Standard substance detection method and device, electronic equipment and readable storage medium

Abstract

The invention provides a standard substance detection method and device, electronic equipment and a readable storage medium, and belongs to the technical field of detection.The method comprises the steps that multiple basic features of a target detection sample are determined; compensating each basic feature based on the target influence factors to obtain a plurality of target features; and detecting the standard substance based on the plurality of target characteristics to obtain a detection result of the standard substance. According to the standard substance detection method and device, the electronic equipment and the readable storage medium provided by the invention, the detection precision of the standard substance can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the field of detection technology, and more specifically, relates to a standard substance detection method and device, electronic equipment, and a readable storage medium. Background Art

[0002] Nitrate has always been an important testing item in the food safety supervision of infant foods, such as milk powder and infant food supplements. The development of reference materials that meet the traceability requirements has very important social and economic benefits.

[0003] There is an urgent need for a method to accurately detect standard substances. Summary of the invention

[0004] The purpose of the present disclosure is to provide a method and device for detecting a standard substance, an electronic device, and a readable storage medium to improve the detection accuracy of the standard substance.

[0005] A first aspect of the embodiments of the present disclosure provides a method for detecting a standard substance, comprising: Determine multiple basic features of target detection samples; Each basic feature is compensated based on the target influencing factors to obtain multiple target features; The standard substance is detected based on the multiple target features to obtain the detection result of the standard substance.

[0006] A second aspect of the embodiments of the present disclosure provides a standard substance detection device, comprising: A basic feature determination module, used to determine multiple basic features of target detection samples; A target feature determination module is used to compensate each basic feature based on the target influencing factors to obtain multiple target features; The detection module is used to detect the standard substance based on the multiple target features to obtain the detection result of the standard substance.

[0007] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned standard substance detection method when executing the computer program.

[0008] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned standard substance detection method are implemented.

[0009] The beneficial effects of the standard substance detection method and device, electronic device, and readable storage medium provided by the embodiments of the present disclosure are: First, by determining multiple basic characteristics of the target detection sample, the present disclosure can systematically understand the relevant characteristic information of the target detection sample; secondly, the present disclosure compensates for each basic characteristic based on the target influencing factor, which can effectively reduce the interference of the target influencing factor, reduce the negative impact on the detection result, and can more accurately reflect the true condition of the standard material; finally, detection based on the compensated multiple target characteristics can significantly improve the accuracy and reliability of the detection result, and enhance the credibility of the detection result. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of a process for detecting a standard substance provided in one embodiment of the present disclosure; Figure 2 A structural block diagram of a standard substance detection device provided in one embodiment of the present disclosure; Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0013] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0014] Please refer to Figure 1 , Figure 1 A schematic diagram of a process for detecting a standard substance provided in an embodiment of the present disclosure, the method comprising: S101: Determine multiple basic features of target detection samples.

[0015] In this embodiment, the target detection sample is an object that needs to be tested for a standard substance. For example, when testing a nitrate standard substance in milk powder, a batch or a brand of milk powder is the target detection sample.

[0016] Basic characteristics are some attributes or parameters that can reflect the properties, state or composition of the target test sample itself. Multiple basic characteristics can describe the target test sample from different dimensions, and have a certain correlation with the presence, content, activity, etc. of the standard substance in the target test sample, and can directly or indirectly affect the test results of the standard substance.

[0017] In this embodiment, multiple basic features of the target detection sample are determined, including: Determine a plurality of first features of the target detection sample based on the first method; Determine a plurality of second features of the target detection sample based on a second method; Determine a plurality of third features of the target detection sample based on a third method; A plurality of first features, a plurality of second features, and a plurality of third features are combined to obtain a plurality of basic features; Among them, the multiple first features are chemical composition features, the multiple second features are physical property features, and the multiple third features are spectral features.

[0018] The first method is to obtain chemical composition data according to the chemical analysis method for analysis, and multiple first features can be obtained. The multiple first features are chemical composition features, and the chemical composition features are the content or proportion information of various chemical components in the target detection sample. Taking milk powder as an example, its chemical composition features include protein content, fat content, carbohydrate content and mineral content (such as calcium, iron, zinc).

[0019] The second method is to analyze the physical property data obtained by the physical measurement method to obtain multiple second features. The multiple second features are physical property features, which are characteristic data of various physical aspects in the target detection sample. For example, the physical property features of milk powder may include solubility, density and particle size.

