CN114722158A - Method and system for matching numerical control machine tool manufacturing process based on subject word clustering - Google Patents
Method and system for matching numerical control machine tool manufacturing process based on subject word clustering Download PDFInfo
- Publication number
- CN114722158A CN114722158A CN202210613478.6A CN202210613478A CN114722158A CN 114722158 A CN114722158 A CN 114722158A CN 202210613478 A CN202210613478 A CN 202210613478A CN 114722158 A CN114722158 A CN 114722158A
- Authority
- CN
- China
- Prior art keywords
- information
- workpiece
- text
- attribute entity
- cutter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- General Factory Administration (AREA)
- Numerical Control (AREA)
Abstract
The invention discloses a method and a system for matching a manufacturing process of a numerical control machine tool based on subject word clustering, wherein the method comprises the following steps: acquiring a processing technology text, performing word marking on the processing technology text, determining cutter information and workpiece information in the processing technology text, and respectively determining first attribute entity information corresponding to the cutter information and second attribute entity information corresponding to the workpiece information; generating three-element group data according to the mapping relation between the cutter information and the first attribute entity information and the mapping relation between the workpiece information and the second attribute entity information; and matching target process information corresponding to the cutter information and the workpiece information based on the subject word model by taking the process information in the processing process text as a subject and the triple data as text words. The invention can realize the automatic matching of the cutter and the workpiece to the process information, realize the high-efficiency determination of the process information and provide a favorable basis for the manufacturing of the numerical control machine.
Description
Technical Field
The invention relates to the technical field of machining and manufacturing of numerical control machines, in particular to a method and a system for matching a manufacturing process of a numerical control machine based on subject word clustering.
Background
When a workpiece is machined by the numerical control machine tool, corresponding machining process information can be set for each workpiece according to machining requirements, the machining process information comprises machining steps, machining parameters and cutter information used in the machining process of the workpiece, each cutter information comprises the corresponding machining process step, namely, the cutter and the workpiece both comprise the corresponding machining process information, and when the numerical control machine tool machines a certain workpiece, the machining process information of the workpiece and a prop required to be used needs to be called out. In the prior art, the corresponding processing process information of the workpiece and the cutter is basically selected manually by a machine tool operator, and the efficiency is low.
Thus, there is a need for improvements and enhancements in the art.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a subject word clustering-based numerical control machine manufacturing process matching method and system aiming at solving the problems that the calling of the processing process information corresponding to a workpiece and a cutter is basically manually selected by a machine tool operator and the efficiency is low in the prior art.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
in a first aspect, the invention provides a method for matching a manufacturing process of a numerical control machine based on subject word clustering, wherein the method comprises the following steps:
acquiring a processing technology text, performing word marking on the processing technology text, determining cutter information and workpiece information in the processing technology text, and respectively determining first attribute entity information corresponding to the cutter information and second attribute entity information corresponding to the workpiece information;
generating three-element group data according to the mapping relation between the cutter information and the first attribute entity information and the mapping relation between the workpiece information and the second attribute entity information;
and matching target process information corresponding to the cutter information and the workpiece information based on a subject word model by taking the process information in the processing process text as a subject and the triple data as text words.
In one implementation, the obtaining a processing text, performing word tagging on the processing text, and determining tool information and workpiece information in the processing text includes:
collecting a technical manual, carding process files of the numerical control machine tool, and screening out the processing process texts for describing the processes;
performing word segmentation processing on the processing technology text to obtain word information;
performing semantic recognition on the vocabulary information, determining the cutter information and the workpiece information in the vocabulary information, and labeling the cutter information and the workpiece information.
In one implementation manner, the determining the first attribute entity information corresponding to the tool information and the second attribute entity information corresponding to the workpiece information respectively includes:
performing grammatical association analysis on the cutter information and the workpiece information based on grammatical features, and determining association sentences corresponding to the cutter information and the workpiece information;
and respectively determining first attribute entity information corresponding to the tool information and second attribute entity information corresponding to the workpiece information based on the associated statements.
In an implementation manner, after the obtaining a processing technology text, performing word tagging on the processing technology text, determining tool information and workpiece information in the processing technology text, and determining first attribute entity information corresponding to the tool information and second attribute entity information corresponding to the workpiece information, respectively, the method further includes:
and training a Bi-LSTM-CRF model based on the cutter information and the corresponding first attribute entity information, the workpiece information and the corresponding second attribute entity information, wherein the trained Bi-LSTM-CRF model is used for identifying the cutter information, the workpiece information and the corresponding attribute entity information of the processing process text.
