Parts classification and processing method before assembly, system, electronic equipment and storage medium

Abstract

This application provides a method, system, electronic device, and storage medium for pre-assembly classification of parts, which acquires data of parts to be assembled; wherein the parts to be assembled include different types of parts that can be assembled together; the data is clustered using a clustering model to obtain clusters; labels are assigned to the data in each cluster to obtain labeled data; and the labeled data is classified using a classification model to obtain classification results indicating the mutual assembly of different types of parts. This solves the problem in the prior art where alignment deviations caused by dimensional differences during assembly lead to a decrease in product quality.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a method, system, electronic equipment and storage medium for classifying and processing parts before assembly. Background Art

[0002] A complete finished product is usually composed of many parts. Due to the process and production equipment, the product is usually divided into many parts and manufactured separately to produce various semi-finished products, and then the related semi-finished products are assembled into a complete finished product. After the semi-finished products are produced, they are not screened for size and are directly assembled into a product. This may cause alignment deviations due to size differences during assembly, resulting in reduced product quality. Summary of the invention

[0003] In view of this, it is necessary to provide a method, system, electronic device and storage medium for sorting and processing parts before assembly to solve the problem in the prior art that alignment deviations are caused by size differences during assembly, resulting in reduced product quality.

[0004] An embodiment of the present application provides a method for sorting and processing parts before assembly, comprising:

[0005] Acquire data of parts to be assembled; wherein the parts to be assembled include parts of different types that are assembled with each other;

[0006] Clustering the data using a clustering model to obtain clusters;

[0007] Setting labels for the data in each cluster to obtain labeled data;

[0008] The labeled data is classified using a classification model to obtain a classification result for indicating that different types of parts are assembled with each other.

[0009] According to one possible implementation of the present application, the method for classifying and processing parts before assembly further includes:

[0010] Acquiring training data of the different types of parts that are assembled with each other;

[0011] Clustering the training data using the clustering model to be trained to obtain various training clusters;

[0012] The clustering model to be trained is adjusted according to preset balance parameters and the various training clusters to obtain a clustering model, wherein the preset balance parameters are used to balance the amount of data in the various training clusters.

[0013] According to one possible implementation of the present application, the method for classifying and processing parts before assembly:

[0014] Setting labels for the training data of each training cluster to obtain labeled training data;

[0015] Using the classification model to be trained to classify the labeled training data to obtain a training classification result;

[0016] The classification model to be trained is adjusted according to preset classification parameters and the training classification results to obtain a classification model, wherein the preset classification parameters make the classification results of the different types of parts assembled with each other consistent.

[0017] According to one possible implementation of the present application, obtaining data of the parts to be assembled includes:

[0018] Reading the production data of a machine that produces the part to be assembled, so as to obtain the size data of the part to be assembled according to the production data;

[0019] Or, the size data of the parts to be assembled are obtained by measuring the size of the parts to be assembled.

[0020] According to one possible implementation of the present application, setting labels for the data in each cluster to obtain the labeled data includes:

[0021] Obtaining the standard part size corresponding to each cluster part;

[0022] Labels are set according to the size data of the parts in each cluster and the corresponding standard part size.

[0023] An embodiment of the present application provides a system for pre-assembly classification of parts, including a data acquisition module, a clustering module, a labeling module and a classification module;

[0024] The data acquisition module is used to acquire data of parts to be assembled; wherein the parts to be assembled include parts of different types that are assembled with each other;

[0025] The clustering module is used to cluster the data to obtain various clusters;

[0026] The label module is used to set labels for the data in each cluster to obtain data with labels;

[0027] The classification module is used to classify the labeled data using a classification model to obtain a classification result for indicating that different types of parts are assembled with each other.

[0028] According to one possible implementation of the present application, the pre-assembly classification processing system for parts further includes a training data acquisition module and a clustering model training module;

[0029] The training data acquisition module is used to acquire the training data of the different types of parts that are assembled with each other;

[0030] The clustering model training module is used to cluster the training data using the clustering model to be trained to obtain various training clusters, and adjust the clustering model to be trained according to preset balance parameters and the various training clusters to obtain a clustering model. The preset balance parameters are used to balance the amount of data in each training cluster.

