CN117952499B - Fruit selecting and transporting method - Google Patents
Fruit selecting and transporting method Download PDFInfo
- Publication number
- CN117952499B CN117952499B CN202410353426.9A CN202410353426A CN117952499B CN 117952499 B CN117952499 B CN 117952499B CN 202410353426 A CN202410353426 A CN 202410353426A CN 117952499 B CN117952499 B CN 117952499B
- Authority
- CN
- China
- Prior art keywords
- maturity
- storage
- fruit
- time
- bin
- 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.)
- Active
Links
- 235000013399 edible fruits Nutrition 0.000 title claims abstract description 260
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012216 screening Methods 0.000 claims abstract description 4
- 238000012360 testing method Methods 0.000 claims description 68
- 239000011973 solid acid Substances 0.000 claims description 35
- 230000008859 change Effects 0.000 claims description 22
- 238000012544 monitoring process Methods 0.000 claims description 22
- 238000001514 detection method Methods 0.000 claims description 16
- 238000013139 quantization Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 6
- 238000003064 k means clustering Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000001174 ascending effect Effects 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000006866 deterioration Effects 0.000 abstract description 3
- 238000009825 accumulation Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 7
- 235000021022 fresh fruits Nutrition 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- 239000002253 acid Substances 0.000 description 2
- 238000002329 infrared spectrum Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000010183 spectrum analysis Methods 0.000 description 2
- 235000019640 taste Nutrition 0.000 description 2
- 235000005976 Citrus sinensis Nutrition 0.000 description 1
- 240000002319 Citrus sinensis Species 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 235000019606 astringent taste Nutrition 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000002542 deteriorative effect Effects 0.000 description 1
- 238000000855 fermentation Methods 0.000 description 1
- 230000004151 fermentation Effects 0.000 description 1
- 239000000796 flavoring agent Substances 0.000 description 1
- 235000019634 flavors Nutrition 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000004345 fruit ripening Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000005389 magnetism Effects 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000001766 physiological effect Effects 0.000 description 1
- 235000019614 sour taste Nutrition 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/68—Food, e.g. fruit or vegetables
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Multimedia (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Educational Administration (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Sorting Of Articles (AREA)
Abstract
The invention belongs to the technical field of logistics transportation, and discloses a fruit selecting and transporting method, which comprises the following steps: detecting and recording a first degree of ripeness of each fruit; clustering all first maturity; dividing and storing all fruits according to the clustering result, and distributing a time tag containing storage starting time and maximum storage duration in a bin for each storage bin; generating order dispatch time, order transportation duration and a transportation storage environment; acquiring a plurality of bin storage time lengths and a plurality of actual storage total time lengths; taking all storage bins with the actual total storage time length less than or equal to the maximum storage time length in the bin as candidate storage bins; screening target storage bins from all candidate storage bins; acquiring an estimated value of the maximum storage time length of transportation of each fruit in the target storage bin; and selecting fruits with the estimated transportation maximum storage time length not less than the order transportation time length from the target storage bin for sorting and transporting. The invention can avoid the deterioration of fruits due to long-time accumulation in the warehouse and ensure the quality of the fruits after delivery.
Description
Technical Field
The invention relates to the technical field of logistics transportation, in particular to a fruit selecting and distributing method.
Background
Fruits belong to high-frequency rigid necessities, and particularly as the living standard of residents increases, people have shifted from pursuing warmth and saturation to pursuing quality of life. In addition, domestic fruits are greatly sold overseas, greatly expanding the demands of fruit logistics transportation. However, most fruits continue to ripen after picking, and have the characteristics of post-ripeness, perishability and the like, which presents a great challenge for optimizing the fruit delivery process. The maturity of fruit is closely related to the storage time and the storage environment. Some fruits are picked later in time, and if the fruits are not sold in time after warehouse entry, the fruits are easy to spoil and deteriorate, and even if the fruits are sold before the fruits are spoiled, the fruits are spoiled or even spoiled due to the influences of the transportation time and the transportation and storage environment in the long-distance transportation process.
Disclosure of Invention
The invention aims to provide a fruit selecting and distributing method, which is used for selecting target fruits from a warehouse to distribute according to the maturity, the storage time and the transportation time of the fruits, so that the phenomena of stocking and spoilage of the fruits due to overlong storage time in the warehouse can be avoided, and the quality of the fruits after delivery can be ensured.
The invention is realized by the following technical scheme:
The fruit selecting and distributing method comprises the following steps: detecting and recording a first degree of ripeness of each fruit; clustering all first maturity; according to the clustering result, storing all fruits in bins, and distributing time labels for each storage bin; the time tag includes: storing the starting time and the maximum storage time in the bin; the maximum storage duration in the bin is the minimum value of duration required by the change of the first maturity of all fruits in the storage bin to the maturity threshold; generating order sending time, order transportation time and transportation storage environment according to the order information; obtaining the difference between each storage starting time and the order dispatch time to obtain a plurality of storage duration in bins; obtaining the sum of the storage duration in each bin and the order transportation duration to obtain a plurality of actual storage total durations; taking all storage bins with the actual total storage time length less than or equal to the maximum storage time length in the bin as candidate storage bins; screening one corresponding to the maximum value of the total actual storage time length from all candidate storage bins as a target storage bin; predicting a second degree of ripeness of each fruit within the target bin at the order serving time; acquiring an estimated transportation maximum storage time length of each fruit in the target storage bin in the transportation storage environment; the transport maximum storage time length estimated value is the minimum value of time length required by the second maturity of all fruits in the target storage bin to be changed to the maturity threshold; and selecting fruits with the estimated transportation maximum storage time length not less than the order transportation time length from the target storage bin for sorting.
Further, before detecting and recording the first maturity of each fruit, the method comprises the following steps: collecting a plurality of first test samples; sampling and detecting the solid-acid ratio of each first test sample fruit to generate a first test sample; acquiring a color image of each first test sample, and generating a second test sample; converting the format of each color image in the second test sample from an RGB format to an HSI format to generate a third test sample; executing step S11 and step S12 on each color image in the third test sample to obtain a plurality of frequency sequences; wherein, step S11: extracting a plurality of chromaticities in a color image; step S12: counting the occurrence frequency of each chromaticity in the color image, and generating a plurality of corresponding frequency sequences; generating a fourth test sample by using the obtained plurality of frequency sequences; training a neural network model by using the first test sample and the fourth test sample by taking a frequency sequence as input and a solid-acid ratio as output to obtain a trained mapper; the mapper is used for extracting the mapping relation between the frequency sequence and the solid-acid ratio.
Further, the detecting and recording of the first maturity of each fruit includes the steps of: step S21-step S26 are performed for each fruit; step S21: collecting color images of fruits; step S22: converting the format of the color image from RGB format to HSI format; step S23: extracting a plurality of chromaticities from a color image in an HSI format; step S24: counting the occurrence frequency of each chromaticity in the color image in the HSI format, and generating a plurality of corresponding frequency sequences; step S25: inputting the generated multiple frequency sequences into the mapper, and outputting the solid-acid ratio corresponding to each fruit; step S26: and taking the solid-acid ratio output by the mapper as the first ripeness of the fruit.
Further, the clustering of all the first maturity includes the following steps: sequencing all the first maturity according to ascending order to obtain a numerical sequence; uniformly dividing the numerical sequence into a plurality of numerical intervals according to the residual quantity of the storage bins; extracting first maturity of each numerical range at the middle position, and taking the extracted first maturity as a plurality of clustering centers; setting a Euclidean distance; and clustering all the first maturity by using a K-means clustering algorithm according to the residual quantity of the storage bins, a plurality of clustering centers and the Euclidean distance to obtain a clustering result.
Further, before the first maturity of each numerical interval at the intermediate position is extracted, the method includes the following steps: and eliminating abnormal data in each numerical value interval.
Further, before the time tag is allocated to each storage bin, the method includes the following steps: collecting a plurality of second test samples; step S31-step S33 are carried out on each second test sample, so that the solid acid ratio of a plurality of second test samples is obtained; wherein, step S31: continuously monitoring each second test sample fruit by utilizing an electronic nose monitoring technology within a first preset time period to obtain a monitoring result, wherein the monitoring result is used for marking the fruit to start spoilage; step S32: marking a monitoring time point corresponding to the monitoring result; step S33: sampling and detecting the solid acid ratio of the second test sample fruit at the monitoring time point; and taking the median of the solid-acid ratios of a plurality of second test fruits to obtain the maturity threshold.
Further, before the time tag is allocated to each storage bin, the method further includes the following steps: collecting a plurality of third test samples; detecting and recording the first maturity of each third test specimen by adopting the method described in the step S21-the step S26 in a second preset time period to generate a fifth test specimen; performing polynomial fitting by using the second preset time period and the fifth test sample to obtain a relation model of maturity and time; and obtaining the time length required for the maturity of each fruit to change from the first maturity to the maturity threshold according to the relation model.
Further, the predicting the second degree of ripeness of each fruit in the target bin at the order dispatch time includes the steps of: the following steps are performed for each fruit: drawing a trend chart of the maturity changing along with time according to the relation model; marking the order dispatch time in the trend graph; reading the corresponding maturity from the trend graph according to the marked order dispatch time; the read maturity is taken as the second maturity.
Further, the method includes the steps of, prior to obtaining an estimate of a maximum storage time period for each fruit in the target storage bin for transport in the transport storage environment: establishing a maturity quantization model of the fruits in the transportation process; the maturity quantization model is used for reflecting the change rate of the maturity of the fruits in the transportation and storage environment; and obtaining the time period required by the fruit to change from the second maturity to the maturity threshold value by using the maturity quantization model.
Further, the expression of the maturity quantization model is: ; wherein f represents the rate of change of the ripeness of the fruit in the transportation storage environment; /(I) The weight of the ith detection index of the fruit maturity; /(I)An ith detection index indicating fruit maturity during the edible period,/>An ith detection index indicating fruit maturity during the pickable period,/>An i-th detection indicator representing fruit maturity during physiological maturity, i=1, 2..n, n representing the number of detection indicators of fruit maturity; /(I)Representing the corresponding influence factors of the transportation storage environment; t represents 1 hour.
The invention has the following advantages and beneficial effects: in order to avoid deterioration of fruits due to long-time stocking in a warehouse and to ensure the quality of the fruits after delivery, the invention selects the maturity of the fruits as a sign reflecting the quality of the fruits, and divides the maturity of the fruits into three gradients from the time dimension, namely, a first maturity before the fruits are put in the warehouse, a second maturity when the fruits are sent and a third maturity (maturity threshold) before the fruits begin to spoil. Dynamically selecting target fruits and throwing the fruits into delivery by simulating the time length of the change of the maturity of the fruits between two adjacent gradients, namely comparing the actual storage total time length of the fruits with the maximum storage time length of the fruits in the warehouse, and preliminarily selecting the fruits with the actual storage total time length less than or equal to the maximum storage time length in the warehouse as the fruits to be delivered, so that the fruits are prevented from being accumulated in the warehouse for a long time and deteriorating; on the premise of guaranteeing the quality of the delivered fruits, the estimated value of the maximum transport storage time length is compared with the transport time length of the order, and the fruits with the estimated value of the maximum transport storage time length not less than the transport time length of the order are finally selected to serve as target fruits for delivery, so that the quality of the delivered fruits is guaranteed.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings that are needed in the examples will be briefly described below, it being understood that the following drawings only illustrate some examples of the present invention and therefore should not be considered as limiting the scope, and that other related drawings may be obtained from these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a fruit selection and distribution method according to an embodiment of the present invention.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present invention and the descriptions thereof are for illustrating the present invention only and are not to be construed as limiting the present invention.
Examples: as shown in fig. 1, the present embodiment provides a fruit selection and distribution method, which includes the following steps:
step 1: the first maturity of each fruit is detected and recorded.
The first maturity is the maturity of the fruits corresponding to the sorting and warehousing time.
Before describing how to detect the first maturity in detail, it should be noted that: the ratio of the soluble solids to the titratable acid content (referred to as the solid-acid ratio) is selected to characterize the ripeness of the fruit, as the content of the soluble solids increases and the acid content decreases as the fruit ripens, and the flavor of the fruit is greatly improved. And a spectral analysis method based on machine vision is adopted to detect the solid-acid ratio of the fruits. Specifically, based on spectral analysis of the fruit color image, a frequency sequence is obtained by obtaining the frequencies corresponding to the respective chromaticities in the color image, and a mapping relation between the frequency sequence and the solid-acid ratio is further established by a machine learning mode. Therefore, before detecting the solid-acid ratio of the fruit, a mapper is first generated to extract the mapping relationship between the frequency sequence and the solid-acid ratio. The specific implementation of the generation mapper is as follows:
Step 1.1.1: a plurality of first test samples are collected.
For example, 500 fruits of different ripeness can be selected as the first test specimen.
Step 1.1.2: and sampling and detecting the solid-acid ratio of each first test sample fruit to generate a first test sample.
The solid-acid ratio of the fruits can be detected by means of material component analysis, and mass spectrometry-spectrum-chromatography-nuclear magnetism analysis instruments are utilized to analyze the material components of the cut fruit pulp, so that the corresponding solid-acid ratio is obtained. The existing solid-acid ratio detection method can also be selected to detect the solid-acid ratio of the fruit, for example, refer to Lisa , lai Zhaosheng and Zeng Ming in the paper "near infrared derivative spectrometry for soluble solid and solid-acid ratio of Gannan navel orange" published in Gannan university journal at 11 and 30 in 2023.
Step 1.1.3: and acquiring a color image of each first test sample by shooting a high-definition color image, and generating a second test sample.
Step 1.1.4: and converting the format of each color image in the second test sample from an RGB format to an HSI format to generate a third test sample.
In image processing, two color models, RGB and HSI, are often used. The color images captured by the camera are typically in RGB format. However, if the RGB color model is directly used, the chromaticity of each pixel needs to be processed, which means that the chromaticity of each pixel needs to be processed on three components, which increases the complexity of the processing. In the HSI color model, the chromaticity information of the pixel point is extracted independently, and only one-dimensional processing is needed when the chromaticity information of the pixel is processed, so that the HSI color model is more convenient to use.
Step 1.1.5: step S11 and step S12 are performed for each color image in the third test sample, and a plurality of frequency sequences are obtained. Wherein, step S11: a plurality of chromaticities in a color image are extracted. Step S12: and counting the occurrence frequency of each chromaticity in the color image, and generating a plurality of corresponding frequency sequences.
Image information is often obtained by analyzing chromaticity. The most basic content of the chromaticity information in the color image is the occupation ratio of the pixel points corresponding to each chromaticity in the whole image. The ratio of each chromaticity in the color image can be intuitively obtained by drawing a chromaticity histogram of the color image, wherein the ordinate in the figure is the frequency of occurrence of pixels corresponding to each chromaticity value in the image, which is the ratio of the number of pixels possessed by each chromaticity in the image to the total number of pixels of the image. For convenience of analysis, the color images of the 500 first test samples may be statistically analyzed to obtain chromaticity distribution in the color images, and chromaticity with higher frequency may be selected for analysis, for example, chromaticity within a range of (1, 210) may be selected for analysis, and 210 frequency values representing image color information may be extracted, and each color image corresponds to a frequency sequence including 210 frequency values, and the chromaticity information of the color image is reflected by the frequency sequence.
Step 1.1.6: and generating a fourth test sample by using the obtained multiple frequency sequences.
Step 1.1.7: and training a neural network model by using the frequency sequence as input and the solid-acid ratio as output and using the first test sample and the fourth test sample to obtain a trained mapper. The mapper is used for extracting the mapping relation between the frequency sequence and the solid-acid ratio.
After training to obtain the mapper, the color images of the fruits are collected, the frequency sequence is extracted from the color images, and then the mapper can be used for indirectly obtaining the solid-acid ratio of the fruits. Thus, a specific operation of detecting the first maturity of each fruit is to perform steps 1.2.1 through 1.2.6 for each fruit.
Step 1.2.1: color images of the fruit are acquired.
Step 1.2.2: the format of the color image is converted from RGB format to HSI format.
Step 1.2.3: a plurality of chromaticities are extracted from a color image in an HSI format.
Step 1.2.4: and counting the occurrence frequency of each chromaticity in the color image in the HSI format, and generating a plurality of corresponding frequency sequences.
Step 1.2.5: and inputting the generated multiple frequency sequences into a trained mapper, and outputting the solid-acid ratio corresponding to each fruit.
Step 1.2.6: and taking the solid-acid ratio output by the mapper as the first ripeness of the fruit.
Step 2: all first maturity of the records are clustered.
The first maturity of each fruit obtained through step 1. Because the picking time of each fruit is different, the first maturity of each fruit is different before warehousing, and therefore a batch of fruits need to be classified according to different maturity before warehousing. The method adopts a K-means clustering algorithm to cluster all the first maturity. The specific clustering steps are as follows:
Step 2.1: and sequencing all the first maturity according to ascending order to obtain a numerical sequence.
Step 2.2: and uniformly dividing the numerical sequence into a plurality of numerical intervals according to the residual quantity of the storage bins.
The K-means clustering algorithm needs to determine the K value (the number of clusters, i.e., the number of cluster centers). The method aims at clustering all the fruits with different maturity degrees by dividing bins, so that the rest number of the storage bins is used as the number of clustering centers. And the numerical sequence is uniformly divided into a plurality of numerical intervals according to the residual quantity of the storage bins, so that primary clustering is realized.
Step 2.3: the first maturity of each numerical value interval at the middle position is extracted, and the extracted first maturity is taken as a plurality of clustering centers.
Since the first maturity levels may be irregularly distributed in a certain numerical interval after the sorting and numerical sequence division, the first maturity levels may only show an increasing relationship. In order to reasonably select the clustering center, the first maturity at the middle position of the numerical interval is selected as the clustering center.
Step 2.4: setting the Euclidean distance. To measure similarity between the first maturity.
Step 2.5: and clustering all the first maturity by using a K-means clustering algorithm according to the residual quantity of the storage bins, a plurality of clustering centers and Euclidean distances to obtain a clustering result. The clustering result visually appears as a plurality of clusters of classes, each cluster of classes aggregating a plurality of similar first maturity.
In addition, in order to obtain a better classification result, the embodiment eliminates the abnormal data in each numerical interval.
Step 3: and storing all fruits in bins according to the clustering result.
And (3) a fruit corresponds to a first maturity, and the fruits can be stored in bins according to the clustering result in the step (2). After the storage bins are separated, the fruits stored in each storage bin have similar maturity.
Step 4: each bin is assigned a time stamp.
The time tag includes: the storage start time and the maximum storage duration in the bin. The maximum storage duration in the bin is the minimum value of the duration required by the change of the first maturity of all fruits in the storage bin to the maturity threshold.
Function of time tag: one aspect is to mark the start time of storage (time to warehouse) of the fruit. The fruit maturity corresponding to the storage start time is the first maturity, and the storage start time can be used for calculating the storage duration in the subsequent acquisition bin and the maximum storage duration in the bin. Another aspect is the maximum storage time in the marker bin. The maturity of the fruits still changes along with the storage time and the storage environment in the storage bin after the fruits are put in the storage bin, and if the fruits are stored in the storage bin for too long, the fruits can be deteriorated finally. The purpose of the maximum storage time in the marking bin is to reflect the maximum time length that the fruit can be stored in the storage bin, so that the fruit is prevented from being stored in the storage bin for a long time to deteriorate.
The method uses the minimum value of the time required for the ripeness of the fruit to change from the first ripeness to the ripeness threshold value to represent the maximum in-bin storage time of the storage bin. The reason is that: first, the maturity threshold value in the method refers to the maturity corresponding to the time when the fruits begin to deteriorate, and in a stable in-bin storage environment, the maturity of the fruits changes from the first maturity at the time of entering the bin to the time required by the maturity threshold value at the time when the fruits begin to deteriorate, so that the maximum duration that the fruits can be stored in the storage bin can be reflected. Second, the method selects the minimum value of the time period required for changing the first maturity of all the fruits to the maturity threshold value as the maximum storage time period in the bin, because the first maturity of each fruit in the storage bin is different, and therefore the time period required for changing the maturity of each fruit from the first maturity to the maturity threshold value is different. For example, the maximum storage time period in the storage bin is 10 days, 12 days, 13 days and 15 days … … respectively, and the time for storing the fruits in the storage bin is the same day, so that the fruits on the 11 th day after being stored in the storage bin are deteriorated by part of the fruits. In order to avoid the phenomenon, the method selects the minimum value of the maximum storage time length in the bin of each fruit as the final maximum storage time length in the bin, thereby avoiding the fruit in the storage bin from going bad due to overlong stocking time. Meaning that the fruit in the storage bin should be distributed within the range of maximum storage time length in the corresponding bin.
The supplementary explanation is that: based on the above explanation of the time tag content, a threshold of maturity is first required to reach the maximum in-bin storage duration for each fruit before a time tag is assigned to each storage bin. The method for obtaining the maximum storage duration in the bin comprises the following steps:
step 4.11: a plurality of second test samples are collected.
Step 4.12: and performing steps 4.12.1 to 4.12.3 on each second test sample to obtain the solid acid ratio of each second test sample. Wherein, step 4.12.1: and continuously monitoring each second test sample by utilizing an electronic nose monitoring technology in a first preset time period to obtain a monitoring result, wherein the monitoring result is used for marking that the fruits start to spoil. Specifically, the method described in paper "electronic nose System for monitoring rot of fruits in storage environment" published in electronic devices "in 2019, 6, 20, and Ding Qinghang, zhao Dongjie, liu Jun, yu Zigong can be referred to realize continuous monitoring of each second test sample; and the fruit spoilage is judged by combining Yang Chen, yuan Hongfei and Ma Huiling with a judging model established by combining Fi step Sher judging and KNN and other methods respectively by utilizing a near infrared spectrum technology and an electronic nose technology in apple mould heart nondestructive test based on Fourier near infrared spectrum and an electronic nose technology which are published in food and fermentation industry at 11 and 13 days of 2020. Step 4.12.2: and marking a monitoring time point corresponding to the monitored result. The monitored time point can be used as a time point for judging the fruit to start spoilage. Step 4.12.3: sampling and detecting the solid-acid ratio of the second test sample at the monitoring time point.
Step 4.13: and taking the median of the solid-acid ratios of the second test fruits to obtain the maturity threshold.
The maturity threshold of the fruit can be obtained through the steps 4.11 to 4.13, the method is based on the fact that the maturity and time are established in a polynomial fitting mode before time labels are distributed to each storage bin, the corresponding time when the maturity of the fruit reaches the maturity threshold is correspondingly obtained by utilizing the relation model, and finally the time (the maximum storage bin storage time) required by the change of the first maturity of the fruit to the maturity threshold can be calculated by combining the storage starting time. The specific method comprises the following steps:
Step 4.21: a plurality of third test samples were collected.
Step 4.22: and (3) detecting and recording the first maturity of each third test specimen in a second preset time period by adopting the method from the step 1.2.1 to the step 1.2.6, and generating a fifth test specimen.
Step 4.23: and performing polynomial fitting by using the second preset time period and the fifth test sample to obtain a relation model of the maturity and time.
Step 4.24: and obtaining the time length required for the maturity of each fruit to change from the first maturity to the maturity threshold according to the relation model.
Step 5: order dispatch time, order shipping duration, and shipping storage environment are generated from the order information.
Wherein, the order dispatch time is determined according to the actual order quantity and the order dispatch plan; the order transportation time length is determined according to the destination of the order, and the order transportation time length can be determined according to the navigation planning time length; the transportation and storage environment is the storage environment of the transportation means, and in the actual transportation process, the storage environments of different transportation means are different.
Step 6: and obtaining the difference between each storage starting time and the order dispatch time to obtain a plurality of storage duration in the bins.
And after the fruits are put in storage and stored until the period of time for generating the order is up to, storing the fruits in the storage bin, wherein the maturity of the fruits changes along with the storage time in the period of time, and meanwhile, the fruits are influenced by the storage environment of the storage bin, and the fruits are put out of the storage and loaded after the order is generated. Therefore, the method takes the period of time from the time when the fruits are put in storage until the order is generated as a first stage, wherein the maturity of the fruits corresponds to a first maturity at the beginning time (fruit put in storage time) of the first stage, and the maturity of the fruits corresponds to a second maturity at the ending time (order generation time) of the first stage.
Therefore, by acquiring the in-bin storage duration corresponding to each storage bin, the maturity (second maturity) corresponding to the fruit at the time of delivery and loading can be predicted. Specifically, the method for predicting the second maturity of each fruit in the target storage bin at the time of order dispatch comprises the following steps: steps 6.1 to 6.4 are performed for each fruit. Wherein, step 6.1: and (3) drawing a trend chart of the maturity changing along with time according to the relation model obtained in the step 4.23. Step 6.2: the order dispatch times are marked in the trend graph. Step 6.3: and reading the corresponding maturity from the trend graph according to the marked order dispatch time. Step 6.4: the read maturity is taken as the second maturity.
Step 7: and obtaining the sum of the storage duration and the order transportation duration in each bin to obtain a plurality of actual storage total durations.
The actual total stored time period includes: the length of time that the fruit is stored in the storage bin before the order is generated, and the length of time that the fruit is stored in the transportation process after the order is generated.
Step 8: and taking all the storage bins with the actual total storage duration less than or equal to the maximum storage duration in the bins as candidate storage bins.
It should be noted that, the difference between the storage environment in the storage bin and the transportation storage environment of the transportation means is considered in this step, and the following three situations exist:
First case: the transportation and storage environment is better than the warehouse storage environment, and the quality of the fruits after the orders are delivered can be ensured. By way of illustration, assuming that fruit can be stored in the in-bin storage environment for up to 10 days, and that fruit has been held in the storage bin for 3 days prior to order generation, it is theorized that fruit can be stored in the in-bin storage environment for up to 7 more days; because the transportation and storage environment is better than the warehouse storage environment, in the first case, the quality of fruits after the order is delivered can be ensured by only ensuring that the order transportation time is less than or equal to 7 days, namely, the total actual storage time is less than or equal to 10 days (3 days and 7 days).
Second case: the transportation and storage environment is the same as the warehouse storage environment, and the quality of the fruits after the orders are delivered is ensured. By way of illustration, assuming that fruit can be stored in the in-bin storage environment for up to 10 days, and that fruit has been held in the storage bin for 3 days prior to order generation, it is theorized that fruit can be stored in the in-bin storage environment for up to 7 more days; because the transportation and storage environment is the same as the warehouse storage environment, in the second case, the transportation duration of the order is ensured to be less than or equal to 7 days, namely the total actual storage duration is less than or equal to 10 days (3 days and 7 days), and the quality of the fruits after the order is delivered can be ensured.
Third case: the transportation and storage environment is worse than the warehouse storage environment, and the quality of the fruits after the orders are delivered cannot be guaranteed. By way of illustration, assuming that fruit can be stored in the in-bin storage environment for up to 10 days, and that fruit has been held in the storage bin for 3 days prior to order generation, it is theorized that fruit can be stored in the in-bin storage environment for up to 7 more days; because the transportation and storage environment is worse than the warehouse storage environment, in the third case, if the order transportation time is more than or equal to 7 days, that is, the total actual storage time is more than or equal to 10 days (3 days+7 days), the quality of the fruits after the order is delivered cannot be ensured.
Therefore, based on the analysis, the method takes all storage bins with the total actual storage time length less than or equal to the maximum storage time length in the bin as candidate storage bins, so that on one hand, the fruits are prevented from being stored in the storage bins for longer than the maximum storage time length in the bin, and the fruits are prevented from being stored for too long to deteriorate, and on the other hand, the quality of the fruits after the order is sent can be ensured theoretically.
Step 9: and screening one corresponding to the maximum value of the total actual storage duration from all the candidate storage bins as a target storage bin.
The objective of this step is to avoid as much as possible the deterioration of the fruits due to the excessive accumulation time. Specifically, assuming that 3 candidate storage bins (respectively denoted as a first candidate storage bin, a second candidate storage bin and a third candidate storage bin) are screened out in the step 8, the total actual storage time length of the first candidate storage bin is 7 days, the total actual storage time length of the second candidate storage bin is 8 days, the total actual storage time length of the third candidate storage bin is 9 days, the conditions of less than or equal to 10 days are satisfied, and the quality of fruits after delivering orders can be ensured. In order to minimize the time of stocking the fruits in the storage bin, the fruits should be selected from the third candidate storage bin for transportation, so that the third candidate storage bin is taken as the target storage bin.
Step 10: predicting a second degree of ripeness of each fruit in the target bin at the time of order dispatch.
Since the maturity of the fruit stored in the bin is changed from the first maturity until the order is generated, prior to the order being generated. As the fruit will be transferred to the shipping storage environment after the order is generated, the second stage is entered. The second stage of the transportation and storage environment may be different from the first stage of the in-bin storage environment, so that the change state of the maturity of the fruits in the transportation and storage environment is changed, and the second maturity of the fruits in the order dispatch time is used as the boundary between the first stage and the second stage of the fruit layer.
Step 11: an estimate of a maximum storage time period for each fruit in the target storage bin for transportation within the transportation storage environment is obtained.
In order to ensure the quality of the fruit after the order is delivered, the maximum storage time of the fruit in the actual transportation and storage environment is ensured to be less than or equal to the transportation time of the order under the three conditions. Thus, there is a need to estimate the maximum length of time each fruit in the target bin is transported in the transport storage environment. The specific method comprises the following steps:
Before an estimated value of the maximum storage time period of each fruit in the target storage bin in the transportation storage environment is obtained, a maturity quantization model of the fruit in the transportation process is established and is used for reflecting the change rate of the maturity of the fruit in the transportation storage environment.
The following description is provided: maturity is one of the major factors affecting fruit quality and post harvest physiological property changes. The change of the fruit maturity is influenced by the external environment such as temperature, humidity, oxygen content and the like, and the characteristics of the fruit. Fruit maturity includes harvestable maturity, edible maturity and physiological maturity. The harvestable maturity means that the fruits are fully developed and reach the picking standard, but the picked fruits are not fully ripe at the moment, have slightly sour and astringent taste and are poor in taste, and are mostly used for storage and transportation. The edible maturity means that the fruits reach edible maturity state, the taste of the fruits and the nutrients of the fruits are in optimal states, but the fruits in the period are ripe very fast and can not be transported and stored for a long distance. Physiological maturity refers to the fact that the fruit has fully matured, some fruits have not been eaten properly, and are not transported or stored.
The change in fruit maturity during the fruit ripening process is not determined by a single indicator. Assuming that the maturity of the fruit reaches the physiological maturity stage to be 100%, the maturity of the fresh fruit at a certain period is measured by the ratio of the weighted average of the content and weight of each index in the fresh fruit at the period to the weighted average of each index and weight when the fresh fruit reaches the physiological maturity stage.
Based on the analysis, the expression of the maturity quantization model provided by the method is as follows: ; wherein f represents the rate of change of the ripeness of the fruit in the transportation storage environment; /(I) The weight of the ith detection index of the fruit maturity; /(I)An ith detection index indicating fruit maturity during the edible period,/>An ith detection index indicating fruit maturity during the pickable period,/>An i-th detection indicator representing fruit maturity during physiological maturity, i=1, 2..n, n representing the number of detection indicators of fruit maturity; /(I)And representing the corresponding influence factors of the transportation storage environment. The impact factor may be defined in terms of the actual transportation storage environment, for example: when the transportation storage environment is better than the in-warehouse storage environment, it is possible to define/>; When the transportation storage environment is the same as the in-warehouse storage environment, it is possible to define/>; When the transportation storage environment is worse than the in-warehouse storage environment, it is possible to define/>。
After establishing the maturity quantization model, the maturity quantization model can be used to estimate the length of time each fruit needs to change from the second maturity to the maturity threshold within the transportation storage environment. The transport maximum storage time period estimate is the minimum time period required for the second ripeness level change of all the fruits in the target storage bin to be the ripeness threshold value.
Step 12: and selecting fruits with the estimated transportation maximum storage time length not less than the order transportation time length from the target storage bin for sorting and transporting.
First, the following is explained: step 11, selecting the minimum value of the time required for changing the second maturity of all fruits to the maturity threshold as the transport maximum storage time estimate, and ensuring the quality of the fruits after the order is delivered. Specifically, the length of time required for changing the maturity of the fruit from the second maturity to the maturity threshold represents the maximum storage time of the fruit in the actual transportation and storage environment, and the maximum storage time is not less than the order transportation time so as to ensure the quality of the fruit after the order is delivered; the minimum maximum storage time length is selected, so that the maximum storage time length of all fruits in the target storage bin in the transportation storage environment is more than or equal to the order transportation time length, and the quality of the fruits after the order is delivered is further ensured.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (7)
1. The fruit selecting and distributing method is characterized by comprising the following steps of:
detecting and recording a first degree of ripeness of each fruit; clustering all first maturity; according to the clustering result, storing all fruits in bins, and distributing time labels for each storage bin; the time tag includes: storing the starting time and the maximum storage time in the bin; the maximum storage duration in the bin is the minimum value of duration required by the change of the first maturity of all fruits in the storage bin to the maturity threshold;
Generating order sending time, order transportation time and transportation storage environment according to the order information; obtaining the difference between each storage starting time and the order dispatch time to obtain a plurality of storage duration in bins; obtaining the sum of the storage duration in each bin and the order transportation duration to obtain a plurality of actual storage total durations; taking all storage bins with the actual total storage time length less than or equal to the maximum storage time length in the bin as candidate storage bins; screening one corresponding to the maximum value of the total actual storage time length from all candidate storage bins as a target storage bin;
predicting a second degree of ripeness of each fruit within the target bin at the order serving time; acquiring an estimated transportation maximum storage time length of each fruit in the target storage bin in the transportation storage environment; the transport maximum storage time length estimated value is the minimum value of time length required by the second maturity of all fruits in the target storage bin to be changed to the maturity threshold; selecting fruits with the estimated transportation maximum storage time length not less than the order transportation time length from the target storage bin for sorting;
Before said detecting and recording the first maturity of each fruit, the steps of:
Collecting a plurality of first test samples;
Sampling and detecting the solid-acid ratio of each first test sample fruit to generate a first test sample;
acquiring a color image of each first test sample, and generating a second test sample;
Converting the format of each color image in the second test sample from an RGB format to an HSI format to generate a third test sample;
Executing step S11 and step S12 on each color image in the third test sample to obtain a plurality of frequency sequences; wherein, step S11: extracting a plurality of chromaticities in a color image; step S12: counting the occurrence frequency of each chromaticity in the color image, and generating a plurality of corresponding frequency sequences;
generating a fourth test sample by using the obtained plurality of frequency sequences;
Training a neural network model by using the first test sample and the fourth test sample by taking a frequency sequence as input and a solid-acid ratio as output to obtain a trained mapper; the mapper is used for extracting the mapping relation between the frequency sequence and the solid-acid ratio;
Said detecting and recording a first maturity of each fruit comprising the steps of:
Step S21-step S26 are performed for each fruit;
Step S21: collecting color images of fruits;
step S22: converting the format of the color image from RGB format to HSI format;
Step S23: extracting a plurality of chromaticities from a color image in an HSI format;
step S24: counting the occurrence frequency of each chromaticity in the color image in the HSI format, and generating a plurality of corresponding frequency sequences;
Step S25: inputting the generated multiple frequency sequences into the mapper, and outputting the solid-acid ratio corresponding to each fruit;
Step S26: taking the solid-acid ratio output by the mapper as the first ripeness of the fruit;
the clustering of all the first maturity comprises the following steps:
sequencing all the first maturity according to ascending order to obtain a numerical sequence;
uniformly dividing the numerical sequence into a plurality of numerical intervals according to the residual quantity of the storage bins;
Extracting first maturity of each numerical range at the middle position, and taking the extracted first maturity as a plurality of clustering centers;
Setting a Euclidean distance;
And clustering all the first maturity by using a K-means clustering algorithm according to the residual quantity of the storage bins, a plurality of clustering centers and the Euclidean distance to obtain a clustering result.
2. A fruit selection and distribution method according to claim 1, wherein before extracting the first maturity of each numerical interval at the intermediate position, the method comprises the steps of: and eliminating abnormal data in each numerical value interval.
3. A fruit selection and distribution method according to claim 1, characterized in that before the time-stamping is assigned to each bin, it comprises the following steps:
collecting a plurality of second test samples;
Step S31-step S33 are carried out on each second test sample, so that the solid acid ratio of a plurality of second test samples is obtained; wherein, step S31: continuously monitoring each second test sample fruit by utilizing an electronic nose monitoring technology within a first preset time period to obtain a monitoring result, wherein the monitoring result is used for marking the fruit to start spoilage; step S32: marking a monitoring time point corresponding to the monitoring result; step S33: sampling and detecting the solid acid ratio of the second test sample fruit at the monitoring time point;
and taking the median of the solid-acid ratios of a plurality of second test fruits to obtain the maturity threshold.
4. A fruit selection and distribution method according to claim 1, further comprising the steps of, before assigning a time stamp to each bin:
collecting a plurality of third test samples;
Executing the steps S21 to S26 on each third test sample in a second preset time period, and recording the first maturity of each third test sample to generate a fifth test sample;
Performing polynomial fitting by using the second preset time period and the fifth test sample to obtain a relation model of maturity and time;
And obtaining the time length required for the maturity of each fruit to change from the first maturity to the maturity threshold according to the relation model.
5. The fruit selection and distribution method according to claim 4, wherein said predicting the second maturity of each fruit in said target bin at said order dispatch time comprises the steps of:
the following steps are performed for each fruit:
drawing a trend chart of the maturity changing along with time according to the relation model;
Marking the order dispatch time in the trend graph;
reading the corresponding maturity from the trend graph according to the marked order dispatch time;
The read maturity is taken as the second maturity.
6. A fruit selection and distribution method according to claim 1, wherein said obtaining an estimate of the maximum storage time period for each fruit in said target storage bin for transportation within said transportation storage environment is preceded by the steps of:
Establishing a maturity quantization model of the fruits in the transportation process; the maturity quantization model is used for reflecting the change rate of the maturity of the fruits in the transportation and storage environment;
And obtaining the time period required by the fruit to change from the second maturity to the maturity threshold value by using the maturity quantization model.
7. The fruit selection and distribution method according to claim 6, wherein the maturity quantization model has the expression: ; wherein f represents the rate of change of the ripeness of the fruit in the transportation storage environment; /(I) The weight of the ith detection index of the fruit maturity; /(I)An ith detection index indicating fruit maturity during the edible period,/>An ith detection index indicating fruit maturity during the pickable period,/>An i-th detection indicator representing fruit maturity during physiological maturity, i=1, 2..n, n representing the number of detection indicators of fruit maturity; /(I)And representing the corresponding influence factors of the transportation storage environment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410353426.9A CN117952499B (en) | 2024-03-27 | 2024-03-27 | Fruit selecting and transporting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410353426.9A CN117952499B (en) | 2024-03-27 | 2024-03-27 | Fruit selecting and transporting method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117952499A CN117952499A (en) | 2024-04-30 |
| CN117952499B true CN117952499B (en) | 2024-06-11 |
Family
ID=90793058
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410353426.9A Active CN117952499B (en) | 2024-03-27 | 2024-03-27 | Fruit selecting and transporting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117952499B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018211366A1 (en) * | 2017-05-18 | 2018-11-22 | 株式会社半導体エネルギー研究所 | Image detection module and information management system |
| EP3889597A1 (en) * | 2018-11-30 | 2021-10-06 | Universidad De Concepcion | In-line system for detecting the quality of fruit via ultrasound |
| CN113822748A (en) * | 2021-11-19 | 2021-12-21 | 季华实验室 | Fruit picking method and device, electronic equipment and storage medium |
| CN115660383A (en) * | 2022-12-12 | 2023-01-31 | 成都工业职业技术学院 | Agricultural product production and marketing resource balanced distribution analysis method, system, terminal and medium |
-
2024
- 2024-03-27 CN CN202410353426.9A patent/CN117952499B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018211366A1 (en) * | 2017-05-18 | 2018-11-22 | 株式会社半導体エネルギー研究所 | Image detection module and information management system |
| EP3889597A1 (en) * | 2018-11-30 | 2021-10-06 | Universidad De Concepcion | In-line system for detecting the quality of fruit via ultrasound |
| CN113822748A (en) * | 2021-11-19 | 2021-12-21 | 季华实验室 | Fruit picking method and device, electronic equipment and storage medium |
| CN115660383A (en) * | 2022-12-12 | 2023-01-31 | 成都工业职业技术学院 | Agricultural product production and marketing resource balanced distribution analysis method, system, terminal and medium |
Non-Patent Citations (2)
| Title |
|---|
| 湖北国储武汉分公司冷库建设的可行性分析;吕俊华;《中国优秀硕士学位论文全文数据库经济与管理科学辑》;20180115(第1期);第J149-685页 * |
| 高光谱技术结合特征波长/光谱指数对冬枣成熟度可视化判别;曹晓峰 等;《光谱学与光谱分析》;20180715(第7期);第189-196页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117952499A (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110648069B (en) | Vegetable quality analysis system based on transport vehicle | |
| US11003958B2 (en) | Food quality image classification | |
| CN114219847B (en) | Method and system for determining crop planting area based on phenological characteristics and storage medium | |
| US11847681B2 (en) | Ultraviolet light and machine learning-based assessment of food item quality | |
| CN113435726A (en) | Commodity management method and system | |
| Wei et al. | Prediction of the maturity of greenhouse grapes based on imaging technology | |
| CN111881864A (en) | Wisdom farming crops growth full-period full-dynamic monitoring management system | |
| Jiang et al. | Identification of tomato maturity based on multinomial logistic regression with kernel clustering by integrating color moments and physicochemical indices | |
| CN113295690A (en) | Strawberry maturity rapid discrimination method based on machine learning | |
| CN113808153A (en) | Tomato maturity detection method and device, computer equipment and storage medium | |
| CN117952499B (en) | Fruit selecting and transporting method | |
| CN109738438B (en) | Method for rapidly measuring aging degree of wheat leaves | |
| Raka et al. | Taste-wise fruit sorting system using thermal image processing | |
| Heryanto et al. | Classification of Coffee Beans Defect Using Mask Region-based Convolutional Neural Network | |
| CN116911698B (en) | Food and drug detection system | |
| CN111077146A (en) | Vegetable quality evaluation system | |
| CN116805239A (en) | Fresh commodity safety intelligent detection management method and system based on big data | |
| CN115130965B (en) | Dish refrigerated transportation delivery monitoring management cloud platform based on central kitchen | |
| CN115616034A (en) | Method and system for detecting food freshness | |
| CN114494405A (en) | Strawberry shape estimation and automatic grading method and device and computer storage medium | |
| CN112770080B (en) | Meter reading method, meter reading device and electronic equipment | |
| CN117391594B (en) | Fresh product storage control method and system | |
| CN118152623B (en) | Intelligent logistics information storage method and system based on cloud platform | |
| CN114399231B (en) | Orchard inspection frequency adjusting method and device, electronic equipment and storage medium | |
| CN115909300A (en) | Construction method of kernel fruit tree yield prediction model |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |