CN117289940B - Optimization method and system for Zeiss three-dimensional equipment based on off-board programming software - Google Patents
Optimization method and system for Zeiss three-dimensional equipment based on off-board programming software Download PDFInfo
- Publication number
- CN117289940B CN117289940B CN202311090132.3A CN202311090132A CN117289940B CN 117289940 B CN117289940 B CN 117289940B CN 202311090132 A CN202311090132 A CN 202311090132A CN 117289940 B CN117289940 B CN 117289940B
- Authority
- CN
- China
- Prior art keywords
- semantic
- topological
- zeiss
- dimensional
- functional requirement
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/40—Transformation of program code
- G06F8/41—Compilation
- G06F8/44—Encoding
- G06F8/447—Target code generation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/10—Requirements analysis; Specification techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/33—Intelligent editors
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Stored Programmes (AREA)
Abstract
The invention discloses an optimization method and a system of a zeiss three-dimensional device based on off-board programming software, wherein a zeiss three-dimensional function requirement text description is input at an off-board programming client; carrying out semantic understanding on the Zeiss three-dimensional functional requirement text description to obtain functional requirement semantic features; and generating computer codes for realizing the Zeiss three-dimensional function requirement based on the semantic features of the function requirement. Therefore, the programming of the automatic three-dimensional equipment of the Zeiss can be realized, so that the programming efficiency of the three-dimensional equipment of the Zeiss is improved, the downtime is reduced, and the operation efficiency of a production line is improved.
Description
Technical Field
The invention relates to the technical field of intelligent off-board programming, in particular to an optimization method and system of a Zeiss three-dimensional device based on off-board programming software.
Background
The Zeiss three-dimensional device is a high-precision measuring instrument for measuring and detecting three-dimensional objects, and is widely applied in manufacturing industry, in particular in the fields of automobiles, aerospace, medical equipment, electronic equipment and the like. The Zeiss three-time unit equipment can be used for product design and development, quality control, process optimization and the like, and helps enterprises to improve production efficiency, product quality and innovation capacity.
However, the existing zeiss three-time equipment programming usually needs to be performed on a computer of the equipment, and the equipment needs to be stopped when the programming is performed, which means that the equipment cannot normally operate during the programming, so that the stop time of a production line is increased, and the production efficiency is seriously affected.
Therefore, an optimization scheme of a zeiss three-dimensional device based on off-board programming software is desired.
Disclosure of Invention
The embodiment of the invention provides an optimization method and a system of a zeiss three-dimensional device based on off-board programming software, wherein a zeiss three-dimensional function requirement text description is input at an off-board programming client; carrying out semantic understanding on the Zeiss three-dimensional functional requirement text description to obtain functional requirement semantic features; and generating computer codes for realizing the Zeiss three-dimensional function requirement based on the semantic features of the function requirement. Therefore, the programming of the automatic three-dimensional equipment of the Zeiss can be realized, so that the programming efficiency of the three-dimensional equipment of the Zeiss is improved, the downtime is reduced, and the operation efficiency of a production line is improved.
The embodiment of the invention also provides an optimization method of the Zeiss three-dimensional equipment based on the off-board programming software, which comprises the following steps:
inputting a zeiss three-dimensional function requirement text description at an off-board programming client;
Carrying out semantic understanding on the Zeiss three-dimensional functional requirement text description to obtain functional requirement semantic features; and
And generating computer codes for realizing the Zeiss three-dimensional function requirement based on the semantic features of the function requirement.
The embodiment of the invention also provides an optimization system of the Zeiss three-dimensional equipment based on the off-board programming software, which comprises the following steps:
The text description input module is used for inputting the text description of the zeiss three-dimensional function requirement at the off-board programming client;
the semantic understanding module is used for carrying out semantic understanding on the Zeiss three-dimensional functional requirement text description so as to obtain functional requirement semantic features; and
And the computer code generation module is used for generating computer codes for realizing the three-dimensional functional requirements of the Zeiss based on the semantic features of the functional requirements.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1A is a schematic diagram of shutdown programming prior to improvement.
FIGS. 1B and 1C are schematic diagrams of improved off-board programming.
Fig. 2 is a flowchart of an optimization method of a zeiss three-dimensional device based on off-board programming software provided in an embodiment of the present invention.
Fig. 3 is a schematic diagram of a system architecture of a method for optimizing zeiss three-dimensional equipment based on off-board programming software according to an embodiment of the present invention.
Fig. 4 is a flowchart of the sub-step of step 120 in a zeiss three-dimensional device optimizing method based on off-board programming software according to an embodiment of the present invention.
Fig. 5 is a block diagram of an optimizing system of a zeiss three-dimensional device based on off-board programming software provided in an embodiment of the present invention.
Fig. 6 is an application scenario diagram of an optimization method of a zeiss three-dimensional device based on off-board programming software provided in an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
Unless defined otherwise, all technical and scientific terms used in the embodiments of the application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application.
In describing embodiments of the present application, unless otherwise indicated and limited thereto, the term "connected" should be construed broadly, for example, it may be an electrical connection, or may be a communication between two elements, or may be a direct connection, or may be an indirect connection via an intermediate medium, and it will be understood by those skilled in the art that the specific meaning of the term may be interpreted according to circumstances.
It should be noted that, the term "first\second\third" related to the embodiment of the present application is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that embodiments of the application described herein may be practiced in sequences other than those illustrated or described herein.