[0031] According to one possible implementation of the present application, the pre-assembly classification processing system for parts further includes a training label module and a classification model training module;

[0032] The training label module is used to set labels for the training data of each training cluster to obtain labeled training data;

[0033] The classification model training module is used to classify the labeled training data using the classification model to be trained to obtain a training classification result, and to adjust the classification model to be trained according to preset classification parameters and the training classification result to obtain a classification model, wherein the preset classification parameters make the classification results of the different types of parts that are assembled together consistent.

[0034] An embodiment of the present application provides an electronic device, the electronic device comprising: one or more processors;

[0035] When one or more programs are executed by the one or more processors, the one or more processors implement the method for sorting parts before assembly as described above.

[0036] One embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for classifying and processing parts before assembly as described above is implemented.

[0037] The embodiments of the present application provide a method, system, electronic device and storage medium for pre-assembly classification of parts, which collects data of different types of parts to be assembled, performs preliminary division by clustering, obtains clusters, and sets labels for the data in each cluster. The classification module classifies the labeled data to obtain classification results for indicating the mutual assembly of different types of parts. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a block diagram of a parts pre-assembly classification and processing system according to one embodiment of the present application.

[0039] Figure 2 It is a schematic flow chart of a method for sorting and processing parts before assembly according to one embodiment of the present application.

[0040] Figure 3 It is a flow chart of a method for sorting and processing parts before assembly according to another embodiment of the present application.

[0041] Main component symbols

[0042] Computer 1

[0043] Parts pre-assembly sorting system 100

[0044] Data acquisition module 10

[0045] Clustering module 20

[0046] Label module 30

[0047] Classification module 40

[0048] Training data acquisition module 50

[0049] Clustering model training module 60

[0050] Training label module 70

[0051] Classification model training module 80

[0052] Display device 11

[0053] Memory 12

[0054] Processor 13

[0055] Communication unit 14

[0056] Host computer A 01

[0057] Host computer B 02

[0058] The following specific implementation methods will further illustrate the present application in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0060] Based on the implementations in this application, all other implementations obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0061] See also Figure 1An embodiment of the present application provides a parts pre-assembly classification processing system 100, including a data acquisition module 10, a clustering module 20, a label module 30, a classification module 40, a training data acquisition module 50, a clustering model training module 60, a training label module 70 and a classification model training module 80.

[0062] In one preferred embodiment, the parts pre-assembly classification processing system 100 runs in a computer 1, and the computer 1 also includes, but is not limited to, a display device 11, a memory 12, a processor 13, and a communication unit 14. The computer 1 is connected to the host computer of the production part through the communication unit 14. For example, the computer 1 can be connected to the host computer A01 of the surviving part A or the host computer B02 of the surviving part B through the communication unit 14.

[0063] In the embodiment of the present application, different production lines produce different types of parts, and these different types of parts need to undergo subsequent processes and processing, which are semi-finished products, and the finished product is the product obtained by assembling the corresponding different types of semi-finished products together. The parts pre-assembly classification processing system 100 is used to classify and process each semi-finished product before assembling the semi-finished products into finished products, so that the semi-finished products assembled together are suitable for each other, and the assembled products are qualified products.

[0064] According to one possible implementation of the present application, the parts pre-assembly classification processing system 100 trains the model through the training data acquisition module 50, the clustering model training module 60, the training label module 70 and the classification model training module 80, so that the trained model processes the data of the parts to be assembled.

[0065] The training data acquisition module 50 is used to acquire the training data of the different types of parts that are assembled with each other.

[0066] In the embodiment of the present application, the parts are different types of parts assembled into a finished product. The parts are assembled with each other into a complete finished product, or a semi-finished product. The parts can be two or more different types of parts.

[0067] In one possible implementation, during the data acquisition process, a threshold is defined as the minimum number of data items that should be accumulated at the beginning. The acquired data is divided into training data and test data according to the threshold as a criterion for modeling and testing. That is, when the total amount of data is less than the threshold, it is training data, and when it exceeds the threshold, it is test data.

