Product test data detection method, system, electronic device and storage medium

Abstract

The present invention discloses a method, system, electronic device and storage medium for detecting product test data, the detection method comprising obtaining historical test data of multiple historical batches of products; screening the historical test data to obtain intermediate test data; grouping the intermediate test data according to preset test parameters to obtain a first group; obtaining the distribution type of the first group according to the intermediate test data of the first group; taking the first group corresponding to the distribution type as a target group when the distribution type is a preset distribution type; obtaining a target test limit according to the intermediate test data corresponding to the target group. The present invention determines the initial test limit based on the historical test data, and realizes tightening the critical limit before detecting a new batch of products to ensure the detection accuracy of the test data of the new batch of products; it can adaptively adjust the test limit dynamically, and effectively detect the chip test data with abnormal data in real time, thereby improving the test quality of the chip.

Description

Technical Field

[0001] The present invention relates to the field of chip testing technology, and in particular to a method, system, electronic equipment and storage medium for detecting product test data. Background Art

[0002] During the mass production test phase of semiconductor chips, parameter test results usually conform to the normal distribution. At present, the test results are mainly judged whether they are within the test specification range. If so, the chip is determined to have passed the test (i.e., the chip quality is qualified); however, even if the test results of some chips are within the test specification range, they will deviate too much from the average value. When these abnormal chips are still shipped as good products, it will affect the quality of chip manufacturing and even cause quality accidents. Therefore, the existing chip test data detection method cannot meet the higher chip production requirements. Summary of the invention

[0003] The technical problem to be solved by the present invention is to overcome the defect that the mass production test method of semiconductor chips in the prior art cannot meet actual needs, and the purpose is to provide a detection method, system, electronic device and storage medium for product test data.

[0004] The present invention solves the above technical problems through the following technical solutions:

[0005] The present invention provides a method for detecting product test data, the method comprising:

[0006] Obtain historical test data corresponding to multiple historical batches of products;

[0007] Screening the historical test data to obtain intermediate test data;

[0008] The intermediate test data is grouped according to different preset test parameters to obtain a plurality of first groups; wherein each of the preset test parameters corresponds to one first group;

[0009] Acquire a first distribution type corresponding to each of the first groups according to the intermediate test data corresponding to the first groups;

[0010] determining whether the first distribution type is a preset distribution type, and if so, taking the first group corresponding to the first distribution type as a target group;

[0011] Acquire a target test limit value according to the intermediate test data corresponding to the target group;

[0012] The target test limit is used to test the test data of a new batch of products.

[0013] Preferably, the step of acquiring the target test limit value according to the intermediate test data corresponding to the target group includes:

[0014] Calculating statistical parameters corresponding to the target group according to the intermediate test data corresponding to the target group; wherein the statistical parameters include a mean value and a mean square error;

[0015] The test upper limit value and the test lower limit value are calculated according to the statistical parameters and the preset constraint conditions, and the test upper limit value and the test lower limit value are used as the target test limit value.

[0016] Preferably, after the step of acquiring the target test limit value according to the intermediate test data corresponding to the target group, the step further includes:

[0017] Get the current test data corresponding to the current test group in the current batch of products;

[0018] Acquire multiple groups of target test data corresponding to different preset test parameters in the current test data;

[0019] Determine whether the target test data is within the corresponding target test limit, if so, determine that the target test data is normal test data; if not, determine that the target test data is abnormal test data;

[0020] When a set number of the target test data are all normal test data, it is determined that the current test data of the current test group passes the test; otherwise, it is determined that the current test data of the current test group fails the test.

[0021] Preferably, when it is determined that the current test data corresponding to the current test group in the current batch of products passes the test and the preset distribution type is a normal distribution, the detection method further includes:

[0022] Using the intermediate test data corresponding to the target group as the current training population;

[0023] Calculate and obtain initial population parameters corresponding to the current training population;

[0024] Determine whether the current test data falls within the central area of ​​the normal distribution corresponding to the current training population according to the initial population parameters, and if so, determine whether the robustness of the current test data meets the preset requirements, and insert the current test data into the training population to form a target training population;

[0025] Updating the target test limit according to the test data corresponding to the target training population;

[0026] For the test data corresponding to the next test group in the current batch of products, the target population parameters corresponding to the target training population are calculated;

[0027] Determine whether the current test data falls within the central area of ​​the normal distribution corresponding to the target training population according to the target population parameters, and if so, determine whether the robustness of the current test data meets the preset requirements, and insert the current test data into the target training population to form a new target training population;

[0028] The target test limit is updated according to the new test data corresponding to the target training population.

[0029] Preferably, the detection method further comprises:

[0030] Determine whether the test data in the target training population meets a preset condition, and if so, generate first test data to update the target training population;

[0031] Among them, the difference between the statistical parameters of the target training population before updating and the target training population after updating is less than a first set threshold, and the test data corresponding to the updated target training population does not meet the preset condition; the statistical parameters include the mean value and the mean square error.

[0032] Preferably, the step of determining whether the test data in the target training population meets a preset condition, and if so, generating first test data to update the target training population comprises:

[0033] Obtaining the quartiles corresponding to the test data in the target training population;

[0034] It is determined whether the first quartile of the quartiles is equal to the third quartile. If so, the first test data is randomly generated to update the target training population.

[0035] Preferably, the step of randomly generating the first test data to update the target training population includes:

[0036] A group of second test data is randomly generated by using at least one of an inverse function sampling method, a Box-Muller transformation method (a method for generating normally distributed random numbers), and a central limit theorem, and the difference between the statistical parameters corresponding to each group of the second test data and the statistical parameters of the target training population before updating is calculated, and the second test data corresponding to the minimum absolute value of the difference is selected as the first test data to update the target training population.

[0037] Preferably, the step of screening the historical test data to obtain the intermediate test data includes:

[0038] Filtering out third test data corresponding to all the preset test parameters in the historical test data;

[0039] The test data exceeding a preset test limit is removed from the third test data to obtain the intermediate test data.

[0040] Preferably, the step of grouping the intermediate test data according to preset test parameters to obtain a plurality of first groups includes:

[0041] Grouping the intermediate test data according to different preset test parameters to obtain multiple intermediate groups;

[0042] It is determined whether the size of the intermediate group is greater than or equal to a second set threshold; if so, the intermediate group is used as the first group.

