CN115452892A - Food pesticide residue safety detection method, system and medium - Google Patents
Food pesticide residue safety detection method, system and medium Download PDFInfo
- Publication number
- CN115452892A CN115452892A CN202211196869.9A CN202211196869A CN115452892A CN 115452892 A CN115452892 A CN 115452892A CN 202211196869 A CN202211196869 A CN 202211196869A CN 115452892 A CN115452892 A CN 115452892A
- Authority
- CN
- China
- Prior art keywords
- result
- odor
- food
- type
- information
- 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.)
- Pending
Links
- 235000013305 food Nutrition 0.000 title claims abstract description 86
- 239000000447 pesticide residue Substances 0.000 title claims abstract description 82
- 238000001514 detection method Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 claims abstract description 57
- 230000002159 abnormal effect Effects 0.000 claims abstract description 52
- 239000000575 pesticide Substances 0.000 claims description 51
- 238000007781 pre-processing Methods 0.000 claims description 44
- 230000004044 response Effects 0.000 claims description 22
- 201000010099 disease Diseases 0.000 claims description 13
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000010586 diagram Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000004913 activation Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 8
- 230000009471 action Effects 0.000 description 4
- 239000003814 drug Substances 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 241000607479 Yersinia pestis Species 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000004659 sterilization and disinfection Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000011282 treatment Methods 0.000 description 2
- 206010059866 Drug resistance Diseases 0.000 description 1
- 206010016952 Food poisoning Diseases 0.000 description 1
- 208000019331 Foodborne disease Diseases 0.000 description 1
- 241000238631 Hexapoda Species 0.000 description 1
- 208000005374 Poisoning Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000000361 pesticidal effect Effects 0.000 description 1
- 231100000572 poisoning Toxicity 0.000 description 1
- 230000000607 poisoning effect Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90344—Query processing by using string matching techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9038—Presentation of query results
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Electrochemistry (AREA)
- Health & Medical Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)
Abstract
The invention relates to a food pesticide residue safety detection method, a system and a medium, belonging to the technical field of food pesticide residue detection, wherein the method comprises the steps of obtaining crop type information of a current storage area, and searching according to the crop type to obtain a search result; and matching according to the identification result and the retrieval result to obtain a matching result, determining an abnormal position node of the current food based on the matching result, and displaying the abnormal position node on the food detection terminal in a preset mode. The method can quickly detect crops with more pesticide residues in the crop storage, so that the position nodes of the areas where the crops with serious pesticide residues are located can be detected, and related personnel are informed to correct the crops.
Description
Technical Field
The invention relates to the technical field of food pesticide residue detection, in particular to a food pesticide residue safety detection method, a system and a medium.
Background
China is a country mainly using agriculture, and the problem of agricultural product safety is always a focus and a hotspot concerned by social public. Many agricultural product growers are vague in pesticide use boundary points and do not pay attention to the problem of pesticide residue. On one hand, because of lack of strict guidance of related professionals on the using process of the pesticide, basic characteristics and prevention and control functions of the pesticide are not clear, and the pesticide is used in a blind mixing mode, the pesticide effect of the pesticide is reduced, and some pests quickly generate drug resistance. Most agricultural product growers often cannot clearly prevent and treat the objects, cannot correctly select medicaments and cannot prescribe medicaments according to symptoms. Even a small number of planters can use the medicine randomly no matter whether the weather is good or bad or the time is long, so that the prevention and treatment effect is poor, and sometimes even the medicine harm or the poisoning phenomenon of personnel occurs. On the other hand, some agricultural product growers are low in quality, even though they are aware of the harm caused by the overproof pesticide residues, the pesticide residue of the agricultural product has direct influence on the health of people while the agricultural product is prevented and treated by the double-edged sword, so that people pay attention to the pesticide residue left when the agricultural product is planted, and the agricultural product supply gradually develops towards green ecology and no pollution. At present, pesticide residues are mainly due to weak safety consciousness of agricultural product growers, and the influence of the overproof pesticide residues on the health of people is not deeply understood. The current agricultural product sales is mainly divided into an online mode and an offline mode, the supervision also has leaks in the problems of pesticide sales and agricultural product detection, the food safety of a part of agricultural products cannot be guaranteed, and the food poisoning phenomenon caused by the overproof pesticide residues is endless, so that the public safety of the food is seriously influenced.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a method, a system and a medium for safely detecting pesticide residues in food.
In order to achieve the purpose, the invention adopts the technical scheme that:
the invention provides a food pesticide residue safety detection method in a first aspect, which comprises the following steps:
acquiring gas electric signal information of a current area within preset time through an array type odor sensor, and preprocessing the gas electric signal information to obtain a preprocessing result;
establishing an odor identification model, identifying the preprocessing result through the odor identification model to obtain a related odor type, and generating an identification result according to the related type;
obtaining crop category information of a current storage area, and searching according to the crop category to obtain a search result;
and matching according to the identification result and the retrieval result to obtain a matching result, determining an abnormal position node of the current food based on the matching result, and displaying the abnormal position node on a food detection terminal according to a preset mode.
Further, in a preferred embodiment of the present invention, an odor recognition model is established, and the preprocessing result is recognized by the odor recognition model to obtain a related odor type, which specifically includes the following steps:
establishing a smell recognition model based on a neural network, setting initialization parameters, acquiring smell sample data from a large database, training the smell recognition model through the smell sample data, adjusting model parameters and reserving optimal model parameters;
extracting features of the preprocessing result to obtain an odor feature matrix, and taking the odor feature matrix as an input signal;
inputting the input signal into a neural network, adopting a linear rectification function as an activation function after convolutional layer operation, and classifying the odor types through a Softmax classifier to obtain the odor types of related classes and the odor types of unrelated classes;
and if the related type of the odor type exists, taking the related type of the odor type as the related odor type, and generating an identification result according to the related odor type.
Further, in a preferred embodiment of the present invention, the method for obtaining the crop type information of the current storage area and searching according to the crop type to obtain the search result specifically includes the following steps:
judging whether the identification result is larger than a preset identification result or not, and if the identification result is larger than the preset identification result, acquiring crop category information in the current storage area;
acquiring disease condition type information under various crops through a big data network, and acquiring pesticide use types under various disease condition type information according to the disease condition type information;
building a database, and importing the pesticide use types under the various disease condition type information into the database to obtain a trained database;
and importing the crop category information in the current storage area into the trained database to obtain the pesticide use type of the crop in the current storage area, and outputting the pesticide use type as a retrieval result.
Further, in a preferred embodiment of the present invention, matching is performed according to the recognition result and the search result to obtain a matching result, which specifically includes the following steps:
pesticide character string information of a current identification result is obtained, and first character string information is generated according to the pesticide character string information of the current identification result;
acquiring a plurality of character string information of a current retrieval result, and generating a plurality of second character string information according to the plurality of character string information of the current retrieval result;
comparing the first character string information with the second character string information one by one to obtain a plurality of similarity degrees, and judging whether the similarity degrees are greater than a preset similarity degree;
and if the similarity is greater than the preset similarity, taking the crops corresponding to the pesticide type of the second character string information as abnormal pesticide residue nodes, and outputting the abnormal pesticide residue nodes as matching results.
Further, in a preferred embodiment of the present invention, the determining of the abnormal position node of the current food based on the matching result and displaying the abnormal position node on the food detection terminal according to a preset mode specifically includes the following steps:
acquiring a plane structure schematic diagram of a current storage area, and acquiring storage area position nodes of each food according to the plane structure schematic diagram;
acquiring character string information of the storage area position nodes of each food, and performing secondary matching on the character string information of the storage area position nodes of each food and the matching result to obtain the similarity of the secondary matching result;
acquiring a position node where the character string information with the similarity of the secondary matching result larger than the preset similarity of the secondary matching result is located;
and taking the position node where the character string information with the secondary matching result similarity larger than the preset secondary matching result similarity is located as an abnormal position node, and displaying the abnormal position node on the food detection terminal according to a preset mode.
Further, in a preferred embodiment of the present invention, the method for acquiring the electrical signal information of the gas in the current area within the preset time by the array type odor sensor and preprocessing the electrical signal information of the gas to obtain the preprocessing result specifically includes the following steps:
acquiring gas electric signal information of a current area at preset time through an array type odor sensor, and calculating the relative deviation of N sample data within the preset time through an RSD method;
judging whether the relative deviation is greater than a preset relative deviation or not, and if the relative deviation is greater than the preset relative deviation, establishing a gas sensor response data curve based on the gas electric signal information of the current area at preset time;
performing smoothness processing on the response data curve of the gas sensor through a filter to obtain a processed response data curve;
and acquiring gas data information of the processed response data curve in a stable stage, and outputting the gas data information as a preprocessing result.
The invention provides a food pesticide residue safety detection system, which comprises a memory and a processor, wherein the memory comprises a food pesticide residue safety detection method program, and when the food pesticide residue safety detection method program is executed by the processor, the following steps are realized:
acquiring gas electric signal information of a current area within preset time through an array type odor sensor, and preprocessing the gas electric signal information to obtain a preprocessing result;
establishing an odor identification model, identifying the preprocessing result through the odor identification model to obtain a related odor type, and generating an identification result according to the related type;
obtaining crop category information of a current storage area, and searching according to the crop category to obtain a search result;
and matching according to the identification result and the retrieval result to obtain a matching result, determining an abnormal position node of the current food based on the matching result, and displaying the abnormal position node on a food detection terminal in a preset mode.
Further, in a preferred embodiment of the present invention, the creating a smell recognition model, and recognizing the preprocessing result through the smell recognition model to obtain the related smell type specifically includes the following steps:
establishing a smell recognition model based on a neural network, setting initialization parameters, acquiring smell sample data from a large database, training the smell recognition model through the smell sample data, adjusting model parameters and reserving optimal model parameters;
extracting features of the preprocessing result to obtain an odor feature matrix, and taking the odor feature matrix as an input signal;
inputting the input signal into a neural network, adopting a linear rectification function as an activation function after convolutional layer operation, and classifying the odor types through a Softmax classifier to obtain the odor types of related classes and the odor types of unrelated classes;
and if the related type of the odor type exists, taking the related type of the odor type as the related odor type, and generating an identification result according to the related odor type.
Further, in a preferred embodiment of the present invention, matching is performed according to the recognition result and the search result to obtain a matching result, which specifically includes the following steps:
pesticide character string information of a current identification result is obtained, and first character string information is generated according to the pesticide character string information of the current identification result;
acquiring a plurality of pieces of character string information of a current retrieval result, and generating a plurality of pieces of second character string information according to the plurality of pieces of character string information of the current retrieval result;
comparing the first character string information with the second character string information one by one to obtain a plurality of similarity degrees, and judging whether the similarity degrees are greater than a preset similarity degree;
and if the similarity is greater than the preset similarity, taking the crops corresponding to the pesticide type of the second character string information as abnormal pesticide residue nodes, and outputting the abnormal pesticide residue nodes as matching results.
The third aspect of the invention provides a computer-readable storage medium, which comprises a food pesticide residue safety detection method program, and when the food pesticide residue safety detection method program is executed by a processor, the steps of any one of the food pesticide residue safety detection methods are realized.
The invention solves the defects in the background technology, and has the following beneficial effects:
the method comprises the steps of acquiring gas electric signal information of a current area within preset time through an array type odor sensor, and preprocessing the gas electric signal information to obtain a preprocessing result; establishing an odor identification model, identifying the preprocessing result through the odor identification model to obtain a related odor type, and generating an identification result according to the related type; acquiring crop type information of a current storage area, and searching according to the crop type to obtain a search result; and matching according to the identification result and the retrieval result to obtain a matching result, determining an abnormal position node of the current food based on the matching result, and displaying the abnormal position node on a food detection terminal according to a preset mode. The method can quickly detect crops with more pesticide residues in the crop storage, so that the position nodes of the areas where the crops with serious pesticide residues are located can be detected, and related personnel are informed to modify the crops.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings of the embodiments can be obtained according to the drawings without creative efforts.
FIG. 1 shows an overall method flow chart of a food pesticide residue safety detection method;
FIG. 2 shows a flow chart of a method of obtaining a search result;
FIG. 3 shows a flow chart of a method of obtaining a matching result;
fig. 4 shows a system block diagram of a food pesticide residue safety detection system.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
FIG. 1 shows an overall method flow chart of a food pesticide residue safety detection method;
the invention provides a food pesticide residue safety detection method in a first aspect, which comprises the following steps:
s102, acquiring gas electric signal information of a current area within preset time through an array type odor sensor, and preprocessing the gas electric signal information to obtain a preprocessing result;
s104, establishing an odor identification model, identifying the preprocessing result through the odor identification model to obtain a related odor type, and generating an identification result according to the related type;
s106, acquiring crop type information of the current storage area, and searching according to the crop type to obtain a search result;
and S108, matching according to the identification result and the retrieval result to obtain a matching result, determining an abnormal position node of the current food based on the matching result, and displaying the abnormal position node on a food detection terminal in a preset mode.
The method can quickly detect crops with more pesticide residues in the crop storage, so that the position nodes of the areas where the crops with serious pesticide residues are located can be detected, and related personnel are informed to modify the crops; by the method, the position node with pesticide residue can be quickly detected, the efficiency of replacing manpower is higher, the export safety of food is improved, and the safety of consumers is ensured to a certain extent.
Further, in a preferred embodiment of the present invention, the creating a smell recognition model, and recognizing the preprocessing result through the smell recognition model to obtain the related smell type specifically includes the following steps:
establishing a smell recognition model based on a neural network, setting initialization parameters, acquiring smell sample data from a large database, training the smell recognition model through the smell sample data, adjusting model parameters and reserving optimal model parameters;
extracting features of the preprocessing result to obtain an odor feature matrix, and taking the odor feature matrix as an input signal;
inputting the input signal into a neural network, adopting a linear rectification function as an activation function after convolutional layer operation, and classifying the odor types through a Softmax classifier to obtain the odor types of related classes and the odor types of unrelated classes;
and if the related type of the odor type exists, taking the related type of the odor type as the related odor type, and generating a recognition result according to the related odor type.
The identification result comprises the type of the residual pesticide, the concentration information of the residual pesticide measured by the gas sensor and the like, pesticide smell information in a crop storage area can be identified through the method, most of crops are stored in a cold storage warehouse for refrigeration after being picked, so that the preservation of the crops can be facilitated, the storage areas of different crops are arranged in the cold storage warehouse, when a large amount of pesticide residues exist in the crops, a certain amount of pesticide residues exist in the air in the cold storage warehouse, the air can be monitored through the gas sensor, and when the content of the pesticide residues in the air is greater than the preset content (the identification result is greater than the preset identification result), unqualified crop storage nodes can be rapidly detected.
FIG. 2 shows a flow chart of a method of obtaining a search result;
further, in a preferred embodiment of the present invention, the obtaining of the crop category information of the current storage area and the searching according to the crop category to obtain the search result specifically includes the following steps:
s202, judging whether the identification result is larger than a preset identification result or not, and if the identification result is larger than the preset identification result, acquiring the crop type information in the current storage area;
s204, acquiring disease condition type information of various crops through a big data network, and acquiring pesticide use types under various disease condition type information according to the disease condition type information;
s206, constructing a database, and importing the database according to the pesticide use types under the various disease condition type information to obtain a trained database;
and S208, importing the crop type information in the current storage area into the trained database to obtain the pesticide use type of the crop in the current storage area, and outputting the pesticide use type as a retrieval result.
It should be noted that, because a plurality of types of crops are stored in the current food storage area, and the types of diseases or insect pests of each type of crops are different in the growth stage, so that the types of pesticides used by various crops are substantially different or the same parts may exist.
FIG. 3 shows a flow chart of a method of obtaining a matching result;
further, in a preferred embodiment of the present invention, matching is performed according to the recognition result and the search result to obtain a matching result, which specifically includes the following steps:
s302, acquiring pesticide character string information of a current recognition result, and generating first character string information according to the pesticide character string information of the current recognition result;
s304, acquiring a plurality of character string information of the current retrieval result, and generating a plurality of second character string information according to the plurality of character string information of the current retrieval result;
s306, comparing the first character string information with the second character string information one by one to obtain a plurality of similarities, and judging whether the similarities are greater than a preset similarity or not;
and S308, if the similarity is greater than the preset similarity, taking the crop corresponding to the pesticide type of the second character string information as an abnormal pesticide residue node, and outputting the abnormal pesticide residue node as a matching result.
It should be noted that crops or foods with serious pesticide residues can be rapidly detected by the method. The preset similarity is set to be 100%, a similarity can be obtained through comparison of the character strings, and when the similarity is larger than the preset similarity, crops corresponding to the pesticide type of the second character string information are used as abnormal pesticide residue nodes.
Further, in a preferred embodiment of the present invention, the determining of the abnormal position node of the current food based on the matching result and displaying the abnormal position node on the food detection terminal according to a preset mode specifically includes the following steps:
acquiring a plane structure schematic diagram of a current storage area, and acquiring storage area position nodes of each food according to the plane structure schematic diagram;
acquiring character string information of the storage area position nodes of each food, and performing secondary matching on the character string information of the storage area position nodes of each food and the matching result to obtain the similarity of the secondary matching result;
acquiring a position node where the character string information with the similarity of the secondary matching result larger than the preset similarity of the secondary matching result is located;
and taking the position node where the character string information with the secondary matching result similarity larger than the preset secondary matching result similarity is located as an abnormal position node, and displaying the abnormal position node on the food detection terminal according to a preset mode.
It should be noted that, by the method, the abnormal position node of the crop with the excessive pesticide residue in the current storage area can be quickly detected, so that the related staff is informed to further process the crop with the excessive pesticide residue. And the similarity of the preset secondary matching result is 100%, and when the similarity of the secondary matching result is greater than the similarity of the preset secondary matching result, the position node where the character string information is located is used as an abnormal position node. The plan structure schematic diagram is a plan structure schematic diagram of a placement area of each crop set by the system at the beginning.
Further, in a preferred embodiment of the present invention, the method for obtaining the electrical signal information of the gas in the current area within the preset time by the array type odor sensor and preprocessing the electrical signal information of the gas to obtain the preprocessing result specifically includes the following steps:
acquiring gas electric signal information of a current area at preset time through an array type odor sensor, and calculating the relative deviation of N sample data within the preset time through an RSD method;
judging whether the relative deviation is greater than a preset relative deviation or not, and if the relative deviation is greater than the preset relative deviation, establishing a gas sensor response data curve based on the gas electric signal information of the current area at preset time;
performing smoothness processing on the response data curve of the gas sensor through a filter to obtain a processed response data curve;
and acquiring gas data information of the processed response data curve in a stable stage, and outputting the gas data information as a preprocessing result.
It should be noted that, in order to allow the program to intelligently determine whether the steady state phase is reached, the RSD (relative standard deviation) method is used to determine whether the response of the gas sensor is stable. The relative standard deviation of the data for N sample points over a continuous period of time (e.g., 30 seconds) is calculated and if sufficiently less than a set threshold (e.g., 10%), the response curve of the sensor is deemed to be stable. Each time a new sample of data arrives, it is recalculated. The steady state phase is considered to have been reached when the response curves of the n sensors all have reached steady state at the same time. Therefore, the gas signal acquired by the gas sensor can be more reliable by the method.
In addition, the method can also comprise the following steps:
acquiring the pesticide use type of crops in the current storage area, and judging whether the pesticide use type of the crops in the current storage area has crops using the same pesticide;
if the pesticide using type of the crop in the current storage area is the crop using the same pesticide, acquiring a pesticide using and growing stage corresponding to the crop through a big data network;
judging whether the using growth stage is a preset growth stage or not, and if the using growth stage is the preset growth stage, taking the current crop as an abnormal pesticide residue node;
and if the growth stage is not the preset growth stage, taking the current crop as a normal node.
It should be noted that in the detection process, the same pesticide application condition may exist in each growth stage of two different crops, and the pesticide is not suitable for the early stage application of some crops and is suitable for the later stage application of the growth stage of the crops. When the situation occurs, whether the using growth stage is a preset growth stage or not is judged, and if the growth stage is the preset growth stage, the crop is an abnormal pesticide residue node. If some pesticides can be used only at the initial stage of crops, the pesticides are not suitable for later use; if the growth stage is not the preset growth stage, the current crop is used as a normal node, and the detection can be more reasonable through the method.
In addition, the method can also comprise the following steps:
acquiring flow information of a current abnormal pesticide residue node, and retrieving working information in the flow information;
judging whether the current working information has a vacancy condition, and if the working information has the vacancy condition, acquiring a process node where the working information is located;
obtaining the working information of the current process node according to the process node, and obtaining the position node of the current abnormal pesticide residue node;
and displaying the working information of the current flow node and the position node of the current abnormal pesticide residue node on a food detection terminal according to a preset mode.
It should be noted that the process information can be understood that the crops need to be transported to a designated area for storage after being subjected to a series of treatments, such as cleaning action, disinfection action and the like, and the working information can be whether the crops need to be subjected to the cleaning action and the disinfection action.
Fig. 4 shows a system block diagram of a food pesticide residue safety detection system.
The invention provides a food pesticide residue safety detection system, which comprises a memory 41 and a processor 62, wherein the memory 41 comprises a food pesticide residue safety detection method program, and when the food pesticide residue safety detection method program is executed by the processor 62, the following steps are realized:
acquiring gas electric signal information of a current area within preset time through an array type odor sensor, and preprocessing the gas electric signal information to obtain a preprocessing result;
establishing an odor identification model, identifying the preprocessing result through the odor identification model to obtain a related odor type, and generating an identification result according to the related type;
obtaining crop category information of a current storage area, and searching according to the crop category to obtain a search result;
and matching according to the identification result and the retrieval result to obtain a matching result, determining an abnormal position node of the current food based on the matching result, and displaying the abnormal position node on a food detection terminal in a preset mode.
The method can quickly detect crops with more pesticide residues in the crop storage, so that the position nodes of the areas where the crops with serious pesticide residues are located can be detected, and related personnel are informed to modify the crops; by the method, the position node with pesticide residue can be quickly detected, the efficiency of replacing manpower is higher, the export safety of food is improved, and the safety of consumers is ensured to a certain extent.
Further, in a preferred embodiment of the present invention, the creating a smell recognition model, and recognizing the preprocessing result through the smell recognition model to obtain the related smell type specifically includes the following steps:
establishing a smell recognition model based on a neural network, setting initialization parameters, acquiring smell sample data from a large database, training the smell recognition model through the smell sample data, adjusting model parameters and reserving optimal model parameters;
extracting features of the preprocessing result to obtain an odor feature matrix, and taking the odor feature matrix as an input signal;
inputting the input signal into a neural network, after convolution layer operation, adopting a linear rectification function as an activation function, and classifying the odor types through a Softmax classifier to obtain the odor types of related classes and the odor types of unrelated classes;
and if the related type of the odor type exists, taking the related type of the odor type as the related odor type, and generating a recognition result according to the related odor type.
Further, in a preferred embodiment of the present invention, matching is performed according to the recognition result and the search result to obtain a matching result, which specifically includes the following steps:
pesticide character string information of a current identification result is obtained, and first character string information is generated according to the pesticide character string information of the current identification result;
acquiring a plurality of character string information of a current retrieval result, and generating a plurality of second character string information according to the plurality of character string information of the current retrieval result;
comparing the first character string information with the second character string information one by one to obtain a plurality of similarity degrees, and judging whether the similarity degrees are greater than a preset similarity degree;
and if the similarity is greater than the preset similarity, taking the crops corresponding to the pesticide type of the second character string information as abnormal pesticide residue nodes, and outputting the abnormal pesticide residue nodes as matching results.
Further, in a preferred embodiment of the present invention, the determining of the abnormal position node of the current food based on the matching result and displaying the abnormal position node on the food detection terminal according to a preset mode specifically includes the following steps:
acquiring a plane structure schematic diagram of a current storage area, and acquiring storage area position nodes of each food according to the plane structure schematic diagram;
acquiring character string information of the storage area position nodes of each food, and performing secondary matching on the character string information of the storage area position nodes of each food and the matching result to obtain the similarity of the secondary matching result;
acquiring a position node where the character string information with the secondary matching result similarity larger than the preset secondary matching result similarity is located;
and taking the position node where the character string information with the secondary matching result similarity larger than the preset secondary matching result similarity is located as an abnormal position node, and displaying the abnormal position node on the food detection terminal according to a preset mode.
It should be noted that, by the method, the abnormal position node of the crop with the excessive pesticide residue in the current storage area can be quickly detected, so that the related staff is informed to further process the crop with the excessive pesticide residue.
Further, in a preferred embodiment of the present invention, the method for acquiring the electrical signal information of the gas in the current area within the preset time by the array type odor sensor and preprocessing the electrical signal information of the gas to obtain the preprocessing result specifically includes the following steps:
acquiring gas electric signal information of a current area at preset time through an array type odor sensor, and calculating the relative deviation of N sample data within the preset time through an RSD method;
judging whether the relative deviation is greater than a preset relative deviation or not, and if the relative deviation is greater than the preset relative deviation, establishing a gas sensor response data curve based on the gas electric signal information of the current area at preset time;
performing smoothness processing on the response data curve of the gas sensor through a filter to obtain a processed response data curve;
and acquiring gas data information of the processed response data curve in a stable stage, and outputting the gas data information as a preprocessing result.
It should be noted that in order to allow the program to intelligently determine whether the steady state phase is reached, the RSD method is used to determine whether the response of the gas sensor is stable. The relative standard deviation of the data for N sample points over a continuous period of time (e.g., 30 seconds) is calculated and if sufficiently less than a set threshold (e.g., 10%), the response curve of the sensor is deemed to be stable. Each time a new sample of data arrives, it is recalculated. When the response curves of the n sensors all reach stability at the same time, the steady state phase is considered to have been reached. Therefore, the gas signal acquired by the gas sensor can be more reliable by the method.
In a third aspect, the present invention provides a computer-readable storage medium, which includes a program of a method for safely detecting pesticide residues in food, and when the program of the method is executed by a processor 62, the method for safely detecting pesticide residues in food realizes any one of the steps of the method for safely detecting pesticide residues in food.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The method for safely detecting pesticide residues in food is characterized by comprising the following steps of:
acquiring gas electric signal information of a current area within preset time through an array type odor sensor, and preprocessing the gas electric signal information to obtain a preprocessing result;
establishing an odor identification model, identifying the preprocessing result through the odor identification model to obtain a related odor type, and generating an identification result according to the related type;
obtaining crop category information of a current storage area, and searching according to the crop category to obtain a search result;
and matching according to the identification result and the retrieval result to obtain a matching result, determining an abnormal position node of the current food based on the matching result, and displaying the abnormal position node on a food detection terminal in a preset mode.
2. The food pesticide residue safety detection method as claimed in claim 1, wherein an odor recognition model is established, and the preprocessing result is recognized by the odor recognition model to obtain a related odor type, and the method specifically comprises the following steps:
establishing a smell recognition model based on a neural network, setting initialization parameters, acquiring smell sample data from a large database, training the smell recognition model through the smell sample data, adjusting model parameters and reserving optimal model parameters;
performing feature extraction on the preprocessing result to obtain an odor feature matrix, and taking the odor feature matrix as an input signal;
inputting the input signal into a neural network, after convolution layer operation, adopting a linear rectification function as an activation function, and classifying the odor types through a Softmax classifier to obtain the odor types of related classes and the odor types of unrelated classes;
and if the related type of the odor type exists, taking the related type of the odor type as the related odor type, and generating a recognition result according to the related odor type.
3. The food pesticide residue safety detection method as claimed in claim 1, wherein crop category information of a current storage area is acquired, and a search is performed according to the crop category to obtain a search result, specifically comprising the following steps:
judging whether the identification result is larger than a preset identification result or not, and if the identification result is larger than the preset identification result, acquiring crop type information in the current storage area;
acquiring disease condition type information under various crops through a big data network, and acquiring pesticide use types under various disease condition type information according to the disease condition type information;
building a database, and importing the pesticide use types under the various disease condition type information into the database to obtain a trained database;
and importing the crop category information in the current storage area into the trained database to obtain the pesticide use type of the crop in the current storage area, and outputting the pesticide use type as a retrieval result.
4. The food pesticide residue safety detection method according to claim 1, characterized in that matching is performed according to the identification result and the search result to obtain a matching result, and the method specifically comprises the following steps:
pesticide character string information of a current identification result is obtained, and first character string information is generated according to the pesticide character string information of the current identification result;
acquiring a plurality of pieces of character string information of a current retrieval result, and generating a plurality of pieces of second character string information according to the plurality of pieces of character string information of the current retrieval result;
comparing the first character string information with the second character string information one by one to obtain a plurality of similarity degrees, and judging whether the similarity degrees are greater than a preset similarity degree;
and if the similarity is greater than the preset similarity, taking the crops corresponding to the pesticide type of the second character string information as abnormal pesticide residue nodes, and outputting the abnormal pesticide residue nodes as matching results.
5. The food pesticide residue safety detection method according to claim 1, wherein the abnormal position node of the current food is determined based on the matching result and displayed on a food detection terminal in a preset manner, and the method specifically comprises the following steps:
acquiring a plane structure schematic diagram of a current storage area, and acquiring storage area position nodes of each food according to the plane structure schematic diagram;
acquiring character string information of the storage area position nodes of each food, and performing secondary matching on the character string information of the storage area position nodes of each food and the matching result to obtain the similarity of the secondary matching result;
acquiring a position node where the character string information with the secondary matching result similarity larger than the preset secondary matching result similarity is located;
and taking the position node where the character string information with the secondary matching result similarity larger than the preset secondary matching result similarity is located as an abnormal position node, and displaying the abnormal position node on the food detection terminal according to a preset mode.
6. The food pesticide residue safety detection method as claimed in claim 1, wherein the gas electric signal information of the current area within a preset time is acquired through the array type odor sensor, and the gas electric signal information is preprocessed to obtain a preprocessing result, and the method specifically comprises the following steps:
acquiring gas electric signal information of a current area at preset time through an array type odor sensor, and calculating the relative deviation of N sample data within the preset time through an RSD method;
judging whether the relative deviation is greater than a preset relative deviation or not, and if the relative deviation is greater than the preset relative deviation, establishing a gas sensor response data curve based on the gas electric signal information of the current area at preset time;
performing smoothness processing on the response data curve of the gas sensor through a filter to obtain a processed response data curve;
and acquiring gas data information of the processed response data curve in a stable stage, and outputting the gas data information as a preprocessing result.
7. The food pesticide residue safety detection system is characterized by comprising a memory and a processor, wherein the memory comprises a food pesticide residue safety detection method program, and when the food pesticide residue safety detection method program is executed by the processor, the following steps are realized:
acquiring gas electric signal information of a current area within preset time through an array type odor sensor, and preprocessing the gas electric signal information to obtain a preprocessing result;
establishing an odor identification model, identifying the preprocessing result through the odor identification model to obtain a related odor type, and generating an identification result according to the related type;
obtaining crop category information of a current storage area, and searching according to the crop category to obtain a search result;
and matching according to the identification result and the retrieval result to obtain a matching result, determining an abnormal position node of the current food based on the matching result, and displaying the abnormal position node on a food detection terminal in a preset mode.
8. The food pesticide residue safety detection system according to claim 7, wherein an odor recognition model is established, and the preprocessing result is recognized by the odor recognition model to obtain a relevant odor type, and the method specifically comprises the following steps:
establishing a smell recognition model based on a neural network, setting initialization parameters, acquiring smell sample data from a large database, training the smell recognition model through the smell sample data, adjusting model parameters and reserving optimal model parameters;
extracting features of the preprocessing result to obtain an odor feature matrix, and taking the odor feature matrix as an input signal;
inputting the input signal into a neural network, after convolution layer operation, adopting a linear rectification function as an activation function, and classifying the odor types through a Softmax classifier to obtain the odor types of related classes and the odor types of unrelated classes;
and if the related type of the odor type exists, taking the related type of the odor type as the related odor type, and generating a recognition result according to the related odor type.
9. The food pesticide residue safety detection system according to claim 7, wherein a matching result is obtained by matching according to the identification result and the search result, and the method specifically comprises the following steps:
pesticide character string information of a current identification result is obtained, and first character string information is generated according to the pesticide character string information of the current identification result;
acquiring a plurality of character string information of a current retrieval result, and generating a plurality of second character string information according to the plurality of character string information of the current retrieval result;
comparing the first character string information with the second character string information one by one to obtain a plurality of similarity degrees, and judging whether the similarity degrees are greater than a preset similarity degree;
and if the similarity is greater than the preset similarity, taking the crops corresponding to the pesticide type of the second character string information as abnormal pesticide residue nodes, and outputting the abnormal pesticide residue nodes as matching results.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a food pesticide residue safety detection method program, and when the food pesticide residue safety detection method program is executed by a processor, the steps of the food pesticide residue safety detection method according to any one of claims 1 to 6 are realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211196869.9A CN115452892A (en) | 2022-09-29 | 2022-09-29 | Food pesticide residue safety detection method, system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211196869.9A CN115452892A (en) | 2022-09-29 | 2022-09-29 | Food pesticide residue safety detection method, system and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115452892A true CN115452892A (en) | 2022-12-09 |
Family
ID=84306560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211196869.9A Pending CN115452892A (en) | 2022-09-29 | 2022-09-29 | Food pesticide residue safety detection method, system and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115452892A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017023217A1 (en) * | 2015-07-31 | 2017-02-09 | Akar Betül Yasemin | Detection of pesticide residues in agricultural plants |
| US20180211156A1 (en) * | 2017-01-26 | 2018-07-26 | The Climate Corporation | Crop yield estimation using agronomic neural network |
| WO2018192418A1 (en) * | 2017-04-17 | 2018-10-25 | 中国检验检疫科学研究院 | Pesticide residue detection data platform based on high resolution mass spectrum, internet and data science, and method for automatically generating detection report |
| CN109131893A (en) * | 2018-10-15 | 2019-01-04 | 南京林业大学 | A kind of pesticide residue real-time detection based on unmanned plane and the system and method accurately removed |
| CN114841824A (en) * | 2022-05-05 | 2022-08-02 | 中国农业科学院烟草研究所(中国烟草总公司青州烟草研究所) | Intelligent batching method, system and medium based on big data |
-
2022
- 2022-09-29 CN CN202211196869.9A patent/CN115452892A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017023217A1 (en) * | 2015-07-31 | 2017-02-09 | Akar Betül Yasemin | Detection of pesticide residues in agricultural plants |
| US20180211156A1 (en) * | 2017-01-26 | 2018-07-26 | The Climate Corporation | Crop yield estimation using agronomic neural network |
| WO2018192418A1 (en) * | 2017-04-17 | 2018-10-25 | 中国检验检疫科学研究院 | Pesticide residue detection data platform based on high resolution mass spectrum, internet and data science, and method for automatically generating detection report |
| CN109131893A (en) * | 2018-10-15 | 2019-01-04 | 南京林业大学 | A kind of pesticide residue real-time detection based on unmanned plane and the system and method accurately removed |
| CN114841824A (en) * | 2022-05-05 | 2022-08-02 | 中国农业科学院烟草研究所(中国烟草总公司青州烟草研究所) | Intelligent batching method, system and medium based on big data |
Non-Patent Citations (3)
| Title |
|---|
| 李文;戴永健;: "传感器技术在有机磷农药残留检测中的应用", 电子世界, no. 20, 30 October 2013 (2013-10-30), pages 88 - 89 * |
| 王光芒: "蔬菜农药残留电子鼻检测中特征提取方法研究", 《中国优秀硕士论文全文数据库 工程科技I辑》, 15 February 2012 (2012-02-15), pages 3 - 4 * |
| 陈红倩;李慧;方艺;刘启贤;陈谊;: "一种农残检测数据的融合对比可视化方法", ***仿真学报, no. 02, 8 February 2016 (2016-02-08), pages 354 - 360 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hill et al. | The use of data mining to assist crop protection decisions on kiwifruit in New Zealand | |
| CN114707773B (en) | Insect pest control scheme generation method and system based on deep learning and storage medium | |
| CN115358883B (en) | Dynamic resistance monitoring and prevention and control drug recommendation method and system for cotton aphids | |
| CN115879773B (en) | Intelligent disease and pest early warning method and system based on Internet of things | |
| CN115983533B (en) | Method and system for identifying and evaluating potential hazard of litchi pedicel borer | |
| CN115496300B (en) | Chinese rose seedling growing information and environment monitoring method | |
| CN113207511A (en) | Pesticide application method and system based on pesticide resistance monitoring and readable storage medium | |
| CN116740644A (en) | Comprehensive evaluation and control method and system for plant diseases and insect pests in passion fruit cultivation process | |
| Africa et al. | Ripe fruit detection and classification using machine learning | |
| CN116030343A (en) | Crop pest monitoring system based on machine vision identification | |
| CN115909060A (en) | Method, system and storage medium capable of accurately preventing and controlling citrus diseases and insect pests | |
| CN117173400B (en) | Low-carbon treatment scheme recommendation method and system for litchi insect pest | |
| Lin et al. | The occurrence of Scirtothrips dorsalis Hood in mango orchards and factors influencing its population dynamics in Taiwan | |
| Hulsegge et al. | A time-series approach for clustering farms based on slaughterhouse health aberration data | |
| CN114266979A (en) | Tea tree pest and disease intelligent identification method, device, equipment and storage medium | |
| CN116523182B (en) | Ecological garden construction and production management method, system and storage medium | |
| CN115452892A (en) | Food pesticide residue safety detection method, system and medium | |
| CN117371604A (en) | Agricultural production prediction method and system based on intelligent perception | |
| Baker et al. | Forecasting dengue fever using machine learning regression techniques | |
| Banerjee et al. | Implications for biological invasion of non‐native plants for sale in the world's largest online market | |
| CN116740645A (en) | Fruit fly monitoring and comprehensive prevention and control method, system and storage medium based on Internet of things | |
| CN115169508B (en) | Data analysis and management method based on supply chain platform | |
| CN114093521B (en) | Random forest based method and system for estimating blood sugar by reconstructing homogenized samples | |
| KR20200036168A (en) | System for matching crops to individual by customizing individual body rhythm | |
| CN110968672B (en) | False public opinion identification method for food safety based on neural network |
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 |