frequency.

6. The architectural design data processing flow based on graph structure according to claim 5 is characterized in that: The method comprises extracting type information of design components according to the first design content and extracting first entity data through a semantic analysis model, importing the first entity data into an architectural knowledge graph, locating a graph structure position where the first entity data is located in the architectural knowledge graph, and acquiring associated entity data based on a preset distance range of the graph structure and taking the first entity data as a center point, retrieving design content based on the associated entity data and the first entity data, wherein the retrieval is performed based on target architectural design data, and obtaining retrieved design content, specifically: Extracting type information of design components and converting text according to the first design content, and importing a semantic analysis model to perform design entity analysis, and extracting first entity data; Importing the first entity data into the architectural knowledge graph to perform entity data retrieval and positioning, wherein the retrieval and positioning are achieved by comparing nodes in the knowledge graph, and obtaining graph positioning based on the first entity data; Based on graph positioning, the entity data and the corresponding nodes are determined in the architectural knowledge graph, and the corresponding nodes are used as the center points. A preset distance range is set in the knowledge graph. Based on the graph structure characteristics of the knowledge graph, the entity data within the preset distance range is retrieved to obtain the associated entity data; The design content is retrieved and extracted by associating the entity data with the first entity data. The retrieval is performed based on the target building design data, and the retrieved design content is obtained.

7. The architectural design data processing flow based on graph structure according to claim 6 is characterized in that: Based on the knowledge graph structure, the retrieved design content is data structured and the design intermediate data based on the graph structure is generated, specifically: Through the first entity data and the associated entity data, entity attributes and relationship data are extracted in the architectural knowledge graph to form attribute and relationship data; Constructing a storage model based on a graph structure, setting a plurality of nodes in the storage model through the first entity data and the associated entity data, and importing the attribute and relationship data into the storage model to fill the graph structure data; The retrieved design content is imported into the storage model, and the node content data is filled according to the node to which the design content belongs, and the obtained storage model is used as the design intermediate data.

8. The architectural design data processing flow based on graph structure according to claim 7 is characterized in that: The user designs the client to send the interactive instruction, and the design system receives the instruction, which includes: In the design system, a cache area is expanded to store the intermediate design data; In real-time design interaction, users interact through user design clients, which generate interaction instructions and send them to the design system; The design system determines whether the design content in the interactive instruction belongs to the design intermediate data. If so, the design intermediate data is corrected, updated and uploaded in real time.

9. A graph-based architectural design data processing system, characterized in that: The system includes: a memory and a processor. The memory includes a graph-structure-based architectural design data processing program. When the graph-structure-based architectural design data processing program is executed by the processor, the following steps are implemented: Obtain design data of each discipline in the target building design data, and obtain type information of design components through the design data of each discipline; The category information is converted into text and imported into the semantic analysis model. Combined with the relationship between the building models, the entity, attribute and relationship data of the category information are extracted to form triple information, and the building knowledge graph is constructed through the triple information. In the design system, the interaction data of the user design client is collected, and the design content, design components, and interaction frequency are counted based on the interaction data, and real-time design interaction statistics are generated; By designing interactive statistics in real time, high-frequency interactive content is marked to obtain the first design content; Extracting type information of design components according to the first design content and extracting first entity data through a semantic analysis model, importing the first entity data into an architectural knowledge graph, locating a graph structure position of the first entity data in the architectural knowledge graph, and acquiring associated entity data based on a preset distance range of the graph structure and taking the first entity data as a center point, retrieving design content based on the associated entity data and the first entity data, wherein the retrieval is performed based on the target architectural design data, and obtaining retrieved design content; Based on the knowledge graph structure, the retrieved design content is structured and the graph-based design intermediate data is generated; The user sends interactive instructions through the design client, the design system receives the instructions, and makes real-time corrections, updates and uploads to the design intermediate data. During the interaction process, the changes to the design intermediate data are recorded in the form of a graph structure, and the design update record is obtained and stored in the system database.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a graph-structure-based architectural design data processing program, and when the graph-structure-based architectural design data processing program is executed by a processor, the steps of the graph-structure-based architectural design data processing flow according to any one of claims 1 to 8 are implemented.

Images