Method and system for establishing and verifying whole vehicle BOM (Bill of Materials)

Abstract

The invention discloses a finished vehicle BOM building verification method and system, and the method comprises the following steps: building a mature vehicle database, and training the sales features and BOM of orders; inputting a to-be-calculated order sales feature or a to-be-verified order sales feature and a BOM, and matching a sample most similar to the input order sales feature; obtaining differential sales characteristics of the order input in the step S2 and the most similar sample; querying a conforming sample, calculating a frequent item set mapped by the differential sales features, and prompting that resources are lacked when no conforming frequent item set exists; s4, performing addition and subtraction operation on the BOM of the most similar sample and the frequent item set obtained in the step S4 to form a whole vehicle BOM, if the order to be calculated is input in the step S2, directly outputting the built whole vehicle BOM, and if the order to be verified is input in the step S2, comparing the built whole vehicle BOM with the BOM of the order to be verified, and outputting a verification list; and after the newly established BOM meets the mature vehicle requirements of the S1 database, the BOM is put in storage for training and learning.

Description

Technical Field

[0001] The present application relates to the technical field of product BOM assembly verification, and in particular to a method and system for assembly verification of a complete vehicle BOM. Background Art

[0002] With the upgrading of consumption and the increasing diversification of market demand, in order to meet the personalized needs of users, companies have launched customized services and the number of products has increased rapidly. Taking heavy-duty commercial vehicles as an example, there are hundreds of millions of product configuration combinations. Currently, companies mainly rely on two modes to build BOMs, manual creation and creation using configuration BOMs or super BOM systems. In the case of complex products, numerous parts, multiple sources of data and information, and frequent changes, relying on manual BOM construction is time-consuming and labor-intensive, inefficient, and prone to errors such as multiple selections, missed selections, and wrong selections, with low accuracy.

[0003] Although configuration BOM and super BOM can automatically perform some logical judgments and configuration operations, they involve a large number of configuration rules and material data, which still require manual preliminary settings and subsequent continuous updates and maintenance, which are highly complex and prone to errors. Therefore, there is an urgent need for a BOM assembly and verification method based on AI technology. Summary of the invention

[0004] The present application provides a vehicle BOM assembly verification method and system to solve the above-mentioned problems.

[0005] On the one hand, the present application provides a method for verifying the assembly of a vehicle BOM, the method comprising the following steps:

[0006] Step S1: Establish a mature vehicle database and train the sales characteristics and BOM of the order;

[0007] Step S2: Input the sales features of the order to be calculated or the sales features of the order to be verified and the BOM, and match the sample that is most similar to the input sales features of the order;

[0008] Step S3: Obtain the difference sales features between the input order in step S2 and the most similar sample;

[0009] Step S4: query the matching samples, calculate the frequent itemsets of the difference sales feature mapping, and prompt the lack of resources when there is no matching frequent itemset;

[0010] Step S5: perform addition and subtraction operations on the BOM of the most similar sample and the frequent item sets obtained in step S4 to form the whole vehicle BOM. If the input of step S2 is the order to be calculated, the assembled whole vehicle BOM is directly output. If the input of step S2 is the order to be verified, the assembled whole vehicle BOM is compared with the BOM of the order to be verified, and the verification list is output;

[0011] Step S6: After the newly constructed BOM meets the mature vehicle requirements of the S1 database, it is put into the database for training and learning.

[0012] In one implementation of the present application, step S1 specifically includes: obtaining sales characteristics and BOM information of valid orders of specified models within a specified time period, screening and cleaning, establishing a mature vehicle database of specified models, and training and learning the data in the database.

[0013] In one implementation of the present application, step S2 specifically includes: when the designer receives an order requirement, he converts it into a standard sales feature language according to the requirement description as input information, and uses the maximum similarity model to find the most similar order sample in the database built in step S1. For the BOM newly created by other means, when it is upgraded, the sales characteristics and BOM of the order are used as input and verified in this model.

[0014] In one implementation of the present application, step S4 specifically includes: screening samples containing a certain differential sales feature, calculating the frequent item sets mapped by the differential sales feature through the category prediction model and the frequent item set model, and when there is no frequent item set that matches the differential sales feature mapping in the data in the library, prompting the designer that there is a lack of resources.

[0015] In one implementation of the present application, the step S5 specifically includes: obtaining the whole vehicle BOM of the most similar sample, adding the frequent item sets corresponding to the differential sales features in the input order, and subtracting the frequent item sets corresponding to the differential sales features in the most similar sample to form the whole vehicle BOM. If the input of step S2 is an order to be calculated, the assembled whole vehicle BOM is directly output; if the input of step S2 is an order to be verified, the assembled whole vehicle BOM is compared with the BOM of the order to be verified, and a verification list is output.

