Intelligent recognition and evaluation method and system for CAD drawing and computer program product

Abstract

The invention discloses a CAD drawing intelligent identification and evaluation method and system and a computer program product, and relates to the field of CAD drawing analysis, and the method comprises the steps: obtaining a sample roll and a CAD drawing specification; according to the sample roll and CAD drawing specifications, a scoring standard is formulated; obtaining a to-be-evaluated drawing; performing intelligent identification on the to-be-evaluated drawing according to the sample roll; scoring the to-be-evaluated drawing according to the scoring standard; a plurality of drawings to be evaluated can be scored in batches; and performing data mining and visual analysis on the scoring result. According to the technical scheme provided by the invention, intelligent identification and scoring of the CAD drawings can be realized, each error of each drawing can be recorded, analysis is objectively and accurately carried out, manual comparison and scoring one by one are not needed, the scoring efficiency is greatly improved, time and labor cost are saved, and human errors are reduced.

Description

Technical Field

[0001] The present invention relates to the field of CAD drawing analysis, and in particular to a method, system and computer program product for intelligently identifying and evaluating CAD drawings. Background Art

[0002] As the digitalization of the manufacturing industry accelerates, the rapid and accurate evaluation of CAD drawings is becoming increasingly important. The current technical solutions on the market focus on the identification of basic graphic elements and simple dimension measurement comparison of drawings in specific formats to achieve preliminary drawing review and scoring functions. These technical solutions mainly rely on established rule libraries and limited algorithm optimization, such as judging the compliance of graphics through preset layer, line type and other attribute rules.

[0003] At present, the existing technical solutions have the following shortcomings: on the one hand, the compatibility with graphics drawn by different CAD software is poor, and it can only adapt to the drawing format generated by specific software, and it is difficult to achieve universal support for graphics drawn by any CAD software. On the other hand, it is relatively weak in intelligent analysis capabilities, and the accuracy and efficiency of graphic recognition are limited. Especially when facing complex graphic structures and massive drawing data, the processing speed is slow and it is easy to make misjudgments. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the current technology, the present invention provides a method for intelligent recognition and evaluation of CAD drawings, which can realize intelligent recognition and scoring of CAD drawings without manual one-to-one comparison and scoring, thereby improving scoring efficiency.

[0005] To achieve the above object, the embodiments of the present invention adopt the following technical solutions: A method for intelligently identifying and evaluating CAD drawings comprises the following steps: Obtain sample rolls and CAD drawing specifications; Formulate scoring criteria based on sample papers and CAD drawing specifications; Get the drawings to be evaluated; Intelligently identify the drawings to be evaluated based on the sample papers; Score the drawings to be evaluated according to the scoring criteria; Among them, the scoring criteria formulated according to the sample papers and CAD drawing specifications include: A comprehensive score is defined as the score of the drawing to be evaluated, wherein the comprehensive score includes an environment score, a graphic element group score, and a subjective score; Wherein, the intelligent identification of drawings to be evaluated based on the sample papers includes: Graphics recognition, clustering and relative position relationship judgment methods are used to identify the types and parameters of the graphics elements in the drawings to be evaluated.

[0006] According to one aspect of the present invention, the CAD drawing intelligent recognition and evaluation method further includes: Check whether the sample roll meets the CAD drawing specifications. If not, make corrections.

[0007] According to one aspect of the present invention, the environmental score is a score obtained based on the layers, text styles, and dimension styles of the drawing to be evaluated, based on CAD drawing specifications and preset requirements; The element group score is based on the CAD drawing specification, and the scoring items are set according to the element group of the sample paper, and the score is obtained by judging the elements of the drawing to be evaluated; The subjective score is the score obtained by judging the completeness, correctness, rationality and aesthetics of the drawings to be evaluated.

[0008] According to one aspect of the present invention, the graphic elements include: contour lines, center lines, pattern fills, texts, dimensions, geometric tolerances, title blocks, drawing frames, roughness, datum elements, and view symbols.

[0009] According to one aspect of the present invention, formulating the scoring criteria according to the sample paper and the CAD drawing specification further comprises: The scoring criteria can be set manually by the user or automatically by a computer program.

[0010] According to one aspect of the present invention, the method of automatically setting the scoring criteria using a computer program includes: For the three types of scoring, namely, environmental scoring, element group scoring, and subjective scoring, a rule engine is set up respectively, and each scoring item and scoring standard is set as a rule to obtain three types of scoring respectively; Set weights for the three types of scores, take weighted sum, and get a comprehensive score.

[0011] According to one aspect of the present invention, the CAD drawing intelligent recognition and evaluation method further includes: Several drawings to be evaluated can be scored in batches.

[0012] According to one aspect of the present invention, the CAD drawing intelligent recognition and evaluation method further includes: Perform data mining and visual analysis on the scoring results.

[0013] A CAD drawing intelligent recognition and evaluation system, based on the CAD drawing intelligent recognition and evaluation method as described above, comprises: Sample volume module, used to obtain sample volumes and CAD drawing specifications; The scoring standard module is used to formulate scoring standards based on sample papers and CAD drawing specifications; The drawing module to be tested is used to obtain the drawing to be tested; Recognition module, used to intelligently identify the drawings to be evaluated based on the sample rolls; The scoring module is used to score the drawings to be evaluated according to the scoring criteria.

[0014] A computer program product comprises a computer program, wherein when the computer program is executed, the steps of the method for intelligently identifying and evaluating CAD drawings as described above are implemented.

[0015] Advantages of the present invention: The present invention provides a CAD drawing intelligent recognition and evaluation method, which can realize intelligent recognition and scoring of CAD drawings, record each error of each drawing, and analyze objectively and accurately without manual one-to-one scoring, thereby greatly improving scoring efficiency, saving time and labor costs, and reducing human errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 The present invention provides a flow chart of a method for intelligently identifying and evaluating CAD drawings. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Embodiment 1

[0020] like Figure 1 As shown, a method for intelligent recognition and evaluation of CAD drawings includes the following steps: S1: Obtain sample rolls and CAD drawing specifications.

[0021] This method requires the use of sample papers and CAD drawing specifications when evaluating the CAD drawings to be tested. Therefore, before formulating the scoring criteria, it is necessary to obtain sample papers for reference, as well as national standards and drawing specifications for CAD drawings.

[0022] Preferably, the method further comprises: Check whether the sample roll meets the CAD drawing specifications. If not, make corrections.

[0023] In the specific implementation, the sample roll used in this method must comply with the CAD drawing specifications. A rule library can be set up to perform a normative check on the sample roll drawings. The rule library has built-in technical drawing, mechanical drawing, product geometry technical specifications and more than 30 national standards and drawing specifications. The inspection items of the rule library include: basic provisions for mechanical drawing, drawing methods, dimensioning methods, surface roughness, limits and fits, geometric tolerances, etc. When checking, the parts of the sample roll inspection items that do not meet the specifications can be highlighted, and the correct national standards and error points can be displayed. For the parts that do not meet the specifications, corrections need to be made to obtain a standardized sample roll without errors.

[0024] S2: Establish scoring criteria based on sample papers and CAD drawing specifications.

[0025] Before evaluating the CAD drawings to be tested, it is necessary to formulate scoring criteria and then score the drawings according to the scoring criteria.

[0026] Specifically, step S2 includes: A comprehensive score is defined as the score of the drawing to be evaluated, and the comprehensive score includes an environment score, a graphic element group score, a subjective score, and the like.

[0027] According to actual needs, multiple scoring items can be set, and weights can be set for each score according to the importance of each item to be rated, and a weighted sum can be taken to obtain a total comprehensive score.

[0028] Specifically, the environmental score is a score obtained based on the layers, text styles, and dimension styles of the drawing to be evaluated, based on CAD drawing specifications and preset requirements.

[0029] For example, for dimension style, you can set Standard, GB_DIMSTYLE, GB_LINEAR, ISO-25 and other styles. Each style sets specific requirements for dimension lines, dimension boundaries, symbols and arrows, text, units, etc.

[0030] Specifically, the element group score is based on the CAD drawing specifications, sets scoring items according to the element group of the sample paper, and evaluates the elements of the drawing to be evaluated.

[0031] The primitives include: contour lines, center lines, pattern fills, texts, dimensions, geometric tolerances, title blocks, drawing frames, roughness, datum elements, view symbols, etc. Take the setting of scoring for a primitive group as an example, the total score is 100, among which, the number of contour lines is 49, the total score is 19, and the scoring method is total score / actual number of primitives; the number of center lines is 5, the total score is 5, and the scoring method is total score / actual number of primitives, and so on.

[0032] Specifically, the subjective score is a score obtained by judging the completeness, correctness, rationality and aesthetics of the drawing to be evaluated.

[0033] The completeness and accuracy of the drawings to be evaluated can be calculated based on the relationship between the sample papers, the scoring items of the elements and all the elements participating in the evaluation.

[0034] When the drawings to be evaluated are scored, the scores of each item will be listed according to the requirements of the above scoring standards. When developing the corresponding application software, the unqualified parts of the drawings to be evaluated can also be viewed visually. By clicking on each scoring item, the corresponding area of ​​the drawing can be quickly located, which clearly and intuitively reflects the difference between the drawings to be evaluated and the sample.

[0035] Preferably, step S2 further includes: Users can set the scoring criteria manually, or use a computer program to automatically set the scoring criteria.

[0036] When manually setting the scoring criteria, you need to select the elements to generate element groups, and set the scoring method by average distribution, setting weights, or until all the points are deducted.

[0037] The automatic setting of the scoring criteria by a computer program comprises: For the three types of scoring, namely, environmental scoring, element group scoring, and subjective scoring, a rule engine is set up respectively, and each scoring item and scoring standard is set as a rule to obtain three types of scoring respectively; The weights of the three types of scores are set, and the weighted sum is taken to get the comprehensive score. The computer program can automatically identify various graphic elements and quickly and accurately generate the scoring criteria.

[0038] S3: Obtain the drawing to be evaluated.

[0039] In practical applications, this method can be used for school teaching. Students do CAD drawing homework based on sample papers, and the instructor needs to score the students' homework drawings.

[0040] S4: Intelligently identify the drawings to be evaluated based on the sample papers.

[0041] Specifically, step S4 includes: Graphics recognition, clustering and relative position relationship judgment methods are used to identify the types and parameters of the graphics elements in the drawings to be evaluated.

[0042] In practical applications, this method is used for intelligent recognition of graphics in drawings in formats such as DWG. When performing graphic analysis, dimension annotations can be directly identified; for the identification of various symbols, clustering technology can be used to group the lines, such as roughness symbols, and the length and angle requirements of the roughness symbols can be judged, and then characteristic lines are selected as the starting point for judgment, such as 45-degree oblique lines, so that various symbols can be identified (with a given error range). For the position matching judgment of the graphics, the relative position relationship is used to judge. For the same drawing, different people draw it, and each element of the sample drawing and the drawing to be evaluated can be accurately located.

[0043] S5: Score the drawings to be evaluated according to the scoring criteria.

[0044] There are many ways to draw CAD drawings. For example, a symmetrical figure can be drawn using mirroring, polylines, multiple straight lines, etc. This method can intelligently identify and score all of them. Finally, all the score details and deduction items of the drawings to be evaluated, as well as the error locations compared with the sample papers, are output for the evaluation users to view.

[0045] For example, if there are duplicate lines in the drawing, after intelligent recognition, as long as the logic is correct, no points will be deducted. There are many ways to draw a circle. For a circle composed of several arcs, after intelligent recognition, as long as the logic is correct, no points will be deducted. The center line is detected by its orientation, not the position or length of its endpoints.

[0046] The dimension marking position of the sample paper and the marking position of the drawing to be evaluated cannot be exactly the same. As long as the logic is correct, no points will be deducted. For the same arc or circle, different drawings can be marked as diameter, radius, and large radius. The system can automatically identify them. As long as the logic is correct, no points will be deducted.

[0047] For graphics with fills, the arrangement and combination of the filled areas in the sample paper and the drawing to be evaluated may be diverse. For example, when filling the sample paper, different views are selected to generate the same fill, while the two views of the drawing to be evaluated are filled separately. Although the filling order is different, the final display result is the same. This situation should also be judged as correct.

[0048] Roughness symbols are commonly used in mechanical drawing. Roughness symbols can be expressed in various forms, depending on the material type, whether annotations are added, etc. Roughness symbols can be drawn in various ways in CAD drawings. Lines, arcs, circles, polylines, single (multi) line texts, or block quotes may be used for combined expression, which can all be intelligently identified and scored.

[0049] Datum is a concept widely used in mechanical manufacturing. Datum symbols on mechanical drawings are represented by capital letters A, B, C, D, etc., with a specific datum symbol with a circle (old national standard) or a specific box (new national standard). In CAD drawings, there may be various ways of expression, which may use straight lines, circles, polylines, single (multi) line text or block references for combined expression, which can all be intelligently identified and scored.

[0050] In CAD drawings, blocks are often used to define repeated graphics. For the same graphics, the sample paper and the test paper may use different areas to define the blocks, but the display is exactly the same. This kind of situation is very common, and the system can intelligently identify and score it.

[0051] Preferably, the method further comprises: S6: Perform data mining and visual analysis on the scoring results.

[0052] This method finally outputs all the score details and deduction items of the drawings to be evaluated. The output personal transcript can include sample drawings, drawings that only show deduction items, and original drawings to be evaluated, which is convenient for evaluation users to compare and view.

[0053] The scoring results can be used to analyze the professional knowledge of the users and the radar chart of patent capabilities. By using sub-item statistical analysis, the instructor can get a clear view of the students' professional knowledge and unit characteristics.

[0054] The beneficial effect of this embodiment is that the method can realize intelligent recognition and scoring of CAD drawings, record every error in each drawing, and analyze objectively and accurately without manual one-to-one scoring, which greatly improves the scoring efficiency, saves time and labor costs, and reduces human errors.

[0055] Embodiment 2

[0056] like Figure 1 As shown, a method for intelligent recognition and evaluation of CAD drawings includes the following steps: S1: Obtain sample rolls and CAD drawing specifications.

[0057] This method requires the use of sample papers and CAD drawing specifications when evaluating the CAD drawings to be tested. Therefore, before formulating the scoring criteria, it is necessary to obtain sample papers for reference, as well as national standards and drawing specifications for CAD drawings.

[0058] Preferably, the method further comprises: Check whether the sample roll meets the CAD drawing specifications. If not, make corrections.

[0059] In the specific implementation, the sample roll used in this method must comply with the CAD drawing specifications. A rule library can be set up to perform a normative check on the sample roll drawings. The rule library has built-in technical drawing, mechanical drawing, product geometry technical specifications and more than 30 national standards and drawing specifications. The inspection items of the rule library include: basic provisions for mechanical drawing, drawing methods, dimensioning methods, surface roughness, limits and fits, geometric tolerances, etc. When checking, the parts of the sample roll inspection items that do not meet the specifications can be highlighted, and the correct national standards and error points can be displayed. For the parts that do not meet the specifications, corrections need to be made to obtain a standardized sample roll without errors.

[0060] S2: Establish scoring criteria based on sample papers and CAD drawing specifications.

[0061] Before evaluating the CAD drawings to be tested, it is necessary to formulate scoring criteria and then score the drawings according to the scoring criteria.

[0062] Specifically, step S2 includes: A comprehensive score is defined as the score of the drawing to be evaluated, and the comprehensive score includes an environment score, a graphic element group score, a subjective score, and the like.

[0063] According to actual needs, multiple scoring items can be set, and weights can be set for each score according to the importance of each item to be rated, and a weighted sum can be taken to obtain a total comprehensive score.

[0064] Specifically, the environmental score is a score obtained based on the layers, text styles, and dimension styles of the drawing to be evaluated, based on CAD drawing specifications and preset requirements.

[0065] For example, for dimension style, you can set Standard, GB_DIMSTYLE, GB_LINEAR, ISO-25 and other styles. Each style sets specific requirements for dimension lines, dimension boundaries, symbols and arrows, text, units, etc.

[0066] Specifically, the element group score is based on the CAD drawing specifications, sets scoring items according to the element group of the sample paper, and evaluates the elements of the drawing to be evaluated.

[0067] The primitives include: contour lines, center lines, pattern fills, texts, dimensions, geometric tolerances, title blocks, drawing frames, roughness, datum elements, view symbols, etc. Take the setting of scoring for a primitive group as an example, the total score is 100, among which, the number of contour lines is 49, the total score is 19, and the scoring method is total score / actual number of primitives; the number of center lines is 5, the total score is 5, and the scoring method is total score / actual number of primitives, and so on.

[0068] Specifically, the subjective score is a score obtained by judging the completeness, correctness, rationality and aesthetics of the drawing to be evaluated.

[0069] The completeness and accuracy of the drawings to be evaluated can be calculated based on the relationship between the sample papers, the scoring items of the elements and all the elements participating in the evaluation.

[0070] When the drawings to be evaluated are scored, the scores of each item will be listed according to the requirements of the above scoring standards. When developing the corresponding application software, the unqualified parts of the drawings to be evaluated can also be viewed visually. By clicking on each scoring item, the corresponding area of ​​the drawing can be quickly located, which clearly and intuitively reflects the difference between the drawings to be evaluated and the sample.

[0071] Preferably, step S2 further includes: Users can set the scoring criteria manually, or use a computer program to automatically set the scoring criteria.

[0072] When manually setting the scoring criteria, you need to select the elements to generate element groups, and set the scoring method by average distribution, setting weights, or until all the points are deducted.

[0073] The automatic setting of the scoring criteria by a computer program comprises: For the three types of scoring, namely, environmental scoring, element group scoring, and subjective scoring, a rule engine is set up respectively, and each scoring item and scoring standard is set as a rule to obtain three types of scoring respectively; The weights of the three types of scores are set, and the weighted sum is taken to get the comprehensive score. The computer program can automatically identify various graphic elements and quickly and accurately generate the scoring criteria.

[0074] S3: Obtain the drawing to be evaluated.

[0075] In practical applications, this method can be used for school teaching. Students do CAD drawing homework based on sample papers, and the instructor needs to score the students' homework drawings.

[0076] The method further comprises: Several drawings to be evaluated can be scored in batches.

[0077] When teaching in school, students' drawing assignments can be graded in batches.

[0078] S4: Intelligently identify the drawings to be evaluated based on the sample papers.

[0079] Specifically, step S4 includes: Graphics recognition, clustering and relative position relationship judgment methods are used to identify the types and parameters of the graphics elements in the drawings to be evaluated.

[0080] In practical applications, this method is used for intelligent recognition of graphics in drawings in formats such as DWG. When performing graphic analysis, dimension annotations can be directly identified; for the identification of various symbols, clustering technology can be used to group the lines, such as roughness symbols, and the length and angle requirements of the roughness symbols can be judged, and then characteristic lines are selected as the starting point for judgment, such as 45-degree oblique lines, so that various symbols can be identified (with a given error range). For the position matching judgment of the graphics, the relative position relationship is used to judge. For the same drawing, different people draw it, and each element of the sample drawing and the drawing to be evaluated can be accurately located.

[0081] S5: Score the drawings to be evaluated according to the scoring criteria.

[0082] There are many ways to draw CAD drawings. For example, a symmetrical figure can be drawn using mirroring, polylines, multiple straight lines, etc. This method can intelligently identify and score all of them. Finally, all the score details and deduction items of the drawings to be evaluated, as well as the error locations compared with the sample papers, are output for the evaluation users to view.

[0083] For example, if there are duplicate lines in the drawing, after intelligent recognition, as long as the logic is correct, no points will be deducted. There are many ways to draw a circle. For a circle composed of several arcs, after intelligent recognition, as long as the logic is correct, no points will be deducted. The center line is detected by its orientation, not the position or length of its endpoints.

[0084] The dimension marking position of the sample paper and the marking position of the drawing to be evaluated cannot be exactly the same. As long as the logic is correct, no points will be deducted. For the same arc or circle, different drawings can be marked as diameter, radius, and large radius. The system can automatically identify them. As long as the logic is correct, no points will be deducted.

[0085] For graphics with fills, the arrangement and combination of the filled areas in the sample paper and the drawing to be evaluated may be diverse. For example, when filling the sample paper, different views are selected to generate the same fill, while the two views of the drawing to be evaluated are filled separately. Although the filling order is different, the final display result is the same. This situation should also be judged as correct.

[0086] Roughness symbols are commonly used in mechanical drawing. Roughness symbols can be expressed in various forms, depending on the material type, whether annotations are added, etc. Roughness symbols can be drawn in various ways in CAD drawings. Lines, arcs, circles, polylines, single (multi) line texts, or block quotes may be used for combined expression, which can all be intelligently identified and scored.

[0087] Datum is a concept widely used in mechanical manufacturing. Datum symbols on mechanical drawings are represented by capital letters A, B, C, D, etc., with a specific datum symbol with a circle (old national standard) or a specific box (new national standard). In CAD drawings, there may be various ways of expression, which may use straight lines, circles, polylines, single (multi) line text or block references for combined expression, which can all be intelligently identified and scored.

[0088] In CAD drawings, blocks are often used to define repeated graphics. For the same graphics, the sample paper and the test paper may use different areas to define the blocks, but the display is exactly the same. This kind of situation is very common, and the system can intelligently identify and score it.

[0089] S6: Perform data mining and visual analysis on the scoring results.

[0090] This method finally outputs all the score details and deduction items of the drawings to be evaluated. The output personal transcript can include sample drawings, drawings that only show deduction items, and original drawings to be evaluated, which is convenient for evaluation users to compare and view.

[0091] The scoring results can be used to analyze the professional knowledge of the users and the radar chart of patent capabilities. By using sub-item statistical analysis, the instructor can get a clear view of the students' professional knowledge and unit characteristics.

[0092] When teaching in school, data mining and visualization analysis can be performed on the scoring results of batch-assessed student homework drawings to analyze the overall situation of the class. For example, using grade analysis bar charts, line charts, etc., the score range distribution can be intuitively displayed; the scores of students in the class can be analyzed, including the number of full marks, average score, lowest score, etc.; and the overall professional knowledge of students and the mastery of drawing tools can be analyzed.

[0093] In practical applications, this method is used to score and evaluate 1,000 drawings, which usually takes no more than 1 minute and is objective, accurate, intelligent and advanced. It can record every error in each drawing and conduct big data analysis objectively and accurately.

[0094] The beneficial effects of this embodiment are: batch processing of drawings to be evaluated can be carried out, big data analysis can be performed on the scoring results, processing efficiency can be greatly improved, and labor costs can be saved.

[0095] Embodiment 3

[0096] A CAD drawing intelligent recognition and evaluation system, based on the CAD drawing intelligent recognition and evaluation method as described in Embodiment 1 or 2, comprises: Sample volume module, used to obtain sample volumes and CAD drawing specifications; The scoring standard module is used to formulate scoring standards based on sample papers and CAD drawing specifications; The drawing module to be tested is used to obtain the drawing to be tested; Recognition module, used to intelligently identify the drawings to be evaluated based on the sample rolls; The scoring module is used to score the drawings to be evaluated according to the scoring criteria.

[0097] Preferably, the system further comprises: The data analysis module is used to perform data mining and visual analysis on the scoring results.

[0098] This system can realize batch identification and scoring of several drawings to be evaluated, conduct data mining and visualization analysis on the batch scoring results, and perform big data analysis.

[0099] Embodiment 4

[0100] A computer program product includes a computer program, and when the computer program is executed, the steps of the CAD drawing intelligent recognition and evaluation method as described in embodiment one or two are implemented.

[0101] Embodiment 5

[0102] A readable storage medium stores a computer program as described in Example 4, and when the computer program is executed, the steps of the CAD drawing intelligent recognition and evaluation method as described in Example 1 or 2 are implemented.

[0103] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the art within the technical scope disclosed in the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for intelligent recognition and evaluation of CAD drawings, characterized in that: The following steps are involved: Obtain sample rolls and CAD drawing specifications; Formulate scoring criteria based on sample papers and CAD drawing specifications; Get the drawings to be evaluated; Intelligently identify the drawings to be evaluated based on the sample papers; Score the drawings to be evaluated according to the scoring criteria; Among them, the scoring criteria formulated according to the sample papers and CAD drawing specifications include: A comprehensive score is defined as the score of the drawing to be evaluated, wherein the comprehensive score includes an environment score, a graphic element group score, and a subjective score; Wherein, the intelligent identification of drawings to be evaluated based on the sample papers includes: Graphics recognition, clustering and relative position relationship judgment methods are used to identify the types and parameters of the graphics elements in the drawings to be evaluated.

2. The CAD drawing intelligent recognition and evaluation method according to claim 1, characterized in that: The CAD drawing intelligent identification and evaluation method also includes: Check whether the sample roll meets the CAD drawing specifications. If not, make corrections.

3. The method for intelligent identification and evaluation of CAD drawings according to claim 1, characterized in that: The environmental score is a score obtained based on the layers, text styles, and dimension styles of the drawings to be evaluated, based on CAD drawing specifications and preset requirements; The element group score is based on the CAD drawing specification, and the scoring items are set according to the element group of the sample paper, and the score is obtained by judging the elements of the drawing to be evaluated; The subjective score is the score obtained by judging the completeness, correctness, rationality and aesthetics of the drawings to be evaluated.

4. The method for intelligent identification and evaluation of CAD drawings according to claim 3, characterized in that: The graphic elements include: contour lines, center lines, pattern fills, texts, dimensions, geometric tolerances, title blocks, drawing frames, roughness, datum elements, and view symbols.

5. The method for intelligent identification and evaluation of CAD drawings according to claim 3, characterized in that: The scoring criteria formulated according to the sample papers and CAD drawing specifications also include: The scoring criteria can be set manually by the user or automatically by a computer program.

6. The method for intelligent identification and evaluation of CAD drawings according to claim 5, characterized in that: The automatic setting of the scoring criteria by a computer program comprises: For the three types of scoring, namely, environmental scoring, element group scoring, and subjective scoring, a rule engine is set up respectively, and each scoring item and scoring standard is set as a rule to obtain three types of scoring respectively; Set weights for the three types of scores, take weighted sum, and get a comprehensive score.

7. The method for intelligent identification and evaluation of CAD drawings according to claim 1, characterized in that: The CAD drawing intelligent identification and evaluation method also includes: Several drawings to be evaluated can be scored in batches.

8. The method for intelligent identification and evaluation of CAD drawings according to claim 1, characterized in that: The CAD drawing intelligent identification and evaluation method also includes: Perform data mining and visual analysis on the scoring results.

9. A CAD drawing intelligent recognition and evaluation system, characterized in that: The method for intelligently identifying and evaluating CAD drawings according to any one of claims 1 to 8 comprises: Sample volume module, used to obtain sample volumes and CAD drawing specifications; The scoring standard module is used to formulate scoring standards based on sample papers and CAD drawing specifications; The drawing module to be tested is used to obtain the drawing to be tested; Recognition module, used to intelligently identify the drawings to be evaluated based on the sample rolls; The scoring module is used to score the drawings to be evaluated according to the scoring criteria.

10. A computer program product, characterized in that It comprises a computer program, which, when executed, implements the steps of the method for intelligent recognition and evaluation of CAD drawings as described in any one of claims 1 to 8.

Images