[0068] The clustering model training module 60 is used to cluster the training data using the clustering model to be trained to obtain various training clusters, and adjust the clustering model to be trained according to preset balance parameters and the various training clusters to obtain a clustering model. The preset balance parameters are used to balance the amount of data in each training cluster.

[0069] In the implementation of the present application, the clustering model training module 60 clusters the obtained different types of part data to obtain various training clusters, and the various training clusters are obtained by clustering according to data similarity, thereby completing the preliminary division. Then, the clustering model to be trained is adjusted according to the preset balance parameter and the various training clusters to obtain a clustering model, and the ratio difference between the various training clusters is less than the preset balance parameter, so as to avoid the imbalance of the number of training clusters after clustering of different production lines on the parts pre-assembly classification processing system 100.

[0070] It is understood that the process of dividing a collection of physical or abstract objects into multiple classes consisting of similar objects is called clustering. The cluster generated by clustering is a collection of data objects that are similar to objects in the same cluster and different from objects in other clusters. This is how different types of parts are initially divided.

[0071] In one possible implementation, a distance formula from each data in the training cluster to the group center of each training cluster is calculated, such as Euclidean distance, Chabyshev distance, etc., and this distance is used for adjustment to redefine the clustering results of data that are closer to the center of other training clusters and farther from the original center, so as to achieve a difference in the number of data between each training cluster that is less than the preset balance parameter.

[0072] The training label module 70 is used to set labels for the training data of each training cluster to obtain labeled training data.

[0073] In the embodiment of the present application, for each training cluster, the training data in it is compared with the standard product size data produced by the production line corresponding to the data, and the corresponding label is set according to the comparison result. The labels of all training data in each training cluster are ordered labels.

[0074] The classification model training module 80 is used to classify the labeled training data using the classification model to be trained to obtain a training classification result, and adjust the classification model to be trained according to preset classification parameters and the training classification result to obtain a classification model, wherein the preset classification parameters make the classification results of the different types of parts assembled with each other consistent.

[0075] In the implementation of the present application, the clustering model training module 60 clusters the obtained different types of part data to obtain various training clusters, and the various training clusters are obtained by clustering according to data similarity, thereby completing the preliminary division. Then, the clustering model to be trained is adjusted according to the preset balance parameter and the various training clusters to obtain a clustering model, and the ratio difference between the various training clusters is less than the preset balance parameter, so as to avoid the imbalance of the number of clusters of different production lines on the parts pre-assembly classification processing system 100.

[0076] In one possible implementation, the classification training model finds a hyperplane that can segment the labeled data, and finds parameters to maximize the distance between the classified categories. The hyperplane is adjusted by the preset balance parameter to change the weight to achieve the problem of balancing the number of categories, so that the number of classification results of the parts that are assembled together is consistent.

[0077] The data acquisition module 10 is used to acquire data of parts to be assembled, wherein the parts to be assembled include parts of different types that are assembled with each other.

[0078] In one possible implementation, the computer 1 is connected to the host computer A01, host computer B02, etc. of different production lines through the communication unit 14, so that the parts pre-assembly classification processing system 100 obtains the parts data of each semi-finished product assembled into a finished product or semi-finished product.

[0079] In the embodiment of the present application, the parts to be assembled are different types of parts that are assembled into a finished product. The parts to be assembled are assembled with each other into a complete finished product, or a semi-finished product. The parts to be assembled can be two or more different types of parts.

[0080] The clustering module 20 is used to cluster the data to obtain clusters.

[0081] In the embodiment of the present application, the clustering module 20 uses a trained clustering model to cluster the obtained different types of part data to obtain clusters, thereby completing a preliminary division.

[0082] The label module 30 is used to set labels for the data in each cluster to obtain data with labels.

[0083] The classification module 40 is used to classify the labeled data using a classification model to obtain a classification result for indicating that different types of parts are assembled with each other.

[0084] In the embodiment of the present application, the classification module 40 classifies the labeled data using a trained classification model.

