Production equipment operation management and control information model construction method and device and storage medium

Abstract

The invention provides a production equipment operation management and control information model construction method and device and a storage medium, and the method comprises the steps: carrying out the type and relation division of a production equipment operation management and control information meta-model, and obtaining a plurality of information meta-models; carrying out data acquisition to obtain production equipment operation management and control field data; extracting production equipment operation management and control field knowledge, and constructing a production equipment operation management and control field knowledge triple through knowledge fusion; extracting the production equipment operation management and control field knowledge triple to obtain a production equipment operation management and control field ontology; supplementing production equipment operation management and control field knowledge entities, attributes and relationships, supplementing hierarchical relationships among production equipment operation management and control field ontologies, and forming a production equipment operation management and control field knowledge graph; and performing mapping conversion on information entities, attributes and relationships in the production equipment operation management and control information model, and constructing the production equipment operation management and control information model. And the adaptability of the multi-source heterogeneous model in the field of production equipment operation management and control is improved.

Description

Technical Field

[0001] The present invention relates to the field of model building technology, and in particular to a method, device and storage medium for building a production equipment operation control information model. Background Art

[0002] The production equipment operation control information model refers to a model that abstractly expresses and organizes information related to production equipment operation control. It is used to standardize the description of the entities, attributes and relationships between entities of production equipment operation control information.

[0003] At present, the construction of production equipment operation control information model generally adopts the forward development idea of ​​"information meta-model-general information model-special information model".

[0004] However, this forward research and development approach only relies on the knowledge and experience of experts in specific fields, which is insufficient to fully reflect the potential common laws contained in the extensive engineering practices in the current field of production equipment operation and control, and has not yet fully utilized the value of multi-source and heterogeneous production equipment operation and control engineering practice data. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a method, device and storage medium for constructing a production equipment operation control information model to support data interaction, information sharing and knowledge collaboration of production equipment operation control functional activities, and effectively address the problem of insufficient adaptability of multi-source heterogeneous models in the field of production equipment operation control.

[0006] In the first aspect, an embodiment of the present invention provides a method for constructing a production equipment operation control information model, which classifies the production equipment operation control information metamodel into categories and relationships to obtain multiple information metamodels; there are corresponding relationships between the multiple information metamodels; data is collected based on a pre-set production equipment operation control field to obtain production equipment operation control field data; production equipment operation control field knowledge is extracted from the production equipment operation control field data, and production equipment operation control field knowledge triples are constructed through knowledge fusion; production equipment operation control field knowledge includes: production equipment operation control field knowledge entities, attributes and relationships; based on the production equipment operation control information metamodel, the production equipment operation control field knowledge triples are refined to obtain the production equipment operation control field ontology; through knowledge reasoning and quality assessment, the production equipment operation control field knowledge entities, attributes and relationships are supplemented, and the hierarchical relationships between the production equipment operation control field ontologies are supplemented to form a production equipment operation control field knowledge graph; based on the production equipment operation control field knowledge graph, the information entities, attributes and relationships in the production equipment operation control information model are mapped and transformed to construct a production equipment operation control information model.

[0007] In a preferred embodiment of the present invention, the above-mentioned production equipment operation control information metamodel is divided into categories and relationships to obtain multiple information metamodels, including: based on pre-set metamodel types, the production equipment operation control information metamodel is divided into categories to obtain multiple information metamodels; metamodel types include: object class, capability class, process class and rule class; based on pre-set relationship types, the relationships of multiple information metamodels are divided into relationships; relationship types include: dependency, realization, association, generalization, aggregation and combination.

[0008] In a preferred embodiment of the present invention, when the metamodel type is an object class, the meta-attributes of the information metamodel include: object name, object type, object characteristics, object value, and value unit; when the metamodel type is a capability class, the meta-attributes of the information metamodel include: capability name, capability characteristics, capability value, value unit, capability type, start time, and end time; when the metamodel type is a process class, the meta-attributes of the information metamodel include: process name, process request, process execution, process response, process status, start time, and end time; when the metamodel type is a rule class, the meta-attributes of the information metamodel include: rule name, rule type, rule description, rule structure, rule behavior, rule status, applicable scope, and update time.

[0009] In a preferred embodiment of the present invention, the above-mentioned extraction of production equipment operation control domain knowledge from production equipment operation control domain data and construction of production equipment operation control domain knowledge triples through knowledge fusion include: based on the acquired first model, extracting production equipment operation control domain knowledge entities, attributes and relationships from production equipment operation control domain data; based on the text editing distance method and the set difference distance method, cleaning the production equipment operation control domain knowledge entities, attributes and relationships to obtain production equipment operation control domain knowledge triples; the production equipment operation control domain knowledge triples include: <entity-relationship-entity> and <entity-attribute-attribute value>.

[0010] In a preferred embodiment of the present invention, knowledge triples in the field of production equipment operation control are refined based on the production equipment operation control information metamodel to obtain a production equipment operation control domain ontology, including: extracting knowledge ontology concepts from the production equipment operation control information metamodel; knowledge ontology concepts include objects, capabilities, processes and rules; constructing multiple knowledge triples based on the knowledge ontology concepts, and the multiple knowledge triples include: <object-has-capability>, <capability-support-process>, <process-call-rule>, <rule-constraint-capability>, <rule-association-object>, <process-includes-object>; constructing a production equipment operation control domain ontology with a hierarchical structure based on multiple knowledge triples.

[0011] In a preferred embodiment of the present invention, the above-mentioned knowledge entities, attributes and relationships in the field of production equipment operation control and the hierarchical relationships between the ontologies in the field of production equipment operation control are supplemented through knowledge reasoning and quality assessment to form a knowledge graph in the field of production equipment operation control, including: calculating the semantic similarity of entities in multiple knowledge triples with entities in the knowledge triples in the field of production equipment operation control to obtain semantic similarity; forming a parallel relationship among the entities of the knowledge triples whose semantic similarity is greater than a preset similarity threshold; based on a preset pattern, performing entity pair extraction processing on the entities of the knowledge triples whose semantic similarity is less than the similarity threshold to construct a hierarchical relationship between knowledge entities; the entity pair extraction processing is to extract entity pairs with a "containment" relationship; clustering processing is performed on entities at each level, and a production equipment operation control and management ontology with a tree structure is constructed through iterative reciprocation; through knowledge reasoning and quality assessment, the hierarchical structure of the production equipment operation control and management ontology and the entities, relationships, attributes and attribute values ​​of the production equipment operation control and management ontology are improved to construct a knowledge graph in the field of production equipment operation control and management.

[0012] In a preferred embodiment of the present invention, the above-mentioned knowledge graph based on the field of production equipment operation control is used to map and transform the information entities, attributes and relationships in the production equipment operation control information model to construct the production equipment operation control information model, including: taking the <entity-relationship-entity> knowledge triple as the first basic template and the knowledge ontology concept as the head entity; extracting the tail entity with a "contains" relationship with each head entity; taking the set of extracted tail entities as the information entity in the production equipment operation control information model; taking the <entity-attribute-attribute value> knowledge triple as the second basic template, extracting the information entities in the production equipment operation control information model; and taking the <entity-attribute-attribute value> knowledge triple as the second basic template. The relevant attribute set corresponding to the information entity; mapping the relevant attribute set into the information entity attributes in the production equipment operation control information model; normalizing the expression of the information entity attribute set based on the meta-attribute expression specification of the production equipment operation control information meta-model of the corresponding meta-model type; mapping the relationship between information entities in the production equipment operation control information model into dependency, realization, association, generalization, aggregation, and combination relationship types; based on the knowledge entities, attributes, and relationships in the production equipment operation control knowledge graph, mapping and transforming the information entities, attributes, and relationships in the production equipment operation control information model to construct a production equipment operation control information model.