In one implementation, the trained Bi-LSTM-CRF model includes a representation layer, a BiLSTM layer, and a CRF layer, where the representation layer is configured to identify word vectors and word vectors in the processing text, and the BiLSTM layer is configured to determine a score of each word in the processing text corresponding to all attribute entity information; the CRF layer is used for determining first attribute entity information corresponding to the cutter information and second attribute entity information corresponding to the workpiece information based on the probability that each word corresponds to all attribute entity information.
In one implementation manner, the matching of the target process information corresponding to the tool information and the workpiece information based on a topic word model with the process information in the processing process text as a topic and the triple data as text words includes:
clustering first attribute entity information and second attribute entity information in the triple data based on the subject word model, and determining first candidate process information corresponding to the first attribute entity information and second candidate process information corresponding to the second attribute entity from the processing process text;
and determining the target process information according to the first candidate process information and the second candidate process information.
In one implementation, the determining the target process information according to the first candidate process information and the second candidate process information includes:
determining the occurrence probability of the cutter information based on the first candidate process information, and determining cutter process information from the first candidate process information based on the occurrence probability of the cutter information;
determining the probability of the workpiece information based on the second candidate process information, and determining the workpiece process information from the second candidate process information based on the probability of the workpiece information;
and generating the target process information based on the cutter process information and the workpiece process information.
In a second aspect, a system for matching a manufacturing process of a numerical control machine based on topic word clustering is characterized in that the system comprises:
the attribute entity information determining module is used for acquiring a processing technology text, performing word marking on the processing technology text, determining cutter information and workpiece information in the processing technology text, and respectively determining first attribute entity information corresponding to the cutter information and second attribute entity information corresponding to the workpiece information;
the three-group data determining module is used for generating three-group data according to the mapping relation between the cutter information and the first attribute entity information and the mapping relation between the workpiece information and the second attribute entity information;
and the process information matching module is used for matching target process information corresponding to the cutter information and the workpiece information based on a subject word model by taking the process information in the processing process text as a subject and the triple data as text words.
In a third aspect, an embodiment of the present invention further provides a terminal device, where the terminal device includes a memory, a processor, and a program for matching a manufacturing process of a cnc machine based on subject word clustering, where the program is stored in the memory and is executable on the processor, and when the processor executes the program for matching a manufacturing process of a cnc machine based on subject word clustering, the step of implementing the method for matching a manufacturing process of a cnc machine based on subject word clustering according to any one of the above schemes is implemented.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where a matching program of a numerically controlled machine tool manufacturing process based on subject word clustering is stored on the computer-readable storage medium, and when the matching program of the numerically controlled machine tool manufacturing process based on subject word clustering is executed by a processor, the step of implementing the method for matching a numerically controlled machine tool manufacturing process based on subject word clustering according to any one of the foregoing schemes is implemented.
Has the advantages that: compared with the prior art, the invention provides a matching method of a numerical control machine manufacturing process based on subject word clustering, which comprises the steps of obtaining a processing process text, carrying out word marking on the processing process text, determining cutter information and workpiece information in the processing process text, and respectively determining first attribute entity information corresponding to the cutter information and second attribute entity information corresponding to the workpiece information; generating three-element group data according to the mapping relation between the cutter information and the first attribute entity information and the mapping relation between the workpiece information and the second attribute entity information; and matching target process information corresponding to the cutter information and the workpiece information based on a subject word model by taking the process information in the processing process text as a subject and the triple data as text words. The method and the device perform word labeling based on the preset processing technology text, then determine the cutter information and the workpiece information, and automatically match the target technology information corresponding to the cutter information and the workpiece information based on the subject word model, thereby realizing efficient matching of the technology information and improving the processing and manufacturing efficiency of the numerical control machine.
Drawings
Fig. 1 is a flowchart of a specific implementation of a method for matching a manufacturing process of a numerical control machine based on topic word clustering according to an embodiment of the present invention.
Fig. 2 is a schematic block diagram of a matching system for a manufacturing process of a numerical control machine tool based on subject word clustering according to an embodiment of the present invention.
Fig. 3 is a schematic block diagram of a terminal device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and effects of the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment provides a numerical control machine tool manufacturing process matching method based on subject term clustering, and based on the method of the embodiment, the quick matching of processing process information can be improved. Specifically, in this embodiment, a processing technology text is first obtained, word labeling is performed on the processing technology text, tool information and workpiece information in the processing technology text are determined, and first attribute entity information corresponding to the tool information and second attribute entity information corresponding to the workpiece information are respectively determined. And then generating ternary group data according to the mapping relation between the cutter information and the first attribute entity information and the mapping relation between the workpiece information and the second attribute entity information. And finally, matching target process information corresponding to the cutter information and the workpiece information based on a subject word model by taking the process information in the processing process text as a subject and the ternary group data as text words. Therefore, the word labeling is carried out on the basis of the preset processing technology text, then the cutter information and the workpiece information are determined, and the target technology information corresponding to the cutter information and the workpiece information is automatically matched on the basis of the subject word model, so that the efficient matching of the technology information is realized, and the processing and manufacturing efficiency of the numerical control machine tool is improved.