The Zeiss three-dimensional device is a high-precision measuring instrument, is used for measuring and detecting three-dimensional objects, and is widely applied in manufacturing industry, in particular in the fields of automobiles, aerospace, medical equipment, electronic equipment and the like. The Zeiss three-dimensional equipment can rapidly and accurately acquire three-dimensional coordinate information of an object by utilizing advanced optical and sensing technologies, and is usually composed of a measuring arm, a measuring probe and measuring software.
The measuring arm is the main part of the device, has a telescopic arm-like structure, and enables the device to flexibly move and reach the required measuring position through articulation. The measuring probe is mounted at the end of the measuring arm for acquiring geometrical information of the object in contact or non-contact. The measurement software is responsible for controlling the operation and data processing of the device, and converting the measurement result into a visual three-dimensional model or a data report.
The Zeiss three-dimensional equipment has the characteristics of high precision, high speed and high flexibility, can measure objects with complex shapes, including curved surfaces, holes, edges and angles and the like, and provides accurate size, shape and position information. Meanwhile, the functions of comparison measurement, shape analysis, fitting and the like can be performed, and the method is used for the aspects of product design and development, quality control, process optimization and the like.
The application field of the Zeiss three-dimensional equipment is wide, for example, the Zeiss three-dimensional equipment can be used for detecting the size and the assembly precision of vehicle body parts in the automobile manufacturing process; in the aerospace field, can be used to measure the shape and position of aircraft parts; in the manufacture of medical devices, it can be used to detect the fit of prostheses and prosthetic limbs; in the electronic equipment industry, the method can be used for detecting the size, welding quality and the like of the circuit board.
The zeiss three-time equipment has the advantages of improving the production efficiency, the product quality and the innovation capability. The measuring and detecting can be performed rapidly, the time and the error of manual operation are reduced, and the operation efficiency of the production line is improved. Meanwhile, the high-precision measurement result can help enterprises to optimize product design and manufacturing processes, improve product quality and innovation capacity, and meet market demands.
Current zeiss three-dimensional device programming typically needs to be performed on the device's own computer, which limits the flexibility and convenience of programming, and operators must program beside the device, and cannot program remotely or off-line elsewhere. When programming, it is often necessary to stop the normal operation of the equipment, which can lead to increased downtime of the production line. An increase in downtime can result in decreased production efficiency, affecting the production plan and delivery time of the enterprise. The programming of the zeiss three-time equipment generally needs to master a specific programming language and an operation flow, has higher requirements on skills of operators, possibly involves complex parameter setting, coordinate system conversion and other operations in the programming process, is easy to cause human errors, and increases programming difficulty and risk. The existing zeiss three-time equipment programming lacks an automatic function, and an operator is required to manually input and adjust parameters.
The defects of the conventional zeiss three-time equipment programming mainly comprise that the programming is limited on the self-powered battery of the equipment, the equipment needs to be shut down for programming, the programming complexity is high, and an automatic programming function is lacked. These problems limit the flexibility of the apparatus, the programming efficiency and the operating efficiency of the production line, which need to be solved by an optimization scheme. Therefore, the application provides an optimization scheme of the Zeiss three-dimensional equipment based on the off-board programming software.
As shown in FIG. 1A, before improvement, the Zeiss three-dimensional elements are programmed and operated by a self-contained computer. And the machine is stopped when programming each time. The machine can only run after programming. The programming takes approximately 4 hours per day, which is equivalent to a 4H downtime per day.
As shown in fig. 1B and 1C, the improved scheme is: by buying off-board programming software on the Taobao, the cost is less than 100 yuan, and off-board programming is realized. The zeiss three-time element does not need to be shut down for programming, and the utilization rate of the machine is greatly improved.
Aiming at the technical problems, the technical conception of the application is to program the zeiss three-time unit equipment based on off-board programming software so as to avoid the problems of increased downtime and reduced production efficiency caused by shutdown programming. In addition, in order to realize automatic programming so as to improve the production efficiency of the equipment, a text semantic understanding model is introduced to carry out semantic analysis on the required text description of the three-dimensional function of the Zeiss input by the client so as to automatically generate a computer code, and in such a way, the programming of the automatic three-dimensional equipment of the Zeiss can be realized, so that the programming efficiency of the three-dimensional equipment of the Zeiss is improved, the downtime is reduced, and the operation efficiency of a production line is improved.
In one embodiment of the present invention, fig. 2 is a flowchart of a method for optimizing zeiss three-dimensional equipment based on off-board programming software provided in the embodiment of the present invention. Fig. 3 is a schematic diagram of a system architecture of a method for optimizing zeiss three-dimensional equipment based on off-board programming software according to an embodiment of the present invention. As shown in fig. 2 and 3, the optimization method 100 of the zeiss three-dimensional device based on the off-board programming software according to the embodiment of the present invention includes: 110, inputting a zeiss three-dimensional function requirement text description at an off-board programming client; 120, carrying out semantic understanding on the zeiss three-dimensional functional requirement text description to obtain functional requirement semantic features; and 130, generating computer codes for realizing the Zeiss three-dimensional function requirement based on the semantic features of the function requirement.
In said step 110, a zeiss three-dimensional function requirement text description is entered at the off-board programming client. The text description of the three-dimensional function requirement of the Zeiss is ensured to be clear and accurate, necessary information and requirements are contained, the function requirement is described by using clear language, and ambiguity are avoided. The off-line programming can be realized by inputting the text description of the functional requirements through the off-board programming client, and the flexibility and convenience of programming are improved. The operator can enter functional requirements anywhere and is no longer limited to programming alongside the device.
