Contribution degree-based bad root cause analysis method and system
Through the poor root cause analysis method based on contribution degree, the contribution rate of the production path combination in the bad rate is calculated, which solves the problem of inaccurate analysis results of existing methods when processing complex production data, and achieves a more accurate root cause of process defects Identification and multi-dimensional analysis.
Patent Information
- Application Number
- CN202411426844.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-14
- Publication Date
- 2025-02-07
AI Technical Summary
The existing poor root cause analysis methods are not accurate or misleading when processing complex related production process data, and are difficult to meet comprehensive and reproducible standards.
By analyzing the root cause of the contribution degree based on the problem, the product defect rate and the defect rate under the combination of the production path is calculated by obtaining and pre-processing the original processing data of the product, and then the contribution rate of each production path combination in the defect rate is calculated. Quantitatively evaluate the impact of different production path combinations on product adverse events.
More accurately identify potential process defect root causes, provide process defect root causes analysis in different dimensions, reduce data scale, avoid high computational costs of establishing fitted models, and be interpretable and adaptable.
Smart Images
Figure CN119398794A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of defect root cause analysis, and in particular to a defect root cause analysis method and system based on contribution. Background Art
[0002] In modern industrial production, the smooth operation of each production line site or equipment directly determines the overall production efficiency and the quality level of the final product. When product quality problems occur, it is crucial to trace their root causes. This tracing process is called root cause analysis, and its core lies in identifying and understanding the specific production line or equipment problems that cause quality problems.
[0003] Root cause analysis is not only a means to solve current problems, but also a key strategy to prevent future problems. By deeply analyzing production data, monitoring equipment operating status and collecting quality feedback, companies can quickly locate the source of problems and take effective measures to repair and improve them. This systematic approach not only helps to improve product quality and production efficiency, but also helps to optimize resource utilization and reduce production costs. By continuously optimizing the root cause analysis process, companies can establish a robust quality management system to ensure the production of products that meet high standards, thereby enhancing market competitiveness.
[0004] However, existing root cause analysis methods face some limitations and shortcomings in modern industrial production, which are particularly significant in large-scale production environments. On the one hand, traditional statistical analysis methods usually rely on specific data distribution assumptions, are inefficient when processing large-scale data, and require complex data preprocessing steps. These methods may be unable to cope with complex and correlated production process data, resulting in inaccurate or misleading analysis results. On the other hand, although manual experience judgment can provide valuable insights in some cases, they are easily affected by individual subjective biases and experience levels, lacking objectivity and consistency. This makes the results of root cause analysis of defects vary from person to person, making it difficult to achieve comprehensive and reproducible standards. In addition, existing methods also face challenges in adapting to different production environments and handling diverse defect types. With the development of manufacturing technology and the complexity of production processes, more flexible and intelligent analysis methods are needed to meet emerging production needs and technical challenges. Summary of the invention
[0005] The present invention provides a defect root cause analysis method and system based on contribution, which solves the problem that the existing defect root cause location method is prone to inaccurate analysis results when processing complex and correlated production process data.
[0006] In a first aspect, an embodiment of the present invention provides a method for analyzing root causes of failures based on contribution, the method comprising the following process:
[0007] Obtain the original processing data of the product and pre-process the original processing data;
[0008] Calculate the defect rate based on the pre-processed raw processing data to obtain the product defect rate;
[0009] Based on the pre-processed raw processing data, production path identification and production path combination are performed to obtain product history data;
[0010] Data splicing of product defect rate and product history data to construct the defect rate under each production path combination;
[0011] Calculate the contribution rate based on the defective rate under each production path combination to obtain the contribution rate of each production path combination in the defective rate;
[0012] The contribution rate of each production path combination to the defect rate is sorted and screened to obtain the suspected defect root cause.
[0013] In the above embodiment, the present invention adopts the method of calculating the contribution rate to quantitatively evaluate the influence of different production path combinations on product defects in the entire processing process, and calculates the marginal contribution of a single production path node through different production path combinations, and then determines the suspicious nodes that cause defects, thereby more accurately identifying the potential root causes of process defects, and solving the problem that the existing root cause location method is prone to inaccurate analysis results when processing complex and related production process data.
