Semiconductor storage intelligent management system

Abstract

The invention discloses a semiconductor storage intelligent management system, and belongs to the technical field of semiconductor management. The method comprises the following steps: performing quality detection on a plurality of finished products produced in the same batch of semiconductor storage from a production quality dimension, and performing processing and data analysis on all abnormal detection results corresponding to different quality detection finished products to obtain a batch abnormal influence state corresponding to a semiconductor storage production batch; the batch abnormal state supervision of the production quality dimension is carried out on the semiconductor storage production batch; periodic stage quality detection data analysis is carried out on all batch production quality supervision data corresponding to different semiconductor storage production batches, and targeted different production optimization management prompts are carried out according to analysis results; the method and the device are used for solving the problems of poor reliability and comprehensiveness of semiconductor storage management caused by single semiconductor storage management scheme and single management level in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of semiconductor management technology, and in particular to a semiconductor storage intelligent management system. Background Art

[0002] Semiconductor memory management involves multiple aspects to ensure that semiconductor memory operates efficiently and reliably throughout its life cycle, from design to end use.

[0003] When implementing existing semiconductor storage management solutions, it is impossible to conduct quality supervision and data analysis on semiconductor storage from different dimensions, integrate the supervision and analysis results of different dimensions and implement quality supervision and analysis of the overall dimension, and adaptively perform dynamic optimization management of semiconductor storage based on the analysis results. The semiconductor storage management solution is single and the management level is single, which leads to poor reliability and comprehensiveness of semiconductor storage management. Summary of the invention

[0004] The purpose of the present invention is to provide a semiconductor storage intelligent management system to solve the technical problems of the existing semiconductor storage management scheme being single and the management level being single, which leads to poor reliability and comprehensiveness of semiconductor storage management.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A semiconductor storage intelligent management system includes a semiconductor storage batch production quality local supervision module, which is used to perform quality inspection on a number of finished products produced in the same batch of semiconductor storage from the production quality dimension, and process and analyze all abnormal inspection results corresponding to finished products with different quality inspections, obtain batch production quality supervision data and upload it to a supervision platform;

[0007] The semiconductor storage batch production quality stage supervision module is used to implement periodic stage quality inspection data analysis on all batch production quality supervision data corresponding to different semiconductor storage production batches, obtain the corresponding stage production quality supervision data and implement targeted stage production optimization management prompts;

[0008] Among them, all batch production quality supervision data and all after-sales problem data corresponding to all semiconductor storage production batches within the preset stage supervision cycle are counted, and all batch production quality supervision data and all after-sales problem data are processed and the stage abnormal impact mark corresponding to the stage supervision cycle is output;

[0009] Conduct data analysis on the stage abnormality impact identification, determine the batch abnormality impact status corresponding to the semiconductor storage production batch, and implement targeted stage production optimization management prompts.

[0010] Preferably, all the test results corresponding to the quality test of the finished products produced in the same batch of semiconductor storage are counted, and the finished products are marked as abnormal finished products according to the abnormal results in the test results, and the abnormal reasons corresponding to the abnormal finished products are obtained. When the reliability of the semiconductor storage production is processed according to the abnormal reasons, the abnormal reasons corresponding to the different abnormal finished products are input into the production reliability identification function for data analysis and the corresponding production reliability identification BKi is output;

[0011] The production reliability flag contains a value of 0 or 1, indicating whether the production status corresponding to the abnormal finished product is reliable or unreliable;

[0012] The production reliability identifications corresponding to different abnormal finished products are sorted and combined in the order of detection time to obtain a production reliability supervision sequence; the production reliability supervision sequence is traversed and analyzed;

[0013] If there is an element with a value of 1 in the production reliable supervision sequence, an overall production optimization control signal is generated and prompted.

[0014] Preferably, the expression for producing a reliable identification function is In the formula, YYi is the abnormal reason corresponding to different abnormal finished products; i is different abnormal finished products, i = {1, 2, 3, ..., n}; n is a positive integer; U is the set of abnormal reasons for production control.

[0015] Preferably, if there is no element with a value of 1 in the production reliable supervision sequence, an abnormal processing signal is generated, and the abnormal causes corresponding to different abnormal finished products are traversed and matched with the pre-built abnormal cause impact table to obtain the abnormal weights YQi corresponding to different abnormal causes; the total number of occurrences ni corresponding to different abnormal causes is counted respectively, and the formula is used to calculate the abnormal weights YQi. Calculate and obtain the batch abnormality impact value PY corresponding to the same production batch of semiconductor storage production; where NZ is the total number of all abnormal causes corresponding to the same production batch; PB is the quality abnormality limit value corresponding to the semiconductor storage production batch; [*] is the rounding function;

[0016] Data analysis is performed on the batch abnormality impact value to determine the batch abnormality impact status corresponding to the semiconductor storage production batch.

