Fruit quality prediction method and device

Abstract

The embodiments of the present disclosure provide a fruit quality prediction method, which is applied to the field of fruit quality prediction. The method includes collecting crop information, ecological management information, and quality information; determining the fruit trees whose quality is to be tested based on the crop information; assigning a corresponding preset score to a data element in the fruit tree quality information based on the correlation between each data element and the quality in the ecological management information; calculating the weight of each data element in the quality factor based on the preset score corresponding to the data element and the number of key data elements in the ecological management information; monitoring the fruit tree quality factors for many consecutive years and calculating the correction coefficient corresponding to the monitoring year; and predicting the quality of the fruit produced by the fruit tree in the quality factor based on the weight of each data element in the quality factor, the correction coefficient corresponding to the monitoring year, and the data elements of each monitoring year. This improves data richness, prediction accuracy, and scientificity, and enhances applicability and practicality.

Description

Technical Field

[0001] The present disclosure relates to the field of fruit quality prediction, and in particular to a fruit quality prediction method and device. Background Art

[0002] There are several methods for predicting the quality of agricultural products on the market: one is the near-infrared spectroscopy method, which can only be used to predict the quality of agricultural products after they are mature and obtained, and is more like a non-destructive testing method; the second is the morphological method, which predicts the yield of agricultural products by analyzing the growth morphology of agricultural products at various growth stages. The prediction accuracy of this method is low because the morphology of agricultural products is not strongly correlated with the morphology of the plants themselves and is easily affected by the external environment. For example, if there is wind when taking morphological photos, its accuracy will be reduced; the third is the process information method, which predicts the quality of agricultural products by summarizing the crop growth process information and using big data to analyze the summarized crop growth process information. Although this method The method has been applied to crops such as rapeseed and tea, but it has the following defects: (1) Because rapeseed is an annual crop and the roasting process of tea is independent of each other every year, the annual data of crops such as rapeseed and tea lack strong continuity, which will affect the accuracy of prediction; (2) At present, this method only considers the information changes of the crop itself, does not pay attention to the influence of people, and does not collect or only collects a small amount of specific information on agricultural operations, such as time, method, operation amount, operator, etc. The data richness needs to be further improved; (3) There is a lack of research on the relationship between the product quality of the same crop in different years, and it is not suitable for quality prediction of fruits produced by perennial fruit trees. Summary of the Invention

[0003] The present disclosure provides a fruit quality prediction method, apparatus, device and storage medium.

[0004] According to a first aspect of the present disclosure, a method for predicting fruit quality is provided. The method comprises:

[0005] Collecting crop information, ecological management information and quality information and storing them in a storage unit;

[0006] Determine the fruit trees whose fruit quality is to be predicted based on crop information;

[0007] For a quality factor in the fruit tree quality information, assign a corresponding preset score to each data element according to the correlation between each data element and the quality in the ecological management information;

[0008] Calculate the weight of each data element in the quality factor based on the preset score corresponding to each data element and the number of key data elements in the ecological management information;

[0009] Conducting quality monitoring on the quality factors of the fruit trees for many consecutive years and calculating correction coefficients corresponding to the quality monitoring years;

[0010] The quality of the fruit produced by the fruit tree in the quality factor is predicted based on the weight of each data element in the quality factor, the correction coefficient corresponding to each quality monitoring year and the data element of each quality monitoring year.

[0011] In some implementations of the first aspect, calculating the weight of each data element in the quality factor based on a preset score corresponding to each data element and the number of key data elements in the ecological management information includes:

[0012] Calculate the weight of each unit of information in the ecological management information based on the number of key data elements in the ecological management information;

[0013] Calculate the weight of each data element in the corresponding unit information according to the preset score corresponding to each data element;

[0014] The weight of each data element in the quality factor is calculated according to the weight corresponding to each unit information and the weight of each data element in the corresponding unit information.

[0015] In some implementations of the first aspect, the unit information includes environmental information, soil information, related biological information, farming information, and harvest information;

[0016] The quality factors include diameter, weight, hardness, sugar content, acidity, aroma, and nutritional content.

[0017] In some implementations of the first aspect, according to the ecological management information

[0018] The correlation between each data element and quality is calculated, and each data element is assigned a corresponding preset score, including:

[0019] If a data element in the ecological management information directly affects the quality of the fruit, the default score of the corresponding data element is 1 point;

[0020] If a data element in the ecological management information indirectly affects fruit quality by affecting a data element that directly affects fruit quality, the preset score for the corresponding data element is 0.7 points;

[0021] If a data element in the ecological management information indirectly affects fruit quality by affecting crops, the preset score of the corresponding data element is 0.4 points;

[0022] If the data element in the ecological management information does not affect the quality of the fruit, the preset score of the corresponding data element is 0.1 points.

[0023] In some implementations of the first aspect, the key data element is a data element that directly affects the quality of the fruit.

[0024] Quality data element.

[0025] In some implementations of the first aspect, the quality factors of the fruit trees are monitored for multiple consecutive years, and the correction coefficients corresponding to the quality monitoring years are calculated, including:

[0026] Conducting quality monitoring on the quality factors of the fruit trees for many consecutive years to obtain the quality corresponding to the quality factors in each quality monitoring year;

[0027] The ratio of the quality of the quality factor obtained in the i-th year to the sum of the qualities corresponding to the quality factors in each quality monitoring year is used as the correction coefficient corresponding to the i-th year.

[0028] In some implementations of the first aspect, predicting the quality of the fruit produced by the fruit tree in the quality factor based on the weight of each data element in the quality factor, the correction coefficient corresponding to each quality monitoring year, and the data element of each quality monitoring year includes:

[0029] For the same digital data element, subtract the value of the digital data element in year (i-1) from the value of the digital data element in year (i-1) to obtain a subtraction result, calculate the ratio of the subtraction result to the value of the digital data element in year (i-1) to obtain a deviation rate of the digital data element; obtain the deviation rate of each digital data element according to the method for obtaining the deviation rate of a digital data element and obtain the maximum deviation rate of the digital data elements;

[0030] Use fuzzy judgment method to score the changes of each non-numeric data element, and obtain the score of each non-numeric data element and the highest score;

[0031] Based on the maximum deviation rate and the highest score of the digital data element, calculate the deviation rate of the non-digital data element corresponding to the highest score; based on the deviation rate of the non-digital data element corresponding to the highest score and the score of each non-digital data element, calculate the deviation rate of each non-digital data element;

[0032] Multiplying the deviation rate of each data element by the weight corresponding to the data element in the quality factor, and accumulating the multiplication results;

[0033] The accumulated value is multiplied by the correction coefficient corresponding to the i-th year to obtain the quality of the fruit produced by the fruit tree in the i-th year in the quality factor;

[0034] According to the method for obtaining the quality of the i-th year, the quality of the fruit produced by the fruit tree in each monitoring year in the quality factors is obtained and the average value is taken to obtain the quality of the fruit produced by the fruit tree in the current year in the quality factors.

[0035] In some implementations of the first aspect, the method further includes:

[0036] After the fruits produced by the fruit trees in the current year are mature, testing the quality of the fruits produced by the fruit trees in the current year in terms of the quality factors;

[0037] Recalculate the correction coefficient corresponding to each quality monitoring year based on the test results.

[0038] According to a second aspect of the present disclosure, a fruit quality prediction device is provided. The device comprises:

[0039] An information collection module, used to collect crop information, ecological management information and quality information and store them in a storage unit;

[0040] The module for determining fruit trees to be tested is used to determine the fruit trees whose fruit quality is to be predicted based on crop information;

[0041] A preset score assignment module is used to assign a corresponding preset score to each data element in the fruit tree quality information according to the association between each data element and the quality in the ecological management information;

[0042] A weight calculation module, used to calculate the weight of each data element in the quality factor based on the preset score corresponding to each data element and the number of key data elements in the ecological management information;

[0043] A correction coefficient calculation module is used to monitor the quality factors of the fruit trees for many consecutive years and calculate the correction coefficients corresponding to the quality monitoring years;

[0044] The quality prediction module is used to predict the quality of the fruit produced by the fruit tree in the quality factors based on the weight of each data element in the quality factors, the correction coefficient corresponding to each quality monitoring year and the data element of each quality monitoring year.

[0045] According to a third aspect of the present disclosure, an electronic device is provided. The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method described above.

[0046] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method described above.

[0047] In the present disclosure, crop information, ecological management information and quality information are collected and stored in a storage unit; wherein, the ecological management information includes five unit information; the fruit tree whose fruit quality is to be predicted is determined based on the crop information; for a quality factor in the fruit tree quality information, the weight corresponding to each unit information is calculated based on the number of key data elements in the ecological management information; according to the association between each data element and the quality in the ecological management information, the data element is assigned a corresponding preset score, and the weight of each data element in the corresponding unit information is calculated; according to the weight corresponding to each unit information and the weight of each data element in the corresponding unit information, the weight of each data element in the quality factor is calculated; the quality factor of the fruit tree is monitored for many consecutive years, and the correction coefficient corresponding to the quality monitoring year is calculated; according to the weight of each data element in the quality factor, the correction coefficient corresponding to each quality monitoring year and the data element in each quality monitoring year, the quality of the fruit produced by the fruit tree in the quality factor is predicted. In this way, the list of data elements is enriched, the data richness and prediction accuracy are improved, and the weighting of each data element improves the efficiency and scientificity of data utilization. The quality monitoring of quality factors of fruit trees for many consecutive years makes this method more suitable for perennial fruit trees, with greater applicability and practicality.

[0048] It should be understood that the contents described in the Summary of the Invention section are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are provided for a better understanding of the present disclosure and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0050] Figure 1 A flow chart of a fruit quality prediction method provided by an embodiment of the present disclosure is shown;

[0051] Figure 2 A structural diagram of a fruit quality prediction device provided by an embodiment of the present disclosure is shown;

[0052] Figure 3 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0053] To make the purpose, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present disclosure.

[0054] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0055] In response to the problems arising from the background technology, the embodiments of the present disclosure provide a fruit quality prediction method and device. Specifically, crop information, ecological management information and quality information are collected and stored in a storage unit; wherein, the ecological management information includes five unit information; the fruit tree whose fruit quality is to be predicted is determined based on the crop information; for a quality factor in the fruit tree quality information, the weight corresponding to each unit information is calculated based on the number of key data elements in the ecological management information; according to the association between each data element and the quality in the ecological management information, the data element is assigned a corresponding preset score, and the weight of each data element in the corresponding unit information is calculated; according to the weight corresponding to each unit information and the weight of each data element in the corresponding unit information, the weight of each data element in the quality factor is calculated; the quality factor of the fruit tree is continuously monitored for many years, and the correction coefficient corresponding to the quality monitoring year is calculated; according to the weight of each data element in the quality factor, the correction coefficient corresponding to each quality monitoring year and the data element in each quality monitoring year, the quality of the fruit produced by the fruit tree in the quality factor is predicted. In this way, the list of data elements is enriched, the data richness and prediction accuracy are improved, and the weighting of each data element improves the efficiency and scientificity of data utilization. The quality monitoring of quality factors of fruit trees for many consecutive years makes this method more suitable for perennial fruit trees, with greater applicability and practicality.

[0056] The fruit quality prediction method and device provided by the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings through specific embodiments.

[0057] Figure 1 A flowchart of a fruit quality prediction method provided by an embodiment of the present disclosure is shown. The method 100 includes the following steps:

[0058] S110 , collecting crop information, ecological management information, and quality information and storing them in a storage unit.

[0059] In some embodiments, the crop information includes crop name, variety, and planting time;

[0060] Ecological management information includes unit information, which includes environmental information, soil information, related biological information, farming information, and harvesting information;

[0061] The data elements in the environmental information include geographical location, ambient temperature, humidity, rainfall, light intensity, and wind speed;

[0062] The data elements in soil information include soil temperature, moisture, and element content (such as the content of N, K, P, Ca, Mg, S, Fe, Cu, B, Zn, Mo, Se, Mn, I, Cl, etc.);

[0063] The data elements in the associated biological information include pathogenic microorganisms, pests, natural enemy insects, weeds, and birds;

[0064] The data elements in the agricultural information include the operation time, operator information, tools used, input types and amounts of tillage / pesticide spraying / fertilization / watering / flower and fruit thinning / artificial pollination / bagging / bagging / fruit rotation operations;

[0065] The data elements in the harvesting information include harvesting time, harvester information, harvesting tools, and harvesting maturity;

[0066] Quality information includes quality factors, which include diameter, weight, hardness, sugar content, acidity, aroma, and nutritional content.

[0067] In some embodiments, the types of data elements are divided into digital data elements and non-digital data elements. Digital data elements refer to data elements whose size can be represented by numbers. For example, the high and low ambient temperatures can be represented by numbers, so the ambient temperature is a digital data element. Non-digital data elements refer to data elements that represent the state of the data element in non-digital form. For example, the state of pathogenic microorganisms in different years is described in non-digital forms such as text, so pathogenic microorganisms belong to non-digital data elements.

[0068] In some embodiments, crop information, ecological management information, and quality information are obtained through IoT devices or manual collection, and classifying and storing this information in a storage unit facilitates the subsequent calculation of weights, correction coefficients, etc. based on this information.

[0069] S120: Determine the fruit trees whose fruit quality is to be predicted based on the crop information.

[0070] S130 , for a quality factor in the fruit tree quality information, assign a corresponding preset score to each data element according to the association between each data element and the quality in the ecological management information.

[0071] In some embodiments, if a data element in the ecological management information directly affects the quality of the fruit (strong correlation), the preset score of the corresponding data element is 1 point;

[0072] If a data element in the ecological management information indirectly affects fruit quality by affecting a data element that directly affects fruit quality (medium association), the preset score for the corresponding data element is 0.7 points;

[0073] If the data element in the ecological management information indirectly affects the quality of fruit by affecting crops (weak correlation), the preset score of the corresponding data element is 0.4 points;

[0074] If the data element in the ecological management information does not affect the quality of the fruit (only relevant), the preset score of the corresponding data element is 0.1 points.

[0075] S140: Calculate the weight of each data element in the quality factor according to the preset score corresponding to each data element and the number of key data elements in the ecological management information.

[0076] In some embodiments, the weight of each data element in the quality factor is calculated based on the preset score corresponding to each data element and the number of key data elements in the ecological management information, including:

[0077] Calculate the weight of each unit of information in the ecological management information based on the number of key data elements in the ecological management information;

[0078] Calculate the weight of each data element in the corresponding unit information according to the preset score corresponding to each data element;

[0079] The weight of each data element in the quality factor is calculated based on the weight corresponding to each unit information and the weight of each data element in the corresponding unit information; wherein,

[0080] Key data elements are data elements that directly affect the quality of fruit (strong correlation).

[0081] In some embodiments, the number of key data elements in environmental information is q1, the number of key data elements in soil information is q2, the number of key data elements in associated biological information is q3, the number of key data elements in agricultural information is q4, and the number of key data elements in harvest information is q5.

[0082] The weight a1 = q1 / (q1+q2+q3+q4+q5), the weight corresponding to soil information a2 = q2 / (q1+q2+q3+q4+q5), and so on, the weight corresponding to each unit information can be obtained; among which, the sum of the weights corresponding to each unit information is equal to 1.

[0083] In some embodiments, the corresponding preset scores of each data element are calculated.

[0084] The weight within the unit information includes:

[0085] Calculate the sum of the preset scores of all data elements in a certain unit of information;

[0086] The ratio of the preset score of a data element in the unit information to the sum of the preset scores of all data elements

[0087] The value is used as the weight of the data element in the unit information;

[0088] For example, when the unit information is environmental information, the preset score corresponding to the geographical location is 0.1, and the environmental

[0089] The preset score of temperature is 0.7, the preset score of humidity is 0.7, the preset score of rainfall is 0.4, the preset score of light intensity is 1, and the preset score of wind force is 0.1. Then the weight of geographical location in environmental information is b1=0.1 / (0.1+0.7+0.7+0.4+1.0+0.1). By analogy, the weight of each data element in the environmental information can be obtained, and the weight of the data element in each unit information in its corresponding unit information can also be obtained.

[0090] In some embodiments, the selected quality factor is acidity, the weight corresponding to the environmental information is a1, the weight of the geographical location in the environmental information is b1, and the weight of the ambient temperature in the environmental information is b2. Then the weight of the geographical location in the acidity is c1=a1×b1, the weight of the ambient temperature in the acidity is c2=a1×b2, and so on. The weight of each data element under the selected quality factor can be obtained.

[0091] In some embodiments, the correlation between each data element and the fruit quality is analyzed by a qualitative analysis method to obtain key data elements with strong correlation.

[0092] S150, monitoring the quality factors of the fruit trees for multiple consecutive years, and calculating correction coefficients corresponding to the quality monitoring years.

[0093] In some embodiments, the quality factors of the fruit trees are monitored for multiple consecutive years, and the correction coefficients corresponding to the quality monitoring years are calculated, including:

[0094] Conducting quality monitoring on the quality factors of the fruit trees for many consecutive years to obtain the quality corresponding to the quality factors in each quality monitoring year;

[0095] The ratio of the quality of the quality factor of the i-th year to the sum of the quality factors corresponding to each quality monitoring year is used as the correction coefficient corresponding to the i-th year;

[0096] For example, the acidity quality of the fruit produced by the same fruit tree is monitored for six consecutive years, and the quality of the acidity of the fruit produced by the fruit tree in each of these six years is obtained; the quality values of the acidity of the fruit produced in each of the six years are accumulated to obtain the total acidity quality value m; the quality value n1 of the acidity of the fruit produced by the fruit tree in the first year is ratioed with the total acidity quality value m to obtain the correction coefficient λ1 corresponding to the first quality monitoring year, that is, λ1=n1 / m. Similarly, the correction coefficient corresponding to any quality monitoring year in these six years can be obtained.

[0097] S160, predicting the quality of the fruit produced by the fruit tree in the quality factor based on the weight of each data element in the quality factor, the correction coefficient corresponding to each quality monitoring year, and the data element of each quality monitoring year.

[0098] In some embodiments, predicting the quality of the fruit produced by the fruit tree in the quality factor based on the weight of each data element in the quality factor, the correction coefficient corresponding to each quality monitoring year, and the data element of each quality monitoring year includes:

[0099] For the same digital data element (such as ambient temperature, element content, etc.), subtract the value of the digital data element in year i-1 from the value of the digital data element in year i-1 to obtain a subtraction result, calculate the ratio of the subtraction result to the value of the digital data element in year i-1, and obtain the deviation rate of the digital data element;

[0100] Obtaining the deviation rate of each digital data element according to the method for obtaining the deviation rate of the digital data element and obtaining the maximum deviation rate of the digital data element;

[0101] Use fuzzy judgment method to score the changes of each non-numeric data element, and obtain the score of each non-numeric data element and the highest score;

[0102] Based on the maximum deviation rate and the highest score of the digital data element, calculate the deviation rate of the non-digital data element corresponding to the highest score; based on the deviation rate of the non-digital data element corresponding to the highest score and the score of each non-digital data element, calculate the deviation rate of each non-digital data element;

[0103] Multiplying the deviation rate of each data element by the weight corresponding to the data element in the quality factor, and accumulating the multiplication results;

[0104] The accumulated value is multiplied by the correction coefficient corresponding to the i-th year to obtain the quality of the fruit produced by the fruit tree in the i-th year in the quality factor;

[0105] According to the method for obtaining the quality of the fruit in the i-th year, the quality of the fruit produced by the fruit tree in each monitoring year in the quality factor is obtained and the average value is taken to obtain the quality of the fruit produced by the fruit tree in the current year in the quality factor;

[0106] For example, there are w data elements in the ecological management information. The j-th data element in the i-th year is represented by Sij, Qij represents the deviation rate of the j-th data element in the i-th year, the weight corresponding to the j-th data element in the i-th year in acidity is represented by Cij, the quality of the fruit in acidity in the i-th year is represented by Pi, and the correction coefficient corresponding to the quality monitoring year in the i-th year is represented by λi. Then Pi is calculated by the following formula:

[0107] ;

[0108] If the jth data element in the i-th year is a numeric data element, then If the jth data element in the i-th year is a non-numeric data element, Qij is obtained by the following method:

[0109] Assuming that the maximum deviation rate of numeric data elements is 12%, for the same non-numeric data element, the fuzzy judgment method is used to compare the changes of the non-numeric data element in year i and year i-1 and score them. The scores include +5, +4, +3, +2, +1, 0, -1, -2, -3, -4, and -5. A positive score indicates that the non-numeric data element in year i has a positive effect on the acidity quality compared with year i-1. A score of 0 indicates that the non-numeric data element in year i has no special contribution to the acidity quality. A negative score indicates that the non-numeric data element in year i has a negative effect on the acidity quality. Assuming that the non-numeric data element The score of the non-numeric data element is +2; this scoring method is used to obtain the score of each non-numeric data element to obtain the highest score. Assume that the highest score is +4; according to the maximum deviation rate of the numeric data element (12%) and the highest score (+4), it can be obtained that the deviation rate of the non-numeric data element corresponding to the highest score is 12%. Therefore, the deviation rate Qij of the non-numeric data element with a score of +2 is (12% / +4)×(+2)=6%, that is, a positive change of 6%. Similarly, if the score of the non-numeric data element is -3, the corresponding deviation rate Qij is (12% / +4)×(-3)=-9%, that is, a negative change of 9%.

[0110] Using the deviation rate of data elements to calculate the acidity quality of fruit can solve the problem of inconsistent units of each data element. If there are 6 years of quality monitoring, that is, i is 6, then the average acidity quality of the fruit in these 6 years is taken to obtain the average quality. This average quality is the predicted acidity quality of the fruit of the fruit tree in the 7th year (i.e., the current year).

[0111] This method can also be used to predict the quality of other quality factors of the fruit tree and the quality of other fruit trees in other quality factors.

[0112] In some embodiments, the change in quality compared to the previous year can be determined based on the positive or negative value of the average quality. For example, when predicting the acidity quality of fruit, if the average quality is less than zero, it means that the acidity of the fruit in the current year has increased compared to the previous year.

[0113] In some embodiments, after the fruits produced by the fruit trees in the current year are ripe, the quality of the fruits produced by the fruit trees in the current year in terms of the quality factors is detected;

[0114] Recalculate the correction coefficient corresponding to each quality monitoring year based on the test results.

[0115] In some embodiments, for the same fruit tree, each time the quality of a quality factor is predicted, the prediction is performed again according to method 100 .

[0116] In some embodiments, the quality prediction model uses method 100 to predict fruit quality. The input of the quality prediction model is the data element in the ecological management information of the required prediction year, and the output is the prediction result of the fruit quality of the fruit tree in a certain quality factor in the required prediction year.

[0117] In some embodiments, data elements in the existing ecological management information of each monitoring year are used as training samples, and the fruit quality corresponding to each quality factor in each monitoring year of the same fruit tree is labeled; the quality prediction model is trained based on the training samples and the labels.

[0118] According to an embodiment of the present disclosure, crop information, ecological management information and quality information are collected and stored in a storage unit; wherein, the ecological management information includes five unit information; the fruit tree whose fruit quality is to be predicted is determined based on the crop information; for a quality factor in the fruit tree quality information, the weight corresponding to each unit information is calculated based on the number of key data elements in the ecological management information; according to the association between each data element and the quality in the ecological management information, the data element is assigned a corresponding preset score, and the weight of each data element in the corresponding unit information is calculated; according to the weight corresponding to each unit information and the weight of each data element in the corresponding unit information, the weight of each data element in the quality factor is calculated; the quality factor of the fruit tree is monitored for many consecutive years, and the correction coefficient corresponding to the quality monitoring year is calculated; according to the weight of each data element in the quality factor, the correction coefficient corresponding to each quality monitoring year and the data element in each quality monitoring year, the quality of the fruit produced by the fruit tree in the quality factor is predicted. In this way, the list of data elements is enriched, the data richness and prediction accuracy are improved, and the weighting of each data element improves the efficiency and scientificity of data utilization. The quality monitoring of quality factors of fruit trees for many consecutive years makes this method more suitable for perennial fruit trees, with greater applicability and practicality.

[0119] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0120] The above is an introduction to the method embodiment. The following is a further explanation of the solution disclosed in the present disclosure through an apparatus embodiment.

[0121] Figure 2 The structure diagram of a fruit quality prediction device provided by an embodiment of the present disclosure is shown. The device 200 includes:

[0122] The information collection module 210 is used to collect crop information, ecological management information and quality information and store them in a storage unit.

[0123] The fruit tree determination module 220 is used to determine the fruit trees whose fruit quality is to be predicted based on the crop information.

[0124] The preset score assignment module 230 is used to assign a corresponding preset score to each data element in the fruit tree quality information according to the association between each data element and the quality in the ecological management information.

[0125] In some embodiments, module 230 is specifically configured to:

[0126] According to the correlation between each data element and quality in the ecological management information, each data element is assigned a

[0127] The score should be preset, including:

[0128] If a data element in the ecological management information directly affects the quality of the fruit, the default score of the corresponding data element is 1 point;

[0129] If a data element in the ecological management information indirectly affects fruit quality by affecting a data element that directly affects fruit quality, the preset score for the corresponding data element is 0.7 points;

[0130] If a data element in the ecological management information indirectly affects fruit quality by affecting crops, the preset score of the corresponding data element is 0.4 points;

[0131] If the data element in the ecological management information does not affect the quality of the fruit, the preset score of the corresponding data element is 0.1 points.

[0132] The weight calculation module 240 is used to calculate the weight of each data element in the quality factor according to the preset score corresponding to each data element and the number of key data elements in the ecological management information.

[0133] In some embodiments, module 240 is specifically configured to:

[0134] The weight of each data element in the quality factor is calculated based on the preset score corresponding to each data element and the number of key data elements in the ecological management information, including:

[0135] Calculate the weight of each unit of information in the ecological management information based on the number of key data elements in the ecological management information;

[0136] Calculate the weight of each data element in the corresponding unit information according to the preset score corresponding to each data element;

[0137] The weight of each data element in the quality factor is calculated according to the weight corresponding to each unit information and the weight of each data element in the corresponding unit information.

[0138] In some embodiments, module 240 is further configured to:

[0139] Unit information, including environmental information, soil information, related biological information, farming information, and harvesting information;

[0140] Quality factors include diameter, weight, hardness, sugar content, acidity, aroma, and nutritional content.

[0141] In some embodiments, module 240 is further configured to:

[0142] Key data elements are data elements that directly affect the quality of fruits.

[0143] The correction coefficient calculation module 250 is used to monitor the quality factors of the fruit trees for many consecutive years and calculate the correction coefficients corresponding to the quality monitoring years.

[0144] In some embodiments, module 250 is specifically configured to:

[0145] Conducting quality monitoring on the quality factors of the fruit trees for many consecutive years and calculating the correction coefficients corresponding to the quality monitoring years, including:

[0146] Conducting quality monitoring on the quality factors of the fruit trees for many consecutive years to obtain the quality corresponding to the quality factors in each quality monitoring year;

[0147] The ratio of the quality of the quality factor obtained in the i-th year to the sum of the qualities corresponding to the quality factors in each quality monitoring year is used as the correction coefficient corresponding to the i-th year.

[0148] The quality prediction module 260 is used to predict the quality of the fruit produced by the fruit tree in the quality factor based on the weight of each data element in the quality factor, the correction coefficient corresponding to each quality monitoring year and the data element of each quality monitoring year.

[0149] In some embodiments, module 260 is specifically configured to:

[0150] Predicting the quality of the fruit produced by the fruit tree in the quality factor based on the weight of each data element in the quality factor, the correction coefficient corresponding to each quality monitoring year, and the data element of each quality monitoring year, including:

[0151] For the same digital data element, subtract the value of the digital data element in year (i-1) from the value of the digital data element in year (i-1) to obtain a subtraction result, calculate the ratio of the subtraction result to the value of the digital data element in year (i-1) to obtain a deviation rate of the digital data element; obtain the deviation rate of each digital data element according to the method for obtaining the deviation rate of a digital data element and obtain the maximum deviation rate of the digital data elements;

[0152] Use fuzzy judgment method to score the changes of each non-numeric data element, and obtain the score of each non-numeric data element and the highest score;

[0153] Based on the maximum deviation rate and the highest score of the digital data element, calculate the deviation rate of the non-digital data element corresponding to the highest score; based on the deviation rate of the non-digital data element corresponding to the highest score and the score of each non-digital data element, calculate the deviation rate of each non-digital data element;

[0154] Multiplying the deviation rate of each data element by the weight corresponding to the data element in the quality factor, and accumulating the multiplication results;

[0155] The accumulated value is multiplied by the correction coefficient corresponding to the i-th year to obtain the quality of the fruit produced by the fruit tree in the i-th year in the quality factor;

[0156] According to the method for obtaining the quality of the i-th year, the quality of the fruit produced by the fruit tree in each monitoring year in the quality factors is obtained and the average value is taken to obtain the quality of the fruit produced by the fruit tree in the current year in the quality factors.

[0157] In some embodiments, the apparatus 200 is further configured to:

[0158] After the fruits produced by the fruit trees in the current year are mature, testing the quality of the fruits produced by the fruit trees in the current year in terms of the quality factors;

[0159] Recalculate the correction coefficient corresponding to each quality monitoring year based on the test results.

[0160] It is understandable that Figure 2 Each module / unit in the illustrated device 200 has the function of implementing each step in the method 100 provided in the embodiment of the present disclosure and can achieve its corresponding technical effects. For the sake of brevity, they will not be described in detail here.

[0161] Figure 3 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. Electronic device 300 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 300 may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0162] like Figure 3 As shown, electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. RAM 303 can also store various programs and data required for the operation of electronic device 300. Computing unit 301, ROM 302, and RAM 303 are connected to each other via a bus 304. An I / O interface 305 is also connected to bus 304.

[0163] Multiple components in the electronic device 300 are connected to the I / O interface 305, including an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a magnetic disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0164] Computing unit 301 may be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Computing unit 301 performs the various methods and processes described above, such as method 100. For example, in some embodiments, method 100 may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed onto electronic device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by computing unit 301, one or more steps of method 100 described above may be performed. Alternatively, in other embodiments, computing unit 301 may be configured to perform method 100 in any other suitable manner (e.g., via firmware).

[0165] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0166] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0167] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0168] It should be noted that the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute method 100 and achieve the corresponding technical effect achieved by executing the method in the embodiment of the present disclosure. For the sake of concise description, they will not be repeated here.

[0169] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0170] The systems and techniques described herein can be implemented on a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with the systems and techniques described herein).

[0171] The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0172] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0173] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0174] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A fruit quality prediction method, characterized in that: include: Collecting crop information, ecological management information and quality information and storing them in a storage unit; Determine the fruit trees whose fruit quality is to be predicted based on crop information; For a quality factor in the fruit tree quality information, assign a corresponding preset score to each data element according to the correlation between each data element and the quality in the ecological management information; Calculate the weight of each data element in the quality factor based on the preset score corresponding to each data element and the number of key data elements in the ecological management information; Performing quality monitoring on the quality factors of the fruit trees for many consecutive years and calculating correction coefficients corresponding to the quality monitoring years, including: performing quality monitoring on the quality factors of the fruit trees for many consecutive years and obtaining the quality corresponding to the quality factors in each quality monitoring year; The ratio of the quality of the quality factor of the i-th year to the sum of the quality factors corresponding to each quality monitoring year is used as the correction coefficient corresponding to the i-th year; The quality of the fruit produced by the fruit tree in the quality factor is predicted based on the weight of each data element in the quality factor, the correction coefficient corresponding to each quality monitoring year and the data element of each quality monitoring year.

2. The method according to claim 1, characterized in that Calculating the weight of each data element in the quality factor based on the preset score corresponding to each data element and the number of key data elements in the ecological management information includes: Calculate the weight of each unit of information in the ecological management information based on the number of key data elements in the ecological management information; Calculate the weight of each data element in the corresponding unit information according to the preset score corresponding to each data element; The weight of each data element in the quality factor is calculated according to the weight corresponding to each unit information and the weight of each data element in the corresponding unit information.

3. The method according to claim 2, characterized in that The unit information includes environmental information, soil information, related biological information, farming information, and harvesting information; The quality factors include diameter, weight, hardness, sugar content, acidity, aroma, and nutritional content.

4. The method according to claim 1, wherein According to the ecological management information The correlation between each data element and quality is calculated, and each data element is assigned a corresponding preset score, including: If a data element in the ecological management information directly affects the quality of the fruit, the default score of the corresponding data element is 1 point; If a data element in the ecological management information indirectly affects fruit quality by affecting a data element that directly affects fruit quality, the preset score for the corresponding data element is 0.7 points; If a data element in the ecological management information indirectly affects fruit quality by affecting crops, the preset score of the corresponding data element is 0.4 points; If the data element in the ecological management information does not affect the quality of the fruit, the preset score of the corresponding data element is 0.1 points.

5. The method according to claim 1, wherein The key data elements are data elements that directly affect the quality of the fruit.

6. The method according to claim 1, characterized in that The method of predicting the quality of the fruit produced by the fruit tree in the quality factor based on the weight of each data element in the quality factor, the correction coefficient corresponding to each quality monitoring year, and the data element of each quality monitoring year includes: For the same digital data element, subtract the value of the digital data element in year (i-1) from the value of the digital data element in year (i-1) to obtain a subtraction result, calculate the ratio of the subtraction result to the value of the digital data element in year (i-1) to obtain a deviation rate of the digital data element; obtain the deviation rate of each digital data element according to the method for obtaining the deviation rate of a digital data element and obtain the maximum deviation rate of the digital data elements; Use fuzzy judgment method to score the changes of each non-numeric data element, and obtain the score of each non-numeric data element and the highest score; Based on the maximum deviation rate and the highest score of the digital data element, calculate the deviation rate of the non-digital data element corresponding to the highest score; based on the deviation rate of the non-digital data element corresponding to the highest score and the score of each non-digital data element, calculate the deviation rate of each non-digital data element; Multiplying the deviation rate of each data element by the weight corresponding to the data element in the quality factor, and accumulating the multiplication results; The accumulated value is multiplied by the correction coefficient corresponding to the i-th year to obtain the quality of the fruit produced by the fruit tree in the i-th year in the quality factor; According to the method for obtaining the quality of the i-th year, the quality of the fruit produced by the fruit tree in each monitoring year in the quality factors is obtained and the average value is taken to obtain the quality of the fruit produced by the fruit tree in the current year in the quality factors.

7. The method according to claim 6, characterized in that The method further comprises: After the fruits produced by the fruit trees in the current year are mature, testing the quality of the fruits produced by the fruit trees in the current year in terms of the quality factors; Recalculate the correction coefficient corresponding to each quality monitoring year based on the test results.

8. A fruit quality prediction device, characterized in that: include: An information collection module, used to collect crop information, ecological management information and quality information and store them in a storage unit; The module for determining fruit trees to be tested is used to determine the fruit trees whose fruit quality is to be predicted based on crop information; A preset score assignment module is used to assign a corresponding preset score to each data element in the fruit tree quality information according to the association between each data element and the quality in the ecological management information; A weight calculation module, used to calculate the weight of each data element in the quality factor based on the preset score corresponding to each data element and the number of key data elements in the ecological management information; A correction coefficient calculation module is used to continuously monitor the quality factors of the fruit trees for multiple years and calculate the correction coefficients corresponding to the quality monitoring years, including: continuously monitoring the quality factors of the fruit trees for multiple years and obtaining the quality corresponding to the quality factors in each quality monitoring year; and using the ratio of the quality of the quality factors obtained in the i-th year to the sum of the qualities corresponding to the quality factors in each quality monitoring year as the correction coefficient corresponding to the i-th year; The quality prediction module is used to predict the quality of the fruit produced by the fruit tree in the quality factors based on the weight of each data element in the quality factors, the correction coefficient corresponding to each quality monitoring year and the data element of each quality monitoring year.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

Images