[0085] The memory 12 is used to store program codes. The memory 12 may be a circuit with storage function in an integrated circuit without a physical form, such as a memory stick, a TF card (Trans-flash Card), a smart media card (smart media card), a secure digital card (secure digital card), a flash memory card (flash card) and other storage devices. The memory 12 may communicate data with the processor 13 through the communication unit 14. The memory 12 may include the pre-assembly classification processing system 100 of parts.

[0086] The processor 13 may be a central processing unit (CPU), or other general-purpose processors 13, digital signal processors 13 (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor 13 may be a microprocessor 13, or the processor 13 may be any other conventional processor 13, etc. The processor 13 may call the program code stored in the memory 12 to execute related functions. For example, Figure 1 The various functional modules described are program codes stored in the memory 12 and executed by the processor 13 to implement a method for classifying and processing parts before assembly.

[0087] In one possible implementation, the functional module referred to in this application refers to a series of program instruction segments that can be executed by the processor 13 of the computer 1 and can complete fixed functions, which are stored in the memory 12 of the computer 1. Figure 2 The flowchart is described in detail.

[0088] See also Figure 2 , a schematic flow chart of a method for classifying and processing parts before assembly according to an embodiment of the present application. The method for classifying and processing parts before assembly is applied to a computer 1 .

[0089] The method for classifying and processing parts before assembly comprises the following steps:

[0090] Step S10: Acquire training data of the different types of parts that are assembled with each other.

[0091] In the embodiment of the present application, different types of parts to be assembled produced by different production lines can be assembled together to obtain a finished product or a semi-finished product.

[0092] In one possible implementation, the corresponding data can be obtained by continuously acquiring machine parameters thrown out by machines in different production lines or measurement data before the assembly station. For example, when etching ink flow channels, the size data of the flow channels can be calculated based on the etching time, the amount of etching liquid or other variables.

[0093] In the process of acquiring data, a first threshold is defined as the minimum number of data items that should be accumulated at the beginning. The acquired data will be divided into training data and test data according to the first threshold as a criterion for modeling and testing. That is, when the total amount of data is less than the first threshold, it is training data, and the training data is used to train the model. When the total amount of data exceeds the first threshold, it is test data, and the test data is used for testing.

[0094] Step S11: clustering the training data using the clustering model to be trained to obtain various training clusters.

[0095] Step S12: adjusting the cluster model to be trained according to preset balance parameters and the various training clusters to obtain a cluster model, wherein the preset balance parameters are used to balance the amount of data in the various training clusters.

[0096] In an embodiment of the present application, the clustering model may be a K-MEANS clustering algorithm, a mean shift clustering algorithm, a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm, etc., and the present application does not make any specific limitation on this.

[0097] In an embodiment of the present application, the preset balance parameter is a pre-set parameter. When the clustering model performs clustering, each training cluster is obtained according to the similarity of the data. The preset balance parameter is used to adjust the proportional difference in the number of each training cluster to avoid an unbalanced situation in the number of clusters of parts produced on different production lines.

[0098] In one possible implementation, a distance formula from each data in the training cluster to the group center of each training cluster is calculated, such as Euclidean distance, Chabyshev distance, etc. This distance is used for adjustment to redefine the clustering results of data that are closer to other group centers and farther from the original center, so as to achieve a difference in the number of data between each training cluster that is less than the preset balance parameter.

[0099] Step S13: setting labels for the training data of each training cluster to obtain labeled training data.

[0100] In the embodiment of the present application, for each training cluster, the training data in it is compared with the standard product size data produced by the production line corresponding to the data, and the corresponding label is set according to the comparison result. The labels of all training data in each training cluster are ordered labels.

[0101] Step S14: classify the labeled training data using the classification model to be trained to obtain a training classification result.

[0102] Step S15: adjusting the classification model to be trained according to preset classification parameters and the training classification results to obtain a classification model, wherein the preset classification parameters make the classification results of the different types of parts that are assembled with each other consistent.

[0103] In one possible implementation, the classification training model finds a hyperplane that can segment the labeled data, and finds parameters to maximize the distance between the classified categories. The hyperplane is adjusted by the preset balance parameter to change the weight to achieve the problem of balancing the number of categories, so that the number of classification results of the parts that are assembled together is consistent.