[0017] Preferably, if the batch abnormality impact value is 0, a batch abnormality impact normal signal is generated;

[0018] If the batch abnormality impact value is not 0, a batch abnormality impact abnormality signal is generated and a batch production optimization control prompt is generated;

[0019] Sort and combine batch abnormality impact values, batch abnormality impact normal signals, or batch abnormality impact abnormal signals to obtain batch abnormality impact analysis data;

[0020] The overall production optimization control signals or batch abnormality impact analysis data obtained by supervision are sorted and combined to obtain the batch production quality supervision data corresponding to the semiconductor storage production batch.

[0021] Preferably, all batch production quality supervision data corresponding to all semiconductor storage production batches within the preset stage supervision cycle are counted, and the corresponding batch abnormality impact values ​​of different batches of production quality supervision data are traversed and counted in turn, and all acquired batch abnormality impact values ​​are analyzed by the stage abnormality identification piecewise function and the stage abnormality impact mark BJ corresponding to the stage supervision cycle is output;

[0022] Among them, the expression of the stage anomaly recognition piecewise function is: Wherein, B1 and B2 are the minimum and maximum requirements for stage abnormality identification, respectively; JY is the stage abnormality impact value corresponding to all semiconductor storage production batches within the stage supervision cycle;

[0023] The stage abnormality impact indicator contains a value of 0, 1 or 2, indicating that the stage abnormality impact of all semiconductor storage production batches in the corresponding stage supervision cycle is normal, slightly abnormal or severely abnormal.

[0024] Preferably, by the formula Calculate and obtain the stage abnormal impact value JY corresponding to all semiconductor storage production batches within the stage supervision period; where N is the total number of abnormal impact values ​​corresponding to all batches.

[0025] Preferably, by the formula Calculate and obtain the stage abnormality impact value JY corresponding to all semiconductor storage production batches within the stage supervision period; where N1 and N2 are the total number of normal signals affected by batch abnormalities and the total number of abnormal signals affected by batch abnormalities, respectively; α is the abnormality impact coefficient, and its value range is [1, +∞).

[0026] Preferably, by the formula Calculate and obtain the stage abnormal impact value JY corresponding to all semiconductor storage production batches within the stage supervision cycle; where N is the total number of abnormal impact values ​​of all batches; β and η are the weight influence coefficients corresponding to different data items, and 0<β≤η<1, β+η=1; WQ is the after-sales weight corresponding to all after-sales problems occurring within the stage supervision cycle; N′ is the total number of all after-sales problems occurring within the stage supervision cycle; WB is the after-sales abnormal limit value corresponding to the stage supervision cycle.

[0027] Preferably, data analysis is performed on the stage abnormality impact flag, and if the stage abnormality impact flag is 0, a stage abnormality impact normal signal is generated;

[0028] If the stage abnormal impact indicator is 1, a mild abnormal signal of the stage abnormal impact is generated and a stage production optimization control prompt is generated;

[0029] If the stage abnormal impact indicator is 2, a batch abnormal impact severe abnormal signal is generated and an overall production optimization control prompt is provided.

[0030] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0031] The present invention performs quality inspection on several finished products produced in the same batch of semiconductor storage from the production quality dimension, and processes and performs data analysis on all abnormal detection results corresponding to different quality inspection finished products to obtain the batch abnormality impact status corresponding to the semiconductor storage production batch. While realizing batch abnormality status supervision in the production quality dimension of the semiconductor storage production batch, the present invention can also provide reliable local batch supervision data support for subsequent stage abnormality impact status analysis corresponding to different semiconductor storage production batches, thereby improving the diversity of semiconductor storage production batch data supervision analysis and the reliability of subsequent expansion and utilization.

[0032] The present invention improves the diversity and comprehensiveness of semiconductor storage production supervision by performing periodic stage quality inspection data analysis on all batch production quality supervision data corresponding to different semiconductor storage production batches, and implementing targeted different production optimization management prompts based on the analysis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The present invention will be further described below in conjunction with the accompanying drawings.