Exemplary method
The subject word clustering-based numerical control machine tool manufacturing process matching method in the embodiment can be applied to terminal equipment and a numerical control machine tool, wherein the terminal equipment can be a computer and is connected with the numerical control machine tool. The terminal device may also be directly set as an intelligent control module in the numerical control machine, and the intelligent control module may implement the method for matching a manufacturing process of a numerical control machine based on subject word clustering, specifically, as shown in fig. 1, the method for matching a manufacturing process of a numerical control machine based on subject word clustering in this embodiment includes the following steps:
step S100, a processing technology text is obtained, word marking is carried out on the processing technology text, cutter information and workpiece information in the processing technology text are determined, and first attribute entity information corresponding to the cutter information and second attribute entity information corresponding to the workpiece information are respectively determined.
The machining process text in this embodiment is a text of machining process information including a plurality of pieces of workpiece information and a plurality of pieces of tool information, the tool information reflects a tool and parameters thereof used by the numerical control machine tool in the machining and manufacturing process, and the piece of workpiece information reflects parameters of a workpiece to be machined by the numerical control machine tool. After the tool information and the workpiece information in the processing technique text are determined, in this embodiment, first attribute entity information corresponding to the tool information and second attribute entity information corresponding to the workpiece information are respectively determined. The first attribute entity information in this embodiment reflects specific information of the tool, and reflects that the tool is a tool provided in the numerical control machine, and reflects a name of the tool, a type of the tool, a function of the tool, a number of the tool, and the like, that is, after determining the tool information from the processing text, this embodiment further determines which tool the tool information specifically corresponds to in the numerical control machine. Similarly, the second attribute entity information in the present embodiment reflects specific information of a workpiece, and reflects information such as a name, a type, and a function of the workpiece. When the workpiece is divided, the workpiece can be divided according to the processing technology, for example, the workpiece processed by the numerically controlled lathe can be divided into turning workpieces, and the workpiece processed by the numerically controlled milling machine can be divided into milling workpieces. Therefore, after the workpiece information is determined from the machining process text, the workpiece information is further determined as to which workpiece corresponds.
In an implementation manner, the step S100 in this embodiment specifically includes the following steps:
s101, collecting a technical manual, carding process files of the numerical control machine tool, and screening out the processing process texts for describing processes;
step S102, performing word segmentation processing on the processing technology text to obtain word information;
step S103, performing semantic recognition on the vocabulary information, determining the cutter information and the workpiece information in the vocabulary information, and labeling the cutter information and the workpiece information.
Specifically, in this embodiment, a technical manual is collected first, and the technical manual may be an operation manual and a product introduction instruction of a numerical control machine tool, or may be a manufacturing manual of a certain workpiece or a certain device. Therefore, the technical manual in this embodiment includes a lot of public information of machining, and for this reason, this embodiment combs the process file of the numerical control machine tool based on the technical manual, and then screens out the text of the machining process for describing the process. Because the process file also includes other information, such as descriptions of a use scene and a use method of the workpiece or the tool, or some workpieces are not manufactured based on the machining of the numerical control machine tool, or only part of processes in the manufacturing process of some workpieces are processed by the numerical control machine tool, the embodiment needs to screen out contents for describing the process from the process file, so as to form the machining process text, so as to improve the accuracy in matching the tool information and the machining process information corresponding to the workpiece information in the subsequent steps.
The processing technology text is composed of a plurality of characters, and comprises information of workpieces, information of tools, parameters, processing steps and the like. Therefore, in order to obtain the tool information and the workpiece information in the machining process text, in this embodiment, after the machining process text is obtained, word segmentation is performed on the machining process text, where the word segmentation is performed by separating words in sentences in the machining process text to obtain word information, and then semantic recognition is performed on the word information, the tool information and the workpiece information in the word information are determined, and the tool information and the workpiece information are labeled. For example, when the "AA milling cutter" is recognized from the vocabulary information in the machining process text based on semantic recognition, the cutter information is the "AA milling cutter", and for example, when the "step axis" is recognized from the vocabulary information in the machining process text, the workpiece information is the "step axis".
Further, after tool information and workpiece information are determined, the embodiment performs syntax association analysis on the tool information and the workpiece information based on the syntax characteristics, and determines an association statement corresponding to the tool information and the workpiece information. The associated statement is a context statement which is linked with the cutter information and the workpiece information in a processing technology text. For example, after the tool information is "AA milling cutter", the position of the tool information "AA milling cutter" may be determined in the machining process text, then the context sentence of the tool information "AA milling cutter" is determined, and then the association sentence corresponding to "AA milling cutter" is determined from the context sentence. In one implementation, the related statement may be name information, type information, and function information of the tool information, or may be name information, machining type information, and parameters of the workpiece information, and the like. After the associated sentences are determined, the embodiment may extract words associated with the tool information or the workpiece information from the associated sentences, so as to determine, based on semantic recognition, first attribute entity information corresponding to the tool information and second attribute entity information corresponding to the workpiece information in the associated sentences. In this embodiment, the first attribute entity information is specific tool name and model information, and the second attribute entity information is specific workpiece name and parameter. The determination of the first attribute entity information and the second attribute entity information in the embodiment is beneficial to accurately and efficiently determining the target process information corresponding to the cutter information and the workpiece information in the subsequent steps.
In another implementation manner, after determining the tool information and the corresponding first attribute entity information thereof, and the workpiece information and the corresponding second attribute entity information thereof, this embodiment may further train a Bi-LSTM-CRF model based on the tool information and the corresponding first attribute entity information, the workpiece information and the corresponding second attribute entity information, where the trained Bi-LSTM-CRF model is used to identify the tool information, the workpiece information and the corresponding attribute entity information for the processing process text. The trained Bi-LSTM-CRF model comprises a representation layer, a BilSTM layer and a CRF layer, wherein the representation layer is used for identifying word vectors and word vectors in the processing text, and the BilSTM layer is used for determining the score of all attribute entity information corresponding to each word in the processing text; the CRF layer is used for determining first attribute entity information corresponding to the cutter information and second attribute entity information corresponding to the workpiece information based on the probability that each word corresponds to all attribute entity information. That is to say, after the tool information and the workpiece information are determined and labeled, the corresponding first attribute entity information and second attribute entity information are determined, and the first attribute entity information corresponds to the tool information and the second attribute entity information corresponds to the workpiece information, so that the Bi-LSTM-CRF model is trained based on the two corresponding relationships. After the training is finished, the trained Bi-LSTM-CRF model is input into the processing technology text, and the trained Bi-LSTM-CRF model can automatically output the cutter information and the corresponding first attribute entity information of the cutter information as well as the workpiece information and the corresponding second attribute entity information of the workpiece information, so that the cutter information and the workpiece information can be quickly found out from the processing technology text, and the corresponding first attribute entity information and the corresponding second attribute entity information can be accurately determined.
And S200, generating ternary group data according to the mapping relation between the cutter information and the first attribute entity information and the mapping relation between the workpiece information and the second attribute entity information.
After determining the tool information and the corresponding first attribute entity information thereof, and the workpiece information and the corresponding second attribute entity information thereof, this embodiment generates triple data according to the mapping relationship between the tool information and the first attribute entity information, and the mapping relationship between the workpiece information and the second attribute entity information. And the triple data reflects cutter information, first attribute entity information and workpiece information, second attribute entity information.
And step S300, matching target process information corresponding to the cutter information and the workpiece information based on a subject word model by taking the process information in the processing process text as a subject and the triple data as text words.
After the triple data are generated, the process information in the processing process text is used as a theme, the triple data are used as text words, and target process information corresponding to the cutter information and the workpiece information is automatically matched from the processing process text based on a theme word model. In this embodiment, the topic word model lda (latent Dirichlet allocation) is a document main body generation model, and also becomes a three-layer bayesian probability model, and includes three layers of structures, i.e., words, main bodies, and documents. The generative model is that each word of an article is obtained by selecting a topic with a certain probability and selecting the word from the topic with a certain probability. Therefore, based on the subject word model, the target process information corresponding to the tool information and the workpiece information can be quickly matched from the processing process text based on the mapping relationship between the tool information and the first attribute entity information and the mapping relationship between the workpiece information and the second attribute entity information in the triple data.
In one implementation, the determining the target process information in this embodiment includes the following steps:
step S301, clustering first attribute entity information and second attribute entity information in the triple data based on the subject term model, and determining first candidate process information corresponding to the first attribute entity information and second candidate process information corresponding to the second attribute entity from the processing process text;
step S302, determining the target process information according to the first candidate process information and the second candidate process information.