[0014] As some optional implementation modes of the present application, the original processing data of the product includes the production path data of the product, the total number of products and the number of abnormal products.
[0015] As some optional implementation methods of the present application, the calculation formula of the product defect rate is as follows:
[0016]
[0017] Among them, ρ represents the product defect rate, n1 represents the total number of products, and n represents the number of abnormal products.
[0018] As some optional implementations of the present application, the process of performing production path identification and production path combination based on the pre-processed original processing data to obtain product history data is as follows:
[0019] Performing production path identification and production path combination based on production path data of each product, wherein the production path data includes production path nodes, node production processing time, and node production waiting time;
[0020] A structured data model is constructed based on the production path data of the production path identifier and the production path combination, and the product history data of each product is queried and acquired based on the structured data model.
[0021] In the above embodiment, the present invention can use product history data for quality control and process improvement. By analyzing the performance of products at different sites, chambers and equipment, possible problems or optimization opportunities can be identified, helping production management teams and decision makers understand key information and trends in the production process, thereby improving production efficiency and product quality.
[0022] As some optional implementation methods of the present application, the process of concatenating product defect rate and product history data to construct the defect rate under each production path combination is as follows:
[0023] The unique identifier in the production path identification process is used as the association key;
[0024] The product defect rate and product history data are concatenated based on the association key to construct the defect rate under each production path combination.
[0025] In the above embodiment, the present invention can ensure that the production path combination information and detailed information of the defective rate of the product history data are retained after data splicing by performing data splicing on the product defective rate and the product history data.
[0026] As some optional implementation modes of the present application, the contribution rate calculation is implemented by using the benefit distribution method in cooperative game.
[0027] In the above embodiments, the advantage of the benefit distribution method in cooperative game adopted by the present invention is that it can comprehensively consider the contributions of different production path combinations, regardless of the complexity of the production path combinations, which makes it suitable for various production environments and complex process flow analysis.
[0028] As some optional implementations of the present application, the contribution rate is calculated based on the defective rate under each production path combination to obtain the contribution rate of each production path combination in the defective rate. The process is as follows:
[0029] Obtain all production path combinations of cooperative games to build a cooperative game system;
[0030] For the defect rate under each production path combination in the cooperative game system, calculate the marginal contribution of each production path combination;
[0031] The boundary contribution of each production path combination is weighted averaged to obtain the contribution rate of each production path combination in the defect rate.
[0032] In the above embodiment, in order to accurately measure the contribution rate of each production path combination, the present invention needs to take into account all possible permutations and combinations, which is the basis for using the benefit allocation method in the cooperative game. By averaging these marginal contributions, the contribution rate of each production path combination can be obtained, thereby determining its contribution to the overall product defect rate.
[0033] As some optional implementation methods of the present application, the contribution rate of each production path combination in the defect rate is sorted and screened to obtain the suspected defect root cause as follows:
[0034] The production path combinations are ranked according to the contribution rate of each production path combination in the defect rate, and several production path combinations with the highest ranking are selected as alternative production path combinations;
[0035] The production path nodes, node production processing time and node production waiting time corresponding to the alternative production path combinations are screened for suspicious root causes to obtain the suspected defective root causes.
[0036] In the above embodiment, after obtaining the contribution rate of each production path combination in the defective rate, the present invention sorts the path combinations according to the contribution rate, selects the top-ranked path combinations as the paths with high contribution rates to the product defective rate, and determines the combination that has the greatest impact on the product defective rate.
[0037] In a second aspect, the present invention provides a contribution-based root cause analysis system, the system comprising:
[0038] A data acquisition unit, the data acquisition unit is used to acquire original processing data of the product and pre-process the original processing data;
[0039] A defect rate calculation unit, wherein the defect rate calculation unit performs defect rate calculation based on the pre-processed original processing data to obtain a product defect rate;
[0040] A history data acquisition unit, wherein the history data acquisition unit performs production path identification and production path combination based on the pre-processed original processing data to obtain product history data;
[0041] A data splicing unit, the data splicing unit is used to perform data splicing on the product defect rate and the product history data to construct the defect rate under each production path combination;
[0042] A contribution rate calculation unit, wherein the contribution rate calculation unit performs contribution rate calculation based on the defective rate under each production path combination to obtain the contribution rate of each production path combination in the defective rate;
[0043] A suspected root cause locating unit is used to sort and screen the contribution rate of each production path combination in the defect rate to obtain the suspected defect root cause.
