Product testing method and device, storage medium and computer program product

Abstract

The invention discloses a product testing method and device, a storage medium and a computer program product, and relates to the technical field of product testing, and the product testing method comprises the steps: obtaining a performance static boundary of a qualified product of a current batch, and a real-time performance data pool; generating a real-time dynamic boundary according to the real-time performance data pool; and comparing the performance parameter information of the qualified products of the current batch based on the performance static boundary and the real-time dynamic boundary to obtain outlier product information. The technical problem that the screening accuracy of outlier products is low in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of product testing technology, and in particular to a product testing method, device, storage medium, and computer program product. Background Art

[0002] In the field of manufacturing, performance testing of products before they leave the factory is the core link to ensure their measurement accuracy and reliability.

[0003] To identify potential product quality risks, it's often necessary to screen outliers from qualified products. Currently, Static Part Average Testing (PAT) is widely used for outlier screening. This involves calculating fixed control limits based on historical test data. These limits are then used as a criterion to identify outliers in real-time test results of qualified products.

[0004] However, the static nature of fixed control limits makes it unable to adapt to normal differences caused by different batches of products or process fluctuations, resulting in low screening accuracy for outlier products. Summary of the Invention

[0005] The main purpose of this application is to provide a product testing method, device, storage medium and computer program product, aiming to solve the technical problem of low accuracy in screening outlier products in the existing technology.

[0006] To achieve the above objectives, the present application proposes a product testing method, which includes: Obtain the static performance boundaries of the current batch of qualified products and the real-time performance data pool; generating a real-time dynamic boundary based on the real-time performance data pool; Based on the performance static boundary and the real-time dynamic boundary, the performance parameter information of the qualified products of the current batch is compared to obtain outlier product information.

[0007] In one embodiment, the step of generating a real-time dynamic boundary based on the real-time performance data pool includes: Performing normal distribution analysis on the performance parameter values ​​in the real-time performance data pool to obtain the limit probability boundaries of the performance parameter values; The extreme probability boundary of the performance parameter value is used as the real-time dynamic boundary.

[0008] In one embodiment, after the step of generating a real-time dynamic boundary based on the real-time performance data pool, the product testing method further includes: Get the historical dynamic boundaries of the previous batch; Calculating a first difference between the historical dynamic boundary and the real-time dynamic boundary; After the first difference is greater than a predetermined difference ratio of the historical dynamic boundary, an alarm prompt operation is performed.

[0009] In one embodiment, after the step of generating a real-time dynamic boundary based on the real-time performance data pool, the product testing method further includes: Obtaining a warning limit boundary, wherein the warning limit boundary is within the performance static boundary; After the real-time dynamic boundary exceeds the warning limit boundary, an alarm prompt operation is performed.

[0010] In one embodiment, the step of comparing the performance parameter information of the current batch of qualified products based on the static performance boundary and the real-time dynamic boundary to obtain outlier product information includes: Determining whether the performance parameter value in the performance parameter information is within the performance static boundary; If the performance parameter value is not within the performance static boundary, it is determined that the qualified product is in an outlier state; If the performance parameter value is within the performance static boundary, determining whether the performance parameter value is within the real-time dynamic boundary; If the performance parameter value is not within the real-time dynamic boundary, it is determined that the qualified product is in an outlier state; The description information of qualified products in the outlier state is used as outlier product information.

[0011] In one embodiment, before the step of obtaining the static performance boundary of the qualified product, the following steps are included: Acquiring performance parameter information of a product to be screened and a performance specification boundary of the product to be screened, wherein the performance static boundary is within the performance specification boundary; Products to be screened whose performance parameter values ​​in the performance parameter information are within the performance specification boundaries are regarded as qualified products.

[0012] In one embodiment, before the step of obtaining the static performance boundary of the current batch of qualified products and the real-time performance data pool, the product testing method further includes: When the real-time performance data pool does not contain performance parameter information of historical batches, the performance parameter information of the current batch of qualified products within the performance static boundary is added to the real-time performance data pool; After the step of comparing the performance parameter information of the current batch of qualified products based on the performance static boundary and the real-time dynamic boundary to obtain outlier product information, the method further includes: if the real-time performance data pool does not reach a predetermined data volume, adding the performance parameter information of the current batch of qualified products within the performance static boundary to the real-time performance data pool to update the real-time performance data pool; If the real-time performance data pool reaches a predetermined data volume, the earliest performance parameter information of the same data volume of the performance parameter information of the current batch of qualified products within the performance static boundary is deleted from the real-time performance data pool, and the performance parameter information of the current batch of qualified products within the performance static boundary is added to the real-time performance data pool to update the real-time performance data pool.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a product testing device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the product testing method described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the product testing method described above are implemented.

[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the product testing method described above are implemented.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: This application obtains the static performance boundaries of the current batch of qualified products and a real-time performance data pool; based on this real-time performance data pool, it generates a real-time dynamic boundary. This real-time dynamic boundary, generated based on the real-time performance data pool, is then dynamically and adaptively adjusted to accommodate deviations from the normal distribution caused by batches, process fluctuations, or environmental changes. The performance parameter information of the current batch of qualified products is then compared based on the static performance boundaries and the real-time dynamic boundaries to obtain outlier product information. Compared to the determination method based on fixed control limits, the real-time dynamic boundary in this application can avoid misjudgments (over-killing) or missed detections (under-killing) caused by normal fluctuations such as batches, process fluctuations, or environmental changes. This dual-dimensional determination mechanism, combining static performance boundaries with real-time dynamic boundaries, simultaneously addresses long-term quality standards and short-term data fluctuations. By adaptively adjusting the dynamic boundary based on the static performance boundaries, this application achieves more accurate and adaptable outlier product identification, effectively improving the accuracy of outlier screening. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 A flow chart of the first embodiment of the product testing method of this application is provided; Figure 2 A scene diagram for constructing a real-time performance data pool according to an embodiment of the present application; Figure 3 A screening scenario diagram for performance parameter information involved in the embodiments of this application; Figure 4 A flow chart of Example 2 of the product testing method of this application is provided; Figure 5 A flow chart of Example 3 of the product testing method of this application is provided; Figure 6 A schematic diagram of a scenario involved in an embodiment of the product testing method of this application; Figure 7 This is a schematic diagram of the equipment structure of the product testing equipment involved in the embodiment of the present application.

[0020] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0022] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of the embodiment of the present application is: to obtain the static performance boundary of the current batch of qualified products and the real-time performance data pool; to generate the real-time dynamic boundary based on the real-time performance data pool; and to compare the performance parameter information of the current batch of qualified products based on the static performance boundary and the real-time dynamic boundary to obtain the outlier product information.

[0024] Existing technologies generally use Static Part Average Testing (PAT) to screen outlier products. This involves calculating fixed control limits based on historical test data and using these fixed control limits as a criterion to identify outliers in the real-time test results of qualified products. However, the static nature of fixed control limits makes them unable to adapt to normal variations caused by different product batches or process fluctuations, making it more likely to lead to misjudgments, overkill, and yield loss. Alternatively, if the fixed control limits are set too wide, outlier products may be missed, resulting in low outlier screening accuracy.

[0025] The present application provides a solution, which generates a real-time dynamic boundary based on the real-time performance data pool, so that the real-time dynamic boundary can be adaptively and dynamically adjusted according to the normal distribution deviation caused by different batches, process fluctuations or environmental changes. Compared with the judgment method of fixed control limits, the real-time dynamic boundary in the present application can avoid misjudgment (overkill) or missed detection (underkill) caused by normal fluctuations such as batches, process fluctuations or environmental changes. Therefore, the present application combines the dual-dimensional judgment mechanism of performance static boundary and real-time dynamic boundary, while taking into account the scenarios of long-term quality specifications and short-term data fluctuations. On the basis of performance static boundary, with the help of adaptive adjustment of dynamic boundary, it realizes more accurate and adaptable outlier product identification, effectively improving the screening accuracy of outlier products.

[0026] Based on this, the present invention provides a product testing method. Figure 1 , Figure 1 This is a flow chart of the first embodiment of the product testing method of this application.

[0027] In this embodiment, the product testing method includes steps S10 to S40: Step S10, obtaining the static performance boundary of the current batch of qualified products and the real-time performance data pool; It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a laptop computer, PDA (Personal Digital Assistant), PAD (Portable Application Description), desktop computer and other electronic devices that can realize the above functions.

[0028] Additionally, it should be noted that qualified products are products whose performance parameter values ​​meet performance specifications, and the performance static boundary is a pre-set boundary value for the performance parameters used to identify qualified products in an outlier state. The real-time performance data pool may include performance parameter information for the most recent batch within the performance static boundary, such as performance parameter information for qualified products within the performance static boundary for the most recent predetermined data volume (e.g., the most recent 8,000, 10,000, or 15,000 data items) or the most recent time period (e.g., the most recent 6, 8, or 12 hours). The performance parameter information may include the performance parameter value for at least one performance item.

[0029] In this embodiment, the static performance boundary of the current batch of qualified products can be read from the cloud or locally to determine the fixed boundary used to determine whether the current batch of qualified products is an outlier. The static performance boundary can be a pre-defined boundary value of a performance parameter, or it can be a value calculated based on the performance parameter information of historical batches of qualified products. For example, it can be a predetermined percentile range (e.g., 1% to 99%), a limit probability boundary under a normal distribution (e.g., μ±3σ, μ±6σ), etc. In addition, this embodiment can also read from the cloud or locally a real-time performance data pool that stores the performance parameter information of historical batches and the current batch of qualified products within the static performance boundary.

