A method, system and terminal for detecting hair care product ingredients

Abstract

The application discloses a kind of hair washing and caring product component detection method, system and terminal, it is related to the field of washing and caring product detection.The method comprises the following steps: obtaining the identification component information of the product to be measured, including component name and addition amount;According to the component name and addition amount, generate the expected detection data of each component;Obtain product sample and carry out component analysis to obtain actual detection data;Compare the expected and actual detection data to obtain the detection deviation value of each component;According to the detection deviation value, generate component compliance evaluation result.The application realizes accurate evaluation of product component compliance by quantitative comparison and analysis of expected detection data and actual detection data, significantly improves detection efficiency and accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of washing and caring product detection, and in particular to a hair washing and caring product component detection method, system and terminal. BACKGROUND

[0002] Hair washing and caring products are an important part of daily personal care, and their component composition directly affects the safety, efficacy and compliance of the products.

[0003] At present, hair washing and caring products are complex systems with many types of components and large differences in content, and production processes may introduce deviations, resulting in a significant risk of differences between actual ingredients and labeled components. Traditional detection methods mainly rely on laboratory wet chemical analysis or single instrument detection, which is time-consuming and labor-intensive and relies on human experience, making it difficult to comprehensively and efficiently evaluate the consistency of multiple components. In addition, traditional detection methods lack the ability to use historical data to build prediction models, resulting in insufficient intelligence in the detection process. SUMMARY

[0004] The present application provides a hair washing and caring product component detection method, system and terminal to address the technical problem of the prior art that cannot effectively verify the consistency of the actual component composition of hair washing and caring products with their labeled formula information.

[0005] The technical solution of the present application to solve the above technical problems is as follows:

[0006] In a first aspect, the present application provides a hair washing and caring product component detection method, comprising:

[0007] Obtaining labeled component information of a hair washing and caring product to be tested, the labeled component information including the component name and addition amount of multiple components;

[0008] Generating expected detection data for each component according to the component name and addition amount of the multiple components;

[0009] Obtaining a hair washing and caring product sample of the hair washing and caring product to be tested, and performing component analysis on the hair washing and caring product sample according to the labeled component information to obtain actual detection data for each component;

[0010] Comparing the expected detection data and the actual detection data of each component to obtain a detection deviation value for each component;

[0011] Generating a component compliance evaluation result for the hair washing and caring product to be tested according to the detection deviation value of each component.

[0012] In a second aspect, the present application provides a hair washing and caring product component detection system, comprising:

[0013] An identification component information acquisition module is configured to acquire identification component information of a hair care product to be tested, the identification component information including component names and addition amounts of multiple components;

[0014] An expected detection data generation module is configured to generate expected detection data of each component according to the component names and addition amounts of the multiple components;

[0015] An actual detection data acquisition module is configured to acquire a hair care product sample of the hair care product to be tested, perform component analysis on the hair care product sample according to the identification component information, and obtain actual detection data of each component;

[0016] A detection deviation value calculation module is configured to compare the expected detection data and the actual detection data of each component to obtain a detection deviation value of each component;

[0017] A conformity evaluation result generation module is configured to generate a component conformity evaluation result of the hair care product to be tested according to the detection deviation value of each component.

[0018] In a third aspect, the present application provides an intelligent terminal, comprising: a memory configured to store a computer software program; and a processor configured to read and execute the computer software program, thereby realizing the hair care product component detection method of the first aspect.

[0019] The present application has the following advantages:

[0020] Compared with the prior art, the present application first automatically acquires identification component information and generates expected detection data of each component, thereby improving the efficiency and consistency of detection preparation and reducing human error. Second, the instrument response value is predicted by using a component detection simulator and other intelligent means, thereby realizing rapid and accurate simulation of each component in a complex mixture and enhancing the intelligence and foresight of the detection process. Third, the expected and actual detection data are compared and the component deviation value is calculated, thereby realizing comprehensive and objective quantitative evaluation of the product component conformity. Finally, the expected detection data and the actual detection data are quantitatively compared and analyzed, thereby realizing accurate evaluation of the product component conformity and significantly improving the detection efficiency and accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 A flowchart of the hair care product component detection method provided by the present application is shown in the figure;

[0022] Figure 2 A structural diagram of the hair care product component detection system provided by the present application is shown in the figure.