[0043] Preferably, before the step of obtaining historical test data corresponding to multiple historical batches of products, the step further includes:

[0044] Pre-establish static data space;

[0045] After the step of acquiring the historical test data corresponding to the plurality of historical batches of products and before the step of screening the historical test data to acquire the intermediate test data, the following steps are included:

[0046] Acquire the historical test data in a set format, decode the historical test data, and store the decoded historical test data in the static data space;

[0047] The step of filtering out the third test data corresponding to all the preset test parameters in the historical test data includes:

[0048] Based on all the preset test parameters, the third test data is output from the static data space through different APIs (application programming interfaces).

[0049] The present invention also provides a product test data detection system, the detection system comprising:

[0050] A historical data acquisition module is used to acquire historical test data corresponding to multiple historical batches of products;

[0051] An intermediate data acquisition module, used for screening the historical test data to obtain intermediate test data;

[0052] A group acquisition module, used for performing group processing on the intermediate test data according to different preset test parameters to acquire a plurality of first groups; wherein each of the preset test parameters corresponds to one first group;

[0053] a distribution type acquisition module, configured to acquire a first distribution type corresponding to each of the first groups according to the intermediate test data corresponding to the first groups;

[0054] A first judging module, configured to judge whether the first distribution type is a preset distribution type, and if so, taking the first group corresponding to the first distribution type as a target group;

[0055] A test limit acquisition module, used to acquire a target test limit according to the intermediate test data corresponding to the target group;

[0056] The target test limit is used to test the test data of a new batch of products.

[0057] Preferably, the test limit acquisition module includes:

[0058] A parameter calculation unit, configured to calculate the statistical parameters corresponding to the target group according to the intermediate test data corresponding to the target group; wherein the statistical parameters include a mean value and a mean square error;

[0059] A test limit calculation unit is used to calculate a test upper limit value and a test lower limit value according to the statistical parameters and preset constraints, and use the test upper limit value and the test lower limit value as the target test limit value.

[0060] Preferably, the detection system further comprises:

[0061] The current data acquisition module is used to obtain the current test data corresponding to the current test group in the current batch of products;

[0062] A target data acquisition module, used to acquire multiple groups of target test data corresponding to different preset test parameters in the current test data;

[0063] A second judgment module is used to judge whether the target test data is within the corresponding target test limit, and if so, determine that the target test data is normal test data; if not, determine that the target test data is abnormal test data;

[0064] The determination module is used to determine that the current test data of the current test group has passed the test when a set number of the target test data are all normal test data; otherwise, determine that the current test data of the current test group has not passed the test.

[0065] Preferably, when it is determined that the current test data corresponding to the current test group in the current batch of products passes the test and the preset distribution type is a normal distribution, the detection system further includes:

[0066] A current population acquisition module, used to use the intermediate test data corresponding to the target group as the current training population;

[0067] A population parameter calculation module, used to calculate the initial population parameters corresponding to the current training population;

[0068] A third judgment module is used to judge whether the current test data falls into the central area of ​​the normal distribution corresponding to the current training population according to the initial population parameters, and if so, determine that the robustness of the current test data meets the preset requirements, and insert the current test data into the training population to form a target training population;

[0069] A test limit updating module, used for updating the target test limit according to the test data corresponding to the target training population;

[0070] For the test data corresponding to the next test group in the current batch of products, the population parameter calculation module is further used to calculate the target population parameters corresponding to the target training population;

[0071] The third judgment module is also used to judge whether the current test data falls into the central area of ​​the normal distribution corresponding to the target training population according to the target population parameters, and if so, determine that the robustness of the current test data meets the preset requirements, and insert the current test data into the target training population to form a new target training population;

[0072] The test limit updating module is also used to update the target test limit according to the new test data corresponding to the target training population.

[0073] Preferably, the detection system further comprises:

[0074] A fourth judgment module, used to judge whether the test data in the target training population meets a preset condition, and if so, to generate first test data to update the target training population;

[0075] Among them, the difference between the statistical parameters of the target training population before updating and the target training population after updating is less than a first set threshold, and the test data corresponding to the updated target training population does not meet the preset condition; the statistical parameters include the mean value and the mean square error.

[0076] Preferably, the fourth determination module includes:

[0077] A quartile acquisition unit, used to acquire the quartiles corresponding to the test data in the target training population;

[0078] A first judging unit, configured to judge whether the first quartile of the quartiles is equal to the third quartile, and if so, calling a generating unit;

[0079] The generating unit is used to randomly generate the first test data to update the target training population.

[0080] Preferably, the generation unit adopts at least one of the inverse function sampling method, the Box-Muller transformation method, and the central limit theorem to randomly generate a group of second test data, calculate the difference between the statistical parameters corresponding to each group of the second test data and the statistical parameters of the target training population before updating, and select the second test data corresponding to the minimum absolute value of the difference as the first test data to update the target training population.

[0081] Preferably, the intermediate data acquisition module includes:

[0082] A screening unit, used for screening out third test data corresponding to all the preset test parameters in the historical test data;

[0083] The elimination unit is used to eliminate the test data exceeding the preset test limit from the third test data to obtain the intermediate test data.

[0084] Preferably, the group acquisition module includes:

[0085] A grouping unit, used for grouping the intermediate test data according to different preset test parameters to obtain multiple intermediate groups;

[0086] The second judgment unit is used to judge whether the size of the intermediate group is greater than or equal to a second set threshold, and if so, use the intermediate group as the first group.

[0087] Preferably, the detection system comprises:

[0088] A data space establishment module is used to establish a static data space in advance;

[0089] A storage module, used for acquiring the historical test data in a set format, decoding the historical test data and storing the decoded historical test data in the static data space;

[0090] The screening unit is used to output the third test data from the static data space through different APIs based on all the preset test parameters.

[0091] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for detecting product test data when executing the computer program.

[0092] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for detecting product test data are implemented.

[0093] On the basis of being in accordance with the common sense in the art, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present invention.

[0094] The positive and progressive effects of the present invention are:

[0095] In the present invention, based on the collected historical test data of several batches of products and preset test parameters (such as test items), filtering, grouping and other processing are performed on them, and the target group is screened out according to the distribution type of the test data in each group to calculate the initial test limit, that is, to tighten the key limit before the new batch of products is tested, so as to ensure the detection accuracy of the test data of the new batch of products, so as to improve the test quality of the chip; when the robustness of the test data of the new batch of products meets the set conditions, the current test data is inserted into the previous training population to form a new training population, and then updated to obtain a new dynamic test limit, that is, to realize adaptive dynamic adjustment of the test limit, which can effectively detect the chip test data with abnormal data in real time, thereby further improving the test quality of the chip. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] Figure 1 This is a flow chart of the method for detecting product test data according to Embodiment 1 of the present invention.

[0097] Figure 2 This is a schematic diagram of the test limit values ​​in the method for detecting product test data in Example 1 of the present invention.

[0098] Figure 3 This is a first flow chart of the method for detecting product test data according to Embodiment 2 of the present invention.

[0099] Figure 4 This is a second flow chart of the method for detecting product test data according to Embodiment 2 of the present invention.

[0100] Figure 5 Schematic diagram of normal distribution of the training population in the method for detecting product test data in Example 2 of the present invention.

[0101] Figure 6 This is a schematic diagram of the process of generating a new training population in the method for detecting product test data according to Embodiment 2 of the present invention.

[0102] Figure 7 This is a first test schematic diagram of the method for detecting product test data according to Embodiment 2 of the present invention.

[0103] Figure 8 This is a second test schematic diagram of the method for detecting product test data according to Embodiment 2 of the present invention.

[0104] Fig. 9 It is a schematic diagram of the detection results corresponding to the existing dynamic DPAT detection method.

[0105] Fig.10 This is a schematic diagram of the detection results corresponding to the detection method for product test data in Example 2 of the present invention.

[0106] Fig.11 This is a module schematic diagram of a system for detecting product test data according to Embodiment 3 of the present invention.

[0107] Fig.12 This is a module schematic diagram of a system for detecting product test data according to Embodiment 4 of the present invention.

[0108] Fig.13 This is a schematic diagram of the structure of an electronic device for implementing a method for detecting product test data according to Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0109] The present invention is further described below by way of examples, but the present invention is not limited to the scope of the examples.

[0110] Example 1

[0111] like Figure 1 As shown, the method for detecting product test data of this embodiment includes:

[0112] S101, obtaining historical test data corresponding to multiple historical batches of products;

[0113] In one practicable manner, the historical test data is test data of at least six historical batches of products with test limits defined by equipment specifications, and each batch of products includes at least 30 test parameters; wherein the number of historical batches of products corresponding to the historical test data and the number of test parameters in each batch of products can be re-determined and adjusted based on actual conditions.

[0114] Historical test data is generally stored as STDF (Standard Test Data Format) files, which are batch production test data files; of course, it can also be stored in other formats according to actual conditions.

[0115] In addition, a static data space needs to be established in the memory in advance. Once the static data space is established, the mass production test process can begin.

[0116] When the detection starts, the STDF file corresponding to the historical test data is initialized, and the STDF content corresponding to the STDF file is decoded and stored in the static data space; wherein the decoded STDF content is ASCII data.

[0117] S102, screening the historical test data to obtain intermediate test data;

[0118] The third test data corresponding to all preset test parameters in the historical test data are screened out, and the test data exceeding the preset test limit are removed from the third test data to obtain the intermediate test data.

[0119] Specifically, based on all preset test parameters, the third test data is output from the static data space through different APIs. The preset test parameters include but are not limited to test items or multiple homologous application sites.

[0120] In addition, it is necessary to check whether the distribution of all intermediate test data obtained is reasonable through manual or automatic methods, and exclude obviously unreasonable test data to ensure the accuracy and reliability of the subsequent test limit determination.

[0121] S103, grouping the intermediate test data according to different preset test parameters to obtain a plurality of first groups; wherein each preset test parameter corresponds to a first group;

[0122] Specifically, the intermediate test data is grouped and processed according to different preset test parameters to obtain multiple intermediate groups, and it is determined whether the size of the intermediate group is greater than or equal to a second set threshold. If so, the intermediate group is used as the first group, that is, the group containing a smaller amount of data is eliminated, thereby reducing the overall calculation amount, improving the calculation efficiency, and thus improving the overall detection efficiency.

[0123] S104, acquiring a first distribution type corresponding to each first group according to the intermediate test data corresponding to the first group;

[0124] S105, determining whether the first distribution type is a preset distribution type, and if so, taking a first group corresponding to the first distribution type as a target group;

[0125] Among them, the preset distribution type includes normal distribution, that is, by comparing the distribution types, groups of other distribution types such as 0-1 distribution are eliminated, and only groups of normal distribution are retained, thereby ensuring the accuracy and reliability of subsequent test limit determination.

[0126] S106, obtaining a target test limit value according to the intermediate test data corresponding to the target group;

[0127] Among them, the target test limit is used to conduct mass production testing on the test data of new batches of products. As the first dynamic limit, the target test limit ensures that the key limit is tightened before starting the testing of new batches of products, ensuring the accuracy of the test data of new batches of products.

[0128] Specifically, the statistical parameters corresponding to the target group are calculated according to the intermediate test data corresponding to the target group; wherein the statistical parameters include the mean value and the mean square error;

[0129] The test upper limit value and the test lower limit value are calculated according to the statistical parameters and the preset constraints (CPK constraints, i.e., the process capability index), and the test upper limit value and the test lower limit value are used as the target test limit values.

[0130] For example:

[0131]

[0132]

[0133] in, represents the mean value, σ represents the mean square error, CPK represents the preset constraint condition, Dynamic UL represents the test upper limit, and Dynamic LL represents the test lower limit.

[0134] In one practicable manner, if Figure 2 As shown in (a) of FIG. 1 , the test limit is [0, 200] based only on the design specification of the product to be tested; Figure 2 As shown in (b), when the test upper limit and test lower limit [46.13, 67.87] are calculated based on statistical parameters and CPK constraints (±CPK*sigma, sigma represents the mean square error), that is, by combining the CPK constraints, a tighter test limit can be calculated to ensure the test quality of the chip.