[0030] In a feasible implementation manner, step S10 may include steps A10 to A20: Step A10, obtaining performance parameter information of the product to be screened and the performance specification boundary of the product to be screened, wherein the performance static boundary is within the performance specification boundary; Step A20: The products to be screened whose performance parameter values ​​in the performance parameter information are within the performance specification boundaries are regarded as qualified products.

[0031] It should be noted that the performance specification boundaries are the upper and lower limits for judging whether the performance parameters of a product are qualified, and the performance static boundary is within the performance specification boundary, that is, the upper limit value of the performance static boundary is less than the upper limit value of the performance specification boundary, and the lower limit value of the performance static boundary is greater than the lower limit value of the performance specification boundary.

[0032] This embodiment can determine whether the performance parameter value in the performance parameter information of the product to be screened is greater than the lower limit of the performance specification boundary and less than the upper limit of the performance specification boundary. If the performance parameter value is greater than the lower limit of the performance specification boundary and less than the upper limit of the performance specification boundary, it can be determined that the performance parameter value in the performance parameter information of the product to be screened is within the performance specification boundary. If the performance parameter value is not greater than the lower limit of the performance specification boundary, and / or not less than the upper limit of the performance specification boundary, it can be determined that the performance parameter value in the performance parameter information of the product to be screened is not within the performance specification boundary. Furthermore, this embodiment can treat the product to be screened whose performance parameter value in the performance parameter information is within the performance specification boundary as a qualified product. Thus, this embodiment quickly screens out qualified products that meet the specifications through the performance specification boundary.

[0033] In a feasible implementation manner, the product testing method before step S10 may further include step B10: Step B10: When the real-time performance data pool does not contain performance parameter information of historical batches, the performance parameter information of the current batch of qualified products within the performance static boundary is added to the real-time performance data pool; After step S30, steps B20 to B30 are included: Step B20: If the real-time performance data pool does not reach the predetermined data volume, the performance parameter information of the current batch of qualified products within the performance static boundary is added to the real-time performance data pool to update the real-time performance data pool; Step B30: If the real-time performance data pool reaches a predetermined data volume, the earliest performance parameter information of the same data volume of the performance parameter information of the current batch of qualified products within the performance static boundary is deleted from the real-time performance data pool, and the performance parameter information of the current batch of qualified products within the performance static boundary is added to the real-time performance data pool to update the real-time performance data pool.

[0034] It should be noted that the predetermined data volume is a preset upper limit of the data volume of the real-time performance data pool.

[0035] When the real-time performance data pool does not contain performance parameter information of historical batches (for example, the first batch for screening of qualified products in an outlier state), the performance parameter information of the current batch of qualified products within the performance static boundary is added to the real-time performance data pool. When the real-time performance data pool contains performance parameter information of historical batches, step S10 can be directly executed. Then, based on the performance static boundary and the real-time dynamic boundary, the performance parameter information of the current batch of qualified products is compared to obtain the outlier product information. In this embodiment, it can be determined whether the data stored in the real-time performance data pool reaches a predetermined data volume. If the real-time performance data pool does not reach the predetermined data volume, it means that the data volume stored in the real-time performance data pool does not meet expectations. Then, the performance parameter information of the current batch of qualified products within the performance static boundary can be added to the real-time performance data pool to update the real-time performance data pool and obtain a new real-time performance pool. If the real-time performance data pool reaches the predetermined data volume, indicating that the data volume stored in the real-time performance data pool has reached the expected volume, then in order to ensure the freshness of the data in the real-time performance data pool, the performance parameter information of the current batch of qualified products within the performance static boundary, which is the earliest performance parameter information of the same data volume, is deleted from the real-time performance data pool, and the performance parameter information of the current batch of qualified products within the performance static boundary is added to the real-time performance data pool to update the real-time performance data pool. Figure 2 As shown in the figure, each color block represents the performance parameter information of a batch of qualified products within the static performance boundary. The corresponding data volume is x, and the predetermined data volume is 10K. Multiple color blocks constitute the real-time performance data pool, with the performance parameter information from left to right representing the earliest to the latest. Therefore, the real-time performance data pool ensures the data freshness of the real-time performance data pool by adding performance parameter information of new batches in real time and removing performance parameter information of the earliest batch, provided that the stored performance parameter information is sufficient. This allows the subsequently generated real-time dynamic boundary to be more adaptable to the changes in recent factors affecting product performance.

[0036] Step S20, generating a real-time dynamic boundary based on the real-time performance data pool; It should be noted that the real-time dynamic boundary is a performance parameter value for distinguishing qualified products in a clustered state, and the real-time dynamic boundary may include a real-time dynamic upper limit value and a real-time dynamic lower limit value.