[0023] Figure 3 A structural diagram of the intelligent terminal provided by the present application is shown in the figure;

[0024] The components represented by the reference signs in the drawings are as follows:

[0025] The identification component information acquisition module 11, the expected detection data generation module 12, the actual detection data acquisition module 13, the detection deviation value calculation module 14, the compliance evaluation result generation module 15, the intelligent terminal 200, the memory 210, the processor 220, the computer software program 211. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0027] In the description of the present application, the terms "first", "second" are used only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0028] In the description of the present application, the term "for example" is used to indicate "as an example, illustration or explanation". Any embodiment described as "for example" in the present application is not necessarily interpreted as more preferred or more advantageous than other embodiments. The following description is given in order to enable any person skilled in the art to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that those skilled in the art can realize the present application without using these specific details. In other examples, well-known structures and processes will not be described in detail to avoid unnecessary details making the description of the present application obscure. Therefore, the present application is not intended to be limited to the shown embodiments, but is consistent with the broadest scope consistent with the principles and characteristics disclosed.

[0029] Embodiment one, as shown in the present application, provides a hair care product component detection method, comprising: Figure 1

[0030] S10: obtaining identification component information of the hair care product to be tested, the identification component information comprising component names and addition amounts of multiple components;

[0031] Specifically, obtaining the identification component information of the hair care product to be tested, the identification component information comprising component names and addition amounts of multiple components, comprising:​

[0032] obtaining a formula file corresponding to the to-be-tested hair care product;

[0033] parsing the formula file to extract the component name and the addition amount in mass percentage of each component in the formula file, to obtain the identified component information.

[0034] Specifically, the to-be-tested hair care product refers to a daily chemical product for cleaning, caring or styling hair, such as shampoo, hair conditioner, hair mask, etc. The identified component information is the component composition description explicitly marked in the product label or technical data, including the standard name of multiple components and the addition amount in mass percentage. Obtaining the identified component information of the to-be-tested hair care product is the initial step of the detection process, which can provide a benchmark basis for subsequent component compliance evaluation.

[0035] Firstly, the formula file corresponding to the to-be-tested hair care product needs to be obtained. The formula file refers to the official document containing all the components and their proportion information of the product, which can be in the form of electronic document or physical carrier, such as digital version of product record data, production record or label identification.

[0036] Secondly, after obtaining the formula file, it needs to be parsed. The specific parsing process is to locate and read the data field related to the component by identifying the data structure and format in the formula file. After parsing, the component name and the addition amount in mass percentage of each component are extracted. The extraction process needs to ensure the integrity and accuracy of the data to avoid omission or misreading.

[0037] Finally, all the extracted component names and addition amount information are integrated to form the identified component information with clear structure and machine readability.

[0038] S20: generating expected detection data of each component according to the component name and the addition amount of the plurality of components;

[0039] According to the component name and the addition amount of the plurality of components, the expected detection data of each component is generated, including:

[0040] determining a first component name and a first addition amount from the plurality of components, and calling a first component detection simulator based on the first component name;

[0041] inputting the first addition amount into the first component detection simulator to generate the expected chromatographic peak area of the first component as the first expected detection data of the first component;

[0042] generating the expected detection data of the remaining components in the same way as generating the first expected detection data of the first component, to obtain the expected detection data of each component.

[0043] First, one component is selected as the first component from the plurality of components in the acquired identification component information, and its name and addition amount are determined. The first component refers to any component selected from a plurality of to-be-tested components for the first round of prediction and modeling, and the selection order can be determined in sequence from high to low according to the addition amount of the component. Further, according to the name of the first component, a pre-trained first component detection simulator is called. The first component detection simulator is a kind of calculation model that can simulate the response behavior of the component in the detection instrument, and can accurately predict the instrument response value of the component under specific analysis conditions according to the input addition amount, and is used to generate the expected detection data of the component under the theoretical condition.