[0034] Figure 1 A module block diagram of a semiconductor storage intelligent management system according to the present invention.

[0035] Figure 2 The present invention is a principle block diagram of the implementation steps of a semiconductor storage intelligent management system. DETAILED DESCRIPTION

[0036] 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.

[0037] like Figure 1 to Figure 2 As shown, the present invention is a semiconductor storage intelligent management system, including a semiconductor storage batch production quality local supervision module, a semiconductor storage batch production quality stage supervision module and a supervision platform;

[0038] The semiconductor storage batch production quality local supervision module is used to perform quality inspection on several finished products produced in the same batch of semiconductor storage from the production quality dimension, and process and analyze all abnormal detection results corresponding to different quality inspection finished products, obtain batch production quality supervision data and upload it to the supervision platform; including:

[0039] It should be noted that semiconductor storage specifically includes but is not limited to integrated circuits, discrete devices, sensors, optoelectronic devices, power semiconductor devices and other semiconductor devices;

[0040] Statistics are collected for all the test results corresponding to the quality inspection of finished products produced in the same batch of semiconductor storage. The implementation of several finished product quality inspections can be realized based on the existing sampling scheme, and the finished products are marked as abnormal finished products according to the abnormal results in the test results. At the same time, the abnormal reasons corresponding to the abnormal finished products are obtained. The abnormal reasons are determined by the existing semiconductor storage production abnormality classification rules. When the reliability of the semiconductor storage production is processed according to the abnormal reasons, the abnormal reasons corresponding to the different abnormal finished products are input into the production reliability identification function for data analysis and the corresponding production reliability identification BKi is output;

[0041] Among them, the expression of the production reliable identification function is Wherein, YYi is the abnormal reason corresponding to different abnormal finished products; i is different abnormal finished products, i={1, 2, 3, ..., n}; n is a positive integer; U is the set of abnormal reasons for production control, which is determined by the specific production quality requirements of the actual production of semiconductor storage;

[0042] It should be noted that the production reliable identification is used to process data of all abnormal causes that occur in the same batch of semiconductor storage production and to digitally represent the production status of semiconductor storage;

[0043] The production reliability flag contains a value of 0 or 1, indicating whether the production status corresponding to the abnormal finished product is reliable or unreliable;

[0044] The production reliability identifications corresponding to different abnormal finished products are sorted and combined in the order of detection time to obtain a production reliability supervision sequence;

[0045] In an embodiment of the present invention, quality inspection is performed on several finished products produced in the same batch of semiconductor storage from the production quality dimension, and different abnormal detection results obtained by the inspection are processed and processed to obtain a corresponding production reliable supervision sequence, which can not only realize the digital representation of the batch production status corresponding to different abnormal causes and the active processing of abnormal production, but also provide reliable supervision data support for subsequent batch abnormal impact analysis and stage abnormal impact analysis.

[0046] Conduct traversal analysis of production reliable regulatory sequences;

[0047] If there is an element with a value of 1 in the production reliable supervision sequence, an overall production optimization control signal is generated and prompted; here, the overall production parameters need to be optimized and adjusted to meet the production quality inspection requirements of semiconductor storage;

[0048] If there is no element with a value of 1 in the production reliable supervision sequence, an abnormal processing signal is generated, and the abnormal causes corresponding to different abnormal finished products are traversed and matched with the pre-built abnormal cause impact table to obtain the abnormal weights YQi corresponding to different abnormal causes;

[0049] It should be explained that the abnormal cause impact table pre-stores a number of different abnormal causes and their corresponding abnormal weights. Different abnormal causes are pre-set with a corresponding abnormal weight, and the abnormal weight is used to digitize and differentiate the abnormal impact corresponding to the abnormal cause. The specific values ​​of different abnormal weights can be customized by professionals in this field based on production experience.

[0050] Count the total number of different abnormal reasons corresponding to ni respectively, and use the formula Calculate and obtain the batch abnormality impact value PY corresponding to the same production batch of semiconductor storage production; where NZ is the total number of all abnormal reasons corresponding to the same production batch; PB is the quality abnormality limit value corresponding to the semiconductor storage production batch, which can be determined according to the actual production quality requirements, or according to the median value of all batch abnormality impact values ​​corresponding to different production batches; [*] is the rounding function;

[0051] It should be noted that the batch abnormality impact value is used to calculate all abnormal data occurring in the same production batch to digitally represent its batch abnormality impact status;

[0052] When performing data analysis on the batch abnormality impact value to determine the batch abnormality impact status corresponding to the semiconductor storage production batch;

[0053] If the batch abnormality impact value is 0, a batch abnormality impact normal signal is generated;

[0054] If the batch abnormality impact value is not 0, a batch abnormality impact abnormality signal is generated and a batch production optimization control prompt is generated;

[0055] Sort and combine batch abnormality impact values, batch abnormality impact normal signals, or batch abnormality impact abnormal signals to obtain batch abnormality impact analysis data;

[0056] Sort and combine the overall production optimization control signals or batch abnormality impact analysis data obtained by supervision to obtain batch production quality supervision data corresponding to the semiconductor storage production batch;

[0057] In an embodiment of the present invention, quality inspection is performed on several finished products produced from the same batch of semiconductor storage from the production quality dimension, and all abnormal detection results corresponding to different quality inspection finished products are processed and data analyzed to obtain the batch abnormality impact status corresponding to the semiconductor storage production batch. While batch abnormality status supervision of the production quality dimension of the semiconductor storage production batch is achieved, reliable local batch supervision data support can be provided for subsequent stage abnormality impact status analysis corresponding to different semiconductor storage production batches, thereby improving the diversity of semiconductor storage production batch data supervision analysis and the reliability of subsequent expansion and utilization.

[0058] The semiconductor storage batch production quality stage supervision module is used to implement periodic stage quality inspection data analysis on all batch production quality supervision data corresponding to different semiconductor storage production batches, obtain the corresponding stage production quality supervision data and implement targeted stage production optimization management prompts; including:

[0059] According to the preset stage supervision cycle, all batches of production quality supervision data corresponding to all semiconductor storage production batches within the period are counted. The stage supervision cycle can be determined according to the preset supervision duration, or according to the preset total number of supervision batches. It is customized according to the actual application needs of the actual application scenario, and the corresponding batch abnormality impact values ​​of different batches of production quality supervision data are traversed and counted in turn. All the acquired batch abnormality impact values ​​are analyzed through the stage abnormality identification piecewise function and the stage abnormality impact mark BJ corresponding to the stage supervision cycle is output;

[0060] Among them, the expression of the stage anomaly recognition piecewise function is: Wherein, B1 and B2 are the minimum and maximum values ​​of the stage abnormality identification requirements, respectively, which can be determined according to the stage production quality requirement data corresponding to the actual semiconductor storage products; JY is the stage abnormality impact value corresponding to all semiconductor storage production batches within the stage supervision cycle;

[0061] It should be noted that the stage abnormality impact identification is used to digitally represent the stage abnormality impact corresponding to the stage supervision cycle by processing the production quality supervision data of different batches obtained by supervision;

[0062] The stage abnormality impact indicator includes a value of 0, 1 or 2, indicating that the stage abnormality impact of all semiconductor storage production batches in the corresponding stage supervision period is normal, slightly abnormal or severely abnormal;

[0063] It is worth noting that, unlike most of the prior art solutions which only use a single processing scheme to perform data processing and calculation on the stage abnormality impacts corresponding to all semiconductor storage production batches within the stage supervision cycle, which results in poor reliability and diversity of data processing and calculation, in the embodiment of the present invention, different processing schemes are used to implement diversified data processing on the stage abnormality impacts corresponding to all semiconductor storage production batches within the stage supervision cycle, which can effectively improve the reliability and diversity of corresponding dimensional data processing and subsequent analysis;

[0064] The steps for obtaining the stage abnormal impact value JY include:

[0065] Option 1: Using the formula Calculate and obtain the stage abnormal impact value JY corresponding to all semiconductor storage production batches within the stage supervision cycle; where N is the total number of abnormal impact values ​​corresponding to all batches;

[0066] Option 2: Using the formula Calculate and obtain the stage abnormal impact value JY corresponding to all semiconductor storage production batches within the stage supervision period; where N1 and N2 are the total number of normal signals affected by batch abnormalities and the total number of abnormal signals affected by batch abnormalities, respectively; α is the abnormal impact coefficient, and its value range is [1, +∞), and the specific value can be 1.2517;

[0067] Option 3: By formula Calculate and obtain the stage abnormal impact value JY corresponding to all semiconductor storage production batches within the stage supervision cycle; where N is the total number of abnormal impact values ​​of all batches; β and η are weight influence coefficients corresponding to different data items, and 0<β≤η<1, β+η=1, and the specific values ​​corresponding to β and η can be 0.375 and 0.625 respectively; WQ is the after-sales weight corresponding to all after-sales problems occurring within the stage supervision cycle; N′ is the total number of all after-sales problems occurring within the stage supervision cycle; WB is the after-sales abnormal limit value corresponding to the stage supervision cycle, which can be determined according to the actual production quality after-sales requirements;

[0068] Among them, a corresponding after-sales weight is pre-set for different after-sales problems, and the after-sales weight is used to digitally represent the after-sales abnormal impact corresponding to the after-sales problem. The specific values ​​of the after-sales weights corresponding to different after-sales problems can be determined by professional and technical personnel in this field according to the total number of historical occurrences of the after-sales problem;

[0069] It should be noted that different schemes can be implemented simultaneously, and the maximum value obtained by calculation is marked as the final stage abnormal impact value;

[0070] The stage abnormal impact value is used to process all abnormal data corresponding to all semiconductor storage production batches within the stage supervision cycle to digitally represent its stage abnormal impact;

[0071] When performing data analysis on the stage abnormality impact identification, determining the batch abnormality impact status corresponding to the semiconductor storage production batch and implementing targeted stage production optimization management prompts;

[0072] If the stage abnormality impact flag is 0, then a stage abnormality impact normal signal is generated;

[0073] If the stage abnormal impact indicator is 1, a mild abnormal signal of the stage abnormal impact is generated and a stage production optimization control prompt is generated; that is, targeted abnormal optimization processing is implemented for all production abnormalities and after-sales abnormalities that occur;

[0074] If the stage abnormality impact indicator is 2, a batch abnormality impact severe abnormality signal is generated and an overall production optimization control prompt is performed; that is, comprehensive optimization processing is implemented for all production parameters and processes.

[0075] In the embodiment of the present invention, by performing periodic stage quality inspection data analysis on all batch production quality supervision data corresponding to different semiconductor storage production batches, and implementing targeted different production optimization management prompts based on the analysis results, the diversity and comprehensiveness of semiconductor storage production supervision are improved.

[0076] In addition, the formulas involved in the above are all dimensionless and numerical calculations. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and simulating it with simulation software.

[0077] In the several embodiments provided by the present invention, it should be understood that the disclosed system can be implemented in other ways. For example, the above-described embodiments of the invention are only illustrative, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0078] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0079] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0080] It is obvious to a person skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the essential characteristics of the present invention.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A semiconductor storage intelligent management system, characterized in that: It includes a semiconductor storage batch production quality local supervision module, which is used to perform quality inspection on several finished products produced in the same batch of semiconductor storage from the production quality dimension, and process and analyze all abnormal detection results corresponding to finished products with different quality inspections, obtain batch production quality supervision data and upload it to the supervision platform; The semiconductor storage batch production quality stage supervision module is used to implement periodic stage quality inspection data analysis on all batch production quality supervision data corresponding to different semiconductor storage production batches, obtain the corresponding stage production quality supervision data and implement targeted stage production optimization management prompts; Among them, all batch production quality supervision data and all after-sales problem data corresponding to all semiconductor storage production batches within the preset stage supervision cycle are counted, and all batch production quality supervision data and all after-sales problem data are processed and the stage abnormal impact mark corresponding to the stage supervision cycle is output; Conduct data analysis on the stage abnormality impact identification, determine the batch abnormality impact status corresponding to the semiconductor storage production batch, and implement targeted stage production optimization management prompts.

2. A semiconductor storage intelligent management system according to claim 1, characterized in that: All the test results corresponding to the quality test of the finished products produced in the same batch of semiconductor storage are counted, and the finished products are marked as abnormal finished products according to the abnormal results in the test results. At the same time, the abnormal reasons corresponding to the abnormal finished products are obtained. When the reliability of the semiconductor storage production is processed according to the abnormal reasons, the abnormal reasons corresponding to the different abnormal finished products obtained are input into the production reliability identification function for data analysis and the corresponding production reliability identification BKi is output; The production reliability flag contains a value of 0 or 1, indicating whether the production status corresponding to the abnormal finished product is reliable or unreliable; The production reliability identifications corresponding to different abnormal finished products are sorted and combined in the order of detection time to obtain a production reliability supervision sequence; the production reliability supervision sequence is traversed and analyzed; If there is an element with a value of 1 in the production reliable supervision sequence, an overall production optimization control signal is generated and prompted.

3. A semiconductor storage intelligent management system according to claim 2, characterized in that: The expression for the production reliable identification function is In the formula, YYi is the abnormal reason corresponding to different abnormal finished products; i is different abnormal finished products, i = {1, 2, 3, ..., n}; n is a positive integer; U is the set of abnormal reasons for production control.

4. A semiconductor storage intelligent management system according to claim 2, characterized in that: If there is no element with a value of 1 in the production reliable supervision sequence, an abnormal processing signal is generated, and the abnormal causes corresponding to different abnormal finished products are traversed and matched with the pre-built abnormal cause impact table to obtain the abnormal weights YQi corresponding to different abnormal causes; the total number of occurrences ni corresponding to different abnormal causes is counted respectively, and the formula is used to calculate the abnormal weights YQi. Calculate and obtain the batch abnormality impact value PY corresponding to the semiconductor storage production of the same production batch; where NZ is the total number of all abnormal causes corresponding to the same production batch; PB is the quality abnormality limit value corresponding to the semiconductor storage production batch; [*] is the rounding function; Data analysis is performed on the batch abnormality impact value to determine the batch abnormality impact status corresponding to the semiconductor storage production batch.

5. A semiconductor storage intelligent management system according to claim 4, characterized in that: If the batch abnormality impact value is 0, a batch abnormality impact normal signal is generated; If the batch abnormality impact value is not 0, a batch abnormality impact abnormality signal is generated and a batch production optimization control prompt is generated; Sort and combine batch abnormality impact values, batch abnormality impact normal signals, or batch abnormality impact abnormal signals to obtain batch abnormality impact analysis data; The overall production optimization control signals or batch abnormality impact analysis data obtained by supervision are sorted and combined to obtain the batch production quality supervision data corresponding to the semiconductor storage production batch.

6. A semiconductor storage intelligent management system according to claim 5, characterized in that: According to the preset stage supervision cycle, all batch production quality supervision data corresponding to all semiconductor storage production batches within the period are counted, and the corresponding batch abnormality impact values ​​of different batch production quality supervision data are traversed and counted in turn, and all the acquired batch abnormality impact values ​​are analyzed by the stage abnormality identification piecewise function and the stage abnormality impact mark BJ corresponding to the stage supervision cycle is output; Among them, the expression of the stage anomaly recognition piecewise function is: Wherein, B1 and B2 are the minimum and maximum requirements for stage abnormality identification, respectively; JY is the stage abnormality impact value corresponding to all semiconductor storage production batches within the stage supervision cycle; The stage abnormality impact indicator contains a value of 0, 1 or 2, indicating that the stage abnormality impact of all semiconductor storage production batches in the corresponding stage supervision cycle is normal, slightly abnormal or severely abnormal.

7. A semiconductor storage intelligent management system according to claim 6, characterized in that: By formula Calculate and obtain the stage abnormal impact value JY corresponding to all semiconductor storage production batches within the stage supervision period; where N is the total number of abnormal impact values ​​corresponding to all batches.

8. A semiconductor storage intelligent management system according to claim 6, characterized in that: By formula Calculate and obtain the stage abnormality impact value JY corresponding to all semiconductor storage production batches within the stage supervision period; where N1 and N2 are the total number of normal signals affected by batch abnormalities and the total number of abnormal signals affected by batch abnormalities, respectively; α is the abnormality impact coefficient, and its value range is [1, +∞).

9. The semiconductor storage intelligent management system according to claim 6, characterized in that: By formula Calculate and obtain the stage abnormal impact value JY corresponding to all semiconductor storage production batches within the stage supervision cycle; where N is the total number of abnormal impact values ​​of all batches; β and η are the weight influence coefficients corresponding to different data items, and 0<β≤η<1, β+η=1; WQ is the after-sales weight corresponding to all after-sales problems occurring within the stage supervision cycle; N′ is the total number of all after-sales problems occurring within the stage supervision cycle; WB is the after-sales abnormal limit value corresponding to the stage supervision cycle.

10. The semiconductor storage intelligent management system according to claim 6, characterized in that: Perform data analysis on the stage abnormality impact flag, and if the stage abnormality impact flag is 0, generate a stage abnormality impact normal signal; If the stage abnormal impact indicator is 1, a mild abnormal signal of the stage abnormal impact is generated and a stage production optimization control prompt is generated; If the stage abnormal impact indicator is 2, a batch abnormal impact severe abnormal signal is generated and an overall production optimization control prompt is provided.

Images