Automatic coding method and device for constructional engineering man-material-machine

Abstract

The invention relates to the technical field of computers, in particular to an automatic coding method and device for constructional engineering people, materials and machines. The method comprises the following steps: acquiring a man-material-machine data set, and carrying out attribute and attribute value identification on each man-material-machine data in the man-material-machine data set to obtain an attribute and an attribute value corresponding to each man-material-machine data; constructing an initial human-material-machine relation library with the attributes corresponding to the attribute values, and optimizing the initial relation library under the condition that the initial relation library meets classification optimization requirements to obtain an optimized human-material-machine relation library; and according to the attribute value of each piece of human-material-machine data in the human-material-machine relation library, generating a code corresponding to each piece of human-material-machine data. By adopting the scheme, human-material-machine coding which adapts to the digital era and has universality and expandability can be realized.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to an automatic coding method and device for construction engineering personnel, materials and machines. Background Art

[0002] The application of personnel, material and machine coding in the field of construction engineering is wide-ranging and frequent, involving the entire life cycle of project design, operation, maintenance, renovation and expansion. Different business processes are often called upon by each other, such as quotation, material management, etc. Therefore, the importance of personnel, material and machine coding is self-evident.

[0003] However, the human resources and machine coding standards in different regions and industries are inconsistent, resulting in a large number of current coding standards and different coding rules, which has caused great difficulties in the application of industry standards; in addition, the collection, accumulation and analysis of human resources and machine data can only be achieved through the conversion of different standards. The coding rules vary greatly, resulting in inconsistent human resources and machine coding, making it difficult to accumulate data and share information; secondly, the existing human resources and machine coding standards are more used to serve the manual identification of human resources and machines. For example, the human resources and machine coding with a fixed length that cannot be dynamically adjusted is used to serve natural persons. When the computer processes information, the current human resources and machine coding is too simple and cannot support complex logical operations and relational operations. It cannot fully cover the various attributes of human resources and machines. From an application perspective, there are great defects and deficiencies, and it cannot adapt to the identification of human resources and machines in the digital age. Summary of the invention

[0004] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the first purpose of the present disclosure is to propose an automatic coding method for construction engineering man-material-machine coding to achieve universal and scalable man-material-machine coding that adapts to the digital age.

[0006] The second objective of the present disclosure is to provide an automatic encoding device for construction engineering personnel, materials and machines.

[0007] A third objective of the present disclosure is to provide an electronic device.

[0008] A fourth objective of the present disclosure is to provide a computer-readable storage medium.

[0009] A fifth object of the present disclosure is to provide a computer program product.

[0010] To achieve the above-mentioned purpose, the first embodiment of the present disclosure proposes an automatic coding method for construction engineering personnel, materials and machines, including:

[0011] Obtaining a human-machine data set, and identifying the attributes and attribute values ​​of each human-machine data in the human-machine data set, to obtain the attributes and attribute values ​​corresponding to each human-machine data;

[0012] Constructing an initial human-material-machine relationship library corresponding to attributes and attribute values, and optimizing the initial relationship library when the initial relationship library meets the classification optimization requirements to obtain an optimized human-material-machine relationship library, wherein the human-material-machine relationship library includes a first association relationship between attributes and attribute values, and a second association relationship between attribute values ​​and attribute values;

[0013] According to the attribute value of each human-machine data in the human-machine-machine relationship library, a code corresponding to each human-machine-machine data is generated, wherein the code is composed of a code segment value corresponding to at least one code segment, the code segment corresponds to the attribute in the human-machine-machine relationship library one-to-one, the code segment value range corresponding to the code segment is determined by the number of attribute values ​​corresponding to the code segment in the human-machine-machine relationship library, and the code segment value is determined by the position of the attribute value in the code segment value range.

[0014] Optionally, obtaining a human-material-machine data set includes:

[0015] Collecting a set of personnel-related data from a data source, wherein the set of personnel-related data includes personnel-related data in at least one format;

[0016] Adopt the analysis method corresponding to the format to analyze the data related to personnel, materials and machines, and obtain the initial data set of personnel, materials and machines;

[0017] The initial data set of human, material and machine is preprocessed to obtain the human, material and machine data set.

[0018] Optionally, data preprocessing is performed on the initial data set of human, material and machine to obtain the human, material and machine data set, including:

[0019] Performing data cleaning on the initial data set of personnel, materials and machines to obtain the initial data set of personnel, materials and machines after data cleaning;

[0020] The initial data set of human, material and machine after data cleaning is normalized to obtain the human, material and machine data set.

[0021] Optionally, the initial data set of human resources and machines after data cleaning is normalized, including:

[0022] Classify the attribute values ​​corresponding to each attribute to obtain at least one category of attribute value set;

[0023] Determine the expression method corresponding to each attribute value in the attribute value set of each category, and obtain a set of non-standard expressions;

[0024] Determine a standardized expression corresponding to the attribute value set according to the set of non-standard expressions;

[0025] A correspondence library between a set of irregular expressions and standardized expressions is constructed, and the initial data set of human, material and machine after data cleaning is normalized according to the correspondence library.

[0026] Optionally, the attributes and attribute values ​​of each human-machine data in the human-machine data set are identified to obtain the attributes and attribute values ​​corresponding to each human-machine data, including:

[0027] Perform word segmentation processing on each human resource and machine data in the human resource and machine data set to obtain a word segmentation set corresponding to each human resource and machine data;

[0028] Perform named entity recognition on the word segmentation set to obtain the attributes corresponding to each human and machine data and the attribute values ​​corresponding to the attributes.

[0029] Optionally, named entity recognition is performed on the word segmentation set, including:

[0030] Determine the part-of-speech tag corresponding to each word in the word set, and mark the word according to the part-of-speech tag to obtain a marked word set;

[0031] Perform named entity recognition on the annotated word set.

[0032] Optionally, constructing an initial human-material-machine relationship library corresponding to attributes and attribute values ​​includes:

[0033] The initial graph database is constructed with attributes and attribute values ​​as nodes and the third relationship between attributes and attribute values ​​as edges;

[0034] The attribute values ​​are classified, and the hierarchical relationship between the attribute values ​​is constructed in the initial graph database according to the classification results, so as to obtain the initial human-material-machine relationship library corresponding to the human-material-machine data set.

[0035] Optionally, when the initial relationship library meets the classification optimization requirements, the initial relationship library is optimized to obtain an optimized human-material-machine relationship library, including:

[0036] Perform data mining on the attribute values ​​to obtain data mining results;

[0037] When the data mining results indicate that different attribute values ​​have a co-occurrence relationship in the same attribute, it is determined that the initial relationship library meets the classification optimization requirements, and the classification of attributes in the initial relationship library and the classification of attribute values ​​are optimized according to the data mining results to obtain an optimized human-material-machine relationship library.

[0038] Optionally, after obtaining the optimized human-material-machine relationship library, the method further includes:

[0039] Obtain updated data sets of personnel, materials and machines at preset intervals;

[0040] According to the personnel-material-machine update data set, update data corresponding to the personnel-material-machine update data set is added on the basis of the personnel-material-machine relationship library, wherein the update data includes update attributes and / or update attribute values.

[0041] To achieve the above-mentioned purpose, the second embodiment of the present disclosure proposes an automatic encoding device for construction engineering personnel, materials and machines, including:

[0042] The data identification unit is used to obtain a human-machine data set, and identify the attributes and attribute values ​​of each human-machine data in the human-machine data set to obtain the attributes and attribute values ​​corresponding to each human-machine data;

[0043] A relationship building unit is used to build an initial human-material-machine relationship library corresponding to attributes and attribute values, and optimize the initial relationship library when the initial relationship library meets the classification optimization requirements to obtain an optimized human-material-machine relationship library, wherein the human-material-machine relationship library includes a first association relationship between attributes and attribute values, and a second association relationship between attribute values ​​and attribute values;

[0044] The data encoding unit is used to generate a code corresponding to each human resource and machine data according to the attribute value of each human resource and machine data in the human resource and machine relationship library, wherein the code is composed of a code segment value corresponding to at least one code segment, the code segment corresponds to the attribute in the human resource and machine relationship library one by one, the code segment value range corresponding to the code segment is determined by the number of attribute values ​​corresponding to the code segment in the human resource and machine relationship library, and the code segment value is determined by the position of the attribute value in the code segment value range.

[0045] To achieve the above-mentioned purpose, a third aspect of the present disclosure provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0046] Memory stores computer-executable instructions;

[0047] The processor executes the computer-executable instructions stored in the memory to implement the method shown in any one of the first aspects above.

[0048] To achieve the above-mentioned objectives, an embodiment of the fourth aspect of the present disclosure proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method shown in any one of the above-mentioned first aspects.

[0049] To achieve the above-mentioned purpose, the fifth aspect of the present disclosure provides a computer program product, including a computer program, which implements the method shown in any one of the above-mentioned first aspects when executed by a processor.

[0050] In summary, the method, device, equipment and storage medium provided by the present disclosure obtains a set of human-machine data, and identifies the attributes and attribute values ​​of each human-machine data in the set of human-machine data to obtain the attributes and attribute values ​​corresponding to each human-machine data; constructs an initial human-machine relationship library corresponding to the attributes and attribute values, and optimizes the initial relationship library when the initial relationship library meets the classification optimization requirements to obtain an optimized human-machine relationship library; generates the code corresponding to each human-machine data according to the attribute value of each human-machine data in the human-machine relationship library. Therefore, human-machine coding that adapts to the digital age and has universality and scalability can be realized.

[0051] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The above and / or additional aspects and advantages of the present disclosure will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0053] Figure 1 A flowchart of an automatic coding method for construction engineering personnel, materials and machines provided by an embodiment of the present disclosure;

[0054] Figure 2 A schematic diagram of the structure of an automatic encoding device for construction engineering personnel, materials and machines provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0055] Embodiments of the present disclosure are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0056] The present disclosure is described in detail below with reference to specific embodiments.

[0057] In the first embodiment, if Figure 1 As shown, Figure 1 This is a flow chart of an automatic coding method for construction engineering personnel and equipment provided by an embodiment of the present disclosure. The method can be implemented by a computer program and can be run on a device for automatic coding of construction engineering personnel and equipment. The computer program can be integrated into an application or run as an independent tool application.

[0058] Among them, the automatic encoding device for construction engineering personnel and equipment can be an electronic device with an automatic encoding function for construction engineering personnel and equipment.

[0059] Among them, the automatic encoding method for construction engineering personnel, materials and machines can be executed by electronic equipment.

[0060] For example, the automatic coding method for construction engineering personnel and equipment includes the following steps:

[0061] S101, obtaining a human-machine data set, and identifying the attributes and attribute values ​​of each human-machine data in the human-machine data set to obtain the attributes and attribute values ​​corresponding to each human-machine data;

[0062] According to some embodiments, the human-material-machine data refers to human-material-machine data. The human-material-machine data set refers to a set formed by at least one human-material-machine data.

