Digital asset management method and system based on component identification codes

Abstract

The invention provides a digital asset management method and system based on component identification codes. The method comprises the following steps: coding each component in a BIM model according to a preset coding method, and associating design data and construction data corresponding to the components with codes; component construction information of a current construction project of the entity road is obtained through analysis according to first real-time construction data uploaded by the field terminal, the component evaluation qualification probability is predicted according to the component construction information, and updating delay duration is obtained through comparison; when the update delay duration is reached, if second real-time construction data belonging to the same construction project and construction stage as the first real-time construction data is not received, updating the BIM model based on the first real-time construction data; and otherwise, updating the BIM model based on the second real-time construction data. According to the component coding method, computer analysis and identification are facilitated, subsequent positioning and searching of workers are utilized, and the probability of manual correction in the digital twin road is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of project management, and more particularly, to a digital asset management method and system based on component identification coding. Background Art

[0002] The digital twin technology has emerged and gradually gained attention and application in the highway field. The digital twin highway aims to achieve real-time mapping and accurate simulation of the entire life cycle of the highway by constructing a virtual digital model corresponding to the physical entity of the real highway. Among them, the physical highway project belongs to the fixed assets of the investor, and the digital twin highway belongs to the digital assets of the investor.

[0003] There is a mature system for the construction management of physical highways, but the construction standards for digital twin highways are still in the process of exploration. The physical highway is divided into sections according to specialties during the design and construction process, and the digital twin highway also needs to be divided into different specialties and sections during the modeling process, so a large number of model files will be generated, and there is currently no mature and standardized system for the management of model files. A complete set of materials will be saved during the construction of the physical highway, and each material will be grouped and coded. This method is suitable for the archiving of paper materials; the digital twin highway can digitalize the materials, and each material is associated with one or more components of the highway engineering model in the form of hyperlinks, and more rapid and efficient queries can be realized in a digital way. Therefore, on the basis of classification coding, highway engineering components also need to be given an identification code similar to the paper material number. This identification code is unique throughout the life cycle, can be read by people to determine the component location, and is a coding integrating multiple functions. However, there is currently no such unified identification coding in the prior art.

[0004] At the same time, in order to ensure the consistency between the digital twin highway and the actual construction process of the physical highway, it is necessary for on-site personnel or equipment to timely upload the actual component construction information of the physical highway to realize the timely update of the BIM models of each component in the digital twin highway. However, during the construction of the physical highway, situations such as rework and reconstruction often occur, resulting in the need for manual correction of the erroneously updated digital twin highway. This undoubtedly increases the workload of the management personnel, and will also lead to inconsistencies between the digital twin highway and the physical highway during the modification period, affecting the remote supervision of the on-site physical highway.

[0005] Therefore, how to uniformly identify and code the components in the digital twin highway, and how to optimize the update strategy between the digital twin highway and the physical highway are the technical problems that need to be solved urgently at present. Summary of the Invention

[0006] In order to at least solve the technical problems existing in the above-mentioned background art, the present invention provides a digital asset management method, system, electronic device, storage medium and computer program product based on component identification coding.

[0007] The present invention provides a digital asset management method based on component identification coding, and the method includes the following steps:

[0008] Encode each component in the BIM model according to a preset coding method, and associate the design data and construction data corresponding to the component with the coding;

[0009] Receive the first real-time construction data of the physical highway uploaded by the on-site terminal, and analyze the component construction information of the current construction project of the physical highway according to the first real-time construction data;

[0010] Predict the qualified probability of the component according to the component construction information, and obtain the update delay duration according to the comparison of the qualified probability of the component;

[0011] When the update delay duration is reached, if the second real-time construction data belonging to the same component and the same construction stage as the first real-time construction data is not received, update the BIM model based on the first real-time construction data; otherwise, update the BIM model based on the second real-time construction data; thereby gradually generating a digital twin highway corresponding to the physical highway, that is, the digital asset.

[0012] Optionally, the preset coding method is:

[0013] In the design stage, use 7 strings to describe the component, and the strings are connected by an underscore "_". Each string represents a specific meaning; among them, the first string represents the road coding, which is determined when the project is approved; the second string represents the type of unit project; the third string represents the location of the unit project; the fourth string represents the left and right sub-frames, L for the left frame, R for the right frame, and W for the full frame; the fifth string represents the type of sub-project; the sixth string represents the location of the sub-project; the seventh string represents the component name, which is used to describe the specific component;

[0014] In the construction stage, just add a string "sequence code" after the design stage identification code. This sequence code is only used in the scenario where the component needs to be stratified, segmented and sectioned during construction.

[0015] Optionally, the analyzing the component construction information of the current construction project of the physical highway according to the first real-time construction data includes:

[0016] Semantic feature extraction is performed on the first real-time construction data using a semantic analysis algorithm, and the extracted semantic features include project scale, construction difficulty, construction technology, and construction environment complexity;

[0017] Vectorize the semantic features to obtain construction feature data, and use the construction feature data as the component construction information of the current construction project of the entity highway.

[0018] Optionally, the prediction of the component evaluation pass probability based on the component construction information includes:

[0019] Use an analysis model based on a deep learning algorithm to analyze and process the construction feature data to obtain a preliminary component evaluation pass probability; wherein, the analysis model is trained based on historical rework data of the same or similar components;

[0020] Use a semantic analysis algorithm to perform semantic analysis on the design data to obtain description information of the construction difficulty corresponding to the current construction component, and comprehensively determine the construction design difficulty according to each piece of description information;

[0021] Calculate the component evaluation pass probability based on the construction design difficulty and the preliminary component evaluation pass probability.

[0022] Optionally, the analysis model is constructed based on Transformer and includes an encoder part, a decoder part, and an output layer; wherein, the encoder part is composed of multiple encoders stacked, and each encoder contains a multi-head attention layer and a feed-forward neural network layer, with residual connection and layer normalization used between them.

[0023] The present invention also provides a digital asset management system based on component identification coding, and the system includes a processing module and a storage module; the processing module calls the computer program code stored in the storage module to perform the following steps:

[0024] Encode each component in the BIM model according to a preset coding method, and associate the design data and construction data corresponding to the component with the coding;

[0025] Receive the first real-time construction data of the entity highway uploaded by the on-site terminal, and analyze the first real-time construction data to obtain the component construction information of the current construction project of the entity highway;

[0026] Predict the component evaluation pass probability based on the component construction information, and obtain the update delay duration according to the component evaluation pass probability;

[0027] When the update delay duration is reached, if the second real-time construction data belonging to the same component and the same construction stage as the first real-time construction data is not received, the BIM model is updated based on the first real-time construction data; otherwise, the BIM model is updated based on the second real-time construction data; thereby gradually generating a digital twin road corresponding to the physical road, that is, the digital asset.

[0028] The present invention also provides an electronic device, including: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory and executes the method described in any one of the previous items.

[0029] The present invention also provides a storage medium, on which a computer program is stored, and when the computer program is run by a processor, it executes the method described in any one of the previous items.

[0030] The present invention also provides a computer program product, which executes the method described in any one of the previous items when running.

[0031] The beneficial effects of the present invention are as follows: on the one hand, based on a suitable coding method, the association between each component in the BIM model and related data is realized, which is not only convenient for computer analysis and identification, but also facilitates subsequent positioning and searching by staff. On the other hand, the update mechanism of the digital twin road designed by the present invention takes into account the uncertainty and possible rework situations in the physical road construction process, avoiding the problems of frequent update and manual correction of the digital twin road caused by frequent rework, and ensuring the effectiveness and timeliness of the digital twin road update. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0033] Figure 1 is a schematic flowchart of a digital asset management method based on component identification coding disclosed in an embodiment of the present invention;

[0034] Figure 2 is a schematic structural diagram of an analysis model disclosed in an embodiment of the present invention;

[0035] Figure 3 is a schematic structural diagram of a digital asset management system based on component identification coding disclosed in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0036] The exemplary embodiments of the present invention will be described below in conjunction with the accompanying drawings. Various details of the embodiments of the present invention are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, descriptions of well-known functions and structures are omitted in the following description for clarity and conciseness.

[0037] Refer to Figure 1 As shown, an embodiment of the present invention discloses a digital asset management method based on component identification coding. The method includes the following steps:

[0038] S1, encode each component in the BIM model according to a preset coding method, and associate the design data and construction data corresponding to the component with the coding.

[0039] S2, receive the first real-time construction data of the physical highway uploaded by the on-site terminal, and analyze the component construction information of the current construction project of the physical highway according to the first real-time construction data.

[0040] In this step, various sensors, mobile devices or other data collection devices are deployed at the construction site of the physical highway. These devices will monitor and record various information of each component during the construction process of the physical highway in real time, such as construction progress, material usage, construction quality indicators, etc., to form the first real-time construction data, and then upload the first real-time construction data to the background management server. By receiving these data, the background management server can comprehensively grasp the construction status of each component of the physical highway at a certain moment. At the same time, the first real-time construction information will also include component construction information, including but not limited to project scale (i.e., component scale), construction difficulty, current construction stage, construction technology used, etc.

[0041] S3, predict the qualified probability of the component based on the component construction information, and obtain the update delay duration according to the qualified probability of the component.

[0042] In this step, after obtaining the component construction information, the qualified probability of the component currently under construction is predicted based on this information. The qualified probability of the component refers to the probability that the component currently under construction is rated as qualified at a stage or finally, that is, the likelihood of rework due to being rated as unqualified in the subsequent construction process. For example, if the component construction information shows that the construction technology of the component project is complex, the construction environment is harsh, or some new technologies are adopted, it may result in a lower qualified probability of the component.

[0043] According to the predicted qualified probability of the component, the update delay duration is obtained by comparison. The update delay duration is a strategic setting based on the predicted qualified probability of the component, aiming to avoid additional manual correction work caused by incorrect updates of the digital twin road due to rework during the construction of the physical road. If the predicted qualified probability of the component is low, a longer update delay duration is set, that is, the update of the digital twin road is not performed temporarily; otherwise, a shorter update delay duration is set to ensure that the digital twin road can reflect the construction situation of the physical road more timely.

[0044] S4. When the update delay duration is reached, if the second real-time construction data belonging to the same component and the same construction stage as the first real-time construction data is not received, the BIM model is updated based on the first real-time construction data; otherwise, the BIM model is updated based on the second real-time construction data; thereby gradually generating the digital twin road corresponding to the physical road, that is, the digital asset.

[0045] In this step, after the set update delay duration is reached, the background management server checks whether the second real-time construction data belonging to the same component and construction stage as the first real-time construction data is received. If not, it means that there is no new data during this period, that is, there is no rework situation. At this time, the BIM model (the model of the digital twin road) is directly updated based on the first real-time construction data, so that the digital twin road can reflect the latest state of the physical road. If the second real-time construction data is received, it means that there is updated information, that is, there may be a rework situation (overall rework or partial rework) in the current construction component. At this time, the BIM model will be updated based on the latest second real-time construction data, thereby gradually generating the digital twin road corresponding to the physical road.

[0046] On the one hand, the above solution of the present invention realizes the association of each component in the BIM model with relevant data based on a suitable coding method, which is not only convenient for computer analysis and identification, but also facilitates subsequent positioning and searching by staff. On the other hand, the update mechanism designed for the digital twin road of the present invention takes into account the uncertainty and possible rework situations during the construction of the physical road, avoiding the problems of frequent updates and manual corrections of the digital twin road caused by frequent rework, and ensuring the effectiveness and timeliness of the update of the digital twin road.

