Intelligent data management system and method based on chip production

Abstract

The invention discloses an intelligent data management system and method based on chip production, and belongs to the technical field of data analysis. According to the method, a database is connected in a chip production process, production data of each process stage of chip production is recorded, and each chip is subjected to process number marking; carrying out production evaluation index analysis on the corresponding production process stages according to the production data of each stage of each chip, and carrying out total process production evaluation index analysis on each chip by integrating the production evaluation index analysis of each production process stage; performing matrix element quantity analysis on chips in the same batch by calling historical chip production data, performing chip matrix construction, and determining a sample matrix by analyzing the credit of each chip matrix; carrying out stability analysis on each chip evaluation matrix based on the sample matrix, and carrying out abnormity judgment based on analysis data; and performing internal chip abnormity analysis on the abnormal chip matrix, positioning abnormal chips and outputting chip production data.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to an intelligent data management system and method based on chip production. Background Art

[0002] Intelligent data management based on chip production integrates advanced data analysis, artificial intelligence and machine learning technologies to achieve real-time monitoring, analysis and optimization of the large amount of data generated in the chip manufacturing process, thereby improving production efficiency, ensuring product quality, enhancing the transparency and predictability of the manufacturing process, and promoting innovation and competitiveness of the entire chip manufacturing industry; In the current environment, due to the rapid development of intelligent technologies such as artificial intelligence, they occupy a very important technical application position in various social production fields; and semiconductor chips play an important role in them. Therefore, the current industrial production and application environment has a very large demand for chips, and while ensuring the quantity, the quality of chips is also high. At present, the chip manufacturing industry requires very rigorous chip testing for the manufacture and delivery of a large number of chips, and traditional testing requires long-term and multi-performance testing after the chip completes the production process. However, this model has a detection lag in the production cycle, and cannot achieve dual-line operation of production and testing. It is impossible to quickly and accurately locate abnormal chips in the production process, which has a considerable impact on the efficiency of chip manufacturing. At this stage, there are technical defects in conducting stage production evaluation and rapid abnormality analysis in the production process of chip production. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent data management system and method based on chip production to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: An intelligent data management method based on chip production, the method comprising the following steps: S100, by connecting to the database in the chip production process, recording the production data of each process stage of chip production, and marking each chip with a process number; S200, performing production evaluation index analysis at the corresponding production process stage according to the production data of each stage of each chip, and performing overall process production evaluation index analysis on each chip by integrating the production evaluation index analysis at each production process stage; S300, constructing a chip matrix for the same batch of chips by retrieving historical chip production data, and determining a sample matrix by analyzing the credit of each chip matrix; performing a difference analysis on the chip matrix of the same batch according to the sample matrix to determine an abnormal chip matrix; The number of elements of the chip matrix is ​​analyzed by comprehensively combining the production evaluation index of the chips in the corresponding batch with the historical chip production defect data, and the chip evaluation matrix is ​​constructed by matrix filling for the chips in the current batch according to the calculated data; the matrix credit corresponding to each matrix is ​​analyzed based on the constructed chip evaluation matrix, and the sample matrix is ​​determined based on the analysis results; the stability of each chip evaluation matrix is ​​analyzed based on the sample matrix, and abnormality judgment is made based on the analysis data; S400, performing internal chip abnormality analysis on the abnormal chip matrix, locating the abnormal chip and outputting chip production data.

[0005] The specific steps of S100, by connecting to the database in the chip production process, recording the production data of each process stage of chip production, and marking each chip with a process number, are as follows: S101, by locating the program port of the chip production process and establishing the port coordinates, using the port coordinates of each production process to establish a data transmission channel with the database, and collecting the production data of each chip production process stage; the production data includes production environment data, production process completion data and production process time data; the environmental data includes temperature data, humidity data, vibration data and pressure data, etc.; wherein the production process completion refers to the operation completion status of each production stage of the chip under the influence of various factors during the production process; S102. Assign numbers to chips produced in the same batch, wherein the batch number is the primary number of each chip and the chip sequence is the secondary number of the chip; divide the data storage space for each chip in the database, using the chip number as the data index and the chip production data as the index data.

[0006] The specific steps of S200 for performing production evaluation index analysis at the corresponding production process stage according to the production data of each stage of each chip, and performing overall process production evaluation index analysis on each chip based on the production evaluation index analysis at each production process stage are as follows: S201, analyzing the production evaluation index of each chip at each production process stage according to the production data of each chip at each production process stage recorded in the database; analyzing the influence degree of environmental factors on the corresponding chip at the corresponding production process stage, the calculation formula is: ;in is the degree of environmental impact on the chip numbered n in the current batch at the mth stage of the production process; s is the number of environmental types; is the relative impact parameter of the corresponding environment type; is the data corresponding to the environment type; is the correction parameter; combined with the impact of environmental factors in each production process stage of each chip, the production evaluation index of each production process of the chip is analyzed, and the calculation formula is: ;in is the production completion degree of the chip numbered n in the current batch at the mth production process stage; is the production process completion time of the chip numbered n in the current batch at the mth production process stage; S202, combining the production evaluation index of each chip production process stage to calculate the production evaluation index of the total production process of each chip, and the calculation formula is: ;in It is the production evaluation index of the overall production process of each chip; Corresponding to the evaluation parameters of each production process stage; performing production evaluation index analysis on each chip in the current production batch, and inputting the analysis results into the storage data of the corresponding chip data in the database.

