Method and device for determining yield impact factor and storage medium

Abstract

The invention discloses a yield impact factor determination method and device and a storage medium, and belongs to the technical field of data analysis. The method comprises the steps of obtaining a first sequence and a second sequence corresponding to a plurality of parameters respectively, determining at least one yield change point based on the first sequence, and determining yield influence factors of a plurality of groups of products from the plurality of parameters based on the at least one yield change point and the second sequence corresponding to the plurality of parameters respectively. According to the method, the second sequence of the multiple parameters is analyzed through the yield change points, the parameters influencing the yield can be accurately determined from the multiple parameters, the parameters influencing the product yield can be analyzed subsequently, and therefore enterprises can respond to abnormal fluctuation in production rapidly, the production process is optimized, and the product quality stability is improved.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and in particular to a method, device and storage medium for determining yield influencing factors. Background Art

[0002] In industrial production, the importance of product yield (also known as "qualified rate") cannot be ignored. It is not only a core indicator for measuring an enterprise's production efficiency and product quality, but also deeply related to the formulation of cost control strategies and the level of market competitiveness. Since there are various parameters in the product production process, such as the temperature of the factory environment, the humidity of the factory environment, the temperature of the equipment, the pressure of the equipment, etc., these multiple parameters permeate every subtle link of the production process and interweave to affect the yield of the product. Therefore, it becomes particularly difficult to accurately determine the parameters that will affect the yield (i.e., the yield influencing factors) from these parameters. Therefore, a method for determining the yield influencing factors is urgently needed to help enterprises accurately identify the parameters that affect the yield in the production process, so as to facilitate the subsequent analysis of the parameters that affect the product yield. Summary of the invention

[0003] The present application provides a method, device and storage medium for determining yield influencing factors, which can identify parameters that affect the yield during the production process. The technical solution is as follows:

[0004] On the one hand, a method for determining a yield influencing factor is provided, the method comprising: obtaining a first sequence and a second sequence corresponding to a plurality of parameters, the first sequence comprising the yields corresponding to a plurality of groups of products of the same model, the plurality of parameters referring to parameters involved in the production process of the plurality of groups of products, the second sequence comprising parameter values ​​corresponding to the corresponding parameters at a plurality of moments in the production process of the plurality of groups of products; determining at least one yield change point based on the first sequence, the yield change point being the yield at which an abnormal change occurs in the first sequence; determining the yield influencing factors of the plurality of groups of products from the plurality of parameters based on the at least one yield change point and the second sequences corresponding to the plurality of parameters.

[0005] In a possible implementation, the determining the yield influencing factors of the multiple groups of products from the multiple parameters based on the at least one yield change point and the second sequences respectively corresponding to the multiple parameters includes:

[0006] Based on the at least one yield change point and the second sequences respectively corresponding to the multiple parameters, determining candidate influencing parameters respectively corresponding to the at least one yield change point from the multiple parameters, the candidate influencing parameters being parameters in the multiple parameters that have an impact on the corresponding yield change point;

[0007] Based on the candidate influencing parameters respectively corresponding to the at least one yield change point, yield influencing factors of the multiple groups of products are determined.

[0008] In a possible implementation, determining, from the multiple parameters, candidate influencing parameters corresponding to the at least one yield change point respectively based on the at least one yield change point and the second sequences corresponding to the multiple parameters respectively, includes:

[0009] Determine, based on a target yield change point and a second sequence corresponding to each of the multiple parameters, the association between the target yield change point and each of the multiple parameters, wherein the target yield change point is any one of the at least one yield change point;

[0010] Based on the correlation between the target yield change points and the multiple parameters, candidate influencing parameters corresponding to the target yield are determined from the multiple parameters.

[0011] In a possible implementation, determining the correlation between the target yield change point and the plurality of parameters based on the target yield change point and the second sequences respectively corresponding to the plurality of parameters includes:

[0012] Based on the target yield change point, determining a first subsequence from the first sequence, the first subsequence including the target yield change point and a plurality of yields adjacent to and before the target yield change point;

[0013] Determine a second subsequence from a second sequence corresponding to a target parameter, the target parameter being any one of the multiple parameters, the second subsequence comprising parameter values ​​of the target parameter within a target time period, the target time period being a time period during which the target parameter participates in a production process of a target product, the target product comprising a product corresponding to a yield in the first subsequence;

[0014] Based on the first subsequence and the second subsequence, a correlation between the target yield change point and the target parameter is determined.

[0015] In a possible implementation, determining, from the multiple parameters, candidate influencing parameters corresponding to the at least one yield change point respectively based on the at least one yield change point and the second sequences corresponding to the multiple parameters respectively, includes:

[0016] Based on the second sequences corresponding to the multiple parameters respectively, determining at least one parameter change point corresponding to the multiple parameters respectively, the parameter change point being a parameter value in the second sequence corresponding to the corresponding parameter where an abnormal change occurs;

[0017] Based on the target yield change point and at least one parameter change point corresponding to the multiple parameters respectively, a candidate influencing parameter corresponding to the target yield change point is determined from the multiple parameters, and the target yield change point is any one of the at least one yield change point.

[0018] In a possible implementation, the determining, based on the target yield change point and at least one parameter change point respectively corresponding to the multiple parameters, a candidate influencing parameter corresponding to the target yield change point from the multiple parameters includes:

[0019] Based on the target yield change point, determining a first subsequence from the first sequence, the first subsequence including the target yield change point and a plurality of yields adjacent to and before the target yield change point;

[0020] Determine a second subsequence from a second sequence corresponding to a target parameter, the target parameter being any one of the multiple parameters, the second subsequence comprising parameter values ​​of the target parameter within a target time period, the target time period being a time period during which the target parameter participates in a production process of a target product, the target product comprising a product corresponding to a yield in the first subsequence;

[0021] If a parameter change point corresponding to the target parameter exists in the second subsequence, the target parameter is determined to be a candidate influencing parameter corresponding to the target yield change point.

[0022] On the other hand, a device for determining a yield influencing factor is provided, the device comprising:

[0023] an acquisition module, configured to acquire a first sequence and a second sequence corresponding to a plurality of parameters, wherein the first sequence includes yields corresponding to a plurality of groups of products of the same model, the plurality of parameters refer to parameters involved in a production process of the plurality of groups of products, and the second sequence includes parameter values ​​corresponding to the corresponding parameters at a plurality of moments in the production process of the plurality of groups of products;

[0024] A first determining module, configured to determine at least one yield change point based on the first sequence, wherein the yield change point is a yield at which an abnormal change occurs in the first sequence;

[0025] The second determination module is used to determine the yield influencing factors of the multiple groups of products from the multiple parameters based on the at least one yield change point and the second sequences respectively corresponding to the multiple parameters.

[0026] On the other hand, an electronic device is provided, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the steps of the yield influencing factor determination method described above.

[0027] On the other hand, a computer-readable storage medium is provided, wherein a computer program is stored in the storage medium, and when the computer program is executed by a processor, the steps of the method for determining the yield influencing factor described above are implemented.

[0028] On the other hand, a computer program product comprising instructions is provided. When the instructions are executed on a computer, the computer executes the steps of the yield influencing factor determination method described above.

[0029] The technical solution provided by this application can at least bring the following beneficial effects:

[0030] Since the yield change point is the yield that undergoes abnormal changes in the first sequence, and the abnormal change in the product yield is usually related to the parameters in the production process, the second sequence of multiple parameters is analyzed through the yield change point, and the parameters that affect the yield, that is, the yield influencing factors, can be accurately determined from multiple parameters, so as to facilitate the subsequent analysis of the parameters that affect the product yield, thereby helping enterprises to quickly respond to abnormal fluctuations in production, optimize production processes, and improve product quality stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0032] Figure 1 It is a flow chart of a method for determining a yield influencing factor provided in an embodiment of the present application;

[0033] Figure 2 It is a structural schematic diagram of a device for determining a yield influencing factor provided in an embodiment of the present application;

[0034] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0036] Before explaining in detail the method for determining the yield influencing factor provided in the embodiment of the present application, the application scenarios involved in the embodiment of the present application are first introduced.

[0037] In modern industrial production, the production line of a product usually includes multiple production equipment, each of which usually corresponds to a different production link. The initial product needs to be processed by multiple production equipment on the production line to obtain the final product. After the product is produced, it can also be tested in all directions and from multiple angles through the yield detection station to determine whether the product meets the quality requirements, so as to control the yield of the product. It can be seen that the importance of product yield (also known as "qualified rate") cannot be ignored. It is not only a core indicator for measuring the production efficiency and product quality of an enterprise, but also deeply related to the formulation of cost control strategies and the level of market competitiveness.

[0038] However, due to the presence of various parameters in the product production process, such as the temperature of the factory environment, the humidity of the factory environment, the temperature of each production equipment, the pressure of each production equipment, the equipment parameters of the production equipment itself, etc., these multiple parameters permeate every subtle link of the production process, interweaving and affecting the yield of the product, therefore, it is particularly difficult to accurately determine the parameters that will affect the yield (i.e., the yield influencing factor) from these parameters. Based on this, the embodiment of the present application provides a method for determining the yield influencing factor, which can determine the yield influencing factors of multiple groups of products from multiple parameters by determining the yield inflection point in the first sequence and the second sequence corresponding to multiple parameters. Since the yield inflection point is the yield that changes abnormally in the first sequence, and the abnormal change in the yield of the product is usually related to the parameters in the production process, therefore, the embodiment of the present application analyzes the second sequence of multiple parameters through the yield inflection point, and can accurately determine the parameters that affect the yield from multiple parameters, i.e., the yield influencing factor, so as to facilitate the subsequent analysis of the parameters that affect the product yield.

[0039] The execution subject of the method provided in the embodiment of the present application is an electronic device, which may be a PC (Personal Computer), a mobile phone, a PDA (Personal Digital Assistant), a Pocket PC (PPC), a tablet computer, a server, etc.

[0040] It should be noted that the application scenarios and execution entities described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the emergence of new application scenarios and the evolution of technology, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0041] Next, the method for determining the yield influencing factor provided in the embodiment of the present application is explained in detail.

[0042] Figure 1 This is a flow chart of a method for determining a yield influencing factor provided in an embodiment of the present application, and the method is applied to electronic equipment. Figure 1 , the method comprises the following steps.

[0043] Step 101: Obtain a first sequence and a second sequence corresponding to multiple parameters, wherein the first sequence includes yields corresponding to multiple groups of products of the same model, the multiple parameters refer to parameters involved in the production process of the multiple groups of products, and the second sequence includes parameter values ​​corresponding to the corresponding parameters at multiple moments in the production process of the multiple groups of products.

[0044] In a possible implementation manner, the multiple parameters include at least one type of parameters among device status parameters, environment parameters, and device maintenance parameters.

[0045] Since the product needs to be processed by at least one production equipment during the production process, in this case, the equipment status parameters are used to characterize the status of the corresponding production equipment, the environment parameters are used to characterize the product production environment, and the equipment maintenance parameters are used to characterize the replacement of parts of the corresponding production equipment, and / or the changes in the equipment parameters of the corresponding production equipment.

[0046] For example, the equipment status parameters include at least one of the following: the temperature of the production equipment, the pressure of the production equipment, the vibration frequency of the production equipment, the sound intensity of the production equipment, and the number of times the production equipment is washed and cleaned. Among them, the second sequence corresponding to the temperature of the production equipment represents the change of the temperature of the production equipment over time; the second sequence corresponding to the pressure of the production equipment represents the change of the pressure of the production equipment over time; the second sequence corresponding to the vibration frequency of the production equipment represents the change of the vibration frequency of the production equipment over time; the second sequence corresponding to the sound intensity of the production equipment represents the change of the sound intensity of the production equipment over time; the second sequence corresponding to the number of times the production equipment is washed and cleaned represents the change of the number of times the production equipment is washed and cleaned over time.

[0047] For example, the environmental parameters include at least one of the following: factory temperature and factory humidity. The second sequence corresponding to the factory temperature represents the change of the factory temperature over time; the second sequence corresponding to the factory humidity represents the change of the factory humidity over time.

[0048] For example, the equipment maintenance parameters include replacement conditions corresponding to at least one part and change conditions corresponding to at least one equipment parameter. For a target part in at least one part, the second sequence corresponding to the replacement condition of the target part represents the replacement condition of the target part over time, and the replacement condition indicates whether the part is replaced; for a target device parameter in at least one equipment parameter, the second sequence corresponding to the change condition of the device parameter represents the change condition of the target device parameter over time.

[0049] Since the parts corresponding to different production equipment and the equipment parameters included in different production equipment are different (for example, at least one part corresponding to the etching equipment includes photoresist, etc., and at least one equipment parameter corresponding to the etching equipment includes etching rate, etching deviation, etc., and at least one part corresponding to the lithography equipment includes mask, shutter, light source laser, etc., and at least one equipment parameter corresponding to the lithography equipment includes scanning speed, resolution, etc.), therefore, the embodiments of the present application do not limit the specific content of at least one part and equipment parameter.

[0050] In some embodiments, the electronic device stores a first sequence and second sequences corresponding to a plurality of parameters respectively. In this case, the electronic device can directly obtain the first sequence and the second sequences corresponding to the plurality of parameters respectively.

[0051] In other embodiments, the data server stores the first sequence and second sequences corresponding to the multiple parameters respectively, and the electronic device can communicate with the data server and obtain the first sequence and second sequences corresponding to the multiple parameters respectively from the database.

[0052] For example, the first sequence and the second sequence corresponding to the multiple parameters are stored in different data servers. In this case, the electronic device can extract the first sequence and the second sequence corresponding to the multiple parameters into the data lake or data middle platform, perform data warehouse management, and obtain data from the data middle platform when needed, thereby reducing the pressure of frequent access to the data server.

[0053] In a possible implementation, the first sequence includes yields corresponding to multiple time periods, the yield corresponding to a time period is the yield of products that pass through a yield detection station in the time period, multiple time periods correspond to multiple groups of products, and the products that pass through a yield detection station in each time period are a group of products. Multiple time periods do not overlap, and the duration of the multiple time periods can be the same or different, which is not limited in the embodiments of the present application. If the duration of multiple time periods is the same, it means that the yield is determined periodically.

[0054] Among them, the yield inspection site is used to inspect the quality of the product to determine the yield of the product.

[0055] In some embodiments, the yield detection site may periodically report the yield, and the period length may be a first duration. For example, the yield of the product detected in the current cycle may be reported at the end of the current cycle. The first duration may be 1 minute or 2 minutes, etc., which is not limited in the embodiments of the present application.

[0056] In other embodiments, the yield inspection site may also calculate and report the yield based on the inspection results of x products after inspecting x products. In this case, the x products form a group of products, and the time period corresponding to the yield is the time period corresponding to the earliest time when the x products enter the yield inspection site and the latest time when the products enter the yield inspection site.

[0057] In a possible implementation manner, the second sequence corresponding to the parameter includes parameter values ​​corresponding to the parameter at multiple time points.

[0058] In some embodiments, the time interval between two adjacent moments in the multiple moments is a second time length. That is, the parameter values ​​of the parameters in the second sequence are obtained by periodic statistics. In this case, the yield of the product detected in the current cycle can be reported at the end of the current cycle. The second time length can be 1 minute or 10 minutes, etc., which is not limited in the embodiments of the present application.

[0059] For example, for the parameter of the temperature of the production equipment, the production equipment 1 can report its own temperature every 1 minute, so that the second sequence corresponding to the temperature of the production equipment can be obtained. For another example, for the parameter of the replacement of parts, the production equipment 1 can report the replacement of its own part 1 every 1 minute, so that the second sequence corresponding to the replacement of the part 1 of the production equipment can be obtained. For another example, for the parameter of the change of equipment parameters, the production equipment 1 can report the value of its own equipment parameter 1 every 1 minute.

[0060] It should be noted that, in order to facilitate subsequent data analysis, the replacement status of the part can be represented by a numerical value. In some embodiments, the first value represents replacement, the second value represents non-replacement, and the first value is different from the second value. For example, the first value can be 1, and the second value can be 0.

[0061] In some embodiments, after obtaining the first sequence and the second sequence corresponding to multiple parameters respectively, data integration can be performed on the first sequence and the second sequence corresponding to the multiple parameters respectively, and the first sequence after the data integration is determined as the first sequence, and the second sequence corresponding to the multiple parameters after the data integration is determined as the second sequence corresponding to the multiple parameters respectively.

[0062] For the convenience of description, the first sequence without data integration will be referred to as the first sequence before integration, and the second sequences corresponding to the multiple parameters without data integration will be referred to as the second sequences before integration corresponding to the multiple parameters.

[0063] Since the amount of data in the first sequence before integration and the multiple second sequences before integration may be large, resulting in a long sequence length, which is not conducive to subsequent data analysis, in this case, based on the first aggregation time, the first sequence before integration and the second sequences before integration corresponding to the multiple parameters can be integrated to obtain the first sequence after data integration and the second sequences after data integration corresponding to the multiple parameters.

[0064] For the first sequence before integration, let j=1. If the jth time period is not the last time period of the sequence, then obtain multiple first time periods from the jth time period to the yth time period in the sequence. The yth time period is the time period corresponding to the end time that is less than the target end time and has the smallest difference with the target end time among the end times of the multiple time periods. The target end time is the time after adding the first aggregation time length on the basis of the start time of the jth time period. Based on the yields corresponding to the multiple first time periods, determine the target yield and the target time period corresponding to the target yield. The target time period is any time period from the jth time period to the yth time period. Let j=y, and re-execute the above step of obtaining multiple first time periods from the jth time period to the yth time period in the sequence if the jth time period is not the last time period of the sequence; if the jth time period is the last time period of the sequence, determine the determined target yield and the target time period corresponding to the target yield as the first sequence after data integration.

[0065] In some embodiments, based on the yields corresponding to the multiple first time periods, the process of determining the target yield includes: determining the mode, maximum value, and minimum value of the yields corresponding to the multiple first time periods as the target yield, or determining the average value of the yields corresponding to the multiple first time periods as the target yield.

[0066] For any sequence in the second sequence before data integration corresponding to multiple parameters, let i=1. If the i-th moment is not the last moment of the sequence, then obtain multiple first moments from the i-th moment to the x-th moment in the sequence, and the x-th moment is the moment after adding the first aggregation time length on the basis of the i-th moment. Based on the parameter values ​​corresponding to the multiple first moments, determine the target parameter value and the target moment corresponding to the target parameter value. The target moment is any moment from the i-th moment to the x-th moment. Let i=x, and re-execute the above step of obtaining multiple first moments from the i-th moment to the x-th moment in the sequence if the i-th moment is not the last moment of the sequence; if the i-th moment is the last moment of the sequence, determine the determined target parameter value and the target moment corresponding to the target parameter value as the second sequence after data integration. In the same way, each sequence in the second sequence before data integration corresponding to multiple parameters is processed to obtain the second sequence after data integration corresponding to multiple parameters.