[0135] In this embodiment, based on the collected historical test data of several batches of products and preset test parameters (such as test items), they are filtered, grouped, and the target group is screened out according to the distribution type of the test data in each group to calculate the test limit, so as to tighten the critical limit before the new batch of products is tested, so as to ensure the detection accuracy of the test data of the new batch of products, thereby improving the test quality of the chip.

[0136] Example 2

[0137] like Figure 3 As shown, the method for detecting product test data of this embodiment is a further improvement on Embodiment 1, specifically:

[0138] After step S106, the following steps are also included:

[0139] S107, obtaining current test data corresponding to the current test group in the current batch of products;

[0140] S108, obtaining multiple groups of target test data corresponding to different preset test parameters in the current test data;

[0141] S109, determining whether the target test data is within the corresponding target test limit, if so, determining that the target test data is normal test data; if not, determining that the target test data is abnormal test data;

[0142] S1010: When the set number of target test data are all normal test data, it is determined that the current test data of the current test group passes the test; otherwise, it is determined that the current test data of the current test group fails the test.

[0143] The set number of target test data may be the total number of target test data, or may be specifically determined according to actual conditions. For example, when 98 of 100 target test data are normal test data, it is determined that the current test data of the current test group passes the detection.

[0144] like Figure 4 As shown, when it is determined that the current test data corresponding to the current test group in the current batch of products passes the test and the preset distribution type is a normal distribution, after step S1010, the following is further included:

[0145] S1011, using the intermediate test data corresponding to the target group as the current training population;

[0146] S1012, calculating and obtaining the initial population parameters corresponding to the current training population;

[0147] S1013, judging whether the current test data falls within the central area of ​​the normal distribution corresponding to the current training population according to the initial population parameters, and if so, determining whether the robustness of the current test data meets the preset requirements, and inserting the current test data into the current training population to form a target training population;

[0148] S1014, updating the target test limit according to the test data corresponding to the target training population;

[0149] like Figure 5 As shown, a1 represents the adaptability of the data, a2 represents normal fitting (normal distribution fitting curve), a3 represents +3sigma, a4 represents -3sigma, MEAT-LL represents the test lower limit, and MEAT-UL represents the test upper limit.

[0150] When the current test data falls into the central area of ​​the normal distribution corresponding to the current training population, it means that the robustness (adaptability) of the current test data is strong enough; Figure 6 As shown, it is now inserted into the previous training population to form a new training population corresponding to new statistical parameters, thereby dynamically establishing a new target test limit.

[0151] Among them, during the batch testing stage of production wafers, the adaptability function is used to continuously monitor the test data of each chip, and the training population continues to evolve to achieve the purpose of adaptive testing.

[0152] S1015. For the test data corresponding to the next test group in the current batch of products, calculate and obtain the target population parameters corresponding to the target training population;

[0153] S1016, judging whether the current test data falls within the central area of ​​the normal distribution corresponding to the target training population according to the target population parameters, and if so, determining whether the robustness of the current test data meets the preset requirements, and inserting the current test data into the target training population to form a new target training population;

[0154] Among them, for the same preset test parameter, when the corresponding test data in the current test data meets the robustness requirement, the corresponding test data in the current test data is inserted into the previous training population to form a target training population.

[0155] Specifically, the robustness can be determined by the following formula:

[0156]

[0157] S1017, updating the target test limit according to the test data corresponding to the new target training population. Specifically, the corresponding statistical parameters are calculated according to the test data corresponding to the new target training population, and the new target test limit is finally calculated in combination with the CPK constraint condition.

[0158] The target test limit is updated in time through the test data corresponding to the new test group in the same batch of products to ensure the quality of chip testing.

[0159] That is, in the process of mass production automatic testing, this embodiment continuously uses the test data of the current chip as a new individual and compares it with the population array through the fitness function to evaluate its robustness.

[0160] The detection method of this embodiment is a real-time test data monitoring algorithm based on evolutionary theory, called MEAT (Monitored Evolutionary Algorithm during Testing), which combines the characteristics of static PAT (Part Average Test Guide) and dynamic PAT, and introduces CPK constraints and evolutionary strategies to achieve high-quality testing of consumer chips.

[0161] like Figure 7 As shown, the horizontal axis represents the test data sequence, the vertical axis Test Data Distribution represents the test data range, LL represents the test lower limit value, UL represents the test upper limit value, and the dots in area A represent each current test data; it can be seen that the current test data is detected based on the target test limit value obtained above.

[0162] In addition, when the preset test parameters include test items, MEAT monitors each test item as a separate training population; when the preset test parameters include sites in multiple homologous applications, MEAT monitors each site in the multiple homologous applications as a separate training population. Figure 8 As shown, for dynamic limits in multi-site applications, each site has an independent limit line.

[0163] In addition, after step S1017, the following steps are also included:

[0164] S1018, determining whether the test data in the target training population meets a preset condition, and if so, generating first test data to update the target training population;

[0165] Among them, the difference between the statistical parameters of the target training population before updating and the target training population after updating is less than a first set threshold, and the test data corresponding to the updated target training population does not meet the preset conditions; the statistical parameters include the mean value and the mean square error.

[0166] Step S1018 specifically includes:

[0167] Get the quartiles corresponding to the test data in the target training population;

[0168] It is determined whether the first quartile among the quartiles is equal to the third quartile. If so, first test data is randomly generated to update the target training population.

[0169] Specifically, at least one of the inverse function sampling method, the Box-Muller transformation method, and the central limit theorem is used to randomly generate a set of second test data, calculate the difference between the statistical parameters corresponding to each set of second test data and the statistical parameters of the target training population before updating, and select the second test data corresponding to the minimum absolute value of the difference as the first test data to update the target training population. Of course, a method that can randomly generate data can also be used to generate test data.

[0170] Using randomly generated test data to replace the test data in the original target training population can effectively avoid the local convergence of the population during the evolution process so that UL and LL are too close, thereby ensuring the reliability of the dynamic test limit.

[0171] The detection method MEAT of this embodiment does not need to be based on other information other than the above content, such as the coordinates of the grains on the wafer, thereby improving the detection efficiency and accuracy of existing product detection methods.

