CN115034303A - Directional detection method and system for harmful substances in food - Google Patents
Directional detection method and system for harmful substances in food Download PDFInfo
- Publication number
- CN115034303A CN115034303A CN202210642769.8A CN202210642769A CN115034303A CN 115034303 A CN115034303 A CN 115034303A CN 202210642769 A CN202210642769 A CN 202210642769A CN 115034303 A CN115034303 A CN 115034303A
- Authority
- CN
- China
- Prior art keywords
- food
- list
- calibration
- detection
- harmful substances
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 239000000126 substance Substances 0.000 title claims abstract description 379
- 235000013305 food Nutrition 0.000 title claims abstract description 352
- 238000001514 detection method Methods 0.000 title claims abstract description 215
- 239000011159 matrix material Substances 0.000 claims abstract description 37
- 238000013210 evaluation model Methods 0.000 claims abstract description 22
- 238000005070 sampling Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims description 44
- 230000002159 abnormal effect Effects 0.000 claims description 21
- 238000012163 sequencing technique Methods 0.000 claims description 21
- 238000011156 evaluation Methods 0.000 claims description 17
- 238000000605 extraction Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 11
- 230000007613 environmental effect Effects 0.000 claims description 7
- 238000013513 substance screening Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000002955 isolation Methods 0.000 claims description 5
- 230000003213 activating effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 239000003344 environmental pollutant Substances 0.000 claims 2
- 231100000719 pollutant Toxicity 0.000 claims 2
- 239000000383 hazardous chemical Substances 0.000 claims 1
- 238000011835 investigation Methods 0.000 abstract description 10
- 230000000694 effects Effects 0.000 abstract description 9
- 230000008569 process Effects 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 235000015097 nutrients Nutrition 0.000 description 2
- 238000001069 Raman spectroscopy Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 235000013601 eggs Nutrition 0.000 description 1
- 229910001385 heavy metal Inorganic materials 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 235000013622 meat product Nutrition 0.000 description 1
- 239000012621 metal-organic framework Substances 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 235000013336 milk Nutrition 0.000 description 1
- 239000008267 milk Substances 0.000 description 1
- 210000004080 milk Anatomy 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/02—Food
Landscapes
- Engineering & Computer Science (AREA)
- Food Science & Technology (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Medicinal Chemistry (AREA)
- Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a directional detection method and a system for harmful substances in food, which relate to the field of food safety detection and comprise the following steps: acquiring food state information and culture environment information of food to be detected, matching with harmful substances, and generating a food harmful substance list; determining a list of harmful substances to be detected according to the food harmful substance proportion list; matching a food detection instrument according to the type of the harmful substances and key detection components, sampling and conveying food to be detected to the food detection instrument, generating detection feedback information, calibrating a characteristic value of a list of the harmful substances to be detected, generating a characteristic matrix of the harmful substances, inputting the characteristic matrix and the type of the food into a food damage level evaluation model, generating a food damage level meeting a first preset threshold, and generating an unqualified label for marking. The technical problem of low detection efficiency caused by comprehensive investigation of food detection is solved. The technical effect of improving the detection efficiency is achieved by carrying out directional detection on more important harmful substances to be detected.
Description
Technical Field
The invention relates to the technical field related to food safety detection, in particular to a method and a system for directionally detecting harmful substances in food.
Background
In the field of food safety, detection of harmful substances in food is a key concern, accurate detection data of the harmful substances in food is main information for food safety assessment, and in the current technology for detecting the harmful substances in food, various types of food detection instruments are selected for carrying out comprehensive harmful substance examination to obtain accurate harmful substance detection results.
The mode has good detection comprehensiveness, but the food detection of the mode lacks important investigation points and has poor purposiveness, and in fact, the food can represent more important harmful substance investigation dimensionality according to the planting environment and the food state of the food, and then the food can be used as the important investigation dimensionality to perform preferential investigation, so that the detection efficiency can be greatly improved, but because the analysis process is more complicated, a scheme capable of falling to the ground has not been provided all the time.
In summary, it can be seen that in the prior art, since food detection is generally performed in an all-around manner, the purpose is poor, and thus the technical problem of low detection efficiency is caused.
Disclosure of Invention
The application provides a directional detection method and system for harmful substances in food, and the technical problem that in the prior art, due to the fact that food detection is generally carried out in a comprehensive mode, the purpose is poor, and therefore the detection efficiency is low is solved.
In view of the above problems, the embodiments of the present application provide a method and a system for directionally detecting harmful substances in food.
In a first aspect, the present application provides a method for directionally detecting harmful substances in food, wherein the method is applied to a system for directionally detecting harmful substances in food, wherein the system is communicatively connected to a plurality of multi-type food detection instruments, and the method includes: acquiring basic information of food to be detected, wherein the basic information of the food to be detected comprises food state information and culture environment information; matching harmful substances with the food state information and the culture environment information to generate a food harmful substance list, wherein the food harmful substance list corresponds to the food harmful substance ratio list in a one-to-one manner; screening the food harmful substance list according to the food harmful substance proportion list, and determining the list of harmful substances to be detected, wherein the list of harmful substances to be detected comprises harmful substance types and key detection components which correspond one to one; matching a food detection instrument according to the type of the harmful substances and the key detection components, sampling the food to be detected, conveying the food to be detected to the food detection instrument, and generating detection feedback information; according to the detection feedback information, calibrating the characteristic value of the harmful substance list to be detected to generate a harmful substance characteristic matrix; inputting the harmful substance characteristic matrix and the food type into a food hazard level evaluation model to generate a food hazard level; and when the food hazard level meets a first preset threshold value, generating an unqualified label to mark the food to be detected.