[0067] In some embodiments, based on the parameter values ​​corresponding to the multiple first moments, the implementation process of determining the target parameter value includes: determining the mode, maximum value, and minimum value of the parameter values ​​corresponding to the multiple first moments as the target parameter value, or determining the average value of the parameter values ​​corresponding to the multiple first moments as the target parameter value.

[0068] It should be noted that for the parameter of the number of water washing and cleaning times, in addition to determining the target parameter value based on the parameter values ​​corresponding to the multiple first moments through the above method, the sum of the parameter values ​​corresponding to the multiple first moments can also be determined as the target parameter value.

[0069] The first aggregation time is greater than the first time, and the first aggregation time is greater than the second time. The first aggregation time is set in advance, for example, the first aggregation time may be 1 hour. It may also be modified according to requirements in different situations.

[0070] Step 102: Determine at least one yield change point based on the first sequence, where the yield change point is the yield at which an abnormal change occurs in the first sequence.

[0071] There are multiple implementations of determining at least one yield change point based on the first sequence, two of which are introduced below.

[0072] The first method is to input the first sequence into the time series model to obtain at least one yield change point in the first sequence output by the time series model.

[0073] In some embodiments, the first sequence may be directly input into the time series model to obtain at least one yield change point in the first sequence output by the time series model.

[0074] In other embodiments, the first sequence can be divided into multiple window subsequences, each window subsequence includes multiple yields, and each window subsequence is input into the time series model to obtain the yield change point in the corresponding window subsequence output by the time series model.

[0075] For example, a sliding window technique may be used to move a fixed-size window on the time series, and each window subsequence is input into the time series model to obtain a yield change point in the corresponding window subsequence output by the time series model.

[0076] It should be noted that before the first sequence is input into the time series model to obtain at least one yield change point in the first sequence output by the time series model, the time series model may also be trained. That is, multiple first training sequences and yield change points in the multiple first training sequences are obtained, the first training sequences are used as inputs of the time series model, the yield change points in the first training sequences are used as outputs of the time series model, and the time series model is trained.

[0077] In one embodiment, the time series model can be an ARIMA (Autoregressive Integrated Moving Average) model, an LSTM (long-short term memory) network model, a GRU (gate recurrent unit), etc., which is not limited to the embodiments of the present application.

[0078] The second method is to input any yield in the first sequence into the autoencoder to obtain a reconstructed yield input by the autoencoder. If the difference between the reconstructed yield and the yield is greater than the difference threshold, the yield is determined as a yield change point. Each yield in the first sequence is processed in the same way to obtain at least one yield change point.

[0079] An autoencoder is an unsupervised learning neural network that learns an effective encoding (i.e., a low-dimensional representation) of input data through a combination of an encoder and a decoder, and reconstructs the original input data from this encoding. The core idea of ​​an autoencoder is to learn an effective representation of data in the process of compressing data (through an encoder) and decompressing data (through a decoder), while minimizing the reconstruction error. In this case, normal data can be effectively compressed by the encoder and accurately reconstructed by the decoder, while abnormal data may not be well reconstructed due to its different distribution from the training data, resulting in a large reconstruction error. Therefore, the yield at which the difference between the reconstructed yield and the yield is greater than the difference threshold can be determined as the yield change point.

[0080] The difference threshold is set in advance and can be adjusted according to needs in different situations.

[0081] In some embodiments, the electronic device includes a display screen. In this case, after determining at least one yield change point, a first prompt information may also be displayed, where the first prompt information is used to indicate that there is an abnormality in the yield of the product.

[0082] In a possible implementation, the first prompt information further includes a product identifier corresponding to at least one yield change point.

[0083] Step 103: Based on at least one yield change point and the second sequences corresponding to the multiple parameters, determine yield influencing factors of multiple groups of products from the multiple parameters.

[0084] Based on at least one yield change point and a second sequence corresponding to multiple parameters, candidate influencing parameters corresponding to at least one yield change point are determined from multiple parameters, where the candidate influencing parameters are parameters among the multiple parameters that affect the corresponding yield change point. Based on the candidate influencing parameters corresponding to at least one yield change point, yield influencing factors for multiple groups of products are determined.

[0085] Based on at least one yield change point and a second sequence corresponding to a plurality of parameters, there are multiple implementation methods for determining candidate influencing parameters corresponding to at least one yield change point from a plurality of parameters, two of which are introduced below.

[0086] The first implementation method is to determine the correlation between the target yield change point and the multiple parameters based on the target yield change point and the second sequence corresponding to the multiple parameters, where the target yield change point is any one of the at least one yield change point; based on the correlation between the target yield change point and the multiple parameters, determine the candidate influencing parameters corresponding to the target yield from the multiple parameters.

[0087] In some embodiments, based on the target yield change point and the second sequence corresponding to the multiple parameters, the implementation process of determining the correlation between the target yield change point and the multiple parameters includes: based on the target yield change point, determining a first subsequence from the first sequence, the first subsequence including the target yield change point and the multiple yields adjacent to each other before and after the target yield change point; determining a second subsequence from the second sequence corresponding to the target parameter, the target parameter is any one of the multiple parameters, the second subsequence includes the parameter value of the target parameter within a target time period, the target time period is the time period in which the target parameter participates in the production process of the target product, and the target product includes the product corresponding to the yield in the first subsequence; based on the first subsequence and the second subsequence, determining the correlation between the target yield change point and the target parameter.

[0088] The implementation method of determining the second subsequence from the second sequence corresponding to the target parameter includes: determining the product corresponding to the yield in the first subsequence as the first product, and if the target parameter is an equipment status parameter or an equipment maintenance parameter, determining the target production equipment corresponding to the target parameter, obtaining the production data of the target production equipment, the production data of the target production equipment including the processing start time and processing end time of each product passing through the target production equipment by the target production equipment, determining the processing start time and processing end time of each product in the first product by the target production equipment from the production data of the target production equipment, determining the earliest processing start time in the first product as the target start time, determining the latest processing end time in the first product as the target end time, and determining the sequence corresponding to the target start time and the target end time in the second subsequence corresponding to the target parameter as the second subsequence. If the target parameter is an environmental parameter, obtain the factory's production data and the inspection records of the yield inspection site, the factory's production data includes the first moment when each product enters the factory, and the inspection records include the second moment when each product enters the yield inspection site; determine the first moment of each of the first products from the factory's production data, determine the earliest moment of the first moment in the first product as the target start time, determine the latest moment of the second moment in the first product as the target end time, and determine the sequence corresponding to the target start time and the target end time in the second subsequence corresponding to the target parameter as the second subsequence.

