Recognition method and recognition system for drawings based on feature quantity slice recognition

Abstract

The present invention discloses a method and system for identifying drawings based on feature quantity slicing, wherein the method for identifying drawings based on feature quantity slicing comprises: obtaining drawings to be detected, adjusting recognizable drawings based on the drawings to be detected; dividing the recognizable drawings into regions, and forming detection regions with feature vectors; highlighting text based on each detection region, and determining the corresponding feature type; traversing the measurement units corresponding to the feature types as keywords to determine the corresponding quantity units; outputting a demand table based on the feature types and quantity units, and forming an overall quantity table of the corresponding drawings; forming an initial procurement plan table based on multiple overall quantity tables obtained within a preset range, and performing sufficient calculation on the initial procurement plan table to determine a final procurement plan table, wherein the final procurement plan table includes the initial procurement plan table and the supplementary quantity corresponding to the initial procurement plan table.

Description

Technical Field

[0001] The present invention relates to the technical field of drawing recognition, and in particular to a recognition method and a recognition system for identifying drawings based on feature quantity slices. Background Art

[0002] With the development of science and technology, drawings are applied to various fields or companies, but the drawing requirements of each company are not consistent. At this time, there are various customized requirements for drawings. The same recognition system cannot be used for multiple customized drawings, resulting in low recognition of existing drawings. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art. The present invention provides a recognition method and a recognition system for identifying drawings based on feature quantity slicing. The identifiable drawings are adjusted based on the drawings to be detected, and the identifiable drawings are divided into regions to form detection areas with feature vectors. At this time, text is highlighted for each of the detection areas. Each of the detection areas can be independently detected synchronously or asynchronously, and the corresponding feature type is determined. It is combined with the measurement unit as a keyword for traversal, thereby clarifying the demand table output, thereby realizing the overall output of the demand table under the separate detection of the drawings in each detection area, thereby maintaining the accuracy of the demand table and improving the recognition of the drawings to be detected.

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a method for identifying drawings based on feature quantity slices, comprising: obtaining a drawing to be detected, and adjusting a recognizable drawing based on the drawing to be detected;

[0005] Dividing the identifiable drawings into regions and forming detection regions with feature vectors;

[0006] Performing text highlighting based on each of the detection areas and determining corresponding feature types;

[0007] Using the measurement units corresponding to the feature types as keywords to traverse to determine the corresponding quantity units;

[0008] Outputting a demand table based on the feature type and the quantity unit, and forming an overall quantity table corresponding to the drawing;

[0009] A preliminary procurement plan table is formed according to the multiple overall quantity tables obtained within a preset range, and a sufficient calculation is performed on the preliminary procurement plan table to determine a final procurement plan table, wherein the final procurement plan table includes the preliminary procurement plan table and the supplementary quantity corresponding to the preliminary procurement plan table.

[0010] In addition, an embodiment of the present invention further provides a system for identifying drawings based on feature quantity slices, the system comprising: an acquisition module for acquiring drawings to be detected, and adjusting identifiable drawings based on the drawings to be detected;

[0011] Display module: used for dividing the identifiable drawings into regions and forming detection regions with feature vectors;

[0012] Positioning module: used to highlight text based on each of the detection areas and determine the corresponding feature type;

[0013] Type module: used to traverse the measurement units corresponding to the feature types as keywords to determine the corresponding quantity units;

[0014] Classification module: used for outputting the demand table based on the characteristic type and the quantity unit, and forming the overall quantity table of the corresponding drawing;

[0015] Learning module: used to form a preliminary procurement plan table based on multiple overall quantity tables obtained within a preset range, and perform sufficient calculations on the preliminary procurement plan table to determine a final procurement plan table, wherein the final procurement plan table includes the preliminary procurement plan table and the supplementary quantity corresponding to the preliminary procurement plan table.