In the step 120, semantic understanding is performed on the zeiss three-dimensional functional requirement text description to obtain functional requirement semantic features. Semantic analysis is performed on the functional demand text using Natural Language Processing (NLP) techniques to understand the meaning and context of the text. And, ensure the key elements of accurate understanding function demand, such as measurement object, measurement precision, measurement mode etc.. Through semantic understanding, key information of functional requirements can be accurately captured, and a basis is provided for subsequent code generation. The extraction of semantic features can help identify and analyze important instructions and parameters in functional requirements, avoiding human error and misunderstanding.
In the step 130, based on the semantic features of the functional requirements, computer code is generated that implements the zeiss three-dimensional functional requirements. Based on the semantic features, computer code meeting the functional requirements is generated using automated code generation techniques. And ensures that the generated codes can accurately realize the requirements of the zeiss three-dimensional functions and meet the programming specifications and limitations of equipment. The automatic code generation can improve programming efficiency, reduce manual operation and errors, ensure the accuracy and consistency meeting functional requirements and improve programming quality and reliability. Through code generation, standardization and modularization of programming can be realized, and maintenance and upgrading are convenient.
The zeiss three-dimensional equipment optimization method based on the off-board programming software comprises the steps of inputting a functional requirement text description at an off-board programming client, carrying out semantic understanding on the functional requirement text description to obtain functional requirement semantic features, and generating computer codes for realizing the functional requirements based on the functional requirement semantic features. The attention and benefits of these steps help to improve the flexibility, efficiency and accuracy of programming.
Specifically, in the step 110, a zeiss three-dimensional function requirement text description is input at the off-board programming client. In the technical scheme of the application, firstly, a zeiss three-dimensional function requirement text description is input at an off-board programming client. By inputting the functional requirement text description, accurate functional requirements can be ensured to be transmitted to the off-board programming software, so that the generated computer codes are prevented from being inconsistent with the actual requirements due to unclear communication or understanding deviation. The functional requirements text description may help identify and determine key elements and parameters required for implementation. Such as the object of measurement, the accuracy of measurement, the manner of measurement, etc., these key elements and parameters are critical to generating accurate computer code. The functional requirement text description may provide guidance and constraints for the code generation process. The off-board programming software can automatically generate computer codes meeting the requirements according to the information in the text description, and instructions and requirements in the text description can be directly converted into logic and operation of the codes. By inputting the functional requirement text description at the off-board programming client, off-line programming can be realized, and the requirement of manual operation is reduced, which can improve the programming efficiency and reduce the risk of programming errors caused by human errors.
By inputting the zeiss three-dimensional function requirement text description at the off-board programming client, the accurate transmission of requirement information can be ensured, the code generation process is guided, and the programming efficiency and accuracy are improved. This helps to generate the computer code that fulfills the functional requirements and ensures that it is consistent with the actual requirements.
Specifically, in the step 120, semantic understanding is performed on the zeiss three-dimensional functional requirement text description to obtain functional requirement semantic features. Fig. 4 is a flowchart of the sub-step of step 120 in a zeiss three-dimensional device optimizing method based on off-board programming software according to an embodiment of the present invention. As shown in fig. 4, the semantic understanding of the zeiss three-dimensional functional requirement text description to obtain the functional requirement semantic features includes: 121, performing word segmentation processing on the zeiss three-dimensional function requirement text description, and then obtaining a sequence of function requirement text description word embedding vectors through a word embedding layer; 122, extracting word granularity semantic association topological feature matrixes from the sequence of the functional requirement text descriptor embedding vectors; and 123, performing association coding on the sequence of the functional requirement text descriptor embedded vector and the word granularity semantic association topological feature matrix to obtain a topological functional requirement semantic understanding feature vector as the functional requirement semantic feature.
Firstly, performing word segmentation processing on the zeiss three-dimensional functional requirement text description, and then obtaining a sequence of functional requirement text description word embedding vectors through a word embedding layer. The word segmentation process can divide the functional requirement text description into sequences of words or phrases, extract semantic basic units, and the word embedding layer maps each word or phrase into a high-dimensional vector representation, thereby capturing semantic relations and similarities among the words.
And then extracting word granularity semantic association topological feature matrixes from the sequence of the functional requirement text descriptor embedding vectors. By extracting the word granularity semantic association topological feature matrix, semantic association and context information among words in the functional demand text description can be captured, and the feature matrix can reflect the relationship among the words, such as similarity, correlation, dependency and the like, so that more comprehensive information is provided for subsequent semantic understanding.
And then, carrying out association coding on the sequence of the functional requirement text descriptor embedded vector and the word granularity semantic association topological feature matrix to obtain a topological functional requirement semantic understanding feature vector as the functional requirement semantic feature. The association code combines word embedding vectors and word granularity semantic association topological feature matrixes, and comprehensively utilizes semantic information of word level and sentence level. The semantic understanding feature vector of the topological function requirement can more comprehensively express semantic meaning and context of the functional requirement text description, and the semantic understanding feature vector of the topological function requirement serves as semantic features of the functional requirement and can be used for subsequent computer code generation or other related tasks.
Semantic features of functional requirements can be obtained by carrying out semantic understanding on text description of the three-dimensional functional requirements of the zeiss, including word segmentation processing, word embedding and semantic association topological feature extraction. The beneficial effects of these steps include capturing semantic relationships, extracting contextual information, and comprehensively utilizing word-level and sentence-level semantic information to more accurately understand the meaning and requirements of functional requirements.
Next, it is considered that the text description is composed of a plurality of words due to the zeiss three-dimensional function requirement, and that the words have semantic association relationships with each other. But due to the different language habits of each user, semantic expressions in the text description of the zeiss three-dimensional functional requirement input may be inaccurate. Therefore, in order to better understand the semantics of the text description, in the technical scheme of the application, the sequence of the function requirement text description word embedded vector is obtained through a word embedding layer after the word segmentation processing is carried out on the zeiss three-dimensional function requirement text description. It should be understood that the word segmentation process may segment the text description according to word boundaries, and divide sentences into individual words, so that semantic information about each word and between words in the text description may be better captured, so that the model may more accurately understand the meaning of the text. Word embedding is a technique that maps words into a low-dimensional vector space. Through the word embedding layer, each word in the text description can be expressed as a vector, so that semantic relations among the words can be captured later, and words with similar meanings are more similar in vector space.
In one embodiment of the present application, extracting the word granularity semantic association topological feature matrix from the sequence of functional requirement text descriptor embedding vectors comprises: calculating cosine similarity between any two functional requirement text descriptor embedded vectors in the sequence of the functional requirement text descriptor embedded vectors to obtain a word granularity semantic association topology matrix; and extracting features of the word granularity semantic association topological feature matrix by a topological feature extractor based on a deep neural network model to obtain the word granularity semantic association topological feature matrix.
The deep neural network model is a convolutional neural network model.
The deep neural network model can learn higher-level semantic representation, converts word granularity semantic association topological matrixes into richer and more abstract feature representations, and the features can better capture semantic relations among words in the text description of the functional requirements.
Through feature extraction, the original word granularity semantic association topological matrix can be converted into a feature matrix with lower dimension. This helps to reduce the storage space and computational complexity of the data and to increase the efficiency of subsequent tasks.
The deep neural network model can fuse semantic associations among different words to generate a more global feature representation. The method is beneficial to extracting more accurate and comprehensive word granularity semantic association topological characteristics and provides richer information for subsequent tasks.
The word granularity semantic association topological feature matrix and the word granularity semantic association topological feature matrix can be obtained by calculating cosine similarity and a feature extractor based on a deep neural network model. These matrices can provide more comprehensive, abstract semantic information, providing a useful feature basis for subsequent semantic understanding and related tasks.
Then, in order to measure the semantic association degree based on word granularity among each word related to the zeiss three-dimensional function requirement in the text description, so as to be more beneficial to semantic understanding of the zeiss three-dimensional function requirement, in the technical scheme of the application, cosine similarity between any two function requirement text descriptor embedding vectors in the sequence of the function requirement text descriptor embedding vectors is further calculated to obtain a word granularity semantic association topology matrix. The semantic association topology matrix of the word granularity can be obtained by calculating cosine similarity among all vectors in the embedded vector sequence of the functional requirement text description words, and the semantic similarity relation among all words in the zeiss three-dimensional functional requirement text description can be reflected by the matrix, namely, which words are judged to be more related or more similar in terms of semantics, so that semantic understanding and code generation of the zeiss three-dimensional functional requirement can be conveniently and accurately carried out.
The cosine similarity is a commonly used method for measuring the similarity between two vectors, and is particularly suitable for semantic similarity comparison of text data. Cosine similarity measures the degree of directional similarity of two vectors, irrespective of their length. The cosine similarity has a value ranging from-1 to 1, wherein 1 indicates that the directions of the two vectors are identical, 0 indicates that no correlation in the direction exists between the two vectors, and-1 indicates that the directions of the two vectors are opposite.
When the calculation function requires the cosine similarity between any two vectors in the text descriptor embedded vector sequence, each vector can be regarded as a vector representation of one word, and the semantic association degree between the two word vectors can be measured by calculating the cosine similarity between the two word vectors. And forming a matrix by cosine similarity of all word vectors, namely, a word granularity semantic association topological matrix, and expressing semantic relations among words in the functional requirement text description.
By calculating cosine similarity, similarity among word vectors can be quantized, so that a foundation is provided for subsequent semantic association topological feature extraction, and semantic association and context information among words in the functional requirement text description can be captured better.
And then, carrying out feature mining on the word granularity semantic association topological matrix through a topological feature extractor based on a convolutional neural network model so as to extract semantic similarity topological association feature information based on word granularity among the words required by the Zeiss three-dimensional function, thereby obtaining the word granularity semantic association topological feature matrix.
In one embodiment of the present application, performing association coding on the sequence of the functional requirement text descriptor embedded vector and the word granularity semantic association topological feature matrix to obtain a topological functional requirement semantic understanding feature vector as the functional requirement semantic feature, including: and embedding the sequence of the functional requirement text descriptor embedded vector and the word granularity semantic association topological feature matrix into a topological functional requirement semantic understanding feature vector through a graph neural network model.
Further, each functional requirement text descriptor embedding vector in the sequence of functional requirement text descriptor embedding vectors is used as a characteristic representation of a node, the word granularity semantic association topological characteristic matrix is used as a characteristic representation of an edge between nodes, and the functional requirement text descriptor embedding matrix obtained by two-dimensional arrangement of the functional requirement text descriptor embedding vectors and the word granularity semantic association topological characteristic matrix are subjected to a graph neural network model to obtain a topological functional requirement semantic understanding characteristic matrix. Specifically, the graph neural network model performs graph structure data coding on the functional requirement text descriptor embedding matrix and the word granularity semantic association topological feature matrix through a learnable neural network parameter to obtain the topological functional requirement semantic understanding feature matrix containing irregular word granularity semantic topological association features and each word meaning feature in the functional requirement text description. And extracting topological function demand semantic understanding feature vectors corresponding to the function demand words from each row vector of the topological function demand semantic understanding feature matrix, wherein the topological function demand semantic understanding feature vectors are used for expressing topological association representations of corresponding functional demand text descriptor embedding vectors based on inter-word semantic similarity topologies of text semantic feature expressions of corresponding zeiss three-dimensional functional demand text descriptor segmentation words.
Specifically, in the step 130, based on the semantic features of the functional requirement, computer code for implementing the zeiss three-dimensional functional requirement is generated, including: performing feature distribution optimization on the topological function demand semantic understanding feature vector to obtain an optimized topological function demand semantic understanding feature vector; and passing the optimized topology function requirement semantic understanding feature vector through a AIGC model-based code generator to obtain computer code for implementing the zeiss three-dimensional function requirement.
And then, passing the semantic understanding feature vector of the topological function requirement through a code generator based on AIGC models to obtain computer codes for realizing the Zeiss three-dimensional function requirement. That is, by semantically understanding the feature vectors of the topological function demands by based on AIGC models, the models can generate computer codes corresponding to the function demands according to the learned mapping relations. These generated codes can fulfill the requirements of the zeiss three-dimensional functions, such as the operation of control equipment, data processing, algorithm implementation and the like. In this way, automated programming can be achieved, reducing the complexity of manual programming and the possibility of errors. And by using codes generated by AIGC models, the development efficiency can be improved, the development period can be shortened, and meanwhile, the method has higher accuracy and reliability.
In particular, in the technical solution of the present application, when the sequence of the functional requirement text descriptor embedding vectors and the word granularity semantic association topological feature matrix are passed through a graph neural network model to obtain topological functional requirement semantic understanding feature vectors, the topological functional requirement semantic understanding feature vectors express topological association representations based on inter-word semantic similarity topologies of the corresponding functional requirement text descriptor embedding vectors for the text semantic feature expressions of the zeiss three-dimensional functional requirement text descriptor, because, in order to avoid the topological functional requirement semantic understanding feature vectors from deviating from the text semantic expressions of the corresponding functional requirement text descriptor embedding vectors, it is desirable to optimize the topological functional requirement semantic understanding feature vectors by fusing the corresponding functional requirement text descriptor embedding vectors, so as to promote the correspondence between computer codes and text descriptions obtained by the topological functional requirement semantic understanding feature vectors through a code generator based on a AIGC model.
Here, considering the non-homogeneous point-by-point correspondence between the corresponding functional requirement text descriptor embedding vector, which is the word-based word embedded text semantic feature of the zeiss three-dimensional functional requirement text descriptor segmentation, and the topological function requirement semantic understanding feature vector, which is the associated feature based on word semantic similarity topology between the text semantic features of the respective words, the spatially adaptive point learning on the non-homogeneous hilbert surface is performed on the corresponding functional requirement text descriptor embedding vector, for example, denoted as V 1 and the topological function requirement semantic understanding feature vector, for example, denoted as V 2, to obtain an optimized topological function requirement semantic understanding feature vector, for example, denoted as V 2', specifically expressed as: performing non-homogeneous Hilbert-face space self-adaptive point learning on the corresponding function requirement text descriptor embedded vector and the corresponding topology function requirement semantic understanding feature vector by using the following optimization formula to obtain the optimized topology function requirement semantic understanding feature vector; wherein, the optimization formula is:
Wherein V 1 is the function requirement text descriptor embedding vector, V 2 is the topology function requirement semantic understanding feature vector, V 2 T is the transpose of the topology function requirement semantic understanding feature vector, p 1≠p2, AndDenotes a non-homogeneous minpoint distance based on gilbert space, and p 1 and p 2 are hyper-parameters,AndThe function requirement text descriptor embedded vector V 1 and the topology function requirement semantic understanding feature vector V 2 are global feature means respectively, the function requirement text descriptor embedded vector V 1 and the topology function requirement semantic understanding feature vector V 2 are row vectors, as indicated by multiplication by location points,Representing the addition by location, cov (·) is the covariance matrix and V 2' is the optimized topology function requirement semantic understanding feature vector.
In this way, by performing one-dimensional convolution on the vector point association between the functional requirement text descriptor embedding vector V 1 and the topological function requirement semantic understanding feature vector V 2 by using non-homogeneous gilbert space metrics, non-axis alignment (non-axion alignment) characteristics of feature manifolds represented by high-dimensional features of the functional requirement text descriptor embedding vector V 1 and the topological function requirement semantic understanding feature vector V 2 in the high-dimensional feature space can be improved, adaptive point learning is performed on the surface of a manifold convergence hyper-plane based on the gilbert space towards the hyper-plane, and air metrics (aerial measurement) facing respective distribution convergence directions of the functional requirement text descriptor embedding vector V 1 and the topological function requirement semantic understanding feature vector V 2 are used as corrections, so that non-homogeneous point fusion performance between the functional requirement text descriptor embedding vector V 1 and the topological function requirement semantic understanding feature vector V 2 is improved, and correspondingly improved by using a functional requirement text generator corresponding to the functional requirement text description model of the corresponding functional requirement text generator V 2' after the optimized text is calculated by using the corresponding functional requirement text description vector 2. Therefore, the computer code can be automatically generated based on the Zeiss three-dimensional function requirement text input by the off-board programming client, so that the programming of the automatic Zeiss three-dimensional equipment is realized, the programming efficiency of the Zeiss three-dimensional equipment is improved, the downtime is reduced, and the operation efficiency of the production line is improved.
In summary, the method 100 for optimizing a zeiss three-dimensional device based on off-board programming software according to the embodiment of the present invention is illustrated, and the problem of increased downtime and reduced production efficiency caused by shutdown programming is avoided by performing the programming of the zeiss three-dimensional device based on off-board programming software. In addition, in order to realize automatic programming so as to improve the production efficiency of the equipment, a text semantic understanding model is introduced to carry out semantic analysis on the required text description of the three-dimensional function of the Zeiss input by the client so as to automatically generate a computer code, and in such a way, the programming of the automatic three-dimensional equipment of the Zeiss can be realized, so that the programming efficiency of the three-dimensional equipment of the Zeiss is improved, the downtime is reduced, and the operation efficiency of a production line is improved.
Fig. 5 is a block diagram of an optimizing system of a zeiss three-dimensional device based on off-board programming software provided in an embodiment of the present invention. As shown in fig. 5, the optimizing system of the zeiss three-dimensional equipment based on the off-board programming software comprises: a text description input module 210, configured to input a zeiss three-dimensional function requirement text description at an off-board programming client; the semantic understanding module 220 is configured to perform semantic understanding on the zeiss three-dimensional functional requirement text description to obtain functional requirement semantic features; and a computer code generating module 230, configured to generate computer code for implementing the zeiss three-dimensional function requirement based on the semantic feature of the function requirement.
Specifically, in the optimization system of the zeiss three-dimensional equipment based on the off-board programming software, the semantic understanding module comprises: the word segmentation processing unit is used for carrying out word segmentation processing on the zeiss three-dimensional functional requirement text description and then obtaining a sequence of functional requirement text description word embedding vectors through a word embedding layer; the extraction unit is used for extracting a word granularity semantic association topological feature matrix from the sequence of the functional requirement text descriptor embedding vector; and the association coding unit is used for carrying out association coding on the sequence of the functional requirement text descriptor embedded vector and the word granularity semantic association topological feature matrix to obtain a topological functional requirement semantic understanding feature vector as the functional requirement semantic feature.
Specifically, in the optimizing system of the zeiss three-dimensional equipment based on the off-board programming software, the extracting unit is used for: calculating cosine similarity between any two functional requirement text descriptor embedded vectors in the sequence of the functional requirement text descriptor embedded vectors to obtain a word granularity semantic association topology matrix; and extracting features of the word granularity semantic association topological feature matrix by a topological feature extractor based on a deep neural network model to obtain the word granularity semantic association topological feature matrix.
It will be appreciated by those skilled in the art that the specific operation of the steps in the above-described zeiss three-dimensional device optimizing system based on the off-board programming software has been described in detail in the above description of the method for optimizing zeiss three-dimensional device based on the off-board programming software with reference to fig. 1 to 4, and thus, repetitive descriptions thereof will be omitted.
As described above, the optimizing system 100 of the zeiss triad based on the off-board programming software according to the embodiment of the present invention may be implemented in various terminal devices, for example, a server for optimizing the zeiss triad based on the off-board programming software, and the like. In one example, the optimization system 100 of the zeiss three-dimensional device based on off-board programming software according to an embodiment of the present invention may be integrated into the terminal device as one software module and/or hardware module. For example, the zeiss three-dimensional device optimization system 100 based on off-board programming software may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the zeiss three-dimensional device optimizing system 100 based on the off-board programming software can also be one of a plurality of hardware modules of the terminal device.
Alternatively, in another example, the optimizing system 100 of the zeiss three-dimensional device based on the off-board programming software and the terminal device may be separate devices, and the optimizing system 100 of the zeiss three-dimensional device based on the off-board programming software may be connected to the terminal device through a wired and/or wireless network and transmit the interaction information according to the agreed data format.
Fig. 6 is an application scenario diagram of an optimization method of a zeiss three-dimensional device based on off-board programming software provided in an embodiment of the present invention. As shown in fig. 6, in this application scenario, first, a zeiss three-dimensional function requirement text description (e.g., C as illustrated in fig. 6) is input at the off-board programming client; the obtained zeiss three-dimensional function requirement text description is then input into a server (e.g. S as illustrated in fig. 6) deployed with an optimization algorithm of a zeiss three-dimensional device based on off-board programming software, wherein the server is capable of processing the zeiss three-dimensional function requirement text description based on the optimization algorithm of the zeiss three-dimensional device of off-board programming software to generate computer code for implementing the zeiss three-dimensional function requirement.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (8)
1. The method for optimizing the Zeiss three-dimensional equipment based on the off-board programming software is characterized by comprising the following steps of:
inputting a zeiss three-dimensional function requirement text description at an off-board programming client;
Carrying out semantic understanding on the Zeiss three-dimensional functional requirement text description to obtain functional requirement semantic features; and
Generating a computer code for realizing the zeiss three-dimensional function requirement based on the function requirement semantic features;
Based on the semantic features of the functional requirements, generating a computer code for realizing the three-dimensional functional requirements of the zeiss, comprising:
Carrying out feature distribution optimization on the semantic understanding feature vector of the topological function requirement to obtain the semantic understanding feature vector of the optimized topological function requirement; and
Passing the optimized topology function requirement semantic understanding feature vector through a AIGC model-based code generator to obtain computer codes for realizing the zeiss three-dimensional function requirement;
performing feature distribution optimization on the topological function demand semantic understanding feature vector to obtain an optimized topological function demand semantic understanding feature vector, including:
Performing non-homogeneous Hilbert-face space self-adaptive point learning on the corresponding functional requirement text descriptor embedded vector and the topological functional requirement semantic understanding feature vector by using the following optimization formula to obtain the optimized topological functional requirement semantic understanding feature vector;
wherein, the optimization formula is: Wherein, Is the functional requirement text descriptor embedding vector,Is the topological function demand semantic understanding feature vector,Is a transpose of the topological function demand semantic understanding feature vector,，AndRepresenting non-homogeneous minpoint distance based on Gilbert space, anAndIs the parameter of the ultrasonic wave to be used as the ultrasonic wave,AndThe function requirement text descriptor embedding vectorsAnd the topological function demand semantic understanding feature vectorAnd the functional requirement text descriptor is embedded into a vectorAnd the topological function demand semantic understanding feature vectorAre all the vectors of the rows and,Representing the multiplication by the position point,The representation is added by location,Is the covariance matrix of the data set,Is the semantic understanding feature vector of the optimized topology function requirement.
2. The method for optimizing a zeiss three-dimensional device based on off-board programming software according to claim 1, wherein performing semantic understanding on a zeiss three-dimensional functional requirement text description to obtain functional requirement semantic features comprises:
performing word segmentation processing on the zeiss three-dimensional function requirement text description, and then obtaining a sequence of function requirement text description word embedding vectors through a word embedding layer;
Extracting word granularity semantic association topological feature matrixes from the sequence of the functional requirement text descriptor embedding vectors; and
And carrying out association coding on the sequence of the functional requirement text descriptor embedded vector and the word granularity semantic association topological feature matrix to obtain a topological functional requirement semantic understanding feature vector serving as the functional requirement semantic feature.
3. The method for optimizing zeiss three-dimensional equipment based on off-board programming software according to claim 2, wherein extracting word granularity semantic association topological feature matrix from the sequence of functional requirement text descriptor embedding vectors comprises:
Calculating cosine similarity between any two functional requirement text descriptor embedded vectors in the sequence of the functional requirement text descriptor embedded vectors to obtain a word granularity semantic association topology matrix; and
And extracting features of the word granularity semantic association topological feature matrix by a topological feature extractor based on a deep neural network model to obtain the word granularity semantic association topological feature matrix.
4. The method for optimizing zeiss three-dimensional equipment based on off-board programming software according to claim 3, wherein the deep neural network model is a convolutional neural network model.
5. The method for optimizing zeiss three-dimensional equipment based on off-board programming software according to claim 4, wherein performing association coding on the sequence of the functional requirement text descriptor embedding vector and the word granularity semantic association topological feature matrix to obtain a topological functional requirement semantic understanding feature vector as the functional requirement semantic feature comprises:
and embedding the sequence of the functional requirement text descriptor embedded vector and the word granularity semantic association topological feature matrix into a topological functional requirement semantic understanding feature vector through a graph neural network model.
6. An optimization system of a zeiss three-dimensional device based on off-board programming software, which is characterized by comprising:
The text description input module is used for inputting the text description of the zeiss three-dimensional function requirement at the off-board programming client;
the semantic understanding module is used for carrying out semantic understanding on the Zeiss three-dimensional functional requirement text description so as to obtain functional requirement semantic features; and
The computer code generation module is used for generating computer codes for realizing the three-dimensional functional requirements of the Zeiss based on the semantic features of the functional requirements;
Based on the semantic features of the functional requirements, generating a computer code for realizing the three-dimensional functional requirements of the zeiss, comprising:
Carrying out feature distribution optimization on the semantic understanding feature vector of the topological function requirement to obtain the semantic understanding feature vector of the optimized topological function requirement; and
Passing the optimized topology function requirement semantic understanding feature vector through a AIGC model-based code generator to obtain computer codes for realizing the zeiss three-dimensional function requirement;
performing feature distribution optimization on the topological function demand semantic understanding feature vector to obtain an optimized topological function demand semantic understanding feature vector, including:
Performing non-homogeneous Hilbert-face space self-adaptive point learning on the corresponding functional requirement text descriptor embedded vector and the topological functional requirement semantic understanding feature vector by using the following optimization formula to obtain the optimized topological functional requirement semantic understanding feature vector;
wherein, the optimization formula is:
Wherein, Is the functional requirement text descriptor embedding vector,Is the topological function demand semantic understanding feature vector,Is a transpose of the topological function demand semantic understanding feature vector,，AndRepresenting non-homogeneous minpoint distance based on Gilbert space, anAndIs the parameter of the ultrasonic wave to be used as the ultrasonic wave,AndThe function requirement text descriptor embedding vectorsAnd the topological function demand semantic understanding feature vectorAnd the functional requirement text descriptor is embedded into a vectorAnd the topological function demand semantic understanding feature vectorAre all the vectors of the rows and,Representing the multiplication by the position point,The representation is added by location,Is the covariance matrix of the data set,Is the semantic understanding feature vector of the optimized topology function requirement.
7. The optimization system of zeiss three-dimensional equipment based on off-board programming software according to claim 6, wherein the semantic understanding module comprises:
the word segmentation processing unit is used for carrying out word segmentation processing on the zeiss three-dimensional functional requirement text description and then obtaining a sequence of functional requirement text description word embedding vectors through a word embedding layer;
The extraction unit is used for extracting a word granularity semantic association topological feature matrix from the sequence of the functional requirement text descriptor embedding vector; and
And the association coding unit is used for carrying out association coding on the sequence of the functional requirement text descriptor embedded vector and the word granularity semantic association topological feature matrix to obtain a topological functional requirement semantic understanding feature vector as the functional requirement semantic feature.
8. The optimization system of zeiss three-dimensional equipment based on off-board programming software according to claim 7, wherein the extraction unit is configured to:
Calculating cosine similarity between any two functional requirement text descriptor embedded vectors in the sequence of the functional requirement text descriptor embedded vectors to obtain a word granularity semantic association topology matrix; and
And extracting features of the word granularity semantic association topological feature matrix by a topological feature extractor based on a deep neural network model to obtain the word granularity semantic association topological feature matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311090132.3A CN117289940B (en) | 2023-08-28 | 2023-08-28 | Optimization method and system for Zeiss three-dimensional equipment based on off-board programming software |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311090132.3A CN117289940B (en) | 2023-08-28 | 2023-08-28 | Optimization method and system for Zeiss three-dimensional equipment based on off-board programming software |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117289940A CN117289940A (en) | 2023-12-26 |
| CN117289940B true CN117289940B (en) | 2024-07-23 |
Family
ID=89256169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311090132.3A Active CN117289940B (en) | 2023-08-28 | 2023-08-28 | Optimization method and system for Zeiss three-dimensional equipment based on off-board programming software |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117289940B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113607815A (en) * | 2021-08-02 | 2021-11-05 | 盐城东山通信技术有限公司 | A programmable manual percussion device |
| CN113791757A (en) * | 2021-07-14 | 2021-12-14 | 北京邮电大学 | Software requirement and code mapping method and system |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6757646B2 (en) * | 2000-03-22 | 2004-06-29 | Insightful Corporation | Extended functionality for an inverse inference engine based web search |
| FR2967799A1 (en) * | 2010-11-23 | 2012-05-25 | Thales Sa | AERONAUTICAL SOFTWARE APPLICATION DEVELOPMENT BENCH HAVING A STRUCTURAL LANGUAGE OF FUNCTIONAL DESCRIPTION |
| CN107808168B (en) * | 2017-10-31 | 2023-08-01 | 北京科技大学 | A Social Network User Behavior Prediction Method Based on Strong and Weak Relationships |
| CN111580825A (en) * | 2020-04-28 | 2020-08-25 | 中国科学院软件研究所 | Compiling method and system for mechanical arm program development programming language |
| CN112799655A (en) * | 2021-01-26 | 2021-05-14 | 浙江香侬慧语科技有限责任公司 | Multi-type code automatic generation method, device and medium based on pre-training |
| CN113805531B (en) * | 2021-09-22 | 2023-03-21 | 格致汽车科技股份有限公司 | Full-automatic unattended early warning method for numerical control machine tool |
| CN116010713A (en) * | 2023-03-27 | 2023-04-25 | 日照职业技术学院 | Innovative entrepreneur platform service data processing method and system based on cloud computing |
| CN116629275B (en) * | 2023-07-21 | 2023-09-22 | 北京无极慧通科技有限公司 | Intelligent decision support system and method based on big data |
-
2023
- 2023-08-28 CN CN202311090132.3A patent/CN117289940B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113791757A (en) * | 2021-07-14 | 2021-12-14 | 北京邮电大学 | Software requirement and code mapping method and system |
| CN113607815A (en) * | 2021-08-02 | 2021-11-05 | 盐城东山通信技术有限公司 | A programmable manual percussion device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117289940A (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116300691A (en) | A state monitoring method and system for multi-axis linkage numerical control machining | |
| CN112632972A (en) | Method for rapidly extracting fault information in power grid equipment fault report | |
| US20250044751A1 (en) | Digital twin enhanced method and system for detecting and compensating complex equipment | |
| CN116975581B (en) | STEP format-based sheet metal part rapid identification method | |
| US20240427305A1 (en) | Graph neural network based plc control logic automatic inspection method | |
| CN114925462B (en) | Thin-wall part machining deformation prediction method based on cutting force and rigidity correlation evolution | |
| CN117421231A (en) | Automatic software testing method, system and device | |
| CN118862003A (en) | Multi-source information fusion analysis system in deep sea experiments | |
| CN118173238A (en) | Medical instrument electronic DHR online processing method and system | |
| CN118081767A (en) | Automatic programming system and method for post-processing machining of casting robot | |
| CN117910356A (en) | Digital twinning-based robot hole making process knowledge planning method and system | |
| CN117289940B (en) | Optimization method and system for Zeiss three-dimensional equipment based on off-board programming software | |
| CN117961976B (en) | Assembly robot online detection method and device based on generated diffusion migration | |
| CN118536641A (en) | Wind farm group power prediction method, device, equipment and storage medium | |
| CN118377916A (en) | Construction method of wind turbine equipment operation and maintenance knowledge graph | |
| CN117056400A (en) | Intelligent management system and method for mechanical equipment | |
| US20250189945A1 (en) | Generative artificial intelligence for creation of instruction code from an input | |
| CN120454848B (en) | Fiber optic positioning system and identification method for fiber optic touch tool | |
| CN120046877B (en) | Information execution management system for die manufacturing | |
| Lu et al. | Procedure2command: an ai-based nuclear power plant control command code generation prototype system | |
| CN120104436A (en) | A fusion visualization method and device for multi-source engineering monitoring data | |
| CN116540627A (en) | Machine tool thermal error prediction and compensation group control method and system based on deep transfer learning | |
| Yuan et al. | Research and Implementation of Pointer Instrument Reading Recognition Method for Power Plant Inspection Robot | |
| CN120450895A (en) | Deep learning-based automatic analysis system and method for power grid wiring diagram | |
| CN116662757A (en) | Machining precision prediction method based on self-adaption of related alignment field |
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 |