Prediction model construction method and transportation route adjustment method

Abstract

The invention provides a prediction model construction method and a transportation route adjustment method, relates to the technical field of computers, and can overcome the problem that the maturity of agricultural products cannot be predicted. Factors influencing the maturity of the agricultural products comprise first-class data used for describing attributes of the agricultural products and second-class data used for describing the internal environment of the agricultural product carrier, and on the basis, a prediction model used for predicting the maturity of the agricultural products can be constructed according to the first-class data and the second-class data. The prediction model learns the relationship between the agricultural product attributes and the internal environment of the agricultural product carrier, so that the agricultural product maturity can be predicted, and related personnel can conveniently predict the agricultural product maturity in the future before transporting the agricultural products, so that the related personnel can make corresponding transportation decisions, and the transportation efficiency is improved. Therefore, the problem that the ripening degree of agricultural products is too high in the transportation process or after transportation is completed can be avoided.

Description

Technical Field

[0001] The present application relates to the field of computer technologies, and in particular, to a method for constructing a prediction model, an apparatus for constructing a prediction model, a method for adjusting a transportation route, an apparatus for adjusting a transportation route, a computer-readable storage medium, and an electronic device. Background Art

[0002] With the establishment and continuous development of the logistics network, the sales channels of agricultural products have gradually widened, and agricultural products in the production areas can be transported to various places for sale through various transportation means. Different agricultural products usually correspond to different ripening speeds. If the agricultural products are transported to the destination after they are overripe, it is likely to cause the problem that the quality of the agricultural products to be sold seriously deteriorates.

[0003] To solve this problem, in the related art, usually, the carrier personnel are arranged to check the ripeness of the agricultural products during the transportation process in a timely manner and adjust the transportation speed accordingly, or requirements are put forward for the ripeness of the agricultural products before transportation to avoid transporting agricultural products that are about to be overripe. It can be seen that in the above process, the ripeness of the agricultural products is a crucial factor.

[0004] However, even if the ripeness of the agricultural products is checked at any time during the transportation process or requirements are put forward for the ripeness before transportation, there may be a problem that the ripeness of the agricultural products is too high during and after the transportation process, and the ripeness of the agricultural products cannot be confirmed before the relevant personnel find that the ripeness of the agricultural products is too high.

[0005] It should be noted that the information disclosed in the above background art section is only used to strengthen the understanding of the background of the present application, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present application is to provide a method for constructing a prediction model, an apparatus for constructing a prediction model, a method for adjusting a transportation route, an apparatus for adjusting a transportation route, a computer-readable storage medium, and an electronic device, which can overcome the problem that the ripeness of agricultural products cannot be predicted. The present application considers that the factors affecting the ripeness of agricultural products include a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the vehicle carrying agricultural products. Based on this, a prediction model for predicting the ripeness of agricultural products can be constructed according to the first type of data and the second type of data. Since this prediction model has learned the relationship between the attributes of agricultural products and the internal environment of the vehicle carrying agricultural products, it can realize the prediction of the ripeness of agricultural products, which can facilitate the relevant personnel to predict the future ripeness of agricultural products before transporting the agricultural products, so that the relevant personnel can make corresponding transportation decisions, thereby helping to avoid the problem that the ripeness of agricultural products is too high during or after the transportation process.

[0007] Other features and advantages of the present application will become apparent from the following detailed description, or will be learned in part through the practice of the present application.

[0008] According to one aspect of the present application, a method for constructing a prediction model is provided, the method comprising:

[0009] Obtaining a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the agricultural product carrier;

[0010] Constructing a prediction model for predicting the maturity of agricultural products based on the first type of data and the second type of data.

[0011] In an exemplary embodiment of the present application, it further comprises:

[0012] Inputting target agricultural product data into the prediction model to trigger the prediction model to generate the maturity of the target agricultural product;

[0013] Wherein, the maturity of the target agricultural product is expressed as immature, mature or over-mature.