[0044] Specifically, the construction step of the first component detection simulator includes:

[0045] Based on the first component name, historical detection records are retrieved, and a plurality of sets of training data are constructed according to the historical detection records, each set of training data including sample addition amount and sample chromatographic peak area;

[0046] The sample addition amount is taken as input, and the sample chromatographic peak area is taken as a supervised label. Based on the plurality of sets of training data, the first component detection simulator is trained and constructed.

[0047] The construction of the first component detection simulator is a process of training a machine learning model based on historical data, aiming to establish an accurate mapping relationship between the component addition amount and the instrument response value. The specific construction steps are as follows:

[0048] First, based on the name of the first component, the historical detection records related to the component are retrieved in the historical database. The historical database is a structured data warehouse that stores the original data and results of the detection of various types of hair care products in the past. The data comes from long-term accumulation of actual detection experiments and compliance testing. The historical detection records contain different addition amounts of the component used in past experiments and the corresponding chromatographic peak areas actually measured in the chromatograph.

[0049] Further, a plurality of sets of training data are constructed according to the retrieved historical detection records. Each set of training data includes two key fields: sample addition amount and sample chromatographic peak area. The sample addition amount represents the actual feed amount of the component in a certain historical experiment, and the sample chromatographic peak area represents the response value actually measured by the chromatograph under the addition amount.

[0050] Further, the first component detection simulator is constructed and trained. Machine learning refers to a kind of calculation method that can automatically learn the rules from historical data and construct a prediction model. By analyzing the statistical characteristics of a large number of sample data, the mapping relationship between the input variable and the output target is established, so as to realize accurate prediction of unknown data. For example, linear regression, support vector regression or neural network algorithm can be used to construct the first component detection simulator.

[0051] Exemplarily, since the relationship between the ingredient addition amount and the chromatographic instrument response value often presents a complex non-linear relationship, and the neural network has an outstanding advantage in fitting high-dimensional non-linear mapping and automatic feature learning, a neural network model is selected to construct the first ingredient detection simulator.

[0052] Specifically, the first ingredient detection simulator mainly consists of an input layer, a hidden layer and an output layer. The input layer receives ingredient addition amount data expressed in mass percentage and eliminates the dimension effect through standardization processing. The hidden layer adopts a multi-layer full connection structure, and the number of hidden layer neurons is dynamically adjusted according to the data complexity. ReLU activation function is used in each layer to enhance the non-linear expression ability. A Dropout layer is also embedded in the network, with a dropout rate of 0.2 to 0.4, to reduce overfitting and improve the generalization performance of the model. The output layer uses a linear activation function to directly regress the expected chromatographic peak area of the ingredient.

[0053] During the training process, the key hyperparameters include a learning rate of 0.0005, a training round number of 150, and a batch size of 64. The learning rate setting takes into account the training stability and convergence speed, the training round number setting ensures that the model fully learns the non-linear relationship in the samples, and the batch size selection balances the memory occupation and gradient update efficiency. Specifically, a supervised learning method is used to construct a training sample set based on historical detection records, where the sample addition amount is used as the input feature and the sample chromatographic peak area is used as the continuous value label. All samples are randomly divided into training set, validation set and test set in proportion.

[0054] Further, the sample addition amount in the training set is input into the network, and the corresponding chromatographic peak area is used as the supervision signal. Through the backpropagation algorithm, the Adam optimizer is used to iteratively adjust the network weight parameters. The mean square error loss function is used to quantify the difference between the predicted peak area and the actual peak area, and the validation set is used to monitor the training process. When the validation set loss does not decrease continuously for multiple rounds and the prediction accuracy reaches the preset prediction accuracy, such as 95%, the training is terminated, and the final converged first ingredient detection simulator is obtained. The first ingredient detection simulator can accurately capture the complex relationship between the addition amount and the instrument response, providing reliable support for generating high-precision expected detection data.