[0020] The third method is to analyze the spectral data obtained by the spectrometer to obtain multiple third features. The multiple third features are spectral features, which are spectral feature data obtained by spectral analysis of the target detection sample. Different target detection substances will absorb, emit or scatter light of a specific wavelength under the irradiation of light of different wavelengths, forming a unique spectrum, and the absorption peak and intensity change can be obtained from the spectrum.

[0021] This embodiment obtains multiple basic characteristics by combining chemical composition characteristics, physical property characteristics and spectral characteristics.

[0022] In the initial stage of standard material testing, it is necessary to analyze the target test sample, extract and determine multiple basic features that can characterize the target test sample. After determining multiple basic features, we can further consider what factors will affect each basic feature, and correct or compensate for the basic features according to the existing influencing factors.

[0023] S102: Compensating each basic feature based on the target influencing factor to obtain multiple target features.

[0024] In this embodiment, the target feature is a feature that can better reflect the true state or property of the standard substance after analyzing and processing the target influencing factors and compensating or correcting each basic feature. After comprehensively considering various interference factors, each basic feature is compensated, so that a more reliable or accurate test result can be obtained when the standard substance is tested in the future.

[0025] After determining multiple basic features of the target detection sample, it is necessary to analyze the target influencing factors that can affect the accuracy and effectiveness of the above basic features. Then, for each basic feature, consider the influencing factors related to each basic feature, and use the corresponding mathematical model or compensation formula to perform compensation operations. Through the above compensation process, this embodiment can reduce the impact of the target influencing factors on the basic features, thereby obtaining multiple target features after compensation, and ultimately improve the credibility and accuracy of the detection results.

[0026] In this embodiment, each basic feature is compensated based on the target influencing factor to obtain multiple target features, including: Performing a first compensation on at least one basic feature based on a first factor to obtain at least one first target feature; Performing a second compensation on the at least one basic feature based on a second factor to obtain at least one second target feature; A third compensation is performed on the at least one basic feature based on a third factor to obtain at least one third target feature.

[0027] The first factor, the second factor and the third factor are external factors that affect the accuracy of the basic characteristics of the target detection sample. The first factor can be the ambient temperature, the second factor can be the ambient humidity, and the third factor can be the instrument error. Among them, the ambient temperature and ambient humidity represent the environmental conditions in the detection process, and the instrument error reflects the measurement deviation of the instrument equipment used for the target detection sample due to manufacturing accuracy, aging and other reasons.

[0028] Taking into account that the ambient temperature will affect the basic characteristics of the target detection sample, a first compensation method is used to correct or adjust the deviation caused by changes in ambient temperature for one or more basic characteristics. For example, if the target detection sample is milk powder, its solubility will be affected by the ambient temperature. Generally speaking, the solubility increases with increasing temperature and decreases with decreasing temperature. In this embodiment, a relationship model between solubility and ambient temperature can be established, and a compensation calculation is performed on the measured solubility value according to the actual temperature of the current detection environment, thereby obtaining a solubility value corrected by the temperature factor, i.e., the first target feature. The first target feature can more accurately reflect the actual situation of the solubility of milk powder in a standard temperature environment, and avoid errors caused by ambient temperature fluctuations.

[0029] Taking into account that the ambient humidity will affect the basic characteristics of the target detection sample, a second compensation method is used to compensate for one or more basic characteristics. Taking milk powder as an example, the moisture content in its chemical composition characteristics will be directly affected by the ambient humidity, and the ambient humidity can also affect other components in the milk powder. If it is known that the moisture content of milk powder is related to the ambient humidity, for example, the moisture content of milk powder increases by a certain amount when the ambient humidity increases by a certain value. During the test, the measured moisture content is corrected using the corresponding compensation algorithm according to the actual ambient humidity, and the second target feature after compensation for the ambient humidity factor is obtained - data that is more in line with the actual moisture content of the milk powder.

[0030] Considering the existence of instrument errors, it is necessary to compensate for the relevant basic features. For example, when using a spectrophotometer to detect the spectral characteristics of certain components in milk powder, the instrument itself may have errors such as inaccurate wavelength and deviation in light intensity measurement. This embodiment regularly calibrates the instrument with standard spectral materials to determine the error values ​​of the instrument in terms of wavelength, light intensity, etc., and establishes a corresponding compensation formula to compensate for the detected spectral characteristics to obtain the corrected third target characteristics, so that the spectral characteristic data can more truly reflect the actual spectral characteristics of the relevant components in milk powder, and improve the accuracy of subsequent detection based on spectral analysis.

[0031] S103: Detecting the standard substance based on multiple target features to obtain detection results of the standard substance.

[0032] In this embodiment, the detection result of the standard substance can be uniform and stable, and the corresponding result can be obtained through the change trend of multiple target characteristics.

[0033] In this embodiment, multiple target features can be used as inputs of the trained model to obtain detection results of standard substances corresponding to the multiple target features.

[0034] In this embodiment, the standard substance is detected based on multiple target features to obtain the detection results of the standard substance, including: Obtain historical test samples; Determine multiple historical basic characteristics of historical detection samples; Compensate multiple historical basic features based on target influencing factors to obtain multiple historical target features; using the plurality of historical target features as input to the second model; Taking historical test results of reference materials corresponding to the plurality of historical target features as outputs of the second model; Train the second model to obtain a trained model; Using multiple target features as input to the trained model, thereby obtaining the test results of the standard substances corresponding to the multiple target features; Among them, the second model can be a machine learning model.

[0035] Training is performed on multiple historical target features corresponding to known historical test samples and historical test results of standard substances corresponding to multiple historical target features, so that the machine learning model can learn the relationship between the two, so that the trained model can obtain the corresponding standard substance test results for new target test samples.

[0036] From the above, it can be concluded that, firstly, the present disclosure can systematically understand the relevant characteristic information of the target detection sample by determining multiple basic characteristics of the target detection sample; secondly, the present disclosure compensates for each basic characteristic based on the target influencing factor, which can effectively reduce the interference of the target influencing factor, reduce the negative impact on the detection result, and can more accurately reflect the true condition of the standard material; finally, detection based on the compensated multiple target characteristics can significantly improve the accuracy and reliability of the detection result, and enhance the credibility of the detection result.

[0037] In one embodiment of the present disclosure, multiple basic features of the target detection sample are determined, including: Obtain target detection samples; The target detection samples are processed based on the extraction method to determine multiple basic features of the target detection samples.

[0038] In this embodiment, obtaining a target detection sample includes: Randomly or intermittently select N untested samples from multiple untested samples; Take N undetected samples as target detection samples.

[0039] Untested samples are raw materials or collections of items that have not yet been tested by the standard substance testing process. Untested samples have the potential to be tested, and their properties and characteristics are mostly unknown or not confirmed in detail before testing, such as a batch of newly produced milk powder products that have not yet been tested for quality.

[0040] The target test samples are specific sample subsets that have not been selected from a large number of untested samples and are prepared for subsequent standard substance testing and related characteristic analysis.

[0041] Random sampling means that in the population of all untested samples, each sample has the same possibility of being selected as the target test sample. It is not restricted by any artificially set order or rules, and the sample to be drawn is determined entirely based on random probability.

[0042] Interval sampling is to select samples from the untested sample sequence at a certain fixed interval. For example, if there are 100 untested samples, one sample is selected every 5. This can ensure that the distribution of the extracted samples in the population has a certain regularity and representativeness to a certain extent, and avoid concentrating in a certain local area or a specific type of sample.

[0043] When random sampling is used, N samples are selected unbiasedly from the untested samples through a random number generator or a similar random selection mechanism; while interval sampling first determines a sampling interval value, and then selects N samples from the population in sequence according to this interval.

[0044] In this embodiment, the extraction method may be certain components separated from the target detection sample, or may be a technical means or operation process for obtaining characteristic information related to the sample, wherein the extraction method may be a chemical analysis method, a physical measurement method, or a spectrometer detection method.

[0045] After obtaining the target detection sample, the target detection sample is analyzed by using an extraction method, and the various components in the target detection sample can be separated, converted, or made to produce detectable data, etc., and then multiple basic characteristics that can reflect the essential characteristics of the target detection sample can be determined. For example, the protein, fat, carbohydrate and other components in milk powder are extracted separately by chemical extraction methods, and then their respective contents are determined by corresponding quantitative analysis methods. These content values ​​and component types constitute some basic characteristics of the milk powder sample; or the target detection sample is scanned by a spectral extraction method to obtain its absorption spectrum, emission spectrum or fluorescence spectrum at different wavelengths. These spectral characteristics are also important components of the basic characteristics of the sample.