[0007] The S300 constructs a chip matrix for the same batch of chips by retrieving historical chip production data, and determines a sample matrix by analyzing the credit of each chip matrix; the specific steps of performing difference analysis on the same batch of chip matrices according to the sample matrix to determine the abnormal chip matrix are as follows: S301, analyze the chip data of the current batch by retrieving the historical chip production data in the database to construct a chip matrix; extract the chip defect ratio value in the historical chip production data, and analyze the number of matrix elements in combination with the production evaluation index of the chips in the current batch. The calculation formula is: ;in is the number of matrix elements; is the average defect ratio of chips in the same batch in the historical chip production data; v is the error parameter; if the calculation result N is not an integer, it is rounded; S302. According to the chip matrix element quantity analysis result, the chip matrix elements are filled for the chips in the current production batch, and the chip matrix is ​​constructed by sequentially filling according to the chip production number. The corresponding chip production evaluation matrix is ​​constructed by taking the total production process evaluation index of the corresponding chip as the matrix element; if there is insufficient quantity to complete the matrix element filling, the average value of the total chip production process is used as virtual data for filling, and the virtual data is marked; the sample matrix selection analysis is performed on each chip production evaluation matrix that has completed the matrix filling, and the matrix credit of each chip production evaluation matrix is ​​analyzed, and the calculation formula is: ;in The matrix credit of each chip production evaluation matrix; It corresponds to the production evaluation matrix of each chip; u is the matrix number; is the error function; is the standard deviation of the total production process evaluation index of each chip in the current batch; Corresponding chip production evaluation matrix The total production process evaluation index of each chip in the chip production evaluation matrix; according to the matrix credit analysis results of each chip production evaluation matrix, the chip production evaluation matrix corresponding to the maximum credit value is taken as the sample matrix; S303, using the sample matrix as a reference to perform difference analysis on the remaining chip production evaluation matrices; analyzing the internal production stability of the sample matrix and the remaining chip production evaluation matrices respectively, and the calculation common formula is: ;in Evaluation matrix for chip production Internal production stability; Evaluation matrix for chip production The maximum value of the corresponding production evaluation index; is the mean value of the total production process evaluation index corresponding to the current batch of chips; Chip Production Evaluation Matrix The minimum value of the corresponding production evaluation index; Corresponding chip production evaluation matrix The standard deviation of the total production process evaluation index of each chip; according to the analysis results, the internal production stability of the sample matrix is ​​obtained and the rest of the chip production evaluation matrix stability ;in is the sample matrix; is the remaining chip production evaluation matrix excluding the sample matrix; according to the analysis results, the remaining chip production evaluation matrices are analyzed for differences. , then the current target chip production evaluation matrix is ​​judged to be abnormal in production stability; when , then it is judged that the current target chip production evaluation matrix is ​​stable and normal; is a ratio parameter; since the sample matrix is ​​obtained based on the matrix credit calculation, the corresponding data of each chip in the sample matrix are all regarded as good data, so the remaining chips are used as references for rapid abnormality analysis; since there are sample matrices and other matrices, the number of overall matrices is greater than or equal to 2, so 2.

[0008] The specific steps of S400 for performing internal chip abnormality analysis on the abnormal chip matrix, locating the abnormal chip and outputting chip production data are as follows: S401, extract the chip production evaluation matrix corresponding to the production stability anomaly, extract the total production process evaluation index of the corresponding chip in the matrix, and perform abnormal chip positioning analysis by combining the sample matrix. The calculation formula is: ;in The corresponding chip production evaluation matrix The abnormal difference value of each chip in; The corresponding chip production evaluation matrix The total production process evaluation index of each chip in; is the corresponding sample matrix The maximum value of the corresponding production evaluation index in; by introducing the chip abnormality difference index ,like , then the current chip production evaluation matrix The target difference analysis chip is normal; if , then the current chip production evaluation matrix The target difference analysis chip is abnormal; the maximum evaluation value in the sample matrix is ​​used as the reference object for difference analysis to ensure the high accuracy of the analysis of abnormal chips; chip abnormal difference index Summarize and obtain by performing multiple chip difference analyses on historical data; S402, number and locate the abnormal chips, output the production data of the corresponding chips, and alert the inspection personnel to perform chip inspection.