[0172] The following is a detailed description with examples:

[0173] like Fig. 9 As shown in the figure, the detection result of the test data based on the existing Dynamic PAT detection method is detected. Among them, the horizontal axis represents the test data sequence, and the vertical axis represents the test data range. DPAT-LL represents the lower limit of the test, and DPAT-UL represents the upper limit of the test. At b1 in the figure, due to the continuous abnormal data in the test data, DPAT-UL also shows a significant increase. It can be seen that this detection method has a high dependence on the test data, so the continuous release of data will have a greater impact on its detection mechanism, and it may even lose its effectiveness.

[0174] like Fig.10 The figure shows the test results of the test data based on the MEAT detection method. The horizontal axis represents the test data sequence and the vertical axis represents the test data range. MEAT-LL represents the lower limit of the test and MEAT-UL represents the upper limit of the test. It can be seen that the MEAT detection method determines whether to perform population evolution based on the robustness of the data, which reduces the sensitivity of the MEAT dynamic limit to the test data and has a more reasonable mechanism to reduce the dependence on the test data. In this detection method, data can even be released continuously, and the dynamic limit can be effectively and strictly tightened during the production process.

[0175] The comparison data of the detection results of the dynamic DPAT detection method and the MEAT detection method of this embodiment are as follows:

[0176] Number of chips to be tested DPPM Number of failed chips DPAT outlier count MEAT outliers 11440 50874 582 4 515

[0177] It can be seen from the above table that the number of chips to be tested is 11440, and the number of failed chips is 582, so the DPPM (defective percentage per million) of this batch of chips = (582 / 11440)*1000000 = 50874.

[0178] The existing DPAT detection method can only detect 4 abnormal test data from the 582 published data, and the corresponding detection rate = (4 / 582)*100% = 0.69%. The MEAT outlier number of this embodiment can detect 515 abnormal test data from the 582 published data, and the corresponding detection rate = (515 / 582)*100% = 88.49%. It can be seen that the test data detection method of this embodiment can effectively analyze abnormal test data, thereby effectively improving the test quality of the chip.

[0179] In addition, experiments have shown that the unit test coverage of the MEAT detection method in this embodiment exceeds 95% of the C++ and Java versions. The MEAT detection method can even be applied to data consistency checks across operating systems and programming languages ​​to achieve the creation and real-time storage of traceable adaptive data.

[0180] In this embodiment, based on the collected historical test data of several batches of products and preset test parameters (such as test items), filtering, grouping and other processing are performed on them, and the target group is screened out according to the distribution type of the test data in each group to calculate the initial test limit; when the robustness of the test data of the new batch of products meets the set conditions, the current test data is inserted into the previous training population to form a new training population, so as to update the new dynamic test limit. That is, the MEAT detection method monitors the evolution of the population according to the robustness of the data (fitness / robustness), realizes adaptive dynamic adjustment of the test limit, and can effectively detect chip test data with abnormal data in real time, thereby improving the test quality of the chip.

[0181] Example 3

[0182] like Fig.11 As shown, the product test data detection system of this embodiment includes a historical data acquisition module 1, an intermediate data acquisition module 2, a grouping acquisition module 3, a distribution type acquisition module 4, a first judgment module 5 and a test limit acquisition module 6.

[0183] The historical data acquisition module 1 is used to acquire historical test data corresponding to multiple historical batches of products;

[0184] In one practicable manner, the historical test data is test data of at least six historical batches of products with test limits defined by equipment specifications, and each batch of products includes at least 30 test parameters; wherein the number of historical batches of products corresponding to the historical test data and the number of test parameters in each batch of products can be re-determined and adjusted based on actual conditions.

[0185] Historical test data is generally stored as STDF files, which are batch production test data files; of course, it can also be stored in other formats according to actual conditions.

[0186] In addition, a static data space needs to be established in the memory in advance. Once the static data space is established, the mass production test process can begin.

[0187] When the detection starts, the STDF file corresponding to the historical test data is initialized, and the STDF content corresponding to the STDF file is decoded and stored in the static data space; wherein the decoded STDF content is ASCII data.

[0188] The product test data detection system of this embodiment also includes a data space establishment module and a storage module. The data space establishment module is used to pre-establish a static data space; the storage module is used to obtain historical test data in a set format, decode the historical test data, and store the decoded historical test data in the static data space.

[0189] The intermediate data acquisition module 2 is used to filter and process the historical test data to obtain the intermediate test data;

[0190] The intermediate data acquisition module 2 includes a screening unit and a rejection unit.

[0191] The screening unit is used to screen out the third test data corresponding to all preset test parameters in the historical test data; the elimination unit is used to eliminate the test data exceeding the preset test limit from the third test data to obtain the intermediate test data.

[0192] Specifically, based on all preset test parameters, the third test data is output from the static data space through different APIs. The preset test parameters include but are not limited to test items or multiple homologous application sites.

[0193] In addition, it is necessary to check whether the distribution of all intermediate test data obtained is reasonable through manual or automatic methods, and exclude obviously unreasonable test data to ensure the accuracy and reliability of the subsequent test limit determination.

[0194] The group acquisition module 3 is used to perform group processing on the intermediate test data according to different preset test parameters to obtain a plurality of first groups; wherein each preset test parameter corresponds to a first group;

[0195] Specifically, the grouping acquisition module 3 includes a grouping unit and a second judgment unit.

[0196] A grouping unit is used to group the intermediate test data according to different preset test parameters to obtain multiple intermediate groups; a second judgment unit is used to judge whether the size of the intermediate group is greater than or equal to a second set threshold. If so, the intermediate group is used as the first group, that is, the group containing a smaller amount of data is eliminated, which reduces the overall calculation amount, improves the calculation efficiency, and thus improves the overall detection efficiency.

[0197] The distribution type acquisition module 4 is used to acquire the first distribution type corresponding to each first group according to the intermediate test data corresponding to the first group;

[0198] The first judgment module 5 is used to judge whether the first distribution type is a preset distribution type, and if so, take the first group corresponding to the first distribution type as the target group;

[0199] Among them, the preset distribution type includes normal distribution, that is, by comparing the distribution types, the groups of other distribution types such as 0-1 distribution are eliminated, and only the groups of normal distribution are retained, thereby ensuring the accuracy and reliability of the subsequent test limit determination. The test limit acquisition module 6 is used to obtain the target test limit according to the intermediate test data corresponding to the target group;

[0200] Among them, the target test limit is used to test the test data of new batches of products.

[0201] The target test limit, as the first dynamic limit, ensures that the critical limit is tightened before starting testing a new batch of products, thereby ensuring the accuracy of the test data for the new batch of products.

[0202] Specifically, the test limit value acquisition module 6 includes a parameter calculation unit and a test limit value calculation unit;

[0203] The parameter calculation unit is used to calculate the statistical parameters corresponding to the target group according to the intermediate test data corresponding to the target group; wherein the statistical parameters include the mean value and the mean square error;

[0204] The test limit calculation unit is used to calculate the test upper limit value and the test lower limit value according to statistical parameters and preset constraints (CPK constraints, i.e., process capability index), and use the test upper limit value and the test lower limit value as target test limits.

[0205] For example:

[0206]

[0207]

[0208] in, represents the mean value, σ represents the mean square error, CPK represents the preset constraint condition, Dynamic UL represents the test upper limit, and Dynamic LL represents the test lower limit.

[0209] In one practicable manner, if Figure 2 As shown in (a) of FIG. 1 , the test limit is [0, 200] based only on the design specification of the product to be tested; Figure 2 As shown in (b), when the test upper limit and test lower limit [46.13, 67.87] are calculated based on statistical parameters and CPK constraints (±CPK*sigma, sigma represents the mean square error), that is, by combining the CPK constraints, a tighter test limit can be calculated to ensure the test quality of the chip.

[0210] In this embodiment, based on the collected historical test data of several batches of products and preset test parameters (such as test items), they are filtered, grouped, and the target group is screened out according to the distribution type of the test data in each group to calculate the test limit, so as to tighten the critical limit before the new batch of products is tested, so as to ensure the detection accuracy of the test data of the new batch of products, thereby improving the test quality of the chip.

[0211] Example 4

[0212] like Fig.12 As shown, the product test data detection system of this embodiment is a further improvement of Embodiment 3, specifically:

[0213] The detection system further includes a current data acquisition module 7 , a target data acquisition module 8 , a second judgment module 9 and a determination module 10 .

[0214] The current data acquisition module 7 is used to acquire the current test data corresponding to the current test group in the current batch of products;

[0215] The target data acquisition module 8 is used to acquire multiple groups of target test data corresponding to different preset test parameters in the current test data;

[0216] The second judgment module 9 is used to judge whether the target test data is within the corresponding target test limit. If so, the target test data is determined to be normal test data; if not, the target test data is determined to be abnormal test data;

[0217] The determination module 10 is used to determine that the current test data of the current test group has passed the test when a set number of target test data are all normal test data; otherwise, determine that the current test data of the current test group has failed the test.

[0218] The set number of target test data may be the total number of target test data, or may be specifically determined according to actual conditions. For example, when 98 of 100 target test data are normal test data, it is determined that the current test data of the current test group passes the detection.

[0219] When it is determined that the current test data corresponding to the current test group in the current batch of products passes the test and the preset distribution type is a normal distribution, the detection system of this embodiment also includes a current population acquisition module 11, a population parameter calculation module 12, a third judgment module 13 and a test limit update module 14.

[0220] The current population acquisition module 11 is used to use the intermediate test data corresponding to the target group as the current training population;

[0221] The population parameter calculation module 12 is used to calculate the initial population parameters corresponding to the current training population;

[0222] The third judgment module 13 is used to judge whether the current test data falls into the central area of ​​the normal distribution corresponding to the current training population according to the initial population parameters. If so, it is determined that the robustness of the current test data meets the preset requirements, and the current test data is inserted into the training population to form a target training population;

[0223] The test limit updating module 14 is used to update the target test limit according to the test data corresponding to the target training population;

[0224] like Figure 5 As shown in , when the current test data falls into the central area of ​​the normal distribution corresponding to the current training population, it means that the robustness (adaptability) of the current test data is strong enough; Figure 6 As shown, it is now inserted into the previous training population to form a new training population corresponding to new statistical parameters, thereby dynamically establishing a new target test limit.

[0225] Among them, during the batch testing stage of production wafers, the adaptability function is used to continuously monitor the test data of each chip, and the training population continues to evolve to achieve the purpose of adaptive testing.

[0226] For the test data corresponding to the next test group in the current batch of products, the population parameter calculation module 12 is also used to calculate the target population parameters corresponding to the target training population;

[0227] The third judgment module 13 is also used to judge whether the current test data falls into the central area of ​​the normal distribution corresponding to the target training population according to the target population parameters, and if so, determine that the robustness of the current test data meets the preset requirements, and insert the current test data into the target training population to form a new target training population;

[0228] Among them, for the same preset test parameter, when the corresponding test data in the current test data meets the robustness requirement, the corresponding test data in the current test data is inserted into the previous training population to form a target training population.

[0229] Specifically, the robustness can be determined by the following formula:

[0230]

[0231] The test limit updating module 14 is further used to update the target test limit according to the new test data corresponding to the target training population.

[0232] Specifically, the corresponding statistical parameters are calculated based on the test data corresponding to the new target training population, and the new target test limit is finally calculated in combination with the CPK constraint condition.

[0233] The target test limit is updated in time through the test data corresponding to the new test group in the same batch of products to ensure the quality of chip testing.

[0234] That is, in the process of mass production automatic testing, this embodiment continuously uses the test data of the current chip as a new individual and compares it with the population array through the fitness function to evaluate its robustness.

[0235] The detection method of this embodiment belongs to a real-time test data monitoring algorithm based on evolution theory, called MEAT, which combines the characteristics of static PAT and dynamic PAT, and introduces CPK constraints and evolution strategies to achieve high-quality testing of consumer chips.

[0236] like Figure 7 As shown, the horizontal axis represents the test data sequence, the vertical axis Test Data Distribution represents the test data range, LL represents the test lower limit value, UL represents the test upper limit value, and the dots in area A represent each current test data; it can be seen that the current test data is detected based on the target test limit value obtained above.