[0104] Step S16: Acquire data of parts to be assembled; wherein the parts to be assembled include parts of different types that are assembled with each other.

[0105] In one possible implementation, obtaining data of the parts to be assembled includes:

[0106] The production data of the machine that produces the part to be assembled is read to obtain the size data of the part to be assembled according to the production data, or the size data of the part to be assembled is obtained by measuring the size of the part to be assembled.

[0107] Step S17: clustering the data using a clustering model to obtain clusters.

[0108] In an embodiment of the present application, the acquired data includes data of different types of parts produced by different production lines. The obtained parts data are clustered through a clustering model, and clusters are divided according to data similarity. When the size data of different types of parts are quite different, clusters corresponding to different types of parts can be obtained.

[0109] In the embodiment of the present application, the clustering model is obtained after training through step S11 and step S12. After the clustering model divides the data, the amount of data in each cluster is balanced.

[0110] Step S18: Setting labels for the data in each cluster to obtain labeled data.

[0111] Please also read Figure 3 In at least one embodiment of the present invention, step S18 sets labels for the data in each cluster, and the data with labels includes:

[0112] Step S181: Obtain the standard part size corresponding to each cluster part.

[0113] In the embodiment of the present application, the parts produced by different production lines have their corresponding standard part sizes. After the division is performed in step S17 to obtain each cluster, the parts produced by different production lines are divided accordingly.

[0114] Step S182: setting labels according to the size data of the parts in each cluster and the corresponding standard part size.

[0115] In the embodiment of the present application, for each cluster, the training data in it is compared with the standard product size data produced by the production line corresponding to the data, and the corresponding label is set according to the comparison result. The labels of all training data in each cluster are ordered labels.

[0116] Step S19: using a classification model to classify the labeled data to obtain a classification result for indicating that different types of parts are to be assembled with each other.

[0117] In an embodiment of the present application, the classification model is obtained after training through steps S14 to S15, and the labeled data is classified by the classification model so that the classification of parts produced by different production lines is consistent according to pre-set parameters, and then different types of parts are instructed to be assembled with each other according to the classification results.

[0118] For example, three different production lines produce three different types of parts, namely part A, part B and part C. Two parts A, one part B and one part C can be assembled into a finished product. The sizes of the parts are all in line with the standard, but there are still small differences. In order to improve the quality, the parts are divided into several groups for assembly. The part data composed of parts A, parts B and parts C are clustered separately. If the parts are to be divided into three sizes, three clusters are constructed to obtain cluster A, cluster B and cluster C. The data of cluster A, cluster B and cluster C are compared according to the standard product size data corresponding to the production line of each part. The part size data of cluster A, cluster B and cluster C are arranged from small to large, so that the three clusters can be redefined as part labels for small size data, part labels for medium size data, and part labels for large size data. The classification model classifies the labeled data in cluster A, cluster B and cluster C so that the classification results of parts A, part B and part C are consistent. Parts A, part B and part C are divided into three categories, including data larger than the standard product size data, data smaller than the standard product size data and data equal to or smaller than the standard product size data. Among them, the number of each category of part A is twice that of parts B and part C. Therefore, parts A, part B and part C larger than the standard product size data can be assembled together, parts A, part B and part C smaller than the standard product size data can be assembled together, and parts A, part B and part C equal to the standard product size data can be assembled together, indicating that parts A, part B and part C with label 1 are transferred together, and parts A, part B and part C with label 2 are transferred together.

[0119] The embodiments of the present application provide a method, system, electronic device and storage medium for pre-assembly classification of parts, which collects data of different types of parts to be assembled, performs preliminary division by clustering, obtains clusters, and sets labels for the data in each cluster. The classification module classifies the labeled data to obtain classification results for indicating the mutual assembly of different types of parts.

[0120] The present invention also provides a storage medium. The storage medium is a computer-readable storage medium. The computer-readable storage medium stores computer instructions. The computer instructions can be stored in the memory 12 or the processor 13, and when executed by one or more processors 13, the method for pre-assembly classification of parts as described in the above method embodiment is implemented, which will not be repeated here.

[0121] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0122] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the modules, which is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or module can be electrical or other forms.

