CN118096091A - Mechanical engineering project demand analysis method, system, equipment and medium - Google Patents
Mechanical engineering project demand analysis method, system, equipment and medium Download PDFInfo
- Publication number
- CN118096091A CN118096091A CN202410524058.XA CN202410524058A CN118096091A CN 118096091 A CN118096091 A CN 118096091A CN 202410524058 A CN202410524058 A CN 202410524058A CN 118096091 A CN118096091 A CN 118096091A
- Authority
- CN
- China
- Prior art keywords
- demand
- mechanical engineering
- engineering project
- data
- labels
- 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.)
- Pending
Links
- 238000011089 mechanical engineering Methods 0.000 title claims abstract description 174
- 238000004458 analytical method Methods 0.000 title claims abstract description 99
- 238000013461 design Methods 0.000 claims abstract description 119
- 238000000034 method Methods 0.000 claims abstract description 47
- 238000011282 treatment Methods 0.000 claims abstract description 5
- 238000005457 optimization Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 21
- 238000003058 natural language processing Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 15
- 238000013145 classification model Methods 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 description 18
- 238000010586 diagram Methods 0.000 description 11
- 239000000463 material Substances 0.000 description 10
- 238000012549 training Methods 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000012360 testing method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 239000000956 alloy Substances 0.000 description 2
- 229910045601 alloy Inorganic materials 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000004381 surface treatment Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a method, a system, equipment and a medium for analyzing requirements of mechanical engineering projects, and relates to the technical field of computers. The mechanical engineering project demand analysis method comprises the following steps: acquiring original demand data input by a user aiming at a mechanical engineering project; carrying out structuring treatment on the original demand data to obtain demand data, and identifying a theme label of the demand data; based on a pre-constructed mechanical engineering project demand library, disassembling the demand data into a plurality of demand tasks according to the topic labels of the demand data; based on a pre-constructed mechanical engineering project knowledge base, acquiring design parameters and physical formulas of each demand task; and combining design parameters and physical formulas of all the demand tasks to generate a demand analysis result of the mechanical engineering project. The embodiment of the invention can automatically analyze the requirements of the mechanical engineering project and improve the efficiency of analyzing the requirements of the mechanical engineering project.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method, a system, equipment and a medium for analyzing requirements of mechanical engineering projects.
Background
Analysis of the needs of a machine engineering project is one of the key steps in the successful implementation of the machine engineering project. In the process of the project establishment of mechanical engineering, most mechanical manufacturing enterprises generally need a great deal of manual participation in demand analysis, project managers and engineers firstly extract and disassemble project demands according to the product demands of users and strategic opinions of an enterprise management layer, and then the disassembled project sub-demands are delivered to research and development design teams of all responsible departments in the enterprise to formulate design targets and design parameters, and research, development, design, manufacture and test are carried out according to the design parameters and related physical formulas. For example, before a new car is on line, an automobile manufacturing enterprise disassembles the requirements of the new car by project managers and engineers to obtain detailed requirements of subsystems such as an engine, a chassis, a car body, an electronic system and the like, and then searches design parameters and physical formulas corresponding to the subsystems such as the engine, the chassis, the car body, the electronic system and the like by research and development design teams of each responsible department in the enterprise to carry out research, development, design, manufacture and test, so as to ensure that the new car put into production meets the project requirements.
Therefore, the existing mechanical engineering project demand analysis method relies on manual analysis, is complex in operation and low in efficiency.
Disclosure of Invention
The embodiment of the invention aims to provide a method, a system, equipment and a medium for analyzing the demand of a mechanical engineering project, which are used for realizing automatic demand analysis on the mechanical engineering project and improving the technical effect of the demand analysis efficiency of the mechanical engineering project.
In a first aspect, an embodiment of the present invention provides a method for analyzing a requirement of a mechanical engineering project, including:
Acquiring original demand data input by a user aiming at a mechanical engineering project;
carrying out structuring treatment on the original demand data to obtain demand data, and identifying a theme label of the demand data;
based on a pre-constructed mechanical engineering project demand library, disassembling the demand data into a plurality of demand tasks according to the topic labels of the demand data;
based on a pre-constructed mechanical engineering project knowledge base, acquiring design parameters and physical formulas of each demand task;
And combining design parameters and physical formulas of all the demand tasks to generate a demand analysis result of the mechanical engineering project.
In the implementation process, when the original demand data input by a user aiming at the mechanical engineering project is obtained, the demand recognition, the demand disassembly, the demand design and other treatments are sequentially carried out on the original demand data, so that the demand analysis result of the mechanical engineering project is obtained, the automatic demand analysis can be carried out on the mechanical engineering project, and the demand analysis efficiency of the mechanical engineering project is improved.
Further, the mechanical engineering project demand analysis method further includes:
and responding to a result optimization request initiated by the user aiming at the requirement analysis result of the mechanical engineering project, and adjusting the requirement analysis result of the mechanical engineering project.
In the implementation process, the requirement analysis result of the mechanical engineering project is adjusted by responding to the result optimization request initiated by the user aiming at the requirement analysis result of the mechanical engineering project, so that the user can conveniently feed back and optimize the requirement analysis result of the mechanical engineering project in real time, and the requirement analysis efficiency of the mechanical engineering project is further improved.
Further, the structuring processing is performed on the original demand data to obtain demand data, which specifically includes:
performing natural language processing on the text data by adopting a pre-established natural language processing model, and extracting text information in the text data;
performing image processing on the image data, and extracting image information in the image data;
integrating the text information and the image information according to a preset data structure to obtain the requirement data;
wherein the raw demand data includes the text data and the image data.
In the implementation process, natural language processing and image processing are introduced to text data and image data in the original demand data, so that the original demand data can be comprehensively and accurately converted into structural data, the demand data is obtained, and further improvement of the demand analysis efficiency of mechanical engineering projects is facilitated.
Further, the theme tag for identifying the requirement data specifically includes:
And classifying the demand data by adopting a pre-established label classification model to obtain the theme label of the demand data.
In the implementation process, the demand data is classified by adopting the pre-established label classification model, so that the topic labels of the demand data can be rapidly and accurately identified, and the demand analysis efficiency of mechanical engineering projects can be further improved.
Further, the disassembling the demand data into a plurality of demand tasks according to the theme label of the demand data based on the pre-constructed mechanical engineering project demand library specifically includes:
screening all demand labels corresponding to the subject labels of the demand data from the mechanical engineering project demand library, and determining all design elements corresponding to the demand labels;
Taking all the demand labels as graph nodes, adding connecting edges between the graph nodes where the two associated demand labels are positioned, generating a demand graph, and constructing a demand tree according to the demand graph;
For each demand label, adding design nodes under the tree nodes where the demand labels are positioned according to all design elements corresponding to the demand labels, and constructing a multi-level demand tree;
and integrating all design nodes of each level in the multi-level demand tree into a demand task respectively to obtain a plurality of demand tasks.
In the implementation process, the multi-level demand tree is constructed by acquiring all demand labels corresponding to the subject labels of the demand data and all design elements corresponding to the demand labels from the mechanical engineering project demand library, and the demand data is disassembled into a plurality of demand tasks based on the multi-level demand tree, so that the demand data can be reasonably disassembled into a plurality of demand tasks, and further improvement of the mechanical engineering project demand analysis efficiency is facilitated.
Further, the obtaining design parameters and physical formulas of each required task based on the pre-constructed mechanical engineering project knowledge base specifically includes:
And searching the design parameters and the physical formulas matched with each required task from the mechanical engineering project knowledge base by adopting a rule engine to obtain the design parameters and the physical formulas of each required task.
In the implementation process, the design parameters and the physical formulas matched with each demand task are searched from the mechanical engineering project knowledge base by adopting the rule engine, so that the design parameters and the physical formulas of each demand task can be rapidly and accurately obtained, and the demand analysis efficiency of the mechanical engineering project is further improved.
In a second aspect, an embodiment of the present invention provides a system for analyzing a demand of a mechanical engineering project, including:
the demand input module is used for acquiring original demand data input by a user aiming at a mechanical engineering project;
The demand identification module is used for carrying out structural processing on the original demand data to obtain demand data and identifying a theme label of the demand data;
The demand dismantling module is used for dismantling the demand data into a plurality of demand tasks according to the theme labels of the demand data based on a pre-constructed mechanical engineering project demand library;
the demand design module is used for acquiring design parameters and physical formulas of each demand task based on a pre-constructed mechanical engineering project knowledge base;
And the result generation module is used for combining the design parameters and the physical formulas of all the demand tasks to generate the demand analysis result of the mechanical engineering project.
Further, the mechanical engineering project demand analysis system further includes:
And the result optimization module is used for responding to a result optimization request initiated by the user aiming at the requirement analysis result of the mechanical engineering project and adjusting the requirement analysis result of the mechanical engineering project.
In a third aspect, embodiments of the present invention provide an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor; the memory is coupled to the processor and the processor when executing the computer program implements the machine engineering project demand analysis method as described above.
In a fourth aspect, embodiments of the present invention provide a computer-readable storage medium including a stored computer program; and controlling equipment where the computer readable storage medium is located to execute the mechanical engineering project demand analysis method when the computer program runs.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments of the present invention will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and should not be considered as limiting the scope, and other related drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for analyzing requirements of a mechanical engineering project according to a first embodiment of the present invention;
FIG. 2 is a flow chart of a method for analyzing a demand of a mechanical engineering project according to an alternative embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a system for analyzing requirements of a mechanical engineering project according to a second embodiment of the present invention;
FIG. 4 is a schematic diagram of a system for analyzing a demand of a mechanical engineering project according to an alternative embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention.
It should be noted that: in the description of the present invention, the terms "first," "second," and the like are used merely to distinguish between descriptions and are not to be construed as indicating or implying relative importance. Meanwhile, step numbers herein are only for convenience of explanation of the embodiments of the present invention, and are not used as limiting the order of execution of the steps. The method provided by the embodiment of the invention can be executed by related terminal equipment, such as the terminal equipment provided with the mechanical engineering project demand analysis system, the SaaS platform provided with the mechanical engineering project demand analysis service, and the like, and the SaaS platform provided with the mechanical engineering project demand analysis service is taken as an execution subject for illustration hereinafter.
The SaaS platform (platform for operating SaaS software) generally refers to a software operation service. The Software operating service (Software AS A SERVICE, abbreviated as SaaS) is a new form of enabling a user to use a cloud-based application program through an internet connection, and is a new form of obtaining a Software service, which does not require the user to install a Software product on his own computer or server, but obtains a service with a corresponding Software function, which is required by the user, directly to a specific provider through a network according to a certain Service Level Agreement (SLA).
Referring to fig. 1, fig. 1 is a flow chart illustrating a method for analyzing a demand of a mechanical engineering project according to a first embodiment of the present invention. The first embodiment of the invention provides a mechanical engineering project demand analysis method, which comprises the following steps of S101-S105:
s101, acquiring original demand data input by a user aiming at a mechanical engineering project;
s102, carrying out structuring processing on the original demand data to obtain demand data, and identifying a theme label of the demand data;
S103, based on a pre-constructed mechanical engineering project demand library, disassembling the demand data into a plurality of demand tasks according to the topic labels of the demand data;
s104, acquiring design parameters and physical formulas of each demand task based on a pre-constructed mechanical engineering project knowledge base;
s105, combining design parameters and physical formulas of all the demand tasks to generate a demand analysis result of the mechanical engineering project.
As an example, according to actual application requirements, the SaaS platform provided with the machine engineering project requirement analysis service is run, waiting to acquire raw requirement data input by a user for the machine engineering project. Wherein the raw demand data includes all data describing the user's demand for the mechanical engineering project, such as text data, image data, etc.
When the original demand data input by a user aiming at the mechanical engineering project is obtained, the original demand data is subjected to structuring processing, so that the original demand data is converted into structured data which can be processed by a SaaS platform provided with mechanical engineering project demand analysis service, the demand data is obtained, and a theme label of the demand data is identified.
The method comprises the steps of collecting various engineering design requirements, such as structural design requirements, material selection requirements, kinematic design requirements, dynamic design requirements, thermodynamic design requirements, hydrodynamic design requirements and the like, marking a requirement label for each engineering design requirement, and combining all engineering design requirements and requirement labels thereof to construct a mechanical engineering project requirement library. Screening all demand labels corresponding to the topic labels of the demand data from a pre-constructed mechanical engineering project demand library, and disassembling the demand data into a plurality of demand tasks according to all demand labels corresponding to the topic labels of the demand data.
The method comprises the steps of collecting engineering design knowledge of a plurality of mechanical design fields, such as design parameters and physical formulas under an ISO mechanical design standard, design parameters and physical formulas under an ASME mechanical design standard and the like, aiming at the characteristics of mechanical engineering projects in advance, determining key information of the engineering design knowledge of each mechanical design field, such as operation relations between each design parameter and each physical formula, each design parameter and application range of each physical formula, wherein the application range comprises applicable engineering design requirements, applicable scene conditions, applicable value intervals and the like, and combining all engineering design knowledge and key information thereof to construct a mechanical engineering project knowledge base. And searching design parameters and physical formulas matched with each demand task from a pre-constructed mechanical engineering project knowledge base to obtain the design parameters and the physical formulas of each demand task.
And combining design parameters and physical formulas of all the demand tasks to generate a demand analysis result of the mechanical engineering project, so that the demand analysis result of the mechanical engineering project is fed back to a user in real time, and the user can conveniently and quickly conduct research, development, design, manufacture and test according to the demand analysis result of the mechanical engineering project.
It can be understood that in the process of demand analysis of a mechanical engineering project, a user only needs to input original demand data for the mechanical engineering project to the SaaS platform provided with the demand analysis service of the mechanical engineering project, and the SaaS platform provided with the demand analysis service of the mechanical engineering project can be triggered to perform the processes of demand identification, demand disassembly, demand design and the like on the original demand data, so that the demand analysis of the mechanical engineering project can be replaced by manual participation, the processing time and the processing manpower of the demand analysis of the mechanical engineering project are greatly reduced, and the comprehensive and accurate demand analysis on the mechanical engineering project is effectively ensured.
According to the embodiment of the invention, when the original demand data input by a user aiming at the mechanical engineering project is obtained, the demand recognition, the demand disassembly, the demand design and the like are sequentially carried out on the original demand data, so that the demand analysis result of the mechanical engineering project is obtained, the mechanical engineering project can be automatically subjected to the demand analysis, and the demand analysis efficiency of the mechanical engineering project is improved.
Referring to fig. 2, fig. 2 is a flow chart illustrating a method for analyzing a demand of a mechanical engineering project according to an alternative embodiment of the invention. In an alternative embodiment, the method for analyzing requirements of a mechanical engineering project further includes step S106:
S106, responding to a result optimization request initiated by a user aiming at the requirement analysis result of the mechanical engineering project, and adjusting the requirement analysis result of the mechanical engineering project.
As an example, when the demand analysis result of the mechanical engineering project is obtained, the demand analysis result of the mechanical engineering project can be fed back to the user in real time, so that the user can conveniently and quickly develop, design, manufacture and test according to the demand analysis result of the mechanical engineering project, and then according to the actual operation situation, whether to optimize the demand analysis result of the mechanical engineering project is selected, if so, a result optimization request for the demand analysis result of the mechanical engineering project is initiated to the SaaS platform provided with the demand analysis service of the mechanical engineering project.
And waiting for receiving a result optimization request initiated by a user aiming at a demand analysis result of the mechanical engineering project in real time. When a result optimization request initiated by a user aiming at a demand analysis result of the mechanical engineering project is received, responding to the result optimization request, and determining the adjustment content of the demand analysis result of the mechanical engineering project by the user according to the result optimization request, wherein the adjustment content corresponds to the demand analysis result of the mechanical engineering project.
In practical application, when the demand data is disassembled into a plurality of demand tasks, all the demand tasks can be fed back to the user in real time, so that the user can conveniently and quickly check all the demand tasks, further, whether all the demand tasks are optimized is selected according to own expertise and project experience, and if so, a demand optimization request aiming at all the demand tasks is initiated to a SaaS platform provided with the mechanical engineering project demand analysis service.
And waiting for receiving a demand optimization request initiated by a user aiming at all demand tasks in real time. When a demand optimization request initiated by a user aiming at all demand tasks is received, responding to the demand optimization request, determining the adjustment content of the user on all demand tasks according to the demand optimization request, correspondingly adjusting all demand tasks, for example, splitting any demand task into two new demand tasks, and combining the two demand tasks into one new demand task.
According to the embodiment of the invention, the demand analysis result of the mechanical engineering project is adjusted by responding to the result optimization request initiated by the user aiming at the demand analysis result of the mechanical engineering project, so that the demand analysis result of the mechanical engineering project can be conveniently fed back and optimized in real time by the user, and the demand analysis efficiency of the mechanical engineering project is further improved.
In an alternative embodiment, the structuring the original demand data to obtain the demand data specifically includes: performing natural language processing on the text data by adopting a pre-established natural language processing model, and extracting text information in the text data; performing image processing on the image data, and extracting image information in the image data; integrating text information and image information according to a preset data structure to obtain demand data; wherein the raw demand data includes text data and image data.
As an example, raw demand data entered by a user for a machine engineering project is obtained, wherein the raw demand data includes text data and image data describing a demand of the user for the machine engineering project.
When the original demand data input by the user for the mechanical engineering project is acquired, text data and image data are extracted from the original demand data.
Considering that a great deal of technical terms exist in the field of mechanical design, a great deal of corpus in the field of mechanical design needs to be collected in advance, such as diversified text data of user demand description text, mechanical design product description text, mechanical design technical specification text and the like, and a corpus is constructed to help to build a natural language processing model. The specific process of establishing the natural language processing model by adopting the corpus is as follows:
1. Mapping all text words in the corpus to a high-dimensional vector space by applying a word embedding (Word Embedding) technology, which is helpful for a subsequent model to mine semantic relations among the text words and accurately understand user requirements;
2. Selecting a Sequence-to-Sequence model (Sequence-to-Sequence), training sequences to the Sequence model by adopting all high-dimensional vectorized text words, and establishing a natural language processing model;
3. attention mechanisms are introduced in the model training process, so that the model focuses on important information when understanding the demands of users, and the sensitivity to the context is improved.
And carrying out natural language processing on the text data by adopting a pre-established natural language processing model, and extracting text information in the text data. The specific process of performing natural language processing on text data is as follows:
1. word segmentation: dividing the text data into basic language units, such as single words or phrases;
2. Part of speech tagging: labeling each word with its part of speech in the sentence, such as nouns, verbs, adjectives, etc., respectively, which is helpful for understanding the grammar structure of the sentence;
3. Entity identification: identifying entities in text data, such as battery packs, sheet metal, tires, etc., facilitates extraction of important information, particularly during demand analysis involving entities in named mechanical engineering projects;
4. Syntax analysis: analyzing the grammar structure of the sentence, determining the relation among various vocabularies, and establishing a grammar tree, which is helpful for understanding the grammar structure and grammar rules of the sentence;
5. Semantic analysis: determining the meaning of text data and identifying semantic relations among key words, which is helpful for the model to understand the user requirements more deeply;
6. Fuzzy demand processing: processing sentences with ambiguous or ambiguous meaning in text data by using an fuzzy matching algorithm, which is helpful for improving the processing capacity of the model for fuzzy requirements;
7. Conversion to structured data: setting a text data structure, and representing the extracted text information according to the text data structure, such as storing the text information as data represented by key value pairs, JSON format or other text data structures;
8. Generating a structured query command: the text data is converted into the structural query command which can be executed by the SaaS platform and provided with the mechanical engineering project demand analysis service, so that the mechanical engineering project demand analysis system can conveniently conduct subsequent processing, analysis and response.
It is appreciated that natural language processing (Natural Language Processing, NLP) is an important direction in the computer science and artificial intelligence fields, aimed at enabling efficient communication between humans and computers in natural language. By introducing natural language processing to text data in the original demand data, the user demand can be comprehensively and accurately understood, and the text data in the original demand data is converted into structured data.
And performing image processing on the image data to extract image information in the image data. The specific process of image processing of the image data is as follows:
1. And (3) image identification: identifying the image data by using a computer vision technology, identifying each object, acquiring the position, shape, size and other information of each object in the image, and providing basic parameters for subsequent engineering design;
2. Feature extraction: extracting key features in the image data, such as edges, colors, textures and the like, so as to acquire more information about the image content;
3. Conversion to structured data: an image data structure is provided, according to which the extracted image information is represented.
It can be appreciated that by introducing image processing for image data in the original demand data, the user demand can be fully and accurately understood, and the image data in the original demand data can be converted into structured data. And the method can adapt to diversified original demand data input by a user to carry out structural processing, and simplify the demand input operation of the user.
Considering the processable structured data of the SaaS platform provided with the mechanical engineering project demand analysis service, presetting a preset data structure, integrating text information and image information according to the preset data structure, and converting the original demand data into the processable structured data of the SaaS platform provided with the mechanical engineering project demand analysis service to obtain the demand data.
According to the embodiment of the invention, the natural language processing and the image processing are introduced for the text data and the image data in the original demand data, so that the original demand data can be comprehensively and accurately converted into the structured data, the demand data is obtained, and the demand analysis efficiency of mechanical engineering projects is further improved.
In an alternative embodiment, the theme tag for identifying the requirement data specifically includes: and classifying the demand data by adopting a pre-established label classification model to obtain the subject label of the demand data.
As an example, a label classification model is built in advance, and the demand data is classified by adopting the pre-built label classification model, so as to obtain the subject label of the demand data. The specific process for establishing the label classification model is as follows:
1. Randomly acquiring a preset number of training data from a corpus, including word vectors, image features, entity information and the like, and combining all the training data to construct a training data set;
2. providing a training data set and corresponding classification labels for the model by using supervised learning, and ensuring that the classification labels are interpretable so as to facilitate the subsequent interpretation and adjustment of the model;
3. Training a deep learning model by using a training data set and corresponding classification labels, and establishing a label classification model; the deep learning model may be a Recurrent Neural Network (RNN) or a long short time memory network (LSTM) to capture timing relationships in the sequence data.
For example, assuming that the demand data relates to the design of a new type of machine, it may involve various requirements of materials, dimensions, kinematics, etc., these requirements may be classified by using a pre-established label classification model, such as: for material requirements, the classification labels are materials, and specific requirements are high-temperature resistant materials, light-weight high-strength materials and the like; for the size requirement, the classification label is the size, and the specific requirements are small-sized design, large-sized design, accurate size and the like; for durability requirements, the classification labels are durability, and specific requirements are long-life design, high-frequency use, wear-resistant design and the like; for the safety requirement, the classification label is safety, the specific requirement is protection design, an emergency shutdown system and the like, and the subject label of the required data is determined to be a multi-category label of materials, sizes, durability and safety according to all the classification labels and the specific requirement.
According to the embodiment of the invention, the demand data is classified by adopting the pre-established label classification model, so that the subject labels of the demand data can be rapidly and accurately identified, and the demand analysis efficiency of mechanical engineering projects can be further improved.
In an optional embodiment, the disassembling the demand data into a plurality of demand tasks according to the topic labels of the demand data based on the pre-constructed demand library of the mechanical engineering project specifically includes: screening all demand labels corresponding to the subject labels of the demand data from a mechanical engineering project demand library, and determining all design elements corresponding to all the demand labels; taking all the demand labels as graph nodes, adding connecting edges between the graph nodes where the two associated demand labels are positioned, generating a demand graph, and constructing a demand tree according to the demand graph; for each demand label, adding design nodes under the tree nodes where the demand labels are positioned according to all design elements corresponding to the demand labels, and constructing a multi-level demand tree; and integrating all design nodes of each level in the multi-level demand tree into one demand task to obtain a plurality of demand tasks.
Illustratively, all demand labels corresponding to the subject labels of the demand data are screened from a pre-constructed mechanical engineering project demand library, and all design elements corresponding to the demand labels are determined.
All the demand labels are used as graph nodes by adopting a graph theory and network analysis method, connecting edges are added between the graph nodes where the two associated demand labels are located, a demand graph is generated, and the demand graph is converted into a tree structure by adopting a recursion algorithm or other algorithms, so that a demand tree is constructed.
For each demand label, adding design nodes under the tree nodes where the demand labels are located according to all the design elements corresponding to the demand labels, so as to refine the tree nodes where the demand labels are located into more detailed mechanical design requirements, and meanwhile ensuring that each design node under the tree nodes where the same demand label is located represents a specific executable design requirement, and connecting edges among the design nodes can reflect the association relation among the design elements to construct a multi-level demand tree.
And integrating all design nodes of each level in the multi-level demand tree into one demand task to obtain a plurality of demand tasks.
For example, assuming that the demand data is "design a lightweight, small, mechanical device suitable for use in high temperature environments", the subject label of the demand data is "materials: a lightweight high strength material; size: a small-sized design; durability: surface treatment "which is required to withstand a high temperature environment, by performing the above operation, the demand data can be disassembled into a plurality of demand tasks such as: for the design requirement, a light high-strength material is used, and the light high-strength metal or alloy can be disassembled into a required task of searching for the light high-strength metal or alloy suitable for a high-temperature environment; for the design of small mechanical devices, the task of designing a compact structure can be disassembled.
According to the embodiment of the invention, the multi-level demand tree is constructed by acquiring all the demand labels corresponding to the subject labels of the demand data and all the design elements corresponding to the demand labels from the mechanical engineering project demand library, and the demand data is disassembled into a plurality of demand tasks based on the multi-level demand tree, so that the demand data can be reasonably disassembled into a plurality of demand tasks, and the demand analysis efficiency of the mechanical engineering project can be further improved.
In an alternative embodiment, the obtaining design parameters and physical formulas of each demand task based on the pre-constructed mechanical engineering project knowledge base specifically includes: and searching the design parameters and the physical formulas matched with each demand task from a mechanical engineering project knowledge base by adopting a rule engine to obtain the design parameters and the physical formulas of each demand task.
Illustratively, a rules engine is pre-designed that contains matching rules for various engineering design requirements and various engineering design knowledge.
When the demand data is disassembled into a plurality of demand tasks, for each demand task, the rule engine is adopted to search design parameters and physical formulas matched with the demand task from a pre-constructed mechanical engineering project knowledge base, so that the design parameters and the physical formulas of the demand task are obtained, and the design parameters and the physical formulas of all the demand tasks are obtained.
According to the embodiment of the invention, the design parameters and the physical formulas matched with each demand task are searched from the mechanical engineering project knowledge base by adopting the rule engine, so that the design parameters and the physical formulas of each demand task can be rapidly and accurately obtained, and the demand analysis efficiency of the mechanical engineering project is further improved.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a system for analyzing requirements of a mechanical engineering project according to a second embodiment of the present invention. A second embodiment of the present invention provides a system for analyzing a demand for a mechanical engineering project, including: a demand input module 201, configured to obtain raw demand data input by a user for a mechanical engineering project; the requirement identification module 202 is configured to perform a structuring process on the original requirement data to obtain requirement data, and identify a subject tag of the requirement data; the demand dismantling module 203 is configured to disassemble demand data into a plurality of demand tasks according to a topic label of the demand data based on a pre-constructed mechanical engineering project demand library; the demand design module 204 is configured to obtain design parameters and physical formulas of each demand task based on a pre-constructed mechanical engineering project knowledge base; the result generation module 205 is configured to combine design parameters and physical formulas of all the requirement tasks to generate a requirement analysis result of the mechanical engineering project.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a system for analyzing requirements of a mechanical engineering project according to an alternative embodiment of the invention. In an alternative embodiment, the system for analyzing requirements of a mechanical engineering project further includes: the result optimization module 206 is configured to adjust a demand analysis result of the mechanical engineering project in response to a result optimization request initiated by a user for the demand analysis result of the mechanical engineering project.
In an alternative embodiment, the structuring the original demand data to obtain the demand data specifically includes: performing natural language processing on the text data by adopting a pre-established natural language processing model, and extracting text information in the text data; performing image processing on the image data, and extracting image information in the image data; integrating text information and image information according to a preset data structure to obtain demand data; wherein the raw demand data includes text data and image data.
In an alternative embodiment, the theme tag for identifying the requirement data specifically includes: and classifying the demand data by adopting a pre-established label classification model to obtain the subject label of the demand data.
In an optional embodiment, the disassembling the demand data into a plurality of demand tasks according to the topic labels of the demand data based on the pre-constructed demand library of the mechanical engineering project specifically includes: screening all demand labels corresponding to the subject labels of the demand data from a mechanical engineering project demand library, and determining all design elements corresponding to all the demand labels; taking all the demand labels as graph nodes, adding connecting edges between the graph nodes where the two associated demand labels are positioned, generating a demand graph, and constructing a demand tree according to the demand graph; for each demand label, adding design nodes under the tree nodes where the demand labels are positioned according to all design elements corresponding to the demand labels, and constructing a multi-level demand tree; and integrating all design nodes of each level in the multi-level demand tree into one demand task to obtain a plurality of demand tasks.
In an alternative embodiment, the obtaining design parameters and physical formulas of each demand task based on the pre-constructed mechanical engineering project knowledge base specifically includes: and searching the design parameters and the physical formulas matched with each demand task from a mechanical engineering project knowledge base by adopting a rule engine to obtain the design parameters and the physical formulas of each demand task.
The implementation process of the functions and roles of each module in the system is specifically shown in the implementation process of the corresponding steps in the method, and is not repeated here.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention. A third embodiment of the invention provides an electronic device 30 comprising a processor 301, a memory 302 and a computer program stored in the memory 302 and configured to be executed by the processor 301; the memory 302 is coupled to the processor 301, and the processor 301 executes the computer program to implement the method for analyzing the requirements of the mechanical engineering project according to the first embodiment of the present invention, and achieve the same advantages as the method.
The processor 301 may implement the method according to any embodiment of the mechanical engineering project requirement analysis method according to the first embodiment of the present invention when reading a computer program from the memory 302 via the bus 303 and executing the computer program.
The processor 301 may process digital signals and may include various computing structures. Such as a complex instruction set computer architecture, a reduced instruction set computer architecture, or an architecture that implements a combination of instruction sets. In some examples, processor 301 may be a microprocessor.
Memory 302 may be used for storing instructions to be executed by processor 301 or data relating to the execution of instructions. Such instructions and/or data may include code to implement some or all of the functions of one or more of the modules described in embodiments of the present invention. The processor 301 of the disclosed embodiment may be configured to execute instructions in the memory 302 to implement the method for analyzing a demand for a machine engineering project according to the first embodiment of the present invention. Memory 302 includes dynamic random access memory, static random access memory, flash memory, optical memory, or other memory known to those skilled in the art.
A fourth embodiment of the present invention provides a computer-readable storage medium including a stored computer program; the equipment where the computer readable storage medium is located is controlled to execute the mechanical engineering project requirement analysis method according to the first embodiment of the invention when the computer program runs, and the same beneficial effects can be achieved.
In summary, the embodiment of the invention provides a method, a system, a device and a medium for analyzing requirements of a mechanical engineering project, where the method for analyzing requirements of a mechanical engineering project includes: acquiring original demand data input by a user aiming at a mechanical engineering project; carrying out structuring treatment on the original demand data to obtain demand data, and identifying a theme label of the demand data; based on a pre-constructed mechanical engineering project demand library, disassembling the demand data into a plurality of demand tasks according to the topic labels of the demand data; based on a pre-constructed mechanical engineering project knowledge base, acquiring design parameters and physical formulas of each demand task; and combining design parameters and physical formulas of all the demand tasks to generate a demand analysis result of the mechanical engineering project. According to the embodiment of the invention, when the original demand data input by a user aiming at the mechanical engineering project is obtained, the demand recognition, the demand disassembly, the demand design and the like are sequentially carried out on the original demand data, so that the demand analysis result of the mechanical engineering project is obtained, the mechanical engineering project can be automatically subjected to the demand analysis, and the demand analysis efficiency of the mechanical engineering project is improved.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, flow diagrams and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified 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. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily appreciate variations or alternatives within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. A method for demand analysis of a mechanical engineering project, comprising:
Acquiring original demand data input by a user aiming at a mechanical engineering project;
carrying out structuring treatment on the original demand data to obtain demand data, and identifying a theme label of the demand data;
based on a pre-constructed mechanical engineering project demand library, disassembling the demand data into a plurality of demand tasks according to the topic labels of the demand data;
based on a pre-constructed mechanical engineering project knowledge base, acquiring design parameters and physical formulas of each demand task;
And combining design parameters and physical formulas of all the demand tasks to generate a demand analysis result of the mechanical engineering project.
2. The machine engineering project demand analysis method according to claim 1, further comprising:
and responding to a result optimization request initiated by the user aiming at the requirement analysis result of the mechanical engineering project, and adjusting the requirement analysis result of the mechanical engineering project.
3. The method for analyzing the demand of the mechanical engineering project according to claim 1, wherein the structuring the raw demand data to obtain the demand data specifically includes:
performing natural language processing on the text data by adopting a pre-established natural language processing model, and extracting text information in the text data;
performing image processing on the image data, and extracting image information in the image data;
integrating the text information and the image information according to a preset data structure to obtain the requirement data;
wherein the raw demand data includes the text data and the image data.
4. The method for analyzing the demand of the mechanical engineering project according to claim 1, wherein the theme tag for identifying the demand data specifically comprises:
And classifying the demand data by adopting a pre-established label classification model to obtain the theme label of the demand data.
5. The method for analyzing the demand of the mechanical engineering project according to claim 1, wherein the disassembling the demand data into a plurality of demand tasks according to the topic labels of the demand data based on the pre-constructed demand library of the mechanical engineering project specifically comprises:
screening all demand labels corresponding to the subject labels of the demand data from the mechanical engineering project demand library, and determining all design elements corresponding to the demand labels;
Taking all the demand labels as graph nodes, adding connecting edges between the graph nodes where the two associated demand labels are positioned, generating a demand graph, and constructing a demand tree according to the demand graph;
For each demand label, adding design nodes under the tree nodes where the demand labels are positioned according to all design elements corresponding to the demand labels, and constructing a multi-level demand tree;
and integrating all design nodes of each level in the multi-level demand tree into a demand task respectively to obtain a plurality of demand tasks.
6. The method for analyzing the requirements of the mechanical engineering project according to claim 1, wherein the obtaining design parameters and physical formulas of each of the required tasks based on the pre-constructed knowledge base of the mechanical engineering project specifically comprises:
And searching the design parameters and the physical formulas matched with each required task from the mechanical engineering project knowledge base by adopting a rule engine to obtain the design parameters and the physical formulas of each required task.
7. A system for demand analysis of a mechanical engineering project, comprising:
the demand input module is used for acquiring original demand data input by a user aiming at a mechanical engineering project;
The demand identification module is used for carrying out structural processing on the original demand data to obtain demand data and identifying a theme label of the demand data;
The demand dismantling module is used for dismantling the demand data into a plurality of demand tasks according to the theme labels of the demand data based on a pre-constructed mechanical engineering project demand library;
the demand design module is used for acquiring design parameters and physical formulas of each demand task based on a pre-constructed mechanical engineering project knowledge base;
And the result generation module is used for combining the design parameters and the physical formulas of all the demand tasks to generate the demand analysis result of the mechanical engineering project.
8. The machine engineering project demand analysis system of claim 7, further comprising:
And the result optimization module is used for responding to a result optimization request initiated by the user aiming at the requirement analysis result of the mechanical engineering project and adjusting the requirement analysis result of the mechanical engineering project.
9. An electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor; the memory is coupled to the processor and the processor when executing the computer program implements the method for analyzing requirements of a mechanical engineering project according to any one of claims 1 to 6.
10. A computer readable storage medium, wherein the computer readable storage medium comprises a stored computer program; wherein the computer program, when run, controls the device in which the computer readable storage medium is located to perform the mechanical engineering project demand analysis method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410524058.XA CN118096091A (en) | 2024-04-29 | 2024-04-29 | Mechanical engineering project demand analysis method, system, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410524058.XA CN118096091A (en) | 2024-04-29 | 2024-04-29 | Mechanical engineering project demand analysis method, system, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118096091A true CN118096091A (en) | 2024-05-28 |
Family
ID=91149425
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410524058.XA Pending CN118096091A (en) | 2024-04-29 | 2024-04-29 | Mechanical engineering project demand analysis method, system, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118096091A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112579444A (en) * | 2020-12-10 | 2021-03-30 | 华南理工大学 | Text cognition-based automatic analysis modeling method, system, device and medium |
| CN116431105A (en) * | 2022-12-13 | 2023-07-14 | 重庆长安汽车股份有限公司 | Software system structural design method and device, electronic equipment and storage medium |
| CN117611295A (en) * | 2023-12-11 | 2024-02-27 | 北京澳环科技有限公司 | Multi-merchant electronic commerce recommendation system based on user requirements |
| CN117608650A (en) * | 2024-01-15 | 2024-02-27 | 钱塘科技创新中心 | Business flow chart generation method, processing device and storage medium |
| CN117707477A (en) * | 2023-11-24 | 2024-03-15 | 上海交通大学 | Civil aircraft demand analysis method based on knowledge graph |
| CN117785918A (en) * | 2023-12-08 | 2024-03-29 | 长城汽车股份有限公司 | Data processing method, device, storage medium, program product and electronic equipment |
-
2024
- 2024-04-29 CN CN202410524058.XA patent/CN118096091A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112579444A (en) * | 2020-12-10 | 2021-03-30 | 华南理工大学 | Text cognition-based automatic analysis modeling method, system, device and medium |
| CN116431105A (en) * | 2022-12-13 | 2023-07-14 | 重庆长安汽车股份有限公司 | Software system structural design method and device, electronic equipment and storage medium |
| CN117707477A (en) * | 2023-11-24 | 2024-03-15 | 上海交通大学 | Civil aircraft demand analysis method based on knowledge graph |
| CN117785918A (en) * | 2023-12-08 | 2024-03-29 | 长城汽车股份有限公司 | Data processing method, device, storage medium, program product and electronic equipment |
| CN117611295A (en) * | 2023-12-11 | 2024-02-27 | 北京澳环科技有限公司 | Multi-merchant electronic commerce recommendation system based on user requirements |
| CN117608650A (en) * | 2024-01-15 | 2024-02-27 | 钱塘科技创新中心 | Business flow chart generation method, processing device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 陈辞;: "基于语义分析的软件需求提取技术研究", 舰船电子工程, no. 06, 20 June 2020 (2020-06-20) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107491534B (en) | Information processing method and device | |
| CN110968684B (en) | Information processing method, device, equipment and storage medium | |
| US11847418B2 (en) | Few-shot language model training and implementation | |
| US20210390370A1 (en) | Data processing method and apparatus, storage medium and electronic device | |
| KR20200007969A (en) | Information processing methods, terminals, and computer storage media | |
| US11030405B2 (en) | Method and device for generating statement | |
| US11886779B2 (en) | Accelerated simulation setup process using prior knowledge extraction for problem matching | |
| CN110795527A (en) | Candidate entity ordering method, training method and related device | |
| CN113434699A (en) | Pre-training method of BERT model, computer device and storage medium | |
| CN110502620B (en) | Method, system and computer equipment for generating guide diagnosis similar problem pairs | |
| CN113705192B (en) | Text processing method, device and storage medium | |
| CN117608650B (en) | Business flow chart generation method, processing device and storage medium | |
| CN110867225A (en) | Character-level clinical concept extraction named entity recognition method and system | |
| US11501071B2 (en) | Word and image relationships in combined vector space | |
| CN113297355A (en) | Method, device, equipment and medium for enhancing labeled data based on countermeasure interpolation sequence | |
| CN112989829A (en) | Named entity identification method, device, equipment and storage medium | |
| Sharif et al. | Function identification in android binaries with deep learning | |
| CN112817560B (en) | Computing task processing method, system and computer readable storage medium based on table function | |
| CN118096091A (en) | Mechanical engineering project demand analysis method, system, equipment and medium | |
| CN113568969B (en) | Information extraction method, apparatus, device and computer readable storage medium | |
| US11599801B2 (en) | Method for solving problem, computing system and program product | |
| CN113822039A (en) | Method and related equipment for mining similar meaning words | |
| CN113159315A (en) | Neural network training method, data processing method and related equipment | |
| JP2021163477A (en) | Method, apparatus, electronic device, computer-readable storage medium, and computer program for image processing | |
| CN111382247A (en) | Content pushing optimization method, content pushing optimization device and electronic equipment |
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 |