[0237] In addition, when the preset test parameters include test items, MEAT monitors each test item as a separate training population; when the preset test parameters include sites in multiple homologous applications, MEAT monitors each site in the multiple homologous applications as a separate training population. Figure 8 As shown, for dynamic limits in multi-site applications, each site has an independent limit line.

[0238] In addition, the detection system of this embodiment further includes a fourth judgment module 15;

[0239] The fourth judgment module 15 is used to judge whether the test data in the target training population meets the preset conditions, and if so, to generate the first test data to update the target training population;

[0240] Among them, the difference between the statistical parameters of the target training population before updating and the target training population after updating is less than a first set threshold, and the test data corresponding to the updated target training population does not meet the preset conditions; the statistical parameters include the mean value and the mean square error.

[0241] Specifically, the fourth judgment module 15 includes a quartile acquisition unit, a first judgment unit and a generation unit.

[0242] The quartile acquisition unit is used to obtain the quartiles corresponding to the test data in the target training population;

[0243] The first judging unit is used to judge whether the first quartile among the quartiles is equal to the third quartile, and if so, call the generating unit;

[0244] The generating unit is used for randomly generating first test data to update the target training population.

[0245] The generating unit adopts at least one of the inverse function sampling method, the Box-Muller transformation method, and the central limit theorem to randomly generate a set of second test data, calculate the difference between the statistical parameters corresponding to each set of second test data and the statistical parameters of the target training population before updating, and select the second test data corresponding to the minimum absolute value of the difference as the first test data to update the target training population. Of course, a method that can randomly generate data can also be used to generate test data.

[0246] Using randomly generated test data to replace the test data in the original target training population can effectively avoid the local convergence of the population during the evolution process so that UL and LL are too close, thereby ensuring the reliability of the dynamic test limit.

[0247] The detection method MEAT of this embodiment does not need to be based on other information other than the above content, such as the coordinates of the grains on the wafer, thereby improving the detection efficiency and accuracy of existing product detection methods.

[0248] The following is a detailed description with examples:

[0249] like Fig. 9As shown in the figure, it is the detection result of the test data based on the existing dynamic DPAT method. Among them, the horizontal axis represents the test data sequence, and the vertical axis represents the test data range. DPAT-LL represents the lower limit of the test, and DPAT-UL represents the upper limit of the test. At b1 in the figure, due to the continuous abnormal data in the test data, DPAT-UL also shows a significant increase. It can be seen that this detection method has a high dependence on the test data, so the continuous release of data will have a greater impact on its detection mechanism, and it may even lose its effectiveness.

[0250] like Fig.10 The figure shows the test results of the test data based on the MEAT detection method. The horizontal axis represents the test data sequence and the vertical axis represents the test data range. MEAT-LL represents the lower limit of the test and MEAT-UL represents the upper limit of the test. It can be seen that the MEAT detection method determines whether to perform population evolution based on the robustness of the data, which reduces the sensitivity of the MEAT dynamic limit to the test data and has a more reasonable mechanism to reduce the dependence on the test data. In this detection method, data can even be released continuously, and the dynamic limit can be effectively and strictly tightened during the production process.

[0251] The comparison data of the detection results of the dynamic DPAT detection method and the MEAT detection method of this embodiment are as follows:

[0252] Number of chips to be tested DPPM Number of failed chips DPAT outlier count MEAT outliers 11440 50874 582 4 515

[0253] It can be seen from the above table that the number of chips to be tested is 11440, and the number of failed chips is 582, so the DPPM (defective percentage per million) of this batch of chips = (582 / 11440)*1000000 = 50874.

[0254] The existing DPAT detection method can only detect 4 abnormal test data from the 582 published data, and the corresponding detection rate = (4 / 582)*100% = 0.69%. The MEAT outlier number of this embodiment can detect 515 abnormal test data from the 582 published data, and the corresponding detection rate = (515 / 582)*100% = 88.49%. It can be seen that the test data detection method of this embodiment can effectively analyze abnormal test data, thereby effectively improving the test quality of the chip.

[0255] In addition, experiments have shown that the unit test coverage of the MEAT detection method in this embodiment exceeds 95% of the C++ and Java versions. The MEAT detection method can even be applied to data consistency checks across operating systems and programming languages ​​to achieve the creation and real-time storage of traceable adaptive data.

[0256] In this embodiment, based on the collected historical test data of several batches of products and preset test parameters (such as test items), filtering, grouping and other processing are performed on them, and the target group is screened out according to the distribution type of the test data in each group to calculate the initial test limit; when the robustness of the test data of the new batch of products meets the set conditions, the current test data is inserted into the previous training population to form a new training population, so as to update the new dynamic test limit. That is, the MEAT detection method monitors the evolution of the population according to the robustness of the data (fitness / robustness), realizes adaptive dynamic adjustment of the test limit, and can effectively detect chip test data with abnormal data in real time, thereby improving the test quality of the chip.

[0257] Example 5

[0258] Fig.13 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present invention. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method for detecting product test data in any one of Embodiments 1 or 2 when executing the program. Fig.13 The electronic device 30 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0259] like Fig.13 As shown, the electronic device 30 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 30 may include, but are not limited to: at least one processor 31, at least one memory 32, and a bus 33 connecting different system components (including the memory 32 and the processor 31).

[0260] The bus 33 includes a data bus, an address bus, and a control bus.

[0261] The memory 32 may include a volatile memory, such as a random access memory (RAM) 321 and / or a cache memory 322 , and may further include a read-only memory (ROM) 323 .

[0262] The memory 32 may also include a program / utility 325 having a set (at least one) of program modules 324, such program modules 324 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0263] The processor 31 executes various functional applications and data processing by running the computer program stored in the memory 32, such as the method for detecting product test data in any one of Embodiments 1 or 2 of the present invention.

[0264] The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 35. Furthermore, the model generating device 30 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 36. Fig.13 As shown, the network adapter 36 communicates with other modules of the model-generated device 30 via the bus 33. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the model-generated device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0265] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0266] Example 6

[0267] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the method for detecting product test data in any one of Embodiments 1 or 2 are implemented.

[0268] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0269] In a possible implementation, the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to enable the terminal device to execute the steps in the method for detecting product test data in any one of embodiments 1 or 2.