[0014] In an exemplary embodiment of the present application, obtaining a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the agricultural product carrier includes:

[0015] Obtaining a first type of data for describing the attributes of agricultural products; wherein, the first type of data includes at least one of the maturity at the time of loading and the flowering period of the agricultural product;

[0016] Periodically obtaining a second type of data for describing the internal environment of the agricultural product carrier; wherein, the second type of data includes at least one of temperature, humidity, ethylene gas concentration, and the loaded duration.

[0017] In an exemplary embodiment of the present application, constructing a prediction model for predicting the maturity of agricultural products based on the first type of data and the second type of data includes:

[0018] Constructing a maturity label based on the first type of data and the second type of data;

[0019] Generating sample data based on the first type of data, the second type of data, and the maturity label;

[0020] Constructing a prediction model for predicting the maturity of agricultural products through the sample data.

[0021] In an exemplary embodiment of the present application, constructing a prediction model for predicting the maturity of agricultural products through the sample data includes:

[0022] Sampling the sample data to obtain a first sampling result, and constructing a first decision tree model based on the first sampling result;

[0023] Sampling the sample data based on the first sampling result to obtain a second sampling result, and constructing a second decision tree model based on the second sampling result until a plurality of decision tree models satisfying a preset quantity are obtained; wherein, the plurality of decision tree models include a first decision tree model and a second decision tree model.

[0024] Integrating a plurality of decision tree models to obtain a prediction model for predicting the maturity of agricultural products.

[0025] According to one aspect of the present application, there is provided a prediction model construction device, including:

[0026] A data acquisition unit, configured to acquire a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the agricultural product carrier;

[0027] A model construction unit, configured to construct a prediction model for predicting the maturity of agricultural products based on the first type of data and the second type of data.

[0028] In an exemplary embodiment of the present application, it further includes:

[0029] A model calling unit, configured to input target agricultural product data into the prediction model to trigger the prediction model to generate the maturity of the target agricultural product;

[0030] Wherein, the maturity of the target agricultural product is expressed as immature, mature or overripe.

[0031] In an exemplary embodiment of the present application, it further includes:

[0032] A suggestion generation unit, configured to generate a transportation route suggestion and / or a transportation mode suggestion according to the transportation destination, the transportation target, and the maturity of the target agricultural product before transporting the agricultural product; wherein, the transportation target is used to define the maturity of the agricultural product when it reaches the transportation destination, and the maturity of the target agricultural product is predicted based on the prediction model.

[0033] In an exemplary embodiment of the present application, it further includes:

[0034] A dynamic adjustment unit, configured to dynamically adjust the transportation route and / or the transportation mode according to the transportation destination, the transportation target, and the maturity of the target agricultural product during the transportation of the agricultural product; wherein, the transportation target is used to define the maturity of the agricultural product when it reaches the transportation destination, and the maturity of the target agricultural product is predicted based on the prediction model.

[0035] In an exemplary embodiment of the present application, the data acquisition unit acquires a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the agricultural product carrier, including:

[0036] Obtain a type of data for describing the attributes of agricultural products; wherein, the type of data includes at least one of the maturity at the time of loading and the flowering period of the agricultural products;

[0037] Periodically obtain a second type of data for describing the internal environment of the agricultural product carrier; wherein, the second type of data includes at least one of temperature, humidity, ethylene gas concentration, and the loaded duration.

[0038] In an exemplary embodiment of the present application, the model construction unit constructs a prediction model for predicting the maturity of agricultural products based on the first type of data and the second type of data, including:

[0039] Construct a maturity label based on the first type of data and the second type of data;

[0040] Generate sample data based on the first type of data, the second type of data, and the maturity label;

[0041] Construct a prediction model for predicting the maturity of agricultural products through the sample data.

[0042] In an exemplary embodiment of the present application, the model construction unit constructs a prediction model for predicting the maturity of agricultural products through the sample data, including:

[0043] Sample the sample data to obtain a first sampling result, and construct a first decision tree model based on the first sampling result;

[0044] Sample the sample data based on the first sampling result to obtain a second sampling result, and construct a second decision tree model based on the second sampling result until a plurality of decision tree models meeting the preset quantity are obtained; wherein, the plurality of decision tree models include the first decision tree model and the second decision tree model.

[0045] Integrate the plurality of decision tree models to obtain a prediction model for predicting the maturity of agricultural products.

[0046] According to one aspect of the present application, there is provided a transportation route adjustment method, including:

[0047] During the transportation of agricultural products, dynamically adjust the transportation route and / or transportation mode according to the transportation destination, transportation target, and target agricultural product maturity; wherein, the transportation target is used to define the maturity of the agricultural products when reaching the transportation destination, and the target agricultural product maturity is predicted based on the prediction model.

[0048] In an exemplary embodiment of the present application, it further includes:

[0049] Before transporting agricultural products, generate a transportation route suggestion and / or a transportation mode suggestion according to the transportation destination, transportation target, and target agricultural product maturity.

[0050] In an exemplary embodiment of the present application, it further includes:

[0051] In response to an operation of inputting a transit location, dynamically adjust the transportation route according to the transit location, transportation destination, transportation target, and maturity of the target agricultural product; wherein, the adjusted transportation route includes a first sub-route composed of the current location and the transit location, and a second sub-route composed of the transit location and the transportation destination.

[0052] In an exemplary embodiment of the present application, it further includes:

[0053] In response to supplementary transported agricultural products with the transit location as the starting point of transportation, update the maturity of the target agricultural product based on the interaction between the supplementary transported agricultural products and the target agricultural product;

[0054] Based on the updated maturity of the target agricultural product, update the second sub-route and / or the transportation mode.

[0055] According to an aspect of the present application, there is provided a transportation route adjustment device, including:

[0056] A route adjustment unit, configured to dynamically adjust the transportation route and / or transportation mode according to the transportation destination, transportation target, and maturity of the target agricultural product during the transportation of agricultural products; wherein, the transportation target is used to define the maturity of the agricultural product when it reaches the transportation destination, and the maturity of the target agricultural product is obtained by prediction based on a prediction model.

[0057] In an exemplary embodiment of the present application, the route adjustment unit is further configured to:

[0058] In response to an operation of inputting a transit location, dynamically adjust the transportation route according to the transit location, transportation destination, transportation target, and maturity of the target agricultural product; wherein, the adjusted transportation route includes a first sub-route composed of the current location and the transit location, and a second sub-route composed of the transit location and the transportation destination.

[0059] In an exemplary embodiment of the present application, the route adjustment unit is further configured to:

[0060] In response to supplementary transported agricultural products with the transit location as the starting point of transportation, update the maturity of the target agricultural product based on the interaction between the supplementary transported agricultural products and the target agricultural product;

[0061] Based on the updated maturity of the target agricultural product, update the second sub-route and / or the transportation mode.

[0062] According to an aspect of the present application, there is provided a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the method of any one of the above.

[0063] According to one aspect of the present application, there is provided an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the method of any one of the above by executing the executable instructions.

[0064] The exemplary embodiments of the present application may have some or all of the following beneficial effects:

[0065] In the prediction model construction method provided by an exemplary embodiment of the present application, the problem that the maturity of agricultural products cannot be predicted can be overcome. The present application considers that the factors affecting the maturity of agricultural products include a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the vehicle carrying agricultural products. Based on this, a prediction model for predicting the maturity of agricultural products can be constructed according to the first type of data and the second type of data. Since this prediction model learns the relationship between the attributes of agricultural products and the internal environment of the vehicle carrying agricultural products, the prediction of the maturity of agricultural products can be realized, which can facilitate relevant personnel to predict the future maturity of agricultural products before transporting agricultural products, so that relevant personnel can make corresponding transportation decisions, thereby helping to avoid the problem of excessive maturity of agricultural products during or after transportation. In addition, the problem of the quality decline of agricultural products to be sold before sale can be avoided to a certain extent, ensuring the quality of agricultural products to be sold.