[0046] It can be concluded from the above that this embodiment can clarify the detection object, making the detection more targeted; then, determining multiple basic features of the target detection sample can provide a basis for subsequent processing and detection.

[0047] In one embodiment of the present disclosure, the target influencing factors include temperature, humidity, and instrument error; The standard substance detection method also includes: determining a first compensation formula based on temperature and humidity; Determining a second compensation formula based on temperature, humidity and instrument error; The accuracy of the first compensation formula is less than the accuracy of the second compensation formula.

[0048] In this embodiment, the first compensation formula is a mathematical expression or calculation model constructed for the influence of two environmental factors, temperature and humidity. Its function is to correct the deviation of the basic characteristics of the target detection sample caused by changes in temperature and humidity to obtain target characteristics that are closer to the true value.

[0049] The second compensation formula is a data expression or calculation model that comprehensively considers the three factors of temperature, humidity and instrument error, and is used to perform more accurate compensation correction on the basic characteristics of the target detection sample. Since this embodiment includes more influencing factors and quantifies the instrument error, the accuracy of the second compensation formula is higher than the first compensation formula that only considers temperature and humidity.

[0050] The first compensation formula is:

[0051] in, represents the target feature, Represents the basic characteristics, Indicates the change in value between the actual temperature and the standard temperature. Indicates the change in actual humidity and standard humidity. All are fitting coefficients.

[0052] When the ambient temperature and humidity in the actual environment deviate from the standard temperature and humidity, and The temperature change and humidity change are substituted into the first compensation formula, and combined with the fitting coefficient, the deviation correction amount caused by the temperature change and humidity change can be calculated.

[0053] Taking into account the direct impact of temperature changes on target characteristics, The direct effect of humidity changes on target characteristics is considered; Taking into account the quadratic effect of temperature change, The quadratic effect of humidity change is taken into account. At this time, the impact of temperature change and humidity change on target features is not only a linear relationship, but also a nonlinear impact; The influence of the interaction between temperature change and humidity change on the target characteristics is considered. At this time, when temperature change and humidity change exist at the same time, the influence of the interaction needs to be considered.

[0054] The coefficients can be obtained by fitting through regression analysis or least squares method.

[0055] The second compensation formula is:

[0056] in, represents the target feature, Represents the basic characteristics, Indicates the change in value between the actual temperature and the standard temperature. Indicates the change in actual humidity and standard humidity. represents the instrument error, All are fitting coefficients.

[0057] The coefficients can be obtained by fitting through regression analysis or least squares method.

[0058] Instrument error refers to the deviation between the measured value and the true value caused by the imperfection and inaccuracy of the measuring instrument itself. In the measurement process of the target detection sample, the instrument error will affect the basic characteristic value obtained by the measurement, and then affect the accuracy of the final target characteristic.

[0059] The method to determine the instrument error is to perform repeated measurements on the same stable measurement object and then analyze the degree of dispersion of the measurement results. According to statistical principles, the standard deviation of the measurement results can reflect the instrument error to a certain extent.

[0060] The second compensation formula It represents the influence of temperature change on the target characteristics, taking into account the nonlinear effect of temperature change; Represents the impact of humidity change on target features, taking into account the nonlinear effect of humidity change; The influence of the interaction between temperature change and humidity change on the target characteristics is considered. That is, when temperature and humidity change exist at the same time, the comprehensive impact on the target characteristics is not simply the temperature impact plus the humidity impact, but there is also an interactive impact.

[0061] represents the instrument error, The influence of instrument error on target characteristics is taken into account. At this time, not only the first-order term of instrument error is considered , and also considers the quadratic effect of instrument error , indicating that the influence of instrument error on target characteristics can be a simple linear relationship or a nonlinear influence.

[0062] The second compensation formula takes into account the instrument error, because in actual measurement, the instrument error cannot be ignored and will have a certain impact on the measurement results. Therefore, the second compensation formula considers more comprehensive target influencing factors and has higher compensation accuracy than the first compensation formula.

[0063] It can be concluded from the above that this embodiment can effectively improve the detection accuracy by considering the target influencing factors such as temperature, humidity and instrument error. The first compensation formula preliminarily corrects the deviation caused by temperature and humidity, making the detection result closer to the true value. The second compensation formula has higher accuracy because it covers the instrument error, which can greatly reduce the adverse effects of environmental and instrument factors on the results and reduce error accumulation.