Specifically, in this embodiment, the first attribute entity information and the second attribute entity information in the triple data may be clustered based on the topic word model, and since the first attribute entity information in this embodiment is specific tool name and model information and the second attribute entity information is specific workpiece name and parameter, when the first attribute entity information and the second attribute entity information are clustered, a relationship between the first attribute entity information and the second attribute entity information may be determined, for example, when a workpiece is machined, the process information of the workpiece includes not only the machining step and parameters of the workpiece itself (i.e., corresponds to the workpiece information), but also the use step and model of the tool used in machining the workpiece (i.e., corresponds to the tool information). Therefore, in this embodiment, by clustering the first attribute entity information and the second attribute entity information, the first candidate process information corresponding to the first attribute entity information and the second candidate process information corresponding to the second attribute entity may be determined from the processing process text. At this time, the first candidate process information and the second candidate process information are information associated with the whole machining process of the workpiece, that is, the first candidate process information is the use step and the model of the tool used by the workpiece during machining, and the second candidate process information is the machining step and the parameter of the workpiece itself. Thus, after the first candidate process information is combined with the second candidate process information, the target process information can be obtained, and the target process information at the moment corresponds to both the cutter information and the workpiece information.
Specifically, since the names and the models of a plurality of tools are similar, the matched first candidate process information may include the use steps and the models of the tools used by other workpieces, but not the tools used by the workpiece, and in order to improve the matching accuracy, the embodiment acquires the occurrence probabilities of all the tool information in the first candidate process information, then screens out the tool information with the highest occurrence probability based on the occurrence probabilities of all the tool information, and then screens out the use steps, the models, and other information of the tools corresponding to the tool information with the highest occurrence probability as the tool process information. Similarly, in the embodiment, the second candidate process information may include processing steps and parameters of other workpieces, but not the processing steps and parameters of the workpiece, so that the embodiment acquires the occurrence probabilities of all the workpiece information in the second candidate process information, then selects the workpiece information with the highest occurrence probability based on the occurrence probabilities of all the workpiece information, and then selects the processing steps and parameters corresponding to the workpiece information with the highest occurrence probability as the workpiece process information. Finally, the target process information can be generated by combining the cutter process information and the workpiece process information.
In summary, in this embodiment, a processing technology text is first obtained, word labeling is performed on the processing technology text, tool information and workpiece information in the processing technology text are determined, and first attribute entity information corresponding to the tool information and second attribute entity information corresponding to the workpiece information are respectively determined. And then generating ternary group data according to the mapping relation between the cutter information and the first attribute entity information and the mapping relation between the workpiece information and the second attribute entity information. And finally, matching target process information corresponding to the cutter information and the workpiece information based on a subject word model by taking the process information in the processing process text as a subject and the ternary group data as text words. According to the method and the device, word labeling is carried out on the basis of the preset machining process text, then the cutter information and the workpiece information are determined, and the target process information corresponding to the cutter information and the workpiece information is automatically matched on the basis of the subject word model, so that efficient matching of the process information is achieved, and machining and manufacturing efficiency of the numerical control machine is improved.
Exemplary System
Based on the above embodiment, the present invention further provides a matching system for manufacturing process of a numerical control machine tool based on topic word clustering, as shown in fig. 2, the system includes: an attribute entity information determination module 10, a triple data determination module 20, and a process information matching module 30. Specifically, the attribute entity information determining module 10 is configured to obtain a processing technique text, perform word tagging on the processing technique text, determine tool information and workpiece information in the processing technique text, and determine first attribute entity information corresponding to the tool information and second attribute entity information corresponding to the workpiece information respectively. The triple data determining module 20 is configured to generate triple data according to a mapping relationship between the tool information and the first attribute entity information and a mapping relationship between the workpiece information and the second attribute entity information. The process information matching module 30 is configured to match target process information corresponding to the tool information and the workpiece information based on a subject word model, where the process information in the processing process text is used as a subject, the triple data is used as a text word, and the target process information is obtained.
In one implementation, the attribute entity information determining module 10 includes:
the processing technology text screening unit is used for collecting a technical manual, carding technology files of the numerical control machine tool and screening out the processing technology text for describing a technology;
the word segmentation processing unit is used for carrying out word segmentation processing on the processing technology text to obtain word information;
and the semantic recognition unit is used for performing semantic recognition on the vocabulary information, determining the cutter information and the workpiece information in the vocabulary information, and labeling the cutter information and the workpiece information.
In one implementation manner, the attribute entity information determining module 10 further includes:
the grammar correlation analysis unit is used for carrying out grammar correlation analysis on the cutter information and the workpiece information based on grammar features and determining correlation sentences corresponding to the cutter information and the workpiece information;
and the attribute entity determining unit is used for respectively determining first attribute entity information corresponding to the tool information and second attribute entity information corresponding to the workpiece information based on the association statement.