[0089] There are multiple implementation methods for determining the correlation between the target yield change point and the target parameter based on the first subsequence and the second subsequence, and two of the implementation methods are introduced below.

[0090] Implementation method 1: Determine the correlation between the first subsequence and the second subsequence through a dynamic time warping algorithm to obtain the correlation between the target yield change point and the target parameter.

[0091] In some embodiments, the correlation between the first subsequence and the second subsequence may be determined directly through a dynamic time warping algorithm.

[0092] In other embodiments, the first subsequence can be flipped to obtain a flipped sequence of the first subsequence, and then the correlation between the first subsequence and the second subsequence can be determined by a dynamic time warping algorithm to obtain a first correlation. The correlation between the flipped sequence of the first subsequence and the second subsequence can be determined by a dynamic time warping algorithm to obtain a second correlation. The correlation with the largest value between the first correlation and the second correlation is determined as the correlation between the target yield change point and the target parameter.

[0093] In some embodiments, each yield in the first subsequence is multiplied by -1 to obtain a flip sequence of the first subsequence.

[0094] Of course, in practical applications, in addition to flipping the first subsequence, the second subsequence can also be flipped. In this case, the correlation between the first subsequence and the second subsequence is determined by a dynamic time warping algorithm to obtain a first correlation. The correlation between the first subsequence and the flipped sequence of the second subsequence is determined by a dynamic time warping algorithm to obtain a second correlation. The correlation with the largest value between the first correlation and the second correlation is determined as the correlation between the target yield change point and the target parameter. The embodiments of the present application do not limit this.

[0095] Since the correlation between two sequences includes positive correlation and negative correlation, where if one sequence shows an upward trend and the other sequence also shows an upward trend, it can be determined that the two sequences are positively correlated, and if one sequence shows an upward trend and the other sequence also shows a downward trend, it can be determined that the two sequences are negatively correlated. Therefore, among the multiple parameters, there are parameters that are positively correlated with the yield change, and there are also parameters that are negatively correlated with the yield change. However, the correlation obtained by the dynamic time warping algorithm indicates the degree of positive correlation between the two sequences. In this case, the correlation between the parameter that is negatively correlated with the yield change and the yield can be determined by flipping the first subsequence or the second subsequence, so that the accuracy of the final determined influencing factor can be guaranteed.

[0096] Implementation method 2, performing wavelet transform on the first subsequence and the second subsequence respectively to obtain a first transform result and a second transform result, wherein the first transform result and the second transform result both include multiple scales and wavelet coefficients corresponding to each scale; based on the first transform result and the second transform result, determining the Pearson correlation coefficients corresponding to the multiple scales respectively, the Pearson correlation coefficient indicates the correlation between the wavelet coefficients corresponding to the corresponding scale in the first transform result and the wavelet coefficients corresponding to the corresponding scale in the second transform result; based on the Pearson correlation coefficients corresponding to the multiple scales respectively, determining the correlation between the first subsequence and the second subsequence to obtain the correlation between the target yield change point and the target parameter.

[0097] For the target scale among the multiple scales, based on the wavelet coefficient corresponding to the target scale in the first transformation result and the wavelet coefficient corresponding to the target scale in the second transformation result, the Pearson correlation coefficient corresponding to the target scale is determined according to the relevant algorithm. Each scale among the multiple scales is processed in the same way to obtain the Pearson correlation coefficients corresponding to the multiple scales.

[0098] In some embodiments, the average value of the Pearson correlation coefficients corresponding to the multiple scales can be determined as the correlation between the first subsequence and the second subsequence. In other embodiments, the mode, maximum value or minimum value of the Pearson correlation coefficients corresponding to the multiple scales can also be determined as the correlation between the first subsequence and the second subsequence, which is not limited in the embodiments of the present application.

[0099] In a possible implementation, before performing wavelet transform on the first subsequence and the second subsequence respectively, the first subsequence and the second subsequence may be preprocessed, and then wavelet transform is performed on the preprocessed first subsequence and the preprocessed second subsequence respectively, and the amount of data in the preprocessed first subsequence and the preprocessed second subsequence is the same.

[0100] In some embodiments, preprocessing includes at least one of data normalization and data padding.

[0101] In some embodiments, the first subsequence and the second subsequence may be normalized respectively to obtain the normalized first subsequence and the normalized second subsequence.

[0102] In some other embodiments, data interpolation may be performed on the subsequence with the least amount of data in the first subsequence and the second subsequence to achieve data filling of the sequence.

[0103] If the sequence is periodic, the subsequence with the least amount of data in the first subsequence and the second subsequence may be extended in a periodic extension manner to achieve data filling of the sequence. This embodiment of the application does not limit this.

[0104] The second implementation method is to determine at least one parameter change point corresponding to the multiple parameters based on the second sequences corresponding to the multiple parameters, where the parameter change point is a parameter value that undergoes an abnormal change in the second sequence corresponding to the corresponding parameter; based on the target yield change point and at least one parameter change point corresponding to the multiple parameters, determine the candidate influencing parameters corresponding to the target yield change point from the multiple parameters, where the target yield change point is any one of the at least one yield change point.

[0105] Among them, based on the second sequences corresponding to the multiple parameters, the implementation method of determining at least one parameter change point corresponding to the multiple parameters is similar to the implementation method of "determining at least one yield change point based on the first sequence, the yield change point is the yield that undergoes abnormal changes in the first sequence" in step 102. For the detailed process, please refer to the relevant content above, which will not be repeated here.

[0106] Based on a target yield change point and at least one parameter change point corresponding to a plurality of parameters, an implementation process of determining a candidate influencing parameter corresponding to a target yield change point from a plurality of parameters includes: determining a first subsequence from a first sequence based on the target yield change point, the first subsequence including the target yield change point and a plurality of yields adjacent to and before the target yield change point; determining a second subsequence from a second sequence corresponding to the target parameter, the target parameter being any one of the plurality of parameters, the second subsequence including parameter values ​​of the target parameter within a target time period, the target time period being a time period in which the target parameter participates in a production process of a target product, the target product including a product corresponding to a yield in the first subsequence; if there is a parameter change point corresponding to the target parameter in the second subsequence, determining the target parameter as a candidate influencing parameter corresponding to the target yield change point.