[0016] In one implementation of the present application, in step S4, the method for calculating frequent item sets includes:

[0017] Step S41: Calculate the material categories affected by the different sales characteristics through the category prediction model;

[0018] Step S42: Filter samples containing a certain differential sales feature, calculate frequent itemsets of the differential sales feature through a frequent itemset model, and obtain material categories of the frequent itemsets;

[0019] Step S43: Compare the material categories of the multiple groups of frequent item sets calculated in step S42 with the material categories affected by the different sales characteristics predicted in step S41, and filter out similar frequent item sets;

[0020] Step S44: reverse matching the samples containing the frequent itemsets filtered out in step S43, and obtaining their sales features;

[0021] Step S45: Filter the samples matched in step S44 to find the sample with the most similar sales feature to the most similar sample obtained in step S2, and obtain the frequent item set corresponding to the sample.

[0022] On the other hand, the present application also provides a vehicle BOM assembly verification system, the system comprising:

[0023] Basic data processing module, used to screen and clean basic data;

[0024] Model training and optimization module, used to train data in the mature vehicle database and optimize models;

[0025] The algorithm application module is used to generate the vehicle BOM of the order to be calculated or to verify the order to be inspected based on the trained model and generate a verification list;

[0026] The interaction and feedback module is used to receive designer requirements and designer's feedback on generated results.

[0027] In one implementation of the present application, the basic data processing module is used to obtain the sales characteristics and BOM information of valid orders of specified models within a specified time period, screen and clean them, eliminate bad data, and supplement missing information to provide basic data support for the system; the model training and optimization module is used to train data in a mature vehicle database through algorithms such as deep learning, so that the model can learn and master data patterns, while continuously optimizing the model to improve accuracy.

[0028] In one implementation of the present application, the algorithm application module is used to generate a vehicle BOM for the order to be calculated or to verify the order to be inspected based on the trained model through algorithm models such as the maximum similarity model, category prediction model, and frequent item set model to generate a verification list.

[0029] In one implementation of the present application, the interaction and feedback module is used to receive the sales characteristics of the order to be calculated or the sales characteristics and BOM of the order to be verified input by the designer, and the designer's modification feedback on the calculated vehicle BOM or the BOM of the order to be verified.

[0030] The present application provides a method and system for verifying the assembly of a complete vehicle BOM. Through training and learning of historical data, after inputting order sales features, the most similar samples and frequent item sets of different sales features can be calculated, and the complete vehicle BOM can be automatically assembled. At the same time, the BOM assembled by other means can be verified, thereby improving the efficiency and accuracy of the BOM of large-scale customized products. The system also has closed-loop learning capabilities and can regularly train and optimize the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0032] Figure 1 A flow chart of a vehicle BOM assembly verification method provided in an embodiment of the present application;

[0033] Figure 2 A flowchart of a frequent itemset calculation method for differential sales feature mapping provided in an embodiment of the present application;

[0034] Figure 3 A schematic diagram of a vehicle BOM assembly verification system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0036] The embodiment of the present application provides a method and system for assembling and verifying a complete vehicle BOM. The technical solution proposed in the embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0037] Example 1

[0038] Figure 1 A flow chart of a vehicle BOM assembly verification method provided in an embodiment of the present application. Figure 1 As shown, the method mainly includes the following steps:

[0039] Step S1: Establish a mature vehicle database and train the sales characteristics and BOM of the order.

[0040] In this embodiment, the sales characteristics and BOM information of valid orders of a specified model within a specified time period are first obtained, screened and cleaned, a mature vehicle database of the specified model is established, and then training and learning are performed on the data in the database.

[0041] Step S2: Input the order sales features to be calculated or the order sales features to be verified and the BOM, and match the sample that is most similar to the input order sales features.

[0042] In this embodiment, when the designer receives an order requirement, he first converts it into a standard sales feature language based on the requirement description as input information, and then uses the maximum similarity model to find the most similar order sample in the database built by S1. For the BOM newly created by other means, when it is upgraded, the sales characteristics and BOM of the order are used as input and verified in this model.

[0043] Step S3: Obtain the difference sales features between the input order in step S2 and the most similar sample.

[0044] In this embodiment, the sales features of the input order and the most similar sample are compared, and the sales features that do not appear repeatedly are the differential sales features.

[0045] Step S4: Query the matching samples, calculate the frequent itemsets of the difference sales feature mapping, and indicate the lack of resources when there is no matching frequent itemset.

[0046] In this embodiment, samples containing a certain differential sales feature are first screened, and then the frequent itemsets mapped by the differential sales feature are calculated through the category prediction model and the frequent itemset model. When there is no frequent itemset matching the differential sales feature mapping in the database data, the designer is prompted with a lack of resources.