[0013] In a preferred embodiment of the present invention, the above-mentioned data collection is performed based on the pre-set production equipment operation control field to obtain production equipment operation control field data, including: based on the production equipment operation control field, collecting structured, semi-structured and unstructured data to obtain production equipment operation control field data.

[0014] In a second aspect, an embodiment of the present invention further provides a device for constructing a production equipment operation control information model, including: a division module, used to classify the production equipment operation control information metamodel into categories and relationships to obtain multiple information metamodels; there are corresponding relationships between the multiple information metamodels; a data acquisition module, used to collect data based on a pre-set production equipment operation control field to obtain production equipment operation control field data; a knowledge triplet construction module, used to extract production equipment operation control field knowledge from production equipment operation control field data, and construct production equipment operation control field knowledge triples through knowledge fusion; production equipment operation control field knowledge includes: production equipment operation control field Domain knowledge entities, attributes and relationships; an extraction module, which is used to extract the knowledge triples in the production equipment operation control field based on the production equipment operation control information metamodel to obtain the production equipment operation control field ontology; a knowledge graph construction module, which is used to supplement the knowledge entities, attributes and relationships in the production equipment operation control field through knowledge reasoning and quality assessment, as well as the hierarchical relationships between the ontologies in the production equipment operation control field to form a knowledge graph in the production equipment operation control field; a production equipment operation control information model construction module, which maps and transforms the information entities, attributes and relationships in the production equipment operation control information model based on the production equipment operation control field knowledge graph to construct a production equipment operation control information model.

[0015] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the production equipment operation control information model construction method of the first aspect mentioned above.

[0016] The embodiments of the present invention bring the following beneficial effects: The embodiment of the present invention provides a method, device and storage medium for constructing a production equipment operation control information model, which obtains multiple information meta-models by classifying the production equipment operation control information meta-model into categories and relationships; there are corresponding relationships between the multiple information meta-models; data is collected based on a pre-set production equipment operation control field to obtain production equipment operation control field data; production equipment operation control field knowledge is extracted from the production equipment operation control field data, and production equipment operation control field knowledge triples are constructed through knowledge fusion; production equipment operation control field knowledge includes: production equipment operation control field knowledge entities, attributes and relationships; based on the production equipment operation control information meta-model, the production equipment operation control field knowledge triples are refined to obtain the production equipment operation control field ontology; through knowledge reasoning and quality assessment, the production equipment operation control field knowledge entities, attributes and relationships are supplemented, and the hierarchical relationships between the production equipment operation control field ontologies are supplemented to form a production equipment operation control field knowledge graph; based on the production equipment operation control field knowledge graph, the information entities, attributes and relationships in the production equipment operation control information model are mapped and transformed to construct the production equipment operation control information model. This approach supports data interaction, information sharing and knowledge collaboration in the functional activities of production equipment operation control, and effectively addresses the problem of insufficient adaptability of multi-source heterogeneous models in the field of production equipment operation control.

[0017] Other features and advantages of the present disclosure will be set forth in the following description, or some features and advantages may be inferred or unambiguously determined from the description, or may be learned by implementing the above-mentioned technology of the present disclosure.

[0018] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A flowchart of a method for constructing a production equipment operation control information model provided by an embodiment of the present invention; Figure 2 A flowchart of another method for constructing a production equipment operation control information model provided by an embodiment of the present invention; Figure 3A flowchart of another method for constructing a production equipment operation control information model provided by an embodiment of the present invention; Figure 4 A schematic diagram of the structure of a device for constructing a production equipment operation control information model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] The production equipment operation control information model refers to a model for abstract expression and organization management of information related to production equipment operation control, and is used to standardize the description of entities, attributes and relationships between entities of production equipment operation control information. At present, the construction of the production equipment operation control information model generally adopts the forward development idea of ​​"information metamodel-general information model-special information model". First, based on the experience and cognition of domain experts, an information metamodel in the field of equipment operation control is constructed, and the information elements contained in the general information model are clearly defined and defined at a higher level. Then, the general information model of production equipment operation control is constructed under the guidance of the information metamodel to support the standardized description and accurate expression of the common information elements of production equipment operation control. On this basis, a special information model for specific equipment operation control functional activities is constructed under the guidance of the general information model, and the general information model is customized and extended to meet the needs of information description of specific equipment operation control functional activities.

[0023] However, this forward research and development approach only relies on the knowledge and experience of experts in a specific field, which is not enough to fully reflect the potential common laws contained in the extensive engineering practice in the current field of production equipment operation control, and has not yet fully utilized the value of multi-source heterogeneous production equipment operation control engineering practice data. To this end, a research and development approach combining forward engineering and reverse engineering can be adopted. Forward engineering can be used to build an equipment operation control information meta-model based on prior knowledge accumulation, general description rules, basic operation logic, etc., and reverse engineering can be used to clean, filter and extract structured, semi-structured and unstructured production equipment operation control engineering practice data through data mining, knowledge graph and other technologies to form a knowledge graph in the field of equipment operation control with a reasonable structure, clear concepts and clear relationships. On this basis, guided by the information meta-model, a production equipment operation control information model is constructed through the mapping transformation from the knowledge graph to the information model to support the unified management, analysis and application of information related to production equipment operation control, thereby supporting the combined interaction and collaborative operation between different equipment operation control functions.

[0024] Based on this, an embodiment of the present invention provides a method, device and storage medium for constructing a production equipment operation control information model. Multiple information meta-models can be obtained by classifying the production equipment operation control information meta-model into categories and relationships. There are corresponding relationships between the multiple information meta-models. Data collection is performed based on a pre-set production equipment operation control field to obtain production equipment operation control field data. Production equipment operation control field knowledge is extracted from the production equipment operation control field data, and knowledge triples of production equipment operation control field knowledge are constructed through knowledge fusion. The production equipment operation control field knowledge includes: production equipment operation control field knowledge entities, attributes and relationships. Based on the production equipment operation control information meta-model, the production equipment operation control field knowledge triples are refined to obtain the production equipment operation control field ontology. The production equipment operation control field knowledge entities, attributes and relationships are supplemented through knowledge reasoning and quality assessment, as well as the hierarchical relationships between the production equipment operation control field ontologies to form a production equipment operation control field knowledge graph. Based on the production equipment operation control field knowledge graph, the information entities, attributes and relationships in the production equipment operation control information model are mapped and transformed to construct a production equipment operation control information model. This approach supports data interaction, information sharing and knowledge collaboration in the functional activities of production equipment operation control, and effectively addresses the problem of insufficient adaptability of multi-source heterogeneous models in the field of production equipment operation control.

[0025] To facilitate understanding of this embodiment, a method for constructing a production equipment operation control information model disclosed in an embodiment of the present invention is first introduced in detail.

[0026] Example 1 The embodiment of the present invention provides a method for constructing a production equipment operation control information model. Figure 1 A flowchart of a method for constructing a production equipment operation control information model provided by an embodiment of the present invention. Figure 1 As shown, the method for constructing the production equipment operation control information model may include the following steps: Step S101, classify the production equipment operation control information metamodel by category and relationship to obtain multiple information metamodels.

[0027] Among them, there are corresponding relationships between multiple information meta-models.

[0028] It should be noted that the classification and relationship classification of the production equipment operation control information metamodel can be understood as the definition of the production equipment operation control information metamodel. The production equipment operation control information metamodel generally includes meta-entities, meta-attributes, and meta-relationships between meta-entities, where meta-entities refer to abstract things in the field of equipment operation control, meta-attributes refer to the characteristics of meta-entities, and meta-relationships refer to the relationships or connections between meta-entities. The construction of meta-entities, meta-attributes, and meta-relationships requires highly abstract and refined professional domain knowledge of production equipment operation control, and a unified semantic description specification is given.

