Data acquisition protocol adaptation analysis method and system based on machine-readable model

Through the data acquisition protocol adaptation analysis method based on machine-readable model, the problem of data acquisition protocol standards in smart factories cannot be shared in data form and poor protocol adaptability is solved, and the construction of the data acquisition semantic framework and knowledge graph of smart factories is realized. It improves the adaptability and quality of the data acquisition protocol and improves the efficiency of information transmission.

CN118175223BActive Publication Date: 2024-11-26QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES) +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410414688.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-08
Publication Date
2024-11-26
Estimated Expiration
2044-04-08

AI Technical Summary

Technical Problem

The data acquisition protocol standards in the field of smart factories are mainly published in paper text or electronic PDF format, and standard data form sharing cannot be achieved. Standard document retrieval remains at the initial stage of simple keyword search, and cannot deeply reveal different standards. The relationship between the engineering personnel, machines and systems is limited in efficiency of standard information transmission and sharing, and it is difficult to select applicable collection protocols when introducing new equipment and upgrading old equipment, affecting the adaptation of the protocol.

Method used

Using the data acquisition protocol adaptation analysis method based on machine-readable model, the protocol standard is converted into editable documents through optical character recognition, combined with the industrial data acquisition ontology model for knowledge extraction, build a knowledge graph, and use the knowledge inference analysis model to evaluate the protocol adaptation Compatibility and data quality, provide intelligent factory data acquisition semantic framework and knowledge graph, and optimize the adaptability and quality of data acquisition protocols.

Benefits of technology

It improves the interactive capabilities of the machine, optimizes the adaptability and quality of the data acquisition protocol, reduces human working time, and realizes collaborative knowledge sharing and efficient transmission of standard information.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118175223B_ABST
    Figure CN118175223B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of standard digitization, and provides a data acquisition protocol adaptation analysis method and system based on a machine-readable model, including: obtaining the protocol standard required for industrial data acquisition, performing format conversion through optical character recognition, and obtaining an editable document; based on the editable document, combined with an ontology model, obtaining a triple through knowledge extraction; based on the triple, performing knowledge association through a machine-readable industrial data acquisition knowledge association model, obtaining a knowledge graph; using an industrial data acquisition knowledge reasoning analysis model, calling the knowledge graph, and obtaining a reasoning analysis knowledge base; based on the reasoning analysis knowledge base, combined with scenario requirements, evaluating the adaptability of different data acquisition protocols. The reasoning analysis data acquisition protocol adaptability is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of standard digitization, and in particular relates to a data acquisition protocol adaptation analysis method and system based on a machine-readable model. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] In order to achieve machine readability of standards in different fields, ISO proposed machine-readable standards (Standards Machine Applicable, Readable and Transferable), abbreviated as SMART, in 2019. Machine-readable standards are technical contents that can be directly parsed and used by machines, software or other automated systems, and provided to applications or user-defined methods in digital form, that is, machine-usable, readable and parsable standards can be achieved without manual operation in the system. At present, most machine-readable standards start from specific scenarios and improve machine interactivity by constructing information models.

[0004] At present, most of the relevant protocol standards in the field of smart factories are published in paper text or electronic PDF format, which fails to realize the sharing and use of standards in the form of data, and no one has proposed a technical method for converting paper text or electronic PDF format documents into high-level machine-readable standards. At the same time, standard document retrieval is still at the primary stage of simple keyword retrieval, unable to deeply reveal the relationship between different standards, unable to meet the knowledge and value application needs of standards, and seriously restricting the efficiency of standard information transmission and information sharing between engineers, machines, and systems. Secondly, there are a large number of data collection protocols, and the machine cannot select the appropriate collection protocol according to the equipment type and scenario requirements, which affects the introduction of new equipment and the adaptation of old equipment to the collection protocol. Summary of the invention

[0005] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a data acquisition protocol adaptation analysis method and system based on a machine-readable model, constructs an ontology model based on the industrial data acquisition field, and provides a semantic framework for intelligent factory data acquisition to facilitate knowledge collaborative sharing. Based on the industrial data acquisition knowledge graph, with triples as the smallest module and guided by specific scenario requirements, a knowledge reasoning analysis library is constructed to reason and analyze the adaptability of data acquisition protocols.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] A first aspect of the present invention provides a data acquisition protocol adaptation analysis method based on a machine-readable model, which comprises:

[0008] Obtain the protocol standards required for industrial data collection, convert the format through optical character recognition, and obtain editable documents;

[0009] Based on the editable document and combined with the ontology model, triples are obtained through knowledge extraction;

[0010] Based on the triples, knowledge association is performed through a machine-readable industrial data collection knowledge association model to obtain a knowledge graph;

[0011] Adopting the industrial data acquisition knowledge reasoning analysis model, calling the knowledge graph, and obtaining the reasoning analysis knowledge base;

[0012] Based on the reasoning analysis knowledge base and combined with scenario requirements, the adaptability of different data collection protocols is evaluated.