[0055] Further, the first addition amount is input into the first ingredient detection simulator. The first ingredient detection simulator processes based on the mapping relationship between the addition amount and the instrument response value established internally, and outputs the expected chromatographic peak area of the ingredient under the simulated detection condition, which is the first expected detection data of the first ingredient.

[0056] Further, in the same way as the first component, the corresponding component detection simulator is called for each of the remaining components in turn. The addition amount of each component is input into its dedicated simulator to generate the corresponding expected chromatographic peak area. Finally, the expected data of all components is summarized to form a complete set of expected detection data of each component, providing a theoretical basis for subsequent comparison with actual detection results.

[0057] S30: Obtain the hair care product sample to be tested, analyze the components of the hair care product sample according to the identification component information, and obtain the actual detection data of each component;

[0058] After obtaining the expected detection data of each component, the actual response value of the hair care product sample needs to be obtained through actual detection for comparison and verification. The specific process is as follows.

[0059] First, the sample to be tested needs to be obtained, which should come from the same production batch or representative product unit to ensure the accuracy and repeatability of the detection results. Then, according to the component types listed in the previously obtained identification component information, the appropriate instrument analysis method is selected for qualitative and quantitative detection of the sample. The instrument method used for actual component analysis should be consistent with the historical detection method used to construct the component detection simulator.

[0060] During the detection process, for each identified component, its response value in the actual sample is obtained through instrument analysis. For example, if chromatographic analysis is used, the chromatogram is analyzed to accurately identify the chromatographic peaks corresponding to each component, and the actual peak area is calculated by integration. The actual peak area is the actual detection data of the component.

[0061] Finally, the actual detection data of all identified components is collected to form an actual detection data set that is completely consistent with the actual sample component response, which is used for subsequent deviation calculation and compliance evaluation.

[0062] S40: Compare the expected detection data and the actual detection data of each component to obtain the detection deviation value of each component;

[0063] Specifically, by comparing the expected detection data and the actual detection data of each component, the detection deviation value of each component is obtained, including:

[0064] Obtain the first expected detection data and the first actual detection data of the first component;

[0065] Calculate the difference between the first expected detection data and the first actual detection data to obtain the first detection deviation value of the first component;

[0066] The detection deviation values of the remaining ingredients are calculated in the same way as the first ingredient, and the detection deviation values of the ingredients are obtained.

[0067] First, the first expected detection data and the first actual detection data of the first ingredient are obtained. The first expected detection data represents the instrument response value that should be generated by the ingredient under ideal conditions, that is, the chromatographic peak area predicted by the first ingredient detection simulator. The first actual detection data represents the actual response value measured by the instrument from the sample of the hair care product, that is, the true peak area obtained by integration in the chromatographic analysis.

[0068] The difference between the first expected detection data and the first actual detection data is calculated to obtain the first detection deviation value of the first ingredient. The first detection deviation value = | (first actual detection data - first expected detection data) | / first expected detection data x 100%, which represents the absolute deviation of the actual instrument response value of the ingredient from the theoretical prediction value, and is used to objectively measure the deviation between the theoretical prediction and the actual measurement of the ingredient.

[0069] Further, the expected detection data and the actual detection data of each of the remaining ingredients are processed in the same way as the calculation of the first ingredient deviation value, and the detection deviation values of each of them are calculated. Finally, the detection deviation value set of all ingredients is obtained, which provides a quantitative basis for subsequent conformity evaluation results.

[0070] S50: generating the ingredient conformity evaluation result of the hair care product to be tested according to the detection deviation values of the ingredients.

[0071] Specifically, the ingredient conformity evaluation result of the hair care product to be tested is generated according to the detection deviation values of the ingredients, including:

[0072] obtaining the reference addition amount of each ingredient and the preset deviation threshold value;

[0073] calculating the ratio of the addition amount of each ingredient to the corresponding reference addition amount to obtain the correction factor of each ingredient;

[0074] adjusting the preset deviation threshold value of each ingredient according to the correction factor to obtain the adjusted deviation threshold value of each ingredient;

[0075] comparing the detection deviation value of each ingredient with the corresponding adjusted deviation threshold value to generate the conformity determination result of each ingredient;

[0076] When the detection deviation value of each ingredient is less than or equal to the corresponding adjusted deviation threshold value, the ingredient conformity evaluation result of the hair care product to be tested is generated as qualified.

[0077] When the detection deviation value of any ingredient exceeds the corresponding adjustment deviation threshold range, the ingredient compliance evaluation result of the to-be-tested hair care product is unqualified.

[0078] Firstly, the reference addition amount and the preset deviation threshold of each ingredient are obtained. The reference addition amount refers to the specified addition amount of the ingredient in the standard formula or the relevant requirements; the preset deviation threshold is the maximum allowable deviation range set initially, which is set comprehensively according to the physicochemical properties of the ingredient, the precision of the detection method and the industry supervision requirements. For example, the preset deviation threshold of the main active ingredient is usually set to ±5% of the nominal addition amount, while the non-key ingredients such as excipients or fragrances can be appropriately relaxed to ±10% or higher.

[0079] Secondly, the ratio of the actual addition amount of each ingredient to the corresponding reference addition amount is calculated to obtain the correction factor of each ingredient. Specifically, the correction factor = actual addition amount / reference addition amount. The correction factor is used to reflect the deviation proportion of the actual addition amount relative to the standard value, and is further used for subsequent adjustment of the evaluation standard.

[0080] Further, the adjustment deviation threshold of each ingredient is obtained according to the correction factor of each ingredient. Specifically, the adjustment deviation threshold = preset deviation threshold x correction factor. This adjustment process makes the evaluation standard adapt to the actual needs of ingredients with different addition amount levels. By introducing a dynamic adjustment mechanism proportional to the addition amount, the ability to distinguish the deviation tolerance of different content ingredients is effectively improved, thereby significantly improving the scientificity and rationality of the evaluation result.

[0081] Further, the detection deviation value of each ingredient is compared with the corresponding adjustment deviation threshold. If the detection deviation value of a certain ingredient is less than or equal to its adjustment deviation threshold, it is determined that the ingredient meets the requirements; if the detection deviation value of a certain ingredient exceeds the threshold range, it is determined that the ingredient does not meet the requirements.

[0082] Since the proportions of each ingredient in the hair care product have been strictly scientifically verified and safety evaluated, the deviation of any ingredient exceeding the standard may disrupt the overall balance of the product formula, leading to reduced product efficacy, increased irritation or unpredictable adverse reactions. Therefore, in order to ensure the safety, effectiveness and quality consistency of the product, the content of each ingredient must be strictly controlled. Specifically, when the detection deviation value of all ingredients is less than or equal to the corresponding adjustment deviation threshold, the final ingredient compliance evaluation result of the to-be-tested hair care product is qualified. When the detection deviation value of any ingredient exceeds the corresponding adjustment deviation threshold, the ingredient compliance evaluation result of the product is unqualified.

[0083] Further, when the composition conformity evaluation result of the to-be-tested hair care product is unqualified, a taboo ingredient library is obtained, the taboo ingredient library comprising a plurality of taboo ingredients prohibited to be used in the hair care product;

[0084] According to the plurality of taboo ingredients, taboo ingredient detection is performed on the hair care product sample to obtain a taboo ingredient detection result;

[0085] When the taboo ingredient detection result shows that a taboo ingredient is detected, it is determined that the unqualified reason of the to-be-tested hair care product is that the taboo ingredient is contained;

[0086] When the taboo ingredient detection result shows that no taboo ingredient is detected, it is determined that the unqualified reason of the to-be-tested hair care product is that the component deviation exceeds the standard.

[0087] When the composition conformity evaluation result of the to-be-tested hair care product is unqualified, the specific reason causing the unqualification needs to be further analyzed. Specifically, by introducing a taboo ingredient screening mechanism, deep diagnosis and reason tracing of unqualified products are realized.

[0088] First, a pre-established taboo ingredient library is obtained, the taboo ingredient library comprising a plurality of taboo ingredients prohibited to be used in the hair care product, such as hormones, antibacterial agents or other limited-use substances that are explicitly prohibited in relevant regulations. According to the plurality of taboo ingredients listed in the taboo ingredient library, taboo ingredient targeted detection is performed on the hair care product sample. Specifically, by using analysis methods such as liquid chromatography-mass spectrometry or gas chromatography-mass spectrometry, high-sensitivity analysis techniques are used to obtain the detection result of whether the taboo ingredient exists in the sample.

[0089] If the taboo ingredient detection result shows that a taboo ingredient is detected, it is determined that the unqualified reason of the to-be-tested hair care product is that the taboo ingredient is contained; if the taboo ingredient detection result shows that no taboo ingredient is detected, it is indicated that the unqualification of the to-be-tested hair care product is not caused by prohibited substances, but by the deviation of the component addition amount exceeding the allowed range found in the previous detection, and accordingly it is determined that the unqualified reason is that the component deviation exceeds the standard.

[0090] Through this kind of step-by-step diagnosis mechanism, not only the specific problem type of unqualified products can be determined, but also accurate basis can be provided for subsequent processing, and the pertinence and effectiveness of quality control are improved.

[0091] In summary, the embodiments of the present application have at least the following technical effects:

[0092] Compared with the prior art, the present application firstly greatly improves the processing efficiency and data consistency of the early stage of the detection process by automatically obtaining product identification component information and intelligently generating expected detection data of each component, effectively avoiding errors that may be introduced by manual operation. Secondly, by using a component detection simulator, the instrument response value can be accurately predicted according to the component name and the addition amount, thereby realizing rapid and accurate simulation of complex mixture systems, and significantly enhancing the intelligent level and prediction ability of the detection process. Thirdly, by comparing the expected theoretical data with the actual detection results, the quantitative deviation of each component is automatically calculated, and a comprehensive, objective and quantifiable scientific evaluation of the product component compliance is realized.

[0093] In summary, the present application realizes accurate evaluation of product component compliance through quantitative comparison and analysis of expected detection data and actual detection data, significantly improving detection efficiency and accuracy.

[0094] Embodiment two, as shown in the same inventive concept as the component detection method of the hair care product provided in embodiment one, the present application embodiment also provides a hair care product component detection system, comprising: Figure 2 An identification component information acquisition module 11 is configured to acquire identification component information of a hair care product to be tested, wherein the identification component information comprises component names and addition amounts of a plurality of components.

[0095] An expected detection data generation module 12 is configured to generate expected detection data of each component according to the component names and addition amounts of the plurality of components.

[0096] An actual detection data acquisition module 13 is configured to acquire a hair care product sample of the hair care product to be tested, perform component analysis on the hair care product sample according to the identification component information, and obtain actual detection data of each component.

[0097] A detection deviation value calculation module 14 is configured to compare the expected detection data and the actual detection data of each component to obtain a detection deviation value of each component.

[0098] A compliance evaluation result generation module 15 is configured to generate a component compliance evaluation result of the hair care product to be tested according to the detection deviation value of each component.

[0099] The identification component information acquisition module 11 is specifically configured to:

[0100] Acquire identification component information of a hair care product to be tested, wherein the identification component information comprises component names and addition amounts of a plurality of components, and comprises:

[0101] Acquire a formula file corresponding to the hair care product to be tested.

[0102] ​

[0103] parsing the formula file to extract ingredient names and addition amounts in mass percentage of each ingredient in the formula file to obtain the identified ingredient information.

[0104] The expected detection data generation module 12 is specifically configured to:

[0105] generate expected detection data of each ingredient according to ingredient names and addition amounts of multiple ingredients, including:

[0106] determine a first ingredient name and a first addition amount from the multiple ingredients, and call a first ingredient detection simulator based on the first ingredient name;

[0107] input the first addition amount into the first ingredient detection simulator to generate expected chromatographic peak area of the first ingredient as first expected detection data of the first ingredient;

[0108] generate expected detection data of the remaining ingredients in the same way as generating the first expected detection data of the first ingredient to obtain expected detection data of each ingredient.

[0109] Specifically, the construction step of the first ingredient detection simulator includes:

[0110] retrieve historical detection records based on the first ingredient name, and construct multiple sets of training data according to the historical detection records, each set of training data including sample addition amount and sample chromatographic peak area;

[0111] train and construct the first ingredient detection simulator based on the multiple sets of training data with the sample addition amount as input and the sample chromatographic peak area as supervised label.

[0112] The actual detection data acquisition module 13 is specifically configured to:

[0113] obtain hair care product samples of the hair care product to be tested, perform ingredient analysis on the hair care product samples according to the identified ingredient information, and obtain actual detection data of each ingredient.

[0114] The detection deviation value calculation module 14 is specifically configured to:

[0115] compare expected detection data and actual detection data of each ingredient to obtain detection deviation values of each ingredient, including:

[0116] obtain first expected detection data and first actual detection data of the first ingredient;

[0117] calculate the difference between the first expected detection data and the first actual detection data to obtain the first detection deviation value of the first ingredient;

[0118] The detection deviation values of the remaining components are respectively calculated in a manner that the first detection deviation value of the first component is calculated, to obtain the detection deviation values of the components.

[0119] The conformity evaluation result generation module 15 is specifically configured to:

[0120] The conformity evaluation result of the hair care product to be tested is generated according to the detection deviation values of the components, including:

[0121] The reference addition amount of each component and the preset deviation threshold are obtained.

[0122] The ratio of the addition amount of each component to the corresponding reference addition amount is calculated to obtain the correction factor of each component.

[0123] The preset deviation threshold of each component is adjusted according to the correction factor to obtain the adjusted deviation threshold of each component.

[0124] The detection deviation value of each component is compared with the corresponding adjusted deviation threshold to generate the conformity determination result of each component.

[0125] When the detection deviation value of each component is less than or equal to the corresponding adjusted deviation threshold, the conformity evaluation result of the hair care product to be tested is qualified.

[0126] Specifically, when the detection deviation value of any component exceeds the corresponding adjusted deviation threshold range, the conformity evaluation result of the hair care product to be tested is unqualified.

[0127] In addition, when the conformity evaluation result of the hair care product to be tested is unqualified, a taboo component library is obtained, and the taboo component library contains a plurality of taboo components prohibited to be used in the hair care product.

[0128] The taboo component detection is performed on the hair care product sample according to the plurality of taboo components to obtain a taboo component detection result.

[0129] When the taboo component detection result shows that a taboo component is detected, it is determined that the unqualified reason of the hair care product to be tested is that the taboo component is contained.

[0130] When the taboo component detection result shows that no taboo component is detected, it is determined that the unqualified reason of the hair care product to be tested is that the component deviation exceeds the standard.

[0131] Embodiment three, as Figure 3As shown, the embodiment of the present application further provides an intelligent terminal 200, which comprises a memory 210, a processor 220, and a computer software program 211 stored in the memory 210 and capable of running on the processor 220, and the processor 220 implements the method for detecting the composition of a hair care product provided by the first embodiment when executing the computer software program 211.

[0132] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. Moreover, the above-mentioned description is made for specific embodiments of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0133] The above only describes the preferred embodiments of the present application and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0134] The present application and the drawings are only exemplary descriptions of the present application, and any and all modifications, changes, combinations or equivalents within the scope of the present application are considered to be covered. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the present application and its equivalent technology, the present application is intended to include these modifications and changes.

