A system and method for rapid determination of nutritional components of castanea mollissima blume

Abstract

The application discloses a kind of conarillae nutrient ingredient spectrum fast determination system and method thereof, belong to component determination technical field, including sample information acquisition module, for obtaining the moisture content data of conarillae sample spectrum determination in time period, time period distinguishing mode includes obtaining conarillae storage period, the duration of storage period is counted, based on the duration of storage period the moisture content data obtained is divided, obtain the data characteristics therein;The application obtains the moisture content data of different storage periods of conarillae sample, constructs database according to moisture content data, divides moisture content data in database, collects characteristic data therein, to analyze the moisture content variation trend of conarillae sample, simultaneously, when collecting moisture content data, can calculate multiple moisture contents on conarillae sample according to the spectral reflectance of different determination points, to analyze the moisture content difference between each determination point, so that the judgment of the moisture content variation trend of conarillae is more accurate.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of component determination, in particular to a quick spectral determination system for nutritional components of Castanea henryi and a method thereof. BACKGROUND

[0002] With the improvement of living standards and the change of consumption concept, people pay more and more attention to the quality of fruits and their effect on consumer health. Among them, the nutritional components contained in fruits are one of the important concerns when people buy, and Castanea henryi is a kind of nut food rich in nutrients, which is deeply loved by consumers because it is rich in healthy fats, proteins, vitamins and minerals and other nutrients. Among them, the water content of Castanea henryi is an important parameter for evaluating its quality. If the water content is too high, the activity of pathogenic bacteria and other microorganisms will be enhanced during storage, increasing the possibility of rotting and deterioration. If the water content is too low, it will affect the taste, resulting in Castanea henryi not being full and light in quality, and thus affecting the economic benefits. The traditional technology for determining the water content of Castanea henryi is mostly by drying and weight loss method, which is destructive to Castanea henryi and takes a long time to determine. In recent years, studies have shown that near-infrared spectroscopy technology can be used to determine the water content of nuts. Spectroscopy is a technology that analyzes the properties of a substance by measuring its absorption, reflection or transmission of light at different wavelengths.

[0003] In spectroscopy, the principle is to measure the absorption, reflection or transmission of light in the near-infrared band (700-2500 nm) to analyze the chemical composition and properties of the substance. When light shines on the surface of the sample, different components of the molecule will respond differently to the light, forming a spectral curve. By analyzing the spectral curve, the water content of the sample can be inferred.

[0004] However, the existing near-infrared spectroscopy technology in the prior art stage for determining the water content of Castanea henryi mostly selects a determination point on the surface of Castanea henryi, and then emits near-infrared light of a specific wavelength band towards the selected determination point to observe the change of the spectral curve of the light of the wavelength band, and then infers the water content of Castanea henryi.

[0005] However, in the process of determination, the determination steps include from DNA sample to final data acquisition, and each link of sample detection, library construction and sequencing will affect the data quality and quantity, and the data quality will directly affect the results of subsequent information analysis, especially in the step of database construction after sample detection, it is difficult to predict the water content trend of Castanea henryi according to the data characteristics in the constructed database, which affects the analysis results of subsequent information, resulting in a large difference in the water content of Castanea henryi cultivated in the same period, and thus affecting people's eating experience. SUMMARY

[0006] In view of the above problems existing in the prior art of component determination, the present application is proposed.

[0007] Therefore, one of the purposes of the present application is to provide a chestnut nutrient component spectrum rapid determination system and method, which obtains moisture content data of chestnut samples at different storage periods, constructs a database according to the moisture content data, divides the moisture content data in the database, collects characteristic data therein to analyze the moisture content change trend of the chestnut samples, and at the same time, when the moisture content data is collected, the moisture content at different determination points can be calculated according to the spectral reflectance of the chestnut samples to analyze the moisture content difference between the determination points, so that the judgment of the moisture content change trend of the chestnut is more accurate, and the planting operation is assisted and guided to ensure the eating experience of people.

[0008] To solve the above technical problems, the present application provides the following technical solutions:

[0009] In one aspect, the present application provides a chestnut nutrient component spectrum rapid determination system, comprising:

[0010] A sample information acquisition module is configured to acquire moisture content data of chestnut sample spectrum determination in different time periods, and the time period division method comprises acquiring the storage period of chestnut, counting the duration of the storage period, dividing the acquired moisture content data based on the duration, and acquiring data characteristics therein.

[0011] A data fusion management unit is configured to construct a database according to the data characteristics, wherein in the database, the data characteristics are divided into θ1, θ2,..., θ n n represents the nth data characteristic, and the division of the acquired moisture content data based on the duration is responded; the data fusion management unit comprises a calculation module, an analysis module and a determination module.

[0012] The calculation module is configured to calculate the data difference of the moisture content data in each data characteristic based on the divided data characteristics.

[0013] The analysis module is configured to arrange the data size of the calculation result based on the calculation result of the calculation module, and analyze the change trend of the moisture content data.

[0014] The determination module is configured to determine the change trend, wherein according to the given level content of the moisture content data, when the change trend develops below the given level content, the system determines that the moisture content of the acquired chestnut sample is low, otherwise, it is not determined.

[0015] a data acquisition module, which is used for acquiring the moisture content data when it is determined that the moisture content of the Castanea henryi sample is the low moisture content, in response to the determination result of the determination module, and the acquisition mode includes acquiring at least 5 moisture content data every day in the storage period lasting days;

[0016] a data processing unit, which is used for counting the total number of the acquired data and processing, in response to the moisture content data acquired by the data acquisition module, and the processing mode includes intercepting the first data to the middle 3 data below the level content in all the data, marking the data as reference data, and marking the data in this process as late data; the data processing unit includes a previous data acquisition module, a processing module and a warning module;

[0017] the previous data acquisition module is used for acquiring the first data to the middle 3 data in all the data, and marking the data in this process as previous data;

[0018] the processing module is used for analyzing and processing the change rule of the previous data and the late data based on the previous data and the late data, and generating a prediction model;

[0019] the warning model is used for warning according to the analysis processing result; when the data in the previous data changes towards the middle 3 data, the system determines that the probability of the moisture content of the corresponding Castanea henryi sample being lower than the level content is 50%; when the middle 3 data in the late data changes towards the reference data, the system determines that the probability of the moisture content of the corresponding Castanea henryi sample being lower than the level content is 100%, and issues a warning.

[0020] As a preferred scheme of the present application, based on the previous data, the spectrum data corresponding to the data is acquired, the spectrum data includes spectrum reflectivity, the acquisition mode includes: collecting the reflection time in the corresponding Castanea henryi sample, intercepting the near-infrared light irradiation depth of the corresponding Castanea henryi sample based on the reflection time, recording the depth data, and simultaneously acquiring the reflected spectrum curve change; the depth data is marked as first depth data; and a determination point corresponding to the first depth data is acquired, and the determination point is marked as first determination point;

[0021] a second determination point and a third determination point are selected on the corresponding Castanea henryi sample, the depth data between different determination points and the spectrum curve change corresponding to the depth data are acquired, and the moisture content is calculated, which is calculated according to the following formula:

[0022] wherein, u k represents the u-th spectrum curve change of the k-th interval measured between determination points.

[0023] In the formula, r i represents the rth depth data collected in the ith acquisition in the third measuring point, x represents the water content corresponding to the depth data, and p represents the water content difference between each measuring point.

[0024] As a preferred scheme of the present application, the following is provided: based on the water content, a data set is generated from the three spectral curve changes obtained from different Castanea henryi samples corresponding to the previous data, spectral reflectance characteristics in each data set are analyzed, at least 10 characteristic values are selected, weights of the characteristic values in the spectral reflectance in the entire data set are calculated, and the following formula is used to calculate:

[0025] In the formula, j represents the average spectral reflectance in the entire data set.

[0026] In the formula, n is a characteristic vector, represents the minimum spectral reflectance obtained in each data set, i represents the difference between the minimum spectral reflectance and the maximum spectral reflectance in the corresponding data set, m o represents the difference between the mth maximum spectral reflectance obtained in the entire data set, and f represents the change trend of the difference.

[0027] As a preferred scheme of the present application, the following is provided: based on the change trend, the time when the entire Castanea henryi sample is obtained is classified into previous acquisition time, middle acquisition time, and later acquisition time, a preset minimum spectral reflectance is determined according to the previous acquisition time and the later acquisition time, the total number of Castanea henryi samples in the previous acquisition time and the later acquisition time is counted, and when the number of times when the spectral reflectance is lower than the preset spectral reflectance is less than one third in the total number, the system determines that the water content of the Castanea henryi sample is stable, otherwise, the system does not determine and issues a warning.

[0028] As a preferred scheme of the present application, the following is provided: based on the Castanea henryi sample obtained in the previous acquisition time, the spectral reflectance of the first measuring point and the second measuring point is collected, the change characteristics of the spectral reflectance of the two are analyzed, and 20-30 spectral reflectances with the highest occurrence frequency are intercepted in the change characteristics, when the difference between the spectral reflectance and the preset spectral reflectance is ≤10%, the system determines that the water content of the corresponding Castanea henryi sample is stable, in which case, no related determination is performed on the third measuring point; otherwise, the system does not determine and issues a warning.

[0029] As a preferred scheme of the present application, wherein: the average reflectivity is calculated in the most frequently occurring spectral reflectivity, and the average reflectivity is marked as the coefficient of variation, wherein, based on the first measuring point, the spectral reflectivity change value of the second measuring point is calculated according to the coefficient of variation, and the spectral reflectivity change value is calculated according to the following formula:

[0030] Wherein, θ represents the spectral reflectivity change value;

[0031] In the formula, λ represents the preset standard deviation, and σ represents the mean value. If the spectral reflectivity change value has a decreasing trend for the spectral reflectivity of the first measuring point, the system determines that the water content of the second measuring point is in a decreasing state, otherwise, it is not determined.

[0032] As a preferred scheme of the present application, wherein: when the system determines that the water content of the second measuring point is in a decreasing state, the spectral reflectivity corresponding to the decreasing state is collected, at least 3-10 characteristic reflectivities first appearing in the spectral reflectivity are collected, and the characteristic reflectivities are marked as judgment data. If the characteristic reflectivities collected in the future period for the Castanea henryi sample are the same as the judgment data, the system determines that the water content of the subsequent second measuring point will be in a decreasing state, otherwise, it is not determined.

[0033] As a preferred scheme of the present application, wherein: the judgment data is divided into several evaluation indexes, and the data is normalized, the weight of each evaluation index in the total spectral reflectivity is calculated, and the weight is used to determine the degree of reduction of the water content of the Castanea henryi sample in the future period.

[0034] On the other hand, the present application provides a method applied to a Castanea henryi nutritional ingredient spectral rapid determination system, comprising the following steps:

[0035] The water content data of the spectral determination of the Castanea henryi sample is obtained in time periods, and the time period division method comprises obtaining the storage period of the Castanea henryi, counting the number of days of the storage period, dividing the obtained water content data based on the number of days, and obtaining the data characteristics thereof;

[0036] A database is constructed according to the data characteristics, wherein, in the database, the data characteristics are divided into θ1, θ2,..., θ n n represents the nth data characteristic, and the division of the obtained water content data based on the number of days is responded;

[0037] The data difference of the water content data in each data characteristic is calculated, and the calculation results are arranged according to the data size, and the change trend of the water content data is analyzed;

[0038] judging the change trend; wherein, a given level of water content is given to the water content data, when the change trend develops towards below the given level of water content, then the system judges that the water content of the obtained Castanea henryi sample is low water content, otherwise, it is not judged;

[0039] collecting the water content data when it is judged that the water content of the obtained Castanea henryi sample is the low water content, and the collection mode includes collecting at least 5 water content data every day in the storage period lasting days;

[0040] counting the total number of the collected data and processing, and the processing mode includes intercepting the middle 3 data to the first data below the level in all the data, marking the data as reference data; and marking the data in this process as late data;

[0041] obtaining the first data to the middle 3 data in all the data, marking the data in this process as early data;

[0042] analyzing and processing the change law of the early data and the late data, and generating a prediction model.

[0043] The present application obtains water content data of Castanea henryi sample in different storage periods, constructs a database according to the water content data, divides the water content data in the database, collects characteristic data, analyzes the change trend of the water content of the Castanea henryi sample, and calculates multiple water contents according to the spectral reflectance of different measuring points on the Castanea henryi sample when collecting the water content data, analyzes the water content difference between the measuring points, and further obtains the stability of the water content of the Castanea henryi sample, so that the judgment of the change trend of the water content of the Castanea henryi is more accurate, and the planting operation is assisted and guided, so as to ensure the eating experience of people. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor. Among them:

[0045] Fig. 1 It is a modular structure diagram of the Castanea henryi nutrient component spectrum rapid determination system of the embodiment of the present application;

[0046] Fig. 2 It is a method flow diagram of the embodiment of the present application;

[0047] Fig. 3 It is a flow structure diagram of the embodiment of the present application;

[0048] The figure labels: 110-sample information acquisition module; 120-data fusion management unit; 1201-computing module; 1202-analysis module; 1203-determination module; 130-data acquisition module; 140-data processing unit; 1401-early data acquisition module; 1402-processing module; 1403-early warning module. DETAILED DESCRIPTION

[0049] To make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the described embodiments of the present application, all other embodiments obtained by a person of ordinary skill in the art belong to the scope of protection of the present application.

[0050] Since in the process of determination, each link from sample detection, library construction and sequencing will affect the data quality and quantity, and the data quality will directly affect the results of subsequent information analysis, especially in the database construction step after sample detection, it is difficult to analyze and predict the moisture content trend of Castanea henryi according to the data characteristics in the constructed database, so as to affect the analysis results of subsequent information, leading to a large difference in the moisture content of Castanea henryi cultivated in the same period, and further affecting people's eating experience.

[0051] Based on this, the present application provides a kind of Castanea henryi nutrient ingredient spectrum rapid determination system and method thereof, it obtains moisture content data of different storage periods by Castanea henryi sample, constructs database according to moisture content data, divides moisture content data in database, and collects characteristic data, to analyze the moisture content trend of Castanea henryi sample, and then assist guiding planting operation, to ensure people's eating experience.

[0052] The present application will be further described below by embodiments and in conjunction with the drawings.

[0053] Reference Figs. 1 to 3 For an embodiment of the present application, the embodiment provides a kind of Castanea henryi nutrient ingredient spectrum rapid determination system, comprising:

[0054] The sample information acquisition module 110 is used to obtain moisture content data of the spectrum determination of the Castanea henryi sample in time periods, and the time period distinction mode includes obtaining the storage period of the Castanea henryi, counting the duration of the storage period, dividing the obtained moisture content data based on the duration, and obtaining the data characteristics;

[0055] The data fusion management unit 120 is used to construct a database according to the data characteristics, wherein in the database, the data characteristics are divided into θ1, θ2,..., θ nn represents the nth data characteristic, in response to the division of the obtained water content data based on the number of days of storage; the data fusion management unit 120 includes a calculation module 1201, an analysis module 1202, and a determination module 1203;

[0056] The calculation module 1201 is configured to calculate the data difference of the water content data in each data characteristic based on the divided data characteristics;

[0057] The analysis module 1202 is configured to arrange the data size of the calculation result based on the calculation result of the calculation module 1201, and analyze the change trend of the water content data;

[0058] The determination module 1203 is configured to determine the change trend; wherein a given level content is given to the water content data, and when the change trend develops below the given level content, the system determines that the water content of the obtained Castanea henryi sample is low water content, otherwise, it is not determined;

[0059] The data acquisition module 130 is configured to acquire water content data when the determination module 1203 determines that the water content of the obtained Castanea henryi sample is low water content, and the acquisition mode includes acquiring at least 5 water content data every day during the number of days of storage;

[0060] The data processing unit 140 is configured to count and process the total number of the acquired data, and the processing mode includes marking the middle 3 data to the first data below the level content in all data as reference data, and marking the data in this process as late data; the data processing unit 140 includes a early data acquisition module 1401, a processing module 1402, and a warning module 1403;

[0061] The early data acquisition module 1401 is configured to acquire the first data to the middle 3 data in all data, and mark the data in this process as early data;

[0062] It is necessary to explain in this embodiment that the spectral data corresponding to the early data is acquired based on the early data, and the spectral data includes spectral reflectivity, and the acquisition mode includes: acquiring the reflection time in the corresponding Castanea henryi sample, acquiring the near-infrared light irradiation depth of the corresponding Castanea henryi sample based on the reflection time, recording the depth data, and simultaneously acquiring the reflected spectral curve change; the depth data is marked as first depth data; and the measurement point corresponding to the first depth data is acquired, and the measurement point is marked as first measurement point;

[0063] A second measurement point and a third measurement point are selected on the corresponding Castanea henryi sample, depth data between different measurement points are collected, and spectral curve changes corresponding to the depth data are collected, and the water content is calculated according to the following formula:

[0064] wherein u k represents the u-th spectral curve change of the k-th interval measured between the measurement points;

[0065] wherein r i represents the r-th depth data collected for the i-th time in the third measurement point, x represents the water content corresponding to the depth data, and p represents the water content difference between the measurement points;

[0066] On the basis of the above, the embodiment obtains the number of Castanea henryi samples corresponding to the previous data based on the water content, generates a data set of the three spectral curve changes obtained in different Castanea henryi samples, analyzes the spectral reflectance characteristics in each data set, selects at least 10 characteristic values, calculates the weight of the characteristic values in the spectral reflectance of the entire data set, and calculates according to the following formula:

[0067] wherein j represents the average spectral reflectance in the entire data set;

[0068] wherein n is a characteristic vector, represents the minimum spectral reflectance obtained in each data set, i represents the difference between the minimum spectral reflectance and the maximum spectral reflectance in the corresponding data set, m o represents the difference between the m-th maximum spectral reflectance obtained for the o-th time in the entire data set, and f represents the change trend of the difference;

[0069] Further, the embodiment classifies the time when the entire Castanea henryi sample is obtained into early acquisition time, middle acquisition time and late acquisition time based on the change trend, and presets the minimum spectral reflectance according to the early acquisition time and the late acquisition time, counts the total number of Castanea henryi samples of the early acquisition time and the late acquisition time, and when the number of times that the spectral reflectance is lower than the preset spectral reflectance is less than one-third in the total number, the system determines that the water content of the Castanea henryi sample is stable, otherwise, it is not determined, and a warning is issued;

[0070] On the basis of the above, the embodiment collects spectral reflectance about the first measurement point and the second measurement point based on the Castanea henryi sample obtained in the early acquisition time, analyzes the change characteristics of the spectral reflectance of the two, and intercepts 20-30 spectral reflectances with the highest occurrence frequency in the change characteristics, when the difference between the spectral reflectance and the preset spectral reflectance is ≤10%, the system determines that the water content of the corresponding Castanea henryi sample is stable, in this case, no related measurement is performed on the third measurement point; otherwise, it is not determined, and a warning is issued;

[0071] It is emphasized that the average reflectance is calculated in the most frequently occurring spectral reflectance, and the average reflectance is marked as the coefficient of variation, wherein the spectral reflectance variation value of the second measuring point is calculated according to the coefficient of variation, and the spectral reflectance variation value is calculated according to the following formula:

[0072] Wherein, θ represents the spectral reflectance variation value;

[0073] In the formula, λ represents the preset standard deviation, and σ represents the mean value. If the spectral reflectance variation value shows a decreasing trend for the spectral reflectance of the first measuring point, then the system determines that the water content of the second measuring point is in a decreasing state, and vice versa.

[0074] Further, when the system determines that the water content of the second measuring point is in a decreasing state, the spectral reflectance corresponding to the decreasing state is collected, and at least 3-10 characteristic reflectances first appearing in the spectral reflectance are collected, which are marked as judgment data. If the characteristic reflectance collected in the future period for the Castanea henryi sample is the same as the judgment data, then the system determines that the water content of the subsequent second measuring point will be in a decreasing state, and vice versa.

[0075] The judgment data is divided into a plurality of evaluation indexes, and the data is normalized to calculate the weight of each evaluation index in the total spectral reflectance, and the weight is used to determine the degree of reduction of the water content of the Castanea henryi sample in the future period.

[0076] The processing module 1402 is used to analyze and process the change rule of the early data and the late data based on the early data and the late data, and generate a prediction model;

[0077] The early warning model 1403 is used to issue a warning according to the analysis and processing result; when the data in the early data changes towards the middle 3 data, the system determines that the probability of the water content of the corresponding Castanea henryi sample being lower than the level content is 50%; when the middle 3 data in the late data changes towards the reference data, the system determines that the probability of the water content of the corresponding Castanea henryi sample being lower than the level content is 100%, and issues a warning.

[0078] Based on the above, the application obtains water content data of different storage periods of Castanea henryi samples, constructs a database according to the water content data, divides the water content data in the database, collects characteristic data, analyzes the water content change trend of the Castanea henryi sample, and further assists in guiding the planting operation to ensure people's eating experience.

[0079] The embodiment combines the above-mentioned Castanea henryi nutrient component spectral rapid determination system, and further proposes a working method applied to the system, as follows:

[0080] S10: Obtain the moisture content data of the Castanea henryi sample spectrum determination by time period, and the time period distinguishing method includes obtaining the storage period of the Castanea henryi, counting the continuous days of the storage period, dividing the obtained moisture content data based on the continuous days, and obtaining the data characteristics therein;

[0081] S20: Construct a database according to the data characteristics, wherein in the database, the data characteristics are divided into θ1, θ2,..., θ n n represents the nth data characteristic, in response to the division of the obtained moisture content data based on the continuous days;

[0082] S30: Calculate the data difference of the moisture content data in each data characteristic, arrange the calculation results according to the data size, and analyze the change trend of the moisture content data;

[0083] S40: Determine the change trend; wherein according to the given level content of the moisture content data, when the change trend develops below the given level content, the system determines that the obtained moisture content of the Castanea henryi sample is low, otherwise, it is not determined;

[0084] S50: Collect the moisture content data when it is determined that the moisture content of the obtained Castanea henryi sample is low, and the collection method includes collecting at least 5 moisture content data every day in the continuous days of the storage period;

[0085] S60: Count and process the total number of the collected data, and the processing method includes intercepting the middle 3 data to the first data below the level content in all the data, marking the data as reference data; and marking the data in this process as late data;

[0086] S70: Obtain the first data to the middle 3 data in all the data, and mark the data in this process as early data;

[0087] S80: Analyze and process the change rule of the early data and the late data, and generate a prediction model.

[0088] As described above, the present application obtains the moisture content data of the Castanea henryi sample in different storage periods, constructs a database according to the moisture content data, divides the moisture content data in the database, collects the characteristic data therein, analyzes the change trend of the moisture content of the Castanea henryi sample, and at the same time, when collecting the moisture content data, calculates multiple moisture contents according to the spectral reflectance of different determination points on the Castanea henryi sample, analyzes the moisture content difference between the determination points, and further obtains the stability of the moisture content of the Castanea henryi sample, so that the judgment of the change trend of the moisture content of the Castanea henryi is more accurate, and the planting operation is assisted and guided, so as to ensure the eating experience of people.

[0089] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced, without departing from the spirit and scope of the technical solutions of the present application, which should be covered in the scope of the claims of the present application.

Claims

1. A system for rapid determination of nutritional components of Castanea mollissima Blume by spectroscopy, characterized by, The system comprises: a sample information acquisition module, configured to acquire water content data of a Castanea henryi sample spectrum measurement in time periods, and the time period distinguishing manner comprises acquiring a C. henryi storage period, counting the number of days of the storage period, dividing the acquired water content data based on the number of days, and acquiring data characteristics therein; The data fusion management unit is used to construct a database based on the data features, wherein the data features are divided into θ1, θ2, ..., θ3 in the database. n , n represents the nth data feature, in response to the division of the acquired moisture content data based on the duration of days; the data fusion management unit includes a calculation module, an analysis module, and a judgment module; the calculation module is configured to calculate data differences of the water content data in each data characteristic based on the divided data characteristics; the analysis module is configured to arrange data sizes of the calculation results of the calculation module based on the calculation results, and analyze a change trend of the water content data; the determination module is configured to determine the change trend; wherein, according to a given level content of the water content data, when the change trend develops towards a level lower than the given level, the system determines that the water content of the acquired C. henryi sample is low water content, otherwise, the system does not determine; a data acquisition module, configured to acquire the water content data when it is determined that the water content of the acquired C. henryi sample is the low water content, and the acquisition manner comprises acquiring at least 5 water content data every day in the number of days of the storage period; a data processing unit, configured to count and process the total number of the acquired water content data, and the processing manner comprises intercepting the middle 3 data to the first data after the level in all the data, marking the first data after the level as reference data, and marking the data in this process as later data; the data processing unit comprises a previous data acquisition module, a processing module and a warning module; the previous data acquisition module is configured to acquire the first data to the middle 3 data in all the data, and mark the data in this process as previous data; the processing module is configured to analyze and process change rules of the previous data and the later data based on the previous data and the later data, and generate a warning model; the warning model is configured to issue a warning according to the analysis and processing results; when the data in the previous data changes towards the middle 3 data, the system determines that the probability of the water content of the corresponding C. henryi sample being lower than the level is 50%; when the middle 3 data in the later data changes towards the reference data, the system determines that the probability of the water content of the corresponding C. henryi sample being lower than the level is 100%, and issues a warning.

2. The system for rapid determination of nutritional components of Castanea mollissima Blume according to claim 1, wherein, based on the previous data, the spectrum data corresponding to the previous data is acquired, and the spectrum data comprises spectrum reflectivity, and the acquisition manner comprises: acquiring a reflection time in the corresponding C. henryi sample, intercepting the near-infrared light irradiation depth of the corresponding C. henryi sample based on the reflection time, recording the depth data, and simultaneously acquiring the reflected spectrum curve change; the depth data is marked as first depth data; and a measurement point corresponding to the first depth data is acquired, and the measurement point is marked as a first measurement point; A second measuring point and a third measuring point are selected on the corresponding Castanea henryi sample, depth data between different measuring points are collected, spectral curve changes corresponding to the depth data are collected, and a water content is calculated according to the following formula: wherein u k represents the u-th spectral curve variation of the k-th distance measured between each measuring point; In the formula, r i represents the rth depth data collected at the ith acquisition in the third measurement point, x represents the water content corresponding to the depth data, and p represents the water content difference between each measurement point.

3. The system for rapid determination of nutritional components of Castanea mollissima Blume according to claim 2, wherein, Based on the water content, the number of Castanea henryi samples corresponding to the previous data is obtained, data sets of three kinds of spectral curve changes obtained in different Castanea henryi samples are generated, spectral reflectance characteristics in each data set are analyzed, at least 10 characteristic values are selected, the weight of the characteristic values in the overall data set is calculated according to the following formula: where j represents the average spectral reflectance across the entire data set; where n is the eigenvector, min spectral reflectance indicates the minimum spectral reflectance obtained in each data set, i indicates the difference between the minimum spectral reflectance and the maximum spectral reflectance in the corresponding data set, m o where o indicates the mth maximum spectral reflectance obtained in all data sets, f indicates the trend of the difference between the mth maximum spectral reflectance and the (m-1)th maximum spectral reflectance.

4. The system for rapid determination of nutritional components of Castanea mollissima Blume according to claim 3, wherein, Based on the trend, the time when all the Castanea henryi samples are obtained is classified according to the previous acquisition time, the middle acquisition time and the later acquisition time, the minimum spectral reflectance is preset according to the previous acquisition time and the later acquisition time, the total number of Castanea henryi samples of the previous acquisition time and the later acquisition time is counted, when the number of spectral reflectance lower than the preset minimum spectral reflectance is less than one third in the total number, the system determines that the water content of the Castanea henryi sample is stable, otherwise, it is not determined, and a warning is issued.

5. The system for rapid determination of nutritional components of Castanea mollissima Blume according to claim 4, wherein, Based on the Castanea henryi sample obtained at the previous acquisition time, the spectral reflectance of the first measuring point and the second measuring point is collected, the change characteristics of the spectral reflectance of the two are analyzed, and 20-30 spectral reflectances with the highest frequency of occurrence are intercepted in the change characteristics, when the difference between the spectral reflectance and the preset minimum spectral reflectance is ≤10%, the system determines that the water content of the corresponding Castanea henryi sample is stable, in which case the third measuring point is not determined; Otherwise, it is not determined, and a warning is issued.

6. The system for rapid determination of nutritional components of Castanea mollissima Blume according to claim 5, wherein, In The average reflectance is calculated in the spectral reflectance with the highest frequency of occurrence, and the average reflectance is marked as a coefficient of variation, wherein, taking the first measuring point as the target, the spectral reflectance change value of the second measuring point is calculated according to the coefficient of variation, and the following formula is used to calculate: wherein θ represents the spectral reflectance change value; In the formula, λ represents a preset standard deviation, and σ represents a mean value. If the spectral reflectance change value shows a shrinking trend for the spectral reflectance of the first measuring point, the system determines that the water content of the second measuring point is in a shrinking state, otherwise, it is not determined.

7. The system for rapid determination of nutritional components of Castanea mollissima Blume according to claim 6, wherein, When the system determines that the water content of the second measuring point is in a shrinking state, the spectral reflectance corresponding to the shrinking state is collected, at least 3-10 characteristic reflectances appearing first are collected in the spectral reflectance, the characteristic reflectances are marked as judgment data, if the characteristic reflectances collected in the future period of the Castanea henryi sample are the same as the judgment data, the system determines that the water content of the subsequent second measuring point will be in a shrinking state, otherwise, it is not determined.

8. The system for rapid determination of nutritional components of Castanea mollissima Blume according to claim 7, wherein, The judgment data is divided into several evaluation indexes, and the data is normalized, the weight of each evaluation index in the overall spectral reflectance is calculated, and the weight is used to determine the reduction degree of the water content of the Castanea henryi sample in the future period.

9. The method applied to the system for rapid determination of the nutritional components of Castanea henryi Garn.-Jones by spectrum as claimed in claim 1, characterized in that, The method comprises the following steps: Periodically acquiring the water content data of the Castanea henryi sample spectrum determination, the period distinguishing method includes acquiring the storage period of the Castanea henryi, counting the duration of the storage period, dividing the acquired water content data based on the duration, and acquiring the data characteristics therein; A database is constructed based on the data features, wherein the data features are divided into θ1, θ2, ..., θ3 in the database. n , n represents the nth data feature, in response to the division of the acquired moisture content data based on the duration of days; Calculating the data difference of the water content data in each data characteristic, arranging according to the data size of the calculation result, and analyzing the change trend of the water content data; Determining the change trend; wherein, a given level content is given to the water content data, when the change trend develops below the given level content, the system determines that the water content of the acquired Castanea henryi sample is low, otherwise, it is not determined; Collecting the water content data when it is determined that the water content of the acquired Castanea henryi sample is the low water content, the collection method includes collecting at least 5 water content data every day in the duration of the storage period; Counting the total number of the collected data and processing, the processing method includes intercepting the middle 3 data to the first data below the level content in all the data, marking the data as reference data; and marking the data in this process as late data; Acquiring the first data to the middle 3 data in all the data, marking the data in this process as early data; Analyzing and processing the change rule of the early data and the late data, and generating a prediction model.

Images