[0047] Step S5: Perform addition and subtraction operations on the BOM of the most similar sample and the frequent item sets obtained in step S4 to form the BOM of the whole vehicle. If the input of step S2 is an order to be calculated, the assembled BOM of the whole vehicle is directly output. If the input of step S2 is an order to be verified, the assembled BOM of the whole vehicle is compared with the BOM of the order to be verified, and the verification list is output.

[0048] In this embodiment, the whole vehicle BOM of the most similar sample is first obtained, and then the BOM is added and subtracted, adding "the frequent item sets corresponding to the different sales features in the input order" and subtracting "the frequent item sets corresponding to the different sales features in the most similar sample" to finally form the whole vehicle BOM. If the S2 input is the order to be calculated, the assembled whole vehicle BOM is directly output; if the S2 input is the order to be verified, the assembled whole vehicle BOM is compared with the BOM of the order to be verified, and the verification list is output.

[0049] Step S6: After the newly constructed BOM meets the mature vehicle requirements of the S1 database, it is put into the database for training and learning.

[0050] In this embodiment, when the newly assembled BOM has been verified by vehicle installation, released for mass production, and meets the mature vehicle requirements of the S1 database, it enters the database for training and learning.

[0051] like Figure 2 As shown, the calculation method of the frequent item set in step S4 includes the following steps:

[0052] Step S41: Calculate the material categories affected by the different sales characteristics through the category prediction model.

[0053] In this embodiment, the differential sales obtained in step S3 is input into the category prediction model to predict the material category affected by the differential sales characteristics.

[0054] Step S42: Calculate frequent itemsets of different sales features through the frequent itemset model, and obtain the material categories of the frequent itemsets.

[0055] In this embodiment, samples containing a certain differential sales feature are first screened in the database in step S1, and then the frequent itemsets are calculated through the frequent itemset model to obtain multiple groups of frequent itemsets mapped by the differential sales feature, and the material categories of the frequent itemsets are obtained.

[0056] Step S43: Compare the material categories of the multiple groups of frequent item sets calculated in step S42 with the material categories affected by the different sales characteristics predicted in step S41, and filter out similar frequent item sets.

[0057] In this embodiment, the difference between the material categories of the multiple groups of frequent item sets obtained in step S42 and the material categories affected by the different sales characteristics predicted in step S41 is first calculated. Taking into account the error of the category prediction model, the difference threshold is relaxed to 1, and frequent item sets with a difference less than or equal to 1 are screened.

[0058] Step S44: reversely match the samples containing the frequent itemsets filtered out in step S43, and obtain their sales features.

[0059] In this embodiment, the frequent itemsets screened out in step S43 are first reverse matched to find samples containing the frequent itemsets, and then the sales features of the samples are obtained.

[0060] Step S45: Filter the samples matched in step S44 to find the sample with the most similar sales feature to the most similar sample obtained in step S2, and obtain the frequent item set corresponding to the sample.

[0061] In this embodiment, the similarity between the sales features of the sample matched in step S44 and the sales features of the most similar sample obtained in step S2 is first determined, and then the most similar sample is selected, and the frequent item sets corresponding to the sample are obtained, that is, the frequent item sets of the difference sales feature mapping.

[0062] Example 2

[0063] The above is a vehicle BOM assembly verification method provided by an embodiment of the present application. Based on the same inventive concept, an embodiment of the present application also provides a vehicle BOM assembly verification system. Figure 3 A diagram of a vehicle BOM assembly verification system provided in an embodiment of the present application, such as Figure 3As shown, the system mainly includes: a basic data processing module 301, which is used to screen and clean the basic data.

[0064] The basic data processing module 301 described in this embodiment is used to obtain the sales characteristics and BOM information of valid orders for a specified vehicle model within a specified time period according to the established data screening rules and data quality judgment rules, and perform screening and cleaning to eliminate bad data and supplement missing information, so as to provide basic data support for the system.

[0065] The model training and optimization module 302 is used to train the data in the mature vehicle database and optimize the model.

[0066] The model training and optimization module 302 described in this embodiment is used to train the data in the mature vehicle database through algorithms such as deep learning, so that the model can learn and master the data rules, and continuously optimize the model to improve the accuracy.

[0067] The algorithm application module 303 is used to generate the vehicle BOM of the order to be calculated or to verify the order to be inspected based on the trained model and generate a verification list.

[0068] The algorithm application module 303 described in this embodiment is used to generate a vehicle BOM for the order to be calculated or to verify the order to be inspected based on the trained model through algorithm models such as the maximum similarity model, the category prediction model, and the frequent item set model, and generate a verification list.

[0069] The interaction and feedback module 304 is used to receive designer requirements and designer feedback on generated results.

[0070] The interaction and feedback module 304 in this embodiment is used to receive the sales characteristics of the order to be calculated or the sales characteristics and BOM of the order to be verified input by the designer, and the designer's modification feedback on the calculated vehicle BOM or the BOM of the order to be verified.