[0270] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0271] Although the specific embodiments of the present invention are described above, it should be understood by those skilled in the art that these are only examples, and the protection scope of the present invention is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but these changes and modifications all fall within the protection scope of the present invention.

Claims

1. A method for detecting product test data, characterized in that: The detection method comprises: Obtain historical test data corresponding to multiple historical batches of products; Screening the historical test data to obtain intermediate test data; The intermediate test data is grouped according to different preset test parameters to obtain a plurality of first groups; wherein each of the preset test parameters corresponds to one first group; Acquire a first distribution type corresponding to each of the first groups according to the intermediate test data corresponding to the first groups; determining whether the first distribution type is a preset distribution type, and if so, taking the first group corresponding to the first distribution type as a target group; Acquire a target test limit value according to the intermediate test data corresponding to the target group; The target test limit is used to test the test data of a new batch of products.

2. The method for detecting product test data according to claim 1, characterized in that: The step of obtaining a target test limit value according to the intermediate test data corresponding to the target group comprises: Calculating statistical parameters corresponding to the target group according to the intermediate test data corresponding to the target group; wherein the statistical parameters include a mean value and a mean square error; The test upper limit value and the test lower limit value are calculated according to the statistical parameters and the preset constraint conditions, and the test upper limit value and the test lower limit value are used as the target test limit value.

3. The method for detecting product test data according to claim 1, characterized in that: After the step of obtaining the target test limit according to the intermediate test data corresponding to the target group, the following step further includes: Get the current test data corresponding to the current test group in the current batch of products; Acquire multiple groups of target test data corresponding to different preset test parameters in the current test data; Determine whether the target test data is within the corresponding target test limit, if so, determine that the target test data is normal test data; if not, determine that the target test data is abnormal test data; When a set number of the target test data are all normal test data, the current test data of the current test group passes the test; otherwise, it is determined that the current test data of the current test group fails the test.

4. The method for detecting product test data according to claim 3, characterized in that: When it is determined that the current test data corresponding to the current test group in the current batch of products passes the test and the preset distribution type is a normal distribution, the detection method further includes: Using the intermediate test data corresponding to the target group as the current training population; Calculate and obtain initial population parameters corresponding to the current training population; Determine whether the current test data falls within the central area of ​​the normal distribution corresponding to the current training population according to the initial population parameters, and if so, determine whether the robustness of the current test data meets the preset requirements, and insert the current test data into the initial training population to form a target training population; Updating the target test limit according to the test data corresponding to the target training population; For the test data corresponding to the next test group in the current batch of products, the target population parameters corresponding to the target training population are calculated; Determine whether the current test data falls within the central area of ​​the normal distribution corresponding to the target training population according to the target population parameters, and if so, determine whether the robustness of the current test data meets the preset requirements, and insert the current test data into the target training population to form a new target training population; The target test limit is updated according to the new test data corresponding to the target training population.

5. The method for detecting product test data according to claim 4, characterized in that: The detection method further comprises: Determine whether the test data in the target training population meets a preset condition, and if so, generate first test data to update the target training population; Among them, the difference between the statistical parameters of the target training population before updating and the target training population after updating is less than a first set threshold, and the test data corresponding to the updated target training population does not meet the preset condition; the statistical parameters include the mean value and the mean square error.

6. The method for detecting product test data according to claim 5, characterized in that: The step of determining whether the test data in the target training population meets a preset condition, and if so, generating first test data to update the target training population comprises: Obtaining the quartiles corresponding to the test data in the target training population; It is determined whether the first quartile of the quartiles is equal to the third quartile. If so, the first test data is randomly generated to update the target training population.

7. The method for detecting product test data according to claim 6, characterized in that: The step of randomly generating the first test data to update the target training population includes: A group of second test data is randomly generated by using at least one of an inverse function sampling method, a Box-Muller transformation method, and a central limit theorem, and the difference between the statistical parameters corresponding to each group of the second test data and the statistical parameters of the target training population before updating is calculated, and the second test data corresponding to the minimum absolute value of the difference is selected as the first test data to update the target training population.

8. The method for detecting product test data according to claim 1, characterized in that: The step of screening the historical test data to obtain intermediate test data comprises: Filtering out third test data corresponding to all the preset test parameters in the historical test data; The test data exceeding a preset test limit is removed from the third test data to obtain the intermediate test data.

9. The method for detecting product test data according to claim 1, characterized in that: The step of grouping the intermediate test data according to different preset test parameters to obtain a plurality of first groups comprises: Grouping the intermediate test data according to different preset test parameters to obtain multiple intermediate groups; It is determined whether the size of the intermediate group is greater than or equal to a second set threshold; if so, the intermediate group is used as the first group.

10. The method for detecting product test data according to claim 8, characterized in that: Before the step of obtaining historical test data corresponding to multiple historical batches of products, the following step is also included: Pre-establish static data space; After the step of acquiring the historical test data corresponding to the plurality of historical batches of products and before the step of screening the historical test data to acquire the intermediate test data, the following steps are included: Acquire the historical test data in a set format, decode the historical test data, and store the decoded historical test data in the static data space; The step of filtering out the third test data corresponding to all the preset test parameters in the historical test data includes: Based on all the preset test parameters, the third test data is output from the static data space through different application program interfaces.

11. A system for detecting product test data, characterized in that: The detection system comprises: A historical data acquisition module is used to acquire historical test data corresponding to multiple historical batches of products; An intermediate data acquisition module, used for screening the historical test data to obtain intermediate test data; A group acquisition module, used for performing group processing on the intermediate test data according to different preset test parameters to acquire a plurality of first groups; wherein each of the preset test parameters corresponds to one first group; a distribution type acquisition module, configured to acquire a first distribution type corresponding to each of the first groups according to the intermediate test data corresponding to the first groups; A first judging module, configured to judge whether the first distribution type is a preset distribution type, and if so, taking the first group corresponding to the first distribution type as a target group; A test limit acquisition module, used to acquire a target test limit according to the intermediate test data corresponding to the target group; The target test limit is used to test the test data of a new batch of products.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for detecting product test data according to any one of claims 1 to 10 is implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for detecting product test data according to any one of claims 1 to 10 are implemented.

Images