[0009] An intelligent data management system based on chip production, the system includes a production data acquisition module, a production evaluation and analysis module, an abnormal matrix analysis module and an abnormal output module; The production data acquisition module connects to the database in the chip production process, records the production data of each process stage of chip production, and marks each chip with a process number; the production evaluation analysis module performs production evaluation index analysis on the corresponding production process stage based on the production data of each chip at each stage, and performs production evaluation index analysis on the entire process for each chip by combining the production evaluation index analysis of each production process stage; the abnormal matrix analysis module constructs a chip matrix for chips of the same batch by retrieving historical chip production data, and determines a sample chip matrix by analyzing the credit of each chip matrix; a difference analysis is performed on chip matrices of the same batch based on the sample chip matrix to determine an abnormal chip matrix; the abnormal output module performs internal chip abnormality analysis on the abnormal chip matrix, locates the abnormal chip, and outputs chip data and abnormal information.

[0010] The production data acquisition module includes a production data acquisition unit and a data storage unit; The production data acquisition unit performs program port positioning and establishes port coordinates for the chip production process, and establishes a data transmission channel between the port coordinates of each production process and the database to collect production data at each chip production process stage; the production data includes production environment data, production process completion data and production process time data; The data storage unit assigns numbers to chips produced in the same batch, wherein the batch number is the main number of each chip and the chip sequence is the auxiliary number of the chip; the data storage space of each chip is divided in the database, the chip number is used as the data index, and the production data of the chip is used as the index data.

[0011] The production evaluation and analysis module includes a stage production evaluation and analysis unit and a comprehensive production evaluation and analysis unit; The stage production evaluation analysis unit analyzes the production evaluation index of each production process stage corresponding to each chip through the production data of each chip corresponding to each production process stage recorded in the database; analyzes the degree of influence of environmental factors on the corresponding chip at the corresponding production process stage; and analyzes the production evaluation index of each production process of the chip in combination with the influence of environmental factors on each chip at each production process stage; The comprehensive production evaluation analysis unit calculates the production evaluation index of the total production process of each chip in combination with the production evaluation index of each production process stage of the chip; performs production evaluation index analysis on each chip in the current production batch respectively, and inputs the analysis results into the storage data of the corresponding chip data in the database.

[0012] The abnormal matrix analysis module includes a chip matrix construction unit, a sample matrix determination unit and an abnormal matrix analysis unit; The chip matrix construction unit analyzes the chip data of the current batch by retrieving the historical chip production data in the database to construct a chip matrix; extracts the defect ratio value of the chip in the historical chip production data, and performs a matrix element quantity analysis in combination with the production evaluation index of the chips in the current batch; The sample matrix determination unit fills the chip matrix elements for the chips in the current production batch according to the chip matrix element quantity analysis result, constructs the chip matrix by sequentially filling according to the chip production number, and constructs the corresponding chip production evaluation matrix by taking the total production process evaluation index of the corresponding chip as the matrix element; performs sample matrix selection analysis on each chip production evaluation matrix that has completed matrix filling, and analyzes the matrix credit of each chip production evaluation matrix; according to the matrix credit analysis result of each chip production evaluation matrix, takes the chip production evaluation matrix corresponding to the maximum credit value as the sample matrix; The abnormal matrix analysis unit performs difference analysis on the remaining chip production evaluation matrices with reference to the sample matrix; analyzes the internal production stability of the sample matrix and the remaining chip production evaluation matrices respectively; obtains the internal production stability of the sample matrix and the stability of the remaining chip production evaluation matrices based on the analysis results; and performs difference analysis on the remaining chip production evaluation matrices based on the analysis results.

[0013] The abnormal output module includes an abnormal chip positioning unit and an abnormal chip output unit; The abnormal chip locating unit extracts the chip production evaluation matrix corresponding to the production stability abnormality, extracts the total production process evaluation index of the corresponding chip in the matrix, and performs abnormal chip locating analysis by combining the sample matrix; and performs abnormal chip judgment analysis on the abnormal matrix by introducing the chip abnormal difference index; The abnormal chip output unit numbers and locates the abnormal chip, outputs the production data of the corresponding chip, and warns the inspection personnel to perform chip inspection.

[0014] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention realizes real-time data monitoring and evaluation index calculation for each chip by performing a series of system architecture analyses including data collection, analysis, abnormal judgment and abnormal output in the chip production process; the chip division and reference object determination are realized by constructing an analysis matrix and performing credit analysis to determine the sample matrix; the sample matrix is ​​used to perform abnormal analysis on the remaining matrices, thereby realizing rapid abnormal analysis of the chip matrix and obtaining the area where the abnormal chip is located; finally, abnormal analysis is performed on each chip in the abnormal matrix to realize the positioning of the abnormal chip; the present invention realizes rapid abnormal detection and positioning of chip detection in the chip production process through a series of chip production evaluation index analysis, matrix construction, sample matrix determination, abnormal matrix determination and final abnormal chip positioning, thereby greatly improving the chip detection efficiency and improving the low efficiency problem existing in traditional chip detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a structural schematic diagram of an intelligent data management system based on chip production of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] See also Figure 1 , the present invention provides a technical solution: An intelligent data management method based on chip production, the method comprising the following steps: S100, by connecting to the database in the chip production process, recording the production data of each process stage of chip production, and marking each chip with a process number; S200, performing production evaluation index analysis at the corresponding production process stage according to the production data of each stage of each chip, and performing overall process production evaluation index analysis on each chip by integrating the production evaluation index analysis at each production process stage; S300, constructing a chip matrix for the same batch of chips by retrieving historical chip production data, and determining a sample matrix by analyzing the credit of each chip matrix; performing a difference analysis on the chip matrix of the same batch according to the sample matrix to determine an abnormal chip matrix; The number of elements of the chip matrix is ​​analyzed by comprehensively combining the production evaluation index of the chips in the corresponding batch with the historical chip production defect data, and the chip evaluation matrix is ​​constructed by matrix filling for the chips in the current batch according to the calculated data; the matrix credit corresponding to each matrix is ​​analyzed based on the constructed chip evaluation matrix, and the sample matrix is ​​determined based on the analysis results; the stability of each chip evaluation matrix is ​​analyzed based on the sample matrix, and abnormality judgment is made based on the analysis data; S400, performing internal chip abnormality analysis on the abnormal chip matrix, locating the abnormal chip and outputting chip production data.