[0044] In a third aspect, the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the contribution-based root cause analysis method when executing the computer program.
[0045] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the contribution-based defect root cause analysis method is implemented.
[0046] The beneficial effects of the present invention are as follows:
[0047] 1. The present invention can quantitatively evaluate the degree of influence of different production path combinations on product defects in the entire processing process by calculating the contribution rate, calculate the marginal contribution of a single production path node through different production path combinations, and then determine the suspicious nodes that cause defects, thereby more accurately identifying the potential root causes of process defects.
[0048] 2. The present invention provides root cause analysis of process defects in different dimensions. The root cause of product defects is located from the site level to the equipment level, making the root cause location more intuitive and easy to analyze, reducing the data scale. Traditional methods generally give the correlation coefficient or feature importance of the fitting model output, such as statistical regression models, machine learning models, etc. These methods rely on good data sources and a high degree of fitting. The present invention does not need to establish any fitting model, thereby avoiding high computing costs.
[0049] 3. The present invention analyzes the contribution rate of different production combination paths to the overall product defects from the perspective of the full history of product production, and can analyze the correlation of the effects of different production path combinations on product defects, that is, how they work together to cause product defects.
[0050] 4. The contribution rate calculation logic of the present invention is simple and feasible, the calculation method is simple, the calculation principle is clear, and it is explainable. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0052] Figure 1 is a schematic diagram of the computer device structure of the hardware operating environment described in the embodiment of the present invention;
[0053] Figure 2 is a flow chart of a defect root cause analysis method based on contribution according to an embodiment of the present invention;
[0054] Figure 3 It is a structural block diagram of the contribution-based defect root cause analysis method described in an embodiment of the present invention. DETAILED DESCRIPTION
[0055] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0056] In order to solve the problem that the existing defect root cause location method is prone to inaccurate analysis results when processing complex and related production process data. The embodiment of the present invention provides a defect root cause analysis method and system based on contribution. Before introducing the specific technical solution of the present application, the hardware operating environment involved in the embodiment of the present application is first introduced.
[0057] See also Figure 1 , Figure 1 The figure is a schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present invention.
[0058] like Figure 1 As shown, the computer device may include: a processor, such as a central processing unit (CPU), a communication bus, a user interface, a network interface, and a memory. Among them, the communication bus is used to realize the connection and communication between these components. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), and optionally, the user interface may also include a standard wired interface and a wireless interface. The network interface may be a wired interface or a wireless interface (such as a wireless fidelity interface). The memory may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory may optionally be a storage device independent of the aforementioned processor.
[0059] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the computer device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.
[0060] like Figure 1As shown, the memory as a storage medium may include an operating system module, a network communication module, a user interface module and a data storage module.
[0061] exist Figure 1 In the computer device shown, the network interface is mainly used for data communication with the network server; the user interface is mainly used for data interaction with the user; the processor and memory in the computer device of the present application can be set in the computer device, and the computer device calls the contribution-based root cause analysis system stored in the data storage module through the processor, and executes the contribution-based root cause analysis method provided in the embodiment of the present application.
[0062] Based on the hardware environment of the aforementioned embodiment, the embodiment of the present application provides a method for analyzing the root cause of a defect based on contribution, please refer to Figure 2 , Figure 2 The flowchart of the contribution-based root cause analysis method is as follows:
[0063] (1) Obtain the original processing data of the product and preprocess the original processing data.
[0064] In an embodiment of the present invention, the original processing data includes but is not limited to production path data, the total number of products and the number of abnormal products in the product production process; at the same time, the original processing data may also include the operating status of the equipment and the product quality.
[0065] In the field of industrial manufacturing, since the original processing data of products has the characteristics of high process parameter dimensions, complex correlations between process parameters, and complex process flows, after obtaining the original processing data of products, the original processing data needs to be preprocessed to ensure the feasibility and accuracy of large-scale process data analysis.
[0066] Specifically, the method of preprocessing the original processed data includes but is not limited to data cleaning, wherein the process of data cleaning is as follows:
[0067] (1.1) Analyze the number of repetitions of the same product processing records in the original processing data and delete the identical processing records.
[0068] (1.2) Eliminate the original processed data with many missing values.
[0069] (1.3) Eliminate the original processed data containing outliers.
[0070] (2) Calculate the defect rate based on the preprocessed raw processing data to obtain the product defect rate.
[0071] In the embodiment of the present invention, the calculation formula of the product defect rate is as follows:
[0072]
[0073] Among them, ρ represents the product defect rate, n1 represents the total number of products, and n represents the number of abnormal products.
[0074] (3) Based on the preprocessed raw processing data, production path identification and production path combination are performed to obtain product history data.
[0075] In an embodiment of the present invention, the process of identifying and combining production paths based on pre-processed raw processing data is as follows:
[0076] (3.1) Performing production path identification and production path combination based on the production path data of each product, wherein the production path data includes production path nodes, node production processing time, and node production waiting time; the production path nodes include but are not limited to product production sites, chambers, and equipment, etc.
[0077] (3.2) A structured data model is constructed based on the production path data of the production path identifier and the production path combination, and the product history data of each product is obtained by querying the structured data model.
[0078] In an embodiment of the present invention, the product history data of each product can be obtained through a structured data model, and by performing quality control and process improvement on the product history data, and by analyzing the performance of each product at different sites, chambers, and equipment, possible problems or optimization opportunities can be identified, helping the production management team and decision makers understand key information and trends in the production process, and improving production efficiency and product quality.
[0079] (4) Data splicing of product defect rate and product history data is performed to construct the defect rate under each production path combination.
[0080] In the embodiment of the present invention, the process of constructing the defect rate under each production path combination is as follows:
[0081] (4.1) The unique identifier in the production path identification process is used as the association key to ensure that the product history data and product defect rate can be associated through a common identifier or key field.
[0082] (4.2) The product defect rate and product history data are spliced based on the association key to construct the defect rate under each production path combination to ensure that the production path combination information and detailed information of the defect rate of the history data can be retained after the data splicing.
[0083] In an embodiment of the present invention, a corresponding chart can be generated based on the defective rate under each production path combination, so that the production management team and the quality control team can quickly understand the impact of different production path combinations on the defective rate; and based on the analysis results, identify high-risk or high-impact path combinations, and take further quality improvement and production optimization measures to reduce the defective rate and improve production efficiency.
[0084] (5) Calculate the contribution rate based on the defective rate under each production path combination to obtain the contribution rate of each production path combination in the defective rate.
[0085] In an embodiment of the present invention, the contribution rate calculation method includes but is not limited to the benefit distribution method (Shapley method) in cooperative game, the average contribution method, etc.; preferably, the embodiment of the present invention adopts the benefit distribution method in cooperative game to calculate the contribution rate. The benefit distribution method in cooperative game is a method for measuring the contribution of participants in cooperative game to the overall result. The present invention applies it to the production path combination contribution analysis to help determine the contribution of each production path combination to the product defective rate.
[0086] In the embodiment of the present invention, the contribution rate is calculated based on the defect rate under each production path combination to obtain the contribution rate of each production path combination in the defect rate. The process is as follows:
[0087] (5.1) Obtain all production path combinations of cooperative games to construct a cooperative game system.
[0088] (5.2) For the defective rate under each production path combination in the cooperative game system, calculate the marginal contribution of each production path combination.
[0089] (5.3) Take a weighted average of the boundary contributions of each production path combination to obtain the contribution rate of each production path combination in the defect rate.