[0016] In an embodiment of the present invention, through the method in the embodiment of the present invention, the identifiable drawings are adjusted based on the drawings to be detected, and the identifiable drawings are divided into regions to form detection areas with feature vectors. At this time, text is highlighted for each detection area, and each detection area can be independently detected synchronously or asynchronously, and the corresponding feature type is determined, and combined with the measurement unit as a keyword for traversal, the demand table output is clarified, so as to realize the overall output of the demand table under the separate detection of each detection area of ​​the drawings, thereby maintaining the accuracy of the demand table and improving the recognition of the drawings to be detected. In addition, a preliminary procurement plan table is formed according to the multiple overall quantity tables obtained within a preset range, and the preliminary procurement plan table is adequately calculated to determine the final procurement plan table, wherein the final procurement plan table includes the preliminary procurement plan table and the supplementary quantity corresponding to the preliminary procurement plan table. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art 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.

[0018] Figure 1 It is a flowchart of a method for identifying drawings based on feature quantity slices in an embodiment of the present invention;

[0019] Figure 2 It is a schematic diagram of the structure of a recognition system for identifying drawings based on feature quantity slices in an embodiment of the present invention;

[0020] Figure 3 The figure is a hardware diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0021] 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.

[0022] Example

[0023] See also Figure 1 , Figure 1 It is a flowchart of a method for identifying drawings based on feature quantity slices in an embodiment of the present invention.

[0024] like Figure 1 As shown, a method for identifying drawings based on feature quantity slices includes:

[0025] S11: Acquire a drawing to be detected, and adjust the identifiable drawing based on the drawing to be detected;

[0026] In the specific implementation process of the present invention, the specific steps may be: collecting the files to be detected, and determining the type of the files to be detected based on the suffixes of the files to be detected; selecting the type of the files to be detected as drawings or photos, and treating the files to be detected as drawings to be detected; blurring the photos, and highlighting the outer contours to form lines, and blurring the bending line areas again to adjust them to straight lines; adjusting the adjustment state based on the drawings to be detected, and obtaining the recognition area in the adjustment state; freezing the recognition area based on the proportion of the recognition area reaching 48% of the overall area of ​​the drawings to be detected, and adjusting the recognizable drawings based on the drawings to be detected.

[0027] Among them, the type of the file to be detected is detected, and the file mainly consisting of drawings or photos is determined. At this time, the type of the file to be detected is determined based on the suffix of the file to be detected, and the drawing to be detected is converted into a drawing file, and the photo needs to be blurred, and the outer contour is highlighted to form lines, and the bending line area is blurred again to adjust it to a straight line to ensure the conversion between the photo and the drawing.

[0028] The adjustment state is adjusted based on the drawing to be detected, and the recognition area is obtained in the adjustment state; based on the proportion of the recognition area reaching 48% of the overall area of ​​the drawing to be detected, the recognition area is frozen, and the recognizable drawing is adjusted based on the drawing to be detected.

[0029] S12: dividing the identifiable drawings into regions and forming detection regions with feature vectors;

[0030] In the specific implementation process of the present invention, the specific steps may be: dividing the identifiable drawing into regions, and forming blank regions, contour regions and other regions, wherein the contour region is between the blank regions and the other regions; traversing annotations based on the contour region, and recording the annotations in text; tracking feature vectors for the annotations, wherein the feature vectors may be product types and product names; saving the feature vectors and forming corresponding feature symbols; recording the feature symbols in the contour region, and performing regionalized display of the detection area with the feature vectors.

[0031] The recognizable drawings are divided into regions to form blank regions, contour regions and other regions, and emphasis is placed on the detection of contour regions. Traversal annotations are performed based on the contour regions, and the annotations are recorded in text. Feature vector tracking is performed on the annotations, wherein the feature vector may be a product type or a product name.

[0032] The feature vector is saved and a corresponding feature symbol is formed; based on the feature symbol, it is recorded in the contour area, and a regionalized display of the detection area with the feature vector is performed. At this time, local recognition of the contour area is achieved, and the recognition is focused on the corresponding annotation to quickly traverse the feature vector, and the feature vector is saved and a corresponding feature symbol is formed; based on the feature symbol, it is recorded in the contour area, and a regionalized display of the detection area with the feature vector is performed.