[0064] In one embodiment of the present disclosure, each basic feature is compensated based on the target influencing factor to obtain multiple target features, including: Compensating each basic feature based on a first compensation formula to obtain a plurality of first target features, and using the plurality of first target features as a plurality of target features; Compensating each basic feature based on a second compensation formula to obtain a plurality of second target features, and using the plurality of second target features as a plurality of target features; The authenticity of the plurality of first target features is less than the authenticity of the plurality of second target features.

[0065] In this embodiment, the plurality of first target features are feature data sets obtained after compensating each basic feature using the first compensation formula.

[0066] The plurality of second target features are feature data sets obtained by compensating each basic feature based on the second compensation formula. Since the second compensation formula not only takes into account environmental factors but also instrument errors, the second target features have higher accuracy and reliability in reflecting the true characteristics of the target detection sample.

[0067] The authenticity is the degree of closeness between the target feature and the feature of the target detection sample under standard conditions. The higher the authenticity, the more accurately the target feature can reflect the true situation of the sample.

[0068] When only the effects of temperature and humidity on basic characteristics are considered, the first compensation formula is used to calculate and correct each basic characteristic (such as the content of various components in the chemical composition characteristics, related parameters in the physical property characteristics, etc.), thereby obtaining a series of first target characteristics after preliminary compensation.

[0069] Taking into account the influence of temperature, humidity and instrument errors, a more accurate second compensation formula is used for each basic feature, and the resulting multiple second target features can more accurately reflect the true characteristics of the target detection sample because it reduces more potential interference factors.

[0070] It can be concluded from the above that this embodiment can reduce the interference of temperature and humidity on detection to a certain extent by preliminarily adjusting the basic characteristics through the first compensation formula, quickly obtain the first target characteristics for reference, and provide data support for preliminary detection and analysis. The second compensation formula not only considers the environmental factors of temperature and humidity, but also considers the instrument error, further improves the compensation accuracy, and obtains the second target characteristics with higher authenticity.

[0071] In one embodiment of the present disclosure, a standard substance is detected based on multiple target features to obtain a detection result of the standard substance, including: Multiple target features are input into a target detection model for detection to determine the detection results of the standard substance; wherein the target detection model is a detection model for determining the standard substance based on multiple simulation features and the detection results corresponding to the multiple simulation features.

[0072] In this embodiment, the target detection model is a model built based on machine learning or deep learning algorithms. By learning and training a large amount of simulated feature data and its corresponding known detection results, the intrinsic correlation and prediction rules between the features and the detection results are established, so that in actual detection, the detection results of standard substances can be predicted based on the input target features.

[0073] Simulated features are feature data sets similar to actual target features that are artificially generated or collected for the purpose of training the model when building a target detection model. The simulated features include various possible situations and changes, and all correspond to known and accurate detection results, which are used to allow the model to learn the mapping relationship between different features and detection results.

[0074] After obtaining multiple compensated target features, the multiple target features are used as input to the target detection model. The target detection model analyzes, processes and calculates the input target features based on the relationship between the features and the detection results learned during the training process, and finally outputs the prediction of the detection results of the standard substance.

[0075] For example, if the target features include the compensated material composition content, physical property parameters, etc., the target detection model will comprehensively judge whether the standard substance meets the specific quality standards and whether its purity meets the requirements based on the above features, and give corresponding test results, such as qualified or unqualified, specific component content values, etc.

[0076] In this embodiment, by inputting simulated feature data into the selected machine learning or deep learning algorithm framework, the model continuously adjusts its own parameters and structure to minimize the error between the predicted results and the known detection results. After multiple rounds of training and optimization, the model gradually masters the mapping rules from features to detection results, thus having the ability to predict the detection results of actual target features.

[0077] It can be concluded from the above that this embodiment uses the target detection model to efficiently process multiple target features, avoiding the tedious manual calculation and analysis of traditional detection methods. The target detection model is trained based on a large number of simulation features and corresponding results, has strong generalization ability, can adapt to standard material detection in different situations, and improve detection accuracy and stability.

[0078] In one embodiment of the present disclosure, the standard substance detection method further includes: taking a plurality of simulation features as input to a first model; Using the detection results corresponding to the plurality of simulated features as outputs of the first model; The first model is trained to obtain a detection model for the standard substance.

[0079] In this embodiment, the first model is an initial model framework that has not yet been fully trained and optimized. It can be a mathematical model structure built based on a machine learning algorithm (such as linear regression, decision tree, etc.) or a deep learning algorithm (such as a neural network). It has the basic functions of accepting input data and generating output predictions, but in the initial state, its prediction accuracy and reliability are still relatively low, and it requires a large amount of data training to continuously adjust and improve its own parameters and internal logic.

[0080] The test result is the test conclusion or numerical information of the known and accurate standard substance corresponding to the simulation feature, which is used to guide the model to learn how to accurately predict the test result from the input simulation feature.

[0081] In this embodiment, a large number of simulated features and their corresponding test results are continuously input into the first model, and the first model uses a specific machine learning or deep learning algorithm to adjust its own parameters according to the error between the predicted output and the actual test result. As the amount of training data increases and the number of training rounds increases, the model continuously optimizes its internal structure and parameter values, gradually reduces the prediction error, and improves the accuracy and reliability of the prediction. Finally, after sufficient training, a detection model for standard substances that can accurately predict the test results of standard substances from actual target features is obtained.

[0082] From the above, it can be concluded that this embodiment uses simulation features as input and corresponding test results as output to train the first model, which enables the first model to fully learn the intrinsic connection between the characteristics of standard substances and the test results, and build an accurate prediction system. Secondly, this embodiment can cope with complex and changeable detection scenarios and enhance the adaptability and robustness of the model. Furthermore, the trained detection model can greatly improve the detection efficiency, realize standardized and automated detection, ensure the detection quality and stability, and promote the efficient development of the detection industry.

[0083] In one embodiment of the present disclosure, the standard substance detection method further includes: Obtaining the nitrate content of the target test sample; Determine the uniformity of nitrate content based on the first formula; The stability of the nitrate content is determined based on the second formula.

[0084] In this embodiment, the nitrate content is the amount of nitrate contained in the target detection sample, and the content is usually determined by chemical analysis methods (such as spectrophotometry, ion chromatography, etc.) or instrumental analysis methods to determine the specific value.

[0085] The first formula is a mathematical expression for evaluating the uniformity of nitrate content in the target test sample. Based on the measured data of nitrate content in different parts or different sub-samples of the target test sample, the first formula is used to quantify the degree of dispersion or consistency of nitrate content, thereby determining whether the nitrate content of the entire sample is uniformly distributed.

[0086] The first formula may be an F-test formula; If the result value of the F test is less than the first preset value, the nitrate content is uniform; If the result value of the F test is greater than or equal to the first preset value, the nitrate content is uneven.

[0087] The second formula is used to determine the stability of nitrate content. This formula takes into account the relationship between time and changes in nitrate content. Through comprehensive analysis and calculation of relevant data, it determines whether the nitrate content remains stable under different conditions, that is, whether it is easy to change and the degree and pattern of the change.

[0088] The second formula may be a standard deviation formula; If the result value of the standard deviation is less than the second preset value, the nitrate content is stable; If the resulting value of the standard deviation is greater than or equal to the second preset value, the nitrate content is unstable.

[0089] This embodiment can consider long-term stability testing. According to the principle of dense first and sparse later, stability testing is carried out at 0, 1, 3, 6, 18, and 36 months under the specified storage conditions (-20±3°C).

[0090] This embodiment can also consider short-term stability testing. According to the principle of dense first and sparse later, the low temperature environment cannot be guaranteed during transportation. The short-term stability of the samples after storage for 0, 1, 3, 7, and 14 days at a temperature of (40±3)°C is examined.

[0091] The trend analysis method is used to calculate the stability test data of the standard substance. If the change of the result fluctuates within the precision range of the measurement method, the characteristic value is considered to be stable within this time interval.

[0092] From the above, it can be concluded that obtaining the nitrate content can intuitively understand the basic situation of nitrate in the target test sample. Based on the first formula to judge the uniformity, it can be determined whether the nitrate distribution in the target test sample is consistent. And using the second formula to judge the stability, the changing trend of nitrate content under different conditions can be clarified.

[0093] Corresponding to the standard substance detection method of the above embodiment, Figure 2 This is a structural block diagram of a standard substance detection device provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The standard material detection device 20 includes: a basic feature determination module 21, a target feature determination module 22 and a detection module 23.

[0094] Wherein, the basic feature determination module 21 is used to determine multiple basic features of the target detection sample; A target feature determination module 22, used to compensate each basic feature based on the target influencing factor to obtain multiple target features; The detection module 23 is used to detect the standard substance based on multiple target features to obtain the detection result of the standard substance.