[0090] Specifically, the formula for calculating the contribution rate using the benefit distribution method in cooperative game is as follows:
[0091] Assume that there are n members in the cooperative game system, denoted as N = {1,2,…,n}, and different members form different alliances denoted as S, where S is a subset of N. The real function v defined on N is the characteristic function, that is, the benefit of alliance S is denoted as v(S). Member i has...S|-1)! sorting when participating in alliance S, |S| represents the number of members included in alliance S, and the remaining (n-|S|) members have more than (n-|S|)! sorting. The different sorting combinations of all member i divided by the random sorting combinations of n members is the weight of the benefits that member i should share with the alliance as a whole, denoted as [(|S|-1)! (n-|S|)! ] / (n!). The marginal contribution created by member i's participation in different alliances S for its own participation in the alliance is denoted as [v(S)-v(S\{i})], then the contribution rate of member i to the overall benefit v(N) is:
[0092]
[0093] When calculating the contribution rate, the key steps include determining the marginal contribution of each production path combination, which means evaluating the change in product defect rate after the production path combination is added to the production process relative to the change without the production path combination. In order to accurately measure the contribution rate of each production path combination, all possible permutations and combinations need to be taken into account, which is the basis for adopting the benefit allocation method in cooperative games. By averaging these marginal contributions, the contribution rate of each path combination can be obtained, thereby determining its contribution to the overall product defect rate.
[0094] Specifically, the advantage of using the benefit allocation method in cooperative games is that it can comprehensively consider the contributions of different path combinations, regardless of the complexity of the path combinations. This makes it suitable for various production environments and complex process flow analysis. For example, in the manufacturing industry, the benefit allocation method in cooperative games can be applied to identify which specific process steps or combinations have a significant impact on product quality issues, thereby optimizing production processes and quality control strategies.
[0095] (6) Sort and screen the contribution rate of each production path combination to the defect rate to obtain the suspected root cause of the defect.
[0096] Specifically, after obtaining the contribution rate of each production path combination in the defect rate, the production path combinations are sorted according to the contribution rate, and the top-ranked production path combinations are selected as the paths with the highest contribution rate to the product defect rate, so as to determine the combination with the greatest impact on the product defect rate. Generally, a production path combination with a high contribution rate may be the source of the problem, and the production path combination contains important suspected root cause sites, chambers or equipment, etc.
[0097] In summary, the present invention can quantitatively evaluate the degree of influence of different production path combinations on product defects in the entire processing process by calculating the contribution rate, calculate the marginal contribution of a single production path node through different production path combinations, and then determine the suspicious nodes that cause the defects, thereby more accurately identifying the potential root causes of process defects, and solving the problem that the existing root cause location method is prone to inaccurate analysis results when processing complex and correlated production process data.
[0098] In addition, in one embodiment, based on the same inventive concept as the above embodiment, the embodiment of the present invention provides a contribution-based root cause analysis system, the system corresponds one-to-one with the method of embodiment 1, and the system includes:
[0099] A data acquisition unit, the data acquisition unit is used to acquire original processing data of the product and pre-process the original processing data;
[0100] A defect rate calculation unit, wherein the defect rate calculation unit performs defect rate calculation based on the pre-processed original processing data to obtain a product defect rate;
[0101] A history data acquisition unit, wherein the history data acquisition unit performs production path identification and production path combination based on the pre-processed original processing data to obtain product history data;
[0102] A data splicing unit, the data splicing unit is used to perform data splicing on the product defect rate and the product history data to construct the defect rate under each production path combination;
[0103] A contribution rate calculation unit, wherein the contribution rate calculation unit performs contribution rate calculation based on the defective rate under each production path combination to obtain the contribution rate of each production path combination in the defective rate;
[0104] A suspected root cause locating unit is used to sort and screen the contribution rate of each production path combination in the defect rate to obtain the suspected defect root cause.
[0105] It should be noted that each unit in the contribution-based root cause analysis system of this embodiment corresponds one-to-one to each step in the contribution-based root cause analysis method of the aforementioned embodiment. Therefore, the specific implementation method and technical effects achieved by this embodiment can refer to the implementation method of the aforementioned contribution-based root cause analysis method, which will not be repeated here.
[0106] In addition, in one embodiment, the present application also provides a computer device, which includes a processor, a memory, and a computer program stored in the memory, and the computer program implements the method in the aforementioned embodiment when executed by the processor.
[0107] In addition, in one embodiment, the present application further provides a computer storage medium, on which a computer program is stored, and the computer program implements the method in the aforementioned embodiment when executed by a processor.
[0108] In some embodiments, the computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.
[0109] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.
[0110] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).
[0111] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.
[0112] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system 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, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.