[0018] The specific steps of S100, by connecting to the database in the chip production process, recording the production data of each process stage of chip production, and marking each chip with a process number, are as follows: S101, by locating the program port of the chip production process and establishing the port coordinates, using the port coordinates of each production process to establish a data transmission channel with the database, and collecting the production data of each chip production process stage; the production data includes production environment data, production process completion data and production process time data; S102. Assign numbers to chips produced in the same batch, wherein the batch number is the primary number of each chip and the chip sequence is the secondary number of the chip; divide the data storage space for each chip in the database, using the chip number as the data index and the chip production data as the index data.

[0019] The specific steps of S200 for performing production evaluation index analysis at the corresponding production process stage according to the production data of each stage of each chip, and performing overall process production evaluation index analysis on each chip based on the production evaluation index analysis at each production process stage are as follows: S201, analyzing the production evaluation index of each chip at each production process stage according to the production data of each chip at each production process stage recorded in the database; analyzing the influence degree of environmental factors on the corresponding chip at the corresponding production process stage, the calculation formula is: ;in is the degree of environmental impact on the chip numbered n in the current batch at the mth stage of the production process; s is the number of environmental types; is the relative impact parameter of the corresponding environment type; is the data corresponding to the environment type; is the correction parameter; combined with the impact of environmental factors in each production process stage of each chip, the production evaluation index of each production process of the chip is analyzed, and the calculation formula is: ;in is the production completion degree of the chip numbered n in the current batch at the mth production process stage; is the production process completion time of the chip numbered n in the current batch at the mth production process stage; S202, combining the production evaluation index of each chip production process stage to calculate the production evaluation index of the total production process of each chip, and the calculation formula is: ;in It is the production evaluation index of the overall production process of each chip; Corresponding to the evaluation parameters of each production process stage; performing production evaluation index analysis on each chip in the current production batch, and inputting the analysis results into the storage data of the corresponding chip data in the database.

[0020] The S300 constructs a chip matrix for the same batch of chips by retrieving historical chip production data, and determines a sample matrix by analyzing the credit of each chip matrix; the specific steps of performing difference analysis on the same batch of chip matrices according to the sample matrix to determine the abnormal chip matrix are as follows: S301, analyze the chip data of the current batch by retrieving the historical chip production data in the database to construct a chip matrix; extract the chip defect ratio value in the historical chip production data, and analyze the number of matrix elements in combination with the production evaluation index of the chips in the current batch. The calculation formula is: ;in is the number of matrix elements; is the mean defect ratio of chips in the same batch in historical chip production data; v is the error parameter; S302. According to the chip matrix element quantity analysis result, fill the chip matrix elements for the chips in the current production batch, construct the chip matrix by filling in the chip production number in sequence, and construct the corresponding chip production evaluation matrix by taking the total production process evaluation index of the corresponding chip as the matrix element; perform sample matrix selection analysis on each chip production evaluation matrix that has completed matrix filling, and calculate the matrix credit of each chip production evaluation matrix by analyzing the matrix credit of each chip production evaluation matrix. ;in The matrix credit of each chip production evaluation matrix; It corresponds to the production evaluation matrix of each chip; u is the matrix number; is the error function; is the standard deviation of the total production process evaluation index of each chip in the current batch; Corresponding chip production evaluation matrix The total production process evaluation index of each chip in the chip production evaluation matrix; according to the matrix credit analysis results of each chip production evaluation matrix, the chip production evaluation matrix corresponding to the maximum credit value is taken as the sample matrix; S303, using the sample matrix as a reference to perform difference analysis on the remaining chip production evaluation matrices; analyzing the internal production stability of the sample matrix and the remaining chip production evaluation matrices respectively, and the calculation common formula is: ;in Evaluation matrix for chip production Internal production stability; Evaluation matrix for chip production The maximum value of the corresponding production evaluation index; is the mean value of the total production process evaluation index corresponding to the current batch of chips; Chip Production Evaluation Matrix The minimum value of the corresponding production evaluation index; Corresponding chip production evaluation matrix The standard deviation of the total production process evaluation index of each chip; according to the analysis results, the internal production stability of the sample matrix is ​​obtained and the rest of the chip production evaluation matrix stability ;in is the sample matrix; is the remaining chip production evaluation matrix excluding the sample matrix; according to the analysis results, the remaining chip production evaluation matrices are analyzed for differences. , then the current target chip production evaluation matrix is ​​judged to be abnormal in production stability; when , then it is judged that the current target chip production evaluation matrix is ​​stable and normal; is the scale parameter.