[0066] In the transportation route adjustment method provided by an exemplary embodiment of the present application, the transportation route and / or transportation mode can be automatically and dynamically adjusted based on the actual situation, which can help improve the utilization rate of transportation resources and reduce the loss rate of agricultural products.

[0067] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0069] Figure 1 Schematically shows a flowchart of a prediction model construction method according to an embodiment of the present application;

[0070] Figure 2 Schematically shows a flowchart of a prediction model construction method according to another embodiment of the present application;

[0071] Figure 3Schematically shows a system structure diagram for implementing a prediction model construction method according to an embodiment of the present application;

[0072] Figure 4 Schematically shows a system structure diagram for implementing a prediction model construction method according to another embodiment of the present application;

[0073] Figure 5 Schematically shows a structural block diagram of a prediction model construction device according to an embodiment of the present application;

[0074] Figure 6 Schematically shows a flowchart of a transportation route adjustment method according to an embodiment of the present application;

[0075] Figure 7 Schematically shows a structural block diagram of a transportation route adjustment device according to an embodiment of the present application;

[0076] Figure 8 Schematically shows a structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application. Detailed implementation manners

[0077] Now, example embodiments will be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more complete and comprehensive, and will fully convey the concept of the example embodiments to those skilled in the art. The features, structures, or characteristics described can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of the present application. However, those skilled in the art will realize that the technical solutions of the present application can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, well-known technical solutions are not shown or described in detail to avoid obscuring the various aspects of the present application.

[0078] In addition, the accompanying drawings are only schematic illustrations of the present application and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0079] Please refer to Figure 1 , Figure 1The flowchart of a method for constructing a prediction model according to an embodiment of the present application is schematically shown. As Figure 1 shown, the method for constructing the prediction model may include: step S110 to step S120.

[0080] Step S110: Obtain a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the carriers of agricultural products.

[0081] Step S120: Construct a prediction model for predicting the maturity of agricultural products based on the first type of data and the second type of data.

[0082] Implement Figure 1 The method shown can overcome the problem that the maturity of agricultural products cannot be predicted. The present application considers that the factors affecting the maturity of agricultural products include the first type of data for describing the attributes of agricultural products and the second type of data for describing the internal environment of the carriers of agricultural products. Based on this, a prediction model for predicting the maturity of agricultural products can be constructed according to the first type of data and the second type of data. Since the prediction model learns the relationship between the attributes of agricultural products and the internal environment of the carriers of agricultural products, the prediction of the maturity of agricultural products can be realized, which can facilitate relevant personnel to predict the future maturity of agricultural products before transporting them, so that relevant personnel can make corresponding transportation decisions, thereby helping to avoid the problem of excessive maturity of agricultural products during or after transportation. In addition, the problem of the quality decline of agricultural products to be sold before sale can be avoided to a certain extent, and the quality of agricultural products to be sold is guaranteed.

[0083] Next, the above steps of the present exemplary embodiment will be described in more detail.

[0084] In step S110, a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the carriers of agricultural products are obtained.

[0085] Specifically, agricultural products refer to agricultural products that rely on soil and / or water bodies for growth, such as apples, bananas, durians, coriander, potatoes, tuna, and shrimps. The first type of data for describing the attributes of agricultural products may include the specific attributes of the agricultural products to be transported. The fields of the first type of data corresponding to different agricultural products may be the same or different, which is not limited in the embodiments of the present application. The second type of data for describing the internal environment of the carriers of agricultural products may include the internal environment of the tools (such as containers, etc.) for loading agricultural products. The first type of data and the second type of data may be stored in the same storage space or in storage spaces with different reading speeds based on different call frequencies, which is not limited in the embodiments of the present application. The triggering timing of the data acquisition instruction may be before boxing or during boxing, which is not limited in the embodiments of the present application.

[0086] As an optional embodiment of step S110, obtaining a type of data for describing the attributes of agricultural products and a type of data for describing the internal environment of the agricultural product carrier includes:

[0087] Step S1101: obtaining a type of data for describing the attributes of agricultural products; wherein the type of data includes at least one of maturity at the time of loading and flowering period of agricultural products;

[0088] Step S1102: periodically acquiring two types of data for describing the internal environment of the agricultural product carrier; wherein the two types of data include at least one of temperature, humidity, ethylene gas concentration, and loading time.

[0089] It can be seen that the implementation of this optional embodiment can achieve differentiated collection of Class I data and Class II data, thereby obtaining accurate and sufficient data for constructing a model.

[0090] Specifically, since the first type of data used to describe the attributes of agricultural products is data that does not change over time, it can be acquired at one time. The second type of data used to describe the internal environment of the agricultural product carrier is dynamic data, so it needs to be acquired periodically.

[0091] Optionally, the first type of data = {maturity at loading, flowering period of agricultural products}, the second type of data = {temperature, humidity, ethylene gas concentration, loading time}, and the same batch of agricultural products can correspond to multiple different second types of data, such as second type of data 1 = {12, 30%, 25%, 35}, second type of data 2 = {15, 35%, 21%, 45}. Among them, the first type of data can be collected by infrared scanning equipment, and the second type of data can be collected by sensors set in the agricultural product carrier.

[0092] In step S120, a prediction model for predicting the maturity of agricultural products is constructed based on the first-category data and the second-category data.

[0093] Specifically, the prediction model for predicting the maturity of agricultural products is a multi-classification model, that is, the results that the prediction model needs to output are divided into multiple types. The prediction model can be: a generalized linear model (GLM) (such as a logistic regression model (LogisticRegression)), a tree model (such as a decision tree, random forests, gradient-boosted decision trees (GBDT), extreme gradient boosting (XGBoost), a framework implementing the GBDT algorithm (Light Gradient Boosting Machine, LightGBM), a machine learning algorithm (Categorical Boosting, CatBoost)), or a neural network (such as a convolutional neural network (CNN), long short-term memory (LSTM), etc.). The embodiments of the present application do not make any limitations in this regard.

[0094] As an optional embodiment of step S120, constructing a prediction model for predicting the maturity of agricultural products based on type-I data and type-II data includes:

[0095] Step S1201: Constructing maturity labels based on type-I data and type-II data;

[0096] Step S1202: Generating sample data based on type-I data, type-II data, and maturity labels;

[0097] Step S1203: Constructing a prediction model for predicting the maturity of agricultural products through the sample data.

[0098] It can be seen that implementing this optional embodiment can realize the model construction process based on the factors affecting the maturity of agricultural products, so as to obtain a model that can facilitate relevant personnel to predict the maturity of agricultural products in advance.

[0099] Specifically, different maturity labels can correspond to the same type-I data and the same type-II data (such as both corresponding to type-I data 1 and type-II data 1), the same type-I data and different type-II data (such as both corresponding to type-I data 1 but respectively corresponding to type-II data 1 and type-II data 2), or different type-I data and different type-II data (such as respectively corresponding to type-I data 1 and type-I data 2 and respectively corresponding to type-II data 3 and type-II data 4).

[0100] Among them, the method of constructing maturity labels based on type-one data and type-two data can be as follows: Determine the label construction timing according to a preset period (such as 1 hour, 6 hours, 1 day, etc.), obtain the target type-one data and target type-two data corresponding to the label construction timing, and construct corresponding maturity labels based on the target type-one data and target type-two data. Accordingly, multiple maturity labels (Label) corresponding to different label construction timings can be obtained.

[0101] In addition, the method of generating sample data based on type-one data, type-two data, and maturity labels can be: Generate sample data based on the container ID of the container for loading agricultural products, type-one data, type-two data, and maturity labels. Exemplarily, each sample data can be represented by the following table:

[0102]

[0103] Among them, different sample data corresponding to different IDs can also be understood as that, except for the field row, each row of data represents a piece of sample data. The column data corresponding to the same field can also characterize the data change trend of this field.