[0033] S13: highlighting text based on each of the detection areas, and determining corresponding feature types;

[0034] In the specific implementation process of the present invention, the specific steps may be: performing regional freezing based on each of the detection areas, and highlighting the feature vector; exporting the feature vector in a guided manner in the form of text, and displaying it as a feature symbol under normal circumstances; performing keyword traversal based on the text, and locating three adjacent words near the keyword, and forming a first search sentence with the three words; obtaining a noun based on the first search sentence, and determining the corresponding feature type based on the noun.

[0035] Among them, the feature vector is exported in a guided manner in the form of text, and is displayed as a feature symbol under normal circumstances. At this time, the feature vector contains a corresponding guided icon, and is revealed during the click process to determine the specific information of the corresponding target, and keyword traversal is performed based on the text, and the three adjacent words near the keyword are located, and the first search sentence is formed with the three words; nouns are obtained based on the first search sentence, and the corresponding feature types are determined based on the nouns, thereby realizing the query of the feature types of the product.

[0036] S14: traversing the measurement units corresponding to the feature types as keywords to determine the corresponding quantity units;

[0037] In the specific implementation process of the present invention, the specific steps may be: taking the measurement unit corresponding to the feature type as the second search sentence; traversing the nearby words of the feature type based on the second search sentence, and performing word matching to locate the position of the quantity unit; determining the corresponding quantity word according to the position, and determining the meaning of the quantity word based on appearance recognition, and forming a sentence with the measurement unit of quantity; extracting the sentence and outputting it in a separate table to form a corresponding product table containing the quantity.

[0038] Among them, the measurement unit corresponding to the feature type is used as the second search sentence, and the second search sentence and the first search sentence are combined for overall detection. At this time, the nearby words of the feature type are traversed based on the second search sentence, and the words are marked to locate the position of the quantity unit; the corresponding quantity word is determined according to the position, and the meaning of the quantity word is determined based on the appearance recognition, and a sentence with the measurement unit of quantity is formed to facilitate quick query of the sentence, and the sentence is extracted and output in a separate table to form a corresponding product table containing quantity, thereby realizing quick export of the product table.

[0039] S15: Outputting a demand table based on the feature type and the quantity unit, and forming an overall quantity table corresponding to the drawing;

[0040] In the specific implementation process of the present invention, the specific steps include: making a single association between the feature type and the corresponding quantity unit, and associating them in the form of a digital arrangement; determining the uniqueness of the feature type based on the association status of the feature type and the quantity unit, and annotating the type mark of each identifiable drawing in the association; outputting a demand table based on the association, and the table can contain multiple associations; each of the associations is aligned with the corresponding identifiable drawing, and integrated into an overall quantity table of the corresponding drawing.

[0041] Among them, the association is performed in the form of digital arrangement, and the association relationship between the feature type and the corresponding quantity unit is constructed. At this time, the uniqueness of the feature type is determined based on the association status of the feature type and the quantity unit, and the type mark of each identifiable drawing is annotated in the association, so as to facilitate data export based on the association.

[0042] A demand table is output based on the associations, and the table may contain multiple associations; each of the associations corresponds to the identifiable drawings and is integrated into an overall quantity table of the corresponding drawings.

[0043] S16: forming a preliminary procurement plan table according to the plurality of overall quantity tables obtained within a preset range, and performing sufficiency calculation on the preliminary procurement plan table to determine a final procurement plan table, wherein the final procurement plan table includes the preliminary procurement plan table and the supplementary quantity corresponding to the preliminary procurement plan table.

[0044] In the specific implementation process of the present invention, the specific steps include: forming a preliminary procurement plan table according to multiple overall quantity tables obtained within a preset range, wherein the preset range refers to a corresponding time range; classifying multiple overall quantity tables within the same time, and superimposing products of the same type to output the corresponding overall quantity of the product; forming a preliminary procurement plan table based on the aggregation of each product and the corresponding overall quantity, and sorting the preliminary procurement plan table based on the current time, and based on the corresponding associated purchasing merchants, wherein the purchasing merchants are derived based on a preset supply chain; performing a sufficient calculation on the preliminary procurement plan table to determine a final procurement plan table, wherein the sufficient calculation is arranged based on the preliminary procurement plan table in combination with the current work progress to supplement the original quantity, and the final procurement plan table includes the preliminary procurement plan table and the supplementary quantity corresponding to the preliminary procurement plan table.

[0045] Among them, the preset range refers to the corresponding time range; multiple overall quantity tables are classified within the same time, and products of the same type are superimposed to output the corresponding overall quantity of the product. At this time, products are superimposed based on time and type, and product planning within this period is planned. A preliminary procurement plan table is formed based on the collection of each of the products and the corresponding overall quantity, and the preliminary procurement plan table is sorted based on the current time and based on the corresponding related procurement merchants, so as to guide the association relationship with the procurement merchants and perform corresponding procurement guidance.

[0046] In addition, the abundance calculation can be statistically performed based on an artificial learning model, and the learning degree of the artificial learning model can be changed based on the adjustment of abundance parameters. At this time, the abundance calculation is arranged based on the initial procurement plan table in combination with the current work progress to supplement the original quantity. The final procurement plan table includes the initial procurement plan table and the supplementary quantity corresponding to the initial procurement plan table.

[0047] In addition, an association relationship is introduced based on the model framework of the abundant computing, so as to switch the abundant computing to perform learning switching for different scenarios.

[0048] In an embodiment of the present invention, through the method in the embodiment of the present invention, the identifiable drawings are adjusted based on the drawings to be detected, and the identifiable drawings are divided into regions to form detection areas with feature vectors. At this time, text is highlighted for each detection area, and each detection area can be independently detected synchronously or asynchronously, and the corresponding feature type is determined, and combined with the measurement unit as a keyword for traversal, the demand table output is clarified, so as to realize the overall output of the demand table under the separate detection of each detection area of ​​the drawings, thereby maintaining the accuracy of the demand table and improving the recognition of the drawings to be detected. In addition, a preliminary procurement plan table is formed according to the multiple overall quantity tables obtained within a preset range, and the preliminary procurement plan table is adequately calculated to determine the final procurement plan table, wherein the final procurement plan table includes the preliminary procurement plan table and the supplementary quantity corresponding to the preliminary procurement plan table.

[0049] Example

[0050] See also Figure 2 , Figure 2 It is a schematic diagram of the structural composition of a recognition system based on feature quantity slice recognition drawings in an embodiment of the present invention.

[0051] like Figure 2 As shown, a recognition system for identifying drawings based on feature quantity slices, the recognition system for identifying drawings based on feature quantity slices comprises:

[0052] Acquisition module 21: used for acquiring drawings to be detected, and adjusting identifiable drawings based on the drawings to be detected;

[0053] Division module 22: used for dividing the identifiable drawings into regions and forming detection regions with feature vectors;

[0054] Text module 23: used for highlighting text based on each of the detection areas and determining the corresponding feature type;

[0055] A traversal module 24 is used for traversing the measurement units corresponding to the feature types as keywords to determine the corresponding quantity units;

[0056] Table module 25: used to output a demand table based on the feature type and the quantity unit, and form an overall quantity table corresponding to the drawing;

[0057] Calculation module 26: used to form a preliminary procurement plan table according to the multiple overall quantity tables obtained within a preset range, and perform sufficient calculation on the preliminary procurement plan table to determine a final procurement plan table, wherein the final procurement plan table includes the preliminary procurement plan table and the supplementary quantity corresponding to the preliminary procurement plan table.

[0058] The present invention provides a method and system for identifying drawings based on feature quantity slicing, wherein identifiable drawings are adjusted based on the drawings to be detected, and the identifiable drawings are divided into regions to form detection regions with feature vectors. At this time, text is highlighted for each detection region, and each detection region can be independently detected synchronously or asynchronously, and the corresponding feature type is determined, and combined with the measurement unit as a keyword for traversal, the demand table output is clarified, thereby realizing the overall output of the demand table under the separate detection of each detection area of ​​the drawing, thereby maintaining the accuracy of the demand table and improving the recognition of the drawings to be detected.

[0059] Example

[0060] See also Figure 3 , refer to the following Figure 3 The electronic device 40 according to this embodiment of the present invention will be described. Figure 3 The electronic device 40 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0061] like Figure 3 As shown, the electronic device 40 is in the form of a general computing device. The components of the electronic device 40 may include but are not limited to: at least one processing unit 41, at least one storage unit 42, and a bus 43 connecting different system components (including the storage unit 42 and the processing unit 41).

[0062] The storage unit stores program codes, which can be executed by the processing unit 41, so that the processing unit 41 executes the steps according to various exemplary embodiments of the present invention described in the above “Embodiment Method” section of this specification.

[0063] The storage unit 42 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 421 and / or a cache memory unit 422 , and may further include a read-only memory unit (ROM) 423 .

[0064] The storage unit 42 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0065] Bus 43 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0066] The electronic device 40 may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 40, and / or any device that enables the electronic device 40 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 45. Furthermore, the electronic device 40 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 46. Figure 3 As shown, the network adapter 46 communicates with other modules of the electronic device 40 via the bus 43. It should be understood that although Figure 3 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 40, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0067] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0068] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. In addition, it stores computer program instructions, and when the computer program instructions are executed by a computer, the computer executes the above method.

[0069] In addition, the above is a detailed introduction to the recognition method and recognition system based on feature quantity slice recognition drawings provided in the embodiments of the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for identifying drawings based on feature quantity slices, characterized in that: include: Acquire a drawing to be detected, and adjust the identifiable drawing based on the drawing to be detected; Dividing the identifiable drawings into regions and forming detection regions with feature vectors; Performing text highlighting based on each of the detection areas and determining corresponding feature types; The measurement units corresponding to the feature types are traversed as keywords to determine the corresponding quantity units; including: Using the measurement unit corresponding to the feature type as the second search sentence; Based on the second search sentence, traverse nearby words of the feature category and perform word matching to locate the position of the quantity unit; Determine the corresponding quantity word according to the position, determine the meaning of the quantity word based on the shape recognition, and form a sentence with the measurement unit of the quantity; Extract the statements and output them in a separate table to form a corresponding product table containing quantities; Outputting a demand table based on the feature type and the quantity unit, and forming an overall quantity table corresponding to the drawing; A preliminary procurement plan table is formed according to the multiple overall quantity tables obtained within a preset range, and a sufficient calculation is performed on the preliminary procurement plan table to determine a final procurement plan table, wherein the final procurement plan table includes the preliminary procurement plan table and the supplementary quantity corresponding to the preliminary procurement plan table.

2. The method for identifying drawings based on feature quantity slices according to claim 1, characterized in that: The step of obtaining the drawing to be detected and adjusting the identifiable drawing based on the drawing to be detected includes: Collecting files to be detected, and determining the type of the files to be detected based on the suffixes of the files to be detected; The type of the document to be detected is selected as a drawing or a photo, and the document to be detected is a drawing to be detected; wherein the photo is blurred, and the outer contour is highlighted to form a line, and the bending line area is blurred again to adjust it to a straight line; Adjusting an adjustment state based on the drawing to be detected, and acquiring a recognition area in the adjustment state; Based on the ratio of the recognition area reaching 48% of the overall area of ​​the drawing to be detected, the recognition area is frozen, and the recognizable drawing is adjusted based on the drawing to be detected.

3. The method for identifying drawings based on feature quantity slices according to claim 2 is characterized in that: The step of dividing the identifiable drawings into regions and forming a detection region having a feature vector includes: Dividing the identifiable drawing into regions to form blank regions, outline regions and other regions, wherein the outline region is between the blank regions and the other regions; Traversing and marking the contour area, and recording the marking in text; Performing feature vector tracking on the annotation, wherein the feature vector is product type and product name; The feature vector is saved and a corresponding feature symbol is formed; Based on the feature symbol recorded in the contour area, a regionalized display of the detection area with the feature vector is performed.

4. The method for identifying drawings based on feature quantity slices according to claim 3 is characterized in that: The text highlighting based on each of the detection areas and determining the corresponding feature type include: Performing regional freeze based on each of the detection areas and highlighting feature vectors; The eigenvectors are exported in a guided manner as text, while they are displayed as eigensymbols in the normal state; Perform keyword traversal based on the text, locate three adjacent words near the keyword, and form a first search sentence with the three words; A noun is obtained based on the first search sentence, and a corresponding feature type is determined based on the noun.

5. The method for identifying drawings based on feature quantity slices according to claim 4 is characterized in that: The outputting of the demand table based on the feature type and the quantity unit and forming an overall quantity table corresponding to the drawing includes: The characteristic type and the corresponding quantity unit are singly associated, and the association is performed in the form of a numerical arrangement; The uniqueness of the feature type is determined based on the association state between the feature type and the quantity unit, and the type mark of each identifiable drawing is annotated in the association; A demand table is output based on the associations, and the table contains a plurality of associations; each of the associations corresponds to the identifiable drawings and is integrated into an overall quantity table of the corresponding drawings.

6. The method for identifying drawings based on feature quantity slices according to claim 5, characterized in that: The initial purchase plan table is formed according to the plurality of overall quantity tables obtained within the preset range, and the initial purchase plan table is subjected to sufficient calculation to determine the final purchase plan table, wherein the final purchase plan table includes the initial purchase plan table and the supplementary quantity corresponding to the initial purchase plan table, including: Forming a preliminary procurement plan table according to the plurality of overall quantity tables obtained within a preset range, wherein the preset range refers to a corresponding time range; Classifying a plurality of the overall quantity tables at the same time, and superimposing the products of the same type to output the corresponding overall quantity of the product; A preliminary purchase plan table is formed based on the aggregation of each of the products and the corresponding total quantity, and the preliminary purchase plan table is sorted based on the current time and based on the corresponding associated purchasers, wherein the purchasers are derived based on a preset supply chain; A sufficiency calculation is performed on the initial procurement plan table to determine the final procurement plan table, wherein the sufficiency calculation is arranged based on the initial procurement plan table in combination with the current work progress to supplement the original quantity, and the final procurement plan table includes the initial procurement plan table and the supplementary quantity corresponding to the initial procurement plan table.

7. The method for identifying drawings based on feature quantity slices according to claim 6, characterized in that: The initial purchase plan table is formed according to the plurality of overall quantity tables obtained within the preset range, and the initial purchase plan table is subjected to sufficient calculation to determine the final purchase plan table, wherein the final purchase plan table includes the initial purchase plan table and the supplementary quantity corresponding to the initial purchase plan table, and also includes: The sufficiency calculation is statistically performed based on an artificial learning model, and the learning degree of the artificial learning model is changed based on the adjustment of sufficiency parameters; The association relationship is introduced based on the model framework of the abundant computing, so as to switch the abundant computing to perform learning switching for different scenarios.

8. A system for identifying drawings based on feature quantity slices, characterized in that: The recognition system for identifying drawings based on feature quantity slices includes: Acquisition module: used for acquiring drawings to be detected, and adjusting identifiable drawings based on the drawings to be detected; Division module: used for dividing the identifiable drawings into regions and forming detection regions with feature vectors; Text module: used to highlight text based on each of the detection areas and determine the corresponding feature type; Traversal module: used to traverse the measurement units corresponding to the feature types as keywords to determine the corresponding quantity units; specifically: Using the measurement unit corresponding to the feature type as the second search sentence; Based on the second search sentence, traverse nearby words of the feature category and perform word matching to locate the position of the quantity unit; Determine the corresponding quantity word according to the position, determine the meaning of the quantity word based on the shape recognition, and form a sentence with the measurement unit of the quantity; Extract the statements and output them in a separate table to form a corresponding product table containing quantities; Table module: used for outputting a demand table based on the feature type and the quantity unit, and forming an overall quantity table of the corresponding drawing; Calculation module: used to form a preliminary procurement plan table according to the multiple overall quantity tables obtained within a preset range, and perform sufficient calculation on the preliminary procurement plan table to determine the final procurement plan table, wherein the final procurement plan table includes the preliminary procurement plan table and the supplementary quantity corresponding to the preliminary procurement plan table.

Images