[0013] Further, it also includes: based on the reasoning analysis knowledge base, evaluating the data quality of data sets collected by different data collection protocols;

[0014] The data quality evaluation criteria include data integrity, data accuracy, data redundancy and data consistency, and the constraints related to data integrity include non-empty constraints and continuity constraints, the constraints related to data accuracy include value range constraints, code constraints and logical dependency constraints, the constraints related to data redundancy include equivalued function dependency constraints, and the constraints related to data consistency include equivalued consistency dependency constraints, logical consistency dependency constraints and existence consistency dependency constraints.

[0015] Further, the ontology model includes industrial data acquisition knowledge ontology;

[0016] The conceptual hierarchical architecture of the industrial data acquisition knowledge ontology is expressed as:

[0017] C knowledge ={DO,CP,DQ,DS,DCP}

[0018] Among them, DO refers to data object, CP refers to collection plan, DQ refers to data quality, DS refers to data security, and DCP refers to data collection protocol;

[0019] The industrial data collection knowledge ontology is defined as a quaternion:

[0020] {CON,NEL,ATT,REA}

[0021] Among them, CON refers to concept, NEL refers to relationship, ATT refers to attribute, and REA refers to inference rule.

[0022] Furthermore, the knowledge extraction includes: extracting the common elements in the standard document through XML tags, and then extracting the triples through dependency syntax analysis.

[0023] Furthermore, the machine-readable industrial data collection knowledge association model is expressed as:

[0024] SIDCKAM={IDCS{DO,CP,DQ,DS,DCP},REL(idc),ATT(idc),REA(idc)}

[0025] Among them, IDCS refers to the standard knowledge of industrial data collection, DO, CP, DQ, DS, and DCP refer to data objects, collection planning, data quality, data security, and data collection protocol respectively, REL(idc) refers to IDCS relationship set, ATT(idc) refers to attributes, and REA(idc) refers to inference rules.

[0026] Furthermore, the scenario requirements include: transmission distance, energy consumption, transmission frequency and transmission speed of the protocol.

[0027] A second aspect of the present invention provides a data acquisition protocol adaptation analysis system based on a machine-readable model, comprising:

[0028] A data acquisition module is configured to: acquire the protocol standard required for industrial data acquisition, perform format conversion through optical character recognition, and obtain an editable document;

[0029] A knowledge management module is configured to: obtain triples through knowledge extraction based on the editable document and the ontology model;

[0030] A knowledge graph module is configured to: based on the triples, collect knowledge association models using machine-readable industrial data, perform knowledge association, and obtain a knowledge graph;

[0031] The reasoning analysis module is configured to: adopt the industrial data acquisition knowledge reasoning analysis model, call the knowledge graph, and obtain a reasoning analysis knowledge base;

[0032] The application evaluation module is configured to evaluate the adaptability of different data acquisition protocols based on the reasoning analysis knowledge base and in combination with scenario requirements.

[0033] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the data acquisition protocol adaptation and analysis method based on a machine-readable model as described above.

[0034] The fourth aspect of the present invention provides a computer device, including a computer-readable storage medium, a processor, and a computer program stored on the computer-readable storage medium and executable on the processor, wherein when the processor executes the program, the steps in the data acquisition protocol adaptation and analysis method based on the machine-readable model as described above are implemented.

[0035] A fifth aspect of the present invention provides a computer program product, which is a computer program product containing a computer program. When a processor executes the computer program, the steps in the data acquisition protocol adaptation and analysis method based on a machine-readable model as described above are implemented.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention proposes a five-dimensional conceptual hierarchical relationship model for industrial data collection at the knowledge management level, constructs an ontology model based on the industrial data collection field, and provides a semantic framework for smart factory data collection to facilitate collaborative knowledge sharing.

[0038] The present invention is based on the industrial data collection knowledge graph, takes the knowledge triple as the smallest module, and is guided by the specific scenario requirements to construct a knowledge reasoning and analysis model. It can reason and analyze the adaptability of data collection protocols, optimize the strategy to ensure the quality of data collection, and improve the machine's interactivity.

[0039] The present invention proposes a five-layer machine-readable model for industrial data collection in smart factories, which specifically includes a data acquisition layer, a knowledge management layer, a knowledge graph layer, a reasoning and analysis layer, and an application evaluation layer. It provides an intelligent reasoning and analysis method for the field of industrial data collection, and evaluates the adaptability of the collection protocol, the quality of the collected data, and the machine-readable maturity of the model, thereby reducing manual operation time. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0041] Figure 1 is a machine-readable model framework diagram of the first embodiment of the present invention;

[0042] Figure 2 This is a schematic diagram of the industrial data acquisition structure of the first embodiment of the present invention;

[0043] Figure 3 is a conceptual hierarchical architecture diagram of the first embodiment of the present invention;

[0044] Figure 4 is a conceptual relationship diagram of the first embodiment of the present invention;

[0045] Figure 5is a relationship diagram between evaluation criteria and data constraint conditions in the first embodiment of the present invention;

[0046] Figure 6 It is a schematic diagram of query results of the corresponding collection protocol of the first embodiment of the present invention;

[0047] Figure 7 It is a schematic diagram of query results of the adapted collection protocol according to the first embodiment of the present invention;

[0048] Figure 8 It is a structural diagram of a computer device according to a fourth embodiment of the present invention. DETAILED DESCRIPTION

[0049] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0050] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0051] Embodiment 1

[0052] This embodiment provides a data acquisition protocol adaptation analysis method based on a machine-readable model.

[0053] The data acquisition protocol adaptation and analysis method based on a machine-readable model provided in this embodiment is oriented towards smart factories, guided by machine-readable standards, establishes a machine-readable model, and improves the intelligence level and interactivity of machines.

[0054] Machine-readable models help machines understand and apply knowledge through natural language processing and semantic reasoning analysis, thereby improving the intelligence and interactivity of machines.

[0055] In view of the problems of difficulty in adapting industrial data acquisition protocols and long development cycles in upgrading old equipment and introducing new equipment in smart factory scenarios, the data acquisition protocol adaptation analysis method based on machine-readable models provided in this embodiment includes reasoning analysis of data acquisition protocol adaptability and optimization of data acquisition quality, and evaluates the machine-readable maturity of machine-readable models through model functions. The machine-readable model includes five layers: data acquisition layer, knowledge management layer, knowledge graph layer, reasoning analysis layer and application evaluation layer. First, the protocol standards in the field of industrial data acquisition are obtained through the data acquisition layer; secondly, an ontology model is established in the knowledge management layer and knowledge triples are extracted; in the knowledge graph layer, a knowledge graph in the field of industrial data acquisition is constructed to achieve unified and comprehensive management of knowledge in the field of data acquisition; then, in the reasoning analysis layer, an industrial data acquisition knowledge reasoning analysis model is established and applied in the knowledge management layer, and the protocol adaptation module and the data quality module are obtained by reasoning analysis according to specific needs and combined to form a reasoning analysis knowledge base based on scenario needs; finally, in the application evaluation layer, the reasoning analysis knowledge base formed in the lower layer is used to evaluate the adaptability of the acquisition protocol, the quality of the acquired data and the machine-readable maturity of the model.

[0056] The data acquisition protocol adaptation analysis method based on a machine-readable model provided in this embodiment is used to alleviate the impact of upgrading old equipment and introducing new equipment on the acquisition protocol adaptation in the smart factory scenario, and to infer and analyze and optimize the strategy for ensuring data quality, thereby improving the machine interactivity in the field of industrial data acquisition. At the same time, a five-layer machine-readable model for industrial data acquisition in smart factories is proposed to provide an intelligent reasoning and analysis method for industrial data acquisition domain knowledge, and to achieve a machine-readable standard application demonstration in the field of smart factories. Moreover, based on the industrial data acquisition knowledge reasoning and analysis model, the knowledge graph constructed in the lower layer is called to derive the protocol adaptation module and the data quality module through reasoning and analysis on demand, and the modules are systematically combined to form a reasoning and analysis knowledge base that meets the scenario requirements, so that the application of industrial data acquisition domain knowledge is more in line with market demand.

[0057] Among them, machine-readable models, such as Figure 1 As shown, there are five layers in total, including data acquisition layer, knowledge management layer, knowledge graph layer, reasoning analysis layer and application evaluation layer:

[0058] Data acquisition layer, which collects and processes paper or PDF versions of protocol standards related to industrial data collection;

[0059] The knowledge management layer is based on the data files input by the data acquisition layer, combined with the domain knowledge of industrial data collection, to summarize the abstract concepts in the knowledge, and gradually refine them into lower-level concepts from top to bottom. It analyzes the concepts, attributes and hierarchical semantic relationships from top to bottom to form an industrial data collection ontology model, and extracts domain knowledge triples, including entities, attributes and relationships between entities, based on the established ontology model;

[0060] The knowledge graph layer is based on the knowledge extracted from the lower layer to build a knowledge graph for industrial data collection.

[0061] Reasoning and analysis layer: This layer can establish an industrial data collection knowledge reasoning and analysis model according to scenario requirements, and call the lower-level knowledge graph to derive the protocol adaptation module and data quality module according to specific requirements, and combine them to form a reasoning and analysis knowledge base based on scenario requirements;

[0062] Application evaluation layer: This layer uses the reasoning analysis knowledge base formed by the lower layer to evaluate the adaptability of the collection protocol, the quality of the collected data, and the machine-readable maturity of the model.

[0063] The data acquisition protocol adaptation analysis method based on a machine-readable model provided in this embodiment includes the following steps:

[0064] Step 1: Build a machine-readable model for industrial data collection, including five layers: data acquisition layer, knowledge management layer, knowledge graph layer, reasoning analysis layer, and application evaluation layer.