[0107] Among them, the implementation method of determining the second subsequence from the second sequence corresponding to the target parameter is similar to the implementation method of determining the second subsequence from the second sequence corresponding to the target parameter in the first implementation method above. For detailed process, please refer to the relevant content in the above text, which will not be repeated here.

[0108] In some embodiments, after at least one parameter change point corresponding to each of the plurality of parameters is determined, a second prompt information may be displayed, where the second prompt information is used to prompt that an abnormality exists in the parameter value of the relevant parameter.

[0109] In a possible implementation, if the relevant parameter is a device status parameter or a device maintenance parameter, the second prompt information also includes the production equipment corresponding to the parameter.

[0110] For example, the second prompt information can be in the form of a table or in the form of a factory plan view. When the second prompt information is in the form of a table, the table includes the identification of the production equipment and the identification of the abnormal parameter. When the second prompt information is a factory plan view, the factory plan view includes multiple production equipment, and the electronic device can highlight the production equipment corresponding to the parameter with abnormal parameter value (i.e., the parameter corresponding to at least one parameter change point). In some embodiments, the electronic device can also display the parameters of the abnormal parameter value corresponding to the production equipment in a pop-up window.

[0111] In some embodiments, the implementation process of determining the yield influencing factors of multiple groups of products based on the candidate influencing parameters corresponding to at least one yield change point includes: determining the intersection or union of the candidate influencing parameters corresponding to the at least one yield change point as the yield influencing factors of multiple groups of products.

[0112] In the embodiment of the present application, since the yield change point is the yield that has undergone abnormal changes in the first sequence, and the abnormal change in the yield of the product is usually related to the parameters in the production process, therefore, by analyzing the second sequence of multiple parameters through the yield change point, the parameters that affect the yield, that is, the yield influencing factors, can be accurately determined from the multiple parameters, so as to facilitate the subsequent analysis of the parameters that affect the product yield, thereby helping enterprises to quickly respond to abnormal fluctuations in production, optimize production processes, and improve product quality stability. Since the correlation between the two sequences includes positive correlation and negative correlation, where if one sequence is on an upward trend and the other sequence is also on an upward trend, it can be determined that the two sequences are positively correlated, and if one sequence is on an upward trend and the other sequence is also on a downward trend, it can be determined that the two sequences are negatively correlated, therefore, there are parameters that are positively correlated with the yield change in the multiple parameters, and there are also parameters that are negatively correlated with the yield change. However, the correlation obtained by the dynamic time warping algorithm indicates the degree of positive correlation between the two sequences. In this case, the correlation between the parameters that are negatively correlated with the yield change and the yield can be determined by flipping the first subsequence or the second subsequence, so that the accuracy of the final determined influencing factor can be guaranteed.

[0113] Figure 2 This is a schematic diagram of the structure of a device for determining a yield influencing factor provided in an embodiment of the present application. The device can be implemented as part or all of an electronic device by software, hardware, or a combination of both. Figure 2 The device includes: an acquisition module 201, a first determination module 202 and a second determination module 203.

[0114] An acquisition module 201 is used to acquire a first sequence and a second sequence corresponding to a plurality of parameters, wherein the first sequence includes yields corresponding to a plurality of groups of products of the same model, the plurality of parameters refer to parameters involved in the production process of the plurality of groups of products, and the second sequence includes parameter values ​​corresponding to the corresponding parameters at a plurality of moments in the production process of the plurality of groups of products;

[0115] A first determination module 202 is used to determine at least one yield change point based on the first sequence, where the yield change point is the yield that undergoes an abnormal change in the first sequence;

[0116] The second determination module 203 is configured to determine yield influencing factors of multiple groups of products from multiple parameters based on at least one yield change point and second sequences corresponding to the multiple parameters.

[0117] In a possible implementation, the second determining module 203 is specifically configured to:

[0118] Based on at least one yield change point and the second sequences respectively corresponding to the multiple parameters, determine a candidate influencing parameter respectively corresponding to at least one yield change point from the multiple parameters, where the candidate influencing parameter is a parameter influencing the corresponding yield change point from the multiple parameters;

[0119] Yield influencing factors of multiple groups of products are determined based on candidate influencing parameters corresponding to at least one yield change point.

[0120] In a possible implementation, the second determining module 203 is specifically configured to:

[0121] Determine, based on the target yield change point and the second sequences corresponding to the multiple parameters, the correlation between the target yield change point and the multiple parameters, wherein the target yield change point is any one of the at least one yield change point;

[0122] Based on the correlation between the target yield change points and the multiple parameters, candidate influencing parameters corresponding to the target yield are determined from the multiple parameters.

[0123] In a possible implementation, the second determining module 203 is specifically configured to:

[0124] Based on the target yield change point, determine a first subsequence from the first sequence, the first subsequence including the target yield change point and a plurality of yields adjacent to and before the target yield change point;

[0125] Determine a second subsequence from a second sequence corresponding to a target parameter, the target parameter being any one of a plurality of parameters, the second subsequence comprising parameter values ​​of the target parameter within a target time period, the target time period being a time period during which the target parameter participates in a production process of a target product, and the target product comprises a product corresponding to a yield in the first subsequence;

[0126] Based on the first subsequence and the second subsequence, a correlation between the target yield change point and the target parameter is determined.

[0127] In a possible implementation, the second determining module 203 is specifically configured to:

[0128] Based on the second sequences corresponding to the multiple parameters, respectively, determining at least one parameter change point corresponding to the multiple parameters, where the parameter change point is a parameter value in the second sequence corresponding to the corresponding parameter where an abnormal change occurs;

[0129] Based on a target yield change point and at least one parameter change point corresponding to each of the multiple parameters, a candidate influencing parameter corresponding to the target yield change point is determined from the multiple parameters, and the target yield change point is any one of the at least one yield change point.

[0130] In a possible implementation, the second determining module 203 is specifically configured to:

[0131] Based on the target yield change point, determine a first subsequence from the first sequence, the first subsequence including the target yield change point and a plurality of yields adjacent to and before the target yield change point;

[0132] Determine a second subsequence from a second sequence corresponding to a target parameter, the target parameter being any one of a plurality of parameters, the second subsequence comprising parameter values ​​of the target parameter within a target time period, the target time period being a time period during which the target parameter participates in a production process of a target product, and the target product comprises a product corresponding to a yield in the first subsequence;

[0133] If there is a parameter change point corresponding to the target parameter in the second subsequence, the target parameter is determined to be a candidate influencing parameter corresponding to the target yield change point.

[0134] In the embodiment of the present application, since the yield change point is the yield that has undergone abnormal changes in the first sequence, and the abnormal change in the yield of the product is usually related to the parameters in the production process, therefore, by analyzing the second sequence of multiple parameters through the yield change point, the parameters that affect the yield, that is, the yield influencing factors, can be accurately determined from the multiple parameters, so as to facilitate the subsequent analysis of the parameters that affect the product yield, thereby helping enterprises to quickly respond to abnormal fluctuations in production, optimize production processes, and improve product quality stability. Since the correlation between the two sequences includes positive correlation and negative correlation, where if one sequence is on an upward trend and the other sequence is also on an upward trend, it can be determined that the two sequences are positively correlated, and if one sequence is on an upward trend and the other sequence is also on a downward trend, it can be determined that the two sequences are negatively correlated, therefore, there are parameters that are positively correlated with the yield change in the multiple parameters, and there are also parameters that are negatively correlated with the yield change. However, the correlation obtained by the dynamic time warping algorithm indicates the degree of positive correlation between the two sequences. In this case, the correlation between the parameters that are negatively correlated with the yield change and the yield can be determined by flipping the first subsequence or the second subsequence, so that the accuracy of the final determined influencing factor can be guaranteed.

[0135] It should be noted that: the yield impact factor determination device provided in the above embodiment only uses the division of the above functional modules as an example when determining the yield impact factor. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the yield impact factor determination device provided in the above embodiment and the yield impact factor determination method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0136] Figure 3 300 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 300 includes a central processing unit (CPU) 301, a system memory 304 including a random access memory (RAM) 302 and a read-only memory (ROM) 303, and a system bus 305 connecting the system memory 304 and the central processing unit 301. The electronic device 300 also includes a basic input / output system (I / O system) 306 that helps transmit information between various devices in the computer, and a large-capacity storage device 307 for storing an operating system 313, an application program 314, and other program modules 315.

[0137] The basic input / output system 306 includes a display 308 for displaying information and an input device 309 such as a mouse and a keyboard for user inputting information. The display 308 and the input device 309 are connected to the central processing unit 301 through an input / output controller 310 connected to the system bus 305. The basic input / output system 306 may also include an input / output controller 310 for receiving and processing inputs from a plurality of other devices such as a keyboard, a mouse, or an electronic stylus. Similarly, the input / output controller 310 also provides output to a display screen, a printer, or other types of output devices.

[0138] The mass storage device 307 is connected to the central processing unit 301 through a mass storage controller (not shown) connected to the system bus 305. The mass storage device 307 and its associated computer-readable media provide non-volatile storage for the electronic device 300. That is, the mass storage device 307 may include a computer-readable medium (not shown) such as a hard disk or a CD-ROM drive.

[0139] Without loss of generality, computer readable media may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information such as computer readable instructions, data structures, program modules or other data. Computer storage media include RAM, ROM, EPROM, EEPROM, flash memory or other solid-state storage technologies, CD-ROM, DVD or other optical storage, cassettes, magnetic tapes, disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that computer storage media are not limited to the above. The above-mentioned system memory 304 and mass storage device 307 can be collectively referred to as memory.

[0140] According to various embodiments of the present application, the electronic device 300 can also be connected to a remote computer on the network through a network such as the Internet. That is, the electronic device 300 can be connected to the network 312 through the network interface unit 311 connected to the system bus 305, or the network interface unit 311 can also be used to connect to other types of networks or remote computer systems (not shown).

[0141] The above-mentioned memory also includes one or more programs, and the one or more programs are stored in the memory and configured to be executed by the CPU.

[0142] In some embodiments, a computer-readable storage medium is further provided, in which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for determining the yield influencing factor in the above embodiment are implemented. For example, the computer-readable storage medium may be a ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0143] It is worth noting that the computer-readable storage medium mentioned in the embodiments of the present application may be a non-volatile storage medium, in other words, a non-transitory storage medium.

[0144] It should be understood that all or part of the steps to implement the above embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The computer instructions can be stored in the above-mentioned computer readable storage medium.

[0145] That is, in some embodiments, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the steps of the method for determining the yield influencing factor described above.

[0146] It should be understood that the "at least one" mentioned herein refers to one or more, and "multiple" refers to two or more. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first", "second" and the like are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not limit them to be necessarily different.

[0147] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data for analysis, stored data, displayed data, etc.) and signals involved in the embodiments of the present application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. For example, the first sequence involved in the embodiments of the present application and the second sequence corresponding to the multiple parameters are obtained with full authorization.

[0148] The above-mentioned embodiments are provided for the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining a yield influencing factor, characterized in that: The method comprises: Obtaining a first sequence and a second sequence corresponding to a plurality of parameters, wherein the first sequence includes yields corresponding to a plurality of groups of products of the same model, the plurality of parameters refer to parameters involved in a production process of the plurality of groups of products, and the second sequence includes parameter values ​​corresponding to the corresponding parameters at a plurality of moments in the production process of the plurality of groups of products; Determine at least one yield change point based on the first sequence, where the yield change point is the yield at which an abnormal change occurs in the first sequence; Based on the at least one yield change point and the second sequences respectively corresponding to the multiple parameters, yield influencing factors of the multiple groups of products are determined from the multiple parameters.

2. The method according to claim 1, characterized in that The determining the yield influencing factors of the multiple groups of products from the multiple parameters based on the at least one yield change point and the second sequences respectively corresponding to the multiple parameters includes: Based on the at least one yield change point and the second sequences respectively corresponding to the multiple parameters, determining candidate influencing parameters respectively corresponding to the at least one yield change point from the multiple parameters, the candidate influencing parameters being parameters in the multiple parameters that have an impact on the corresponding yield change point; Based on the candidate influencing parameters respectively corresponding to the at least one yield change point, yield influencing factors of the multiple groups of products are determined.

3. The method according to claim 2, characterized in that The determining, based on the at least one yield change point and the second sequences respectively corresponding to the multiple parameters, candidate influencing parameters respectively corresponding to the at least one yield change point from the multiple parameters includes: Determine, based on a target yield change point and a second sequence corresponding to each of the multiple parameters, the association between the target yield change point and each of the multiple parameters, wherein the target yield change point is any one of the at least one yield change point; Based on the correlation between the target yield change points and the multiple parameters, candidate influencing parameters corresponding to the target yield are determined from the multiple parameters.

4. The method according to claim 3, characterized in that The determining, based on the target yield change point and the second sequences respectively corresponding to the multiple parameters, the correlation between the target yield change point and the multiple parameters respectively includes: Based on the target yield change point, determining a first subsequence from the first sequence, the first subsequence including the target yield change point and a plurality of yields adjacent to and before the target yield change point; Determine a second subsequence from a second sequence corresponding to a target parameter, the target parameter being any one of the multiple parameters, the second subsequence comprising parameter values ​​of the target parameter within a target time period, the target time period being a time period during which the target parameter participates in a production process of a target product, the target product comprising a product corresponding to a yield in the first subsequence; Based on the first subsequence and the second subsequence, a correlation between the target yield change point and the target parameter is determined.

5. The method according to claim 2, characterized in that The determining, based on the at least one yield change point and the second sequences respectively corresponding to the multiple parameters, candidate influencing parameters respectively corresponding to the at least one yield change point from the multiple parameters includes: Based on the second sequences corresponding to the multiple parameters respectively, determining at least one parameter change point corresponding to the multiple parameters respectively, the parameter change point being a parameter value in the second sequence corresponding to the corresponding parameter where an abnormal change occurs; Based on the target yield change point and at least one parameter change point corresponding to the multiple parameters respectively, a candidate influencing parameter corresponding to the target yield change point is determined from the multiple parameters, and the target yield change point is any one of the at least one yield change point.

6. The method according to claim 5, characterized in that The determining, based on the target yield change point and at least one parameter change point respectively corresponding to the multiple parameters, a candidate influencing parameter corresponding to the target yield change point from the multiple parameters comprises: Based on the target yield change point, determining a first subsequence from the first sequence, the first subsequence including the target yield change point and a plurality of yields adjacent to and before the target yield change point; Determine a second subsequence from a second sequence corresponding to a target parameter, the target parameter being any one of the multiple parameters, the second subsequence comprising parameter values ​​of the target parameter within a target time period, the target time period being a time period during which the target parameter participates in a production process of a target product, the target product comprising a product corresponding to a yield in the first subsequence; If a parameter change point corresponding to the target parameter exists in the second subsequence, the target parameter is determined to be a candidate influencing parameter corresponding to the target yield change point.

7. A device for determining a yield influencing factor, characterized in that: The device comprises: an acquisition module, configured to acquire a first sequence and a second sequence corresponding to a plurality of parameters, wherein the first sequence includes yields corresponding to a plurality of groups of products of the same model, the plurality of parameters refer to parameters involved in the production process of the plurality of groups of products, and the second sequence includes parameter values ​​corresponding to the corresponding parameters at a plurality of moments in the production process of the plurality of groups of products; A first determining module, configured to determine at least one yield change point based on the first sequence, wherein the yield change point is a yield at which an abnormal change occurs in the first sequence; The second determination module is used to determine the yield influencing factors of the multiple groups of products from the multiple parameters based on the at least one yield change point and the second sequences respectively corresponding to the multiple parameters.

8. The device according to claim 7, characterized in that The second determining module is specifically used for: Based on the at least one yield change point and the second sequences respectively corresponding to the multiple parameters, determining candidate influencing parameters respectively corresponding to the at least one yield change point from the multiple parameters, the candidate influencing parameters being parameters in the multiple parameters that have an impact on the corresponding yield change point; Based on the candidate influencing parameters respectively corresponding to the at least one yield change point, yield influencing factors of the multiple groups of products are determined.

9. The device according to claim 8, characterized in that The second determining module is specifically used for: Determine, based on a target yield change point and a second sequence corresponding to each of the multiple parameters, the association between the target yield change point and each of the multiple parameters, wherein the target yield change point is any one of the at least one yield change point; Based on the correlation between the target yield change points and the multiple parameters, candidate influencing parameters corresponding to the target yield are determined from the multiple parameters.

10. The device according to claim 9, characterized in that The second determining module is specifically used for: Based on the target yield change point, determining a first subsequence from the first sequence, the first subsequence including the target yield change point and a plurality of yields adjacent to and before the target yield change point; Determine a second subsequence from a second sequence corresponding to a target parameter, the target parameter being any one of the multiple parameters, the second subsequence comprising parameter values ​​of the target parameter within a target time period, the target time period being a time period during which the target parameter participates in a production process of a target product, the target product comprising a product corresponding to a yield in the first subsequence; Based on the first subsequence and the second subsequence, a correlation between the target yield change point and the target parameter is determined.

11. The device according to claim 8, characterized in that The second determining module is specifically used for: Based on the second sequences corresponding to the multiple parameters respectively, determining at least one parameter change point corresponding to the multiple parameters respectively, the parameter change point being a parameter value in the second sequence corresponding to the corresponding parameter where an abnormal change occurs; Based on the target yield change point and at least one parameter change point corresponding to the multiple parameters respectively, a candidate influencing parameter corresponding to the target yield change point is determined from the multiple parameters, and the target yield change point is any one of the at least one yield change point.

12. The device according to claim 11, characterized in that The second determining module is specifically used for: Based on the target yield change point, determining a first subsequence from the first sequence, the first subsequence including the target yield change point and a plurality of yields adjacent to and before the target yield change point; Determine a second subsequence from a second sequence corresponding to a target parameter, the target parameter being any one of the multiple parameters, the second subsequence comprising parameter values ​​of the target parameter within a target time period, the target time period being a time period during which the target parameter participates in a production process of a target product, the target product comprising a product corresponding to a yield in the first subsequence; If a parameter change point corresponding to the target parameter exists in the second subsequence, the target parameter is determined to be a candidate influencing parameter corresponding to the target yield change point.

13. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory is used to store a computer program, and the processor is configured to execute the computer program stored in the memory to implement the steps of the method according to any one of claims 1 to 6.

14. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

15. A computer program product comprising instructions, characterized in that When the instructions are executed on a computer, the computer is enabled to execute the steps of the method according to any one of claims 1 to 6.

Images