[0029] Specifically, the production equipment operation control information metamodel may be classified based on a preset metamodel type to obtain a plurality of information metamodels.

[0030] Among them, the metamodel types include: object class, capability class, process class and rule class; When the meta-model type is an object class, the meta-attributes of the information meta-model include: object name, object type, object property, object value, and value measurement unit.

[0031] Specifically, the equipment operation control object class information metamodel is mainly used to specify the common attribute structure and expression specifications of object class information entities in production equipment operation control activities, and can guide the construction of common information models for different object class entities.

[0032] The meta-attributes contained in the object class meta-entity can be: object name (MO_p1): unique identifier of object information; object type (MO_p2): abstraction of information with common characteristics expressed or represented by the object; object properties (MO_p3): additional information of the object, an object entity can have n object properties; object value (MO_p4): value of the object property, a set or range of values; unit of measurement of the value (MO_p5): if available, the unit of measurement of the corresponding property value.

[0033] When the meta-model type is capability class, the meta-attributes of the information meta-model include: capability name, capability characteristics, capability value, value unit, capability type, start time, and end time.

[0034] Specifically, the meta-model of equipment operation control capability information is mainly used to specify the common attribute structure and expression specifications of capability information entities in production equipment operation control activities, and can guide the construction of common information models for different capability entities. The meta-attributes contained in the capability meta-entity can be: capability name (MC_p1): unique identifier of capability information; capability characteristics (MC_p2): additional information and description of capability definition, a capability entity can have n capability characteristics; capability value (MC_p3): value of capability characteristics, set or range of values; unit of measurement of value (MC_p4): if available, the unit of measurement of the corresponding characteristic value; capability type (MC_p5): contains 6 types, specifically "1-used, 2-unused, 3-all, 4-available, 5-unavailable, 6-in-use"; start time (MC_p6): the start date and time of the period defining the capability type; end time (MC_p7): the end date and time of the period defining the capability type.

[0035] Among them, when the meta-model type is process class, the meta-attributes of the information meta-model include: process name, process request, process execution, process response, process status, start time, and end time.

[0036] Specifically, the equipment operation control process information metamodel is mainly used to specify the common attribute structure and expression specifications of process information entities in production equipment operation control activities, and can guide the construction of common information models for different process entities. The meta-attributes contained in the process meta-entity can be: process name MP_p1: the unique identifier of the process information; process request MP_p2: the process request related information generated to complete specific business goals or business needs; process execution MP_p3: the related information generated during the execution process based on the process request; process response MP_p4: the result feedback information obtained after the process execution is completed; process status MP_p5: contains 5 states, specifically "1-started, 2-waiting, 3-cancelled, 4-paused, 5-completed"; start time MP_p6: the start time of the process; end time MP_p7: the completion time of the process.

[0037] Among them, when the meta-model type is rule class, the meta-attributes of the information meta-model include: rule name, rule type, rule description, rule structure, rule behavior, rule status, applicable scope, and update time.

[0038] Specifically, the meta-model of equipment operation control rule information is mainly used to specify the common attribute structure and expression specifications of rule information entities in production equipment operation control activities, and can guide the construction of common information models for different rule entities. The meta-attributes contained in the rule meta-entity can be: rule name MR_p1: unique identifier of rule information; rule type MR_p2: abstract information with common characteristics expressed or represented by the rule; rule description MR_p3: additional information and description related to the rule; rule structure MR_p4: information on the components of the rule and the logical relationship between them; rule behavior MR_p5: response or execution information of the rule under specific conditions, and a rule entity can have n rule behaviors; rule status MR_p6: contains 5 states, specifically "1-published, 2-updated, 3-replaced, 4-suspended, 5-abandoned"; scope of application MR_p7: the scope of the field to which the rule applies; update time MR_p8: the date and time of rule update.

[0039] Specifically, the relationships of the plurality of information meta-models may be divided based on pre-set relationship types; the relationship types may include: dependency, realization, association, generalization, aggregation and combination.

[0040] Among them, dependency means that one information entity depends on the definition of another information entity; realization means that one information entity is the specific realization of another information entity; association means that there is a connection between two information entities in terms of functions, attributes, etc.; generalization means inheritance between information entities, and the behavioral characteristics of one information entity are inherited from another information entity; aggregation means that there is a relationship between the whole and the individual between information entities, and the whole and the individual can exist independently; combination means that there is a relationship between the whole and the individual between information entities, and the whole and the individual cannot exist independently.

[0041] Step S102, data collection is performed based on the pre-set production equipment operation control field to obtain production equipment operation control field data.

[0042] Specifically, data collection is performed based on a pre-set production equipment operation control field to obtain data in the production equipment operation control field, which may include: based on the production equipment operation control field, collecting structured, semi-structured and unstructured data to obtain data in the production equipment operation control field.

[0043] It should be noted that the data sources for production equipment operation control include not only structured data sources related to the production equipment operation control system, such as asset management system, inventory system, process system, scheduling system, process monitoring system, equipment health management system, etc., but also unstructured data sources such as equipment manuals, operating manuals, standards and specifications, work records, structural principles, and process rules. The data collection method is difficult to unify, and a general data collection template is needed to standardize the target content of data collection. The collection content mainly includes the number, name, description, input, output, constraint, support, etc. of the functional activity.

[0044] For ease of understanding, taking equipment failure repair activities as an example, Table 1 is a sample of production equipment operation control data collection (failure repair activities).

[0045] Table 1 Production equipment operation control data collection sample (fault repair activities)

[0046] Step S103, extracting production equipment operation control domain knowledge from production equipment operation control domain data, and constructing production equipment operation control domain knowledge triples through knowledge fusion.

[0047] Among them, the knowledge in the field of production equipment operation control includes: knowledge entities, attributes and relationships in the field of production equipment operation control.

[0048] Specifically, extracting knowledge in the field of production equipment operation control from data in the field of production equipment operation control, and constructing knowledge triples in the field of production equipment operation control through knowledge fusion, can include: extracting knowledge entities, attributes and relationships in the field of production equipment operation control from data in the field of production equipment operation control based on the acquired first model; cleaning knowledge entities, attributes and relationships in the field of production equipment operation control based on a text edit distance method and a set difference distance method to obtain knowledge triples in the field of production equipment operation control.

[0049] Among them, the knowledge triples in the field of production equipment operation control include two forms: <entity-relationship-entity> and <entity-attribute-attribute value>.

[0050] Among them, cleaning can include: eliminating duplication, redundancy and ambiguous information in knowledge entities, attributes and relationships to form unambiguous knowledge triples in the field of production equipment operation control.

[0051] Among them, the first model can be a BiLSTM-CRF model.

[0052] Among them, based on the first model obtained, knowledge entities, attributes and relationships in the field of production equipment operation control are extracted from the data in the field of production equipment operation control. Specifically, the data in the field of production equipment operation control is input into the BiLSTM neural network, and the semantic dependencies in the data are captured bidirectionally through the forward LSTM and backward LSTM, and then the semantic features are extracted to delete useless information, and the feature vector sequence of the solidified production equipment operation control semantic structure is formed; the feature vector sequence of the equipment operation control data sample obtained in the previous sequence is input into the CRF conditional random field, and the labels of the entities, relationships, and attributes in the feature vector sequence are calculated through the transfer score matrix to form the maximum probability label prediction results of "entity", "relationship", and "attribute" in the data sample; based on the maximum probability label prediction results of "entity", "relationship", and "attribute" in the data sample, the basic knowledge elements in the field of equipment operation control are constructed.

[0053] Specifically, the collected data in the field of production equipment operation control is input into the BiLSTM neural network, and the semantic dependencies in the data are captured bidirectionally through the forward LSTM and backward LSTM, and then the semantic features are extracted to delete useless information, and the feature vector sequence of the semantic structure of the production equipment operation control is formed. The BiLSTM calculation method is as follows:

[0054] in, Indicates the input equipment operation control data sample, Represents the historical information of the forward LSTM network, Represents the historical information of the backward LSTM network, Represents the forward LSTM operation result, Represents the result of the backward LSTM operation, It represents the feature vector sequence of the final output equipment operation control data sample, where t represents the state of the LSTM network at time t.

[0055] The equipment operation control data sample feature vector sequence obtained in the previous order Input into the CRF conditional random field, and calculate the labels of entities, relations, and attributes in the feature vector sequence through the transfer score matrix , forming the maximum probability label prediction result of "entity", "relationship" and "attribute" in the data sample. The CRF calculation method is as follows:

[0056] in, represents the input device operation control data sample feature vector sequence, and Y is the output label sequence , Is the label from arrive The transition probability, yes is marked as the i-th label probability.

[0057] Through the above operations, based on the input production equipment operation control data sample, the extracted entity set is described as , where n is the number of entities; the relationship set ,in Mainly used to describe entities and The relationship between , where q is the number of attributes.

[0058] Taking the equipment failure maintenance activity data sample as an example, we extracted the entity set E={vertical machining center, equipment failure, CNC workshop, thermistor, torque wrench, maintenance personnel,...}, the attribute set A={shutdown status, fault cause, fault name, maintenance strategy,...}, and the relationship set R={include, be included, replace,...}. E, A, and R constitute the basic knowledge elements in the field of equipment operation control.

[0059] Specifically, the text edit distance is a measure of the degree of difference between texts by calculating the minimum number of editing operations required to convert texts into each other. Editing operations include replacing one character with another, inserting a character, or deleting a character. The smaller the text edit distance, the higher the similarity between the two texts. The specific calculation method is as follows:

[0060] in, Represents the edit distance between the first i characters of Text1 and the first j characters of Text2. Indicates deleting a character from Text1. Indicates inserting a character in Text1. Indicates that Text1 and Text2 replace characters with each other, and each operation is the edit distance + 1.

[0061] Set difference mainly refers to the degree of difference between the character sets of two texts. The smaller the set difference, the higher the similarity between the two texts. The specific calculation formula is as follows:

[0062] The comprehensive distance between texts It is calculated by the weighted average of the text edit distance and the set difference distance, as follows:

[0063] in, is the weight of the text edit distance, is the weight of the set difference distance. The larger the value, the greater the difference between the two texts, and the smaller the value, the smaller the difference between the two texts.

[0064] Eliminate redundant entity collections , attribute set A and relationship set R are merged and converted into knowledge triples, mainly including <entity-relationship-entity> (< - - >) and <entity-attribute-attribute-value> (< - - >) in two forms.

[0065] Taking the equipment failure maintenance activity data sample as an example, the <entity-relationship-entity> (< - - >) in the form of knowledge triples, such as <vertical machining center-located-CNC workshop>, <vertical machining center-occurred-temperature compensation alarm>, etc.; get <entity-attribute-attribute value> (< - - >), such as <temperature compensation alarm-fault code-MA2094>, <thermistor-name-RA010>, etc. So far, the extraction, fusion and conversion of multi-source heterogeneous data from production equipment operation control to high-quality knowledge triples have been completed to support the subsequent ontology construction and knowledge graph generation.

[0066] Step S104: extracting the production equipment operation control domain knowledge triples based on the production equipment operation control information meta-model to obtain the production equipment operation control domain ontology.

[0067] Specifically, based on the production equipment operation control information metamodel, the knowledge triples in the production equipment operation control field are refined to obtain the production equipment operation control field ontology, which can include: extracting knowledge ontology concepts from the production equipment operation control information metamodel; the knowledge ontology concepts include objects, capabilities, processes and rules; constructing multiple knowledge triples based on the knowledge ontology concepts; and constructing a production equipment operation control field ontology with a hierarchical structure based on multiple knowledge triples.

[0068] Among them, four top-level knowledge ontology concepts of "object", "capability", "process" and "rule" are extracted from the production equipment operation control information metamodel, and six knowledge triples are constructed. The knowledge triples include: <object-has-capability>, <capability-support-process>, <process-call-rule>, <rule-constraint-capability>, <rule-association-object>, and <process-includes-object>.

[0069] Step S105, supplementing the knowledge entities, attributes and relationships in the field of production equipment operation control and the hierarchical relationships between ontologies in the field of production equipment operation control through knowledge reasoning and quality assessment, to form a knowledge graph in the field of production equipment operation control.

[0070] Among them, the entities in the knowledge triples can be processed accordingly by comparing the semantic similarity between the entities in the knowledge triples and the entities in the knowledge triples in the field of production equipment operation control, so as to complete the construction of the knowledge graph in the field of production equipment operation control.

[0071] Step S106, based on the knowledge graph in the field of production equipment operation control, map and transform the information entities, attributes and relationships in the production equipment operation control information model to construct the production equipment operation control information model.

[0072] Among them, the head entity, tail entity and related attribute sets can be extracted by setting the basic template, so as to perform mapping conversion based on the knowledge graph in the field of production equipment operation control and management, and complete the conversion of the production equipment operation control information model.

[0073] The method for constructing a production equipment operation control information model provided by an embodiment of the present invention can obtain multiple information meta-models by classifying the production equipment operation control information meta-model into categories and relationships; there are corresponding relationships between the multiple information meta-models; data is collected based on a pre-set production equipment operation control field to obtain production equipment operation control field data; production equipment operation control field knowledge is extracted from the production equipment operation control field data, and production equipment operation control field knowledge triples are constructed through knowledge fusion; production equipment operation control field knowledge includes: production equipment operation control field knowledge entities, attributes and relationships; based on the production equipment operation control information meta-model, the production equipment operation control field knowledge triples are refined to obtain the production equipment operation control field ontology; through knowledge reasoning and quality assessment, the production equipment operation control field knowledge entities, attributes and relationships are supplemented, and the hierarchical relationships between the production equipment operation control field ontologies are supplemented to form a production equipment operation control field knowledge graph; based on the production equipment operation control field knowledge graph, the information entities, attributes and relationships in the production equipment operation control information model are mapped and transformed to construct the production equipment operation control information model. This approach supports data interaction, information sharing and knowledge collaboration in the functional activities of production equipment operation control, and effectively addresses the problem of insufficient adaptability of multi-source heterogeneous models in the field of production equipment operation control.

[0074] Example 2 An embodiment of the present invention also provides another method for constructing a production equipment operation control information model; this method is implemented on the basis of the method in the above embodiment; this method focuses on describing a specific implementation method of supplementing the knowledge entities, attributes and relationships in the field of production equipment operation control through knowledge reasoning and quality assessment, and supplementing the hierarchical relationships between ontologies in the field of production equipment operation control to form a knowledge graph in the field of production equipment operation control.

[0075] Figure 2 A flowchart of another method for constructing a production equipment operation control information model provided by an embodiment of the present invention is shown in FIG. Figure 2 As shown, the knowledge entities, attributes and relationships in the field of production equipment operation control are supplemented through knowledge reasoning and quality assessment, and the hierarchical relationships between ontologies in the field of production equipment operation control are supplemented to form a knowledge graph in the field of production equipment operation control, which may include the following steps: Step S201 , calculating semantic similarity between entities in a plurality of knowledge triples and entities in knowledge triples in the field of production equipment operation control, to obtain semantic similarity.

[0076] Among them, the semantic similarity between the entities in the six knowledge triples and the entities in the knowledge triples in the field of production equipment operation control is calculated to obtain the semantic similarity.

[0077] Specifically, the six knowledge triples are put into the knowledge triple set in the field of equipment operation control to construct an ontology with a hierarchical structure. The semantic similarity of each entity in the knowledge triple set is calculated to determine whether different entities belong to the same semantic category, and the semantic similarity calculation method is as follows.