In another aspect, the present application provides a system for directionally detecting harmful substances in food, wherein the system is communicatively connected to a plurality of multi-type food detection apparatuses, and comprises: the information acquisition module: the method comprises the steps of acquiring basic information of food to be detected, wherein the basic information of the food to be detected comprises food state information and culture environment information; an information matching module: the culture environment information is used for matching harmful substances with the food state information and the culture environment information to generate a food harmful substance list, wherein the food harmful substance list corresponds to the food harmful substance proportion list in a one-to-one manner; the information screening module: the food harmful substance list is screened according to the food harmful substance proportion list, and the list of harmful substances to be detected is determined, wherein the list of harmful substances to be detected comprises harmful substance types and key detection components which correspond to each other one by one; the food detection module comprises: the food detection instrument is matched with the food detection instrument according to the type of the harmful substances and the key detection components, the food to be detected is sampled and is conveyed to the food detection instrument, and detection feedback information is generated; a characteristic calibration module: the characteristic value calibration is carried out on the harmful substance list to be detected according to the detection feedback information, and a harmful substance characteristic matrix is generated; a hazard evaluation module: the harmful substance characteristic matrix and the food type are input into a food hazard level evaluation model to generate a food hazard level; an information identification module: and when the food hazard level meets a first preset threshold value, generating an unqualified label to mark the food to be detected.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the method adopts the steps of collecting basic information of the food to be detected, wherein the basic information comprises food state information and culture environment information; matching harmful substances according to the food state and the culture environment information, and determining a harmful substance list; screening the harmful substances according to the harmful substance list and the proportion thereof, and determining the harmful substances to be detected; matching a corresponding food detection instrument according to the type of the harmful substances to be detected and the key detection components, sampling and conveying the samples to the corresponding food detection instrument for detection to obtain detection feedback information; according to the technical scheme, the method comprises the steps of calibrating the characteristic value of a harmful substance list to be detected according to detection feedback information to obtain a harmful substance characteristic matrix, evaluating the damage level of the harmful substance characteristic matrix and the food type according to a food damage level evaluation model, identifying unqualified food, conducting directional investigation on the harmful substance according to the food state and the culture environment, determining the important harmful substance to be detected, preferentially detecting, conducting food safety evaluation, reducing detection dimensionality and full-automatic control, and achieving the technical effect of improving food safety detection efficiency and detection accuracy.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
FIG. 1 is a schematic flow chart of a method for directionally detecting harmful substances in food according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of determining a list of harmful substances in a food harmful substance directional detection method according to an embodiment of the present application;
fig. 3 is a schematic flow chart illustrating a harmful substance feature matrix determination process in a method for directionally detecting harmful substances in food according to an embodiment of the present application;
FIG. 4 is a schematic structural diagram of a system for directionally detecting harmful substances in food according to an embodiment of the present disclosure;
description of reference numerals: the system comprises a multi-type food detection instrument terminal 001, an information acquisition module 11, an information matching module 12, an information screening module 13, a food detection module 14, a characteristic calibration module 15, a hazard evaluation module 16 and an information identification module 17.
Detailed Description
The embodiment of the application provides a directional detection method and a system for harmful substances in food, and solves the technical problems that in the prior art, the food detection is generally carried out in an all-round mode, the purpose is poor, the detection efficiency is low, the harmful substances are directionally examined through the food state and the culture environment, the important harmful substances to be detected are determined, the detection is preferentially carried out, the food safety assessment is carried out, the detection dimensionality and full-automatic control are reduced, and the technical effects of improving the food safety detection efficiency and the detection accuracy are achieved.
Summary of the application
The detection of harmful substances in food is an important investigation content in food safety detection, in the prior art, harmful substance detection is usually carried out on food in an all-round manner, but actually, harmful substances in food are closely related to the growth environment of the harmful substances and the food states of storage, transportation and the like, and the harmful substances in food can be evaluated through the information so as to realize directional harmful substance detection, so that the technical effects of improving detection efficiency and detection accuracy can be achieved.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides a method and a system for directionally detecting harmful substances in food. The method adopts the steps of collecting basic information of the food to be detected, wherein the basic information comprises food state information and culture environment information; matching harmful substances according to the food state and the culture environment information, and determining a harmful substance list; screening the harmful substances according to the list of the harmful substances and the proportion of the harmful substances, and determining the harmful substances to be detected; matching a corresponding food detection instrument according to the type of the harmful substances to be detected and the key detection components, sampling and conveying the samples to the corresponding food detection instrument for detection to obtain detection feedback information; according to the technical scheme, the method comprises the steps of calibrating the characteristic value of a harmful substance list to be detected according to detection feedback information to obtain a harmful substance characteristic matrix, evaluating the damage level of the harmful substance characteristic matrix and the food type according to a food damage level evaluation model, identifying unqualified food, conducting directional investigation on the harmful substance according to the food state and the culture environment, determining the important harmful substance to be detected, preferentially detecting, conducting food safety evaluation, reducing detection dimensionality and full-automatic control, and achieving the technical effect of improving food safety detection efficiency and detection accuracy.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
As shown in fig. 1, the present application provides a method for directionally detecting a harmful substance in food, wherein the method is applied to a system for directionally detecting a harmful substance in food, wherein the system is communicatively connected to a plurality of multi-type food detection instruments, and the method includes the steps of:
s100: acquiring basic information of food to be detected, wherein the basic information of the food to be detected comprises food state information and culture environment information;
in particular, the food to be tested refers to the food to be tested, including but not limited to: food types such as fruits, vegetables, raw fresh, egg and milk, meat products, and the like; food status information refers to current status characteristic data of a food, including but not limited to: data such as color characteristics, surface morphology characteristics, transportation condition characteristics, storage condition characteristics and the like; culture environment information refers to environmental data of food cultivation or planting or growth, including but not limited to: temperature, humidity, pH value, geographical position, climatic environment, nutrient addition and other culture data. The real-time state of the food to be detected can be represented by collecting the basic information of the food to be detected, and the accurate and comprehensive basic information of the food to be detected is the basis for ensuring the accuracy of the analysis of the subsequent data.
Before the detection of the harmful substances in the food, classification operation is required, and the process is as an example:
first-level clustering analysis: clustering the foods according to the types of the foods to be detected and then storing the foods in groups to obtain a plurality of groups of foods to be detected, wherein the foods corresponding to different groups are different in type; and further collecting food state information and culture environment information, and performing secondary clustering analysis on the foods in each group to obtain a secondary group, wherein the secondary group is a more detailed food group grouped by the primary clustering analysis, and the foods in each group of the secondary group have the same food state information and culture environment information. Different batches of food harmful substance detection can be determined through the first-level grouping data, uniform sampling in the food harmful substance detection process can be determined according to the second-level grouping data, food harmful substances of different food state information and cultivation environment information can be uniformly sampled, and the fineness of food harmful substance detection is improved.
S200: matching harmful substances with the food state information and the culture environment information to generate a food harmful substance list, wherein the food harmful substance list corresponds to the food harmful substance ratio list in a one-to-one manner;
further, as shown in fig. 2, a list of food harmful substances is generated based on the matching of the food state information and the cultivation environment information, and step S200 includes the steps of:
s210: performing first preset feature extraction on the food state information to generate a state feature set;
s220: performing second preset feature extraction on the culture environment information to generate an environment feature set;
s230: inputting the food types into a harmful substance screening table, and matching all harmful substances;
s240: carrying out proportion calibration on all harmful substances according to the state feature set and the environment feature set to generate proportion calibration results of all harmful substances;
s250: and sequencing all harmful substances from large to small according to the proportion calibration result of all the harmful substances to generate the food harmful substance list.
Specifically, the list of harmful substances of food refers to a list of harmful substances determined by matching based on historical empirical data according to food state information and cultivation environment information of food, and includes a list of proportions of harmful substances of food evaluated according to historical experience, which correspond one-to-one to the list of harmful substances of food.
The process of determining the list of harmful substances of food exemplifies one example of a limitation:
extracting food characteristics:
the first step is as follows: and (3) state feature extraction: the first preset feature refers to a preset food state feature extraction dimension, such as: characteristic dimensions such as color characteristics, surface morphology characteristics, transportation condition characteristics, storage condition characteristics and the like; the state feature set refers to a result obtained after state feature extraction is carried out on the food to be detected according to the first preset feature and the one-to-one corresponding identification is stored. Through to injecing the feature extraction dimension, can improve feature extraction efficiency, avoid improving the data redundancy with the lower feature of food harmful substance degree of relevance, above-mentioned dimension is left out to first preset characteristic, can be by staff according to actual conditions custom setting.
The second step: extracting environmental features: the second preset feature refers to a preset feature extraction dimension of the food cultivation environment, such as, for example: temperature, humidity, pH value, geographical position, climatic environment, nutrient addition and other culture data; the environmental feature set refers to a result obtained after extracting the environmental features of the food to be detected according to the second preset features and storing the one-to-one corresponding identifiers. Through to injecing the extraction dimension, can improve feature extraction efficiency, avoid improving the data redundancy with the lower feature of food harmful substance degree of relevance, the second is preset the feature and is left above-mentioned dimension, can be by staff according to actual conditions custom setting.
Matching harmful substances:
the harmful substance screening table refers to characterization obtained by counting expert experiences: the data sheet of food type-harmful substance set, the preferred form with virtual table of on-line of harmful substance sieve list is saved, can gather big data according to predetermineeing the cycle and update the harmful substance sieve list, guarantee the accuracy and the ageing of harmful substance sieve list. The food type refers to the food type corresponding to the food to be detected, all harmful substances corresponding to the food type are determined by inputting the food type into the harmful substance screening table, and an information feedback basis is provided for the subsequent harmful substance screening.
And (3) proportion calibration:
all harmful substances are subjected to proportional calibration through the extracted state feature set and the extracted environment feature set, the proportional calibration result of all harmful substances can represent the proportional content information of all harmful substances in the food to be detected based on empirical evaluation, the accurate proportional calibration result is the guarantee of the accuracy of subsequent directional detection, the proportional calibration of all harmful substances according to the state feature set and the environment feature set is a more complex process, the subjectivity of the calibration result of a single participant is strong, therefore, the preferred proportional calibration database constructed based on multiple participants is adopted for proportional calibration, and multiple groups are stored in the proportional calibration database: (status characteristics, environmental characteristics) -database of all harmful substance ratio calibration result information.
Generating a list of food harmful substances:
and sequencing all the harmful substances from large to small or from small to large according to the calibration result of the proportion of all the harmful substances, wherein the harmful substances in the food have the same sequencing serial number in the same proportion, and generating a list of the harmful substances in the food. The estimated proportion data of each harmful substance in the food can be determined through the food harmful substance list, and further important reference data are provided for oriented analysis.
The detailed proportion calibration mode is as follows:
further, based on the proportion calibration of all harmful substances according to the state feature set and the environmental feature set, a proportion calibration result of all harmful substances is generated, and step S240 further includes the steps of:
s241: activating a proportion calibration database, wherein the proportion calibration database comprises a first calibration sub-library, a second calibration sub-library and an Nth calibration sub-library, and any two character libraries from the first calibration sub-library, the second calibration sub-library and the Nth calibration sub-library are in an information isolation state;
s242: inputting the state feature set, the environment feature set, the substance types and all harmful substances into the first calibration sub-library and the second calibration sub-library in parallel until the Nth calibration sub-library, and generating a first calibration result and a second calibration result until the Nth calibration result;
s243: and traversing all harmful substances according to the first calibration result, the second calibration result and the Nth calibration result and according to a preset proportion calibration rule to perform proportion calculation to generate a proportion calibration result of all harmful substances.
Further, based on the preset proportion calibration rule, the step S243 further includes the steps of:
s243-1: traversing all the harmful substances according to the first calibration result, the second calibration result and the Nth calibration result to generate a first substance proportion calibration list, and traversing the second substance proportion calibration list and the Mth substance proportion calibration list;
s243-2: obtaining a preset proportion calibration formula:
wherein eta is m For the m-th material ratio calibration result, x n Calibrating the value of the mth substance in the nth calibration sub-library;
s243-3: and calculating the proportion calibration list of the first substance, the proportion calibration list of the second substance and the proportion calibration list of the Mth substance by using the preset proportion calibration formula to obtain the proportion calibration result of all the harmful substances.
Specifically, the first calibration sub-library, the second calibration sub-library and up to the nth calibration sub-library are databases built on the basis of local historical experience data in an information isolation state respectively from the first food detection participant, the second food detection participant and up to the nth food detection participant, and the first food detection participant, the second food detection participant and up to the nth food detection participant are selected from food detection manufacturers, food detection research experts, food detection units or organizations and the like; the first calibration result, the second calibration result and the Nth calibration result refer to the result that the state feature set, the environment feature set, the material types and all harmful substances are input into the first calibration sub-library and the second calibration sub-library in parallel until the Nth calibration sub-library is used for carrying out harmful substance proportion calibration, and the data isolation between the first calibration sub-library and the second calibration sub-library and the Nth calibration sub-library guarantees privacy among all databases on one hand and avoids interference of other participants during evaluation on the other hand, and can be more objective and accurate during data fusion of later steps.
The first substance proportion calibration list, the second substance proportion calibration list and the No. M substance proportion calibration list refer to proportion calibration results of all harmful substances, and any one of the M groups has N proportion calibration results; the preset proportion calibration rule refers to a rule for performing proportion calibration in a preset mode, namely performing data fusion on the first calibration result, the second calibration result and the nth calibration result, and is preferably: calibrating a formula through a preset proportion:
the proportion calibration result of any harmful substance can be determined by traversing the first substance proportion calibration list and the second substance proportion calibration list to the Mth substance proportion calibration list through a preset proportion calibration formula, and a proportion calibration database shared by decision data is formed by breaking a data island and based on multiple participants, so that the accurate proportion calibration of the harmful substances in the food is realized, and the objectivity and the accuracy of data are ensured.
S300: screening the food harmful substance list according to the food harmful substance proportion list, and determining a to-be-detected harmful substance list, wherein the to-be-detected harmful substance list comprises harmful substance types and key detection components which correspond to one another one by one;
specifically, the list of harmful substances to be detected refers to the directionally detected harmful substances determined after screening the list of harmful substances of food, and the preferred screening process is as follows: by determining a preset proportion threshold: representing a preset minimum proportion to be detected, dividing a part of a list which is larger than or equal to a preset proportion threshold value in a food harmful substance proportion list, and setting the part as a list of harmful substances to be detected; the rest are set as a secondary detection list, namely, the significance and the urgency of the evidence detection are lower than those of the list of harmful substances to be detected. The values corresponding to the preset proportion threshold value can be directly compared in a list form, namely, the list on one side of the values can be divided, and compared with one-to-one comparison, the data processing efficiency is improved. The harmful substance type refers to the harmful substance type in a list of harmful substances to be detected; the key detection components refer to key detection components corresponding to the types of harmful substances one by one, and the key detection components are exemplarily shown as follows: key detection components corresponding to different types of pesticides, detection components corresponding to heavy metals and the like; the food detection instrument can be used for storing the types of the harmful substances and the key detection components in a one-to-one correspondence manner, waiting for later calling, and quickly determining the key detection components.
S400: matching a food detection instrument according to the type of the harmful substances and the key detection components, sampling the food to be detected, conveying the food to be detected to the food detection instrument, and generating detection feedback information;
in particular, the food detection apparatus refers to an apparatus for actually detecting harmful substances in food, including but not limited to: the detection instrument comprises an ion migration detection instrument, a metal organic framework detection instrument, an enhanced Raman scattering detection instrument and the like, detection data of the detection instruments are uploaded to a control terminal, the terminal is in communication connection with a food harmful substance directional detection system, when the types and key detection components of harmful substances are determined, the corresponding detection instrument can be determined, namely, samples with preset weight or preset volume can be taken from food to be detected in corresponding groups, and the food to be detected can be conveyed to the detection instrument for detection through a conveying device; the detection feedback information refers to information of characteristic detection data sent by the control terminal to the food harmful substance directional detection system when the detection instrument is uploaded to the control terminal after the detection of the detection instrument is completed, the actual proportion and content of harmful substances detected directionally can be determined through the detection data, the food hazard degree can be evaluated, and accurate reference data is provided for food safety evaluation.
S500: according to the detection feedback information, calibrating the characteristic value of the harmful substance list to be detected to generate a harmful substance characteristic matrix;
further, as shown in fig. 3, based on the characteristic value calibration of the to-be-detected harmful substance list according to the detection feedback information, a harmful substance characteristic matrix is generated, and step S500 includes the steps of:
s510: according to the detection feedback information, adjusting the corresponding proportion calibration information of the list of the harmful substances to be detected to generate a detection proportion calibration result;
s520: sequencing and adjusting the list of the harmful substances to be detected according to the detection proportion calibration result to generate a detected harmful substance list, wherein the detected harmful substance list has sequencing information;
s530: and setting the sequencing information and the detection proportion calibration result as binary characteristic values, calibrating the detected harmful substance list, and generating the harmful substance characteristic matrix.
Specifically, the detection ratio calibration result refers to a ratio calibration result obtained by adjusting the corresponding ratio calibration information of the harmful substance list to be detected according to the actual harmful substance ratio which is determined after detection and corresponds to the harmful substance list to be detected one by one, and is an actual ratio detection result; the detected harmful substance list refers to a result obtained by reordering the to-be-detected harmful substance list according to the detection proportion calibration result; and setting the sequencing information and the detection proportion calibration result as binary characteristic values, and calibrating the detected harmful substance list to further obtain harmful substance characteristic matrixes representing sequencing data of the detected harmful substance list and the detection proportion calibration result. The directional detection result of the food to be detected can be represented through the harmful substance characteristic matrix, the mathematical quantification of the detection result is realized, and an accurate data basis is provided for the subsequent evaluation of food safety.
Further, based on the setting of the sorting information and the detection ratio calibration result as binary eigenvalues, the detected harmful substance list is calibrated to generate the harmful substance characteristic matrix, and the previous step S530 includes the steps of:
s531: acquiring food detection standard data, wherein the food detection standard data comprise a harmful substance content threshold list and the detected harmful substance list in one-to-one correspondence;
s532: comparing the harmful substance content threshold list with the detected harmful substance list to generate abnormal harmful substance types and proportion deviation degrees;
s533: sorting the abnormal harmful substance types according to the proportion deviation degree to obtain an abnormal harmful substance sorting result;
s534: and setting the sequencing result of the abnormal harmful substances and the proportional calibration result corresponding to the types of the abnormal harmful substances as binary characteristic values, and generating the characteristic matrix of the harmful substances.
Specifically, the harmful substance feature matrix determination process is detailed as follows: the food detection standard data refers to the inspection standard specified by the relevant food detection department; the harmful substance content threshold list refers to a proportional content threshold which is extracted from food detection standard data and corresponds to the detected harmful substance list one by one; the abnormal harmful substance type refers to the detected harmful substances with the extracted proportional content being more than or equal to the harmful substance content threshold value by comparing the detected harmful substance list with the harmful substance content threshold value list one by one; the proportion deviation degree refers to the proportion deviation degree which corresponds to the abnormal harmful substance type one by one; according to the deviation degree, the abnormal harmful substances are sequenced from large to small to obtain sequencing results of the abnormal harmful substances, the sequencing results of the abnormal harmful substances and the proportion calibration results corresponding to the types of the abnormal harmful substances are set as binary characteristic values to generate a harmful substance characteristic matrix, and the harmful substances which do not meet the limit standard can be characterized through the harmful substance characteristic matrix:
if harmful substances which do not meet the limited standard appear, the oriented detection of the food to be detected is unqualified, and the danger level evaluation is needed to be carried out on the food to be detected, so that the subsequent processing treatment is facilitated; if harmful substances which do not meet the limited standard do not appear, the oriented detection safety degree of the food to be detected is higher, an oriented detection qualified instruction is generated, the food detection in the next step can be carried out, and the fine degree of the food harmful substance detection can be improved and the detection efficiency can be improved by preferentially detecting the harmful substances with possibly higher content.
S600: inputting the harmful substance characteristic matrix and the food type into a food hazard grade evaluation model to generate a food hazard grade;
specifically, the food hazard level evaluation model refers to an intelligent model for performing security evaluation on the food to be detected aiming at multiple harmful substances, preferably a decision tree model, and the training process is as follows: step 1: collecting historical data, including as input data: a plurality of groups of harmful substance characteristic matrixes and food types are used as a plurality of groups of damage level division identification data of output data; step 2: the method comprises the steps of dividing historical data into 10 proportions according to a first preset proportion, setting 8 proportions of historical data as training data, and setting second preset proportions, preferably 2 proportions of historical data as verification data, wherein the first preset proportion is larger than the second preset proportion; and step 3: and training the food hazard level evaluation model according to the training data, verifying the output accuracy of the food hazard level evaluation model through the verification data after the output is stable, and generating the food hazard level evaluation model if the output accuracy meets the requirement. The food hazard level can be accurately evaluated under the co-training of a large amount of historical data through the decision tree model.
S700: and when the food hazard level meets a first preset threshold value, generating an unqualified label to mark the food to be detected.
Specifically, the first preset threshold refers to a preset minimum hazard level of the food hazard level that is required to characterize severe hazards, as an example without limitation: preferably three levels, the first level: is dangerous; and (3) second grade: danger; and a third stage: and (4) common. The food to be detected is classified into different grades through the food hazard grade evaluation model evaluation data, the first preset threshold is the third grade, and when the food to be detected is classified into the first grade, the second grade or the third grade, the food to be detected is subjected to hazard grade identification through the unqualified label, so that the food can be conveniently processed in the next step. By marking the hazard level of the food to be detected, reference data is provided for the post-processing of unqualified food.
In summary, the method and the system for directionally detecting harmful substances in food provided by the embodiment of the application have the following technical effects:
1. the method adopts the steps of collecting basic information of the food to be detected, wherein the basic information comprises food state information and culture environment information; matching harmful substances according to the food state and the culture environment information, and determining a harmful substance list; screening the harmful substances according to the harmful substance list and the proportion thereof, and determining the harmful substances to be detected; matching a corresponding food detection instrument according to the type of the harmful substances to be detected and the key detection components, sampling and conveying the samples to the corresponding food detection instrument for detection to obtain detection feedback information; according to the technical scheme, the method comprises the steps of calibrating the characteristic value of a harmful substance list to be detected according to detection feedback information to obtain a harmful substance characteristic matrix, evaluating the damage level of the harmful substance characteristic matrix and the food type according to a food damage level evaluation model, identifying unqualified food, conducting directional investigation on the harmful substance according to the food state and the culture environment, determining the important harmful substance to be detected, preferentially detecting, conducting food safety evaluation, reducing detection dimensionality and full-automatic control, and achieving the technical effect of improving food safety detection efficiency and detection accuracy.
Example two
Based on the same inventive concept as the directional detection method for harmful substances in food in the foregoing embodiments, as shown in fig. 4, an embodiment of the present application provides a directional detection system for harmful substances in food, wherein the system is communicatively connected to a plurality of multi-type food detection apparatuses, and the directional detection system includes:
the information acquisition module 11: the method comprises the steps of acquiring basic information of food to be detected, wherein the basic information of the food to be detected comprises food state information and culture environment information;
the information matching module 12: the culture environment information is used for matching harmful substances with the food state information and the culture environment information to generate a food harmful substance list, wherein the food harmful substance list corresponds to the food harmful substance proportion list in a one-to-one manner;
the information screening module 13: the food harmful substance list is screened according to the food harmful substance proportion list, and the list of harmful substances to be detected is determined, wherein the list of harmful substances to be detected comprises harmful substance types and key detection components which correspond to each other one by one;
the food detection module 14: the food detection instrument is matched with the food detection instrument according to the type of the harmful substances and the key detection components, the food to be detected is sampled and conveyed to the food detection instrument, and detection feedback information is generated;
the characteristic calibration module 15: the characteristic value calibration is carried out on the harmful substance list to be detected according to the detection feedback information, and a harmful substance characteristic matrix is generated;
hazard evaluation module 16: the system is used for inputting the harmful substance characteristic matrix and the food type into a food hazard level evaluation model to generate a food hazard level;
the information identification module 17: and when the food hazard level meets a first preset threshold value, generating an unqualified label to mark the food to be detected.
Further, the information matching module further performs the following steps:
performing first preset feature extraction on the food state information to generate a state feature set;
performing second preset feature extraction on the culture environment information to generate an environment feature set;
inputting the food type into a harmful substance screening table, and matching all harmful substances;
carrying out proportion calibration on all harmful substances according to the state characteristic set and the environment characteristic set to generate proportion calibration results of all harmful substances;
and sequencing all harmful substances from large to small according to the proportion calibration result of all the harmful substances to generate the food harmful substance list.
Further, the information matching module further performs the following steps:
activating a proportion calibration database, wherein the proportion calibration database comprises a first calibration sub-library, a second calibration sub-library and an Nth calibration sub-library, and any two character libraries from the first calibration sub-library, the second calibration sub-library and the Nth calibration sub-library are in an information isolation state;
inputting the state feature set, the environment feature set, the substance types and all harmful substances into the first calibration sub-library and the second calibration sub-library in parallel until the Nth calibration sub-library, and generating a first calibration result and a second calibration result until the Nth calibration result;
and traversing all harmful substances according to the first calibration result, the second calibration result and the Nth calibration result and according to a preset proportion calibration rule to perform proportion calculation to generate a proportion calibration result of all harmful substances.
Further, the information matching module further performs the following steps:
traversing all the harmful substances according to the first calibration result, the second calibration result and the Nth calibration result to generate a first substance proportion calibration list, and traversing the second substance proportion calibration list and the Mth substance proportion calibration list;
obtaining a preset proportion calibration formula:
wherein eta is m For the m-th material ratio calibration result, x n Calibrating the value of the mth substance in the nth calibration sub-library;
and calculating the proportion calibration list of the first substance, the proportion calibration list of the second substance and the proportion calibration list of the Mth substance by using the preset proportion calibration formula to obtain the proportion calibration result of all the harmful substances.
Further, the feature calibration module further performs the following steps:
according to the detection feedback information, adjusting the corresponding proportion calibration information of the list of the harmful substances to be detected to generate a detection proportion calibration result;
sequencing and adjusting the list of the harmful substances to be detected according to the detection proportion calibration result to generate a detected harmful substance list, wherein the detected harmful substance list has sequencing information;
and setting the sequencing information and the detection proportion calibration result as binary characteristic values, calibrating the detected harmful substance list, and generating the harmful substance characteristic matrix.
Further, the feature calibration module further performs the following steps:
acquiring food detection standard data, wherein the food detection standard data comprise a harmful substance content threshold list and the detected harmful substance list in one-to-one correspondence;
comparing the harmful substance content threshold list with the detected harmful substance list to generate abnormal harmful substance types and proportion deviation degrees;
sorting the abnormal harmful substance types according to the proportion deviation degree to obtain an abnormal harmful substance sorting result;
and setting the sequencing result of the abnormal harmful substances and the proportional calibration result corresponding to the types of the abnormal harmful substances as binary characteristic values, and generating the characteristic matrix of the harmful substances.
Further, the hazard evaluation module further performs the following steps:
step 1: collecting historical data, including as input data: a plurality of groups of harmful substance characteristic matrixes and food types are used as a plurality of groups of damage level division identification data of output data;
step 2: setting the historical data of a first preset proportion as training data, and setting the historical data of a second preset proportion as verification data, wherein the first preset proportion is larger than the second preset proportion;
and step 3: and training the food hazard level evaluation model according to the training data pair, verifying the output accuracy of the food hazard level evaluation model through the verification data after the output is stable, and generating the food hazard level evaluation model if the output accuracy is satisfied.
In the embodiment of the present application, through connecting multiple types of food detection instrument terminals 001 and food detection modules 14 in a communication manner, interactive processing of food detection feedback information is performed, and virtual function modules are set in software units executed by any hardware and processor: the system comprises an information acquisition module 11, an information matching module 12, an information screening module 13, a food detection module 14, a characteristic calibration module 15, a hazard evaluation module 16 and an information identification module 17; on a storage medium, such as, for example: RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, a removable disk, a CD-ROM, or any other form of storage medium in the art, in which the steps of any one of the methods of the first embodiment are stored, wherein by connecting the storage medium to a processor, the optional processor and storage medium may be provided in an ASIC, which may be provided in a terminal, programs corresponding to the steps of the respective methods may be identified by a plurality of virtual function modules in the processor, and corresponding functions of the steps of any one of the methods of the first embodiment may be implemented. In the alternative, the processor and the storage medium may reside in different components within the terminal.
The embodiment of the application provides a method and a system for directionally detecting harmful substances in food. The method adopts the steps of collecting basic information of the food to be detected, wherein the basic information comprises food state information and culture environment information; matching harmful substances according to the food state and the culture environment information, and determining a harmful substance list; screening the harmful substances according to the harmful substance list and the proportion thereof, and determining the harmful substances to be detected; matching a corresponding food detection instrument according to the type of the harmful substances to be detected and the key detection components, sampling and conveying the samples to the corresponding food detection instrument for detection to obtain detection feedback information; according to the technical scheme, the method comprises the steps of calibrating the characteristic value of a harmful substance list to be detected according to detection feedback information to obtain a harmful substance characteristic matrix, evaluating the damage level of the harmful substance characteristic matrix and the food type according to a food damage level evaluation model, identifying unqualified food, conducting directional investigation on the harmful substance according to the food state and the culture environment, determining the important harmful substance to be detected, preferentially detecting, conducting food safety evaluation, reducing detection dimensionality and full-automatic control, and achieving the technical effect of improving food safety detection efficiency and detection accuracy.
Although the present application has been described in conjunction with specific features and embodiments thereof, it will be evident that various modifications and combinations can be made thereto without departing from the spirit and scope of the application. Accordingly, the specification and figures are merely exemplary of the application as defined in the appended claims and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of the application. It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and its equivalent technology, it is intended that the present application include such modifications and variations.
Claims (8)
1. A method for directionally detecting harmful substances in food, which is applied to a system for directionally detecting the harmful substances in the food, wherein the system is in communication connection with a plurality of multi-type food detection instruments, and the method comprises the following steps:
acquiring basic information of food to be detected, wherein the basic information of the food to be detected comprises food state information and culture environment information;
matching harmful substances with the food state information and the culture environment information to generate a food harmful substance list, wherein the food harmful substance list corresponds to the food harmful substance proportion list in a one-to-one manner;
screening the food harmful substance list according to the food harmful substance proportion list, and determining the list of harmful substances to be detected, wherein the list of harmful substances to be detected comprises harmful substance types and key detection components which correspond one to one;
matching a food detection instrument according to the type of the harmful substances and the key detection components, sampling the food to be detected, conveying the food to be detected to the food detection instrument, and generating detection feedback information;
calibrating the characteristic value of the harmful substance list to be detected according to the detection feedback information to generate a harmful substance characteristic matrix;
inputting the harmful substance characteristic matrix and the food type into a food hazard grade evaluation model to generate a food hazard grade;
and when the food hazard level meets a first preset threshold value, generating an unqualified label to mark the food to be detected.
2. The method of claim 1, wherein said matching of said food status information and said cultivation environment information with a harmful substance, generating a list of food harmful substances, comprises:
performing first preset feature extraction on the food state information to generate a state feature set;
performing second preset feature extraction on the culture environment information to generate an environment feature set;
inputting the food types into a harmful substance screening table, and matching all harmful substances;
carrying out proportion calibration on all harmful substances according to the state feature set and the environment feature set to generate proportion calibration results of all harmful substances;
and sequencing all harmful substances from large to small according to the proportion calibration result of all the harmful substances to generate the food harmful substance list.
3. The method of claim 2, wherein the scaling the total pollutant according to the state feature set and the environmental feature set to generate a total pollutant scaling result comprises:
activating a proportion calibration database, wherein the proportion calibration database comprises a first calibration sub-library, a second calibration sub-library and an Nth calibration sub-library, and any two character libraries from the first calibration sub-library, the second calibration sub-library and the Nth calibration sub-library are in an information isolation state;
inputting the state feature set, the environment feature set, the substance types and all harmful substances into the first calibration sub-library and the second calibration sub-library in parallel until the Nth calibration sub-library, and generating a first calibration result and a second calibration result until the Nth calibration result;
and traversing all harmful substances according to the first calibration result, the second calibration result and the Nth calibration result and according to a preset proportion calibration rule to perform proportion calculation to generate a proportion calibration result of all harmful substances.
4. The method of claim 3, wherein the preset scaling rule comprises:
traversing all the harmful substances according to the first calibration result, the second calibration result and the Nth calibration result to generate a first substance proportion calibration list, and traversing the second substance proportion calibration list and the Mth substance proportion calibration list;
obtaining a preset proportion calibration formula:
wherein eta is m Is the m substance proportion scaleDetermining the result, x n Calibrating the value of the mth substance in the nth calibration sub-library;
and calculating the proportion calibration list of the first substance, the proportion calibration list of the second substance and the proportion calibration list of the Mth substance by using the preset proportion calibration formula to obtain the proportion calibration result of all the harmful substances.
5. The method of claim 1, wherein the performing characteristic value calibration on the list of harmful substances to be detected according to the detection feedback information to generate a harmful substance characteristic matrix comprises:
according to the detection feedback information, adjusting the corresponding proportion calibration information of the list of the harmful substances to be detected to generate a detection proportion calibration result;
sequencing and adjusting the list of the harmful substances to be detected according to the detection proportion calibration result to generate a detected harmful substance list, wherein the detected harmful substance list has sequencing information;
and setting the sequencing information and the detection proportion calibration result as binary characteristic values, calibrating the detected harmful substance list, and generating the harmful substance characteristic matrix.
6. The method of claim 5, wherein the setting the sorting information and the detection ratio calibration result as binary eigenvalues, calibrating the list of detected harmful substances, and generating the harmful substance feature matrix comprises:
acquiring food detection standard data, wherein the food detection standard data comprise a harmful substance content threshold list and the detected harmful substance list in one-to-one correspondence;
comparing the harmful substance content threshold list with the detected harmful substance list to generate abnormal harmful substance types and proportion deviation degrees;
sorting the abnormal harmful substance types according to the proportion deviation degree to obtain an abnormal harmful substance sorting result;
and setting the sequencing result of the abnormal harmful substances and the proportional calibration result corresponding to the types of the abnormal harmful substances as binary characteristic values, and generating the characteristic matrix of the harmful substances.
7. The method of claim 1, wherein the food hazard level assessment model is a decision tree model trained by:
step 1: collecting historical data, including as input data: a plurality of groups of harmful substance characteristic matrixes and food types are used as a plurality of groups of damage level division identification data of output data;
step 2: setting the historical data of a first preset proportion as training data, and setting the historical data of a second preset proportion as verification data, wherein the first preset proportion is larger than the second preset proportion;
and 3, step 3: and training the food hazard level evaluation model according to the training data pair, verifying the output accuracy of the food hazard level evaluation model through the verification data after the output is stable, and generating the food hazard level evaluation model if the output accuracy meets the requirement.
8. A system for directionally detecting hazardous materials in food, said system communicatively coupled to a plurality of multi-type food detection instruments, comprising:
the information acquisition module: the food basic information detection system is used for acquiring basic information of food to be detected, wherein the basic information of the food to be detected comprises food state information and culture environment information;
an information matching module: the culture environment information is used for matching harmful substances with the food state information and the culture environment information to generate a food harmful substance list, wherein the food harmful substance list corresponds to the food harmful substance proportion list in a one-to-one manner;
the information screening module: the food harmful substance list is screened according to the food harmful substance proportion list, and the list of harmful substances to be detected is determined, wherein the list of harmful substances to be detected comprises harmful substance types and key detection components which correspond to each other one by one;
the food detection module comprises: the food detection instrument is matched with the food detection instrument according to the type of the harmful substances and the key detection components, the food to be detected is sampled and conveyed to the food detection instrument, and detection feedback information is generated;
a characteristic calibration module: the characteristic value calibration is carried out on the harmful substance list to be detected according to the detection feedback information, and a harmful substance characteristic matrix is generated;
a hazard evaluation module: the system is used for inputting the harmful substance characteristic matrix and the food type into a food hazard level evaluation model to generate a food hazard level;
an information identification module: and when the food hazard level meets a first preset threshold value, generating an unqualified label to mark the food to be detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210642769.8A CN115034303A (en) | 2022-06-08 | 2022-06-08 | Directional detection method and system for harmful substances in food |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210642769.8A CN115034303A (en) | 2022-06-08 | 2022-06-08 | Directional detection method and system for harmful substances in food |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115034303A true CN115034303A (en) | 2022-09-09 |
Family
ID=83123665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210642769.8A Withdrawn CN115034303A (en) | 2022-06-08 | 2022-06-08 | Directional detection method and system for harmful substances in food |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115034303A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115358631A (en) * | 2022-09-21 | 2022-11-18 | 张家港市艾尔环保工程有限公司 | Waste gas directional treatment method and system based on harmful substance detection |
| CN116542565A (en) * | 2023-05-09 | 2023-08-04 | 上海依蕴宠物用品有限公司 | Pet puffed food management method and system based on proportion detection technology |
-
2022
- 2022-06-08 CN CN202210642769.8A patent/CN115034303A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115358631A (en) * | 2022-09-21 | 2022-11-18 | 张家港市艾尔环保工程有限公司 | Waste gas directional treatment method and system based on harmful substance detection |
| CN115358631B (en) * | 2022-09-21 | 2023-09-05 | 张家港市艾尔环保工程有限公司 | Method and system for directionally treating waste gas based on harmful substance detection |
| CN116542565A (en) * | 2023-05-09 | 2023-08-04 | 上海依蕴宠物用品有限公司 | Pet puffed food management method and system based on proportion detection technology |
| CN116542565B (en) * | 2023-05-09 | 2024-04-16 | 上海依蕴宠物用品有限公司 | Pet puffed food management method and system based on proportion detection technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115034303A (en) | Directional detection method and system for harmful substances in food | |
| TU et al. | Selection for high quality pepper seeds by machine vision and classifiers | |
| Al-Amery et al. | Near-infrared spectroscopy used to predict soybean seed germination and vigour | |
| Lien et al. | Non-destructive impact test for assessment of tomato maturity | |
| CN109490306B (en) | Pork freshness detection method based on color and smell data fusion | |
| CN107944213B (en) | PMF online source analysis method, PMF online source analysis system, terminal device and computer readable storage medium | |
| CN109064039B (en) | Farmland soil health evaluation method | |
| CN105044022B (en) | A kind of method and application based on near-infrared spectrum technique Fast nondestructive evaluation wheat hardness | |
| CN115453064B (en) | Fine particulate matter air pollution cause analysis method and system | |
| CN109557080A (en) | A kind of spectroscopic data homing method based on machine learning | |
| Phate et al. | Classification and weighing of sweet lime (Citrus limetta) for packaging using computer vision system | |
| CN111160667B (en) | Method and device for improving robustness of food safety prediction model | |
| CN115860581A (en) | Method, device, equipment and storage medium for evaluating suitability of crop variety | |
| CN116433218A (en) | Self-organizing mapping clustering-based mine mechanical equipment online health assessment method | |
| CN104316492A (en) | Method for near-infrared spectrum measurement of protein content in potato tuber | |
| CN112651173A (en) | Agricultural product quality nondestructive testing method based on cross-domain spectral information and generalizable system | |
| CN114972234B (en) | Edible fungus quality monitoring method and system | |
| CN116759014A (en) | Random forest-based gas type and concentration prediction method, system and device | |
| CN114778485B (en) | Variety identification method and system based on near infrared spectrum and attention mechanism network | |
| Walsh et al. | Sampling and statistics in assessment of fresh produce | |
| CN106338526B (en) | A kind of correction model and detection method based on microwave moisture instrument | |
| Araújo et al. | Appropriate search techniques to estimate Weibull function parameters in a Pinus spp. plantation | |
| CN111967799B (en) | Method for identifying materials and process problems of circulator by sticking integrated parameter table | |
| Dujak et al. | Comprehensive morphometric analysis of apple fruits and weighted class assignation using machine learning | |
| CN117611927B (en) | Method and device for detecting rice mixing rate |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220909 |