[0047] Optionally, the preset coding method is as follows:

[0048] In the design stage, 7 strings are used to describe the components. The strings are connected by an underscore "_", and each string represents a specific meaning. Among them, the 1st string represents the road code, which is determined when the project is approved; the 2nd string represents the type of unit project; the 3rd string represents the location of the unit project; the 4th string represents the left / right division, where L represents the left side, R represents the right side, and W represents the whole width; the 5th string represents the type of sub-project; the 6th string represents the location of the sub-project; the 7th string represents the component name, which is used to describe the specific component.

[0049] In the construction stage, only add a string "sequence code" after the design stage identification code. This sequence code is only used in scenarios where components need to be stratified, segmented, and sectioned during construction.

[0050] In this embodiment, the encoding of the present invention can not only uniquely identify components within the system, but also be interpreted by people for positioning and searching in the model, and can also become the encoding of digital assets.

[0051] The above preset encoding method is divided into the design stage and the construction stage. Among them, in the design stage, the 2nd string represents the type of unit project, and specific information can be queried in Table 1 below. The 3rd string represents the location of the unit project. For paragraph structures such as subgrade, pavement, and tunnel, the starting and ending pile numbers are used, and for structures such as bridges and culverts, the center pile number is used. The 5th string represents the type of sub-project, and specific details can be seen in Table 1 below. The 6th string represents the location of the sub-project. For subgrade, pavement, tunnel, etc., the starting and ending pile numbers are used, and for the lower structure of bridges, culverts, etc., the center pile number is used. The 7th string represents the component name, which is used to describe the specific component, such as "No. 3 pier, No. 3-1 pile foundation, No. 5 pier cap", etc., and a combination of numbers, symbols, and Chinese characters can be used.

[0052] For example:

[0053] S307_01_KXX+XXX.XX~KXX+XXX.XX_L_A_KXX+XXX.XX~KXX+XXX.XX_Component name; S307_01_KXX+XXX.XX_L_A_KXX+XXX.XX_Component name.

[0054] Table 1

[0055]

[0056]

[0057]

[0058] In the construction stage, only add a string "sequence code" after the design stage identification code. For example:

[0059] S307_01_KXX+XXX.XX~KXX+XXX.XX_L_A_KXX+XXX.XX~KXX+XXX.XX_Component Name_001; S307_01_KXX+XXX.XX_L_A_KXX+XXX.XX_Component Name_001.

[0060] Components that do not need to be split can directly use the design identification code. This continuous use method can not only ensure the uniqueness of the identification code but also be interpretable by people, accurately transmitting data from the design stage to the construction stage. Taking the identification code as a link can meet the requirement of digital data transfer between different links put forward in the "Opinions on Promoting the Digital Transformation of Highways and Accelerating the Development of Smart Highways" issued by the Ministry of Transport. The finally formed digital twin highway will be a digital asset with structured and standardized data.

[0061] Optionally, the component construction information of the current construction project of the physical highway obtained by analyzing the first real-time construction data includes:

[0062] Use a semantic analysis algorithm to extract semantic features from the first real-time construction data. The extracted semantic features include project scale, construction difficulty, construction technology, and construction environment complexity.

[0063] Perform vectorization processing on the semantic features to obtain construction feature data, and use the construction feature data as the component construction information of the current construction project of the physical highway.

[0064] In this embodiment, the semantic analysis algorithm is a technology that can understand the meaning of text or data. It can deeply mine the information in the data, such as algorithms based on the Bag of Words (BoW), Word2Vec, GloVe (Global Vectors for Word Representation), etc. The present invention uses a semantic analysis algorithm to extract semantic features related to component projects from the first real-time construction data (usually including both structural data and unstructured data), such as project scale (i.e., component scale), construction difficulty, construction technology, and construction environment complexity.

