Construction rule judgment method, device and equipment based on knowledge graph

Abstract

The invention relates to the technical field of knowledge graphs, and discloses a construction rule judgment method, device and equipment based on a knowledge graph, and the method comprises the steps: obtaining construction rules, construction requirements and safety specifications of a general plane of a construction site, and building a basic rule database; expanding the basic rule database into a generalized rule database; preprocessing the generalized rule database, and standardizing a text format and an expression mode of each rule; performing feature extraction and reference classification on the preprocessed generalized rule database, and constructing a construction rule judgment knowledge graph; according to the received judgment conditions input by the user, retrieval is carried out in the construction rule judgment knowledge graph, judgment results including logic correctness, step feasibility and time sequence rationality are output, the judgment conditions input by the user are judged through the construction rule judgment knowledge graph, an effective management tool is provided for construction management, and the construction management efficiency is improved. And the management efficiency and the management quality are improved.

Description

Technical Field

[0001] The present invention relates to the field of knowledge graph technology, and specifically to a construction rule judgment method, device and equipment based on knowledge graph. Background Art

[0002] The work content involved in the general plan management of the construction site includes temporary land management, construction channel management, construction site excavation management, on-site construction electricity, construction water supply and drainage management, etc. Due to the large scale of the project and the long construction period, the general plan management of the project site is complicated, the work links are cross-linked, and many units are involved. At present, there is a lack of effective general plan management tools, which brings great difficulties to the general plan management of the site. It is easy to have problems such as non-intuitive construction process, complicated process, difficult process verification, and mutual interference, which leads to delays in construction period and increased costs. Summary of the invention

[0003] In view of this, the present invention provides a construction rule judgment method, device and equipment based on knowledge graph to solve the problem of difficulty in process verification in existing construction processes.

[0004] In a first aspect, the present invention provides a construction rule judgment method based on a knowledge graph, the method comprising:

[0005] Obtain the construction rules, construction requirements and safety specifications of the general plan of the construction site, and establish a basic rule database;

[0006] Expand the basic rule database into a generalized rule database;

[0007] Preprocess the generalized rule database to standardize the text format and expression of each rule;

[0008] Perform feature extraction and reference classification on the preprocessed generalized rule database, and build a knowledge graph for construction rule judgment;

[0009] According to the judgment conditions received from the user, a search is performed in the construction rule judgment knowledge graph, and the judgment results are output. The judgment results include logical correctness, step feasibility, and timing rationality.

[0010] The present invention expands and normalizes the basic rule database established according to the construction rules, construction requirements and safety specifications of the general plan of the construction site, and establishes a construction rule judgment knowledge graph. The construction rule judgment knowledge graph is used to judge the judgment conditions input by the user, thereby verifying the logical correctness of the judgment conditions, the feasibility of the steps and the rationality of the timing, so as to facilitate the general plan management of the construction site, provide effective management tools for construction management, and improve management efficiency and management quality.

[0011] In an optional implementation, establishing a basic rule database includes:

[0012] At least one of a temporal relationship, a logical relationship and a quantitative judgment condition is extracted from construction rules, construction requirements and safety specifications to establish a basic rule database.

[0013] The present invention extracts at least one of the temporal relationship, logical relationship and quantitative judgment condition from the construction rules, construction requirements and safety specifications when establishing the basic rule database, so as to judge the rationality, compliance and process logic of the overall plan construction.

[0014] In an optional implementation, the basic rule database is expanded into a generalized rule database, including:

[0015] Crawl relevant terms and use text extraction tools to convert the crawled relevant terms into text files;

[0016] Use the reference context extraction tool to identify the rules in the text file and obtain context text data;

[0017] The basic rule database is expanded into a generalized rule database according to the text files and context text data.

[0018] The present invention crawls relevant entries on the basis of the established basic rule database to rationally expand the basic rule database, so as to provide more comprehensive data support for plane construction management.

[0019] In an optional implementation, after obtaining the context text data, the method further includes:

[0020] Extract semantic keywords from contextual text data and crawl similar terms using network request tools;

[0021] The crawled similar terms are merged with the basic rule database and stored locally.

[0022] The present invention crawls similar rule terms according to context text data and merges the crawled similar terms with basic rule data to provide more comprehensive data support for plane construction management.

[0023] In an optional implementation, the generalized rule database is preprocessed to standardize the text format and expression of each rule, including:

[0024] Use document parsing tools to extract standardized entries and standardize the text format of each rule;

[0025] The string similarity comparison strategy is used to perform similarity matching between the keywords mentioned in each rule description and the reference documents, and the expression of each rule is standardized.

[0026] The present invention effectively increases the richness and dimensionality of knowledge graph establishment by normalizing the entries of the generalized rule database, thereby providing intelligent and digital technical support for plane construction.

[0027] In an optional implementation, feature extraction and reference classification are performed on the preprocessed generalized rule database, including:

[0028] Perform semantic similarity and keyword library extraction on the preprocessed generalized rule database;

[0029] The preprocessed generalized rule database is classified by using feature classifier.

[0030] The present invention performs semantic similarity and keyword library extraction on the generalized rule database to extract features that meet the similarity requirements, performs reference classification to reduce data redundancy and ensure data integrity, and provides data support for constructing a construction rule judgment knowledge graph.

[0031] In an optional implementation, constructing a construction rule judgment knowledge graph includes:

[0032] Use statistics to statistically merge the quantitative discriminant conditions, and merge descriptions with similar logical relationships or dependency relationships into the same rule entry;

[0033] A construction rule judgment knowledge graph is established with the merged rule entries as nodes and the logical relationships or dependency relationships between rules as edges.

[0034] The present invention performs statistical merging by utilizing statistical substitution to merge descriptions with similar logical relationships or dependency relationships into the same rule entry, thereby increasing the reliability of information and establishing a knowledge graph for construction rule judgment, so as to provide effective management tools for plane construction management personnel and further improve the management efficiency and quality of the plane.

[0035] In a second aspect, the present invention provides a construction rule judgment device based on a knowledge graph, the device comprising:

[0036] Establish a module to obtain the construction rules, construction requirements and safety specifications of the general plan of the construction site, and establish a basic rule database;

[0037] An expansion module, used to expand the basic rule database into a generalized rule database;

[0038] The preprocessing module is used to preprocess the generalized rule database and standardize the text format and expression of each rule;

[0039] A construction module is used to extract features and classify references from the preprocessed generalized rule database, and to construct a knowledge graph for construction rule judgment;

[0040] The judgment module is used to search the construction rule judgment knowledge graph according to the judgment conditions received from the user, and output the judgment results, which include logical correctness, step feasibility and timing rationality.

[0041] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the construction rule judgment method based on the knowledge graph of the above-mentioned first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0042] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the construction rule judgment method based on a knowledge graph according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 is a flow chart of a construction rule judgment method based on a knowledge graph according to an embodiment of the present invention;

[0045] Figure 2 It is a schematic diagram of the process of constructing a construction rule judgment knowledge graph according to an embodiment of the present invention;

[0046] Figure 3 It is a schematic diagram of the use of the construction rule judgment knowledge graph and user input and output according to an embodiment of the present invention;

[0047] Figure 4 is a schematic diagram of a construction rule judgment knowledge graph judgment software tool interface according to an embodiment of the present invention;

[0048] Figure 5 is a schematic diagram outputted when the construction rule judgment knowledge graph judgment software tool according to an embodiment of the present invention is used;

[0049] Figure 6 is a structural block diagram of a construction rule judgment device based on a knowledge graph according to an embodiment of the present invention;

[0050] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0052] According to an embodiment of the present invention, an embodiment of a construction rule judgment method based on a knowledge graph is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0053] In this embodiment, a construction rule judgment method based on knowledge graph is provided. Figure 1 is a flow chart of a construction rule judgment method based on a knowledge graph according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0054] Step S101, obtaining the construction rules, construction requirements and safety specifications of the general plan of the construction site, and establishing a basic rule database.

[0055] In an embodiment of the present invention, based on the general plan construction rules, construction requirement documents, safety specification documents and other materials of the construction site project, quantitative judgment conditions or logical relationships, front-end and back-end timing constraint relationships, etc. are extracted and summarized, and a basic rule database for the judgment rule algorithm is established, which can improve the accuracy of knowledge representation and the precision of retrieval.

[0056] Step S102: Expand the basic rule database into a generalized rule database.

[0057] In the embodiment of the present invention, the basic rule database is expanded, and relevant entries outside the network are crawled to expand the basic rule database into a generalized rule database.

[0058] Step S103, preprocessing the generalized rule database to standardize the text format and expression of each rule.

[0059] In the embodiment of the present invention, the generalized rule database is preprocessed, and the text format and expression method of each rule are standardized, and its key elements include: description, temporal relationship, logical relationship and quantitative judgment conditions.

[0060] Step S104, perform feature extraction and reference classification on the preprocessed generalized rule database, and construct a construction rule judgment knowledge graph.

[0061] In the embodiment of the present invention, the preprocessed generalized rule database is subjected to feature extraction and reference classification, and the extracted typical features include semantic similarity and keyword library extraction, using common feature classifiers such as support vector machine (SVM) and random forest. According to the feature extraction results and reference classification results, a construction rule judgment knowledge graph is constructed, and judgment is performed using the constructed construction rule judgment knowledge graph.

[0062] Step S105: search the construction rule judgment knowledge graph according to the judgment condition received from the user, and output the judgment result.

[0063] In the embodiment of the present invention, the user inputs an event description, and the event description input by the user should include at least one of a temporal relationship, a logical relationship, and a quantitative judgment condition. The event description input by the user is such as: after pouring the underground pipe gallery, a high-voltage pipeline is laid under the pipe gallery.

[0064] The construction rule judgment knowledge graph is used to automatically judge the logical correctness, step feasibility and timing rationality of the event description, and output the judgment results, which include logical correctness, step feasibility and timing rationality, and the output method is text prompt.

[0065] The knowledge graph-based construction rule judgment method provided in this embodiment expands and normalizes the basic rule database established according to the construction site master plan construction rules, construction requirements and safety specifications, and establishes a construction rule judgment knowledge graph, so as to use the construction rule judgment knowledge graph to judge the judgment conditions input by the user, thereby verifying the logical correctness of the judgment conditions, the feasibility of the steps and the rationality of the timing, so as to facilitate the management of the construction site master plan, provide effective management tools for construction management, and improve management efficiency and management quality.

[0066] In this embodiment, a construction rule judgment method based on a knowledge graph is provided, and the process includes the following steps:

[0067] Step S201, obtaining the construction rules, construction requirements and safety specifications of the general plan of the construction site, and establishing a basic rule database.

[0068] Specifically, the above step S201 includes:

[0069] Step S2011, extracting at least one of a temporal relationship, a logical relationship and a quantitative judgment condition from construction rules, construction requirements and safety specifications, and establishing a basic rule database.

[0070] In the embodiment of the present invention, when establishing the basic rule database, at least one of the temporal relationship, the logical relationship and the quantitative judgment condition is extracted from the construction rules, the construction requirements and the safety specifications, which is specifically explained as follows:

[0071] (1) Sequential relationship: It indicates the time sequence of the construction process. For example, the construction sequence of trenches and pipelines should be from bottom to top. Before a certain trench or pipeline is constructed, there should be no unconstructed items below it.

[0072] (2) Logical relationships: These represent the dependencies and constraints between construction procedures and processes, including predecessor and successor relationships. For example, temporary facilities need to be constructed, relocated, and demolished according to the schedule. Before demolishing temporary roads, the temporary buildings connected to them should be demolished first.

[0073] (3) Quantitative judgment conditions: These are construction rules that can be quantified and extracted, such as height limit, weight limit, and operating radius. For example, trenches and pipelines need to undergo a horizontal collision check before construction, and a horizontal spacing of more than 5 meters can meet construction requirements.

[0074] By extracting at least one of the temporal relationship, logical relationship and quantitative judgment condition from the construction rules, construction requirements and safety specifications when establishing the basic rule database, it is convenient to judge the rationality, compliance and process logic of the overall plan construction.

[0075] Step S202: Expand the basic rule database into a generalized rule database.

[0076] Specifically, the above step S202 includes:

[0077] Step S2021, crawling related terms, and using a text extraction tool to convert the crawled related terms into a text file.

[0078] Step S2022: using a reference context extraction tool to identify the rules in the text file to obtain context text data.

[0079] Step S2023, expanding the basic rule database into a generalized rule database according to the text file and the context text data.

[0080] In an embodiment of the present invention, after crawling external related terms on the Internet, a text extraction tool, such as iFlytek, Editpad software, etc., is used to convert the web page image containing the text terms into a text file (txt file), and parsCittool (a reference context extraction tool based on conditional random fields) is used to identify the rule semantics existing in the document, and all texts of a certain length in the context of keyword occurrence are extracted as context text data for rule description.

[0081] By crawling relevant entries based on the established basic rule database, the basic rule database can be rationally expanded to provide more comprehensive data support for plane construction management.

[0082] Step S2022a, extracting semantic keywords from the context text data, and crawling similar terms using a network request tool.

[0083] Step S2022b, merge the crawled similar terms and the basic rule database, and store them locally.

[0084] In an embodiment of the present invention, after obtaining the expanded context text data, semantic keywords are extracted from the text description of the context text data, and the request module in urllib of Python is used to crawl similar rule terms on the Internet. This is only an example and is not intended to be limiting. After crawling external similar terms on the Internet, the crawled similar terms and the basic rule database are merged and converted into a readable format of the Mysql database. A rule-based matching method such as a regularized matching re library is used for data preprocessing to realize local storage of the database.

[0085] It has been verified that using the WPSpdf-to-text tool + WPS javascript macro interface to automatically script and generate txt text files has been experimentally verified that using an automatic script to transfer txt format files can extract 5% more rule entries from the text in the subsequent process than using the python-docx library to transfer.

[0086] By crawling similar rule terms based on contextual text data and merging the crawled similar terms with basic rule data, more comprehensive data support is provided for plane construction management.

[0087] Step S203, preprocessing the generalized rule database to standardize the text format and expression of each rule.

[0088] Specifically, the above step S203 includes:

[0089] Step S2031, using a document parsing tool to perform standardized extraction of entries and standardize the text format of each rule.

[0090] Step S2032: Use a string similarity comparison strategy to perform similarity matching between the keywords mentioned in each rule description and the reference document, and standardize the expression of each rule.

[0091] In an embodiment of the present invention, the generalized rule database is preprocessed, and the ParsCit document parsing tool is used to perform standardized extraction of entries, and all entries containing a relevant construction rule and the number of corresponding reference context texts are obtained. The string similarity comparison strategy based on the difflib library in Python is used to compare the keyword information mentioned in the rule description with other document information on the Internet. If the similarity is higher than the threshold, it is considered a successful match. All successfully matched data entries are taken, and the keyword elements are extracted to obtain an unlabeled data set including "description, temporal relationship, logical relationship, and quantitative judgment conditions".

[0092] By normalizing the entries in the generalized rule database, the richness and dimensionality of the knowledge graph are effectively increased, thereby providing intelligent and digital technical support for plane construction.

[0093] Step S204, perform feature extraction and reference classification on the preprocessed generalized rule database, and construct a construction rule judgment knowledge graph.

[0094] Specifically, the feature extraction and reference classification of the preprocessed generalized rule database in the above step S204 includes:

[0095] Step S2041, performing semantic similarity and keyword library extraction on the preprocessed generalized rule database.

[0096] Step S2042: Use a feature classifier to perform reference classification on the preprocessed generalized rule database.

[0097] In the embodiment of the present invention, feature extraction is performed on the preprocessed generalized rule database, and the extracted typical features include semantic similarity and keyword library extraction. Semantic similarity calculation uses Doc2Vec text embedding method to automatically encode the rules and the content of the document where the rules are located, and then calculates the cosine similarity of the two encoded vectors for measurement. When the cosine value is close to 1, the angle tends to 0, indicating that the two vectors are more similar.

[0098] Using the PV-DBOW (Distributed Bag of Words version of Paragraph Vector) model, we extract continuous text with a fixed window size as training data. The window is continuously moved back until the entire rule entry is traversed to generate a large number of continuous text segments as training data. We use (e_i......e_(i+n)) to represent the sequence of continuous text segments, where n represents half the size of the window, i represents the current position of the window, and the model training encoding vector is represented as doc. We use the neural network model to train the randomly initialized fixed-length vectors of all keywords and the randomly initialized doc vectors of the same length. The loss function J is:

[0099]

[0100] Among them, N is the total length of the document, y i Represents the output of the second-to-last layer in the neural network at position i, y doc It is the second layer output corresponding to the initialization vector doc position.

