CN113111920B - Project data management system based on PLM and application method - Google Patents
Project data management system based on PLM and application method Download PDFInfo
- Publication number
- CN113111920B CN113111920B CN202110293782.2A CN202110293782A CN113111920B CN 113111920 B CN113111920 B CN 113111920B CN 202110293782 A CN202110293782 A CN 202110293782A CN 113111920 B CN113111920 B CN 113111920B
- Authority
- CN
- China
- Prior art keywords
- classification
- project
- module
- algorithm
- information
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a project data management system and an application method based on PLM, comprising the following steps: a server and a terminal; the PLM system is installed in the server and comprises a project module, a classification module, a pushing module and a training module; the terminal is provided with an evaluation module; a classification algorithm is arranged in the classification module and used for adding classification labels to the items; the item module is used for receiving item information containing the classification labels and storing the item information in a classification mode according to the classification labels; the pushing module is used for the first storage of the project, extracting the similar project information from the project module and sending the similar project information to the corresponding terminal; the evaluation module is used for receiving the push feedback information and sending the push feedback information to the training module; the training module corrects a classification algorithm according to the received push feedback information; the method has the advantages that by combining algorithm classification and similar project pushing, the preparation work of research and development personnel in the early stage of research and development can be reduced, and data support is provided for the next technical innovation.
Description
Technical Field
The invention relates to the technical field of product/project life cycle management, in particular to a project data management system and an application method based on PLM.
Background
At present, research and development process data of various large enterprise research and development centers mainly take personnel communication and written catalogues as main materials, and paperless and informatization management is difficult to achieve. Even if a part of large enterprises adopt full online office, information among projects and groups has certain intercommunication difficulty, and no project management tool is used for content synchronization, which particularly influences the progress of projects when large project research is involved. The system has the advantages that great manpower resources are wasted in communication, meanwhile, informatization data storage cannot be completely realized, a reasonable data catalogue is not available, and content support research and development work such as historical data records required by corresponding work cannot be autonomously provided for workers. Obviously, the original working mode can not avoid the waste of human resources, and the bottom of the research center is not well exerted. Meanwhile, as time increases, the quantity of projects also increases greatly, and sometimes, projects are found when project establishment reaches the middle stage, similar or same projects can be used for reference or comparison in the past, and similar project collection is carried out only by manpower, so that the processing efficiency is greatly reduced, and as the quantity of projects continuously increases, problems such as personnel mobility are troubled, so that the system is not suitable for technical research and development requirements any more, and the existing project management system needs to be improved.
Chinese patent CN112100749A discloses an automobile intelligent development system, which comprises an artificial intelligence system, a PLM system and a database, wherein the artificial intelligence system is provided with a CAD data input unit, a CAE data input unit, a new design CAE performance requirement input unit and a new design CAD constraint condition input unit, and the artificial intelligence system is respectively connected with the PLM system and the database; the PLM system is connected with a database. The construction and application method comprises the following steps: digitizing, parameterizing and inputting CAD data into a manual intelligent system for storage; after the CAE data are analyzed and optimized to obtain results, the results are also output to an artificial intelligent system for storage, and the CAD data and the CAE data are kept in one-to-one correspondence; the new design is firstly input according to CAE performance requirements and CAD constraint conditions, and a preliminary feasible CAD design scheme is reversely searched and output in a data model constructed by an artificial intelligence system. According to the technical scheme, a data information processing mode is provided by applying a PLM (product/project life cycle management system) in the research and development process and combining a time-lapse artificial intelligence technology, so that the valuable information supply speed and accuracy in the initial research and development stage are improved, but the application of artificial intelligence cannot cope with the complex situation, the accuracy cannot be independently improved, and further improvement is needed.
Disclosure of Invention
In view of the above, the present invention provides a project data management system and an application method based on PLM, which can solve the above problems.
For this purpose, the present invention is implemented by the following technical means.
A PLM-based project data management system, comprising: a server and a terminal; the server is connected with the terminal through the Internet or a local area network;
a PLM system is installed in the server, and comprises a project module, a classification module, a pushing module and a training module; the terminal is provided with an evaluation module;
a classification algorithm is arranged in the classification module and is used for adding classification labels to the items;
the project module is used for receiving project information containing the classification labels, recording according to the time period from project establishment to project ending, and performing classification storage according to the classification labels;
the push module is used for the first storage of the project, extracting the similar project information from the project module and sending the similar project information to the corresponding terminal;
the evaluation module is used for receiving push feedback information and sending the push feedback information to the training module;
and the training module corrects the classification algorithm according to the received push feedback information.
Further, the classification algorithm is a machine learning algorithm and comprises one or more of SVM algorithm, KNN algorithm and neural network algorithm.
Furthermore, an optical character reader is arranged in the classification module.
Further, the terminal includes a desktop computer, a portable computer, a mobile communication device, and a multimedia device having an interactive function.
On the other hand, the invention also provides an application method of the project data management system based on the PLM, which comprises the following specific steps:
s1, building a classification module;
s2, receiving and classifying the project information;
s3, pushing similar project information;
and S4, receiving the push feedback information and modifying the classification algorithm.
Further, in the S1, the classification algorithm is a machine learning algorithm; the concrete construction steps are as follows:
s11, preparing training samples manually, and establishing the corresponding relation between the existing project information and project classification;
and S12, introducing the training samples into the classification algorithm for training, and forming a classification model.
Furthermore, an optical character reader is arranged in the classification module;
in S11, the sample input parameter selection rule includes, but is not limited to:
1. item high frequency keywords and character spacing: converting the image into a text format through an optical character reader, screening all text data of the project, and obtaining keywords with the occurrence frequency higher than a preset value and character intervals among the keywords;
2. project use or effect: marked by the entry personnel of the project;
3. the names of upstream and downstream manufacturers covered in the project;
the classification labels of the items are artificially labeled and used as sample results.
Further, in S2, the data generated by the project for the first time is uploaded to the server through the terminal, and enters the classification module, and a corresponding classification label is generated through the operation of the classification model, where the classification label includes a confidence of the classification result;
then the classification module sends the project data and the classification label to the project module; the item module receives item data containing the classification labels, and stores the item data in a classification mode according to the classification labels;
after data generated subsequently by the project are uploaded to the server through the terminal, the data do not enter the classification module any more, and directly enter the project module, and are recorded and stored by the project module according to the time period from project establishment to project conclusion;
and the same group of people can access the server through the terminal and check or update the project information.
Further, in S3, the pushing module obtains the classification label, sends a request to the item module, extracts item information under the corresponding classification, and pushes the received similar item information to the terminal; the pushed project information also comprises the confidence of the first classification result of each project, and is displayed according to the high and low degrees of the confidence.
Further, in S4, the user feeds back the similar items pushed by the user in the terminal, including scoring the matching degree or marking the matching items; after receiving the feedback information, the evaluation module sends the feedback information to the training module; and the training module trains the classification model again according to the feedback information for improving the accuracy of the model.
The invention has the following advantages:
after the scale of the research and development center of a company and the increasing research and development tasks are continuously carried out, the data can be reasonably managed, synchronized and stored, and project information can be completely recorded according to a project period. By combining algorithm classification and similar project pushing, the preparation work of research and development personnel in the early stage of research and development can be reduced, and the research and development personnel can be helped to seek enough successful cases and related research and development data in a short time. Meanwhile, assets in the process of all research and development projects can be saved, technical implications of the company are formed, and data support is provided for the next technical innovation of the company.
Drawings
In order to illustrate the embodiments of the present invention more clearly, the drawings that are needed in the embodiments will be briefly described below, it is obvious that the drawings in the following description are only one or several embodiments of the present invention, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is a system diagram of an embodiment of the invention;
FIG. 2 is a flow chart of an embodiment of the present invention.
Detailed Description
The conception, the specific structure and the technical effects of the present invention will be clearly and completely described in conjunction with the embodiments and the accompanying drawings to fully understand the objects, the schemes and the effects of the present invention. It should be noted that, in the case of no conflict, the features in the embodiments of the present application may be combined with each other.
The invention will be further explained with reference to the drawings.
A PLM-based project data management system, as shown in fig. 1, comprising: a server and a terminal; the corresponding server is used as a data processing and storage center. Preferably, the terminal includes, but is not limited to, a desktop computer, a portable computer, a mobile communication device, and a multimedia device with an interactive function, wherein a client platform is installed, and a project developer can log in the platform system through an account or other authentication means, so as to create a new project or view and update information of an existing project.
The server is connected with the terminal through the internet or a local area network in an enterprise, and in order to ensure the security of information, an encryption communication mode can be adopted, and the specific encryption mode is not described in a limiting way.
The PLM system (product/project life cycle management system) is installed in the server, and the existing PLM system is characterized by comprising project information in a complete cycle, has multilayer storage capacity, is more reasonable and standard for information storage, can better feed back content, is very suitable for managers to use, but completely needs manual processing when information needs to be stored or extracted every time, and when the classification is increased or the number of projects is increased, the defects of the pure manual mode are gradually revealed. Therefore, the PLM system also comprises a project module, a classification module, a pushing module and a training module, and an evaluation module is arranged at the terminal.
The classification module is internally provided with a classification algorithm and is used for adding classification labels to the items; preferably, the classification algorithm is a machine learning algorithm, including one or more of a SVM algorithm, a KNN algorithm, and a neural network algorithm. Furthermore, an optical character reader is arranged in the classification module.
The project module is used for receiving project information containing the classification labels, recording according to the time period from project establishment to project ending, and storing in a classification mode according to the classification labels.
The pushing module is used for the first storage of the project, and extracting the similar project information from the project module and sending the similar project information to the corresponding terminal.
The evaluation module is used for receiving the push feedback information and sending the push feedback information to the training module.
And the training module corrects the classification algorithm according to the received push feedback information.
Preferably, in order to keep the project data updated automatically in real time, the office system and the office equipment may be connected to the server, such as an internal mailbox and a printer, and project information is sent through the mailbox, or a print header including a project number or a project name is uploaded to a project module of the server through the printer, and the data of the project is recorded and stored.
The invention provides an application method based on the project data management system of the PLM in the embodiment, which comprises the following specific steps in combination with the steps shown in FIG. 2:
s1, building a classification module; preferably, the classification algorithm is a machine learning algorithm; the concrete construction steps are as follows:
s11, preparing training samples manually, and establishing the corresponding relation between the existing project information and project classification; preferably, an optical character reader is arranged in the classification module; the purpose is that there are a lot of image files in the existing technical data, for example, the data in pdf format is not only limited to text, but also includes drawings partially converted into pdf format, the characters in the drawings are identified by optical character reader and converted into text format, which is convenient for computer screening.
The method is characterized in that two steps are basically needed for preparing a sample for machine learning, namely, input parameters are screened out, and results are marked out, wherein for the research and development center project text analysis, the traditional manual determination technology key words are simply adopted as input conditions, the manual classification is adopted as results, the test effect is not ideal, the accuracy is between 15% and 30%, and the actual requirements cannot be met. After analysis, the manually screened keywords are partially too high in repetition rate, and for example, for development of a vehicle body structure, names of key technical indexes and parameters in the project are basically consistent, but research and development of the vehicle body structure need to be divided into a plurality of parts, such as research and development of a cab structure, research and development of a dump box structure, research and development of a vehicle girder structure and the like. Therefore, through long-term comparison, a sample input parameter selection rule is formulated as follows:
1. item high frequency keywords and character spacing: converting the image into a text format through an optical character reader, screening all text data of the project to obtain keywords with the occurrence frequency higher than a preset value or intercepting keywords which are 10% of the occurrence frequency and character intervals among the keywords; the keyword selection automatically deletes common words according to a word bank, such as: words and phrases are commonly used in the fields of processing, devices, equipment, bending, cold welding, electric welding and the like.
2. Project use or effect: the entry personnel of the project marks and specifically presents in a form of key words, and because the long and short sentences can not become effective input quantity, the entry personnel selects the purpose and the expected effect of the project according to the preset word stock;
3. the names of upstream and downstream manufacturers covered in the project;
the item labels are manually marked except the 2 nd point, and other items are screened by a data preprocessing module arranged in front of a classification module, and the classification labels of the items are manually marked and serve as sample results.
And S12, introducing the training samples into a classification algorithm for training, and forming a classification model. The existing classification algorithms are more commonly used algorithms such as those described above, but actual modeling tests show that the effect is not ideal when one of the algorithms is independently used for classification modeling, and the actual correct classification proportion is 55% -67%, and the reason for analyzing the algorithm is known that there is an abnormal value in the input quantity, for example, in a certain project, a keyword is extracted to contain more technical feature words related to welding processing, but actually, the project theme is a new material application, and only a document is cited in the material to show that the melting point of the material is higher and the material shows the phenomenon in friction welding, so that the classification result can enter the sub-classification under welding with a high probability. The abnormal value screening function is needed to be added at the modeling stage, namely a multi-algorithm mixing mode is adopted, preferably, the KNN algorithm-SVM algorithm-artificial neural network algorithm is adopted to carry out data series connection analysis in sequence, in the model formed in the mode, the actual influence of outliers can be reduced through the KNN algorithm, the SVM algorithm of the RBF kernel function is used for building high-dimensional space for primary classification, the prediction result and the corresponding confidence coefficient are output, the prediction result and the confidence coefficient are used as the input quantity of the artificial neural network algorithm for training, and finally the model of the three algorithms is synthesized to obtain a complete classification model. The accuracy rate of the model can reach more than 91% through verification, and the requirement is well met.
S2, receiving and classifying the project information; preferably, the system is built in the current period, and subsequent projects can be normally input into the system for retention or viewing and updating; the specific project establishment process comprises the following steps:
1. firstly, selecting senior engineers in different research directions as project managers;
2. selecting a technical side according to different product research projects
3. The key project manager is favorable for accelerating the development progress of the project;
4. the existing research and development processes of a company are introduced, work plan arrangement is carried out, and project starting meetings are developed;
the main content of project initiation includes establishing project responsible persons and project group members to divide respective work duties, analyzing project background, establishing project final purpose and achievement, and simultaneously making clear the commitment of leaders to project research resources, so as to provide convenience for coordinating related parties in the future.
a. The requirement list is mainly formed by establishing main functional requirements of the research product by a project manager and team members through brain storm, thinking guide picture, user interview and other modes, and carrying out requirement treatment
b. Importance ranking, etc.
c. The work decomposition structure: the work is divided mainly according to the previous work, and the work is subdivided until the work period can be evaluated, so that the relevant contents such as daily work plans are made.
d. The work manuscript is also called a problem list and is used for recording all problems, technical difficulties and solutions in the process of the research project.
And after the project content is correspondingly finished, corresponding project data arrangement is carried out.
Data generated by each project for the first time is uploaded to a server through a terminal, the data enters a classification module firstly, input quantity is obtained in a front data preprocessing module, the input quantity and project marks input by input personnel enter a classification model for operation together, corresponding classification labels are generated, and the classification labels comprise confidence degrees of classification results.
Then the classification module sends the project data and the classification label to the project module; and the item module receives the item data containing the classification labels, classifies and stores the item data according to the classification labels, and establishes a corresponding item catalog.
After data generated subsequently by the project are uploaded to the server through the terminal, the data do not enter the classification module, the data directly enter the project module, and the data are recorded and stored by the project module according to the time period from project establishment to project conclusion; the cycle setting may refer to common logical relationships: standing-mid-check-heading, or simply in chronological order, is shown in the item catalog.
The same group of people can access the server through the terminal and view or update the project information.
S3, pushing similar project information; preferably, the pushing module obtains the classification label of the new item in S2, and sends a request to the item module to extract the item information under the corresponding classification, i.e. the same kind of items (the same, similar or technically related items). Pushing the received similar project information to a terminal in an abstract form; the pushed project information also comprises the confidence of the first classification result of each project, and is displayed according to the high and low degrees of the confidence, so that project entry personnel (such as project managers in the foregoing) can quickly see the information of the similar projects, and preferentially display the most relevant projects according to the confidence.
The process only needs to simply arrange project establishment information, and a plurality of groups of keywords are labeled according to the word stock to upload, establish project files, and simultaneously can obtain the technical accumulation support in the early stage and obtain the technical inspiration, thereby greatly reducing the time for self-searching, improving the accuracy of data acquisition and providing data help for the subsequent technical innovation.
S4, receiving the push feedback information and correcting the classification algorithm; preferably, the user feeds back the pushed similar items in the terminal, including scoring the matching degree or marking the matching items; specifically, push items with poor relevance are labeled in a targeted mode, and a correct classification label is given, so that the item is not correct in the first classification. After receiving the feedback information, the evaluation module sends the feedback information to the training module; and the training module trains the classification model again according to the feedback information for improving the accuracy of the model. And meanwhile, the pushed item information is stored again according to the modified classification label. On the one hand, a supervised machine learning structure is formed through feedback-retraining step by step without obviously increasing the workload of project personnel, and the accuracy of the classification module is continuously improved; on the other hand, the case of early classification errors is gradually modified.
The automation degree of the whole system is high, the waste of manpower is avoided, the accuracy is continuously improved by utilizing simple feedback, correct technical support can be obtained initially for a project, and meanwhile, the error classification possibly existing in the early stage is corrected due to the fact that more data are required to be expanded continuously. Furthermore, when new classification occurs, the items with low matching degree with the classification can be transferred to the new classification through continuous feedback correction in daily input, so that the new classification is perfected without deliberate adjustment. For example, the following steps are carried out: because there is not radiator structural design in the present classification and classify, the radiator design belongs to under the engine design is categorised, when newly offering radiator classification, need not to adjust by accident, because its classification confidence is lower, it looks over this content both to take notes when feedback catalogue to type personnel, simple inquiry can discover to have radiator classification, feedback after marking can, at this moment, the propelling movement module receives feedback information, inform the training module and retrain again, through a period of time iterative training, the model can correctly discern and the relevant project of radiator, and is categorised, radiator project also progressively saves under new radiator classification simultaneously, realize the efficiency of killing two birds with one stone, need not to add a new classification and just adjust one by one, unified training.
Although the present invention has been described in detail with reference to examples, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (6)
1. A PLM-based project data management system, comprising: a server and a terminal; the server is connected with the terminal through the Internet or a local area network;
the system is characterized in that a PLM system is installed in the server, and the PLM system comprises a project module, a classification module, a pushing module and a training module; the terminal is provided with an evaluation module;
a classification algorithm is arranged in the classification module and is used for adding classification labels to the items; the classification algorithm is a machine learning algorithm, the machine learning algorithm sequentially adopts a KNN algorithm-SVM algorithm-artificial neural network algorithm to carry out data series connection analysis, the actual influence of outliers is reduced through the KNN algorithm, then a high-dimensional space is constructed through the SVM algorithm of the RBF kernel function to carry out primary classification, a prediction result and corresponding confidence coefficient are output, the prediction result and the confidence coefficient are used as input quantity of the artificial neural network algorithm to carry out training, and finally models of the three algorithms are synthesized to obtain a complete classification model; an optical character reader is arranged in the classification module;
the project module is used for receiving project information containing the classification labels, recording according to the time period from project establishment to project ending, and performing classification storage according to the classification labels;
the push module is used for the first storage of the project, extracting the similar project information from the project module and sending the similar project information to the corresponding terminal;
the evaluation module is used for receiving push feedback information and sending the push feedback information to the training module;
and the training module corrects the classification algorithm according to the received push feedback information.
2. The project data management system of claim 1, wherein the terminal comprises a desktop computer, a portable computer, a mobile communication device and a multimedia device with an interactive function.
3. The method for applying a PLM-based project data management system according to any of claims 1-2, characterized by the specific steps of:
s1, building a classification module;
s2, receiving and classifying the project information;
s3, pushing similar project information;
s4, receiving the push feedback information and correcting the classification algorithm;
in S1, a classification algorithm is provided in the classification module, and is used to add a classification label to the item; the classification algorithm is a machine learning algorithm, the machine learning algorithm sequentially adopts a KNN algorithm-SVM algorithm-artificial neural network algorithm to carry out data series connection analysis, the actual influence of outliers is reduced through the KNN algorithm, then a high-dimensional space is constructed through the SVM algorithm of the RBF kernel function to carry out primary classification, a prediction result and corresponding confidence coefficient are output, the prediction result and the confidence coefficient are used as input quantity of the artificial neural network algorithm to carry out training, and finally models of the three algorithms are synthesized to obtain a complete classification model; the specific construction steps of the classification module are as follows:
s11, preparing training samples manually, and establishing the corresponding relation between the existing project information and project classification;
s12, introducing the training samples into the classification algorithm for training, and forming a classification model;
an optical character reader is arranged in the classification module;
in S11, the sample input parameter selection rule includes, but is not limited to:
1. item high frequency keywords and character spacing: converting the image into a text format through an optical character reader, screening all text data of the project, and obtaining keywords with the occurrence frequency higher than a preset value and character intervals among the keywords;
2. project use or effect: marked by the entry personnel of the project;
3. the names of upstream and downstream manufacturers covered in the project;
the classification labels of the items are artificially labeled and used as sample results.
4. The application method of the project data management system according to claim 3, wherein in the S2, the data generated by the project for the first time is uploaded to the server through the terminal, and enters the classification module, and through the operation of the classification model, a corresponding classification label is generated, and the classification label includes the confidence of the classification result;
then the classification module sends the project data and the classification label to the project module; the item module receives item data containing the classification labels, and stores the item data in a classification mode according to the classification labels;
after data generated subsequently by the project are uploaded to the server through the terminal, the data do not enter the classification module any more, and directly enter the project module, and are recorded and stored by the project module according to the time period from project establishment to project conclusion;
and the same group of people can access the server through the terminal and check or update the project information.
5. The application method of the project data management system of claim 4, wherein in the S3, the pushing module obtains the classification label and sends a request to the project module, extracts project information under corresponding classification, and pushes the received similar project information to the terminal; the pushed project information also comprises the confidence of the first classification result of each project, and is displayed according to the high and low degrees of the confidence.
6. The method for applying the project data management system of claim 3, wherein in the S4, the user feeds back the similar projects pushed in the terminal, including scoring the matching degree or marking the matching projects; after receiving the feedback information, the evaluation module sends the feedback information to the training module; and the training module trains the classification model again according to the feedback information for improving the accuracy of the model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110293782.2A CN113111920B (en) | 2021-03-19 | 2021-03-19 | Project data management system based on PLM and application method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110293782.2A CN113111920B (en) | 2021-03-19 | 2021-03-19 | Project data management system based on PLM and application method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113111920A CN113111920A (en) | 2021-07-13 |
| CN113111920B true CN113111920B (en) | 2021-12-28 |
Family
ID=76711764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110293782.2A Active CN113111920B (en) | 2021-03-19 | 2021-03-19 | Project data management system based on PLM and application method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113111920B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014144869A1 (en) * | 2013-03-15 | 2014-09-18 | Lehrer David | System and method for providing a semi-automated research tool |
| CN106600232A (en) * | 2016-12-19 | 2017-04-26 | 广东技术师范学院 | Personalized project application information pushing system and personalized project application information pushing method |
| CN108197910A (en) * | 2018-03-27 | 2018-06-22 | 四川国际招标有限责任公司 | A kind of project for bidding project verification management system |
| CN109918626A (en) * | 2017-12-13 | 2019-06-21 | 厦门头家信息科技有限公司 | A kind of foundation investment and financing service system |
| CN110019672A (en) * | 2017-11-09 | 2019-07-16 | 北京国双科技有限公司 | A kind of method for pushing of similar case, system, storage medium and processor |
| CN110264106A (en) * | 2019-06-28 | 2019-09-20 | 浪潮卓数大数据产业发展有限公司 | A kind of project work amount assessment system and method based on agile management exploitation |
| CN111026858A (en) * | 2019-11-29 | 2020-04-17 | 腾讯科技（深圳）有限公司 | Project information processing method and device based on project recommendation model |
| CN112100749A (en) * | 2020-09-29 | 2020-12-18 | 上海卓位信息技术有限公司 | Automobile intelligent development system and construction and application method thereof |
| CN112148866A (en) * | 2020-09-10 | 2020-12-29 | 江门市邑科通科技有限公司 | Online intelligent project declaration resource matching pushing system and method thereof |
| CN112330303A (en) * | 2020-11-27 | 2021-02-05 | 同济大学建筑设计研究院(集团)有限公司 | Intelligent project evaluation cooperative management system |
-
2021
- 2021-03-19 CN CN202110293782.2A patent/CN113111920B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014144869A1 (en) * | 2013-03-15 | 2014-09-18 | Lehrer David | System and method for providing a semi-automated research tool |
| CN106600232A (en) * | 2016-12-19 | 2017-04-26 | 广东技术师范学院 | Personalized project application information pushing system and personalized project application information pushing method |
| CN110019672A (en) * | 2017-11-09 | 2019-07-16 | 北京国双科技有限公司 | A kind of method for pushing of similar case, system, storage medium and processor |
| CN109918626A (en) * | 2017-12-13 | 2019-06-21 | 厦门头家信息科技有限公司 | A kind of foundation investment and financing service system |
| CN108197910A (en) * | 2018-03-27 | 2018-06-22 | 四川国际招标有限责任公司 | A kind of project for bidding project verification management system |
| CN110264106A (en) * | 2019-06-28 | 2019-09-20 | 浪潮卓数大数据产业发展有限公司 | A kind of project work amount assessment system and method based on agile management exploitation |
| CN111026858A (en) * | 2019-11-29 | 2020-04-17 | 腾讯科技（深圳）有限公司 | Project information processing method and device based on project recommendation model |
| CN112148866A (en) * | 2020-09-10 | 2020-12-29 | 江门市邑科通科技有限公司 | Online intelligent project declaration resource matching pushing system and method thereof |
| CN112100749A (en) * | 2020-09-29 | 2020-12-18 | 上海卓位信息技术有限公司 | Automobile intelligent development system and construction and application method thereof |
| CN112330303A (en) * | 2020-11-27 | 2021-02-05 | 同济大学建筑设计研究院(集团)有限公司 | Intelligent project evaluation cooperative management system |
Non-Patent Citations (7)
| Title |
|---|
| M集团产品全生命周期管理系统（PLM）的构建规划研究;张浩;《中国优秀硕士学位论文全文数据库 经济与管理科学辑》;20100815(第（2010）08期);J152-194 * |
| PLM 中的项目管理应用研究与实践;丁刚强;《装备制造技术》;20191231(第3期);第216-221页 * |
| Project Management implementation for healthcare activities organization;GIUSEPPE CONVERSO等;《Advances in Computer Science》;20121231;第436-443页 * |
| 个性化信息推送服务的用户模型研究;陈诚等;《情报科学》;20141130;第32卷(第11期);第71-76、87页 * |
| 基于PLM系统的研发项目管理平台构建研究;李大鹏等;《中国管理信息化》;20160501;第19卷(第09期);第67-71页 * |
| 基于反馈机制的三维模型分类检索系统;王勇睿等;《计算机工程与应用》;20050921;第27卷;第164-167、177页 * |
| 面向PLM的数据挖掘技术和应用研究;徐河杭;《中国博士学位论文全文数据库 信息科技辑》;20110815(第（2011）08期);I138-20 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113111920A (en) | 2021-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110825882B (en) | Knowledge graph-based information system management method | |
| CN107967575B (en) | Artificial intelligence platform system for artificial intelligence insurance consultation service | |
| CN111489800A (en) | Analysis method and system for identifying and storing medical record and report list images | |
| US11675750B2 (en) | User generated tag collection system and method | |
| CN110489749B (en) | Business process optimization method of intelligent office automation system | |
| CN102880683A (en) | Automatic network generation system for feasibility study report and generation method thereof | |
| CN114119058A (en) | User portrait model construction method and device and storage medium | |
| CN112836018A (en) | Method and device for processing emergency plan | |
| CN115481827A (en) | Method for intelligently matching supply and demand of innovative entrepreneurship service | |
| CN110310012B (en) | Data analysis method, device, equipment and computer readable storage medium | |
| CN114911893A (en) | Method and system for automatically constructing knowledge base based on knowledge graph | |
| CN103377403A (en) | Enterprise business module modeling method and enterprise business module modeling system | |
| US11055666B2 (en) | Systems and methods for automation of corporate workflow processes via machine learning techniques | |
| CN110490547A (en) | Office system intellectualized technology | |
| Bhupathi et al. | Artificial Intelligence-Enabled Knowledge Management Using a Multidimensional Analytical Framework of Visualizations | |
| CN113111920B (en) | Project data management system based on PLM and application method | |
| CN116595191A (en) | Construction method and device of interactive low-code knowledge graph | |
| Shi et al. | Knowledge management platforms and intelligent knowledge beyond data mining | |
| Hansen | Cutting edge and cutting corners: Evolving technology, expanding usership, and responsive solutions in a museum database | |
| CN114969544A (en) | Hot data-based recommended content generation method, device, equipment and medium | |
| CN112906683A (en) | Text labeling method, device and equipment | |
| CN113254612A (en) | Knowledge question-answering processing method, device, equipment and storage medium | |
| Nabais et al. | SSD2 and FoodEx2 compliant real‐time registration and classification of food sampling data‐Improving Data Quality for Risk Assessment (IDRisk) | |
| US20230050571A1 (en) | Docketing translation tool | |
| CN111858978B (en) | Method and system for automatically making network courseware icons |
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 |