[0065] Step 2: Build a machine-readable model data acquisition layer. This layer collects paper or PDF versions of protocol standards related to industrial data collection and preprocesses them to obtain editable documents.

[0066] Step 201: document collection.

[0067] Collect the paper or PDF version of the protocol standards required in the field of industrial data collection, and convert them into editable Word format documents by using OCR recognition (optical character recognition) technology.

[0068] Step 202: Data preprocessing.

[0069] (1) Text cleaning. Standard documents (protocol standards) are mostly stored in PDF format. When converted to Word, problems such as spaces and typos may occur. You can manually check to delete spaces and correct typos.

[0070] (2) Text processing. Some sentences in the standard document lack subjects or contain unclear terms such as "this standard". The subjects in the sentences are completed and the referential terms are replaced with real words to facilitate the next step of knowledge extraction;

[0071] (3) Table processing. The table data in the standard file is not convenient for direct triple extraction, and the data relationship is not clear. It is necessary to extract the table data first and define the relationship between different data.

[0072] Step 3: Construct a machine-readable model knowledge management layer. This layer is based on the data files (editable documents) input by the data acquisition layer, summarizes the abstract concepts in the domain knowledge, and gradually refines them into lower-level concepts from top to bottom. It analyzes the concepts, attributes and hierarchical semantic relationships from top to bottom to form an industrial data acquisition ontology model. Based on the established ontology model, extract domain standard knowledge triples, including entities, attributes and the relationship between entities.

[0073] The industrial data collection ontology model (abbreviated as ontology model) is mainly divided into two parts, namely, the industrial data collection structure ontology constructed based on the hierarchical characteristics of the knowledge structure and the industrial data collection knowledge ontology based on knowledge content knowledge.

[0074] (1) Figure 2 As shown in the figure, by analyzing the common elements in the standard structure to form concepts, summarizing the relationship between concepts to form an industrial data acquisition structure ontology based on the hierarchical characteristics of the knowledge structure, it can be expressed as:

[0075] O structure ={SCN,Sta,SEN,OS,Dra,RT,IT,RC,AL,Ter{DT,TEN},CT{AT}}

[0076] Among them, SCN represents the Chinese name of the standard, Sta represents the standard number, SEN represents the English name of the standard, OS represents the organization, Dra represents the drafter, RT represents the release time, IT represents the implementation time, RC represents the specified content, AL represents the applicable scope, Ter represents the term, DT represents the definition of the term, TEN represents the English name of the term, CT represents the chapter title, and AT represents the article title.

[0077] (2) Use the seven-step method to construct the industrial data collection knowledge ontology based on knowledge content knowledge:

[0078] (201) Figure 3 As shown in the figure, the conceptual hierarchical architecture in the industrial data acquisition knowledge ontology (data acquisition ontology) can be expressed as:

[0079] C knowledge ={DO,CP,DQ,DS,DCP}

[0080] Among them, DO refers to data object, CP refers to collection plan, DQ refers to data quality, DS refers to data security, and DCP refers to data collection protocol; the conceptual hierarchy diagram is as follows Figure 3As shown in the conceptual relationship diagram, Figure 4 shown.

[0081] (202) The knowledge ontology model of industrial data collection is defined as a four-tuple, expressed as:

[0082] {CON,NEL,ATT,REA}

[0083] Among them, CON refers to concept, NEL refers to relationship, ATT refers to attribute, and REA refers to inference rule. Concept represents a collection of objects. For example, in the constructed industrial data collection knowledge ontology, data objects, collection planning, data quality, data security, and data collection protocols are all concepts.

[0084] (203) The conceptual hierarchy in the data object can be expressed as:

[0085] DO={DS,DC{IS,OMF,SL},TD}

[0086] Among them, DS refers to data source, DC refers to data classification, IS refers to industry field, OMF refers to operation and maintenance field, SL refers to system level, and TD refers to data type.

[0087] (204) The conceptual hierarchy of acquisition planning can be expressed as:

[0088] CP={CM,CR,CPs,DP}

[0089] Among them, CM refers to the acquisition method, CR refers to the acquisition range, CPs refers to the acquisition parameters, and DP refers to data preprocessing.

[0090] (205) The conceptual hierarchy of data quality can be expressed as:

[0091] DQ={DCR{NNC,RC,Cod-C,LC,ECDC,CCE,LCC,EFDC,Con-C},QCM,QIA}

[0092] Among them, DCR refers to data constraint rules, NNC refers to non-empty constraints, RC refers to range constraints, Cod-C refers to code constraints, LC refers to logical constraints, ECDC refers to equivalent consistency dependency constraints, CCE refers to existence consistency dependency constraints, LCC refers to logical consistency dependency constraints, EFDC refers to equivalent function dependency constraints, Con-C refers to continuity constraints, QCM quality control methods, and QIA quality detection and analysis methods.

[0093] (206) The conceptual hierarchy of the data collection protocol can be expressed as:

[0094] DCP={WP,WlP}

[0095] Among them, WP refers to the wired protocol and WIP refers to the wireless protocol.

[0096] (3) Knowledge extraction.

[0097] Knowledge extraction includes coarse-grained knowledge extraction of knowledge structure and fine-grained knowledge extraction of knowledge content. First, the standard document is simply split through XML tags to obtain coarse-grained standard knowledge, and then knowledge triples are extracted through dependency syntax analysis to obtain fine-grained standard knowledge.

[0098] Coarse-grained knowledge extraction takes knowledge structure as the extraction object and industrial data acquisition structure ontology model as the extraction constraint to extract common elements in the standard; XML can be used to mark common elements in the standard, including standard cover, introduction, scope of application, term definition and other elements and extract them.

[0099] Fine-grained knowledge extraction takes knowledge content as the extraction object and the industrial data acquisition knowledge ontology model as the extraction basis to extract knowledge triples; dependency syntax analysis tools can be used to analyze the dependency relationship between words in a sentence, determine the central word of the sentence, identify the relationship type of words in a sentence, and extract knowledge triples.

[0100] Step 4: Build a machine-readable model knowledge graph layer. This layer performs knowledge association based on the extracted triples and builds a knowledge graph in the field of industrial data collection.

[0101] Industrial data collection knowledge association is to associate the fine-grained knowledge in different standards according to the original structure of the standards and the reasoning rules between concepts. The machine-readable industrial data collection knowledge association model (SIDCKAM) is expressed as:

[0102] SIDCKAM={IDCS{DO,CP,DQ,DS,DCP},REL(idc),ATT(idc),REA(idc)}

[0103] Among them, IDCS refers to the standard knowledge of industrial data collection, DO, CP, DS, DQ, and DCP refer to data objects, collection planning, data quality, data security, and data collection protocol respectively, REL(idc) refers to IDCS relationship set, ATT(idc) refers to attributes, and REA(idc) refers to inference rules.

[0104] Through the association model (machine-readable industrial data collection knowledge association model), the extracted knowledge triples are stored in neo4j (graph database) to form a knowledge graph in the field of industrial data collection.

[0105] Step 5: Build a machine-readable model reasoning and analysis layer. This layer can establish an industrial data collection knowledge reasoning and analysis model and call the underlying knowledge graph according to scenario requirements, reason and analyze the adaptability of the collection protocol, optimize the strategy to ensure data collection quality, and form a reasoning and analysis knowledge base based on scenario requirements.

[0106] In IDCS, knowledge extraction results are represented by triples, and the knowledge graph also uses triples as nodes and edges to represent the relationship between entities. Using a triple, i.e. <entity, relationship, entity> or <entity, attribute, value> as the minimum IDCS module makes it easier to understand and maintain standard knowledge, and facilitates query and reuse.

[0107] The industrial data collection knowledge reasoning analysis model (SIDCKRM) can be expressed as:

[0108] SIDCKRM={IDCS,REL(idc),DO}

[0109] Based on scenario requirements and device types, neo4j query statements are constructed. According to the industrial data collection knowledge reasoning and analysis model, the lower-level knowledge graph is called, and the protocol adaptation module and data quality module are obtained through reasoning and analysis according to specific requirements. The obtained protocol adaptation module and data quality module are combined to form a reasoning and analysis knowledge base based on scenario requirements, including the device adaptation protocol, data quality assurance strategy and data constraint rules obtained through reasoning and analysis.

[0110] Among them, the data quality module is based on the acquired acquisition protocol or based on the acquired data object to derive the data quality assurance strategy and data constraint rules. For example, if the MODBUS protocol (serial communication protocol) is used, parity check, LRC (longitudinal redundancy check) or CRC check (cyclic redundancy check) can be used according to the specific situation to detect whether there are errors in the data during transmission to ensure the accuracy of the transmitted data; data constraint rules are non-empty constraints, value range constraints, etc.

[0111] Step 6: Establish a machine-readable model application evaluation layer. This layer uses the reasoning analysis knowledge base formed by the lower layer to evaluate the adaptability of the collection protocol, the quality of the collected data, and the machine readability maturity of the model.

[0112] The reasoning and analysis knowledge base formed in the lower layer is used to evaluate the adaptability of the acquisition protocol and the quality of the acquired data.

[0113] (1) Protocol adaptability assessment is used to evaluate the adaptability of the acquisition protocol based on the specific scenario requirements and the attribute characteristics of the protocol presented in the reasoning analysis knowledge base. A qualitative assessment is performed based on the focus of the scenario equipment and the transmission distance, energy consumption, transmission frequency, real-time (transmission speed) and other aspects of the protocol to select the best adaptive acquisition protocol.

[0114] First, analyze the focus of the scene or device, and take the most important demand as the highest priority for selecting the adaptation protocol; then, compare and analyze the various attributes of the collection protocol according to the importance of the demand, and select the most suitable collection protocol.

[0115] Example 1: Use Cypher statements to query the acquisition protocol required for the scenario in the knowledge graph. Take the most important requirement as: select a wireless protocol that can transmit about 50 meters, and require the collected sensors to be able to be controlled in time, as an example, enter the statement:

[0116] MATCH(sensor:data_source{name:"sensor"})-[:`Applicable protocol`]->(protocol)-[:`Property`]->(property)

[0117] WHERE property.content CONTAINS 'wireless'

[0118] WITH sensor,protocol,property

[0119] MATCH(protocol)-[:`Transmission distance`]->(distanceProperty)

[0120] WHERE toInteger(distanceProperty.maxValue)>50

[0121] RETURN sensor,protocol,distanceProperty;

[0122] Obtain the appropriate acquisition protocol, that is, the protocol adapter module, such as Figure 6 shown.

[0123] According to the obtained protocol adaptation module and actual application requirements, the acquisition protocol with the strongest adaptability is obtained. That is, the transmission speed of the acquisition protocol is compared with the previously obtained acquisition protocol, and the acquisition protocol with the fastest transmission speed is selected. Enter the statement:

[0124] MATCH(sensor:data_source{name:"sensor"})-[:`Applicable protocol`]->(protocol)-[:`Property`]->(property)

[0125] WHERE property.content CONTAINS 'wireless'

[0126] WITH sensor,protocol

[0127] MATCH(protocol)-[:`Transmission distance`]->(distanceProperty)

[0128] WHERE toInteger(distanceProperty.maxValue)>50

[0129] WITH sensor,protocol,distanceProperty

[0130] MATCH(protocol)-[:`baud rate`]->(baudRateRelation)

[0131] WITH sensor,protocol,distanceProperty,baudRateRelation,toString(reduce(s="",x IN split(baudRateRelation.maxValue,"")|CASE WHEN x IN["0","1","2","3","4","5","6","7","8","9"]THEN s+x ELSE s END))AS numericValu e

[0132] WITH sensor,protocol,distanceProperty,baudRateRelation,toInteger(numer icValue)AS maxValue

[0133] ORDER BY maxValue DESC

[0134] LIMIT 1

[0135] RETURN sensor, protocol, distanceProperty, baudRateRelation”;

[0136] Get the most adaptable acquisition protocol, such as Figure 7 shown.

[0137] (2) Data quality assessment is used to evaluate the data quality of the data set collected through the collection protocol based on the constraints of the data in the reasoning and analysis knowledge base. The evaluation criteria include data completeness, accuracy, redundancy and consistency. The relationship between the evaluation criteria and the data constraints is as follows: Figure 5As shown in the figure, the constraints related to integrity include non-empty constraints and continuity constraints, the constraints related to accuracy include range constraints, code constraints, and logical dependency constraints, the constraints related to redundancy include equivalent function dependency constraints, and the constraints related to consistency include equivalent consistency dependency constraints, logical consistency dependency constraints, and existence consistency dependency constraints. When evaluating, first add data constraints to the data or data set that needs to be evaluated.

[0138] Data constraint value calculation method:

[0139] X=A / B

[0140] Among them, A refers to the number of elements in the data set that meet the constraints, and B refers to the total number of elements in the data set being evaluated.

[0141] Data quality assessment is calculated as follows:

[0142]

[0143] Among them, I i Represents X nn , X con , that is, non-empty constraint value and continuity constraint value; A i Represents X r , X cod , X ld , namely, the value range constraint value, code constraint value, and logical dependency constraint value; R x Represents X ef , that is, the equivalence function depends on the constraint value; C i Represents X ec , X lc , X tc , namely, the equality consistency dependency constraint value, the logic consistency dependency constraint value, and the existence consistency dependency constraint value.

[0144] (3) Machine readability maturity assessment, which is used to assess the machine readability maturity based on the degree of completion of machine readability model operations.

[0145] According to the degree of completion of standard document operations, the machine readability maturity is quantitatively evaluated. The evaluation indicators and scores are shown in Table 1.

[0146] Table 1. Evaluation indicators and scores

[0147]

[0148]

[0149] Each operation level corresponds to a score, such as the completion level of paper standard document conversion is evaluated according to the accuracy of standard knowledge conversion; the completion level of XML knowledge processing is evaluated according to the completeness of standard structural elements, the reasonableness of table and formula label use, and the matching degree of label data type and label; the completion level of knowledge extraction is evaluated according to the fragmentation of knowledge extraction (such as chapters, clauses, entity relationship triples, etc.), the accuracy of table and formula extraction expression; the completion level of knowledge graph is evaluated according to the accuracy and completeness of data in the knowledge graph, the clarity of entity and relationship structure, and the frequency of data update. When evaluating the score, the percentage of completion is multiplied by the full score of the indicator.

[0150] Among them, there are two quantitative criteria for evaluation indicators:

[0151] One is to convert the judgment result into an indicator value. For example, "standard knowledge conversion accuracy" refers to comparing the paper standard with the converted electronic standard, which can be compared manually or by electronic scanning tools, and converted into an indicator value based on the conversion accuracy. For example, "knowledge graph data accuracy" can be compared based on the search results of the knowledge graph and the corresponding content of the actual standard document to see whether they are the same and accurate. Random sampling detection methods can be used to evaluate the accuracy of the search results and convert them into indicator values.

[0152] The other is manual judgment and scoring by experts and scholars. For example, the "reasonable degree of use of tags in tables and formulas" requires experts and scholars in the field of standards to determine whether the XML tags used are reasonable and score them based on the specific meaning of the table or formula.

[0153] The evaluation calculation formula is:

[0154]

[0155] The evaluation criteria are shown in Table 2.

[0156] Table 2. Evaluation criteria

[0157]

[0158]

[0159] The data collection protocol adaptation analysis method based on the machine-readable model provided in this embodiment proposes a five-layer machine-readable model for industrial data collection in smart factories, including a data acquisition layer, a knowledge management layer, a knowledge graph layer, a reasoning analysis layer, and an application evaluation layer. It provides an intelligent reasoning analysis method for the field of industrial data collection, evaluates the adaptability of the collection protocol, the quality of the collected data, and the machine-readable maturity of the model, and reduces manual operation time.

[0160] The data acquisition protocol adaptation analysis method based on a machine-readable model provided in this embodiment proposes a five-dimensional conceptual hierarchical relationship model for industrial data acquisition at the knowledge management level, constructs an ontology model based on the industrial data acquisition field, and provides a semantic framework for smart factory data acquisition to facilitate collaborative knowledge sharing.

[0161] The data acquisition protocol adaptation analysis method based on a machine-readable model provided in this embodiment is based on the industrial data acquisition knowledge graph, takes the knowledge triple as the smallest module, and is guided by specific scenario requirements to build a knowledge reasoning analysis model. It can reason and analyze the adaptability of the data acquisition protocol, optimize the strategy to ensure the quality of data acquisition, and improve the machine's interactivity.

[0162] Embodiment 2

[0163] This embodiment provides a data acquisition protocol adaptation analysis system based on a machine-readable model, which specifically includes:

[0164] A data acquisition module is configured to: acquire the protocol standard required for industrial data acquisition, perform format conversion through optical character recognition, and obtain an editable document;

[0165] A knowledge management module is configured to: obtain triples through knowledge extraction based on the editable document and the ontology model;

[0166] A knowledge graph module is configured to: based on the triples, collect knowledge association models using machine-readable industrial data, perform knowledge association, and obtain a knowledge graph;

[0167] The reasoning analysis module is configured to: adopt the industrial data acquisition knowledge reasoning analysis model, call the knowledge graph, and obtain a reasoning analysis knowledge base;

[0168] The application evaluation module is configured to evaluate the adaptability of different data acquisition protocols based on the reasoning analysis knowledge base and in combination with scenario requirements.

[0169] It should be noted here that each module in this embodiment corresponds to each step in Example 1 one by one, and the specific implementation process is the same, which will not be repeated here.

[0170] Embodiment 3

[0171] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the data acquisition protocol adaptation and analysis method based on a machine-readable model as described in the first embodiment above are implemented.

[0172] Embodiment 4

[0173] This embodiment provides a computer device, such as Figure 8As shown, it includes a computer-readable storage medium 1003, a processor 1001, a communication interface 1002, and a computer program stored on the computer-readable storage medium 1003 and executable on the processor 1001, wherein the processor 1001, the communication interface 1002, and the computer-readable storage medium 1003 can be connected via a bus or other means. The communication interface 1002 is used to receive and send data, and when the processor 1001 executes the program, the steps in the data acquisition protocol adaptation analysis method based on the machine-readable model as described in the first embodiment are implemented.

[0174] Embodiment 5

[0175] This embodiment provides a computer program product, which is a computer program product containing a computer program. When a processor executes the computer program, the steps in the data acquisition protocol adaptation analysis method based on a machine-readable model as described in the first embodiment above are implemented.