[0113] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.
[0114] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a multimedia terminal device (which can be a mobile phone, a computer, a television receiver, or a network device, etc.) to execute the methods described in each embodiment of the present application.
[0115] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A method for analyzing root causes of defects based on contribution, characterized in that: The method comprises the following steps: Obtain the original processing data of the product and pre-process the original processing data; Calculate the defect rate based on the pre-processed raw processing data to obtain the product defect rate; Based on the pre-processed raw processing data, production path identification and production path combination are performed to obtain product history data; Data splicing of product defect rate and product history data to construct the defect rate under each production path combination; Calculate the contribution rate based on the defective rate under each production path combination to obtain the contribution rate of each production path combination in the defective rate; The contribution rate of each production path combination to the defect rate is sorted and screened to obtain the suspected defect root cause.
2. The method for analyzing the root cause of a defect based on contribution according to claim 1, characterized in that: The original processing data of the product includes the production path data of the product, the total number of products and the number of abnormal products.
3. The method for analyzing root causes of defects based on contribution according to claim 2, characterized in that: The calculation formula of the product defect rate is as follows: Among them, ρ represents the product defect rate, n1 represents the total number of products, and n represents the number of abnormal products.
4. The method for analyzing root causes of defects based on contribution according to claim 2, characterized in that: The process of identifying and combining production paths based on the pre-processed raw processing data to obtain product history data is as follows: Performing production path identification and production path combination based on production path data of each product, wherein the production path data includes production path nodes, node production processing time, and node production waiting time; A structured data model is constructed based on the production path data of the production path identifier and the production path combination, and the product history data of each product is queried and acquired based on the structured data model.
5. The method for failure root cause analysis based on contribution according to claim 1, characterized in that: The process of combining product defect rate and product history data to construct the defect rate for each production path combination is as follows: The unique identifier in the production path identification process is used as the association key; The product defect rate and product history data are concatenated based on the association key to construct the defect rate under each production path combination.
6. The method for analyzing root causes of defects based on contribution according to claim 1, characterized in that: The contribution rate calculation is implemented by using the benefit distribution method in cooperative game.
7. The method for analyzing root causes of defects based on contribution according to claim 6, characterized in that: The contribution rate is calculated based on the defective rate under each production path combination to obtain the contribution rate of each production path combination in the defective rate. The process is as follows: Obtain all production path combinations of cooperative games to build a cooperative game system; For the defect rate under each production path combination in the cooperative game system, calculate the marginal contribution of each production path combination; The boundary contribution of each production path combination is weighted averaged to obtain the contribution rate of each production path combination in the defect rate.
8. The method for analyzing root causes of defects based on contribution according to claim 4, characterized in that: The process of sorting and screening the contribution rate of each production path combination in the defect rate to obtain the suspected defect root cause is as follows: The production path combinations are ranked according to the contribution rate of each production path combination in the defect rate, and several production path combinations with the highest ranking are selected as alternative production path combinations; The production path nodes, node production processing time and node production waiting time corresponding to the alternative production path combinations are screened for suspicious root causes to obtain the suspected defective root causes.
9. A contribution-based root cause analysis system, characterized in that: The system comprises: A data acquisition unit, the data acquisition unit is used to acquire original processing data of the product and pre-process the original processing data; A defect rate calculation unit, wherein the defect rate calculation unit performs defect rate calculation based on the pre-processed original processing data to obtain a product defect rate; A history data acquisition unit, wherein the history data acquisition unit performs production path identification and production path combination based on the pre-processed original processing data to obtain product history data; A data splicing unit, the data splicing unit is used to perform data splicing on the product defect rate and the product history data to construct the defect rate under each production path combination; A contribution rate calculation unit, wherein the contribution rate calculation unit performs contribution rate calculation based on the defective rate under each production path combination to obtain the contribution rate of each production path combination in the defective rate; A suspected root cause locating unit is used to sort and screen the contribution rate of each production path combination in the defect rate to obtain the suspected defect root cause.
10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for analyzing the root cause of a defect based on contribution described in any one of claims 1 to 8 is implemented.
11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for analyzing the root cause of a defect based on contribution described in any one of claims 1 to 8 is implemented.