[0078]

[0079] in, and Represents two entities respectively. and represent and Two vectors mapped to the vector space, the cosine of the angle between the vectors As a measure and The measure of the semantic difference between the two, its value range is [-1,1], the closer the value is to 1, the and The more similar the semantics are.

[0080] Step S202 , entities of knowledge triples whose semantic similarity is greater than a preset similarity threshold are grouped into parallel relationships.

[0081] Specifically, by calculating the semantic similarity, the semantic similarity between any two given entities can be obtained. The higher the semantic similarity, the more likely the two entities belong to the same concept category and form a parallel relationship.

[0082] Among them, the parallel relationship is relative to the vertical conceptual hierarchical relationship. For example, "vertical machining center" and "horizontal lathe" are both entities of the equipment concept and have a higher parallel relationship; while "vertical machining center" and "maintenance personnel" are less likely to belong to the same semantic category, so they have a lower parallel relationship.

[0083] Step S203 , based on a preset pattern, entity pairs are extracted from entities of knowledge triples whose semantic similarity is less than a similarity threshold, so as to construct a hierarchical relationship between knowledge entities.

[0084] Among them, the entity pair extraction process is to extract entity pairs with a "contains" relationship.

[0085] The preset mode may be the Hearst mode.

[0086] Specifically, for entity sets with low parallel relationships, the Hearst model is used to automatically discover the ontology hyponymy relationship between different entities based on the syntactic pattern of the original text in which they are located, that is, to extract entity pairs with "Inclusion (IsA)" relationships. After completing the extraction of entity pairs with hierarchical relationships, the entities at each level are clustered, and one or more common hypernyms are assigned to each type of entity. Through iterative back-and-forth construction, a tree-structured production equipment operation control domain ontology is formed.

[0087] Taking the equipment failure maintenance knowledge triple as an example, the hypernym of "vertical machining center" is extracted as "equipment" based on the Hearst pattern, and "thermistor" belongs to the concept of "vertical machining center", thus finding the hierarchical relationship of "equipment", "vertical machining center" and "thermistor". Through the iterative operation of the above method, the existing concept hierarchy is continuously enriched and improved, so as to construct a hierarchical structure of the production equipment operation control domain ontology.

[0088] Among them, the principle of ontology hierarchical relationship extraction method based on Hearst pattern is shown in Table 2.

[0089] Table 2 Principle of ontology hierarchical relationship extraction method based on Hearst pattern Syntactic Pattern illustrate NP such as NP (or|and) NP Identify hypernyms and hyponyms within a group of things, such as equipment, e.g. vertical machining center, horizontal lathe, etc. NP, NP, (or|and) other NP Identify a group of things of the same level and their common superordinate concepts, such as vertical machining centers, horizontal lathes, and other equipment. NP, especially NP, (or|and) NP Identify containment relationships, such as: equipment, especially vertical machining centers, horizontal lathes, etc. NP, including NP, (or|and) NP Identify inclusion relationships, such as: equipment includes vertical machining centers, horizontal lathes, etc. NP is (a|an) NP Identify affiliations, such as: vertical machining center is a type of equipment. ...... ...... Step S204, clustering the entities at each level, and constructing a production equipment operation control domain ontology with a tree structure through iterative back-and-forth construction.

[0090] By clustering entities at each level, one or more common hypernyms can be assigned to each type of entity.

[0091] Step S205, through knowledge reasoning and quality assessment, improve the hierarchical structure of the ontology of the production equipment operation control field and the entities, relationships, attributes and attribute values ​​of the production equipment operation control field, and construct a knowledge graph of the production equipment operation control field.

[0092] Among them, through knowledge reasoning and quality assessment, the ontology hierarchical structure and the entities, relationships, attributes and attribute values ​​therein are improved, so as to construct a knowledge graph in the field of production equipment operation control.

[0093] Specifically, based on the relationship between existing entities, different knowledge entities are mapped to vector space reasoning to discover new related relationships to complete the relationship network in the knowledge graph. In addition, the ontology hierarchical structure and the entities, relationships, attributes and attribute values ​​therein are improved through quality assessment. Finally, a knowledge graph in the field of production equipment operation control is constructed. For example, circles can represent knowledge entities, ellipses represent attribute values, lines between knowledge entities represent relationships, and lines between knowledge entities and attribute values ​​represent attributes. "Objects, capabilities, processes, and rules" are the four top-level concepts. Knowledge entities connected to the four top-level concepts and having an "Include (IsA)" relationship are primary ontology, and knowledge entities connected to the primary ontology and having an "Include (IsA)" relationship are secondary ontology.

[0094] Example 3 An embodiment of the present invention also provides another method for constructing a production equipment operation control information model; this method is implemented on the basis of the method in the above-mentioned embodiment; this method focuses on describing a specific implementation method of mapping and transforming information entities, attributes and relationships in the production equipment operation control information model based on a knowledge graph in the field of production equipment operation control to construct a production equipment operation control information model.

[0095] Figure 3 A flowchart of another method for constructing a production equipment operation control information model provided by an embodiment of the present invention is shown in FIG. Figure 3 As shown, based on the knowledge graph in the field of production equipment operation control, the information entities, attributes and relationships in the production equipment operation control information model are mapped and converted to construct the production equipment operation control information model, which may include the following steps: Step S301, taking the <entity-relationship-entity> knowledge triple as the first basic template and taking the knowledge ontology concept as the head entity.

[0096] Among them, the top-level entities of "object", "capability", "process" and "rule" are used as head entities.

[0097] Step S302, extracting the tail entities that have a "contains" relationship with each head entity.

[0098] Among them, each top-level entity is taken as a head entity, and the tail entity having an "include" or IsA relationship with each head entity is extracted.

[0099] Step S303: taking the set of extracted tail entities as information entities in the production equipment operation control information model.

[0100] For example, for the "object" entity, a set of knowledge entities such as "equipment, materials, personnel, tools" can be extracted. For the extracted set of knowledge entities that have an IsA relationship with the four top-level entities, the knowledge entities connected to this layer in the knowledge graph are used as information entities in the general information model for production equipment operation control, thereby realizing the mapping conversion from knowledge entities in the knowledge graph to information entities in the information model.

[0101] Specifically, the four types of meta-entities "object MO", "capability MC", "process MP" and "rule MR" of the information meta-model layer are mapped to the general information model layer through the knowledge graph to form the corresponding general information entity sets GO, GC, GP and GR. Specifically, the following information entities are included: object-class general information entity set GO = {"equipment", "asset", "personnel", "raw materials", "product", "process", "communication network", "spare parts", "auxiliary devices", "energy medium", "embedded software", "data model", "management system"}; capability-class general information entity set GC = {"equipment capability", "asset capability", "personnel capability", "raw materials capability", "resource capability"}; process-class general information entity set GP = {"asset creation process", "asset use process", "asset disposal process", "equipment scheduling process", "process configuration process", "resource configuration process", "fault diagnosis process", "fault repair process", "daily maintenance process"}; rule-class general information entity set GR = {"asset management rules", "equipment scheduling rules", "process control rules", "resource configuration rules", "repair and maintenance rules", "asset value measurement model", "operation performance optimization model", "fault diagnosis model"}.

[0102] Step S304: Using the <entity-attribute-attribute value> knowledge triple as the second basic template, extract the relevant attribute set corresponding to the information entity in the production equipment operation control information model.