[0021] The specific steps of S400 for performing internal chip abnormality analysis on the abnormal chip matrix, locating the abnormal chip and outputting chip production data are as follows: S401, extract the chip production evaluation matrix corresponding to the production stability anomaly, extract the total production process evaluation index of the corresponding chip in the matrix, and perform abnormal chip positioning analysis by combining the sample matrix. The calculation formula is: ;in The corresponding chip production evaluation matrix The abnormal difference value of each chip in; The corresponding chip production evaluation matrix The total production process evaluation index of each chip in; is the corresponding sample matrix The maximum value of the corresponding production evaluation index in; by introducing the chip abnormality difference index ,like , then the current chip production evaluation matrix The target difference analysis chip is normal; if , then the current chip production evaluation matrix The target difference analysis chip is abnormal; S402, number and locate the abnormal chips, output the production data of the corresponding chips, and alert the inspection personnel to perform chip inspection.

[0022] An intelligent data management system based on chip production, the system includes a production data acquisition module, a production evaluation and analysis module, an abnormal matrix analysis module and an abnormal output module; The production data acquisition module connects to the database in the chip production process, records the production data of each process stage of chip production, and marks each chip with a process number; the production evaluation analysis module performs production evaluation index analysis on the corresponding production process stage based on the production data of each chip at each stage, and performs production evaluation index analysis on the entire process for each chip by combining the production evaluation index analysis of each production process stage; the abnormal matrix analysis module constructs a chip matrix for chips of the same batch by retrieving historical chip production data, and determines a sample chip matrix by analyzing the credit of each chip matrix; a difference analysis is performed on chip matrices of the same batch based on the sample chip matrix to determine an abnormal chip matrix; the abnormal output module performs internal chip abnormality analysis on the abnormal chip matrix, locates the abnormal chip, and outputs chip data and abnormal information.

[0023] The production data acquisition module includes a production data acquisition unit and a data storage unit; The production data acquisition unit performs program port positioning and establishes port coordinates for the chip production process, and establishes a data transmission channel between the port coordinates of each production process and the database to collect production data at each chip production process stage; the production data includes production environment data, production process completion data and production process time data; The data storage unit assigns numbers to chips produced in the same batch, wherein the batch number is the main number of each chip and the chip sequence is the auxiliary number of the chip; the data storage space of each chip is divided in the database, the chip number is used as the data index, and the production data of the chip is used as the index data.

[0024] The production evaluation and analysis module includes a stage production evaluation and analysis unit and a comprehensive production evaluation and analysis unit; The stage production evaluation analysis unit analyzes the production evaluation index of each production process stage corresponding to each chip through the production data of each chip corresponding to each production process stage recorded in the database; analyzes the degree of influence of environmental factors on the corresponding chip at the corresponding production process stage; and analyzes the production evaluation index of each production process of the chip in combination with the influence of environmental factors on each chip at each production process stage; The comprehensive production evaluation analysis unit calculates the production evaluation index of the total production process of each chip in combination with the production evaluation index of each production process stage of the chip; performs production evaluation index analysis on each chip in the current production batch respectively, and inputs the analysis results into the storage data of the corresponding chip data in the database.

[0025] The abnormal matrix analysis module includes a chip matrix construction unit, a sample matrix determination unit and an abnormal matrix analysis unit; The chip matrix construction unit analyzes the chip data of the current batch by retrieving the historical chip production data in the database to construct a chip matrix; extracts the defect ratio value of the chip in the historical chip production data, and performs a matrix element quantity analysis in combination with the production evaluation index of the chips in the current batch; The sample matrix determination unit fills the chip matrix elements for the chips in the current production batch according to the chip matrix element quantity analysis result, constructs the chip matrix by sequentially filling according to the chip production number, and constructs the corresponding chip production evaluation matrix by taking the total production process evaluation index of the corresponding chip as the matrix element; performs sample matrix selection analysis on each chip production evaluation matrix that has completed matrix filling, and analyzes the matrix credit of each chip production evaluation matrix; according to the matrix credit analysis result of each chip production evaluation matrix, takes the chip production evaluation matrix corresponding to the maximum credit value as the sample matrix; The abnormal matrix analysis unit performs difference analysis on the remaining chip production evaluation matrices with reference to the sample matrix; analyzes the internal production stability of the sample matrix and the remaining chip production evaluation matrices respectively; obtains the internal production stability of the sample matrix and the stability of the remaining chip production evaluation matrices based on the analysis results; and performs difference analysis on the remaining chip production evaluation matrices based on the analysis results.

[0026] The abnormal output module includes an abnormal chip positioning unit and an abnormal chip output unit; The abnormal chip locating unit extracts the chip production evaluation matrix corresponding to the production stability abnormality, extracts the total production process evaluation index of the corresponding chip in the matrix, and performs abnormal chip locating analysis by combining the sample matrix; and performs abnormal chip judgment analysis on the abnormal matrix by introducing the chip abnormal difference index; The abnormal chip output unit numbers and locates the abnormal chip, outputs the production data of the corresponding chip, and warns the inspection personnel to perform chip inspection; In the examples: A chip manufacturing company now needs to optimize the detection link in the chip production process. It uses a database combined with the intelligent data management system based on chip production of the present invention to realize rapid detection and positioning of abnormal chips; by locating the program port of the chip production process and establishing port coordinates, a data transmission channel is established between the port coordinates of each production process and the database, and the production data of each chip production process stage is collected; the chips produced in the same batch are numbered, wherein the batch number is the main number of each chip, and the chip sequence is the auxiliary number of the chip; the data storage space of each chip is divided in the database, the chip number is used as the data index, and the production data of the chip is used as the index data; The production evaluation index of each chip at each production process stage is analyzed by the production data of each chip at each production process stage recorded in the database; the influence degree of environmental factors on the corresponding chip at the corresponding production process stage is analyzed, and the calculation formula is: ; Combined with the impact of environmental factors in each production process stage of each chip, the production evaluation index of each production process of the chip is analyzed, and the calculation formula is: ; Combined with the production evaluation index of each chip production process stage, the production evaluation index of the total production process of each chip is calculated, and the calculation formula is: ; Perform production evaluation index analysis on each chip in the current production batch, and input the analysis results into the storage data of the corresponding chip data in the database; The chip data of the current batch is analyzed by retrieving the historical chip production data in the database to construct a chip matrix; the defect ratio value of the chip in the historical chip production data is extracted, and the number of matrix elements is analyzed in combination with the production evaluation index of the chip in the current batch. The calculation formula is: ; According to the chip matrix element quantity analysis results, the chip matrix elements are filled in the chips in the current production batch, and the chip matrix is ​​constructed by filling in the chip production number in sequence. The corresponding chip production evaluation matrix is ​​constructed by taking the total production process evaluation index of the corresponding chip as the matrix element; the sample matrix selection analysis is performed on each chip production evaluation matrix that has completed the matrix filling, and the matrix credit of each chip production evaluation matrix is ​​analyzed, and the calculation formula is: ; According to the matrix credit analysis results of each chip production evaluation matrix, the chip production evaluation matrix corresponding to the maximum credit value is taken as the sample matrix; the difference analysis of the remaining chip production evaluation matrices is performed with the sample matrix as a reference; the internal production stability of the sample matrix and the remaining chip production evaluation matrices is analyzed respectively, and the calculation formula is: ;According to the analysis results, obtain the internal production stability of the sample matrix and the rest of the chip production evaluation matrix stability ; Based on the analysis results, the remaining chip production evaluation matrices are analyzed for differences. , then the current target chip production evaluation matrix is ​​judged to be abnormal in production stability; when , then it is judged that the current target chip production evaluation matrix is ​​stable and normal; Extract the chip production evaluation matrix corresponding to the production stability anomaly, extract the total production process evaluation index of the corresponding chip in the matrix, and perform abnormal chip positioning analysis by combining the sample matrix. The calculation formula is ; By introducing the chip abnormality difference index ,like , then the current chip production evaluation matrix The target difference analysis chip is normal; if , then the current chip production evaluation matrix Analyze chip abnormalities in target differences; number and locate abnormal chips, output the production data of the corresponding chips, and alert the inspection personnel to conduct chip inspection.

[0027] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are 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 other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0028] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent data management method based on chip production, characterized in that: The method comprises the following steps: S100, by connecting to the database in the chip production process, recording the production data of each process stage of chip production, and marking each chip with a process number; S200, performing production evaluation index analysis at the corresponding production process stage according to the production data of each stage of each chip, and performing overall process production evaluation index analysis on each chip by integrating the production evaluation index analysis at each production process stage; S300, constructing a chip matrix for the same batch of chips by retrieving historical chip production data, and determining a sample matrix by analyzing the credit of each chip matrix; performing a difference analysis on the chip matrix of the same batch according to the sample matrix to determine an abnormal chip matrix; The number of elements of the chip matrix is ​​analyzed by comprehensively combining the production evaluation index of the chips in the corresponding batch with the historical chip production defect data, and the chip evaluation matrix is ​​constructed by matrix filling for the chips in the current batch according to the calculated data; the matrix credit corresponding to each matrix is ​​analyzed based on the constructed chip evaluation matrix, and the sample matrix is ​​determined based on the analysis results; the stability of each chip evaluation matrix is ​​analyzed based on the sample matrix, and abnormality judgment is made based on the analysis data; S400, performing internal chip abnormality analysis on the abnormal chip matrix, locating the abnormal chip and outputting chip production data.