[0063] In some embodiments, an attribute refers to a characteristic, property or feature of a human, material or machine, and an attribute value refers to a specific manifestation of the attribute.

[0064] S102, constructing an initial human-material-machine relationship library corresponding to attributes and attribute values, and optimizing the initial relationship library when the initial relationship library meets the classification optimization requirements to obtain an optimized human-material-machine relationship library;

[0065] According to some embodiments, the initial human-material-machine relationship library includes a third association relationship between attributes and attribute values, and the library includes a fourth association relationship between attributes and attribute values.

[0066] In some embodiments, the classification optimization requirement refers to a requirement used when determining whether the initial relationship library can be optimized. The classification optimization requirement does not specifically refer to a fixed requirement, and the classification optimization requirement can be adjusted according to actual application scenarios.

[0067] According to some embodiments, optimizing the initial relationship library includes optimizing the third association relationship between attributes and attribute values, and the fourth association relationship between attributes and attribute values ​​in the library, to obtain the optimized first association relationship between attributes and attribute values, and the second association relationship between attribute values ​​and attribute values.

[0068] In some embodiments, the optimized human-material-machine relationship library includes a first association relationship between attributes and attribute values, and a second association relationship between attribute values ​​and attribute values.

[0069] S103, generating a code corresponding to each human resource and machine data according to the attribute value of each human resource and machine data in the human resource and machine relationship library.

[0070] According to some embodiments, the code is composed of a code segment value corresponding to at least one code segment, the code segments correspond one-to-one to the attributes in the human-material-machine relationship library, the code segment value range corresponding to the code segment is determined by the number of attribute values ​​corresponding to the code segment in the human-material-machine relationship library, and the code segment value is determined by the position of the attribute value in the code segment value range.

[0071] In summary, the method provided in this embodiment obtains a set of human-machine data, and identifies the attributes and attribute values ​​of each human-machine data in the human-machine data set to obtain the attributes and attribute values ​​corresponding to each human-machine data; constructs an initial human-machine relationship library corresponding to the attributes and attribute values, and optimizes the initial relationship library when the initial relationship library meets the classification optimization requirements to obtain an optimized human-machine relationship library; generates the code corresponding to each human-machine data according to the attribute value of each human-machine data in the human-machine relationship library. Therefore, human-machine coding that adapts to the digital age and has universality and scalability can be realized.

[0072] This embodiment also provides another automatic coding method for construction engineering personnel, materials and machines. The method can be executed by an electronic device.

[0073] For example, the automatic coding method for construction engineering personnel and equipment may include the following steps:

[0074] S201, collecting a set of data related to personnel, materials and machines from a data source;

[0075] According to some embodiments, the methods of collecting human-material-machine related data sets from data sources include but are not limited to crawlers, application programming interfaces (APIs), and the like.

[0076] In some embodiments, the data related to the personnel and the machine refers to data related to the personnel and the machine, including various descriptions of the personnel and the machine and constrained personnel and machine attributes. Among them, the various descriptions of the personnel and the machine and constrained personnel and machine attributes may include the attributes and attribute values ​​of the personnel and the machine.

[0077] In some embodiments, the human-material-machine related data set includes human-material-machine related data in at least one format.

[0078] For example, crawlers, APIs and other methods can be used to collect human-related data in various formats such as pdf, excel, and xml from data sources to obtain a human-related data set.

[0079] S202, using a parsing method corresponding to the format to parse the data related to personnel, materials and machines, and obtain an initial data set of personnel, materials and machines;

[0080] According to some embodiments, the human-material-machine initial data set includes at least one human-material-machine initial data.

[0081] For example, for personnel, materials and machine-related data in PDF format, PDFBox can be used to parse the data and obtain the corresponding personnel, materials and machine initial data.

[0082] For example, for personnel, materials and machine-related data in Excel format, Apache POI can be used to parse the data and obtain the corresponding personnel, materials and machine initial data.

[0083] For example, for personnel, materials and machine-related data in XML format, JDOM can be used to parse the data and obtain the corresponding personnel, materials and machine initial data.

[0084] S203, performing data preprocessing on the initial data set of personnel, materials and machines to obtain a data set of personnel, materials and machines;

[0085] According to some embodiments, when data preprocessing is performed on the initial data set of human-material-machine, data cleaning can be performed on the initial data set of human-material-machine to obtain the initial data set of human-material-machine after data cleaning; and normalization processing is performed on the initial data set of human-material-machine after data cleaning to obtain the human-material-machine data set. Therefore, the effect of data preprocessing can be improved.

[0086] In some embodiments, data cleaning is used to identify and correct problems in the data. Data cleaning includes but is not limited to missing value processing, outlier processing, duplicate data processing, etc.;

[0087] Among them, missing value processing is used to delete missing values, replace missing values, and interpolate;

[0088] Among them, outlier processing is used to identify and mark outliers;

[0089] Among them, duplicate data processing is used to identify and delete duplicate data, and merge multiple similar data into one;

[0090] According to some embodiments, normalization processing is used to process scale differences between different features. When normalizing the initial data set of human, material and machine after data cleaning, the attribute values ​​corresponding to each attribute can be classified to obtain at least one category of attribute value set; determine the expression corresponding to each attribute value in the attribute value set of each category to obtain a set of non-standard expressions; determine the standardized expression corresponding to the attribute value set based on the non-standard expression set; construct a correspondence library between the non-standard expression set and the standardized expression, and normalize the initial data set of human, material and machine after data cleaning based on the correspondence library. Therefore, the efficiency and effect of the normalization processing can be improved.

[0091] That is to say, the normalization process is to process the attribute value data corresponding to each attribute according to the preset rules, wherein the preset rules include the correspondence between the non-standard expression mode and the standardized expression mode of the attribute value.

[0092] In some embodiments, data analysis can be performed on the initial data set of human-material-machine after data cleaning, and the attribute values ​​of each attribute can be classified and sorted according to the data analysis results to obtain at least one category of attribute value set;

[0093] In some embodiments, when determining the expression corresponding to each attribute value in the attribute value set of each category and obtaining the non-standard expression set, the diversified expressions in the attribute value set of each category can be stored to ensure that each expression is recorded only once to obtain the non-standard expression set. The non-standard expression in the non-standard expression set can correspond to at least one attribute value in the attribute value set.

[0094] In some embodiments, when determining the standardized expression corresponding to the attribute value set based on the set of non-standard expressions, any non-standard expression can be selected from the set of non-standard expressions as the unified standardized expression corresponding to the attribute value set, or a new expression can be constructed based on the set of non-standard expressions as the unified standardized expression corresponding to the attribute value set.

[0095] For example: the attribute value collected for the attribute "specification model" is "Q235Bδ=6-10", which should be "Q235Bδ6", "Q235Bδ7", "Q235Bδ8", "Q235Bδ9", "Q235Bδ10" after normalization.

[0096] Taking a scenario as an example, the initial data set of human, material and machine is shown in Table (1):

[0097] Table (1)

[0098]

[0099] Among them, the second to fifth rows in Table (1) respectively represent the initial data of a person machine.

[0100] When the data shown in Table (1) is cleaned and normalized, the corresponding relationship library is used to normalize the data in Table (1), identify the non-compliant content, and process it. For example, the corresponding relationship library stipulates that the standardized expression of the specification model of hot-rolled round steel bars is "HPB300 ”, where X is the diameter value, but the expression used in Table (1) is “ HPB300", and deduplication is performed at the same time. After processing, Table (2) can be obtained:

[0101] Table (2)

[0102]

[0103] S204, performing word segmentation processing on each human resource and machine data in the human resource and machine data set to obtain a word segmentation set corresponding to each human resource and machine data;

[0104] According to some embodiments, word segmentation processing is performed on each human-machine data in the human-machine data set, so that the collected text data can be segmented into meaningful vocabulary units.

[0105] For example, the second row of data in Table (2) can be segmented into "steel", "hot-rolled", "plain round", "HPB300", And other vocabulary.

[0106] S205, performing named entity recognition on the word segmentation set to obtain the attribute corresponding to each human and machine data and the attribute value corresponding to the attribute;

[0107] According to some embodiments, named entity recognition (NER), also known as "proper name recognition", is a basic task in natural language processing and has a wide range of applications. Named entities refer to entities with specific meanings or strong referentiality in texts, including but not limited to names of people, places, organizations, dates and times, proper nouns, etc. NER usually includes two parts: identifying the boundaries of entities and determining the type of entities (names of people, places, organizations, or others).

[0108] For example, for Table (2), after word segmentation and NER processing, it can be identified that "specification model" is an attribute, and "HPB300 " is the attribute value of this attribute.

[0109] According to some embodiments, the part-of-speech tag corresponding to each word in the word segmentation set can be determined, and the word segmentation is labeled according to the part-of-speech tag to obtain the labeled word segmentation set; and named entity recognition is performed on the labeled word segmentation set. Therefore, the efficiency and effect of named entity recognition can be improved.

[0110] In some embodiments, part-of-speech tags include, but are not limited to, nouns, verbs, adjectives, and the like.

[0111] For example, for Table (2), "rebar" can be labeled as a noun, and "hot rolling" can be labeled as a verb.

[0112] It should be noted that the attribute values ​​that meet the specific pattern can also be extracted from the human-material-machine data set by predefined rules. The predefined rules can include numbers and letters, for example, and can be regular expressions or the standardized expressions constructed in step S203.

[0113] For example, you can use the regular expression Matching to "HPB300 ”, and extract “HPB300” and As a property value.

[0114] S206, constructing an initial graph database with attributes and attribute values ​​as nodes and third association relationships between attributes and attribute values ​​as edges;

[0115] According to some embodiments, in the initial graph database, each attribute and attribute value is represented as a node, and the relationship between them is connected by edges. For example, the attribute "specification model" and the attribute value "HPB300 There will be an edge between them to indicate their relationship.

[0116] Taking a scenario as an example, for table (2), when using the graph database Neo4j to store attributes and attribute values, the following code can be used:

[0117] CREATE(a:Attribute{name:'Specification model'}),

[0118] (v:AttributeValue{name:'HPB300 }),

[0119] (v2:AttributeValue{name:'HPB300 }),

[0120] (v3:AttributeValue{name:'HRB400E }),

[0121] (a)-[:HAS_VALUE]->(v),

[0122] (a)-[:HAS_VALUE]->(v2),

[0123] (a)-[:HAS_VALUE]->(v3)

[0124] Among them, HAS_VALUE represents the type of relationship between the attribute and the attribute value.

[0125] It should be noted that the third association relationship between attributes and attribute values ​​can be obtained through manual entry or through data analysis.

[0126] S207, classifying the attribute values, and constructing hierarchical relationships between the attribute values ​​in the initial graph database according to the classification results, to obtain an initial human-material-machine relationship library corresponding to the human-material-machine data set;

[0127] According to some embodiments, similar or identical attribute values ​​may be grouped into one category through cluster analysis, which may include, but is not limited to, unsupervised learning algorithms (such as K-means), DBSCAN, and the like.

[0128] For example, the extracted specification model attribute value "HPB300 ”, “HPB300 ”, “HRB400E Through cluster analysis, it can be identified that "HPB300" and "HRB400E" are different material series. and are of different sizes. In this way, similar attribute values ​​are grouped into the same category.

[0129] Taking a scenario as an example, the materials in Table (2) can be further divided into ferrous and non-ferrous metals and other non-metallic materials and products such as rubber and plastic. Ferrous and non-ferrous metals can include steel bars, steel wires, etc.

[0130] For example, in the graph database Neo4j, the following code can be used to represent the hierarchical relationship:

[0131] CREATE(material:Category{name:'Material'}),

[0132] (metal:Category{name:'Ferrous and non-ferrous metals'}),

[0133] (steel:Category{name:'Rebar'}),

[0134] (material)-[:CONTAINS]->(metal),

[0135] (metal)-[:CONTAINS]->(steel)

[0136] Among them, CONTAINS indicates that one category contains another category.

[0137] S208, performing data mining on the attribute values ​​to obtain data mining results;

[0138] According to some embodiments, association rules between attribute values ​​may be mined through data mining, and these rules may reveal implicit relationships between attribute values.

[0139] For example, the Apriori algorithm can be used to mine association rules between attribute values ​​from large amounts of data.

[0140] Take a scenario as an example, the Apriori algorithm is used to derive a rule: "If the attribute contains HPB300 If the steel bar is HRB400E, then this attribute is likely to include The co-occurrence relationship of different attribute values ​​in the attribute can be understood.

[0141] S209, when the data mining result indicates that different attribute values ​​have a co-occurrence relationship in the same attribute, determining that the initial relationship library meets the classification optimization requirements, and optimizing the classification of attributes and the classification of attribute values ​​in the initial relationship library according to the data mining result, to obtain an optimized human-material-machine relationship library;

[0142] According to some embodiments, when data mining results indicate that different attribute values ​​have a co-occurrence relationship in the same attribute, it means that certain attribute values ​​often appear together, and their classification can be reconsidered or new classification can be created to better reflect these relationships.

[0143] For example, when the data mining results indicate that "city A" and "city B" often appear together in attributes, a new subcategory "region" can be added to the classification, and the two attribute values ​​can be classified into this new subcategory.

[0144] Taking a scenario as an example, the optimized human-material-machine relationship library includes the attributes of four major categories: materials, labor, machinery, and equipment. The optimized human-material-machine relationship library can be shown in Table (3):

[0145] Table (3)

[0146]

[0147]

[0148]

[0149] According to some embodiments, a personnel-machine update data set may be obtained at preset intervals; and based on the personnel-machine update data set, update data corresponding to the personnel-machine update data set is added to the personnel-machine relationship library.

[0150] In some embodiments, updating data includes updating attributes and / or updating attribute values, that is, attributes and / or attribute values ​​that do not exist in the optimized human-material-machine relationship library.

[0151] It should be noted that the personnel-machine update data set may include attributes or attribute values ​​that already exist in the optimized personnel-machine relationship library. When the optimized personnel-machine relationship library is updated, the update data can be selected from the personnel-machine update data set for addition. Therefore, a dynamically adjusted personnel-machine relationship library can be formed, and absolute coding with full coverage of personnel-machine attribute information can be achieved.

[0152] When adding an updated attribute, reference may be made to step S03 to determine a set of non-standard expressions and a standardized expression of the attribute value corresponding to the updated attribute, and update a corresponding relationship library between the set of non-standard expressions and the standardized expression.

[0153] Taking a scenario as an example, when updating the optimized human-material-machine relationship library shown in Table (3), add a row at the bottom of attribute 5 corresponding to attribute 4 hot-rolled round steel bar and add the attribute value "HPB300 ”, as shown in Table (4):

[0154] Table (4)

[0155]

[0156] S210, generating a code corresponding to each human resource and machine data according to the attribute value of each human resource and machine data in the human resource and machine relationship library.

[0157] Taking a scenario as an example, for the human-material-machine relationship library shown in Table (3), there are five attributes, namely attribute 1, attribute 2, attribute 3, attribute 4, and attribute 5. The encoding is composed of the code segment values ​​corresponding to code segment 1, code segment 2, code segment 3, code segment 4, and code segment 5, respectively. Code segment 1 represents attribute 1, code segment 2 represents attribute 2, code segment 3 represents attribute 3, code segment 4 represents attribute 4, and code segment 5 represents attribute 5.

[0158] According to some embodiments, the code segment value range corresponding to the code segment can be determined by exhaustive enumeration, which can be the number of attribute values ​​of the next level included in the attribute value of the previous level corresponding to the code segment, or the number of all attribute values ​​corresponding to the code segment.

[0159] For example, for the human-material-machine relationship library shown in Table (3), the code segment of attribute 1 "Major Category" has 4 attribute values ​​(material, labor, machinery, equipment), and the code segment value range of the attribute "Major Category" is 1 to 4. The number of attribute values ​​of attribute 5 "Specification Model" corresponding to hot-rolled plain round steel bars is 3, and the total number of attribute values ​​of attribute 5 "Specification Model" is 60. Therefore, the code segment value range of attribute 5 "Specification Model" corresponding to hot-rolled plain round steel bars can be set to 1 to 3, or it can be set to 1 to 60.

[0160] For example, when the code value range of attribute 5 "Specification Model" corresponding to hot-rolled round steel bars is set to 1 to 60, in the human-material-machine relationship library shown in Table (3), the major category is material, the classification is ferrous and non-ferrous metals, the subcategory is steel bars, the material name is hot-rolled round steel bars, and the specification model is HPB300. The code for human resource and machine data is 11010101.

[0161] It should be noted that as the data continues to change, the data source can be continuously updated, the attribute values ​​in the human-material-machine relationship library can be automatically updated, the human-material-machine coding rules can be dynamically adjusted, and the unique coding of human-material-machine can be maintained to maintain the timeliness and accuracy of the coding and achieve absolute coding that fully covers the human-material-machine attribute information.

[0162] Take a scenario as an example, add the attribute value "HPB300" in Table (4) "After that, the number of attribute values ​​of the code segment of attribute 5 "Specification model" corresponding to hot-rolled plain round steel bars is changed from 3 to 4. When the code segment value range of attribute 5 "Specification model" corresponding to hot-rolled plain round steel bars is set to 1 to 60, the code segment value range is updated to 1 to 61, and the major category is material, classified as ferrous and non-ferrous metals, the subcategory is steel bars, the material name is hot-rolled plain round steel bars, and the specification model is "HPB300 The code of human resource and machine data is 11010104.

[0163] It should be noted that the specific generation rules of the coding corresponding to the human, material and machine data, that is, the coding is composed of a code segment value corresponding to at least one code segment, the code segment corresponds to the attribute in the human, material and machine relationship library one-to-one, the code segment value range corresponding to the code segment is determined by the number of attribute values ​​corresponding to the code segment in the human, material and machine relationship library, and the code segment value is determined by the position of the attribute value in the code segment value range. This can be used as human, material and machine coding rules and made public through the Internet, thereby realizing unified coding that adapts to the digital age; a detailed coding manual can also be constructed to comprehensively explain the rules and examples of human, material and machine coding, so as to facilitate learning and use by relevant personnel.

[0164] In summary, the method provided in this embodiment, first, collects a set of data related to human resources and machines from a data source; adopts a parsing method corresponding to the format to parse the data related to human resources and machines to obtain an initial set of human resources and machines data; performs data preprocessing on the initial set of human resources and machines data to obtain a set of human resources and machines data; therefore, the accuracy of obtaining the set of human resources and machines data can be improved. Then, by performing word segmentation processing on each human resources and machine data in the human resources and machine data set, a set of word segments corresponding to each human resources and machine data can be obtained; named entity recognition is performed on the word segmentation set to obtain the attributes corresponding to each human resources and machine data and the attribute values ​​corresponding to the attributes; therefore, the efficiency and accuracy of attribute and attribute value recognition can be improved. Then, an initial graph database is constructed with attributes and attribute values ​​as nodes and the third association relationship between attributes and attribute values ​​as edges; the attribute values ​​are classified, and a hierarchical relationship between attribute values ​​and attribute values ​​is constructed in the initial graph database according to the classification results to obtain an initial human resources and machine relationship library corresponding to the human resources and machine data set; therefore, the efficiency and effect of constructing the initial human resources and machine relationship library can be improved. Next, data mining is performed on the attribute values ​​to obtain data mining results; when the data mining results indicate that different attribute values ​​have a co-occurrence relationship in the same attribute, it is determined that the initial relationship library meets the classification optimization requirements, and the classification of the attributes in the initial relationship library and the classification of the attribute values ​​are optimized according to the data mining results to obtain the optimized human-machine relationship library; therefore, the optimization effect of the initial relationship library can be improved. Finally, according to the attribute value of each human-machine data in the human-machine relationship library, the corresponding code of each human-machine data is generated; therefore, human-machine coding that adapts to the digital age and has universality and scalability can be realized.

[0165] In order to implement the above embodiments, the present disclosure also proposes an automatic encoding device for construction engineering personnel, materials and machines.

[0166] like Figure 2 As shown, the automatic encoding device 200 for construction engineering personnel and equipment includes:

[0167] The data identification unit 201 is used to obtain a personnel-machine data set, and identify the attributes and attribute values ​​of each personnel-machine data in the personnel-machine data set to obtain the attributes and attribute values ​​corresponding to each personnel-machine data;

[0168] The relationship building unit 202 is used to build an initial human-material-machine relationship library corresponding to attributes and attribute values, and optimize the initial relationship library when the initial relationship library meets the classification optimization requirements to obtain an optimized human-material-machine relationship library, wherein the human-material-machine relationship library includes a first association relationship between attributes and attribute values, and a second association relationship between attribute values ​​and attribute values;

[0169] The data encoding unit 203 is used to generate a code corresponding to each human-machine data according to the attribute value of each human-machine data in the human-machine-machine relationship library, wherein the code is composed of a code segment value corresponding to at least one code segment, the code segment corresponds to the attribute in the human-machine-machine relationship library one-to-one, the code segment value range corresponding to the code segment is determined by the number of attribute values ​​corresponding to the code segment in the human-machine-machine relationship library, and the code segment value is determined by the position of the attribute value in the code segment value range.

[0170] Optionally, when the data identification unit 201 is used to obtain the human-material-machine data set, it is specifically used to:

[0171] Collecting a set of personnel-related data from a data source, wherein the set of personnel-related data includes personnel-related data in at least one format;

[0172] Adopt the analysis method corresponding to the format to analyze the data related to personnel, materials and machines, and obtain the initial data set of personnel, materials and machines;

[0173] The initial data set of human, material and machine is preprocessed to obtain the human, material and machine data set.

[0174] Optionally, the data identification unit 201 is used to perform data preprocessing on the initial data set of personnel, materials and machines, and when obtaining the data set of personnel, materials and machines, specifically to:

[0175] Performing data cleaning on the initial data set of personnel, materials and machines to obtain the initial data set of personnel, materials and machines after data cleaning;

[0176] The initial data set of human, material and machine after data cleaning is normalized to obtain the human, material and machine data set.

[0177] Optionally, when the data identification unit 201 is used to normalize the initial data set of personnel, materials and machines after data cleaning, it is specifically used to:

[0178] Classify the attribute values ​​corresponding to each attribute to obtain at least one category of attribute value set;

[0179] Determine the expression method corresponding to each attribute value in the attribute value set of each category, and obtain a set of non-standard expressions;

[0180] Determine a standardized expression corresponding to the attribute value set according to the set of non-standard expressions;

[0181] A correspondence library between a set of irregular expressions and standardized expressions is constructed, and the initial data set of human, material and machine after data cleaning is normalized according to the correspondence library.

[0182] Optionally, the data identification unit 201 is used to identify the attributes and attribute values ​​of each human-machine data in the human-machine data set, and when obtaining the attributes and attribute values ​​corresponding to each human-machine data, specifically:

[0183] Perform word segmentation processing on each human resource and machine data in the human resource and machine data set to obtain a word segmentation set corresponding to each human resource and machine data;

[0184] Perform named entity recognition on the word segmentation set to obtain the attributes corresponding to each human and machine data and the attribute values ​​corresponding to the attributes.

[0185] Optionally, when the data identification unit 201 is used to perform named entity recognition on the word segmentation set, it is specifically used to:

[0186] Determine the part-of-speech tag corresponding to each word in the word set, and mark the word according to the part-of-speech tag to obtain a marked word set;

[0187] Perform named entity recognition on the annotated word set.

[0188] Optionally, when the relationship building unit 202 is used to build an initial human-material-machine relationship library corresponding to attributes and attribute values, it is specifically used to:

[0189] The initial graph database is constructed with attributes and attribute values ​​as nodes and the third relationship between attributes and attribute values ​​as edges;

[0190] The attribute values ​​are classified, and the hierarchical relationship between the attribute values ​​is constructed in the initial graph database according to the classification results, so as to obtain the initial human-material-machine relationship library corresponding to the human-material-machine data set.

[0191] Optionally, the relationship building unit 202 is used to optimize the initial relationship library when the initial relationship library meets the classification optimization requirements, and obtain the optimized human-material-machine relationship library, specifically to:

[0192] Perform data mining on the attribute values ​​to obtain data mining results;

[0193] When the data mining results indicate that different attribute values ​​have a co-occurrence relationship in the same attribute, it is determined that the initial relationship library meets the classification optimization requirements, and the classification of attributes in the initial relationship library and the classification of attribute values ​​are optimized according to the data mining results to obtain an optimized human-material-machine relationship library.

[0194] Optionally, after obtaining the optimized human-material-machine relationship library, the relationship building unit 202 is further used to:

[0195] Obtain updated data sets of personnel, materials and machines at preset intervals;

[0196] According to the personnel-material-machine update data set, update data corresponding to the personnel-material-machine update data set is added on the basis of the personnel-material-machine relationship library, wherein the update data includes update attributes and / or update attribute values.

[0197] It should be noted that the aforementioned explanation of the embodiment of the automatic encoding method for construction engineering personnel, materials and machines is also applicable to the automatic encoding device for construction engineering personnel, materials and machines of this embodiment, and will not be repeated here.

[0198] In summary, the device provided by the embodiment of the present disclosure obtains a set of human-machine data, and identifies the attributes and attribute values ​​of each human-machine data in the set of human-machine data to obtain the attributes and attribute values ​​corresponding to each human-machine data; constructs an initial human-machine relationship library corresponding to the attributes and attribute values, and optimizes the initial relationship library when the initial relationship library meets the classification optimization requirements to obtain an optimized human-machine relationship library; generates the code corresponding to each human-machine data according to the attribute value of each human-machine data in the human-machine relationship library. Therefore, human-machine coding that adapts to the digital age and has universality and scalability can be realized.

[0199] In order to implement the above embodiments, the present disclosure also proposes an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0200] In order to implement the above embodiments, the present disclosure further proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0201] In order to implement the above embodiments, the present disclosure also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0202] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this disclosure shall comply with the relevant laws and regulations and shall not violate public order and good morals.

[0203] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0204] The present disclosure anticipates providing implementation schemes for users to selectively block the use or access of personal information data. That is, the present disclosure anticipates providing hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, risks can be minimized by limiting data collection and deleting the data. In addition, when applicable, such personal information is de-identified to protect the privacy of the user.

[0205] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0206] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0207] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present disclosure belong.

[0208] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary, and then stored in a computer memory.

[0209] It should be understood that the various parts of the present disclosure can be implemented with hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented with hardware, as in another embodiment, it can be implemented with any one of the techniques known in the art or a combination thereof.

[0210] A person of ordinary skill in the art may understand that all or part of the steps in the above-mentioned embodiment method may be completed by instructing related hardware through a program, and that the program corresponding to the method provided in the embodiment of the present disclosure may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps in the method embodiment.

[0211] In addition, each functional unit in each embodiment of the present disclosure may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0212] The storage medium mentioned above may be a read-only memory, a disk or an optical disk, etc. Although the embodiments of the present disclosure have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present disclosure. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present disclosure.