[0103] Specifically, based on the knowledge entity set with IsA relationship with the four top-level entities extracted in step S303, the knowledge triple of <entity-attribute-attribute value> is used as the basic template to extract the relevant attribute set corresponding to the knowledge entity. Based on the attribute definition of each type of information in the production equipment operation control information meta-model, the semantic similarity of the knowledge entity attribute and the meta-attributes of the corresponding type of information meta-entity is obtained, and the meta-attribute that should be used to express the knowledge entity attribute is determined based on the result, and then the relevant attributes connected to the knowledge entity at this level in the knowledge graph are mapped and converted into the attributes of the information entity in the general information model of production equipment operation control. For example, there is a knowledge entity "equipment", which contains attributes such as "name, location, status", etc. For the attributes such as "name, location, status" of the knowledge entity "equipment", the "name" attribute conforms to the "object ID (name)" in the attribute description rule of the object class information meta-model, and the "location" and "status" attributes conform to the "object characteristics" in the description rule, and then the corresponding mapping can be performed. For the attributes of the information entity obtained by the previous mapping transformation, the attribute set of the information entity is standardized based on the meta-attribute expression specification of the corresponding type of information meta-entity, thereby completing the concretization of the meta-attributes from the meta-model layer to the attributes in the general information model layer.

[0104] Step S305: Mapping the relevant attribute set into information entity attributes in the production equipment operation control information model.

[0105] Specifically, taking the general information entity "equipment scheduling process" in the process-type general information entity set GP as an example, the <entity-attribute-attribute value> knowledge triple is used as a template to extract the attribute set of the corresponding knowledge entity from the knowledge graph, and further mapped and transformed to form the corresponding information entity attribute set.

[0106] Step S306 , based on the meta-attribute expression specification of the production equipment operation control information meta-model of the corresponding meta-model type, a standardized expression of the information entity attribute set is performed.

[0107] For example, based on the meta-attribute expression specification of the process-type information meta-entity, its attribute set is expressed as equipment scheduling process = {"task name", "scheduling task request", "scheduling task assignment", "scheduling result feedback", "task status", "task start time", "task completion time"}.

[0108] Among them, the meta-attribute normalized expression of the object class meta-entity MO can be: MO={MO_p1, MO_p2,<MO_p3_i,MO_p4_i,MO_p5_i>}(1 ).

[0109] Among them, object characteristics, object values ​​and value measurement units correspond to each other.<MO_p3_i,MO_p4_i,MO_p5_i> Represents a set of object properties, object values, and value units. The n object properties of an object entity can be listed in this combination. The object value and value unit corresponding to each object property can be empty.

[0110] The meta-attribute normalized expression of the capability meta-entity MC can be: MC={MC_p1,<MC_p2_i,MC_p3_i,MC_p4_i> , MC_p5_j, MC_p6, MC_p7} (1≤i≤n), (1≤j≤6).

[0111] Among them, the ability characteristics, ability values ​​and value units correspond to each other.<MC_p2_i,MC_p3_i,MC_p4_i> Represents a set of capability characteristics, capability values ​​and value units. The n capability characteristics of a capability entity can be listed in this combination. The capability value and value unit corresponding to each capability characteristic can be empty; the capability type attribute MC_p5_j of the capability entity can have 6 options, that is, MC_p5_j=j. For specific values, see the detailed description of the capability type above.

[0112] Among them, the meta-attributes of the process meta-entity MP are standardized as follows: MP={MP_p1, MP_p2, MP_p3, MP_p4, MP_p5_j, MP_p6, MP_p7} (1≤j≤5).

[0113] Among them, the process state attribute MP_p5_j of the process entity can have 5 options, that is, MP_p5_j=j. The specific values ​​can be found in the detailed description of the process state above.

[0114] The meta-attribute normalized expression of the rule-type meta-entity MR can be: MR={MR_p1, MR_p2, MR_p3, MR_p4,<MR_p5_i> , MR_p6_j, MR_p7, MR_p8} (1≤i≤n), (1≤j≤5).

[0115] Among them,<MR_p5_i> It represents the rule behavior of the rule entity. The n rule behaviors of the rule entity can be listed in sequence in this form. The rule state attribute MR_p6_j of the rule entity can have 5 options, that is, MR_p6_j=j. The specific value can be found in the detailed description of the rule state above.

[0116] Step S307, converting the relationship mapping between information entities in the production equipment operation control information model into dependency, realization, association, generalization, aggregation, and combination relationship types.

[0117] Specifically, in addition to the "inclusion" relationship, the common relationships between knowledge entities in production equipment operation control also include "possession, support, call, association, involvement, constraint" and other relationship types. The relationships between these knowledge entities need to be mapped to the relationships between information entity concepts. The common relationships between information entities are "dependency, realization, association, generalization, aggregation, and combination". The mapping rules of common knowledge entity relationships to information entity relationships are shown in Table 3. For example, the relationship between the two knowledge entities "object" and "capability" in the knowledge triple <object-possession-capability> is "possession", and the relationship between the two information entities "object" and "capability" in the information model is "dependency". In actual operation, it is necessary to further combine expert experience to complete the mapping transformation from the knowledge entity relationship in the knowledge graph to the information entity relationship in the information model. In addition, since there are related relationships between information entities of the same type, four types of related relationships within information entities are designed for this purpose.

[0118] In the mapping transformation rules from knowledge entity relationships to information entity relationships presented in Table 3, the 7th and 8th mapping transformation rules map the "inclusion" relationship between (object and object, capability and capability) knowledge entities to the "association / aggregation / combination" relationship between corresponding information entities. According to Table 1, the "association" relationship between information entities indicates the interactive and cooperative relationship between the two, which is the weakest of the three relationships; the "aggregation" relationship indicates the relationship between the part and the whole, and the part and the whole can exist independently; the "combination" relationship, as a special form of aggregation relationship, indicates that the part cannot exist independently from the whole. Therefore, the three relationships of association, aggregation, and combination between information entities reflect the closeness of the relationship between information entities from weak to strong. By calculating the semantic similarity between two knowledge entities (the higher the similarity, the stronger the correlation between the two knowledge entities, and vice versa), the "inclusion" relationship between object and object, capability and capability knowledge entities is mapped and converted into one of the "association / aggregation / combination" relationships between corresponding information entities according to the relevant threshold of semantic similarity.

[0119] Table 3 General rules for mapping knowledge entity relationships to information entity relationships

[0120] Step S308, based on the knowledge entities, attributes, and relationships in the production equipment operation control knowledge graph, the information entities, attributes, and relationships in the production equipment operation control information model are mapped and transformed to construct a production equipment operation control information model.

[0121] Specifically, based on the mapping and transformation of knowledge entities, attributes, and relationships in the knowledge graph of production equipment operation control to information entities, attributes, and relationships in the information model, a set of general information reference model for production equipment operation control is constructed and described using the UML class diagram syntax specification.

[0122] The overall solution of the present invention has at least the following advantages compared with the related art: 1) The present invention breaks through the conventional information model construction path of "information metamodel-general information model-special information model", and adopts the development idea of ​​"forward engineering + reverse engineering" to construct a production equipment operation control information model that fully reflects the knowledge concepts and extensive engineering practice experience in the specific field of production equipment operation control. The production equipment operation control information metamodel is formed by analyzing the knowledge concept design in the field of production equipment operation control. In the reverse direction, the multi-source heterogeneous engineering practice data of production equipment operation control containing potential common laws are mined, analyzed and refined through the "data-information-knowledge" method, and the production equipment operation control knowledge graph is constructed under the guidance of the equipment operation control information metamodel. On this basis, the production equipment operation control information model is formed through the mapping of entities, attributes and relationships from the knowledge graph to the information model to support data interaction, information sharing and knowledge collaboration of production equipment operation control functional activities, which effectively addresses the problem of insufficient adaptability of multi-source heterogeneous models in the field of production equipment operation control.