[0095] In one embodiment of the present disclosure, the basic feature determination module 21 is further configured to: Obtain target detection samples; The target detection samples are processed based on the extraction method to determine multiple basic features of the target detection samples.

[0096] In one embodiment of the present disclosure, the target influencing factors include temperature, humidity, and instrument error; The standard substance detection device 20 further includes: a compensation module; A compensation module, used for determining a first compensation formula based on temperature and humidity; Determining a second compensation formula based on temperature, humidity and instrument error; The accuracy of the first compensation formula is less than the accuracy of the second compensation formula.

[0097] In one embodiment of the present disclosure, the target feature determination module 22 is further configured to: Compensating each basic feature based on a first compensation formula to obtain a plurality of first target features, and using the plurality of first target features as a plurality of target features; Compensating each basic feature based on a second compensation formula to obtain a plurality of second target features, and using the plurality of second target features as a plurality of target features; The authenticity of the plurality of first target features is less than the authenticity of the plurality of second target features.

[0098] In one embodiment of the present disclosure, the detection module 23 is further configured to: Multiple target features are input into a target detection model for detection to determine the detection results of the standard substance; wherein the target detection model is a detection model for determining the standard substance based on multiple simulation features and the detection results corresponding to the multiple simulation features.

[0099] In one embodiment of the present disclosure, the standard substance detection device 20 further includes: a training module: A training module for using the plurality of simulated features as input to a first model; Using the detection results corresponding to the plurality of simulated features as outputs of the first model; The first model is trained to obtain a detection model for the standard substance.

[0100] In one embodiment of the present disclosure, the standard substance detection device 20 further includes: a judgment module; A judgment module, used to obtain the nitrate content of the target detection sample; Determine the uniformity of nitrate content based on the first formula; The stability of the nitrate content is determined based on the second formula.

[0101] See also Figure 3 , Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 23 are shown.

[0102] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0103] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0104] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0105] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the standard substance detection method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0106] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0107] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0108] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0109] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0110] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0111] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0112] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0113] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for detecting a standard substance, characterized in that: include: Determine multiple basic features of target detection samples; Each basic feature is compensated based on the target influencing factors to obtain multiple target features; The standard substance is detected based on the multiple target features to obtain the detection result of the standard substance.

2. The standard substance detection method according to claim 1, characterized in that: The multiple basic features of the target detection sample are determined, including: Obtain target detection samples; The target detection sample is processed based on the extraction method to determine multiple basic features of the target detection sample.

3. The standard substance detection method according to claim 1, characterized in that: The target influencing factors include temperature, humidity and instrument error; The standard substance detection method further comprises: determining a first compensation formula based on the temperature and the humidity; determining a second compensation formula based on the temperature, the humidity, and the instrument error; The accuracy of the first compensation formula is less than the accuracy of the second compensation formula.

4. The standard substance detection method according to claim 3, characterized in that: The target influencing factors are used to compensate each basic feature to obtain multiple target features, including: Compensating each basic feature based on a first compensation formula to obtain a plurality of first target features, and using the plurality of first target features as the plurality of target features; Compensating each basic feature based on a second compensation formula to obtain a plurality of second target features, and using the plurality of second target features as the plurality of target features; The authenticity of the plurality of first target features is less than the authenticity of the plurality of second target features.

5. The standard substance detection method according to claim 4, characterized in that: The detecting the standard substance based on the multiple target features to obtain the detection result of the standard substance includes: The multiple target features are input into a target detection model for detection to determine the detection result of the standard substance; wherein the target detection model is a detection model for determining the standard substance based on multiple simulation features and the detection results corresponding to the multiple simulation features.

6. The standard substance detection method according to claim 5, characterized in that: Also includes: using the plurality of simulation features as input to a first model; Using the detection results corresponding to the multiple simulation features as outputs of the first model; The first model is trained to obtain a detection model for the standard substance.

7. The standard substance detection method according to claim 1, characterized in that: Also includes: Obtaining the nitrate content of the target test sample; Determining the uniformity of the nitrate content based on the first formula; The stability of the nitrate content is determined based on the second formula.

8. A standard substance detection device, characterized in that: include: A basic feature determination module, used to determine multiple basic features of target detection samples; A target feature determination module is used to compensate each basic feature based on the target influencing factors to obtain multiple target features; The detection module is used to detect the standard substance based on the multiple target features to obtain the detection result of the standard substance.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images