[0071] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0072] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0073] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for verifying the assembly of a complete vehicle BOM, characterized in that: The method comprises the following steps: Step S1: Establish a mature vehicle database and train the sales characteristics and BOM of the order; Step S2: Input the sales features of the order to be calculated or the sales features of the order to be verified and the BOM, and match the sample that is most similar to the input sales features of the order; Step S3: Obtain the difference sales features between the input order in step S2 and the most similar sample; Step S4: query the matching samples, calculate the frequent itemsets of the difference sales feature mapping, and prompt the lack of resources when there is no matching frequent itemset; Step S5: perform addition and subtraction operations on the BOM of the most similar sample and the frequent item sets obtained in step S4 to form the whole vehicle BOM. If the input of step S2 is the order to be calculated, the assembled whole vehicle BOM is directly output. If the input of step S2 is the order to be verified, the assembled whole vehicle BOM is compared with the BOM of the order to be verified, and the verification list is output; Step S6: After the newly constructed BOM meets the mature vehicle requirements of the S1 database, it is put into the database for training and learning.

2. A vehicle BOM assembly verification method according to claim 1, characterized in that: The step S1 specifically includes: obtaining sales characteristics and BOM information of valid orders of a specified model within a specified time period, screening and cleaning, establishing a mature vehicle database of the specified model, and training and learning the data in the database.

3. A vehicle BOM assembly verification method according to claim 1, characterized in that: The step S2 specifically includes: when the designer receives an order requirement, he converts it into a standard sales feature language according to the requirement description as input information, and uses the maximum similarity model to find the most similar order sample in the database built in step S1. For the BOM newly created by other means, when it is upgraded, the sales features and BOM of the order are used as input and verified in this model.

4. A vehicle BOM assembly verification method according to claim 1, characterized in that: Step S4 specifically includes: screening samples containing a certain differential sales feature, calculating the frequent itemsets mapped by the differential sales feature through the category prediction model and the frequent itemset model, and when there is no frequent itemset matching the differential sales feature mapping in the database data, prompting the designer that there is a lack of resources.

5. A vehicle BOM assembly verification method according to claim 1, characterized in that: The step S5 specifically includes: obtaining the whole vehicle BOM of the most similar sample, adding the frequent item sets corresponding to the different sales features in the input order, and subtracting the frequent item sets corresponding to the different sales features in the most similar sample to form the whole vehicle BOM. If the input of step S2 is the order to be calculated, the assembled whole vehicle BOM is directly output; if the input of step S2 is the order to be verified, the assembled whole vehicle BOM is compared with the BOM of the order to be verified, and a verification list is output.

6. A vehicle BOM assembly verification method according to claim 1, characterized in that: In step S4, the calculation method of frequent item sets includes: Step S41: Calculate the material categories affected by the different sales characteristics through the category prediction model; Step S42: Filter samples containing a certain differential sales feature, calculate frequent itemsets of the differential sales feature through a frequent itemset model, and obtain material categories of the frequent itemsets; Step S43: Compare the material categories of the multiple groups of frequent item sets calculated in step S42 with the material categories affected by the different sales characteristics predicted in step S41, and filter out similar frequent item sets; Step S44: reverse matching the samples containing the frequent itemsets filtered out in step S43, and obtaining their sales features; Step S45: Filter the samples matched in step S44 to find the sample with the most similar sales feature to the most similar sample obtained in step S2, and obtain the frequent item set corresponding to the sample.

7. A vehicle BOM assembly verification system, characterized in that: The system comprises: Basic data processing module, used to screen and clean basic data; Model training and optimization module, used to train data in the mature vehicle database and optimize the model; The algorithm application module is used to generate the vehicle BOM of the order to be calculated or to verify the order to be inspected based on the trained model and generate a verification list; The interaction and feedback module is used to receive designer requirements and designer's feedback on generated results.

8. A vehicle BOM assembly verification system according to claim 7, characterized in that: The basic data processing module is used to obtain the sales characteristics and BOM information of valid orders of specified models within a specified time period, screen and clean them, eliminate bad data, and supplement missing information to provide basic data support for the system; the model training and optimization module is used to train data in a mature vehicle database through algorithms such as deep learning, so that the model can learn and master data patterns, while continuously optimizing the model to improve accuracy.

9. A vehicle BOM assembly verification system according to claim 7, characterized in that: The algorithm application module is used to generate a vehicle BOM for the order to be calculated or to verify the order to be inspected and generate a verification list based on the trained model through algorithm models such as the maximum similarity model, the category prediction model, and the frequent item set model.

10. A vehicle BOM assembly verification system according to claim 7, characterized in that: The interaction and feedback module is used to receive the sales characteristics of the order to be calculated or the sales characteristics and BOM of the order to be verified input by the designer, and the designer's modification feedback on the calculated vehicle BOM or the BOM of the order to be verified.

Images