[0123] 2) The present invention innovatively proposes a mapping conversion rule from knowledge graph to information model, and generates a general information reference model for equipment operation control based on the rule. By locating the four top-level entities of "object", "capability", "process" and "rule" in the knowledge graph of production equipment operation control, using the <entity-relationship-entity> knowledge triple as the basic template, taking each top-level entity as the head entity, extracting the tail entity with a "contains" relationship with each head entity, and realizing the mapping conversion from the knowledge entity in the knowledge graph to the information entity in the information model. Based on the extracted knowledge entity set with a "contains" relationship with the four top-level entities, using the <entity-attribute-attribute value> knowledge triple as the basic template, extract the relevant attribute set corresponding to the knowledge entity, and realize the mapping conversion and standardized expression from the knowledge entity attribute in the knowledge graph to the information entity attribute. Referring to the relationship between the four top-level knowledge ontologies given by the top-level knowledge ontology triple of production equipment operation control, the mapping conversion from the knowledge entity, attribute, and relationship in the knowledge graph to the information entity, attribute, and relationship in the information model is realized.

[0124] Example 4 Corresponding to the above method embodiment, the embodiment of the present invention provides a device for constructing a production equipment operation control information model, Figure 4A schematic diagram of a production equipment operation control information model building device provided by an embodiment of the present invention is shown in FIG. Figure 4 As shown, the production equipment operation control information model building device may include: The division module 401 is used to divide the production equipment operation control information meta-model into categories and relationships to obtain multiple information meta-models; there are corresponding relationships between the multiple information meta-models.

[0125] The data collection module 402 is used to collect data based on a preset production equipment operation control field to obtain production equipment operation control field data.

[0126] The knowledge triplet construction module 403 is used to extract production equipment operation control domain knowledge from production equipment operation control domain data, and construct production equipment operation control domain knowledge triplet through knowledge fusion; production equipment operation control domain knowledge includes: production equipment operation control domain knowledge entities, attributes and relationships.

[0127] The refining module 404 is used to refine the production equipment operation control domain knowledge triples based on the production equipment operation control information meta-model to obtain the production equipment operation control domain ontology.

[0128] The knowledge graph construction module 405 is used to supplement the knowledge entities, attributes and relationships in the field of production equipment operation control and the hierarchical relationships between ontologies in the field of production equipment operation control through knowledge reasoning and quality assessment, so as to form a knowledge graph in the field of production equipment operation control.

[0129] The production equipment operation control information model construction module 406 is used to map and transform the information entities, attributes and relationships in the production equipment operation control information model based on the knowledge graph of the production equipment operation control field, and construct the production equipment operation control information model.

[0130] The production equipment operation control information model construction device provided by the embodiment of the present invention obtains multiple information meta-models by classifying the production equipment operation control information meta-model into categories and relationships; there are corresponding relationships between the multiple information meta-models; data is collected based on the pre-set production equipment operation control field to obtain production equipment operation control field data; production equipment operation control field knowledge is extracted from the production equipment operation control field data, and production equipment operation control field knowledge triples are constructed through knowledge fusion; production equipment operation control field knowledge includes: production equipment operation control field knowledge entities, attributes and relationships; based on the production equipment operation control information meta-model, the production equipment operation control field knowledge triples are refined to obtain the production equipment operation control field ontology; through knowledge reasoning and quality assessment, the production equipment operation control field knowledge entities, attributes and relationships are supplemented, and the hierarchical relationships between the production equipment operation control field ontologies are supplemented to form a production equipment operation control field knowledge graph; based on the production equipment operation control field knowledge graph, the information entities, attributes and relationships in the production equipment operation control information model are mapped and transformed to construct the production equipment operation control information model. This approach supports data interaction, information sharing and knowledge collaboration in the functional activities of production equipment operation control, and effectively addresses the problem of insufficient adaptability of multi-source heterogeneous models in the field of production equipment operation control.

[0131] In some embodiments, the partitioning module is also used to classify the production equipment operation control information metamodel based on pre-set metamodel types to obtain multiple information metamodels; the metamodel types include: object class, capability class, process class and rule class; the relationships of multiple information metamodels are partitioned based on pre-set relationship types; the relationship types include: dependency, realization, association, generalization, aggregation and combination.

[0132] In some embodiments, when the metamodel type is an object class, the meta-attributes of the information metamodel include: object name, object type, object characteristics, object value, and unit of measurement of the value; when the metamodel type is a capability class, the meta-attributes of the information metamodel include: capability name, capability characteristics, capability value, unit of measurement of the value, capability type, start time, and end time; when the metamodel type is a process class, the meta-attributes of the information metamodel include: process name, process request, process execution, process response, process status, start time, and end time; when the metamodel type is a rule class, the meta-attributes of the information metamodel include: rule name, rule type, rule description, rule structure, rule behavior, rule status, scope of application, and update time.

[0133] In some embodiments, the knowledge triplet construction module is also used to extract knowledge entities, attributes and relationships in the field of production equipment operation control from the data in the field of production equipment operation control based on the acquired first model; based on the text editing distance method and the set difference distance method, the knowledge entities, attributes and relationships in the field of production equipment operation control are cleaned to obtain knowledge triples in the field of production equipment operation control; the knowledge triples in the field of production equipment operation control include: <entity-relationship-entity> and <entity-attribute-attribute value>.

[0134] In some embodiments, the refining module is also used to extract knowledge ontology concepts from the production equipment operation control information metamodel; the knowledge ontology concepts include objects, capabilities, processes and rules; based on the knowledge ontology concepts, multiple knowledge triples are constructed, and the multiple knowledge triples include: <object-has-capability>, <capability-support-process>, <process-call-rule>, <rule-constraint-capability>, <rule-association-object>, <process-includes-object>; based on multiple knowledge triples, a production equipment operation control domain ontology with a hierarchical structure is constructed.

[0135] In some embodiments, the knowledge graph construction module is also used to calculate the semantic similarity of entities in multiple knowledge triples with entities in the knowledge triples of the production equipment operation control field to obtain semantic similarity; the entities of the knowledge triples whose semantic similarity is greater than a preset similarity threshold are arranged in parallel relationship; based on a preset pattern, entity pairs are extracted for the entities of the knowledge triples whose semantic similarity is less than the similarity threshold to construct a hierarchical relationship between knowledge entities; the entity pair extraction is to extract entity pairs with a "containment" relationship; the entities at each level are clustered to form a production equipment operation control field ontology with a tree structure through iterative reciprocating construction; through knowledge reasoning and quality assessment, the hierarchical structure of the production equipment operation control field ontology and the entities, relationships, attributes and attribute values ​​of the production equipment operation control field ontology are improved to construct a knowledge graph in the production equipment operation control field.

[0136] In some embodiments, the production equipment operation control information model construction module is also used to use the <entity-relationship-entity> knowledge triple as the first basic template and the knowledge ontology concept as the head entity; extract the tail entity that has a "contains" relationship with each head entity; use the set of extracted tail entities as the information entity in the production equipment operation control information model; use the <entity-attribute-attribute value> knowledge triple as the second basic template to extract the relevant attribute set corresponding to the information entity in the production equipment operation control information model; map the relevant attribute set into the information entity attribute in the production equipment operation control information model; based on the meta-attribute expression specification of the production equipment operation control information meta-model of the corresponding meta-model type, perform a standardized expression of the information entity attribute set; map the relationship between the information entities in the production equipment operation control information model into dependency, realization, association, generalization, aggregation, and combination relationship types; based on the knowledge entities, attributes, and relationships in the production equipment operation control knowledge graph, map and transform the information entities, attributes, and relationships in the production equipment operation control information model to construct a production equipment operation control information model.

[0137] In some embodiments, the data collection module is also used to collect structured, semi-structured and unstructured data based on the production equipment operation control field to obtain production equipment operation control field data.

[0138] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0139] An embodiment of the present invention also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the above-mentioned production equipment operation control information model construction method. The specific implementation can be found in the method embodiment, which will not be repeated here.