[0037] As an example, the real-time performance data pool includes a large amount of performance parameter information. This embodiment can perform a normal distribution analysis on the performance parameter values ​​in the performance parameter information to obtain a limit probability boundary for the performance parameter values. This limit probability boundary can then be used as the real-time dynamic boundary. The limit probability boundary is μ±nσ, i.e., the upper limit of the limit probability boundary is μ+nσ, and the lower limit is μ-nσ. μ is the mean of the performance parameter values, σ is the standard deviation of the performance parameter values, and n is a positive integer. The value of n can be selected as needed, for example, 3, 4, 5, or 6. It is understood that the mean of the performance parameter values ​​can be either a robust mean or an arithmetic mean, and the standard deviation of the performance parameter values ​​can be either a robust standard deviation or an arithmetic standard deviation. The robust mean is the median, and the robust standard deviation = (K2 - K1) / 1.35, where K1 is the 25th percentile and K2 is the 75th percentile.

[0038] As another example, the predetermined percentile range may include a predetermined upper percentile and a predetermined lower percentile. This embodiment may also perform percentile analysis on the performance parameter values ​​in the performance parameter information to obtain an upper limit value corresponding to the predetermined upper percentile and a lower limit value corresponding to the predetermined lower percentile in the performance parameter value, and then the upper limit value corresponding to the predetermined upper percentile and the lower limit value corresponding to the predetermined lower percentile may be used as real-time dynamic boundaries. The predetermined upper percentile is a percentile pre-set as the upper limit of the real-time dynamic boundary, and the predetermined lower percentile is a percentile pre-set as the lower limit of the real-time dynamic boundary. For example, the predetermined upper percentile may be 99.9%, and the predetermined lower percentile may be 0.1%.

[0039] In a feasible implementation, step S20 may include steps S21 and S22: Step S21, performing normal distribution analysis on the performance parameter values ​​in the real-time performance data pool to obtain the limit probability boundary of the performance parameter values; Step S22: taking the extreme probability boundary of the performance parameter value as the real-time dynamic boundary.

[0040] In this embodiment, the limit probability boundary of the performance parameter value can be obtained by performing a normal distribution analysis on the performance parameter values in the performance parameter information, and then the limit probability boundary of the performance parameter value can be used as the real-time dynamic boundary. The limit probability boundary is μ ± nσ, where μ is the average value of the performance parameter value, σ is the standard deviation of the performance parameter value, n is the coefficient of the standard deviation, n is a positive integer, and the value of n can be selected according to requirements, such as 3, 4, 5, 6. That is, the upper limit value of the limit probability boundary is μ + nσ, and the lower limit value of the limit probability boundary is μ - nσ. Exemplarily, taking the real-time dynamic boundary as μ ± 3σ as an example, P(μ - 3σ < X < μ + 3σ) = 0.9973, that is, this real-time dynamic boundary indicates that there is about 0.27% possibility that a qualified product may fall outside this range and be judged as an outlier state. Taking the real-time dynamic boundary as μ ± 6σ as an example, P(μ - 6σ < X < μ + 6σ) = 0.9999999983, that is, this real-time dynamic boundary indicates that there is about 0.00000017% possibility that a qualified product may fall outside this range and be judged as an outlier state. Further, before step S21, this embodiment can also obtain the production scenario information of the current batch, and determine the corresponding coefficient of the standard deviation according to the production stability of the production scenario information. The coefficient of the standard deviation is positively correlated with the production stability. The production stability describes the stable degree of the production scenario of the products in the current batch. For example, the production stability is relatively low in scenarios such as the trial production stage and after debugging the production process, while the production stability is relatively high in scenarios such as the formal production stage and after stable production for a period of time. It can be understood that the production stability can be described by the standard deviation and / or the range of the performance parameter values in the performance parameter information. Then, step S21 can be executed based on the coefficient of the standard deviation. Thus, in an unstable production scenario, this embodiment reduces the coefficient of the standard deviation and narrows the real-time dynamic boundary to improve sensitivity. In a stable production scenario, this embodiment can increase the coefficient of the standard deviation and widen the real-time dynamic boundary to avoid overkill. This embodiment can adaptively adjust the coefficient of the standard deviation according to the stable degree of the production scenario to adjust the range of the real-time dynamic boundary, so as to balance the missed detection rate and the overkill rate of the screening for the outlier state.

[0041] Step S30: Based on the performance static boundary and the real-time dynamic boundary, compare the performance parameter information of the qualified products in the current batch to obtain outlier product information.

[0042] It should be noted that the outlier product information is the descriptive information of the qualified products in the outlier state, such as product codes, identifiers, etc. The qualified products in the outlier state are the qualified products whose performance parameter values in the performance parameter information exceed the performance static boundary and / or the real-time dynamic boundary.

[0043] Since both the performance static boundary and the real-time dynamic boundary are used to identify qualified products in an outlier state, the performance parameter information of the qualified products of the current batch can be compared based on the performance static boundary and the real-time dynamic boundary, and qualified products whose performance parameter values ​​in the performance parameter information exceed the performance static boundary and / or the real-time dynamic boundary are determined to be in an outlier state, and the description information of the qualified products in the outlier state is used as the outlier product information. Therefore, this embodiment combines the dual-dimensional judgment mechanism of the performance static boundary and the real-time dynamic boundary, while taking into account the scenarios of long-term quality specifications and short-term data fluctuations. On the basis of the performance static boundary, with the help of the adaptive adjustment of the dynamic boundary, it realizes more accurate and adaptable outlier product identification, effectively improving the screening accuracy of outlier products. Figure 3 As shown, this embodiment can screen each batch of products to be screened by using the real-time dynamic boundary generated based on the real-time performance data pool, as well as the pre-set performance specification boundary and performance static boundary, to obtain qualified products in the outlier state (i.e. Figure 3① and ② in it). Thus, this embodiment can determine the performance fluctuation status of qualified products based on the outlier product information. Exemplarily, this embodiment can perform an alarm prompt operation after the number or proportion of qualified products in the outlier state reaches a predetermined alarm threshold, so as to prompt the user that the performance fluctuation of qualified products is relatively serious, so that the user can improve the process content in time to avoid the occurrence of a large number of qualified products or even unqualified products in the outlier state. It should be understood that a qualified product in the outlier state is a product for which the performance parameter value of at least one performance item exceeds the performance static boundary and / or the real-time dynamic boundary, that is, a qualified product in the outlier state may have multiple performance parameter values ​​of performance items that exceed the performance static boundary and / or the real-time dynamic boundary. Furthermore, this embodiment can perform spatiotemporal clustering (such as clustering operations on the dimensions of time window and production location) on the qualified products in the outlier state based on the outlier product information to obtain occasional anomaly clusters and system offset clusters. The occasional anomaly cluster is a cluster of qualified products that are not concentrated in time and space, while the system deviation cluster is a cluster of qualified products that are concentrated in time and space. That is, if the qualified products in the occasional anomaly cluster are not temporally or spatially correlated, this indicates that the qualified products in the occasional anomaly cluster are outliers caused by accidental factors. If the qualified products in the system deviation cluster are concentrated in time and space, this indicates that the qualified products in the system deviation cluster are not outliers caused by accidental factors. Furthermore, this embodiment obtains performance parameter information for each qualified product in the system deviation cluster, as well as each performance item in an outlier state, as outlier performance characteristics. These outlier performance characteristics are matched with performance characteristics of a predetermined anomaly scenario to obtain the predetermined anomaly scenario corresponding to each qualified product in the system deviation cluster. The performance characteristics of the predetermined anomaly scenario are the outlier performance characteristics under the predetermined anomaly scenario. Therefore, this embodiment first uses clustering operations in time and space to eliminate qualified products that are outliers due to occasional anomalies. Then, based on the performance parameter information of each qualified product in the system deviation cluster and whether each performance item of the performance parameter information is outlier, matching is performed with the predetermined abnormal scenario to implement root cause analysis and determine the predetermined abnormal scenario that causes the system deviation to be outlier.

[0044] In a feasible implementation, step S30 may include steps S31 to S35: Step S31, determining whether the performance parameter value in the performance parameter information is within the performance static boundary; Step S32: if the performance parameter value is not within the performance static boundary, it is determined that the qualified product is in an outlier state; Step S33: If the performance parameter value is within the performance static boundary, determine whether the performance parameter value is within the real-time dynamic boundary; Step S34: if the performance parameter value is not within the real-time dynamic boundary, it is determined that the qualified product is in an outlier state; Step S35: Using the description information of the qualified product in the outlier state as the outlier product information.

[0045] Only qualified products whose performance parameter values ​​in the performance parameter information exceed the performance static boundary and / or the real-time dynamic boundary will be determined to be in an outlier state. Therefore, this embodiment can determine whether the performance parameter values ​​in the performance parameter information are within the performance static boundary. If the performance parameter value is not within the performance static boundary, the qualified product is determined to be in an outlier state. If the performance parameter value is within the real-time dynamic boundary, it can be further determined whether the performance parameter value is within the real-time dynamic boundary. If the performance parameter value is not within the real-time dynamic boundary, the qualified product is determined to be in an outlier state; if the performance parameter value is within the real-time dynamic boundary, it can be determined that the qualified product is not in an outlier state. Since, in general, the real-time dynamic boundary is within the performance static boundary, this embodiment can first make a judgment based on the performance static boundary and then further make a judgment based on the real-time dynamic boundary, which can effectively improve the efficiency of judging qualified products in an outlier state.

[0046] A first embodiment of the present application provides a product testing method that obtains static performance boundaries for a current batch of qualified products and a real-time performance data pool; then generates a real-time dynamic boundary based on the real-time performance data pool. This embodiment generates a real-time dynamic boundary based on the real-time performance data pool, enabling the real-time dynamic boundary to dynamically and adaptively adjust to deviations from normal distributions caused by batches, process fluctuations, or environmental changes. Furthermore, based on the static performance boundaries and the real-time dynamic boundaries, performance parameter information for the current batch of qualified products is compared to obtain outlier product information. Compared to a fixed control limit determination method, the real-time dynamic boundary in this application can avoid misjudgments (over-killing) or missed detections (under-killing) caused by normal fluctuations such as batches, process fluctuations, or environmental changes. This embodiment, by combining a dual-dimensional determination mechanism of static performance boundaries and real-time dynamic boundaries, simultaneously addresses both long-term quality standards and short-term data fluctuations. By adaptively adjusting the dynamic boundary based on the static performance boundaries, it achieves more accurate and adaptable outlier product identification, effectively improving the accuracy of outlier product screening.

[0047] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 4After step S30, the product testing method further includes steps C10 to C30: Step C10, obtaining the historical dynamic boundary of the previous batch; Step C20, calculating a first difference between the historical dynamic boundary and the real-time dynamic boundary; Step C30: After the first difference is greater than a predetermined difference ratio of the historical dynamic boundary, an alarm prompt operation is performed.

[0048] It should be noted that the historical dynamic boundary of the previous batch is the real-time dynamic boundary of the previous batch, and the predetermined difference ratio is a pre-set ratio value for determining the degree of boundary fluctuation, such as 8%, 10%, 12%, etc.

[0049] In real-world production scenarios, product performance may fluctuate significantly due to factors such as process improvements and equipment anomalies, but this may not exceed either the real-time dynamic boundary or the static performance boundary. Therefore, this embodiment can obtain the historical dynamic boundary of the previous batch and then calculate a first difference between the historical dynamic boundary and the real-time dynamic boundary to determine the degree of fluctuation of the real-time dynamic boundary compared to the historical dynamic boundary. Furthermore, this embodiment can determine whether the first difference is greater than a predetermined difference ratio of the historical dynamic boundary. If the first difference is greater than the predetermined difference ratio of the historical dynamic boundary, this embodiment can determine that the real-time dynamic boundary fluctuates significantly compared to the historical dynamic boundary, indicating that the current batch of qualified products, regardless of whether they exceed the real-time dynamic boundary or the static performance boundary, exhibits excessive performance fluctuations. An alarm can then be issued to alert the user that the performance fluctuations of the qualified products are severe, allowing the user to promptly improve the process. The alarm can be output in at least one of the following formats: voice, text, or image.

[0050] A second embodiment of the present application provides a product testing method that obtains the historical dynamic boundary of a previous batch and calculates a first difference between the historical dynamic boundary and the real-time dynamic boundary. When the first difference exceeds a predetermined difference ratio of the historical dynamic boundary, an alarm prompt is executed. Thus, this embodiment can detect significant fluctuations in product performance by comparing the real-time dynamic boundary to the historical dynamic boundary. This provides a performance fluctuation warning, allowing users to intervene promptly and further reduce the failure rate of shipped products.

[0051] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 5After step S30, the product testing method further includes steps D10 to D20: Step D10, obtaining a warning limit boundary, wherein the warning limit boundary is within the performance static boundary; Step D20: After the real-time dynamic boundary exceeds the warning limit boundary, an alarm prompt operation is performed.

[0052] It should be noted that the early warning limit is within the performance static limit and is used to determine whether the real-time dynamic limit is approaching the performance static limit. That is, the upper limit of the early warning limit is less than the upper limit of the performance static limit, and the lower limit of the early warning limit is greater than the lower limit of the performance static limit. Exemplarily, the upper limit of the early warning limit is 0.95 times the upper limit of the performance static limit, and the lower limit of the early warning limit is 1.05 times the lower limit of the performance static limit.

[0053] Generally speaking, the real-time dynamic boundary is within the static performance boundary. However, if product performance fluctuates significantly due to factors such as process improvements and equipment anomalies, the real-time dynamic boundary may overlap with or even exceed the static performance boundary. Therefore, this embodiment can obtain a warning limit boundary, where the warning limit boundary is within the static performance boundary. Furthermore, this embodiment determines whether the upper limit of the real-time dynamic boundary is greater than the upper limit of the warning limit boundary, or whether the lower limit of the real-time dynamic boundary is less than the lower limit of the warning limit boundary. If the upper limit of the real-time dynamic boundary is greater than the upper limit of the warning limit boundary, and / or the lower limit of the real-time dynamic boundary is less than the lower limit of the warning limit boundary, then the real-time dynamic boundary can be determined to have exceeded the warning limit boundary. If the upper limit of the real-time dynamic boundary is not greater than the upper limit of the warning limit boundary, and the lower limit of the real-time dynamic boundary is less than the lower limit of the warning limit boundary, then the real-time dynamic boundary can be determined to have not exceeded the warning limit boundary. Furthermore, this embodiment can perform an alarm prompt operation if the real-time dynamic boundary exceeds the warning limit boundary.