[0176] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0177] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0178] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0179] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A data acquisition protocol adaptation analysis method based on a machine-readable model, characterized in that: include: Obtain the protocol standards required for industrial data collection, convert the format through optical character recognition, and obtain editable documents; Based on the editable document and combined with the ontology model, triples are obtained through knowledge extraction; The ontology model includes industrial data collection knowledge ontology; The conceptual hierarchical architecture of the industrial data acquisition knowledge ontology is expressed as: C knowledge ={ DO,CP,DQ,DS,DCP} Among them, DO refers to data object, CP refers to collection plan, DQ refers to data quality, DS refers to data security, and DCP refers to data collection protocol; The industrial data collection knowledge ontology is defined as a quaternion: {CON,NEL,ATT,REA} Among them, CON refers to concept, NEL refers to relationship, ATT refers to attribute, and REA refers to inference rule; Based on the triples, knowledge association is performed through a machine-readable industrial data collection knowledge association model to obtain a knowledge graph; The machine-readable industrial data collection knowledge association model is expressed as: SIDCKAM={IDCS{DO,CP,DQ,DS,DCP},REL(idc),ATT(idc), REA (idc)} Among them, IDCS refers to industrial data collection standard knowledge, DO, CP, DQ, DS, and DCP refer to data objects, collection planning, data quality, data security, and data collection protocol, respectively, REL (idc) refers to IDCS relationship set, ATT (idc) refers to attributes, and REA (idc) refers to inference rules; Adopting the industrial data acquisition knowledge reasoning analysis model, calling the knowledge graph, and obtaining the reasoning analysis knowledge base; Based on the reasoning analysis knowledge base and in combination with scenario requirements, the adaptability of different data collection protocols is evaluated; Based on the inference analysis knowledge base, evaluating the data quality of data sets collected by different data collection protocols; The data quality evaluation criteria include data integrity, data accuracy, data redundancy and data consistency, and the constraints related to data integrity include non-empty constraints and continuity constraints, the constraints related to data accuracy include value range constraints, code constraints and logical dependency constraints, the constraints related to data redundancy include equivalued function dependency constraints, and the constraints related to data consistency include equivalued consistency dependency constraints, logical consistency dependency constraints and existence consistency dependency constraints.

2. The data acquisition protocol adaptation analysis method based on a machine-readable model according to claim 1, characterized in that: The knowledge extraction includes: extracting the common elements in the protocol standard through XML tags, and then extracting the triples through dependency syntax analysis.

3. The data acquisition protocol adaptation analysis method based on a machine-readable model according to claim 1, characterized in that: The scenario requirements include: transmission distance, energy consumption, transmission frequency and transmission speed of the protocol.

4. A data acquisition protocol adaptation and analysis system based on a machine-readable model, characterized in that: include: A data acquisition module is configured to: acquire the protocol standard required for industrial data acquisition, perform format conversion through optical character recognition, and obtain an editable document; A knowledge management module is configured to: obtain triples through knowledge extraction based on the editable document and the ontology model; The ontology model includes industrial data collection knowledge ontology; The conceptual hierarchical architecture of the industrial data acquisition knowledge ontology is expressed as: C knowledge ={ DO,CP,DQ,DS,DCP} Among them, DO refers to data object, CP refers to collection plan, DQ refers to data quality, DS refers to data security, and DCP refers to data collection protocol; The industrial data collection knowledge ontology is defined as a quaternion: {CON,NEL,ATT,REA} Among them, CON refers to concept, NEL refers to relationship, ATT refers to attribute, and REA refers to inference rule; A knowledge graph module is configured to: based on the triples, collect knowledge association models using machine-readable industrial data, perform knowledge association, and obtain a knowledge graph; The reasoning analysis module is configured to: adopt the industrial data acquisition knowledge reasoning analysis model, call the knowledge graph, and obtain a reasoning analysis knowledge base; The machine-readable industrial data collection knowledge association model is expressed as: SIDCKAM={IDCS{DO,CP,DQ,DS,DCP},REL(idc),ATT(idc), REA (idc)} Among them, IDCS refers to industrial data collection standard knowledge, DO, CP, DQ, DS, and DCP refer to data objects, collection planning, data quality, data security, and data collection protocol, respectively, REL (idc) refers to IDCS relationship set, ATT (idc) refers to attributes, and REA (idc) refers to inference rules; Based on the inference analysis knowledge base, evaluating the data quality of data sets collected by different data collection protocols; The evaluation criteria for data quality include data integrity, data accuracy, data redundancy and data consistency, and the constraints related to data integrity include non-empty constraints and continuity constraints, the constraints related to data accuracy include value range constraints, code constraints and logical dependency constraints, the constraints related to data redundancy include equivalent function dependency constraints, and the constraints related to data consistency include equivalent consistency dependency constraints, logical consistency dependency constraints and existence consistency dependency constraints; The application evaluation module is configured to evaluate the adaptability of different data acquisition protocols based on the reasoning analysis knowledge base and in combination with scenario requirements.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the data acquisition protocol adaptation analysis method based on a machine-readable model as described in any one of claims 1 to 3 are implemented.

6. A computer device comprising a computer-readable storage medium, a processor, and a computer program stored on the computer-readable storage medium and executable on the processor, characterized in that: When the processor executes the program, the steps in the data acquisition protocol adaptation and analysis method based on a machine-readable model as described in any one of claims 1 to 3 are implemented.

7. A computer program product, which is a computer program product containing a computer program, characterized in that When the processor executes the computer program, the steps in the data acquisition protocol adaptation analysis method based on a machine-readable model as described in any one of claims 1 to 3 are implemented.