[0140] The computer program product for the method of constructing a production equipment operation control information model provided in an embodiment of the present invention includes a computer-readable storage medium storing non-volatile program code executable by a processor. The instructions included in the program code can be used to execute the method described in the previous method embodiment. The specific implementation can be found in the method embodiment, which will not be repeated here.

[0141] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0142] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0143] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0144] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0145] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that can be executed by a processor. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., various media that can store program codes.

[0146] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for constructing a production equipment operation control information model, It is characterized in that The method comprises: The production equipment operation control information metamodel is divided into categories and relationships to obtain a plurality of information metamodels; corresponding relationships exist between the plurality of information metamodels; Data is collected based on the pre-set production equipment operation control field to obtain production equipment operation control field data; Extracting production equipment operation control domain knowledge from the production equipment operation control domain data, and constructing production equipment operation control domain knowledge triples through knowledge fusion; the production equipment operation control domain knowledge includes: production equipment operation control domain knowledge entities, attributes and relationships; Based on the production equipment operation control information meta-model, the production equipment operation control domain knowledge triples are refined to obtain the production equipment operation control domain ontology; Supplement the knowledge entities, attributes and relationships in the field of production equipment operation control and the hierarchical relationships between ontologies in the field of production equipment operation control through knowledge reasoning and quality assessment, so as to form a knowledge graph in the field of production equipment operation control; Based on the knowledge graph in the field of production equipment operation control, the information entities, attributes and relationships in the production equipment operation control information model are mapped and transformed to construct a production equipment operation control information model.

2. The method according to claim 1, It is characterized in that The production equipment operation control information meta-model is divided into categories and relationships to obtain multiple information meta-models, including: Classify the production equipment operation control information metamodel based on the preset metamodel types to obtain multiple information metamodels; the metamodel types include: object class, capability class, process class and rule class; The relationships of the plurality of information meta-models are divided based on the preset relationship types; the relationship types include: dependency, realization, association, generalization, aggregation and combination.

3. The method according to claim 2, It is characterized in that When the meta-model type is an object class, the meta-attributes of the information meta-model include: object name, object type, object property, object value, and value measurement unit; When the meta-model type is capability class, the meta-attributes of the information meta-model include: capability name, capability characteristics, capability value, value measurement unit, capability type, start time, and end time; When the metamodel type is a process class, the meta-attributes of the information metamodel include: process name, process request, process execution, process response, process status, start time, and end time; When the meta-model type is a rule class, the meta-attributes of the information meta-model include: rule name, rule type, rule description, rule structure, rule behavior, rule status, applicable scope, and update time.

4. The method according to claim 3, It is characterized in that The extracting of production equipment operation control domain knowledge from the production equipment operation control domain data and constructing a production equipment operation control domain knowledge triplet through knowledge fusion includes: Based on the acquired first model, extracting knowledge entities, attributes and relationships in the field of production equipment operation control from the production equipment operation control field data; Based on the text edit distance method and the set difference distance method, the knowledge entities, attributes and relationships in the field of production equipment operation control are cleaned to obtain knowledge triples in the field of production equipment operation control; the knowledge triples in the field of production equipment operation control include: <entity-relationship-entity> and <entity-attribute-attribute value>.

5. The method according to claim 4, It is characterized in that The production equipment operation control domain ontology is obtained by refining the production equipment operation control domain knowledge triples based on the production equipment operation control information meta-model, including: Extracting knowledge ontology concepts from the production equipment operation control information meta-model; the knowledge ontology concepts include objects, capabilities, processes and rules; Based on the knowledge ontology concept, a plurality of knowledge triples are constructed, wherein the plurality of knowledge triples include: <object-possess-capability>, <capability-support-process>, <process-call-rule>, <rule-constraint-capability>, <rule-association-object>, <process-include-object>; A production equipment operation control domain ontology with a hierarchical structure is constructed based on a plurality of the knowledge triples.

6. The method according to claim 5, It is characterized in that The knowledge entities, attributes and relationships in the field of production equipment operation control are supplemented through knowledge reasoning and quality assessment, and the hierarchical relationships between ontologies in the field of production equipment operation control are supplemented to form a knowledge graph in the field of production equipment operation control, including: Calculate semantic similarity between entities in the plurality of knowledge triples and entities in the production equipment operation control domain knowledge triples to obtain semantic similarity; The entities of the knowledge triples whose semantic similarity is greater than a preset similarity threshold are formed into parallel relationships; Based on a preset pattern, entity pairs are extracted from entities of the knowledge triples whose semantic similarity is less than the similarity threshold, so as to construct a hierarchical relationship between knowledge entities; the entity pair extraction process is to extract entity pairs with a "contains" relationship; Cluster entities at all levels and construct a tree-like production equipment operation control domain ontology through iterative reciprocation. Through the knowledge reasoning and the quality assessment, the hierarchical structure of the ontology in the field of production equipment operation control and management, as well as the entities, relationships, attributes and attribute values ​​in the field of production equipment operation control and management are improved, and a knowledge graph in the field of production equipment operation control and management is constructed.

7. The method according to claim 6, It is characterized in that Based on the knowledge graph of the production equipment operation control field, mapping and converting the information entities, attributes and relationships in the production equipment operation control information model to construct the production equipment operation control information model includes: Taking the <entity-relationship-entity> knowledge triple as the first basic template and taking the knowledge ontology concept as the head entity; Extracting tail entities having a "contains" relationship with each of the head entities; The set of extracted tail entities is used as the information entity in the production equipment operation control information model; Using the <entity-attribute-attribute value> knowledge triple as the second basic template, extracting the relevant attribute set corresponding to the information entity in the production equipment operation control information model; Mapping the relevant attribute set into information entity attributes in the production equipment operation control information model; Based on the meta-attribute expression specification of the production equipment operation control information meta-model of the corresponding meta-model type, the information entity attribute set is standardizedly expressed; Convert the relationship mapping between information entities in the production equipment operation control information model into dependency, realization, association, generalization, aggregation, and combination relationship types; Based on the knowledge entities, attributes and relationships in the production equipment operation control knowledge graph, the information entities, attributes and relationships in the production equipment operation control information model are mapped and transformed to construct a production equipment operation control information model.

8. The method according to claim 1, It is characterized in that The data collection based on the pre-set production equipment operation control field to obtain the production equipment operation control field data includes: Based on the production equipment operation control field, structured, semi-structured and unstructured data are collected to obtain production equipment operation control field data.

9. A device for constructing a production equipment operation control information model, It is characterized in that The device comprises: A division module is used to divide the production equipment operation control information meta-model into categories and relationships to obtain multiple information meta-models; there are corresponding relationships between the multiple information meta-models; A data collection module is used to collect data based on a preset production equipment operation control field to obtain data in the production equipment operation control field; A knowledge triplet construction module is used to extract production equipment operation control domain knowledge from the production equipment operation control domain data, and construct a production equipment operation control domain knowledge triplet through knowledge fusion; the production equipment operation control domain knowledge includes: production equipment operation control domain knowledge entities, attributes and relationships; An extraction module, used for extracting the production equipment operation control domain knowledge triples based on the production equipment operation control information meta-model to obtain the production equipment operation control domain ontology; A knowledge graph construction module is used to supplement the knowledge entities, attributes and relationships in the field of production equipment operation control and management through knowledge reasoning and quality assessment, and to supplement the hierarchical relationships between ontologies in the field of production equipment operation control and management, so as to form a knowledge graph in the field of production equipment operation control and management; The production equipment operation control information model construction module is used to map and transform the information entities, attributes and relationships in the production equipment operation control information model based on the knowledge graph of the production equipment operation control field, and construct the production equipment operation control information model.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to implement the method for constructing a production equipment operation control information model as described in any one of claims 1 to 8.

Images