Construction project archive management method and system based on artificial intelligence

Abstract

The present disclosure relates to a construction project archive management method and system based on artificial intelligence. The method comprises: after performing text sentence granular semantic coding on the acquired construction project archive to be archived, inputting a semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of semantic coding vectors of enhanced description sentences of the construction project document to be archived; performing contextual semantic understanding on the sequence of semantic coding vectors of enhanced description sentences of the construction project document to be archived to obtain a global text semantic coding vector of the construction project document to be archived, and then determining the type of the construction project archive to be archived, and automatically archiving the construction project archive to be archived. In this way, the type of the construction project archive to be archived can be automatically identified, and automatically archived based on the type of the archive, so as to realize the intelligent management of the construction project archive.

Description

Technical Field

[0001] The present disclosure relates to the technical field of archive management, and in particular, to a construction project archive management method and system based on artificial intelligence. Background Art

[0002] With the rapid development of modern construction industry, construction project archive management has become an indispensable part of project management. These archives not only contain key information such as the design, construction, and supervision of engineering projects, but also have important significance for the monitoring of engineering quality, post-maintenance, and query of historical data.

[0003] However, the traditional archive management method has many shortcomings, such as low efficiency of manual classification and filing, difficulty in information retrieval, and difficulty in adapting to the growing amount of engineering data. Therefore, an intelligent construction project archive management method and system is expected. Summary of the invention

[0004] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides a construction project archive management method based on artificial intelligence, the method comprising:

[0006] Obtain construction project files to be archived;

[0007] Performing text sentence granularity semantic coding on the construction engineering archive to be archived to obtain a sequence of semantic coding vectors of description sentences of the construction engineering document to be archived;

[0008] Inputting the sequence of semantic coding vectors of the description sentences of the construction engineering document to be archived into a semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of enhanced semantic coding vectors of the description sentences of the construction engineering document to be archived;

[0009] Performing contextual semantic understanding on the sequence of semantic coding vectors of description sentences of the enhanced construction engineering document to be archived to obtain a global text semantic coding vector of the construction engineering document to be archived;

[0010] Based on the global text semantic coding vector of the construction project document to be archived, the type of the construction project archive to be archived is determined, and the construction project archive to be archived is automatically archived.

[0011] Optionally, the construction project archives to be archived are semantically encoded at the text sentence granularity to obtain a sequence of semantic encoding vectors of description sentences of the construction project documents to be archived, including: extracting a text portion from the construction project archives to be archived to obtain a text portion of the construction project archives to be archived; performing sentence processing on the text portion of the construction project archives to be archived to obtain a sequence of description sentences of the construction project documents to be archived; and passing the sequence of description sentences of the construction project documents to be archived through a sentence semantic encoder to obtain a sequence of semantic encoding vectors of description sentences of the construction project documents to be archived.

[0012] Optionally, the sentence semantic encoder includes an embedding layer and a BERT model.

[0013] Optionally, the sequence of semantic coding vectors of the construction project document description sentences to be archived is input into a semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of enhanced semantic coding vectors of the construction project document description sentences to be archived, including: quantifying the semantic relevance and semantic distance between the semantic coding vectors of the construction project document description sentences to be archived and other semantic coding vectors of the construction project document description sentences to be archived in the sequence of semantic coding vectors of the construction project document description sentences to be archived to obtain a sequence of sentence-granularity semantically-related construction project document description feature vectors to be archived containing semantic distance information; taking the mean vector of the sequence of sentence-granularity semantically-related construction project document description feature vectors to be archived containing semantic distance information to obtain the enhanced semantic coding vectors of the construction project document description sentences to be archived.

[0014] Optionally, the semantic correlation and semantic distance between the semantic coding vector of the construction engineering document description sentence to be archived and the semantic coding vectors of other construction engineering document description sentences to be archived in the sequence of semantic coding vectors of the construction engineering document description sentence to be archived are quantified to obtain a sequence of sentence-granularity semantically-related construction engineering document description feature vectors to be archived containing semantic distance information, including: calculating the semantic similarity between the semantic coding vector of the construction engineering document description sentence to be archived and the semantic coding vectors of other construction engineering document description sentences to be archived in the sequence of semantic coding vectors of the construction engineering document description sentence to be archived to obtain M semantic similarities; calculating the number of feature vectors separated between the semantic coding vector of the construction engineering document description sentence to be archived and the semantic coding vectors of other construction engineering document description sentences to be archived in the sequence of semantic coding vectors of the construction engineering document description sentence to be archived to obtain M separation numbers; for each of the semantic similarities and each of the separation numbers, calculating the product of the semantic coding vector of the construction engineering document description sentence to be archived and the semantic similarity and dividing it by the separation number to obtain the sequence of sentence-granularity semantically-related construction engineering document description feature vectors to be archived containing semantic distance information.

[0015] Optionally, the semantic similarity between the semantic coding vector of the construction project document description sentence to be archived and the semantic coding vectors of other construction project document description sentences to be archived in the sequence of semantic coding vectors of the construction project document description sentences to be archived is calculated to obtain M semantic similarities, including: calculating the cosine similarity between the semantic coding vector of the construction project document description sentence to be archived and the semantic coding vectors of other construction project document description sentences to be archived in the sequence of semantic coding vectors of the construction project document description sentences to be archived to obtain the M semantic similarities.

[0016] Optionally, contextual semantic understanding is performed on the sequence of semantic coding vectors of the description sentences of the enhanced construction project documents to be archived to obtain the global text semantic coding vector of the construction project documents to be archived, including: passing the sequence of semantic coding vectors of the description sentences of the enhanced construction project documents to be archived through a context encoder based on a converter structure to obtain the global text semantic coding vector of the construction project documents to be archived.

[0017] Optionally, the sequence of the enhanced semantic coding vectors of the description sentences of the construction project documents to be archived is passed through a context encoder based on a converter structure to obtain a global text semantic coding vector of the construction project documents to be archived, including: using the context encoder based on the converter structure to perform global context semantic coding on the sequence of the enhanced semantic coding vectors of the description sentences of the construction project documents to be archived to obtain a plurality of feature vectors of the construction project documents to be archived; and, cascading the plurality of feature vectors of the construction project documents to be archived to obtain the global text semantic coding vector of the construction project documents to be archived.

[0018] Optionally, based on the global text semantic coding vector of the construction project document to be archived, the type of the construction project archive to be archived is determined, and the construction project archive to be archived is automatically archived, including: passing the global text semantic coding vector of the construction project document to be archived through a classifier-based archive classifier to obtain a classification result, and the classification result is used to represent the type label to which the construction project archive to be archived belongs; based on the classification result, the construction project archive to be archived is automatically archived.

[0019] In a second aspect, the present disclosure provides a construction project archive management system based on artificial intelligence, the system comprising:

[0020] The project archive acquisition module is used to obtain the construction project archives to be archived;

[0021] A text sentence granularity semantic encoding module, used for performing text sentence granularity semantic encoding on the construction engineering archive to be archived to obtain a sequence of semantic encoding vectors of description sentences of the construction engineering document to be archived;

[0022] A semantic enhancement module, used for inputting the sequence of semantic coding vectors of the description sentences of the construction engineering document to be archived into a semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of enhanced semantic coding vectors of the description sentences of the construction engineering document to be archived;

[0023] A context semantic understanding module, used for performing context semantic understanding on the sequence of semantic coding vectors of description sentences of the enhanced construction engineering document to be archived to obtain a global text semantic coding vector of the construction engineering document to be archived;

[0024] The file type determination module is used to determine the type of the construction project file to be archived based on the global text semantic coding vector of the construction project document to be archived, and automatically archive the construction project file to be archived.

[0025] The above technical solution is adopted, after the acquired construction engineering archives to be archived are semantically encoded at the text sentence granularity, a semantic enhancer based on semantic relevance and semantic distance is input to obtain a sequence of semantic encoding vectors of enhanced description sentences of construction engineering documents to be archived; contextual semantic understanding is performed on the sequence of semantic encoding vectors of enhanced description sentences of construction engineering documents to be archived to obtain the global text semantic encoding vector of the construction engineering document to be archived, and then the type of the construction engineering archives to be archived is determined, and the construction engineering archives to be archived are automatically archived. In this way, the type of the construction engineering archives to be archived can be automatically identified, and automatically archived based on the type of the archives, so as to realize the intelligent management of construction engineering archives.

[0026] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:

[0028] Figure 1 It is a flowchart of a construction project archive management method based on artificial intelligence according to an exemplary embodiment.

[0029] Figure 2 It is a block diagram of a construction project archive management system based on artificial intelligence according to an exemplary embodiment.

[0030] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment.

[0031] Figure 4It is an application scenario diagram of a construction project archive management method based on artificial intelligence according to an exemplary embodiment. DETAILED DESCRIPTION

[0032] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0033] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0034] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0035] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0036] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0037] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0038] In order to solve the above problems, the present disclosure provides a construction project archive management method and system based on artificial intelligence, which performs text sentence granular semantic coding on the acquired construction project archive to be archived, inputs a semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of semantic coding vectors of enhanced description sentences of the construction project document to be archived; performs contextual semantic understanding on the sequence of semantic coding vectors of enhanced description sentences of the construction project document to be archived to obtain the global text semantic coding vector of the construction project document to be archived, and then determines the type of the construction project archive to be archived, and automatically archives the construction project archive to be archived. In this way, the type of the construction project archive to be archived can be automatically identified, and automatically archived based on the type of the archive, so as to realize the intelligent management of construction project archives.

[0039] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0040] Figure 1 is a flowchart of a construction project archive management method based on artificial intelligence according to an exemplary embodiment, such as Figure 1 As shown, the method includes:

[0041] Step 101, obtaining the construction project files to be archived;

[0042] Step 102: Performing text sentence granularity semantic coding on the construction engineering archive to be archived to obtain a sequence of semantic coding vectors of description sentences of the construction engineering document to be archived;

[0043] Step 103, inputting the sequence of semantic coding vectors of the description sentences of the construction engineering document to be archived into a semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of enhanced semantic coding vectors of the description sentences of the construction engineering document to be archived;

[0044] Step 104: performing contextual semantic understanding on the sequence of semantic coding vectors of description sentences of the enhanced construction engineering document to be archived to obtain a global text semantic coding vector of the construction engineering document to be archived;

[0045] Step 105: Determine the type of the construction project archive to be archived based on the global text semantic coding vector of the construction project document to be archived, and automatically archive the construction project archive to be archived.

[0046] In response to the above technical problems, the technical concept of the present application is to use natural language processing technology and artificial intelligence technology to perform sentence-granularity-based text semantic encoding and text semantic understanding analysis on the text part of the archived construction project archives, and introduce a semantic enhancement mechanism to optimize the expression of the text semantic features of the archived construction project documents. In this way, after the optimized text sentence-granularity semantic features are subjected to contextual semantic association analysis, the type of the archived construction project archives is automatically identified, and automatic archiving is performed based on the type of archives, so as to realize intelligent management of construction project archives.

[0047] Based on this, in the technical solution of the present application, first, the construction project archives to be archived are obtained; and the text part is extracted from the construction project archives to be archived to obtain the text part of the construction project archives to be archived. Among them, the construction project archives to be archived are various records and certificates generated during the implementation of the project, which are crucial to ensuring the quality and compliance of the project, as well as subsequent maintenance, auditing and historical record inquiries. In actual application scenarios, the construction project archives to be archived can be design documents such as architectural design plans, structural calculation books, and water supply and drainage designs, or they can be construction records such as construction logs, construction schedules, and construction quality inspection records. Considering that text is usually the main carrier of information in construction project archives, extracting the text part can facilitate subsequent information processing and analysis.

[0048] Since in text data, sentences are usually the basic units for expressing complete ideas. In the technical solution of the present application, the text part of the construction engineering archive to be archived is processed by sentence segmentation so as to capture and understand the semantic expression of the document in the future, so as to obtain a sequence of description sentences of the construction engineering document to be archived. It is worth mentioning that through sentence segmentation, continuous text information can be structured so that each sentence can be processed as an independent information unit. After obtaining the sequence of description sentences of the construction engineering document to be archived, since it cannot be directly read and recognized by a computer, it is naturally expected that the sequence of description sentences of the construction engineering document to be archived is semantically encoded to understand the semantic meaning contained therein. In an embodiment of the present application, the sequence of description sentences of the construction engineering document to be archived is passed through a sentence semantic encoder to obtain a sequence of semantic encoding vectors of the description sentences of the construction engineering document to be archived. More specifically, the sentence semantic encoder includes an embedding layer (Embedding Layer) and a BERT (Bidirectional Encoder Representations from Transformers) model.

[0049] In one embodiment of the present disclosure, text sentence granularity semantic encoding is performed on the construction project archive to be archived to obtain a sequence of semantic encoding vectors of description sentences of the construction project document to be archived, including: extracting a text portion from the construction project archive to be archived to obtain a text portion of the construction project archive to be archived; performing sentence processing on the text portion of the construction project archive to be archived to obtain a sequence of description sentences of the construction project document to be archived; and passing the sequence of description sentences of the construction project document to be archived through a sentence semantic encoder to obtain a sequence of semantic encoding vectors of description sentences of the construction project document to be archived.

[0050] The sentence semantic encoder includes an embedding layer and a BERT model.

[0051] Considering that the sentence semantic encoder is designed to process each of the description sentences of the construction engineering document to be archived, it may ignore the contextual information and contextual meaning of the sentence, resulting in ignoring the ambiguity and particularity of the sentence. Therefore, in the technical solution of the present application, the sequence of semantic encoding vectors of the description sentences of the construction engineering document to be archived is input into a semantic enhancer based on semantic relevance and semantic distance to optimize the semantic feature expression of each of the semantic encoding vectors of the description sentences of the construction engineering document to be archived, thereby obtaining a sequence of enhanced semantic encoding vectors of the description sentences of the construction engineering document to be archived.

[0052] Among them, in the semantic enhancer based on semantic relevance and semantic distance, by calculating the cosine similarity between the semantic coding vector of the construction engineering document description sentence to be archived and the semantic coding vectors of other construction engineering document description sentences to be archived in the sequence of the semantic coding vector of the construction engineering document description sentence to be archived, the semantic similarity and correlation between other sentences and the current sentence can be quantified. At the same time, calculating the number of feature vectors between the semantic coding vector of the construction engineering document description sentence to be archived and the semantic coding vectors of other construction engineering document description sentences to be archived can introduce the sentence order, structure and distance relationship, which helps to maintain the context information of the sentence. Generally speaking, the correlation between sentences usually decreases as the distance increases, that is, the semantics of two sentences are close or the correlation is high, but the importance of this semantic correlation decreases as the distance between the two increases. According to this characteristic, the semantic enhancer based on semantic relevance and semantic distance fuses the semantic similarity feature and the semantic distance feature when capturing the context information of the sentence, thereby optimizing the expression of the semantic content, so that the distribution of semantic features is closer to the actual situation and the core content of the document.

[0053] In one embodiment of the present disclosure, the sequence of semantic coding vectors of the construction engineering document description sentences to be archived is input into a semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of enhanced semantic coding vectors of the construction engineering document description sentences to be archived, including: quantifying the semantic relevance and semantic distance between the semantic coding vectors of the construction engineering document description sentences to be archived and other semantic coding vectors of the construction engineering document description sentences to be archived in the sequence of semantic coding vectors of the construction engineering document description sentences to be archived to obtain a sequence of sentence-granularity semantically-related construction engineering document description feature vectors to be archived containing semantic distance information; taking the mean vector of the sequence of sentence-granularity semantically-related construction engineering document description feature vectors to be archived containing semantic distance information to obtain the enhanced semantic coding vectors of the construction engineering document description sentences to be archived.

[0054] Furthermore, in one embodiment of the present disclosure, the semantic correlation and semantic distance between the semantic coding vector of the construction engineering document description sentence to be archived and the semantic coding vectors of other construction engineering document description sentences to be archived in the sequence of the semantic coding vectors of the construction engineering document description sentence to be archived are quantified to obtain a sequence of sentence-granularity semantically-related construction engineering document description feature vectors to be archived containing semantic distance information, including: calculating the semantic similarity between the semantic coding vector of the construction engineering document description sentence to be archived and the semantic coding vectors of other construction engineering document description sentences to be archived in the sequence of the semantic coding vectors of the construction engineering document description sentence to be archived to obtain M semantic similarities; calculating the number of feature vectors separated between the semantic coding vector of the construction engineering document description sentence to be archived and the semantic coding vectors of other construction engineering document description sentences to be archived in the sequence of the semantic coding vectors of the construction engineering document description sentence to be archived to obtain M separation numbers; for each of the semantic similarities and each of the separation numbers, calculating the product of the semantic coding vector of the construction engineering document description sentence to be archived and the semantic similarity and dividing it by the separation number to obtain the sequence of sentence-granularity semantically-related construction engineering document description feature vectors to be archived containing semantic distance information.

[0055] Furthermore, in one embodiment of the present disclosure, the semantic similarity between the semantic coding vector of the construction project document description sentence to be archived and the semantic coding vectors of other construction project document description sentences to be archived in the sequence of semantic coding vectors of the construction project document description sentences to be archived is calculated to obtain M semantic similarities, including: calculating the cosine similarity between the semantic coding vector of the construction project document description sentence to be archived and the semantic coding vectors of other construction project document description sentences to be archived in the sequence of semantic coding vectors of the construction project document description sentences to be archived to obtain the M semantic similarities.

[0056] Specifically, the sequence of semantic coding vectors of the description sentences of the construction engineering document to be archived is input into the semantic enhancer based on semantic relevance and semantic distance according to the following semantic enhancement formula to obtain a sequence of enhanced semantic coding vectors of the description sentences of the construction engineering document to be archived; in one embodiment of the present disclosure, a semantic coding vector of the description sentence of the construction engineering document to be archived is introduced, wherein the semantic enhancement formula is:

[0057]

[0058] Among them, v i and v j are the i-th and j-th semantic coding vectors of the description sentences of the construction engineering document to be archived in the sequence of semantic coding vectors of the description sentences of the construction engineering document to be archived, respectively, f(v i , v j ) represents the cosine similarity between the semantic encoding vectors of the i-th and j-th construction engineering document description sentences to be archived, Count(v j →v i ) represents the number of feature vectors between the i-th and j-th semantic coding vectors of the description sentences of the construction engineering document to be archived, M represents the total number of feature vectors in the sequence of semantic coding vectors of the description sentences of the construction engineering document to be archived minus one, v i Represents the semantic encoding vector of the i-th enhanced description sentence of the construction engineering document to be archived.

[0059] Furthermore, the sequence of the semantic encoding vectors of the description sentences of the enhanced construction engineering document to be archived is passed through a context encoder based on a transformer structure to obtain a global text semantic encoding vector of the construction engineering document to be archived. That is, the global semantic information of the sequence of the semantic encoding vectors of the description sentences of the enhanced construction engineering document to be archived is integrated through the context encoder based on the transformer structure.

[0060] In one embodiment of the present disclosure, contextual semantic understanding is performed on the sequence of semantic coding vectors of description sentences of the enhanced construction project documents to be archived to obtain the global text semantic coding vector of the construction project documents to be archived, including: passing the sequence of semantic coding vectors of description sentences of the enhanced construction project documents to be archived through a context encoder based on a converter structure to obtain the global text semantic coding vector of the construction project documents to be archived.

[0061] Furthermore, in one embodiment of the present disclosure, the sequence of the enhanced semantic coding vectors of the description sentences of the construction project documents to be archived is passed through a context encoder based on a converter structure to obtain a global text semantic coding vector of the construction project documents to be archived, including: using the context encoder based on the converter structure to perform global context semantic coding on the sequence of the enhanced semantic coding vectors of the description sentences of the construction project documents to be archived to obtain a plurality of feature vectors of the construction project documents to be archived; and, cascading the plurality of feature vectors of the construction project documents to be archived to obtain the global text semantic coding vector of the construction project documents to be archived.

[0062] Then, the global text semantic coding vector of the construction engineering document to be archived is passed through a classifier-based archive classifier to obtain a classification result, and the classification result is used to represent the type label to which the construction engineering document to be archived belongs; and based on the classification result, the construction engineering document to be archived is automatically archived. In this way, after the global text semantic coding vector of the construction engineering document to be archived is mapped to a type label by the classifier, the document type of the construction engineering document to be archived is determined, which provides important support for the archiving work.

[0063] In one embodiment of the present disclosure, based on the global text semantic coding vector of the construction project document to be archived, the type of the construction project archive to be archived is determined, and the construction project archive to be archived is automatically archived, including: passing the global text semantic coding vector of the construction project document to be archived through a classifier-based archive classifier to obtain a classification result, and the classification result is used to represent the type label to which the construction project archive to be archived belongs; based on the classification result, the construction project archive to be archived is automatically archived.

[0064] In the technical solution of the present application, the semantic enhancer based on semantic relevance and semantic distance uses the semantic correlation and semantic span between the semantic coding vectors of the description sentences of the construction engineering documents to be archived in the sequence of the semantic coding vectors of the description sentences of the construction engineering documents to be archived to perform multi-dimensional semantic enhancement. However, this also causes the multi-dimensionality of the global interaction of the feature context to cause feature interaction disorder when the sequence of the enhanced semantic coding vectors of the description sentences of the construction engineering documents to be archived is passed through the context encoder based on the converter structure, resulting in local overflow features in the global text semantic coding vector of the construction engineering documents to be archived, thereby affecting the accuracy of the global text semantic coding vector of the construction engineering documents to be archived when it is classified by the classifier.

[0065] Preferably, the global text semantic encoding vector of the construction engineering document to be archived is passed through a classifier-based archive classifier to obtain a classification result, which includes the following steps:

[0066] Calculate the self-mean matrix and self-variance matrix of the global text semantic encoding vector of the construction engineering document to be archived, wherein the value of the (i, j)th position of the self-mean matrix is ​​the mean of the eigenvalue at the i-th position and the eigenvalue at the j-th position of the global text semantic encoding vector of the construction engineering document to be archived, and the value of the (i, j)th position of the self-variance matrix is ​​the variance of the eigenvalue at the i-th position and the eigenvalue at the j-th position of the global text semantic encoding vector of the construction engineering document to be archived;

[0067] Performing matrix multiplication of the transposed vector of the global text semantic coding vector of the construction engineering document to be archived as the row feature vector with the self-mean matrix to obtain a first intermediate vector and performing matrix multiplication of the self-variance matrix with the global text semantic coding vector of the construction engineering document to be archived to obtain a second intermediate vector;

[0068] calculating a point sum of the first intermediate vector and the transposed vector of the second intermediate vector to obtain a third intermediate vector;

[0069] Calculating the matrix product of the self-mean matrix and the self-variance matrix, and performing matrix multiplication on the transposed vector of the global text semantic encoding vector of the construction engineering document to be archived and the matrix product to obtain a fourth intermediate vector;

[0070] Calculating the point sum of the transposed vectors of the third intermediate vector and the fourth intermediate vector to obtain an optimized global text semantic encoding vector of the construction engineering document to be archived; and

[0071] The optimized global text semantic encoding vector of the construction engineering document to be archived is passed through a classifier-based archive classifier to obtain a classification result.

[0072] Based on this, the self-mean matrix and self-variance matrix of the group aggregation statistical evaluation of the local distribution of the feature value granularity of the global text semantic coding vector of the construction engineering document to be archived are used as the retrieval and response distribution enhancement of the global text semantic coding vector of the construction engineering document to be archived, and a reference-free distribution retrieval response framework based on the group aggregation feature distribution open domain of the global text semantic coding vector of the construction engineering document to be archived is constructed to avoid the distribution response redundancy caused by the local overflow characteristics of the global text semantic coding vector of the construction engineering document to be archived through response superposition, so as to realize the fidelity constraint related to the self-aggregation statistics of the response of the optimized global text semantic coding vector of the construction engineering document to be archived to the classification target domain, and improve the accuracy of the classification result obtained by the optimized global text semantic coding vector of the construction engineering document to be archived through the classifier-based archive classifier.

[0073] To sum up, by adopting the above scheme, by utilizing natural language processing technology and artificial intelligence technology, the text part of the construction project archives to be archived is subjected to sentence-granularity-based text semantic encoding and text semantic understanding analysis, and a semantic enhancement mechanism is introduced to optimize the expression of the text semantic features of the construction project documents to be archived. In this way, after the optimized text sentence-granularity semantic features are subjected to contextual semantic association analysis, the type of the construction project archives to be archived is automatically identified, and automatic archiving is performed based on the type of archives, so as to realize the intelligent management of construction project archives.

[0074] Figure 2 FIG. 1 is a block diagram of a construction project archive management system based on artificial intelligence according to an exemplary embodiment. Figure 2 As shown, the construction project archive management system 200 includes:

[0075] The project archive acquisition module 201 is used to acquire the construction project archive to be archived;

[0076] A text sentence granularity semantic coding module 202 is used to perform text sentence granularity semantic coding on the construction engineering archive to be filed to obtain a sequence of semantic coding vectors of description sentences of the construction engineering document to be filed;

[0077] The semantic enhancement module 203 is used to input the sequence of semantic coding vectors of the description sentences of the construction engineering document to be archived into a semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of enhanced semantic coding vectors of the description sentences of the construction engineering document to be archived;

[0078] A context semantic understanding module 204 is used to perform context semantic understanding on the sequence of semantic coding vectors of the description sentences of the enhanced construction engineering document to be archived to obtain a global text semantic coding vector of the construction engineering document to be archived;

[0079] The file type determination module 205 is used to determine the type of the construction project file to be archived based on the global text semantic coding vector of the construction project document to be archived, and automatically archive the construction project file to be archived.

[0080] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0081] like Figure 3 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0082] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0083] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0084] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0085] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0086] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0087] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0088] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0089] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a module does not limit the module itself in some cases. For example, a test parameter acquisition module may also be described as a "module for acquiring device test parameters corresponding to a target device".

[0090] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0091] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0092] Figure 4 FIG. 1 is an application scenario diagram of a construction project archive management method based on artificial intelligence according to an exemplary embodiment. Figure 4 As shown, in this application scenario, first, obtain the construction project archive to be archived (for example, Figure 4 Then, the acquired construction project archive to be archived is input into a server (for example, Figure 4 In S) shown in , the server is capable of processing the construction project archives to be archived based on an artificial intelligence-based construction project archive management algorithm to determine the type of the construction project archives to be archived, and automatically archive the construction project archives to be archived.

[0093] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0094] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0095] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims

1. A construction project archive management method based on artificial intelligence, characterized in that: include: Obtain construction project files to be archived; Performing text sentence granularity semantic coding on the construction engineering archive to be archived to obtain a sequence of semantic coding vectors of description sentences of the construction engineering document to be archived; Inputting the sequence of semantic coding vectors of the description sentences of the construction engineering document to be archived into a semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of enhanced semantic coding vectors of the description sentences of the construction engineering document to be archived; Performing contextual semantic understanding on the sequence of semantic coding vectors of description sentences of the enhanced construction engineering document to be archived to obtain a global text semantic coding vector of the construction engineering document to be archived; Determining the type of the construction project file to be filed based on the global text semantic coding vector of the construction project document to be filed, and automatically filing the construction project file to be filed; Based on the global text semantic coding vector of the construction project document to be archived, determining the type of the construction project file to be archived, and automatically archiving the construction project file to be archived, including: The global text semantic encoding vector of the construction engineering document to be archived is passed through a classifier-based archive classifier to obtain a classification result, wherein the classification result is used to indicate the type label to which the construction engineering archive to be archived belongs; Based on the classification result, automatically archiving the construction project archives to be archived; The global text semantic encoding vector of the construction engineering document to be archived is passed through a classifier-based archive classifier to obtain a classification result, including the following steps: Calculate the self-mean matrix and self-variance matrix of the global text semantic encoding vector of the construction engineering document to be archived, wherein the self-mean matrix The value of position is the first position of the global text semantic encoding vector of the construction engineering document to be archived. Position eigenvalue and The mean of the position eigenvalues, and the self-variance matrix The value of position is the first position of the global text semantic encoding vector of the construction engineering document to be archived. Position eigenvalue and The variance of the location eigenvalues; Performing matrix multiplication of the transposed vector of the global text semantic coding vector of the construction engineering document to be archived as the row feature vector with the self-mean matrix to obtain a first intermediate vector and performing matrix multiplication of the self-variance matrix with the global text semantic coding vector of the construction engineering document to be archived to obtain a second intermediate vector; calculating a point sum of the first intermediate vector and the transposed vector of the second intermediate vector to obtain a third intermediate vector; Calculating the matrix product of the self-mean matrix and the self-variance matrix, and performing matrix multiplication on the transposed vector of the global text semantic encoding vector of the construction engineering document to be archived and the matrix product to obtain a fourth intermediate vector; Calculating the point sum of the transposed vectors of the third intermediate vector and the fourth intermediate vector to obtain an optimized global text semantic encoding vector of the construction engineering document to be archived; and Passing the optimized global text semantic encoding vector of the construction engineering document to be archived through a classifier-based archive classifier to obtain a classification result; Inputting the sequence of semantic coding vectors of the description sentences of the construction engineering document to be archived into a semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of enhanced semantic coding vectors of the description sentences of the construction engineering document to be archived, including: Quantifying the semantic correlation and semantic distance between the semantic coding vector of the construction engineering document description sentence to be archived and the semantic coding vectors of other construction engineering document description sentences to be archived in the sequence of the semantic coding vectors of the construction engineering document description sentence to be archived to obtain a sequence of sentence-granular semantically related construction engineering document description feature vectors to be archived containing semantic distance information; Taking the mean vector of the sequence of sentence-granular semantically relevant construction engineering document description feature vectors to be archived containing semantic distance information to obtain the semantic encoding vector of the enhanced construction engineering document description sentence to be archived; Quantifying the semantic correlation and semantic distance between the semantic coding vector of the construction engineering document description sentence to be archived and the semantic coding vectors of other construction engineering document description sentences to be archived in the sequence of the semantic coding vectors of the construction engineering document description sentence to be archived to obtain a sequence of sentence-granular semantically related construction engineering document description feature vectors to be archived containing semantic distance information, including: Calculating the semantic similarity between the semantic coding vector of the construction engineering document description sentence to be archived and the semantic coding vectors of other construction engineering document description sentences to be archived in the sequence of the semantic coding vectors of the construction engineering document description sentences to be archived to obtain M semantic similarities; Calculating the number of feature vectors between the semantic coding vector of the construction engineering document description sentence to be archived and other semantic coding vectors of the construction engineering document description sentence to be archived in the sequence of the semantic coding vectors of the construction engineering document description sentence to be archived to obtain M spacing numbers; For each of the semantic similarities and each of the intervals, the product of the semantic encoding vector of the construction engineering document description sentence to be archived and the semantic similarity is calculated and then divided by the interval to obtain a sequence of sentence-granular semantically related construction engineering document description feature vectors to be archived containing semantic distance information; Performing contextual semantic understanding on the sequence of semantic coding vectors of description sentences of the enhanced construction engineering document to be archived to obtain a global text semantic coding vector of the construction engineering document to be archived, including: The sequence of semantic coding vectors of description sentences of the reinforced construction engineering document to be archived is passed through a context encoder based on a transformer structure to obtain the global text semantic coding vector of the construction engineering document to be archived.

2. The construction project archive management method based on artificial intelligence according to claim 1 is characterized in that: Performing text sentence granular semantic coding on the construction engineering archive to be archived to obtain a sequence of semantic coding vectors of description sentences of the construction engineering document to be archived, including: Extracting a text portion from the to-be-filed construction engineering archive to obtain a to-be-filed construction engineering archive text portion; Sentence processing is performed on the text portion of the construction project archive to be filed to obtain a sequence of description sentences of the construction project document to be filed; The sequence of description sentences of the construction engineering document to be archived is passed through a sentence semantic encoder to obtain a sequence of semantic encoding vectors of the description sentences of the construction engineering document to be archived.

3. The construction project archive management method based on artificial intelligence according to claim 2 is characterized in that: The sentence semantic encoder includes an embedding layer and a BERT model.

4. The construction project archive management method based on artificial intelligence according to claim 3 is characterized in that: Calculating the semantic similarity between the semantic coding vector of the construction engineering document description sentence to be archived and other semantic coding vectors of the construction engineering document description sentence to be archived in the sequence of the semantic coding vectors of the construction engineering document description sentence to be archived to obtain M semantic similarities, including: The cosine similarity between the semantic coding vector of the construction engineering document description sentence to be archived and other semantic coding vectors of the construction engineering document description sentence to be archived in the sequence of the semantic coding vectors of the construction engineering document description sentence to be archived is calculated to obtain the M semantic similarities.

5. The construction project archive management method based on artificial intelligence according to claim 4 is characterized in that: The sequence of the semantic coding vectors of the description sentences of the enhanced construction engineering document to be archived is passed through a context encoder based on a transformer structure to obtain the global text semantic coding vector of the construction engineering document to be archived, including: Using the context encoder based on the transformer structure, performing global context semantic encoding on the sequence of semantic encoding vectors of the description sentences of the enhanced construction engineering document to be archived to obtain multiple feature vectors of the construction engineering document to be archived; and The feature vectors of the multiple construction engineering documents to be archived are cascaded to obtain a global text semantic encoding vector of the construction engineering documents to be archived.

6. A construction project archive management system based on artificial intelligence, used to execute the construction project archive management method based on artificial intelligence as claimed in claim 1, characterized in that: include: The project archive acquisition module is used to obtain the construction project archives to be archived; A text sentence granularity semantic encoding module, used for performing text sentence granularity semantic encoding on the construction engineering archive to be archived to obtain a sequence of semantic encoding vectors of description sentences of the construction engineering document to be archived; A semantic enhancement module, used for inputting the sequence of semantic coding vectors of the description sentences of the construction engineering document to be archived into a semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of enhanced semantic coding vectors of the description sentences of the construction engineering document to be archived; A context semantic understanding module, used for performing context semantic understanding on the sequence of semantic coding vectors of description sentences of the enhanced construction engineering document to be archived to obtain a global text semantic coding vector of the construction engineering document to be archived; The file type determination module is used to determine the type of the construction project file to be archived based on the global text semantic coding vector of the construction project document to be archived, and automatically archive the construction project file to be archived.

Images