[0054] A third embodiment of the present application provides a product testing method that obtains a warning limit boundary, wherein the warning limit boundary is within the static performance boundary, and then performs an alarm prompt operation when the real-time dynamic boundary exceeds the warning limit boundary. Therefore, this embodiment can use the warning limit boundary to determine whether the real-time dynamic boundary is approaching the static performance boundary, and determine whether the product performance has fluctuated significantly, thereby providing a performance fluctuation warning, allowing users to intervene in time and further reducing the failure rate of shipped products.

[0055] As a feasible embodiment, the following table describes the identification of outlier products and the update of the real-time performance data pool.

[0056]

[0057] It can be seen from this that in this embodiment, when the performance parameter value in the performance parameter information of the product to be screened exceeds the performance specification boundary, the performance static boundary and the real-time dynamic boundary, the screened product is determined to be an outlier product and an unqualified product, and therefore the performance parameter information of the screened product is not added to the real-time performance data pool of the next batch. In this embodiment, when the performance parameter value in the performance parameter information of the product to be screened does not exceed the performance specification boundary, but exceeds the performance static boundary and the real-time dynamic boundary, the screened product is determined to be an outlier product and a qualified product, and therefore the performance parameter information of the screened product is not added to the real-time performance data pool of the next batch. In this embodiment, when the performance parameter value in the performance parameter information of the product to be screened does not exceed the performance specification boundary and the real-time dynamic boundary, but exceeds the performance static boundary, the screened product is determined to be an outlier product and a qualified product, and therefore the performance parameter information of the screened product is not added to the real-time performance data pool of the next batch. In this embodiment, when the performance parameter values ​​in the performance parameter information of the product to be screened do not exceed the performance specification boundary and the performance static boundary, but exceed the real-time dynamic boundary, the screened product is determined to be an outlier product and a qualified product, thus not exceeding the performance specification boundary and the performance static boundary, and therefore the performance parameter information of the screened product can be added to the real-time performance data pool of the next batch. In this embodiment, when the performance parameter values ​​in the performance parameter information of the product to be screened do not exceed the performance specification boundary, the performance static boundary and the real-time dynamic boundary, the screened product is determined to be not an outlier product and a qualified product, and therefore the performance parameter information of the screened product can be added to the real-time performance data pool of the next batch. Figure 6As shown, this embodiment can obtain the latest real-time performance pool data, generate a real-time dynamic boundary, and obtain a performance specification boundary and a performance static boundary. Based on the performance parameter information of the current batch of products to be screened, it is determined whether the performance parameter values ​​in the performance parameter information exceed the performance specification boundary. If so, the product to be screened is determined to be an unqualified product. If not, the product to be screened is determined to be a qualified product. Furthermore, it is determined whether the performance parameter values ​​in the performance parameter information exceed the performance static boundary. If so, the qualified product is determined to be in an outlier state. If not, it is determined whether the performance parameter values ​​in the performance parameter information exceed the real-time dynamic boundary. If not, the qualified product can be determined to be a non-outlier state, and the performance parameter information of the qualified product in the non-outlier state can be added to the real-time performance data pool. If so, the qualified product can be determined to be an outlier state, and the performance parameter information within the performance static boundary can be filtered out and added to the real-time performance data pool. It is then determined whether the upper limit of the real-time performance data pool is full. If so, the performance parameter information of the historical batch is deleted and the real-time performance data pool is refreshed. If not, the real-time performance data pool is directly refreshed based on the added performance parameter information.

[0058] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the product testing method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0059] The present application provides a product testing device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the product testing method in the above-mentioned embodiment one.

[0060] Reference below Figure 7 , which shows a schematic diagram of the structure of a product testing device suitable for implementing the embodiments of the present application. The product testing device in the embodiments of the present application may include, but is not limited to, terminal devices such as laptop computers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), desktop computers, servers, and the like. Figure 7 The product testing device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0061] like Figure 7As shown, the product testing equipment may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the product testing equipment. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An I / O (input / output) interface 1006 is also connected to the bus. Typically, the following systems may be connected to I / O interface 1006: input devices 1007, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008, such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003, such as a magnetic tape or hard disk; and communication device 1009. Communication device 1009 can allow the product testing device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a product testing device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have alternatively.

[0062] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are performed.

[0063] The product testing device provided in this application, utilizing the product testing method in the aforementioned embodiment, can address the technical issue of low outlier product screening accuracy in the prior art. Compared to the prior art, the beneficial effects of the product testing device provided in this application are the same as those of the product testing method provided in the aforementioned embodiment. Other technical features of this product testing device are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0064] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0065] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0066] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer program) stored thereon, wherein the computer-readable program instructions are used to execute the product testing method in the above-mentioned embodiment.

[0067] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0068] The computer-readable storage medium may be included in the product testing device, or may exist independently without being assembled into the product testing device.

[0069] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the product testing equipment, the product testing equipment is enabled to: obtain the performance static boundaries and the real-time performance data pool of the current batch of qualified products; generate real-time dynamic boundaries based on the real-time performance data pool; and compare the performance parameter information of the current batch of qualified products based on the performance static boundaries and the real-time dynamic boundaries to obtain outlier product information.

[0070] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0071] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0072] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0073] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned product testing method. This computer-readable storage medium can address the low accuracy of outlier product screening in existing technologies. Compared to existing technologies, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the product testing method provided in the aforementioned embodiments and are not further elaborated here.

[0074] The present application also provides a computer program product, comprising a computer program, which implements the steps of the above-mentioned product testing method when executed by a processor.

[0075] The computer program product provided in this application can solve the technical problem of low accuracy in screening outlier products in the prior art. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the product testing method provided in the above embodiment, and will not be repeated here.

[0076] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A product testing method, characterized in that: The product testing method includes: Obtain the static performance boundaries of the current batch of qualified products and the real-time performance data pool; generating a real-time dynamic boundary based on the real-time performance data pool; Based on the performance static boundary and the real-time dynamic boundary, the performance parameter information of the qualified products of the current batch is compared to obtain outlier product information.

2. The product testing method according to claim 1, wherein: The step of generating a real-time dynamic boundary based on the real-time performance data pool includes: Performing normal distribution analysis on the performance parameter values ​​in the real-time performance data pool to obtain the limit probability boundaries of the performance parameter values; The extreme probability boundary of the performance parameter value is used as the real-time dynamic boundary.

3. The product testing method according to claim 1, wherein: After the step of generating a real-time dynamic boundary based on the real-time performance data pool, the product testing method further includes: Get the historical dynamic boundaries of the previous batch; Calculating a first difference between the historical dynamic boundary and the real-time dynamic boundary; After the first difference is greater than a predetermined difference ratio of the historical dynamic boundary, an alarm prompt operation is performed.

4. The product testing method according to claim 1, wherein: After the step of generating a real-time dynamic boundary based on the real-time performance data pool, the product testing method further includes: Obtaining a warning limit boundary, wherein the warning limit boundary is within the performance static boundary; After the real-time dynamic boundary exceeds the warning limit boundary, an alarm prompt operation is performed.

5. The product testing method according to claim 1, wherein: The step of comparing the performance parameter information of the current batch of qualified products based on the static performance boundary and the real-time dynamic boundary to obtain outlier product information includes: Determining whether the performance parameter value in the performance parameter information is within the performance static boundary; If the performance parameter value is not within the performance static boundary, it is determined that the qualified product is in an outlier state; If the performance parameter value is within the performance static boundary, determining whether the performance parameter value is within the real-time dynamic boundary; If the performance parameter value is not within the real-time dynamic boundary, it is determined that the qualified product is in an outlier state; The description information of qualified products in the outlier state is used as outlier product information.

6. The product testing method according to claim 1, wherein: Before the step of obtaining the static performance boundary of the qualified product, the following steps are included: Acquiring performance parameter information of a product to be screened and a performance specification boundary of the product to be screened, wherein the performance static boundary is within the performance specification boundary; Products to be screened whose performance parameter values ​​in the performance parameter information are within the performance specification boundaries are regarded as qualified products.

7. The product testing method according to any one of claims 1 to 6, characterized in that: Before the step of obtaining the static performance boundary of the current batch of qualified products and the real-time performance data pool, the product testing method further includes: When the real-time performance data pool does not contain performance parameter information of historical batches, the performance parameter information of the current batch of qualified products within the performance static boundary is added to the real-time performance data pool; After the step of comparing the performance parameter information of the current batch of qualified products based on the static performance boundary and the real-time dynamic boundary to obtain outlier product information, the method includes: If the real-time performance data pool does not reach the predetermined data volume, adding the performance parameter information of the current batch of qualified products within the performance static boundary to the real-time performance data pool to update the real-time performance data pool; If the real-time performance data pool reaches a predetermined data volume, the earliest performance parameter information of the same data volume of the performance parameter information of the current batch of qualified products within the performance static boundary is deleted from the real-time performance data pool, and the performance parameter information of the current batch of qualified products within the performance static boundary is added to the real-time performance data pool to update the real-time performance data pool.

8. A product testing device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the product testing method according to any one of claims 1 to 7.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the product testing method according to any one of claims 1 to 7 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the product testing method according to any one of claims 1 to 7 are implemented.

Images