[0065] Among them, the project scale includes information such as highway length, width, number of lanes, bridge length and span, tunnel length and diameter, etc.

[0066] The construction difficulty includes information such as the topography and geomorphology of the construction site (such as mountains, plains, swamps, etc.), geological conditions (such as soft soil foundation, rock foundation, etc.), groundwater level, and surrounding building conditions.

[0067] The construction process includes information on specific construction techniques and operation procedures, such as "adopting the prefabrication and hoisting techniques of prestressed concrete beams", and different construction processes have different construction difficulties.

[0068] The complexity of the construction environment involves information such as meteorological data, surrounding traffic conditions, human environment, and the impact of construction on the surrounding environment. For example, if the first real-time construction data mentions that "heavy rain is expected during construction, and there are multiple residential areas nearby that need to coordinate the construction impact", this information will be used as the characteristics of the construction environment complexity.

[0069] After extracting the semantic features, in order to more conveniently perform subsequent calculations and processing on these features, it is necessary to vectorize them. This data representation form is conducive to more efficient processing by the computer in the future. At this point, the vectorized construction feature data is the component construction information of the currently constructed component.

[0070] Optionally, the predicting the qualified probability of the component according to the component construction information includes:

[0071] Using an analysis model based on a deep learning algorithm to analyze and process the construction feature data to obtain a preliminary qualified probability of the component evaluation; wherein, the analysis model is trained based on the historical rework data of the same or similar components;

[0072] Using a semantic analysis algorithm to perform semantic analysis on the design data to obtain descriptive information on the construction difficulty corresponding to the currently constructed component, and comprehensively determining the construction design difficulty according to each piece of the descriptive information;

[0073] Calculating the qualified probability of the component according to the construction design difficulty and the preliminary qualified probability of the component evaluation.

[0074] In this embodiment, as Figure 2 shown, an analysis model based on a deep learning algorithm is pre-constructed, and the analysis model is trained based on the historical rework data of the same or similar construction projects. During the training process, the model will learn the relationship between the construction feature data of different components and the actual rework situation. For example, learning the probability of rework occurrence in a component project under a certain component project scale, specific construction process, and construction environment complexity. When the construction feature data of the current component project is input, the model can predict a preliminary qualified probability of the component evaluation according to the previously learned pattern.

[0075] Next, a semantic analysis algorithm is used to perform semantic analysis on the design data to obtain descriptive information about the construction difficulty corresponding to the current construction component. The design data includes information such as the planning, design intent, and requirements of the component project. Through semantic analysis, information that affects the construction difficulty can be extracted from it, such as information about structural complexity, the use of special materials, special construction technical requirements, etc. This information will be extracted by the semantic analysis algorithm and comprehensively form descriptive information about the construction difficulty, that is, the construction design difficulty, which is used to characterize the magnitude of the construction difficulty of the current construction component analyzed from the perspective of the designer. It can be a specific characterization value or a difficulty level.

[0076] Among them, the construction design difficulty is comprehensively determined according to each of the described information. Specifically: if the described information belongs to the direct descriptive information of the construction difficulty, its evaluation value is set to the first value and the corresponding weighting coefficient is the first coefficient; if the described information belongs to the non-direct descriptive information of the construction difficulty, its evaluation value is set to the second value and the corresponding weighting coefficient is the second coefficient; among them, the first coefficient is greater than the second coefficient; and the non-direct descriptive information includes the magnitude of the error range higher than the conventional design standard; the weighted mean value is calculated based on each of the evaluation values and the weighting coefficients, and this weighted mean value is used as the construction design difficulty.

[0077] When designing a construction plan, designers usually respond to the importance and criticality of a construction project by reducing the error range, which indirectly indicates that the construction difficulty at this place is relatively large. In a few cases, they will directly indicate that the construction difficulty at this place is relatively large in the form of remarks, etc., but this indicates that the construction difficulty at this place is unusually large. Based on the above situation, the present invention evaluates the construction difficulty of each piece of descriptive information according to a preset evaluation method to obtain the corresponding evaluation value; then, the weighting coefficient of the evaluation value of the above direct descriptive information is set to a larger first coefficient, while the weighting coefficient of the evaluation value of the non-direct descriptive information is set to a smaller second coefficient. Finally, the weighted mean value of each evaluation value is calculated based on the above weighting coefficients, and this weighted mean value is used to represent the construction design difficulty considered by the designer. The above evaluation can be a rule-based evaluation. For example, when the direct descriptive information contains high-difficulty-related words such as "difficult" and "severe", and the error range in the non-direct descriptive information is much smaller than the conventional design standard (for example, only 75% of the conventional design standard), the evaluation value is set to high, which means a large construction difficulty and a high rework rate; otherwise, the evaluation value is set to low, which means a small construction difficulty and a low rework rate. It can also be implemented by a specific model, and the present invention does not make specific limitations on this.

[0078] Finally, the construction design difficulty obtained is used to correct the preliminary component evaluation qualified probability predicted above, and the final component evaluation qualified probability can be obtained. In this process, a correction coefficient can also be pre-matched from the control relationship according to the construction design difficulty, and then the correction coefficient is multiplied by the preliminary component evaluation qualified probability to obtain the corrected component evaluation qualified probability. For the control relationship between the correction coefficient and the construction design difficulty, for example: when the construction design difficulty is at a low level, the correction coefficient is 1; when the construction design difficulty is at a medium level, the correction coefficient is 1.2; when the construction design difficulty is at a high level, the correction coefficient is 1.5, and so on.

[0079] The component evaluation qualified probability predicted by the present invention comprehensively considers the actual situation and design requirements during the component construction process, provides a more reliable basis for the subsequent setting of the update delay duration and the update strategy of the digital twin highway, and helps to better balance the timeliness of the digital twin highway update and reduce the additional workload caused by the rework of the physical highway.

[0080] Optionally, the analysis model is constructed based on Transformer and includes an encoder part, a decoder part and an output layer; wherein, the encoder part is composed of a plurality of encoders stacked together, and each encoder includes a multi-head attention layer and a feed-forward neural network layer, and a residual connection and layer normalization are used between the two.

[0081] Transformer is a deep learning architecture based on the attention mechanism, which has powerful feature extraction and sequence modeling capabilities. The present invention preferably uses Transformer to construct the analysis model. The functions of each part of the analysis model are as follows:

[0082] A plurality of encoder layers are stacked together to form the encoder part of Transformer. Each encoder layer includes a multi-head attention layer and a feed-forward neural network layer, and a residual connection and layer normalization are used between them. In the analysis model, the encoder can gradually perform feature extraction and transformation on the input construction feature data, and gradually abstract out high-level features related to the component evaluation qualified probability. For example, the first layer focuses on the basic features of the component project, such as the project scale and the complexity of the construction environment, and as the number of layers increases, the subsequent layers may gradually fuse these features with the features of the construction difficulty and construction technology to form a more advanced representation.

[0083] Decoder part: The analysis model also inputs additional input information that needs to be considered, such as the construction plan for the subsequent stage, into the decoder part, such as Figure 2As shown in the figure. The decoder also includes multi-head attention, a feed-forward neural network, as well as residual connections and layer normalization. However, its attention mechanism considers the output from the encoder and the information of its own input to generate the final output.

[0084] Output layer: After being processed by multiple encoder layers, a linear layer is used to map the final feature vector into a single value, representing the qualified probability of the preliminary component assessment. The output of this linear layer passes through an activation function (such as the Sigmoid function) to limit the output value between 0 and 1 to represent the rework probability. For example, if the output is 0.7, it means the predicted qualified probability of the preliminary component assessment is 70%.