Claims

1. An automatic coding method for construction engineering personnel, materials and machines, characterized in that: include: Acquire a personnel-machine data set, and identify the attributes and attribute values ​​of each personnel-machine data in the personnel-machine data set to obtain the attributes and attribute values ​​corresponding to each personnel-machine data; Constructing an initial human-talent-machine relationship library corresponding to the attribute and the attribute value, and optimizing the initial relationship library when the initial relationship library meets the classification optimization requirements to obtain an optimized human-talent-machine relationship library, wherein the human-talent-machine relationship library includes a first association relationship between the attribute and the attribute value, and a second association relationship between the attribute value and the attribute value; According to the attribute value of each human-machine data in the human-machine-relationship library, a code corresponding to each human-machine data is generated, wherein the code is composed of a code segment value corresponding to at least one code segment, the code segment corresponds one-to-one to the attribute in the human-machine-relationship library, the code segment value range corresponding to the code segment is determined by the number of attribute values ​​corresponding to the code segment in the human-machine-relationship library, and the code segment value is determined by the position of the attribute value in the code segment value range.

2. The method according to claim 1, characterized in that The obtaining of a human-material-machine data set includes: Collecting a set of personnel-related data from a data source, wherein the set of personnel-related data includes personnel-related data in at least one format; Using the parsing method corresponding to the format, the data related to the personnel, materials and machines are parsed to obtain an initial data set of personnel, materials and machines; Data preprocessing is performed on the initial data set of personnel, materials and machines to obtain a data set of personnel, materials and machines.

3. The method according to claim 2, characterized in that The data preprocessing of the initial data set of personnel, materials and machines to obtain the data set of personnel, materials and machines includes: Performing data cleaning on the initial data set of personnel, materials and machines to obtain the initial data set of personnel, materials and machines after data cleaning; The human-material-machine initial data set after data cleaning is normalized to obtain a human-material-machine data set.

4. The method according to claim 3, characterized in that The normalizing of the initial data set of human, material and machine after the data cleaning includes: Classify the attribute values ​​corresponding to each attribute to obtain at least one category of attribute value set; Determine the expression method corresponding to each attribute value in the attribute value set of each category, and obtain a set of non-standard expressions; Determining a standardized expression corresponding to the attribute value set according to the set of non-standard expressions; A correspondence library between the set of non-standard expressions and the standardized expressions is constructed, and the initial data set of human, material and machine after data cleaning is normalized according to the correspondence library.

5. The method according to claim 1, characterized in that The identifying of the attributes and attribute values ​​of each human-machine data in the human-machine data set to obtain the attributes and attribute values ​​corresponding to each human-machine data includes: Performing word segmentation processing on each human resource and machine data in the human resource and machine data set to obtain a word segmentation set corresponding to each human resource and machine data; Named entity recognition is performed on the word segmentation set to obtain the attributes corresponding to each human and machine data and the attribute values ​​corresponding to the attributes.

6. The method according to claim 5, characterized in that The performing named entity recognition on the word segmentation set includes: Determine the part-of-speech tag corresponding to each participle in the participle set, and mark the participle according to the part-of-speech tag to obtain a marked participle set; Perform named entity recognition on the annotated word segmentation set.

7. The method according to claim 1, characterized in that The constructing of the initial human-material-machine relationship library corresponding to the attributes and the attribute values ​​comprises: An initial graph database is constructed by using the attributes and the attribute values ​​as nodes and the third association relationship between the attributes and the attribute values ​​as edges; The attribute values ​​are classified, and hierarchical relationships between the attribute values ​​are constructed in the initial graph database according to the classification results, so as to obtain an initial human-material-machine relationship library corresponding to the human-material-machine data set.

8. The method according to claim 1, characterized in that When the initial relationship library meets the classification optimization requirements, the initial relationship library is optimized to obtain an optimized human-material-machine relationship library, including: Performing data mining on the attribute value to obtain a data mining result; When the data mining results indicate that different attribute values ​​have a co-occurrence relationship in the same attribute, it is determined that the initial relationship library meets the classification optimization requirements, and the classification of the attributes and the classification of the attribute values ​​in the initial relationship library are optimized according to the data mining results to obtain an optimized human-material-machine relationship library.

9. The method according to claim 1, characterized in that: After obtaining the optimized human-material-machine relationship library, the method further includes: Obtain updated data sets of personnel, materials and machines at preset intervals; According to the personnel-machine update data set, update data corresponding to the personnel-machine update data set is added on the basis of the personnel-machine relationship library, wherein the update data includes update attributes and / or update attribute values.

10. An automatic encoding device for construction engineering personnel and equipment, characterized in that: include: A data identification unit is used to obtain a set of human-machine data, and identify the attributes and attribute values ​​of each human-machine data in the set of human-machine data to obtain the attributes and attribute values ​​corresponding to each human-machine data; a relationship building unit, configured to build an initial human-material-machine relationship library corresponding to the attribute and the attribute value, and optimize the initial relationship library to obtain an optimized human-material-machine relationship library when the initial relationship library meets the classification optimization requirements, wherein the human-material-machine relationship library includes a first association relationship between the attribute and the attribute value, and a second association relationship between the attribute value and the attribute value; A data encoding unit is used to generate a code corresponding to each human-machine data according to the attribute value of each human-machine data in the human-machine-relationship library, wherein the code is composed of a code segment value corresponding to at least one code segment, the code segment corresponds to the attribute in the human-machine-relationship library one-to-one, the code segment value range corresponding to the code segment is determined by the number of attribute values ​​corresponding to the code segment in the human-machine-relationship library, and the code segment value is determined by the position of the attribute value in the code segment value range.

Images