Skin evaluation method, skin evaluation device, and storage medium

Abstract

The application discloses a skin evaluation method, a skin evaluation device and a storage medium. The method comprises the following steps: obtaining test sample data of a target evaluation dimension; determining a target corresponding relationship between a measurement value and a score value according to the test sample data; and determining a skin score value of a target object corresponding to the target evaluation dimension according to the target corresponding relationship and measurement data of the target object. The application aims to improve the accuracy of skin evaluation results.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of skin testing, in particular to a skin evaluation method, a skin evaluation device and a storage medium. BACKGROUND

[0002] Skin management is becoming more and more popular in daily life, and the demand for skin testing is also increasing. At present, spectral imaging technology is generally used to qualitatively and quantitatively analyze the color plate, pores, stability, smoothness and other indicators of the skin, and to feed back evaluation results of different dimensions to the user according to the analysis results.

[0003] At present, when evaluating the skin quality of a user based on data of different dimensions, a plurality of fixed numerical intervals are generally set in advance through theoretical calculation, each numerical interval is set to correspond to a score, and the skin score is determined based on the numerical interval in which the actual detection value of the target dimension is located. However, such a way is easy to make the evaluation result not match the actual situation of the user, resulting in insufficient accuracy of the skin evaluation result of the user. SUMMARY

[0004] The main purpose of the present application is to provide a skin evaluation method, a skin evaluation device and a storage medium, which aims to improve the accuracy of the skin evaluation result.

[0005] To achieve the above-mentioned purpose, the present application provides a skin evaluation method, which comprises the following steps:

[0006] Obtaining test sample data of a target evaluation dimension;

[0007] Determining a target correspondence relationship between a measurement value and a score value according to the test sample data;

[0008] Determining a skin score value of a target object corresponding to the target evaluation dimension according to the target correspondence relationship and measurement data of the target object.

[0009] Optionally, the test sample data comprises a plurality of test sample values, and the step of determining a target correspondence relationship between a measurement value and a score value according to the test sample data comprises:

[0010] Determining a reference measurement value corresponding to a preset score value according to the distribution characteristics of the plurality of test sample values;

[0011] Determining the target correspondence relationship according to the preset score value and the corresponding reference measurement value.

[0012] Optionally, the step of determining a reference measurement value corresponding to a preset score value according to the distribution characteristics of the plurality of test sample values comprises:

[0013] determining a numerical interval in which each of the test samples is located in a plurality of preset numerical intervals, and counting a number of the test samples distributed in each of the preset numerical intervals;

[0014] determining a preset numerical interval with the largest number of the test samples as a target numerical interval;

[0015] determining the reference measurement value according to a numerical value in the target numerical interval.

[0016] Optionally, the step of determining the target corresponding relationship according to the preset score value and the corresponding reference measurement value comprises:

[0017] dividing at least two measurement value intervals according to the reference measurement value;

[0018] determining a score value interval corresponding to each of the measurement value intervals according to a corresponding relationship between the reference measurement value and the preset score value;

[0019] determining the target corresponding relationship between the measurement value interval and the score value interval.

[0020] Optionally, the step of determining the target corresponding relationship according to the preset score value and the corresponding reference measurement value comprises:

[0021] determining a target change trend of the score value with respect to the measurement value according to a target correlation corresponding to the target evaluation dimension, the target correlation comprising a correlation between the size of the measurement value and the quality level of the skin;

[0022] determining the target corresponding relationship according to the target change trend, the preset score value and the reference measurement value.

[0023] Optionally, the number of the target evaluation dimensions is more than one, different target corresponding relationships correspond to different target evaluation dimensions, and the step of determining the skin score value of the target object according to the target corresponding relationship and the measurement data of the target object corresponding to the target evaluation dimension comprises:

[0024] determining a corresponding sub-score according to the target corresponding relationship corresponding to each of the target evaluation dimensions and the measurement data, to obtain more than one sub-score;

[0025] determining the skin score value according to more than one sub-score.

[0026] Optionally, the step of determining the skin score value according to more than one sub-score comprises:

[0027] The plurality of sub-scores are weighted and averaged according to the weight values corresponding to each of the target evaluation dimensions to obtain the skin score value.

[0028] Optionally, the plurality of target evaluation dimensions include a first type of target evaluation dimension and a second type of target evaluation dimension, the weight value corresponding to the first type of target evaluation dimension is smaller than the weight value corresponding to the second type of target evaluation dimension, and the probability of the measurement value corresponding to the first type of target evaluation dimension changing with environmental factors is greater than the probability of the second type of target evaluation dimension changing with environmental factors.

[0029] Optionally, the plurality of target evaluation dimensions include anti-aging degree, water content, melanin, oil content, and sensitivity.

[0030] In addition, in order to achieve the above-mentioned purpose, the present application also provides a skin evaluation device, which comprises a memory, a processor, and a skin evaluation program stored on the memory and executable on the processor, and the skin evaluation program implements the steps of the skin evaluation method according to any one of the above-mentioned embodiments when executed by the processor.

[0031] In addition, in order to achieve the above-mentioned purpose, the present application also provides a storage medium, which stores a skin evaluation program, and the skin evaluation program implements the steps of the skin evaluation method according to any one of the above-mentioned embodiments when executed by a processor.

[0032] The skin evaluation method provided by the present application establishes a target correspondence relationship between the measurement value and the score value based on the test sample data of the target evaluation dimension, determines the skin score value of the target object based on the target correspondence relationship and the measurement data of the target object corresponding to the target evaluation dimension, and analyzes the corresponding relationship between the measurement value and the score value based on the actual test sample data of the target evaluation dimension to score the skin quality of the user. This method is beneficial to the actual situation of the user and can avoid the incompatibility between the score based on the theoretical calculation and the actual state of the user, thereby effectively improving the accuracy of the skin evaluation result. BRIEF DESCRIPTION OF DRAWINGS

[0033] Figure 1 The hardware structure diagram related to the operation of an embodiment of the skin evaluation device of the present application;

[0034] Figure 2 The flowchart of an embodiment of the skin evaluation method of the present application;

[0035] Figure 3 The flowchart of another embodiment of the skin evaluation method of the present application;

[0036] Figure 4A flowchart of another embodiment of the skin evaluation method of the present application is shown in FIG. 6.

[0037] Figure 5 A flowchart of another embodiment of the skin evaluation method of the present application is shown in FIG. 6.

[0038] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0039] It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

[0040] An embodiment of the present application provides a skin evaluation device. In the embodiment, the skin evaluation device is a server of an application installed in an Android system. In other embodiments, the skin evaluation device can also be a detection device with a separate testing function.

[0041] In the embodiment of the present application, referring to Figure 1 , the skin evaluation device includes a processor 1001 (such as a CPU), a memory 1002, a timer 1003, and the like. The components in the control device are connected through a communication bus. The memory 1002 can be a high-speed RAM memory, or a stable memory (non-volatile memory) such as a disk memory. The memory 1002 can also be an optional storage device independent of the aforementioned processor 1001.

[0042] Specifically, the skin evaluation device can be communicatively connected with a skin tester or have a skin tester built-in, and can obtain detection data of different skin indexes tested by the skin tester.

[0043] Those skilled in the art can understand that Figure 1 the device structure shown in the above embodiment does not constitute a limitation on the device, and can include more or fewer components than those shown in the figure, or combine certain components, or different component arrangements.

[0044] As shown in Figure 1 , the memory 1002 as a storage medium can include a skin evaluation program. In the device shown in Figure 1 , the processor 1001 can be used to call the skin evaluation program stored in the memory 1002, and perform the related step operations of the skin evaluation method in the following embodiments.

[0045] An embodiment of the present application also provides a skin evaluation method applied to the skin evaluation device described above.

[0046] Referring to Figure 2 , an embodiment of the skin evaluation method of the present application is provided. In the embodiment, the skin evaluation method includes:

[0047] In step S10, test sample data of a target evaluation dimension is obtained.

[0048] The test sample data specifically includes a plurality of test results of the user collected before the current time in the target evaluation dimension. The plurality of test results can include test results of the target object at multiple times before the current time and / or test results of a plurality of objects other than the target object at the current time.

[0049] The target evaluation dimension is specifically an evaluation item for evaluating the skin quality of the target object. The number of target evaluation dimensions can be one or more. The target evaluation dimension can be a pre-set fixed parameter or a parameter determined according to a user-set parameter.

[0050] The target evaluation dimension can be anti-aging degree, water content, melanin, oil content, or sensitivity, etc. In the embodiment, the number of target evaluation dimensions is more than one, and the more than one target evaluation dimensions include anti-aging degree, water content, melanin, oil content, and sensitivity. Alternatively, the more than one target evaluation dimensions can include part of anti-aging degree, water content, melanin, oil content, and sensitivity.

[0051] In step S20, a target correspondence between the measurement value and the score value is determined according to the test sample data.

[0052] The target correspondence can include a mapping relationship, a calculation formula, etc. Specifically, a calculation formula between the measurement value and the score value can be determined according to the test sample data. For example, a mathematical relationship model with unknown model parameters between the measurement value and the score value can be pre-established. According to the data analysis result of the test sample data, the model parameters can be determined. The quantitative relationship model with known model parameters is taken as the calculation formula between the measurement value and the score value to obtain the target correspondence. For another example, a plurality of preset measurement value intervals and a score interval corresponding to each preset measurement value interval can be pre-set. According to the distribution characteristics (such as the number or average value of test samples in different preset measurement intervals, etc.) of the test sample data in the plurality of preset measurement value intervals, the corresponding score interval is adjusted according to the distribution characteristics. The adjusted plurality of preset measurement value intervals and the corresponding score interval are taken as the target correspondence.

[0053] When the number of target evaluation dimensions is more than one, a corresponding target correspondence can be determined according to the test sample data corresponding to each target evaluation dimension. Each target evaluation dimension corresponds to at least one target correspondence.

[0054] In step S30, a skin score value of the target object is determined according to the target correspondence and the measurement data of the target object corresponding to the target evaluation dimension.

[0055] The measurement data consists of test values ​​for the target evaluation dimensions obtained from testing the skin of the target object.

[0056] The target object is the object that needs to undergo skin testing. In this embodiment, the target object is the user. In other embodiments, the target object can also be any object that is tested by the skin testing device according to preset skin testing rules, such as an animal.

[0057] The score value corresponding to the measurement data in the target correspondence is determined as the reference score value, which can be directly used as the skin score value.

[0058] When there is more than one target evaluation dimension, the score value of the measurement data of each target evaluation dimension in the corresponding target correspondence can be determined as a reference score value to obtain more than one reference score value. The skin score value can be calculated based on the more than one reference score value.

[0059] This invention proposes a skin assessment method. This method establishes a target correspondence between measured values ​​and scoring values ​​based on test sample data of a target evaluation dimension. Based on this target correspondence and the measured data of the target object corresponding to the target evaluation dimension, the skin score of the target object is determined. The target correspondence is obtained by analyzing the correspondence between measured values ​​and scoring values ​​from actual test sample data of the target evaluation dimension to score the user's skin condition. This method is beneficial for accurately reflecting the user's actual situation and avoids scoring based on theoretically calculated correspondences that may not match the user's actual condition, effectively improving the accuracy of skin assessment results.

[0060] Furthermore, based on the above embodiments, another embodiment of the skin assessment method of this application is proposed. In this embodiment, the test sample data includes multiple test sample values, each test sample value being the test result value of a user in the target evaluation dimension corresponding to the current time. (Refer to...) Figure 3 Step S20 includes:

[0061] Step S21: Determine the benchmark measurement value corresponding to the preset score value based on the distribution characteristics of the multiple test sample values;

[0062] Specifically, the collected test sample values ​​can be imported into a hash map. By analyzing the distribution of values ​​and the clusters of data points in the hash map, the distribution characteristics of multiple test sample values ​​(such as sample density, mean, or standard deviation in different data intervals) can be determined. Based on these distribution characteristics, the measurement value corresponding to the preset score value can be determined as the benchmark measurement value.

[0063] The preset score value can be a score value determined according to the skin test needs of the user. Different preset score values correspond to different reference measurement values. Specifically, the target condition of the distribution characteristics of the plurality of test samples can be determined according to the preset score value, and the reference measurement value herein can be determined according to the set of test sample values that meet the target condition.

[0064] The preset score value can be one or more, and the corresponding reference measurement value can be one or more.

[0065] In this embodiment, the preset score value is one, the reference measurement value is one, the reference measurement value is the value in the value interval with the maximum distribution density among the plurality of test samples, and the preset score value is a pre-set passing score (for example, 60 points).

[0066] In other embodiments, the preset score value can be more than one, and the reference measurement value can be more than one. Specifically, different preset score values can correspond to different preset distribution densities, the distribution density of the plurality of test samples in different value intervals is determined, the value in the value interval with the minimum deviation of the distribution density from the preset distribution density corresponding to the preset score value is taken as the reference measurement value corresponding to the preset score value, and based on this, more than one reference measurement value can be obtained.

[0067] Step S22, determining the target correspondence relationship according to the preset score value and the reference measurement value.

[0068] Specifically, the second quantity relationship (for example, difference or ratio) between the corresponding score value and the preset score value is determined according to the first quantity relationship (for example, difference or ratio) between the plurality of target measurement values and the reference measurement value; the target score value corresponding to each target measurement value is determined according to each second quantity relationship and the preset score value; the target correspondence relationship is determined according to the plurality of correspondence relationships between the target measurement values and the target score values. Specifically, at least two measurement value intervals can be divided from the plurality of target measurement values, and the score value interval corresponding to each measurement value interval is determined as the target correspondence relationship according to the plurality of correspondence relationships between the target measurement values and the target score values. The calculation formula between the measurement value and the score value can also be fitted from the plurality of correspondence relationships between the target measurement values and the target score values as the target correspondence relationship.

[0069] In the embodiment, the reference measurement value corresponding to the preset score value is determined according to the distribution characteristics of the plurality of test sample values, and the corresponding relationship between the score value and the measurement value is established based on the preset score value and the reference measurement value corresponding to the preset score value. The preset score value can be used as a skin evaluation requirement representation. The measurement value corresponding to the preset score value that meets the evaluation can be accurately analyzed as the reference measurement value based on the distribution characteristics of the plurality of test sample values. The target corresponding relationship is established based on the corresponding relationship between the reference measurement value and the preset score value, which is beneficial to ensure that the evaluation score of the target evaluation dimension output based on the target corresponding relationship can be accurately matched with the output test requirement, and is beneficial to further improve the user experience of the skin evaluation process.

[0070] Further, in the embodiment, step S21 includes: determining the numerical value interval in which each of the test samples is located in a plurality of preset numerical value intervals, and counting the number of test samples distributed in each of the preset numerical value intervals; determining the preset numerical value interval with the largest number as a target numerical value interval; and determining the reference measurement value according to the numerical value in the target numerical value interval.

[0071] Specifically, the collected plurality of test sample values can be imported into a hash chart. A plurality of preset numerical value intervals can be identified on the hash chart. By analyzing the distribution of values and the point clusters of data points in the hash chart, the preset numerical value interval with the most dense test sample values can be determined as the target numerical value interval. In the embodiment, the median value of the target numerical value interval is used as the reference measurement value. In other embodiments, the critical value of the target numerical value interval or any value in the interval can also be used as the reference measurement value.

[0072] In the embodiment, the reference measurement value is determined in the numerical value interval with the most dense sample distribution, which is beneficial to ensure that the evaluation scores obtained by most users are controlled near the preset score value, and to avoid the actual measurement value of the target object deviating too much from the average situation of most groups, so that the obtained score value cannot accurately reflect the actual skin quality. This is beneficial to improve the accuracy of the determined skin evaluation result and improve the user experience.

[0073] Further, in the embodiment, the preset score value is greater than or equal to 50% of the preset highest score, which is beneficial to ensure that the skin evaluation results of most users are not too low, and further improves the user skin evaluation experience.

[0074] Further, in the embodiment, step S22 includes: dividing at least two measurement value intervals according to the reference measurement value; determining the score value interval corresponding to each of the measurement value intervals according to the corresponding relationship between the reference measurement value and the preset score value; and determining the corresponding relationship between the measurement value interval and the score value interval as the target corresponding relationship.

[0075] Specifically, the reference measurement value can be used to divide at least two measurement value intervals; or the reference measurement value can be a median value of one of the intervals, and a plurality of measurement value intervals can be divided according to a preset interval interval (a preset deviation between the maximum value and the minimum value of the interval), and the interval interval of each measurement value interval is the preset interval interval, and the median value of one of the measurement value intervals is the reference measurement value.

[0076] When the number of reference measurement values is one, a test value set greater than or equal to the reference measurement value can be divided into a first measurement value interval, and a test value set less than the reference measurement value can be divided into a second measurement value interval. Alternatively, one or more reference measurement values can be determined according to the reference measurement value and the preset interval interval, the plurality of reference measurement values can all be greater than the reference measurement value, all be less than the reference measurement value, or part be greater than the reference measurement value and part be less than the reference measurement value, the reference measurement value and all the reference measurement values are sequentially sorted to obtain a target sequence, and a numerical set between any two adjacent measurement values in the target sequence is divided into a measurement value interval to obtain at least two measurement value intervals.

[0077] When the number of reference measurement values is more than one, a plurality of measurement values can be sequentially sorted to obtain a target sequence, and a numerical set between any two adjacent measurement values in the target sequence is divided into a measurement value interval to obtain at least two measurement value intervals.

[0078] Specifically, one or all numerical values of each measurement value interval can be determined as a target measurement value, a first quantity relationship (such as a difference value or a ratio value) between the target measurement value and the reference measurement value, a second quantity relationship (such as a difference value or a ratio value) between a target score value corresponding to each target measurement value and a preset score value according to the first quantity relationship, and a target score value corresponding to each target measurement value according to the second quantity relationship and the preset score value. The corresponding relationship between the target measurement value and the target score value can be determined according to the corresponding relationship.

[0079] All numerical values in the measurement interval can be used as the target measurement value, and the corresponding relationship between the target measurement value and the target score value can be directly used as the target corresponding relationship.

[0080] The target measurement value can also be a critical value of the measurement value interval, and a plurality of score value intervals can be divided based on a plurality of target score values, and the corresponding relationship between the measurement value interval and the score value interval can be determined as the target corresponding relationship based on the corresponding relationship between the target measurement value and the target score value.

[0081] In the embodiment, the measurement value interval is divided and the corresponding score value interval is determined in the above manner, different score value intervals can represent different score levels, so that when subsequent skin testing is performed based on the target correspondence relationship, the score level of the user can be known by determining the measurement value interval in which the measurement data is located, which is beneficial to reducing the influence of detection errors on the deviation of the skin output result and improving the user experience.

[0082] Further, based on any of the above embodiments, another embodiment of the skin evaluation method of the application is proposed. In this embodiment, referring to Figure 4 , the step S22 comprises:

[0083] Step S221, determining a target change trend of the score value with the measurement value according to a target correlation corresponding to the target evaluation dimension, the target correlation including the correlation between the size of the measurement value and the skin quality level represented;

[0084] The target correlation corresponding to different target evaluation dimensions is different, and specifically, it can be set according to the representation definition of the measurement value of different target evaluation dimensions. For example, the size of the water content is positively correlated with the skin quality level, that is, the greater the water content, the better the skin quality, and the smaller the water content, the worse the skin quality; for example, the size of the melanin is negatively correlated with the skin quality level, that is, the greater the value of the melanin, the worse the skin quality, and the smaller the value of the melanin, the better the skin quality, and so on.

[0085] Wherein, the skin quality level is positively correlated with the score value, that is, the better the skin quality, the higher the score value, and the worse the skin quality, the lower the score value.

[0086] Specifically, when the target correlation is positive, the target change trend includes that the score value increases with the increase of the measurement value, and the score value decreases with the decrease of the measurement value; when the target correlation is negative, the target change trend includes that the score value decreases with the increase of the measurement value, and the score value increases with the decrease of the measurement value.

[0087] For example, the correlation between the measurement value corresponding to different target evaluation dimensions and the skin quality level is as shown in the following table:

[0088] Dimension Value range Numerical definition Anti-aging degree 0～100 Weak (0-40) Normal (41-70) Strong (71-100) Moisture content 0～100 Lack (0-50) Moderate (51-80) Full (81-100) Melanin 0～100 Less (0-20) Normal (21-80) Heavy (81-100) Oil 0～5 Lack (0-2) Moderate (3) Excess (4-5) Sensitivity 0～100 Healthy (0-30) Mild (31-75) Severe (76-100)

[0089] Step S222, determining the target correspondence relationship according to the target change trend, the preset score value and the reference measurement value.

[0090] Specifically, the second quantity relationship can be determined according to the target change trend and the first quantity relationship.

[0091] The change trend of the score value with the measurement value in the determined target correspondence relationship matches the target change trend.

[0092] When the target change trend is that the score value increases as the measurement value increases and decreases as the measurement value decreases, the score value corresponding to the measurement value less than the reference measurement value is less than the preset score value, and the score value corresponding to the measurement value greater than the reference measurement value is greater than the preset score value; when the target change trend is that the target change trend includes that the score value decreases as the measurement value increases and increases as the measurement value decreases, the score value corresponding to the measurement value less than the reference measurement value is greater than the preset score value, and the score value corresponding to the measurement value greater than the reference measurement value is less than the preset score value.

[0093] In the embodiment, the above method is used to improve the accuracy of the skin evaluation result of the target object with respect to the target evaluation dimension.

[0094] In order to better understand the establishment process of the target correspondence in the skin evaluation method of the embodiment of the application, a specific example is given as follows:

[0095] Specifically, taking the water content as an example, the water content value is positively correlated with the skin quality, and the water content values of most people in the hash chart are in the interval [20, 70], and the values around 40 are the most concentrated. Therefore, 40 (that is, the reference measurement value) is basically an average value of 60 (that is, the preset score value), and the measurement value interval [0, 40] corresponds to a score value from 0 to 60 by equal proportion, the measurement value interval [41, 80] also belongs to the dense area above the average value, and the corresponding score value is increased from 60 to 80 by equal proportion, and the measurement value interval [81, 100] has a small probability, and the corresponding score value is increased from 80 to 100 by equal proportion. Based on this, the score value range corresponding to different measurement value intervals can be obtained as the target correspondence.

[0096] Further, based on any of the above embodiments, another embodiment of the skin evaluation method of the application is provided. In the embodiment, referring to Figure 5 , the number of the target evaluation dimensions is more than one, different target evaluation dimensions correspond to different target correspondences, and the step of determining the skin score value of the target object according to the target correspondence and the measurement data of the target object corresponding to the target evaluation dimension comprises:

[0097] Step S31, determining a corresponding sub-score according to the target correspondence corresponding to each target evaluation dimension and the measurement data to obtain more than one sub-score;

[0098] Step S32, determining the skin score value according to more than one sub-score.

[0099] Specifically, the skin score value can be calculated by more than one sub-score.

[0100] In the embodiment, by the above manner, the target corresponding relationship of different target evaluation dimensions is determined based on the corresponding actual test sample data, and the skin evaluation is performed on the corresponding measurement data based on the different target corresponding relationship, which is favorable for improving the accuracy of the skin test result of different target evaluation dimensions, and the skin score value of the target object is determined by comprehensively considering more than one evaluation dimension, and the skin score value can accurately reflect the overall skin condition of the target object, thereby further improving the accuracy of the skin test result.

[0101] Further, in the embodiment, the skin score value can be output after step S32, and after the skin score value is output, if a demand instruction of skin condition improvement suggestion is received, a target dimension needing to be improved in more than one target evaluation dimension can be determined according to more than one sub-score, and prompt information corresponding to the target dimension is output, which is favorable for the user to locate and improve the skin problem.

[0102] Further, in the embodiment, step S32 includes: performing weighted average calculation on the more than one sub-score according to the weight value corresponding to each of the target evaluation dimensions, to obtain the skin score value.

[0103] In the embodiment, the weight values corresponding to different target evaluation dimensions are different. The sum of all weight values corresponding to all target evaluation dimensions is 1.

[0104] For example, the sub-scores of the five dimensions of anti-aging degree, water content, melanin, oil content and sensitivity are A, B, C, D and E in sequence, and the corresponding weight values are i, j, k, m and n in sequence, where (i+j+k+m+n=1), and then the skin score value Q can be calculated according to the following formula: Q=A*i+B*j+C*k+D*m+E*n.

[0105] In the embodiment, by the above manner, the skin score value can more accurately reflect the overall skin condition of the user, which is favorable for improving the accuracy of the skin evaluation result.

[0106] Further, in the embodiment, the more than one target evaluation dimension includes a first type of target evaluation dimension and a second type of target evaluation dimension, the weight value corresponding to the first type of target evaluation dimension is less than the weight value corresponding to the second type of target evaluation dimension, and the probability that the measurement value corresponding to the first type of target evaluation dimension changes with the environmental factor is greater than the probability that the second type of target evaluation dimension changes with the environmental factor.

[0107] In the first type of target evaluation dimension, the weight value corresponding to the target evaluation dimension with a greater probability of changing with the environmental factor can be less than the weight value corresponding to the target evaluation dimension with a smaller probability of changing with the environmental factor.

[0108] For example, in the embodiment, the measured data is obtained by RGB and UV spectral imaging technology test, among the five evaluation dimensions of anti-aging degree, water content, melanin, oil content and sensitivity, the anti-aging degree, water content and oil content are easily affected by environmental factors to change the results, which can be classified as the first type of target evaluation dimension, and the melanin and sensitivity are not easily affected by environmental factors to change the results, which can be classified as the second type of target evaluation dimension, and the corresponding weight values of the anti-aging degree, water content, melanin, oil content and sensitivity are 15%, 15%, 30%, 10% and 30% respectively.

[0109] In the embodiment, the weight values of different target evaluation dimensions are not fixed as the same weight, and the weight proportion of some dimensions whose results are easily changed by external environment is adjusted to be low, which is beneficial to avoid the influence of environmental factors on the detection results and further improve the accuracy of the skin test results.

[0110] In other embodiments, the priority of different target evaluation dimensions set by the user can also be obtained, and the weight values corresponding to each target evaluation dimension are determined according to the priority.

[0111] In addition, the embodiment of the present application also provides a storage medium, and the storage medium stores a skin evaluation program. When the skin evaluation program is executed by a processor, the related steps of any one of the above skin evaluation methods are realized.

[0112] It should be noted that in this paper, the term "include", "contain" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, method, article or system. Without more limitations, the element defined by the statement "including a" does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0113] The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0114] Those skilled in the art can clearly understand the above-mentioned embodiment method can be realized by means of software and the necessary general hardware platform, of course, can also be through hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application essentially or say the part of the prior art contribution can be embodied in the form of software products, the computer software product is stored in a storage medium (such as ROM / RAM, magnetic disc, optical disc) as described above, including a number of instructions to make a terminal device (may be a mobile phone, computer, server, skin evaluation device, or network equipment, etc.) executes the method described in various embodiments of the present application.

[0115] The above is only the preferred embodiment of the present application, not therefore limit the patent scope of the present application, any equivalent structure or equivalent flow transformation made by using the content of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method of skin evaluation, characterized by, The skin evaluation method comprises the following steps: Obtaining test sample data of a target evaluation dimension, the target evaluation dimension being an evaluation item for evaluating the skin quality of a target object, and the test sample data being a plurality of test results of the target object and / or a plurality of objects other than the target object in the target evaluation dimension collected before the current time; Determining a target correspondence relationship between a measurement value and a score value according to the test sample data; Determining a skin score value of the target object according to the target correspondence relationship and measurement data of the target object corresponding to the target evaluation dimension, the measurement data being a test value of the target evaluation dimension obtained by testing the skin of the target object at the current time; The test sample data comprises a plurality of test sample values, and the step of determining the target correspondence relationship between the measurement value and the score value according to the test sample data comprises: Determining a reference measurement value corresponding to a preset score value according to the distribution characteristics of the plurality of test sample values, the preset score value being a score value determined according to the skin test requirements of a user, and the reference measurement value corresponding to the preset score value being different; Determining the target correspondence relationship according to the preset score value and the corresponding reference measurement value.

2. The skin evaluation method of claim 1, wherein, The step of determining the reference measurement value corresponding to the preset score value according to the distribution characteristics of the plurality of test sample values comprises: Determining the numerical value interval in which each test sample is located in a plurality of preset numerical value intervals, and counting the number of test samples distributed in each preset numerical value interval; Determining the preset numerical value interval with the largest number as a target numerical value interval; Determining the reference measurement value according to the numerical value in the target numerical value interval.

3. The skin evaluation method of claim 1, wherein, The step of determining the target correspondence relationship according to the preset score value and the corresponding reference measurement value comprises: Dividing at least two measurement value intervals according to the reference measurement value; Determining the score value interval corresponding to each measurement value interval according to the correspondence relationship between the reference measurement value and the preset score value; Determining the correspondence relationship between the measurement value interval and the score value interval as the target correspondence relationship.

4. The skin evaluation method of claim 1, wherein, The step of determining the target correspondence relationship according to the preset score value and the corresponding reference measurement value comprises: Determining a target change trend of the score value with the measurement value according to a target correlation corresponding to the target evaluation dimension, the target correlation comprising the correlation between the size of the measurement value and the skin quality level represented; Determining the target correspondence relationship according to the target change trend, the preset score value and the reference measurement value.

5. The skin evaluation method of any one of claims 1 to 4, wherein, The number of target evaluation dimensions is more than one, different target evaluation dimensions correspond to different target correspondence relationships, and the step of determining the skin score value of the target object according to the target correspondence relationship and the measurement data of the target object corresponding to the target evaluation dimension comprises: Determining a corresponding sub-score according to the measurement data and the target correspondence relationship corresponding to each target evaluation dimension to obtain more than one sub-score; Determining the skin score value according to more than one sub-score.

6. The skin evaluation method of claim 5, wherein, The step of determining the skin score value according to the plurality of sub-scores comprises: The plurality of sub-scores are weighted and averaged according to the weight value corresponding to each target evaluation dimension to obtain the skin score value.

7. The skin evaluation method of claim 6, wherein, The plurality of target evaluation dimensions comprises a first type of target evaluation dimension and a second type of target evaluation dimension, the weight value corresponding to the first type of target evaluation dimension is less than the weight value corresponding to the second type of target evaluation dimension, and the probability of the measurement value corresponding to the first type of target evaluation dimension changing with environmental factors is greater than the probability of the second type of target evaluation dimension changing with environmental factors.

8. The skin evaluation method of claim 5, wherein, The plurality of target evaluation dimensions comprises anti-aging degree, water content, melanin, oil content, and sensitivity.

9. A skin evaluation device characterized by, The skin evaluation device comprises a memory, a processor, and a skin evaluation program stored on the memory and executable on the processor, and the skin evaluation program, when executed by the processor, implements the steps of the skin evaluation method according to any one of claims 1 to 8.

10. A storage medium, characterized by The storage medium stores a skin evaluation program, and the skin evaluation program, when executed by the processor, implements the steps of the skin evaluation method according to any one of claims 1 to 8.

Images