[0085] In addition, an improvement scheme is provided:

[0086] When it is detected that there is an input of construction plan information for the subsequent stage in the decoder part, determine whether the construction plan information belongs to a basic project or a non-basic project; if the construction plan information belongs to a non-basic project, clear the input construction plan information for the subsequent stage.

[0087] In this improvement scheme, the above-mentioned additional input information input to the decoder part can be information related to the current construction component project automatically identified by the on-site terminal based on the subsequent construction plan, or information manually fed back by on-site management personnel to the background management server. These information can only be used for predicting the qualified probability of component assessment when they are highly correlated with the current construction component project.

[0088] The present invention further sets to determine whether the input construction plan information for the subsequent stage belongs to a basic project or a non-basic project. Basic projects, for example, refer to roadbed construction information, street lamp layout information, intelligent device layout information, etc. that are highly correlated with design information, while non-basic projects, for example, refer to information with a very low correlation with design information, such as road surface cleaning after construction, road maintenance before acceptance, etc.

[0089] Refer to Figure 3 As shown in the figure, the embodiment of the present invention also discloses a digital asset management system based on component identification coding. The system includes a processing module 10 and a storage module 20; the processing module 10 calls the computer program code stored in the storage module 20 to perform the following steps:

[0090] Encode each component in the BIM model according to a preset coding method, and associate the design data and construction data corresponding to the component with the coding;

[0091] Receive the first real-time construction data of the physical highway uploaded by the on-site terminal, and analyze the component construction information of the current construction project of the physical highway based on the first real-time construction data;

[0092] Predict the qualified probability of the component based on the component construction information, and obtain the update delay duration according to the qualified probability of the component.

[0093] When the update delay duration is reached, if the second real-time construction data belonging to the same component and the same construction stage as the first real-time construction data is not received, update the BIM model based on the first real-time construction data; otherwise, update the BIM model based on the second real-time construction data; thereby gradually generating the digital twin road corresponding to the physical road, that is, the digital asset.

[0094] The above digital asset management system based on component identification coding of the present invention corresponds to the foregoing digital asset management method based on component identification coding. For the technical effects of the system, refer to the foregoing method and will not be elaborated here.

[0095] An embodiment of the present invention also discloses an electronic device, including: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory and executes the method as described in the foregoing embodiment.

[0096] An embodiment of the present invention also discloses a storage medium, on which a computer program is stored, and the computer program executes the method as described in the foregoing embodiment when run by a processor. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0097] An embodiment of the present invention also discloses a computer program product, which executes the method as described in the foregoing embodiment when running.

[0098] The preferred embodiments of the present invention have been described in detail above in conjunction with the accompanying drawings. However, the present invention is not limited to the specific details in the above embodiments. Within the scope of the technical concept of the present invention, various simple modifications can be made to the technical solutions of the present invention, and these simple modifications all fall within the protection scope of the present invention.

[0099] In addition, it should be noted that, in the various specific technical features described in the above specific embodiments, they can be combined in any appropriate manner without contradiction. To avoid unnecessary repetition, the present invention will not separately describe various possible combination manners.

[0100] Furthermore, any combination can be made among various different embodiments of the present invention, as long as it does not violate the idea of the present invention, and it should also be regarded as the content disclosed by the present invention.

Claims

1. A digital asset management method based on component identification coding, characterized in that: The method comprises the following steps: Encode each component in the BIM model according to a preset encoding method, and associate the design data and construction data corresponding to the component with the code; Receiving first real-time construction data of a physical highway uploaded by a field terminal, and obtaining component construction information of a current construction project of the physical highway according to analysis of the first real-time construction data; Predicting a component qualification probability according to the component construction information, and determining an update delay time according to the component qualification probability; When the update delay time is reached, if the second real-time construction data belonging to the same component and the same construction stage as the first real-time construction data is not received, the BIM model is updated based on the first real-time construction data; otherwise, the BIM model is updated based on the second real-time construction data; thereby gradually generating a digital twin highway corresponding to the physical highway, namely the digital asset.