2. The intelligent data management method based on chip production according to claim 1, characterized in that: The specific steps of S100, by connecting to the database in the chip production process, recording the production data of each process stage of chip production, and marking each chip with a process number, are as follows: S101, by locating the program port of the chip production process and establishing the port coordinates, using the port coordinates of each production process to establish a data transmission channel with the database, and collecting the production data of each chip production process stage; the production data includes production environment data, production process completion data and production process time data; S102. Assign numbers to chips produced in the same batch, wherein the batch number is the primary number of each chip and the chip sequence is the secondary number of the chip; divide the data storage space for each chip in the database, using the chip number as the data index and the chip production data as the index data.

3. The intelligent data management method based on chip production according to claim 2, characterized in that: The specific steps of S200 for performing production evaluation index analysis at the corresponding production process stage according to the production data of each stage of each chip, and performing overall process production evaluation index analysis on each chip based on the production evaluation index analysis at each production process stage are as follows: S201, analyzing the production evaluation index of each chip at each production process stage according to the production data of each chip at each production process stage recorded in the database; analyzing the influence degree of environmental factors on the corresponding chip at the corresponding production process stage, the calculation formula is: ;in is the degree of environmental impact on the chip numbered n in the current batch at the mth stage of the production process; s is the number of environmental types; is the relative impact parameter of the corresponding environment type; is the data corresponding to the environment type; is the correction parameter; combined with the impact of environmental factors in each production process stage of each chip, the production evaluation index of each production process of the chip is analyzed, and the calculation formula is: ;in is the production completion degree of the chip numbered n in the current batch at the mth production process stage; is the production process completion time of the chip numbered n in the current batch at the mth production process stage; S202, combining the production evaluation index of each chip production process stage to calculate the production evaluation index of the total production process of each chip, and the calculation formula is: ;in It is the production evaluation index of the overall production process of each chip; Corresponding to the evaluation parameters of each production process stage; performing production evaluation index analysis on each chip in the current production batch, and inputting the analysis results into the storage data of the corresponding chip data in the database.

4. The intelligent data management method based on chip production according to claim 3, characterized in that: The S300 constructs a chip matrix for the same batch of chips by retrieving historical chip production data, and determines a sample matrix by analyzing the credit of each chip matrix; the specific steps of performing difference analysis on the same batch of chip matrices according to the sample matrix to determine the abnormal chip matrix are as follows: S301, analyze the chip data of the current batch by retrieving the historical chip production data in the database to construct a chip matrix; extract the chip defect ratio value in the historical chip production data, and analyze the number of matrix elements in combination with the production evaluation index of the chips in the current batch. The calculation formula is: ;in is the number of matrix elements; is the average defect ratio of chips in the same batch in historical chip production data; v is the error parameter; S302, according to the chip matrix element quantity analysis result, fill the chip matrix elements for the chips in the current production batch, construct the chip matrix by filling in the order according to the chip production number, and construct the corresponding chip production evaluation matrix by taking the total production process evaluation index of the corresponding chip as the matrix element; The sample matrix selection analysis is performed on each chip production evaluation matrix that has completed matrix filling. By analyzing the matrix credit of each chip production evaluation matrix, the calculation formula is: ;in The matrix credit of each chip production evaluation matrix; It corresponds to the production evaluation matrix of each chip; u is the matrix number; is the error function; is the standard deviation of the total production process evaluation index of each chip in the current batch; Corresponding chip production evaluation matrix The total production process evaluation index of each chip in the chip production evaluation matrix; according to the matrix credit analysis results of each chip production evaluation matrix, the chip production evaluation matrix corresponding to the maximum credit value is taken as the sample matrix; S303, using the sample matrix as a reference to perform difference analysis on the remaining chip production evaluation matrices; analyzing the internal production stability of the sample matrix and the remaining chip production evaluation matrices respectively, and the calculation common formula is: ;in Evaluation matrix for chip production Internal production stability; Evaluation matrix for chip production The maximum value of the corresponding production evaluation index; is the mean value of the total production process evaluation index corresponding to the current batch of chips; Chip Production Evaluation Matrix The minimum value of the corresponding production evaluation index; Corresponding chip production evaluation matrix The standard deviation of the total production process evaluation index of each chip; Obtain internal production stability of the sample matrix based on the analysis results and the rest of the chip production evaluation matrix stability ;in is the sample matrix; is the remaining chip production evaluation matrix excluding the sample matrix; according to the analysis results, the remaining chip production evaluation matrices are analyzed for differences. , then it is judged that the production stability of the current target chip production evaluation matrix is ​​abnormal; when , then it is judged that the current target chip production evaluation matrix is ​​stable and normal; is the scale parameter.