Claims

1. A method for detecting the ingredients in hair care products, characterized in that, The method includes: Obtain the labeling ingredient information of the hair care product to be tested, wherein the labeling ingredient information includes the ingredient names and amounts of multiple ingredients; Based on the ingredient names and amounts of multiple components, generate the expected detection data for each component, including: Determine the name and amount of a first component from the plurality of components, and retrieve the first component detection simulator based on the name of the first component; The first addition amount is input into the first component detection simulator to generate the expected chromatographic peak area of ​​the first component, which is used as the first expected detection data of the first component. The expected detection data of the remaining components are generated in the same way as the first expected detection data of the first component, thus obtaining the expected detection data of each component. The construction steps of the first component detection simulator include: Based on the name of the first component, historical detection records are retrieved, and multiple sets of training data are constructed according to the historical detection records. Each set of training data includes the amount of sample added and the chromatographic peak area of ​​the sample. Using the amount of sample added as input and the chromatographic peak area of ​​the sample as a supervision label, the first component detection simulator is trained and constructed based on the multiple sets of training data; Obtain a sample of the hair care product to be tested, and perform component analysis on the hair care product sample according to the labeled ingredient information to obtain the actual test data of each component; By comparing the expected detection data and the actual detection data of each component, the detection deviation value of each component is obtained; Based on the detection deviation values ​​of each component, the component conformity evaluation results of the hair care product under test are generated, including: Obtain the baseline addition amount and preset deviation threshold for each component; Calculate the ratio of the amount of each component added to the corresponding baseline amount to obtain the correction factor for each component; The corresponding preset deviation threshold is adjusted according to the correction factor of each component to obtain the adjustment deviation threshold of each component; The detection deviation value of each component is compared with the corresponding adjustment deviation threshold to generate the compliance judgment result of each component; When the detection deviation values ​​of each component are all less than or equal to the corresponding adjustment deviation threshold, the component conformity evaluation result of the hair care product to be tested is qualified.

2. The method according to claim 1, characterized in that, Obtain the labeling ingredient information of the hair care product to be tested. This labeling ingredient information includes the ingredient names and amounts of multiple ingredients, including: Obtain the formula file corresponding to the hair care product to be tested; The formula file is parsed to extract the ingredient names and the amount added as a percentage by mass for each component, thus obtaining the identifying ingredient information.

3. The method according to claim 1, characterized in that, By comparing the expected detection data and the actual detection data for each component, the detection deviation value for each component is obtained, including: Obtain the first expected detection data and the first actual detection data of the first component; Calculate the difference between the first expected detection data and the first actual detection data to obtain the first detection deviation value of the first component; The detection deviation values ​​of the remaining components are calculated in the same way as the first detection deviation value of the first component, thus obtaining the detection deviation value of each component.

4. The method according to claim 1, characterized in that, When the detection deviation value of any component exceeds the corresponding adjustment deviation threshold range, the component conformity evaluation result of the hair care product under test is deemed unqualified.

5. The method according to claim 4, characterized in that, The method further includes: When the conformity evaluation result of the ingredients of the hair care product to be tested is unqualified, a prohibited ingredient library is obtained, which contains multiple prohibited ingredients that are prohibited from being used in hair care products. Based on the aforementioned multiple contraindicated ingredients, the hair care product samples were tested for contraindicated ingredients, and the test results were obtained. When the test results for the prohibited ingredients show that prohibited ingredients are detected, it is determined that the reason for the failure of the hair care product to be tested is that it contains prohibited ingredients. When the test results for the prohibited ingredients show that no prohibited ingredients are detected, the reason for the failure of the hair care product to be tested is determined to be excessive deviation of ingredients.

6. A system for detecting the ingredients of hair care products, characterized in that, For performing the method according to any one of claims 1-5, comprising: The labeling ingredient information acquisition module is used to acquire the labeling ingredient information of the hair care product to be tested. The labeling ingredient information includes the ingredient names and amounts of multiple ingredients. The expected detection data generation module is used to generate expected detection data for each component based on the component name and amount added. The actual test data acquisition module is used to acquire the hair care product sample to be tested, perform component analysis on the hair care product sample according to the identified component information, and obtain the actual test data of each component. The detection deviation value calculation module is used to compare the expected detection data and the actual detection data of each component to obtain the detection deviation value of each component. The conformity evaluation result generation module is used to generate the conformity evaluation results of the components of the hair care product to be tested based on the detection deviation values ​​of each component.

7. A smart terminal, characterized in that, include: Memory, used to store computer software programs; A processor is configured to read and execute the computer software program, thereby implementing the method for detecting the ingredients of a hair care product as described in any one of claims 1-5.

Images