[0101] The citation classification of the database can be performed using common feature classifiers such as support vector machines and random forests. During classification, considering the limited computing power of most devices, the DistilBERT model compressed from the BERT (Bidirectional Encoder Representation from Transformers, a pre-trained language representation model) model is used in the classification process.

[0102] By performing semantic similarity and keyword library extraction on the generalized rule database, features that meet the similarity requirements are extracted, and reference classification is performed to reduce data redundancy and ensure data integrity, providing data support for building a construction rule judgment knowledge graph.

[0103] Specifically, the construction rule judgment knowledge graph is constructed in the above step S204, including:

[0104] Step S2043: Statistically merge the quantitative discrimination conditions using statistics, and merge descriptions with similar logical relationships or dependency relationships into the same rule entry.

[0105] Step S2044, using the merged rule entries as nodes and the logical relationships or dependency relationships between the rules as edges, establish a construction rule judgment knowledge graph.

[0106] In an embodiment of the present invention, statistics are used instead of maximum, minimum, mean and other statistics to statistically merge the corresponding features of the quantitative judgment conditions, so that descriptions of the same or similar logical relationships or dependency relationships that appear multiple times in the rule base can be classified as the same rule entry, and the merged rule entries are used as nodes, and the logical relationships or dependency relationships between the rules are used as edges to construct a construction rule judgment knowledge graph to increase information reliability.

[0107] Step S205: search the construction rule judgment knowledge graph according to the judgment condition received from the user, and output the judgment result.

[0108] For details, please see Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.

[0109] As a specific application example of the embodiment of the present invention, Figure 2 As shown, the knowledge graph construction of the embodiment of the present invention is divided into the following five steps:

[0110] Step 1: Establish a basic discrimination rule algorithm database based on the quantitative discrimination conditions or logical relationships summarized and extracted from the current general plan construction rules, construction requirements, and safety specifications;

[0111] Step 2: crawl external data based on the semantic features of the basic database and expand the basic rule data into a generalized rule database;

[0112] Step 3: preprocess the generalized rule database to standardize the text format and expression of each rule. The key elements include: description, temporal relationship, logical relationship, and quantitative judgment conditions;

[0113] Step 4: Extract features and classify references from the database, build a knowledge graph for intelligent judgment of construction rules, and use statistics to replace statistics. Use maximum, minimum, mean and other statistics to statistically merge the corresponding features of the quantitative judgment conditions, so that descriptions of the same or similar logical relationships or dependency relationships that appear multiple times in the rule base can be classified as the same rule entry, thereby increasing information reliability.

[0114] Step 5: For the judgment conditions input by the user, quickly retrieve their associations from the knowledge graph, make rationality and logic judgments, and output the judgment results.

[0115] Based on the knowledge graph constructed in the above steps, develop software tools for construction rule judgment, such as Figure 3As shown in Figure 1, the knowledge graph is in the middle of the user's input and output. At the back end of the tool, the user provides 20 quantitative judgment conditions summarized and extracted from construction rules, construction requirements, and safety specifications. These 20 conditions should cover one of the following three categories:

[0116] (1) Temporal relationship, which indicates the time sequence of the construction process;

[0117] (2) Logical relationships, which represent the dependencies and constraints between construction procedures and processes, including predecessor or successor relationships;

[0118] (3) Quantitative judgment conditions, which represent construction rules that can be quantified and extracted, such as height limit, weight limit, operating radius, etc.

[0119] After that, the software tool will automatically crawl and expand the related and similar rule bases based on the above algorithm and build a knowledge graph. The software tool interface is as follows: Figure 4 shown.

[0120] When in use, the user enters a new event description, such as: laying high-voltage pipelines under the underground corridor after pouring. The software automatically determines the logical correctness of the time description, the feasibility of the steps, and the rationality of the timing, and outputs the judgment result, such as Figure 5 shown.

[0121] The knowledge graph-based construction rule judgment method provided in this embodiment performs statistical merging by using statistical substitution to merge descriptions with similar logical relationships or dependency relationships into the same rule entry, thereby increasing the reliability of information and establishing a construction rule judgment knowledge graph to provide effective management tools for plane construction management personnel, thereby further improving plane management efficiency and management quality.

[0122] The knowledge graph-based construction rule judgment method provided by the present invention aims to expand and standardize the content rules of the plant area master plan management, and establish a knowledge graph based on rule judgment for advance planning of the construction process, which is helpful for overall planning, overall arrangement, and orderly implementation of on-site master plan management related work, and to quickly discover, respond quickly, effectively solve, and provide timely feedback on master plan problems that occur on site.

[0123] By developing a dynamic knowledge graph for plant master plan construction, by inputting the rules, procedures, and processes related to plant master plan construction and combining dynamic simulation technology and verification algorithms, the rationality, compliance, and process logic of plant master plan construction can be judged and demonstrated, including the site leveling process, negative excavation process, underground facilities (pipelines, trenches, building foundations) construction process, and ground facilities (roads, pipe racks, buildings) construction process. In this way, the cross-influence of construction sequence, construction period, and space during on-site construction can be simulated, and the plant plan layout plan can be visualized in three dimensions and optimized and verified. This can provide intelligent and digital technical support for plant plan construction, and provide effective management tools for plant master plan managers to improve plant master plan management efficiency and management quality.

[0124] It has the following advantages:

[0125] (1) The master plan management of construction sites using knowledge graphs can help to quickly and intuitively preview, predict, and make rational decisions on events encountered during construction.

[0126] (2) Based on the construction rules input by the user, the construction rules can be retrieved, rationally expanded and standardized, providing intelligent and digital technical support for plant plan construction and effective management tools for plant plan managers to improve the efficiency and quality of plant plan management;

[0127] (3) Compared with the existing knowledge graph construction work, the semantic-based retrieval and reasonable expansion of the present invention effectively increase the richness and dimension of the knowledge graph;

[0128] (4) Compared with the existing intelligent rule judgment and retrieval methods, the present invention can provide intelligent and digital technical support for plant plan construction through three-dimensional visualization and optimization verification, and provide effective management tools for plant master plan management personnel to improve the efficiency and quality of plant master plan management.

[0129] In this embodiment, a construction rule judgment device based on a knowledge graph is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0130] This embodiment provides a construction rule judgment device based on knowledge graph, such as Figure 6 As shown, including:

[0131] A module 601 is established to obtain the construction rules, construction requirements and safety specifications of the general plan of the construction site and to establish a basic rule database.

[0132] The expansion module 602 is used to expand the basic rule database into a generalized rule database.

[0133] The preprocessing module 603 is used to preprocess the generalized rule database and standardize the text format and expression of each rule.

[0134] The construction module 604 is used to perform feature extraction and reference classification on the preprocessed generalized rule database and construct a construction rule judgment knowledge graph.

[0135] The judgment module 605 is used to search in the construction rule judgment knowledge graph according to the judgment conditions received from the user, and output the judgment results, which include logical correctness, step feasibility and timing rationality.

[0136] In some optional implementations, the establishing module 601 includes:

[0137] An establishment unit is used to extract at least one of a temporal relationship, a logical relationship and a quantitative judgment condition from construction rules, construction requirements and safety specifications to establish a basic rule database.

[0138] In some optional implementations, the expansion module 602 includes:

[0139] The crawling unit is used to crawl relevant entries and convert the crawled relevant entries into text files using text extraction tools.

[0140] The recognition unit is used to recognize the rules in the text file by using the reference context extraction tool to obtain context text data.

[0141] The expansion unit is used to expand the basic rule database into a generalized rule database according to the text file and the context text data.

[0142] In some optional embodiments, the device further comprises:

[0143] The extraction module is used to extract semantic keywords from contextual text data and crawl similar terms using network request tools.

[0144] The merging module is used to merge the crawled similar terms with the basic rule database and store them locally.

[0145] In some optional implementations, the preprocessing module 603 includes:

[0146] The first standardization unit is used to perform standardized extraction of entries using document parsing tools and to standardize the text format of each rule.

[0147] The second standardization unit is used to use a string similarity comparison strategy to perform similarity matching between the keywords mentioned in each rule description and the reference document, and standardize the expression of each rule.

[0148] In some optional implementations, the preprocessing module 603 further includes:

[0149] The extraction unit is used to extract semantic similarity and keyword library from the preprocessed generalized rule database.

[0150] The reference classification unit is used to perform reference classification on the preprocessed generalized rule database using a feature classifier.

[0151] In some optional implementations, the construction module 604 includes:

[0152] The merging unit is used to statistically merge the quantitative discrimination conditions using statistics, and merge the descriptions with similar logical relationships or dependency relationships into the same rule entry.

[0153] The construction unit is used to establish a construction rule judgment knowledge graph with the merged rule entries as nodes and the logical relationships or dependency relationships between the rules as edges.

[0154] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0155] The knowledge graph-based construction rule judgment device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0156] The embodiment of the present invention also provides a computer device having the above Figure 6 The construction rule judgment device based on knowledge graph is shown.

[0157] See also Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0158] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0159] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0160] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0161] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0162] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.

[0163] The input device 30 can receive input digital or character information and generate key signal input related to user settings and function control of the computer device, such as a touch screen, etc. The output device 40 can include a display device, etc.

[0164] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0165] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0166] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope of the present application.

Claims

1. A construction rule judgment method based on knowledge graph, characterized in that: The method comprises: Obtain the construction rules, construction requirements and safety specifications of the general plan of the construction site, and establish a basic rule database; Expanding the basic rule database into a generalized rule database; Preprocessing the generalized rule database to standardize the text format and expression of each rule; Perform feature extraction and reference classification on the preprocessed generalized rule database, and build a knowledge graph for construction rule judgment; According to the judgment conditions received from the user, a search is performed in the construction rule judgment knowledge graph, and a judgment result is output, which includes logical correctness, step feasibility, and timing rationality.

2. The method according to claim 1, characterized in that The establishing of the basic rule database comprises: At least one of a temporal relationship, a logical relationship and a quantitative judgment condition is extracted from the construction rules, construction requirements and safety specifications to establish a basic rule database.

3. The method according to claim 1, characterized in that The step of expanding the basic rule database into a generalized rule database includes: Crawl relevant terms and use text extraction tools to convert the crawled relevant terms into text files; Use the reference context extraction tool to identify the rules in the text file and obtain context text data; The basic rule database is expanded into a generalized rule database according to the text file and the context text data.

4. The method according to claim 3, characterized in that After obtaining the context text data, the method further includes: Extracting semantic keywords from the context text data and crawling similar terms using a network request tool; The crawled similar terms are merged with the basic rule database and stored locally.

5. The method according to claim 1, characterized in that: The preprocessing of the generalized rule database to standardize the text format and expression of each rule includes: Use document parsing tools to extract standardized entries and standardize the text format of each rule; The string similarity comparison strategy is used to perform similarity matching between the keywords mentioned in each rule description and the reference documents, and the expression of each rule is standardized.

6. The method according to claim 1, characterized in that The feature extraction and reference classification of the preprocessed generalized rule database includes: Perform semantic similarity and keyword library extraction on the preprocessed generalized rule database; The preprocessed generalized rule database is classified by reference using a feature classifier.

7. The method according to claim 2, characterized in that: The construction rule judgment knowledge graph is constructed, including: Use statistics to statistically merge the quantitative discriminant conditions, and merge descriptions with similar logical relationships or dependency relationships into the same rule entry; A construction rule judgment knowledge graph is established with the merged rule entries as nodes and the logical relationships or dependency relationships between rules as edges.

8. A construction rule judgment device based on knowledge graph, characterized in that: The device comprises: Establish a module to obtain the construction rules, construction requirements and safety specifications of the general plan of the construction site, and establish a basic rule database; An expansion module, used to expand the basic rule database into a generalized rule database; A preprocessing module, used to preprocess the generalized rule database and standardize the text format and expression of each rule; A construction module is used to extract features and classify references from the preprocessed generalized rule database, and to construct a knowledge graph for construction rule judgment; The judgment module is used to search the construction rule judgment knowledge graph according to the judgment conditions received from the user, and output the judgment results, which include logical correctness, step feasibility and timing rationality.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the construction rule judgment method based on the knowledge graph as described in any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the construction rule judgment method based on the knowledge graph as described in any one of claims 1 to 7.

Images