CN110688722A - Automatic generation method of part attribute matrix based on deep learning - Google Patents
Automatic generation method of part attribute matrix based on deep learning Download PDFInfo
- Publication number
- CN110688722A CN110688722A CN201910986705.8A CN201910986705A CN110688722A CN 110688722 A CN110688722 A CN 110688722A CN 201910986705 A CN201910986705 A CN 201910986705A CN 110688722 A CN110688722 A CN 110688722A
- Authority
- CN
- China
- Prior art keywords
- parts
- matrix
- attribute matrix
- attribute
- deep learning
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- 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)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a deep learning-based automatic generation method of a part attribute matrix, which comprises the following steps: A. acquiring part information of a product serving as a sample, and creating a part dictionary; B. creating a numerical mapping of the parts; C. defining the size of the attribute matrix E; D. establishing a part sequence model according to the structure of a sample product; E. setting a fixed sliding window, and dividing a part sequence model to form a training sample set D; F. constructing a neural network structure, and determining an input layer, a hidden layer and an output layer of the network; G. training the relevant samples; H. by using the attribute matrix E, the invention provides a method for automatically generating the attribute matrix of the parts based on deep learning, and by the method, the attribute matrix can be automatically obtained without manually marking a large number of attributes of a large number of parts one by one.
Description
Technical Field
The invention relates to the technical field of intelligent manufacturing, in particular to a method for automatically generating a part attribute matrix based on deep learning.
Background
In the field of intelligent manufacturing at present, when parts are analyzed by means of data mining or artificial intelligence and the like, the relevance of the parts is often lost easily. And the similarity between parts can be known very effectively by enhancing the relevance of the parts in data mining. During product design, the similarity of parts is accurately and effectively calculated, and the parts can be effectively recommended to be selected, so that the intelligent design efficiency of the product can be improved; during the design of the processing technology, the reusability of process information such as process resources, process parameters and the like can be greatly improved, so that the efficiency of the design of the processing technology can be greatly improved intelligently; when the assembly process is designed, the reusability of the assembly process and the assembly resources of the components can be greatly improved, so that the intelligent design efficiency of the assembly process route can be greatly improved; during simulation analysis, based on recommendation of similarity, grids and loads which are divided previously can be effectively borrowed, and therefore the efficiency of intelligent simulation analysis is greatly improved. Therefore, the method for enhancing the relevance of the parts in data mining has great promotion effect on various links of the manufacturing industry, and is even an extremely important link in large-scale customized intelligent manufacturing.
Currently, when parts are analyzed by means of data mining or artificial intelligence and the like, one-hot vectors are often adopted to carry out numerical processing on the parts, and due to the characteristics of the one-hot vectors, namely the inner product of the one-hot vectors of any two different parts in a part dictionary is 0, the correlation between the parts is lost. And since the dimension of the one-hot vector is easily affected by the length of the dictionary, the related calculation tends to increase exponentially with the increase of the dimension of the vector.
In order to improve the correlation between parts, the property information (such as aperture, outer contour dimension, hole characteristic, outer cylinder characteristic, and the like) of the parts is often used to perform vectorization representation on the parts. The attribute correlation values of each part form an m × n-dimensional matrix (m is the number of parts in the part dictionary, and n is the number of all the corresponding attributes), i.e., an attribute matrix. When the components are vectorized and represented through the attribute matrix, a vector which is lower in dimension than a one-hot vector and contains the attribute information of the parts is obtained. Because the method contains the attribute information of the parts, the relevance of the parts can be greatly improved, and the effectiveness of calculating the content such as the similarity of the parts is improved.
However, the marking of the attribute information often requires a large amount of manual work. Moreover, manually marking and assigning the attribute information of the parts is a very resource-consuming task.
Disclosure of Invention
The invention aims to provide a method for automatically generating a part attribute matrix based on deep learning, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a method for automatically generating a part attribute matrix based on deep learning is characterized by comprising the following steps:
A. acquiring part information of a product serving as a sample, and creating a part dictionary;
B. creating a numerical mapping of the parts;
C. defining the size of the attribute matrix E;
D. establishing a part sequence model according to the structure of a sample product;
E. setting a fixed sliding window, and dividing a part sequence model to form a training sample set D;
F. constructing a neural network structure, and determining an input layer, a hidden layer and an output layer of the network;
G. training the relevant samples;
H. the attribute matrix E is used.
As a further scheme of the invention: the first step is specifically as follows: and acquiring all product structures serving as samples, and creating a part dictionary for part information in the product structures. Different parts are distinguished through the serial numbers of the parts, clustering processing is carried out on each different part, the parts are placed in a part dictionary, and the number of the parts in the part dictionary is N.
As a further scheme of the invention: the second step is specifically: a numerical map is created for each part in the parts dictionary, where the contents of the parts map are defined as an N-dimensional vector. As shown in fig. 1, the dimension of the vector is determined by the size of the part dictionary (i.e., the dimension of the vector is N), and is defined as one-hot vector of the part.
As a further scheme of the invention: the third step is specifically as follows: the attribute matrix E is defined as a matrix of N multiplied by M, wherein the abscissa of the matrix E represents N parts in the dictionary, and the ordinate of the matrix represents M pieces of common characteristic information of the parts.
As a further scheme of the invention: the fourth step is specifically: and acquiring all product structures serving as samples, and processing the serialization of the parts in the product structures according to the structure tree of the product.
As a further scheme of the invention: the fifth step is specifically as follows: setting a fixed sliding window with n parts, assuming that n is 3, determining input and output of a training sample according to three parts in the fixed sliding window and the next part, in the part sequence model, taking three parts in the fixed sliding window P1, P2 and P3 as input of the training sample, taking the next part P4 as output of the training sample, adding P1, P2, P3 and P4 as a sample to the training sample set, sliding the fixed sliding window to the right by one part, changing the input of the training sample into parts P2, P3 and P4 in the fixed sliding window, changing the output into the next part P5, adding P2, P3, P4 and P5 as a sample to the training sample set, and so on, when the sequence model of the part product is divided, dividing the next part product sequence model according to the above process, finally, through continuous sliding window, a training sample set D is formed.
As a further scheme of the invention: the sixth step is specifically: establishing the number of neurons of an input layer and an output layer of the neural network according to the one-hot vector dimension N of the parts, wherein the input of a training sample is three parts in a sliding window, and the output of the training sample is one part behind the three parts, so that the number of neurons of the input layer consists of one-hot vectors of the three parts, namely Nx 3 neurons of the input layer; the number of neurons of the output layer consists of one-hot vectors of one part, namely N multiplied by 1 neurons of the output layer, the number of neurons of the hidden layer of the neural network can be determined by an attribute matrix E with the size of N multiplied by M defined in the fourth step, the neurons from the input layer to the hidden layer are not fully connected, the attribute matrix E is regarded as a weight matrix from the input layer to the hidden layer, the weight matrix is multiplied by the one-hot vectors of the input three parts respectively to obtain embedded vectors of the three parts, the dimensions of the embedded vectors are all equal to M, and therefore the number of neurons of the hidden layer consists of the embedded vectors of the three parts, namely M multiplied by 3 neurons of the hidden layer.
As a further scheme of the invention: the seventh step is specifically: converting the training sample set D into a sample matrix, putting the sample matrix into a constructed neural network, selecting a proper activation function, finally obtaining a network structure which accords with expectation and all optimal weight parameters through calculation, and obtaining a weight matrix from an input layer to a hidden layer, namely an attribute matrix E.
As a further scheme of the invention: the eighth step specifically comprises: and multiplying the one-hot vector of the given part by the trained attribute matrix E to obtain the attribute vector corresponding to the part. If the attribute vectors of the two parts are adopted, the attribute vectors can be applied to related algorithms such as cosine included angles, neural networks and the like, and the similarity of the two parts is calculated.
Compared with the prior art, the invention has the beneficial effects that: the invention provides a method for automatically generating a part attribute matrix based on deep learning, and the method can automatically obtain the attribute matrix without manually marking a large number of attributes of mass parts one by one.
Drawings
FIG. 1 is a one-hot vector diagram of the ith part in the parts dictionary.
FIG. 2 is a schematic diagram of an attribute matrix E of a manual mark.
Fig. 3 is a schematic view of a part sequence model.
Fig. 4 is a schematic diagram of a training sample set D.
FIG. 5 is a schematic diagram of attribute matrix training based on deep learning.
FIG. 6 is a diagram illustrating a one-hot vector dimension reduction calculation process.
FIG. 7 is a diagram of a parts dictionary.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-7, example 1: in the embodiment of the invention, a method for automatically generating a part attribute matrix based on deep learning comprises the following steps:
acquiring part information of a product serving as a sample, and creating a part dictionary.
And acquiring all product structures serving as samples, and creating a part dictionary for part information in the product structures. Different parts are distinguished through the serial numbers of the parts, clustering processing is carried out on each different part, the parts are placed in a part dictionary, and the number of the parts in the part dictionary is N.
And secondly, creating a numerical value mapping of the parts.
A numerical map is created for each part in the parts dictionary, where the contents of the parts map are defined as an N-dimensional vector. As shown in fig. 1, the dimension of the vector is determined by the size of the part dictionary (i.e., the dimension of the vector is N), and is defined as one-hot vector of the part.
And thirdly, defining the size of the attribute matrix E.
The attribute matrix E is defined as a matrix of N × M size, wherein the abscissa of the matrix E represents N parts in the dictionary, and the ordinate of the matrix represents M pieces of common characteristic information of the parts, as shown in fig. 2.
And fourthly, establishing a part sequence model according to the product structure in the sample.
All product structures are obtained as samples, and the serialization of the parts in the product structures is processed according to the structure tree of the products, such as the parts shown in fig. 3.
And fifthly, setting a fixed sliding window, dividing a part sequence model, and forming a training sample set D.
And setting a fixed sliding window with n parts, assuming that n is 3, and determining the input and the output of the training sample according to three parts in the fixed sliding window and the next part. As shown in fig. 4, in the part sequence model, three parts P1, P2, and P3 in the fixed sliding window are input of a training sample, and the next part P4 is output of the training sample, and P1, P2, P3, and P4 are added as one sample to a training sample set. Then the fixed sliding window is slid to the right by one part, the input of the training sample becomes the parts P2, P3, P4 in the fixed history window, the output becomes the next part P5, and P2, P3, P4 and P5 are added to the training sample set as one sample. And by analogy, when the sequence model of the part product is divided, dividing the sequence model of the next part product according to the process, and finally forming a training sample set D through a continuous sliding window.
And sixthly, constructing a neural network structure, and determining an input layer, a hidden layer and an output layer of the network.
And establishing the number of the neurons of the input layer and the output layer of the neural network according to the one-hot vector dimension N of the part. Because the input of the training sample is three parts in the fixed history window and the output is one part behind the training sample, the number of the neurons in the input layer consists of one-hot vectors of the three parts, namely Nx 3 neurons in the input layer; the number of output layer neurons is composed of one-hot vectors of a part, namely, Nx 1 output layer neurons.
The number of neurons in the hidden layer of the neural network can be derived from the attribute matrix E of size N × M defined in step 4. As shown in fig. 5, the neurons from the input layer to the hidden layer are not fully connected, the attribute matrix E is regarded as a weight matrix from the input layer to the hidden layer, and is multiplied by one-hot vectors of the three input components, respectively, to obtain embedded vectors of the three components, and the dimensions of the embedded vectors are all equal to M, so that the number of the neurons in the hidden layer is formed by the embedded vectors of the three components, that is, M × 3 neurons in the hidden layer.
And seventhly, training the related samples.
The training sample set D is converted into a sample matrix (the row number of the sample matrix is the number of samples divided by the part sequence model, the column number is the dimensionality of one-hot vectors of three parts, namely Nx 3), the sample matrix is put into a constructed neural network, a proper activation function (such as Tanh, Sigmoid, ReLu, Softmax and the like) is selected, and a network structure meeting expectations and all optimal weight parameters are finally obtained through calculation (BP neural network and the like), and a weight matrix from an input layer to a hidden layer, namely an attribute matrix E, is obtained.
And eighthly, using the attribute matrix E.
Example 2: on the basis of the embodiment 1, in step eight, the one-hot vector of the given part is multiplied by the trained attribute matrix E to obtain the attribute vector corresponding to the part. If the attribute vectors of the two parts are adopted, the attribute vectors can be applied to related algorithms such as cosine included angles, neural networks and the like, and the similarity of the two parts is calculated.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (9)
1. A method for automatically generating a part attribute matrix based on deep learning is characterized by comprising the following steps:
acquiring part information of a product serving as a sample, and creating a part dictionary;
secondly, creating numerical value mapping of parts;
thirdly, defining the size of the attribute matrix E;
fourthly, establishing a part sequence model according to the structure of the sample product;
fifthly, setting a fixed sliding window, dividing a part sequence model, and forming a training sample set D;
constructing a neural network structure, and determining an input layer, a hidden layer and an output layer of the network;
seventhly, training related samples;
and eighthly, using the attribute matrix E.
2. The method for automatically generating the part attribute matrix based on deep learning according to claim 1, wherein the first step specifically comprises: and acquiring all product structures serving as samples, and creating a part dictionary for part information in the product structures. Different parts are distinguished through the serial numbers of the parts, clustering processing is carried out on each different part, the parts are placed in a part dictionary, and the number of the parts in the part dictionary is N.
3. The method for automatically generating the part attribute matrix based on deep learning according to claim 2, wherein the second step specifically comprises: a numerical map is created for each part in the parts dictionary, where the contents of the parts map are defined as an N-dimensional vector, where the dimension of the vector is determined by the size of the parts dictionary (i.e., the dimension of the vector is N), and is defined as a one-hot vector for the part.
4. The method for automatically generating the part attribute matrix based on deep learning according to claim 3, wherein the third step specifically comprises: the attribute matrix E is defined as a matrix of N multiplied by M, wherein the abscissa of the matrix E represents N parts in the dictionary, and the ordinate of the matrix represents M pieces of common characteristic information of the parts.
5. The method for automatically generating the part attribute matrix based on deep learning according to claim 4, wherein the fourth step is specifically: and acquiring all product structures serving as samples, and processing the serialization of the parts in the product structures according to the structure tree of the product.
6. The method for automatically generating the part attribute matrix based on deep learning according to claim 4, wherein the fifth step is specifically: setting a fixed sliding window with n parts, assuming that n is 3, determining input and output of a training sample according to three parts in the fixed sliding window and the next part, in the part sequence model, taking three parts in the fixed sliding window P1, P2 and P3 as input of the training sample, taking the next part P4 as output of the training sample, adding P1, P2, P3 and P4 as a sample to the training sample set, sliding the fixed sliding window to the right by one part, changing the input of the training sample into parts P2, P3 and P4 in the fixed sliding window, changing the output into the next part P5, adding P2, P3, P4 and P5 as a sample to the training sample set, and so on, when the sequence model of the part product is divided, dividing the next part product sequence model according to the above process, finally, through continuous sliding window, a training sample set D is formed.
7. The method for automatically generating the part attribute matrix based on deep learning according to claim 6, wherein the sixth step is specifically: establishing the number of neurons of an input layer and an output layer of the neural network according to the one-hot vector dimension N of the parts, wherein the input of a training sample is three parts in a fixed sliding window, and the output of the training sample is one part behind the three parts, so that the number of neurons of the input layer consists of one-hot vectors of the three parts, namely Nx 3 neurons of the input layer; the number of neurons of the output layer consists of one-hot vectors of one part, namely N multiplied by 1 neurons of the output layer, the number of neurons of the hidden layer of the neural network can be determined by an attribute matrix E with the size of N multiplied by M defined in the fourth step, the neurons from the input layer to the hidden layer are not fully connected, the attribute matrix E is regarded as a weight matrix from the input layer to the hidden layer, the weight matrix is multiplied by the one-hot vectors of the input three parts respectively to obtain embedded vectors of the three parts, the dimensions of the embedded vectors are all equal to M, and therefore the number of neurons of the hidden layer consists of the embedded vectors of the three parts, namely M multiplied by 3 neurons of the hidden layer.
8. The method for automatically generating the part attribute matrix based on deep learning according to claim 1, wherein the seventh step is specifically: converting the training sample set D into a sample matrix, putting the sample matrix into a constructed neural network, selecting a proper activation function, finally obtaining a network structure which accords with expectation and all optimal weight parameters through calculation, and obtaining a weight matrix from an input layer to a hidden layer, namely an attribute matrix E.
9. The method for automatically generating the part attribute matrix based on deep learning according to claim 1, wherein the eighth step specifically comprises: and multiplying the one-hot vector of the given part by the trained attribute matrix E to obtain the attribute vector corresponding to the part. If the attribute vectors of the two parts are adopted, the attribute vectors can be applied to related algorithms such as cosine included angles, neural networks and the like, and the similarity of the two parts is calculated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910986705.8A CN110688722B (en) | 2019-10-17 | 2019-10-17 | Automatic generation method of part attribute matrix based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910986705.8A CN110688722B (en) | 2019-10-17 | 2019-10-17 | Automatic generation method of part attribute matrix based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110688722A true CN110688722A (en) | 2020-01-14 |
| CN110688722B CN110688722B (en) | 2023-08-08 |
Family
ID=69113315
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910986705.8A Active CN110688722B (en) | 2019-10-17 | 2019-10-17 | Automatic generation method of part attribute matrix based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110688722B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111625912A (en) * | 2020-06-04 | 2020-09-04 | 深制科技(苏州)有限公司 | Deep learning oriented Bom structure and creation method thereof |
| CN112232423A (en) * | 2020-10-21 | 2021-01-15 | 深制科技(苏州)有限公司 | Part2Vec Part vectorization processing method based on deep learning |
| CN112232423B (en) * | 2020-10-21 | 2024-05-28 | 深制科技(苏州)有限公司 | Part2Vec Part vectorization processing method based on deep learning |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105405060A (en) * | 2015-12-01 | 2016-03-16 | 中国计量学院 | Customized product similarity calculation method based on structure editing operation |
| CN105607288A (en) * | 2015-12-29 | 2016-05-25 | 大连楼兰科技股份有限公司 | Intelligent glasses omnibearing vehicle part completeness detection method based on acoustic detection assistance |
| CN106372732A (en) * | 2016-08-22 | 2017-02-01 | 中国北方车辆研究所 | Hybrid decision method for maintainability and general characteristics of armored vehicle |
| US20170091615A1 (en) * | 2015-09-28 | 2017-03-30 | Siemens Aktiengesellschaft | System and method for predicting power plant operational parameters utilizing artificial neural network deep learning methodologies |
| CN106874914A (en) * | 2017-01-12 | 2017-06-20 | 华南理工大学 | A kind of industrial machinery arm visual spatial attention method based on depth convolutional neural networks |
| CN107153877A (en) * | 2017-05-24 | 2017-09-12 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of machine learning method of rule-based matrix multiway tree |
| CN107204043A (en) * | 2017-06-23 | 2017-09-26 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of distributed design approach of feature based mapping |
| CN108009527A (en) * | 2017-12-26 | 2018-05-08 | 东北大学 | A kind of intelligent characteristic recognition methods towards STEP-NC2.5D manufacturing features |
| CN108197702A (en) * | 2018-02-09 | 2018-06-22 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of method of the product design based on evaluation network and Recognition with Recurrent Neural Network |
| CN108230121A (en) * | 2018-02-09 | 2018-06-29 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of product design method based on Recognition with Recurrent Neural Network |
| CN108280057A (en) * | 2017-12-26 | 2018-07-13 | 厦门大学 | A kind of microblogging rumour detection method based on BLSTM |
| CN108280746A (en) * | 2018-02-09 | 2018-07-13 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of product design method based on bidirectional circulating neural network |
| CN108388651A (en) * | 2018-02-28 | 2018-08-10 | 北京理工大学 | A kind of file classification method based on the kernel of graph and convolutional neural networks |
| CN108563863A (en) * | 2018-04-11 | 2018-09-21 | 北京交通大学 | The energy consumption calculation and dispatching method of City Rail Transit System |
| CN108596327A (en) * | 2018-03-27 | 2018-09-28 | 中国地质大学（武汉） | A kind of seismic velocity spectrum artificial intelligence pick-up method based on deep learning |
| CN108763445A (en) * | 2018-05-25 | 2018-11-06 | 厦门智融合科技有限公司 | Construction method, device, computer equipment and the storage medium in patent knowledge library |
| WO2018204410A1 (en) * | 2017-05-04 | 2018-11-08 | Minds Mechanical, Llc | Metrology system for machine learning-based manufacturing error predictions |
| CN109344405A (en) * | 2018-09-25 | 2019-02-15 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of similarity processing method based on TF-IDF thought and neural network |
| CN109740536A (en) * | 2018-06-12 | 2019-05-10 | 北京理工大学 | A kind of relatives' recognition methods based on Fusion Features neural network |
| CN109977972A (en) * | 2019-03-29 | 2019-07-05 | 东北大学 | A kind of intelligent characteristic recognition methods based on STEP |
-
2019
- 2019-10-17 CN CN201910986705.8A patent/CN110688722B/en active Active
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170091615A1 (en) * | 2015-09-28 | 2017-03-30 | Siemens Aktiengesellschaft | System and method for predicting power plant operational parameters utilizing artificial neural network deep learning methodologies |
| CN105405060A (en) * | 2015-12-01 | 2016-03-16 | 中国计量学院 | Customized product similarity calculation method based on structure editing operation |
| CN105607288A (en) * | 2015-12-29 | 2016-05-25 | 大连楼兰科技股份有限公司 | Intelligent glasses omnibearing vehicle part completeness detection method based on acoustic detection assistance |
| CN106372732A (en) * | 2016-08-22 | 2017-02-01 | 中国北方车辆研究所 | Hybrid decision method for maintainability and general characteristics of armored vehicle |
| CN106874914A (en) * | 2017-01-12 | 2017-06-20 | 华南理工大学 | A kind of industrial machinery arm visual spatial attention method based on depth convolutional neural networks |
| WO2018204410A1 (en) * | 2017-05-04 | 2018-11-08 | Minds Mechanical, Llc | Metrology system for machine learning-based manufacturing error predictions |
| CN107153877A (en) * | 2017-05-24 | 2017-09-12 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of machine learning method of rule-based matrix multiway tree |
| CN107204043A (en) * | 2017-06-23 | 2017-09-26 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of distributed design approach of feature based mapping |
| CN108280057A (en) * | 2017-12-26 | 2018-07-13 | 厦门大学 | A kind of microblogging rumour detection method based on BLSTM |
| CN108009527A (en) * | 2017-12-26 | 2018-05-08 | 东北大学 | A kind of intelligent characteristic recognition methods towards STEP-NC2.5D manufacturing features |
| CN108230121A (en) * | 2018-02-09 | 2018-06-29 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of product design method based on Recognition with Recurrent Neural Network |
| CN108197702A (en) * | 2018-02-09 | 2018-06-22 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of method of the product design based on evaluation network and Recognition with Recurrent Neural Network |
| CN108280746A (en) * | 2018-02-09 | 2018-07-13 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of product design method based on bidirectional circulating neural network |
| CN108388651A (en) * | 2018-02-28 | 2018-08-10 | 北京理工大学 | A kind of file classification method based on the kernel of graph and convolutional neural networks |
| CN108596327A (en) * | 2018-03-27 | 2018-09-28 | 中国地质大学（武汉） | A kind of seismic velocity spectrum artificial intelligence pick-up method based on deep learning |
| CN108563863A (en) * | 2018-04-11 | 2018-09-21 | 北京交通大学 | The energy consumption calculation and dispatching method of City Rail Transit System |
| CN108763445A (en) * | 2018-05-25 | 2018-11-06 | 厦门智融合科技有限公司 | Construction method, device, computer equipment and the storage medium in patent knowledge library |
| CN109740536A (en) * | 2018-06-12 | 2019-05-10 | 北京理工大学 | A kind of relatives' recognition methods based on Fusion Features neural network |
| CN109344405A (en) * | 2018-09-25 | 2019-02-15 | 艾凯克斯（嘉兴）信息科技有限公司 | A kind of similarity processing method based on TF-IDF thought and neural network |
| CN109977972A (en) * | 2019-03-29 | 2019-07-05 | 东北大学 | A kind of intelligent characteristic recognition methods based on STEP |
Non-Patent Citations (1)
| Title |
|---|
| 宋晶晶: "产品技术特征与零部件特征配置及其优化技术研究", no. 12, pages 028 - 27 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111625912A (en) * | 2020-06-04 | 2020-09-04 | 深制科技(苏州)有限公司 | Deep learning oriented Bom structure and creation method thereof |
| CN112232423A (en) * | 2020-10-21 | 2021-01-15 | 深制科技(苏州)有限公司 | Part2Vec Part vectorization processing method based on deep learning |
| CN112232423B (en) * | 2020-10-21 | 2024-05-28 | 深制科技(苏州)有限公司 | Part2Vec Part vectorization processing method based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110688722B (en) | 2023-08-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109960759B (en) | Recommendation system click rate prediction method based on deep neural network | |
| CN110929697B (en) | Neural network target identification method and system based on residual error structure | |
| CN110609899B (en) | Specific target emotion classification method based on improved BERT model | |
| CN104598611B (en) | The method and system being ranked up to search entry | |
| CN109284406B (en) | Intention identification method based on difference cyclic neural network | |
| CN110263323A (en) | Keyword abstraction method and system based on the long Memory Neural Networks in short-term of fence type | |
| CN105631479A (en) | Imbalance-learning-based depth convolution network image marking method and apparatus | |
| EP4009219A1 (en) | Analysis of natural language text in document using hierarchical graph | |
| CN104834748A (en) | Image retrieval method utilizing deep semantic to rank hash codes | |
| CN108197294A (en) | A kind of text automatic generation method based on deep learning | |
| CN108875000A (en) | A kind of semantic relation classification method merging more syntactic structures | |
| CN104731962A (en) | Method and system for friend recommendation based on similar associations in social network | |
| CN103324954A (en) | Image classification method based on tree structure and system using same | |
| CN113344615B (en) | Marketing campaign prediction method based on GBDT and DL fusion model | |
| CN110598869B (en) | Classification method and device based on sequence model and electronic equipment | |
| CN111523420A (en) | Header classification and header list semantic identification method based on multitask deep neural network | |
| CN112860904B (en) | External knowledge-integrated biomedical relation extraction method | |
| CN107247753A (en) | A kind of similar users choosing method and device | |
| CN113010683B (en) | Entity relationship identification method and system based on improved graph attention network | |
| CN104850533A (en) | Constrained nonnegative matrix decomposing method and solving method | |
| CN110688722A (en) | Automatic generation method of part attribute matrix based on deep learning | |
| CN112100486B (en) | Deep learning recommendation system and method based on graph model | |
| CN107589936B (en) | Product line variability configuration optimization method based on requirement text and variability model tracking relation | |
| CN111797135A (en) | Structured data processing method based on entity embedding | |
| CN108280746B (en) | Product design method based on bidirectional cyclic neural network |
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 |