2. A digital asset management method based on component identification coding according to claim 1, characterized in that: in, The preset encoding method is: In the design stage, 7 character strings are used to describe the components. The character strings are connected by underscores "_", and each character string represents a specific meaning. Among them, the first character string represents the road code, which is determined when the project is established; the second character string represents the unit project type; the third character string represents the unit project location; the fourth character string represents the left and right sections, L for the left section, R for the right section, and W for the whole section; the fifth character string represents the sub-section project type; the sixth character string represents the sub-section project location; the seventh character string represents the component name, which is used to describe the specific component; During the construction phase, just add a string "sequence code" after the design phase identification code. This sequence code is only used in scenarios where components need to be layered, segmented and divided during construction.

3. A digital asset management method based on component identification coding according to claim 1, characterized in that: The component construction information of the current construction project of the physical highway is obtained according to the analysis of the first real-time construction data, including: Using a semantic analysis algorithm to extract semantic features from the first real-time construction data, the extracted semantic features include project scale, construction difficulty, construction technology, and construction environment complexity; Vectorization is performed on the semantic features to obtain construction feature data, and the construction feature data is used as the component construction information of the current construction project of the physical highway.

4. A digital asset management method based on component identification coding according to claim 3, characterized in that: The component qualification probability is predicted based on the component construction information, including: Using an analysis model based on a deep learning algorithm to analyze and process the construction characteristic data to obtain a preliminary component qualification probability; wherein the analysis model is trained based on historical rework data of the same or similar components; Using a semantic analysis algorithm to perform semantic analysis on the design data, obtain descriptive information of the construction difficulty corresponding to the current construction component, and comprehensively determine the construction design difficulty based on each of the descriptive information; The component assessment pass probability is calculated based on the construction design difficulty and the preliminary component assessment pass probability.

5. A digital asset management method based on component identification coding according to claim 4, characterized in that: The analysis model is built based on Transformer, including an encoder part, a decoder part and an output layer; wherein the encoder part is composed of multiple encoder stacks, and each encoder contains a multi-head attention layer and a feedforward neural network layer, and residual connections and layer normalization are used between the two.

6. A digital asset management system based on component identification coding, the system comprising a processing module and a storage module; characterized in that: The processing module calls the computer program code stored in the storage module to perform the following steps: Encode each component in the BIM model according to a preset encoding method, and associate the design data and construction data corresponding to the component with the code; Receiving first real-time construction data of a physical highway uploaded by a field terminal, and obtaining component construction information of a current construction project of the physical highway according to analysis of the first real-time construction data; Predicting a component qualification probability according to the component construction information, and determining an update delay time according to the component qualification probability; When the update delay time is reached, if the second real-time construction data belonging to the same component and the same construction stage as the first real-time construction data is not received, the BIM model is updated based on the first real-time construction data; otherwise, the BIM model is updated based on the second real-time construction data; thereby gradually generating a digital twin highway corresponding to the physical highway, namely the digital asset.

7. A digital asset management system based on component identification coding according to claim 6, characterized in that: in, The preset encoding method is: In the design stage, 7 character strings are used to describe the components. The character strings are connected by underscores "_", and each character string represents a specific meaning. Among them, the first character string represents the road code, which is determined when the project is established; the second character string represents the unit project type; the third character string represents the unit project location; the fourth character string represents the left and right sections, L for the left section, R for the right section, and W for the whole section; the fifth character string represents the sub-section project type; the sixth character string represents the sub-section project location; the seventh character string represents the component name, which is used to describe the specific component; During the construction phase, just add a string "sequence code" after the design phase identification code. This sequence code is only used in scenarios where components need to be layered, segmented and divided during construction.

8. An electronic device, comprising: A memory storing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1-5.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is executed.

10. A computer program product, characterized in that: When the computer program product is run, the method according to any one of claims 1 to 5 is executed.

Images