In one implementation manner, the attribute entity information determining module 10 further includes:
the model training unit is used for training a Bi-LSTM-CRF model based on the cutter information and the corresponding first attribute entity information, the workpiece information and the corresponding second attribute entity information, and the trained Bi-LSTM-CRF model is used for identifying the cutter information, the workpiece information and the corresponding attribute entity information of the processing process text; the trained Bi-LSTM-CRF model comprises a representation layer, a BilSTM layer and a CRF layer, wherein the representation layer is used for identifying word vectors and word vectors in the processing text, and the BilSTM layer is used for determining the score of all attribute entity information corresponding to each word in the processing text; the CRF layer is used for determining first attribute entity information corresponding to the cutter information and second attribute entity information corresponding to the workpiece information based on the probability that each word corresponds to all attribute entity information.
In one implementation, the process information matching module 30 includes:
the information clustering processing unit is used for clustering first attribute entity information and second attribute entity information in the triple data based on the subject term model, and determining first candidate process information corresponding to the first attribute entity information and second candidate process information corresponding to the second attribute entity from the processing process text;
and the process information determining unit is used for determining the target process information according to the first candidate process information and the second candidate process information.
In one implementation, the process information determining unit includes:
a first probability determination subunit, configured to determine the tool information occurrence probability based on the first candidate process information, and determine tool process information from the first candidate process information based on the probability of occurrence of the tool information;
a second probability determination subunit, configured to determine a probability of occurrence of the workpiece information based on the second candidate process information, and determine workpiece process information from the second candidate process information based on the probability of occurrence of the workpiece information;
and the process information generating subunit is used for generating the target process information based on the tool process information and the workpiece process information.
The working principle of each module in the matching device of the numerical control machine tool manufacturing process based on subject term clustering in the embodiment is the same as the principle of each step in the method embodiment, and the details are not repeated here.
Based on the above embodiments, the present invention further provides a terminal device, and a schematic block diagram of the terminal device may be as shown in fig. 3. The terminal equipment comprises a processor and a memory which are connected through a system bus, and the processor and the memory are arranged in a host. Wherein the processor of the terminal device is configured to provide computing and control capabilities. The memory of the terminal equipment comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the terminal equipment is used for communicating with an external terminal through network communication connection. The computer program is executed by a processor to realize a matching method of the numerical control machine manufacturing process based on subject word clustering.
It will be understood by those skilled in the art that the schematic block diagram shown in figure 3 is only a block diagram of a portion of the structure associated with the inventive solution and does not constitute a limitation of the numerically controlled machine tool to which the inventive solution is applied, a particular numerically controlled machine tool being intended to include more or fewer components than those shown in the figures, or to combine certain components, or to have a different arrangement of components.
In one embodiment, a numerical control machine tool is provided, the numerical control machine tool comprises a memory, a processor and a program of a numerical control machine manufacturing process matching method based on subject word clustering, which is stored in the memory and can run on the processor, and when the processor executes the program of the numerical control machine manufacturing process matching method based on subject word clustering, the following operation instructions are realized:
acquiring a processing technology text, performing word marking on the processing technology text, determining cutter information and workpiece information in the processing technology text, and respectively determining first attribute entity information corresponding to the cutter information and second attribute entity information corresponding to the workpiece information;
generating three-element group data according to the mapping relation between the cutter information and the first attribute entity information and the mapping relation between the workpiece information and the second attribute entity information;
and matching target process information corresponding to the cutter information and the workpiece information based on a subject word model by taking the process information in the processing process text as a subject and the triple data as text words.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, operational databases, or other media used in embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
In summary, the invention discloses a method and a system for matching a numerical control machine manufacturing process based on subject word clustering, wherein the method comprises the following steps: acquiring a processing technology text, performing word marking on the processing technology text, determining cutter information and workpiece information in the processing technology text, and respectively determining first attribute entity information corresponding to the cutter information and second attribute entity information corresponding to the workpiece information; generating ternary group data according to the mapping relation between the cutter information and the first attribute entity information and the mapping relation between the workpiece information and the second attribute entity information; and matching target process information corresponding to the cutter information and the workpiece information based on the subject word model by taking the process information in the processing process text as a subject and the triple data as text words. The invention can realize the automatic matching of the cutter and the workpiece to the process information, realize the high-efficiency determination of the process information and provide a favorable basis for the manufacturing of the numerical control machine.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A numerical control machine tool manufacturing process matching method based on subject word clustering is characterized by comprising the following steps:
acquiring a processing technology text, performing word marking on the processing technology text, determining cutter information and workpiece information in the processing technology text, and respectively determining first attribute entity information corresponding to the cutter information and second attribute entity information corresponding to the workpiece information;
generating three-element group data according to the mapping relation between the cutter information and the first attribute entity information and the mapping relation between the workpiece information and the second attribute entity information;
and matching target process information corresponding to the cutter information and the workpiece information based on a subject word model by taking the process information in the processing process text as a subject and the triple data as text words.
2. The method according to claim 1, wherein the obtaining of the processing technique text, the word labeling of the processing technique text, and the determining of the tool information and the workpiece information in the processing technique text comprise:
collecting a technical manual, carding process files of the numerical control machine tool, and screening out the processing process texts for describing the processes;
performing word segmentation processing on the processing technology text to obtain word information;
performing semantic recognition on the vocabulary information, determining the cutter information and the workpiece information in the vocabulary information, and labeling the cutter information and the workpiece information.
3. The method for matching numerical control machine tool manufacturing process based on subject word clustering according to claim 2, wherein the determining the first attribute entity information corresponding to the tool information and the second attribute entity information corresponding to the workpiece information respectively comprises:
performing grammatical association analysis on the cutter information and the workpiece information based on grammatical features, and determining association sentences corresponding to the cutter information and the workpiece information;
and respectively determining first attribute entity information corresponding to the tool information and second attribute entity information corresponding to the workpiece information based on the associated statements.
4. The method according to claim 3, wherein after obtaining the processing technique text, performing word labeling on the processing technique text, determining the tool information and the workpiece information in the processing technique text, and determining the first attribute entity information corresponding to the tool information and the second attribute entity information corresponding to the workpiece information, respectively, the method further comprises:
and training a Bi-LSTM-CRF model based on the cutter information and the corresponding first attribute entity information, the workpiece information and the corresponding second attribute entity information, wherein the trained Bi-LSTM-CRF model is used for identifying the cutter information, the workpiece information and the corresponding attribute entity information of the processing process text.
5. The method of claim 4, wherein the trained Bi-LSTM-CRF model comprises a representation layer, a BilSTM layer and a CRF layer, the representation layer is used for identifying word vectors and word vectors in the process text, and the BilSTM layer is used for determining scores of all attribute entity information corresponding to each word in the process text; the CRF layer is used for determining first attribute entity information corresponding to the cutter information and second attribute entity information corresponding to the workpiece information based on the probability that each word corresponds to all attribute entity information.
6. The method for matching a numerical control machine tool manufacturing process based on topic word clustering according to claim 1, wherein the matching of the target process information corresponding to the tool information and the workpiece information based on topic word models with the process information in the process text as a topic and the triple data as text words comprises:
clustering first attribute entity information and second attribute entity information in the triple data based on the subject word model, and determining first candidate process information corresponding to the first attribute entity information and second candidate process information corresponding to the second attribute entity from the processing process text;
and determining the target process information according to the first candidate process information and the second candidate process information.
7. The method as claimed in claim 6, wherein the determining the target process information according to the first candidate process information and the second candidate process information comprises:
determining the occurrence probability of the cutter information based on the first candidate process information, and determining cutter process information from the first candidate process information based on the occurrence probability of the cutter information;
determining the probability of the workpiece information based on the second candidate process information, and determining the workpiece process information from the second candidate process information based on the probability of the workpiece information;
and generating the target process information based on the cutter process information and the workpiece process information.
8. A matching system of numerical control machine manufacturing process based on subject word clustering is characterized by comprising the following steps:
the attribute entity information determining module is used for acquiring a processing technology text, performing word marking on the processing technology text, determining cutter information and workpiece information in the processing technology text, and respectively determining first attribute entity information corresponding to the cutter information and second attribute entity information corresponding to the workpiece information;
the three-group data determining module is used for generating three-group data according to the mapping relation between the cutter information and the first attribute entity information and the mapping relation between the workpiece information and the second attribute entity information;
and the process information matching module is used for matching target process information corresponding to the cutter information and the workpiece information based on a subject word model by taking the process information in the processing process text as a subject and the triple data as text words.
9. A terminal device, characterized in that the terminal device comprises a memory, a processor and a matching program of a numerically-controlled machine tool manufacturing process based on subject word clustering stored in the memory and capable of running on the processor, and when the processor executes the matching program of the numerically-controlled machine tool manufacturing process based on subject word clustering, the steps of the matching method of the numerically-controlled machine tool manufacturing process based on subject word clustering according to any one of claims 1 to 7 are realized.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores thereon a program for matching a subject word cluster-based nc manufacturing process, and the program for matching a subject word cluster-based nc manufacturing process is executed by a processor to implement the steps of the subject word cluster-based nc manufacturing process matching method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210613478.6A CN114722158B (en) | 2022-06-01 | 2022-06-01 | Method and system for matching numerical control machine tool manufacturing process based on subject word clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210613478.6A CN114722158B (en) | 2022-06-01 | 2022-06-01 | Method and system for matching numerical control machine tool manufacturing process based on subject word clustering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114722158A true CN114722158A (en) | 2022-07-08 |
| CN114722158B CN114722158B (en) | 2022-09-02 |
Family
ID=82232694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210613478.6A Active CN114722158B (en) | 2022-06-01 | 2022-06-01 | Method and system for matching numerical control machine tool manufacturing process based on subject word clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114722158B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006187352A (en) * | 2004-12-28 | 2006-07-20 | Samii Kk | Pachinko game machine |
| WO2015096511A1 (en) * | 2013-12-24 | 2015-07-02 | 沈阳飞机工业（集团）有限公司 | Intelligent numerical control machining programming system and method for aircraft structural parts |
| CN108897857A (en) * | 2018-06-28 | 2018-11-27 | 东华大学 | The Chinese Text Topic sentence generating method of domain-oriented |
| CN111563173A (en) * | 2020-05-09 | 2020-08-21 | 北京中科院软件中心有限公司 | Knowledge graph construction method and system based on manufacturing field |
| US20210103256A1 (en) * | 2019-09-06 | 2021-04-08 | Intelligent Fusion Technology, Inc. | Decision support method and apparatus for machinery control |
| CN113987212A (en) * | 2021-11-17 | 2022-01-28 | 武汉理工大学 | Knowledge graph construction method for process data in numerical control machining field |
| CN114064932A (en) * | 2021-11-30 | 2022-02-18 | 清华大学 | Data integration and mining method and device for curved surface part milling process system |
-
2022
- 2022-06-01 CN CN202210613478.6A patent/CN114722158B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006187352A (en) * | 2004-12-28 | 2006-07-20 | Samii Kk | Pachinko game machine |
| WO2015096511A1 (en) * | 2013-12-24 | 2015-07-02 | 沈阳飞机工业（集团）有限公司 | Intelligent numerical control machining programming system and method for aircraft structural parts |
| CN108897857A (en) * | 2018-06-28 | 2018-11-27 | 东华大学 | The Chinese Text Topic sentence generating method of domain-oriented |
| US20210103256A1 (en) * | 2019-09-06 | 2021-04-08 | Intelligent Fusion Technology, Inc. | Decision support method and apparatus for machinery control |
| CN111563173A (en) * | 2020-05-09 | 2020-08-21 | 北京中科院软件中心有限公司 | Knowledge graph construction method and system based on manufacturing field |
| CN113987212A (en) * | 2021-11-17 | 2022-01-28 | 武汉理工大学 | Knowledge graph construction method for process data in numerical control machining field |
| CN114064932A (en) * | 2021-11-30 | 2022-02-18 | 清华大学 | Data integration and mining method and device for curved surface part milling process system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114722158B (en) | 2022-09-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111753531B (en) | Text error correction method, device, equipment and storage medium based on artificial intelligence | |
| WO2020220539A1 (en) | Data increment method and device, computer device and storage medium | |
| CN109584882B (en) | Method and system for optimizing voice to text conversion aiming at specific scene | |
| CN109145276A (en) | A kind of text correction method after speech-to-text based on phonetic | |
| CN113506574A (en) | Method and device for recognizing user-defined command words and computer equipment | |
| CN101667176A (en) | Method and system for counting machine translation based on phrases | |
| CN101655837A (en) | Method for detecting and correcting error on text after voice recognition | |
| CN110569486B (en) | Sequence labeling method and device based on double architectures and computer equipment | |
| CN111191032A (en) | Corpus expansion method and device, computer equipment and storage medium | |
| CN110309504B (en) | Text processing method, device, equipment and storage medium based on word segmentation | |
| CN115981615B (en) | G code generation method integrating language model and knowledge graph and related equipment | |
| CN114863927B (en) | Numerical control machine tool interaction control method and system based on voice recognition | |
| CN113076404B (en) | Text similarity calculation method and device, computer equipment and storage medium | |
| CN114722158B (en) | Method and system for matching numerical control machine tool manufacturing process based on subject word clustering | |
| CN114282513A (en) | Text semantic similarity matching method and system, intelligent terminal and storage medium | |
| CN113157887A (en) | Knowledge question-answering intention identification method and device and computer equipment | |
| CN110797012B (en) | Information extraction method, equipment and storage medium | |
| CN112287657A (en) | Information matching system based on text similarity | |
| CN106682642A (en) | Multi-language-oriented behavior identification method and multi-language-oriented behavior identification system | |
| CN115964115A (en) | Numerical control machine tool interaction method based on pre-training reinforcement learning and related equipment | |
| CN115599908A (en) | Method and system for labeling unstructured data document | |
| CN114722159A (en) | Multi-source heterogeneous data processing method and system for numerical control machine tool manufacturing resources | |
| CN112987653B (en) | Method and device for converting Chinese program into G code | |
| CN111354339B (en) | Vocabulary phoneme list construction method, device, equipment and storage medium | |
| CN109727591B (en) | Voice search method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |