CN110674263A - Method and device for automatically classifying model component files - Google Patents
Method and device for automatically classifying model component files Download PDFInfo
- Publication number
- CN110674263A CN110674263A CN201911224204.2A CN201911224204A CN110674263A CN 110674263 A CN110674263 A CN 110674263A CN 201911224204 A CN201911224204 A CN 201911224204A CN 110674263 A CN110674263 A CN 110674263A
- Authority
- CN
- China
- Prior art keywords
- model
- description
- classification
- corpus
- component
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A method and device for automatically classifying model component files comprise the following steps: analyzing the text description information of the model component to obtain a description text file; establishing a corpus by using the description text file; training a classification model by using the established corpus; and automatically classifying by using the trained classification model. The automatic classification of the model component files can be realized, and the efficiency of sorting the model component material library is improved.
Description
Technical Field
The application belongs to the technical field of computer geometric modeling, and particularly relates to a method and a device for automatically classifying model component files.
Background
In the field of engineering and construction, more and more designers (including architectural designers, structural engineers, electromechanical designers, etc.) are beginning to model buildings using three-dimensional simulation techniques. After the model is created, the designer delivers the model to a developer (first party) of the building, a constructor (construction company), and the like for acceptance, examination, guidance of construction, and the like.
When a designer designs a building model, the designer typically uses model elements for modeling. In consideration of reusability of model members, designers can efficiently complete building models, so that model members are accumulated from individual designers to design units to form a model member library. An ordered library of model building block materials is efficiently available. Usually, a design enterprise has a professional to maintain its own component material library, and usually, according to professional knowledge, model components are judged and classified, and model component files are stored in a pre-established folder according to the classification.
However, the existing component material library is organized by manual participation, the component classification level depends on the service level of workers, the classification efficiency is low, and the subjectivity is strong.
Disclosure of Invention
The invention aims to provide a method and a device for automatically classifying model component files, which can realize automatic classification of the model component files and improve the efficiency of sorting a model component material library.
The invention provides a method for automatically classifying model component files, which comprises the following steps:
step 1: analyzing the text description information of the model component to obtain a description text file;
step 2: establishing a corpus by using the description text file;
and step 3: training a classification model by using the established corpus;
and 4, step 4: and automatically classifying by using the trained classification model.
Further, the parsing the text description information of the model component specifically includes:
(1) opening a model component and deriving the text description information;
(2) and saving the derived text description information as a description text file.
Further, the text description information includes: attribute parameter information, material information, and other textual description information.
Further, the establishing a corpus by using the description text file specifically includes:
(1) a general building industry corpus is used as an initial corpus;
(2) segmenting the description text in the description text file;
(3) and manually checking the word segmentation result, and supplementing the information which cannot be correctly segmented to form a complete corpus.
Further, the training of the classification model using the established corpus includes:
(1) manually labeling the classification of model members;
(2) performing feature selection by using the word segmentation result in the corpus;
(3) establishing a relation between the description characteristics and the classification of the model components to obtain training data;
(4) machine learning results in a classification model.
Further, the selecting features by using the word segmentation result in the corpus specifically includes:
1) segmenting a description text of the model component to obtain candidate description features;
2) and classifying the candidate description features in the segmentation result according to the model components, checking the relevance and selecting proper features.
Further, the establishing of the relationship between the description features and the classification of the model components to obtain the training data specifically includes:
1) performing feature mapping on the component description information to obtain a feature descriptor;
2) and combining the feature descriptors and the classification values into complete training data.
Further, the automatically classifying by using the trained classification model specifically includes:
(1) analyzing the model component file to obtain a description text;
(2) mapping the description text to obtain description characteristics;
(3) and inputting the description characteristics into the classification model for automatic classification to obtain a classification result.
The invention also provides a device for automatically classifying model component files, which comprises a component analysis unit, a corpus establishing unit, a model training unit and an automatic classification unit, wherein:
the component analysis unit is used for analyzing the text description information of the model component to obtain a description text file;
the corpus establishing unit is used for establishing a corpus by utilizing the description text file;
the model training unit is used for training a classification model by using the established corpus;
and the automatic classification unit is used for automatically classifying by using the trained classification model.
Further, the component analysis unit is specifically configured to:
(1) opening a model component and deriving the text description information;
(2) and saving the derived text description information as a description text file.
Further, the text description information includes: attribute parameter information, material information, and other textual description information.
Further, the corpus establishing unit is specifically configured to:
(1) a general building industry corpus is used as an initial corpus;
(2) segmenting the description text in the description text file;
(3) and manually checking the word segmentation result, and supplementing the information which cannot be correctly segmented to form a complete corpus.
Further, the model training unit is specifically configured to:
(1) manually labeling the classification of model members;
(2) performing feature selection by using the word segmentation result in the corpus;
(3) establishing a relation between the description characteristics and the classification of the model components to obtain training data;
(4) machine learning results in a classification model.
Further, the selecting features by using the word segmentation result in the corpus specifically includes:
1) segmenting a description text of the model component to obtain candidate description features;
2) and classifying the candidate description features in the segmentation result according to the model components, checking the relevance and selecting proper features.
Further, the establishing of the relationship between the description features and the classification of the model components to obtain the training data specifically includes:
1) performing feature mapping on the component description information to obtain a feature descriptor;
2) and combining the feature descriptors and the classification values into complete training data.
Further, the automatic classification unit is specifically configured to:
(1) analyzing the model component file to obtain a description text;
(2) mapping the description text to obtain description characteristics;
(3) and inputting the description characteristics into the classification model for automatic classification to obtain a classification result.
Compared with the prior art, the method and the device for automatically classifying the model component files, provided by the invention, classify the model components and store the classified model components into the model component library, so that the classified model components can be displayed, the existing well-organized and classified model components are used as training data, an automatic classification model is obtained through a machine learning algorithm, the model components can be automatically classified, subjective dependence is reduced by the algorithm classification, and the efficiency of arranging the model component material library is improved.
Drawings
To facilitate understanding and implementing the present application by those of ordinary skill in the art, the following technical solutions of the present application are described clearly and completely with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.
FIG. 1 is a flow chart diagram of a method for automatically classifying model component files according to the present application.
Fig. 2 is a schematic block diagram of an apparatus for automatically classifying model component files according to the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Before describing the scheme of the present application, several terms of art are defined:
building a model: is a representation form of the building, which vividly and completely describes various aspects of the building (such as the appearance, the internal structure, the design of water heating electric pipelines and the like of the building) through three-dimensional stereo representation; the building model mentioned in the application mainly refers to a model file designed and stored by a designer through computer simulation software.
A model component: the digital representation form of the component in the computer visually and completely describes various aspects of the component (such as three-dimensional geometric information, parameter attribute information, installation process information, maintenance information and the like) through three-dimensional stereo representation and is stored in a storage device of the computer. The model component mentioned in the invention refers to a model file designed and stored by a designer through three-dimensional design software. The model member is equivalent to the logical concept of the member to the building relative to the modeling model, and the whole building model is combined through a large number of model member designs.
Model component library: the model elements are used by designers to design building models, and the model elements correspond to building design materials. The model component library is a material library and is a collection of a large number of model components. When a designer designs a building model, the designer looks up and uses the model components to model from a library of model components.
The first embodiment is as follows:
the embodiment of the invention provides a method for automatically classifying model component files, which comprises the following steps:
step 1: and analyzing the text description information of the model component to obtain a description text file.
Analyzing the model component firstly, in order to obtain original description information of the model component, automatic classification needs to use the original information and apply the original information to a classification model to obtain a final result; secondly, to supplement the existing corpus with descriptive text files.
The text description information of the analysis model component specifically comprises:
(1) opening a model component, deriving textual description information, the deriving textual description information comprising: deriving attribute parameter information, texture information, and other text description information (e.g., file name information);
(2) and saving the derived text description information as a description text file.
Step 2: and establishing a corpus by using the description text file.
The corpus is the basis of word segmentation, and the word segmentation is the basis of searching classification characteristics. The corpus is available, and the description text file analyzed in the step one can supplement the existing corpus.
The establishing of the corpus specifically comprises the following steps:
(1) a general building industry corpus is used as an initial corpus;
(2) segmenting the description text in the description text file by using a segmentation tool;
(3) and manually checking the word segmentation result, and supplementing the information which cannot be correctly segmented to form a complete corpus. This is not required if there is a corpus that is the most complete in terms of model building blocks and the word segmentation results are completely correct. In actual operation, the result that the word segmentation result is not ideal can occur, such as: in the safe experience area, the possible word segmentation results are 'safe' and 'experience area', but the ideal result is 'safe experience area', and at the moment, the word needs to be supplemented to the corpus.
And step 3: and training a classification model by using the established corpus.
The training of the classification model by using the established corpus comprises the following steps:
(1) manually marking the classification of the model components, and classifying the model components by depending on professionals;
(2) performing feature selection by using the word segmentation result in the corpus;
1) segmenting a description text of the model component to obtain candidate description features;
2) and (3) carrying out correlation degree check on the candidate description features in the segmentation result according to model component classification, namely calculating the correlation degree of the candidate description features and the model component classification, selecting proper features, and generally selecting high correlation degree as the features.
(3) Establishing a relation between the description features and the classification of the model components to obtain training data, and specifically comprising the following steps:
1) and performing feature mapping on the component description information to obtain a feature descriptor. The feature descriptor is a multi-dimensional vector, the number of description features is n, so that the feature descriptor has n dimensions, and for a specific model component, the component description information of the model component contains a certain feature, so that the value of the feature descriptor of the dimension is 1.
2) And combining the feature descriptors and the classification values into complete training data. The features and the classifications are specific expressions, and the feature descriptors and the classification values are mappings which enable a computer to operate on realistic meanings.
(4) The classification model is obtained by machine learning, and the machine learning algorithm can be SVM, Logistic and the like.
The steps 1, 2 and 3 are all basic steps, and are used for obtaining the machine learning model with automatic classification.
And 4, step 4: and automatically classifying by using the trained classification model.
The automatic classification is carried out by using the trained classification model, and specifically comprises the following steps:
(1) analyzing the model component file to obtain a description text;
(2) mapping the description text to obtain description characteristics; in short, the description text of a member may only contain a part of the features, each member is different, and the mapping is a mathematical expression which is finally expressed as a multi-dimensional vector and does not contain the features.
(3) And inputting the description characteristics into the classification model for automatic classification to obtain a classification result.
Example two:
the second embodiment of the invention provides a device for automatically classifying model component files, which comprises a component analysis unit, a corpus establishing unit, a model training unit and an automatic classification unit.
And the component analysis unit is used for analyzing the text description information of the model component to obtain a description text file.
Analyzing the model component firstly, in order to obtain original description information of the model component, automatic classification needs to use the original information and apply the original information to a classification model to obtain a final result; secondly, to supplement the existing corpus with descriptive text files.
The component analysis unit is specifically configured to:
(1) opening a model component, deriving textual description information, the deriving textual description information comprising: deriving attribute parameter information, texture information, and other text description information (e.g., file name information);
(2) and saving the derived text description information as a description text file.
And the corpus establishing unit is used for establishing a corpus by utilizing the description text file.
The corpus is the basis of word segmentation, and the word segmentation is the basis of searching classification characteristics. The corpus is available, and the description text file analyzed in the step one can supplement the existing corpus.
The corpus establishing unit is specifically configured to:
(1) a general building industry corpus is used as an initial corpus;
(2) segmenting the description text in the description text file by using a segmentation tool;
(3) and manually checking the word segmentation result, and supplementing the information which cannot be correctly segmented to form a complete corpus. This is not required if there is a corpus that is the most complete in terms of model building blocks and the word segmentation results are completely correct. In actual operation, the result that the word segmentation result is not ideal can occur, such as: in the safe experience area, the possible word segmentation results are 'safe' and 'experience area', but the ideal result is 'safe experience area', and at the moment, the word needs to be supplemented to the corpus.
And the model training unit is used for training a classification model by using the established corpus.
The model training unit is specifically configured to:
(1) manually marking the classification of the model components, and classifying the model components by depending on professionals;
(2) performing feature selection by using the word segmentation result in the corpus;
1) segmenting a description text of the model component to obtain candidate description features;
2) and (3) carrying out correlation degree check on the candidate description features in the segmentation result according to model component classification, namely calculating the correlation degree of the candidate description features and the model component classification, selecting proper features, and generally selecting high correlation degree as the features.
(3) Establishing a relation between the description features and the classification of the model components to obtain training data, and specifically comprising the following steps:
1) and performing feature mapping on the component description information to obtain a feature descriptor. The feature descriptor is a multi-dimensional vector, the number of description features is n, so that the feature descriptor has n dimensions, and for a specific model component, the component description information of the model component contains a certain feature, so that the value of the feature descriptor of the dimension is 1.
2) And combining the feature descriptors and the classification values into complete training data. The features and the classifications are specific expressions, and the feature descriptors and the classification values are mappings which enable a computer to operate on realistic meanings.
(4) The classification model is obtained by machine learning, and the machine learning algorithm can be SVM, Logistic and the like.
The component analysis unit, the corpus establishing unit and the model training unit are used for obtaining the machine learning model with automatic classification.
And the automatic classification unit is used for automatically classifying by using the trained classification model.
The automatic classification unit is specifically configured to:
(1) analyzing the model component file to obtain a description text;
(2) mapping the description text to obtain description characteristics; in short, the description text of a member may only contain a part of the features, each member is different, and the mapping is a mathematical expression which is finally expressed as a multi-dimensional vector and does not contain the features.
(3) And inputting the description characteristics into the classification model for automatic classification to obtain a classification result.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods, apparatus, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart and block diagrams may represent a unit, module, segment, or portion of code, which comprises one or more computer-executable instructions for implementing the logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. It will also be noted that each block of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The present application is not limited to any specific form of hardware or software combination. In summary, the above description is only a preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (12)
1. A method for automatically classifying model component files, the method comprising the steps of:
step 1: analyzing the text description information of the model component to obtain a description text file;
step 2: establishing a corpus by using the description text file;
and step 3: training a classification model by using the established corpus;
and 4, step 4: automatically classifying by using the trained classification model;
the training of the classification model by using the established corpus specifically includes:
(1) manually labeling the classification of model members;
(2) utilizing the word segmentation result in the corpus to perform feature selection, specifically comprising:
1) segmenting a description text of the model component to obtain candidate description features;
2) classifying the candidate description features in the segmentation result according to the model components, checking the relevance, and selecting proper features;
(3) establishing a relation between the description characteristics and the classification of the model components to obtain training data;
(4) machine learning results in a classification model.
2. The method according to claim 1, wherein parsing the textual description information of the model component specifically comprises:
(1) opening a model component and deriving the text description information;
(2) and saving the derived text description information as a description text file.
3. The method according to claim 1 or 2, wherein the text description information comprises: attribute parameter information or material information.
4. The method according to claim 1 or 2, wherein the establishing a corpus using the description text file specifically comprises:
(1) a general building industry corpus is used as an initial corpus;
(2) segmenting the description text in the description text file;
(3) and manually checking the word segmentation result, and supplementing the information which cannot be correctly segmented to form a complete corpus.
5. The method according to claim 1, wherein the establishing of the relationship between the descriptive characteristics and the classification of the model components to obtain the training data specifically comprises:
1) performing feature mapping on the component description information to obtain a feature descriptor;
2) and combining the feature descriptors and the classification values into complete training data.
6. The method according to claim 1 or 2, wherein the automatic classification using the trained classification model specifically comprises:
(1) analyzing the model component file to obtain a description text;
(2) mapping the description text to obtain description characteristics;
(3) and inputting the description characteristics into the classification model for automatic classification to obtain a classification result.
7. The device for automatically classifying the model component files is characterized by comprising a component analyzing unit, a corpus establishing unit, a model training unit and an automatic classifying unit, wherein:
the component analysis unit is used for analyzing the text description information of the model component to obtain a description text file;
the corpus establishing unit is used for establishing a corpus by utilizing the description text file;
the model training unit is used for training a classification model by using the established corpus;
the automatic classification unit is used for automatically classifying by using the trained classification model;
the training of the classification model by using the established corpus specifically includes:
(1) manually labeling the classification of model members;
(2) utilizing the word segmentation result in the corpus to perform feature selection, specifically comprising:
1) segmenting a description text of the model component to obtain candidate description features;
2) classifying the candidate description features in the segmentation result according to the model components, checking the relevance, and selecting proper features;
(3) establishing a relation between the description characteristics and the classification of the model components to obtain training data;
(4) machine learning results in a classification model.
8. The apparatus according to claim 7, wherein the component parsing unit is specifically configured to:
(1) opening a model component and deriving the text description information;
(2) and saving the derived text description information as a description text file.
9. The apparatus according to claim 7 or 8, wherein the text description information comprises: attribute parameter information or material information.
10. The apparatus according to claim 7 or 8, wherein the corpus establishing unit is specifically configured to:
(1) a general building industry corpus is used as an initial corpus;
(2) segmenting the description text in the description text file;
(3) and manually checking the word segmentation result, and supplementing the information which cannot be correctly segmented to form a complete corpus.
11. The apparatus according to claim 7, wherein the establishing of the relationship between the descriptive characteristics and the classification of the model components to obtain the training data specifically comprises:
1) performing feature mapping on the component description information to obtain a feature descriptor;
2) and combining the feature descriptors and the classification values into complete training data.
12. The apparatus according to claim 7 or 8, wherein the automatic classification unit is specifically configured to:
(1) analyzing the model component file to obtain a description text;
(2) mapping the description text to obtain description characteristics;
(3) and inputting the description characteristics into the classification model for automatic classification to obtain a classification result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911224204.2A CN110674263B (en) | 2019-12-04 | 2019-12-04 | Method and device for automatically classifying model component files |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911224204.2A CN110674263B (en) | 2019-12-04 | 2019-12-04 | Method and device for automatically classifying model component files |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110674263A true CN110674263A (en) | 2020-01-10 |
| CN110674263B CN110674263B (en) | 2022-02-08 |
Family
ID=69088331
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911224204.2A Active CN110674263B (en) | 2019-12-04 | 2019-12-04 | Method and device for automatically classifying model component files |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110674263B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819106A (en) * | 2021-04-16 | 2021-05-18 | 江西博微新技术有限公司 | IFC component type identification method, device, storage medium and equipment |
| CN113553483A (en) * | 2021-07-02 | 2021-10-26 | 广联达科技股份有限公司 | Component retrieval method, component retrieval device, electronic equipment and readable storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1564129A (en) * | 2004-04-02 | 2005-01-12 | 清华大学 | Method of packing member and consistent visit |
| CN101794303A (en) * | 2010-02-11 | 2010-08-04 | 重庆邮电大学 | Method and device for classifying text and structuring text classifier by adopting characteristic expansion |
| CN104965867A (en) * | 2015-06-08 | 2015-10-07 | 南京师范大学 | Text event classification method based on CHI feature selection |
| CN106503254A (en) * | 2016-11-11 | 2017-03-15 | 上海智臻智能网络科技股份有限公司 | Language material sorting technique, device and terminal |
| CN106897428A (en) * | 2017-02-27 | 2017-06-27 | 腾讯科技（深圳）有限公司 | Text classification feature extracting method, file classification method and device |
| CN108153895A (en) * | 2018-01-06 | 2018-06-12 | 国网福建省电力有限公司 | A kind of building of corpus method and system based on open data |
| CN108170818A (en) * | 2017-12-29 | 2018-06-15 | 深圳市金立通信设备有限公司 | A kind of file classification method, server and computer-readable medium |
| CN108241741A (en) * | 2017-12-29 | 2018-07-03 | 深圳市金立通信设备有限公司 | A kind of file classification method, server and computer readable storage medium |
| CN108334501A (en) * | 2018-03-21 | 2018-07-27 | 王欣 | Electronic document analysis system based on machine learning and method |
| CN109189932A (en) * | 2018-09-06 | 2019-01-11 | 北京京东尚科信息技术有限公司 | File classification method and device, computer readable storage medium |
| CN109684476A (en) * | 2018-12-07 | 2019-04-26 | 中科恒运股份有限公司 | A kind of file classification method, document sorting apparatus and terminal device |
| CN109857860A (en) * | 2019-01-04 | 2019-06-07 | 平安科技（深圳）有限公司 | File classification method, device, computer equipment and storage medium |
-
2019
- 2019-12-04 CN CN201911224204.2A patent/CN110674263B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1564129A (en) * | 2004-04-02 | 2005-01-12 | 清华大学 | Method of packing member and consistent visit |
| CN101794303A (en) * | 2010-02-11 | 2010-08-04 | 重庆邮电大学 | Method and device for classifying text and structuring text classifier by adopting characteristic expansion |
| CN104965867A (en) * | 2015-06-08 | 2015-10-07 | 南京师范大学 | Text event classification method based on CHI feature selection |
| CN106503254A (en) * | 2016-11-11 | 2017-03-15 | 上海智臻智能网络科技股份有限公司 | Language material sorting technique, device and terminal |
| CN106897428A (en) * | 2017-02-27 | 2017-06-27 | 腾讯科技（深圳）有限公司 | Text classification feature extracting method, file classification method and device |
| CN108170818A (en) * | 2017-12-29 | 2018-06-15 | 深圳市金立通信设备有限公司 | A kind of file classification method, server and computer-readable medium |
| CN108241741A (en) * | 2017-12-29 | 2018-07-03 | 深圳市金立通信设备有限公司 | A kind of file classification method, server and computer readable storage medium |
| CN108153895A (en) * | 2018-01-06 | 2018-06-12 | 国网福建省电力有限公司 | A kind of building of corpus method and system based on open data |
| CN108334501A (en) * | 2018-03-21 | 2018-07-27 | 王欣 | Electronic document analysis system based on machine learning and method |
| CN109189932A (en) * | 2018-09-06 | 2019-01-11 | 北京京东尚科信息技术有限公司 | File classification method and device, computer readable storage medium |
| CN109684476A (en) * | 2018-12-07 | 2019-04-26 | 中科恒运股份有限公司 | A kind of file classification method, document sorting apparatus and terminal device |
| CN109857860A (en) * | 2019-01-04 | 2019-06-07 | 平安科技（深圳）有限公司 | File classification method, device, computer equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819106A (en) * | 2021-04-16 | 2021-05-18 | 江西博微新技术有限公司 | IFC component type identification method, device, storage medium and equipment |
| CN113553483A (en) * | 2021-07-02 | 2021-10-26 | 广联达科技股份有限公司 | Component retrieval method, component retrieval device, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110674263B (en) | 2022-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110968695A (en) | Intelligent labeling method, device and platform based on active learning of weak supervision technology | |
| CN106777335A (en) | It is a kind of to be remembered based on shot and long term（LSTM）The multi-tag trade classification method and device of model | |
| CN111309910A (en) | Text information mining method and device | |
| CN108563703A (en) | A kind of determination method of charge, device and computer equipment, storage medium | |
| CN110674263B (en) | Method and device for automatically classifying model component files | |
| CN109800354B (en) | Resume modification intention identification method and system based on block chain storage | |
| CN110705283A (en) | Deep learning method and system based on matching of text laws and regulations and judicial interpretations | |
| CN109189894A (en) | A kind of answer extracting method and device | |
| CN109491915A (en) | Data processing method and device, medium and calculating equipment | |
| CN110990917A (en) | BIM model display method, device and system | |
| CN110968664A (en) | Document retrieval method, device, equipment and medium | |
| CN112613321A (en) | Method and system for extracting entity attribute information in text | |
| CN113742396A (en) | Mining method and device for object learning behavior pattern | |
| CN112685374B (en) | Log classification method and device and electronic equipment | |
| CN114491034B (en) | Text classification method and intelligent device | |
| CN110414124B (en) | Analysis method and device for similarity of model member files | |
| CN109359288B (en) | Method for quantitatively evaluating documents in legal field | |
| CN113033186B (en) | Error correction early warning method and system based on event analysis | |
| CN111191029B (en) | AC construction method based on supervised learning and text classification | |
| CN111666748B (en) | Construction method of automatic classifier and decision recognition method | |
| CN111523301B (en) | Contract document compliance checking method and device | |
| CN115438153A (en) | Training method and device for intention matching degree analysis model | |
| CN105373561B (en) | The method and apparatus for identifying the logging mode in non-relational database | |
| CN110442708A (en) | A kind of information classification approach based on Granular Computing | |
| Hans et al. | Work in progress—Design and development of a project management intelligence (PMInt) tool |
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 |