[0123] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0124] In addition, each functional module in each embodiment of the present invention may be integrated into one processor, or each module may exist physically separately, or two or more modules may be integrated into one module. The above integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0125] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0126] It should also be noted that, in this article, the term "includes" or "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0127] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for sorting and processing parts before assembly, characterized in that: include: Acquire data of parts to be assembled; wherein the parts to be assembled include different types of parts that are assembled into a finished product, and the data of the parts to be assembled include size data of the parts to be assembled; Clustering the data of the parts to be assembled using a clustering model to obtain clusters corresponding to each type of parts; Obtaining standard part sizes corresponding to each type of parts; For each cluster, the size data in it is compared with the size data of the standard products produced by the production line corresponding to the data, and the corresponding label is set according to the comparison result; The classification model is used to classify the labeled data to obtain classification results for various types of parts, wherein the classification results include data larger than standard product size, data smaller than standard product size, and data equal to standard product size. The classification model includes preset classification parameters, and the preset classification parameters make the classification results of different types of mutually assembled parts consistent.

2. The method for sorting and processing parts before assembly as claimed in claim 1, characterized in that: return include: Acquiring training data of the different types of parts that are assembled with each other; Clustering the training data using the clustering model to be trained to obtain various training clusters; The clustering model to be trained is adjusted according to preset balance parameters and the various training clusters to obtain a clustering model, wherein the preset balance parameters are used to balance the amount of data in the various training clusters.

3. The method for sorting and processing parts before assembly as claimed in claim 2, characterized in that: return include: Setting labels for the training data of each training cluster to obtain labeled training data; Using the classification model to be trained to classify the labeled training data to obtain a training classification result; The classification model to be trained is adjusted according to preset classification parameters and the training classification results to obtain a classification model.

4. The method for sorting and processing parts before assembly as claimed in claim 1, characterized in that: Place The data of the parts to be assembled are obtained as follows: Reading the production data of a machine that produces the part to be assembled, so as to obtain the size data of the part to be assembled according to the production data; Or, the size data of the parts to be assembled are obtained by measuring the size of the parts to be assembled.

5. A system for sorting and processing parts before assembly, characterized in that: Including data acquisition module Block, clustering module, labeling module and classification module; The data acquisition module is used to acquire data of the parts to be assembled; wherein the parts to be assembled include different types of parts that are assembled into a finished product, and the data of the parts to be assembled include size data of the parts to be assembled; The clustering module is used to cluster the data of the parts to be assembled to obtain clusters corresponding to each type of parts; The label module is used to obtain the standard part sizes corresponding to the various types of parts, and for each cluster, compare the size data therein with the standard product size data produced by the production line corresponding to the data, and set the corresponding label according to the comparison result; The classification module is used to classify the labeled data using a classification model to obtain classification results for various types of parts. The classification results include data that are larger than standard product size data, data that are smaller than standard product size data, and data that are equal to standard product size data. The classification model includes preset classification parameters, and the preset classification parameters make the classification results of different types of mutually assembled parts consistent.

6. The parts pre-assembly sorting and processing system as claimed in claim 5, characterized in that: return Including training data acquisition module and clustering model training module; The training data acquisition module is used to acquire the training data of the different types of parts that are assembled with each other; The clustering model training module is used to cluster the training data using the clustering model to be trained to obtain various training clusters, and adjust the clustering model to be trained according to preset balance parameters and the various training clusters to obtain a clustering model. The preset balance parameters are used to balance the amount of data in each training cluster.

7. The parts classification and processing system before assembly as claimed in claim 6, characterized in that: return Including training label module and classification model training module; The training label module is used to set labels for the training data of each training cluster to obtain labeled training data; The classification model training module is used to classify the labeled training data using the classification model to be trained to obtain a training classification result, and to adjust the classification model to be trained according to preset classification parameters and the training classification result to obtain a classification model.

8. An electronic device, characterized in that: The electronic device includes: one or more processors; When one or more programs are executed by the one or more processors, the one or more processors implement the method for sorting parts before assembly as claimed in any one of claims 1 to 4.

9. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for pre-assembly classification of parts as claimed in any one of claims 1 to 4.

Images