5. The intelligent data management method based on chip production according to claim 4, characterized in that: The specific steps of S400 for performing internal chip abnormality analysis on the abnormal chip matrix, locating the abnormal chip and outputting chip production data are as follows: S401, extract the chip production evaluation matrix corresponding to the production stability anomaly, extract the total production process evaluation index of the corresponding chip in the matrix, and perform abnormal chip positioning analysis by combining the sample matrix. The calculation formula is: ;in The corresponding chip production evaluation matrix The abnormal difference value of each chip in; The corresponding chip production evaluation matrix The total production process evaluation index of each chip in; is the corresponding sample matrix The maximum value of the corresponding production evaluation index in; by introducing the chip abnormality difference index ,like , then the current chip production evaluation matrix The target difference analysis chip is normal; if , then the current chip production evaluation matrix The target difference analysis chip is abnormal; S402, number and locate the abnormal chips, output the production data of the corresponding chips, and alert the inspection personnel to perform chip inspection.

6. An intelligent data management system based on chip production, characterized by: The system includes a production data acquisition module, a production evaluation and analysis module, an abnormal matrix analysis module and an abnormal output module; The production data acquisition module connects to the database in the chip production process, records the production data of each process stage of chip production, and marks each chip with a process number; the production evaluation analysis module performs production evaluation index analysis on the corresponding production process stage based on the production data of each chip at each stage, and performs production evaluation index analysis on the entire process for each chip by combining the production evaluation index analysis of each production process stage; the abnormal matrix analysis module constructs a chip matrix for chips of the same batch by retrieving historical chip production data, and determines a sample chip matrix by analyzing the credit of each chip matrix; a difference analysis is performed on chip matrices of the same batch based on the sample chip matrix to determine an abnormal chip matrix; the abnormal output module performs internal chip abnormality analysis on the abnormal chip matrix, locates the abnormal chip, and outputs chip data and abnormal information.

7. The intelligent data management system based on chip production according to claim 6, characterized in that: The production data acquisition module includes a production data acquisition unit and a data storage unit; The production data acquisition unit performs program port positioning and establishes port coordinates for the chip production process, and establishes a data transmission channel between the port coordinates of each production process and the database to collect production data at each chip production process stage; the production data includes production environment data, production process completion data and production process time data; The data storage unit assigns numbers to chips produced in the same batch, wherein the batch number is the main number of each chip and the chip sequence is the auxiliary number of the chip; the data storage space of each chip is divided in the database, the chip number is used as the data index, and the production data of the chip is used as the index data.

8. The intelligent data management system based on chip production according to claim 7, characterized in that: The production evaluation and analysis module includes a stage production evaluation and analysis unit and a comprehensive production evaluation and analysis unit; The stage production evaluation analysis unit analyzes the production evaluation index of each production process stage corresponding to each chip through the production data of each chip corresponding to each production process stage recorded in the database; analyzes the degree of influence of environmental factors on the corresponding chip at the corresponding production process stage; and analyzes the production evaluation index of each production process of the chip in combination with the influence of environmental factors on each chip at each production process stage; The comprehensive production evaluation analysis unit calculates the production evaluation index of the total production process of each chip in combination with the production evaluation index of each production process stage of the chip; performs production evaluation index analysis on each chip in the current production batch respectively, and inputs the analysis results into the storage data of the corresponding chip data in the database.

9. The intelligent data management system based on chip production according to claim 8, characterized in that: The abnormal matrix analysis module includes a chip matrix construction unit, a sample matrix determination unit and an abnormal matrix analysis unit; The chip matrix construction unit analyzes the chip data of the current batch by retrieving the historical chip production data in the database to construct a chip matrix; extracts the defect ratio value of the chip in the historical chip production data, and performs a matrix element quantity analysis in combination with the production evaluation index of the chips in the current batch; The sample matrix determination unit fills the chip matrix elements for the chips in the current production batch according to the chip matrix element quantity analysis result, constructs the chip matrix by sequentially filling according to the chip production number, and constructs the corresponding chip production evaluation matrix by taking the total production process evaluation index of the corresponding chip as the matrix element; Perform sample matrix selection analysis on each chip production evaluation matrix that has completed matrix filling, and analyze the matrix credit of each chip production evaluation matrix; according to the matrix credit analysis results of each chip production evaluation matrix, take the chip production evaluation matrix corresponding to the maximum credit value as the sample matrix; The abnormal matrix analysis unit performs difference analysis on the remaining chip production evaluation matrices with reference to the sample matrix; analyzes the internal production stability of the sample matrix and the remaining chip production evaluation matrices respectively; According to the analysis results, the internal production stability of the sample matrix and the stability of the production evaluation matrices of the remaining chips are obtained; according to the analysis results, the difference analysis of the production evaluation matrices of the remaining chips is performed.

10. The intelligent data management system based on chip production according to claim 9, characterized in that: The abnormal output module includes an abnormal chip positioning unit and an abnormal chip output unit; The abnormal chip locating unit extracts the chip production evaluation matrix corresponding to the production stability abnormality, extracts the total production process evaluation index of the corresponding chip in the matrix, and performs abnormal chip locating analysis by combining the sample matrix; and performs abnormal chip judgment analysis on the abnormal matrix by introducing the chip abnormal difference index; The abnormal chip output unit numbers and locates the abnormal chip, outputs the production data of the corresponding chip, and warns the inspection personnel to perform chip inspection.

Images