[0104] Based on the above sample data, a specified model structure can be trained to construct a prediction model for predicting the maturity of agricultural products.

[0105] Among them, optionally, in addition to constructing sample data, data of other types such as test data can also be constructed based on type-one data and type-two data, and accordingly, links such as testing and validating the prediction model can be completed to ensure the reliability of the prediction model. Regarding the proportion between the data participating in different links, this application does not make any limitations. For example, the data volume ratio between the sample data participating in the training link and the test data participating in the test link can be 7:3.

[0106] In addition, optionally, the comprehensive performance of the prediction model can also be evaluated based on a model evaluation metric (Area under the ROC Curve, AUC), and the evaluation result can be used as the basis for the prediction model to go online. And, optionally, the accuracy and recall rate under each classification can also be evaluated based on a confusion matrix, and this evaluation result can also be used as the basis for the prediction model to go online. And, optionally, the influence degree of any field value (i.e., feature value) in type-one data and type-two data on the output result of the prediction model can also be evaluated based on a SHAP Value, and this evaluation result can be used as the basis for feature optimization and feature engineering.

[0107] As an optional embodiment of step S1203, constructing a prediction model for predicting the maturity of agricultural products through sample data includes:

[0108] Step S12031: Sample the sample data to obtain a first sampling result, and construct a first decision tree model based on the first sampling result;

[0109] Step S12032: Sample the sample data based on the first sampling result to obtain a second sampling result, and construct a second decision tree model based on the second sampling result until multiple decision tree models meeting a preset quantity are obtained; among them, the multiple decision tree models include the first decision tree model and the second decision tree model;

[0110] Step S12033: Integrate the multiple decision tree models to obtain a prediction model for predicting the maturity of agricultural products.

[0111] It can be seen that by implementing this optional embodiment, a prediction model for predicting the maturity of agricultural products can be constructed based on the decision tree model, and then relevant personnel can conveniently predict the maturity of agricultural products at any time, so as to predict in advance the maturity of agricultural products at future times to assist in making decisions on agricultural product transportation.

[0112] Optionally, the sample data can be expressed as {X mn ,Y m}; where X mn is expressed as an m*n matrix, m represents the number of samples, n represents the number of features included in one sample, and Y is an m-dimensional vector used to represent the maturity label Label. Among them, after performing multiple sampling without replacement on the sample data, multiple (e.g., M kinds) of sampling results can be obtained. The subsequent sampling operation is based on the previous sampling result, and each sampling result can participate in the following calculations: information gain H(Y|X)=H(X,Y)-H(X), conditional entropy H(X,Y)=-∑P(X)H(Y|X=x), entropy H(X)=-∑p(x)log2p(x), to determine the feature with the maximum information gain as the node feature of the corresponding decision tree model. By performing the above calculations on multiple sampling results, multiple (e.g., T) decision tree models can be generated. Furthermore, a prediction model can be integrated from multiple decision tree models based on the principle of majority voting.

[0113] As an optional embodiment, it further includes:

[0114] Step S140: Input the target agricultural product data into the prediction model to trigger the prediction model to generate the maturity of the target agricultural product;

[0115] wherein, the maturity of the target agricultural product is expressed as immature, mature or overripe.

[0116] It can be seen that by implementing this optional embodiment, the prediction of the maturity of future agricultural products can be realized, thus facilitating risk intervention.

[0117] Specifically, the target agricultural product data may include at least one field value in the first type of data and at least one field value in the second type of data. It should be noted that step S140 is only an optional implementation manner. In actual application, the maturity of agricultural products can also be divided into other numbers (such as 4 types, 5 types) of categories, which are not limited in the embodiments of the present application.

[0118] As an optional embodiment, it further includes:

[0119] Step S150: Before transporting the agricultural products, generate a transportation route suggestion and / or a transportation mode suggestion according to the transportation destination, the transportation target, and the maturity of the target agricultural products; wherein, the transportation target is used to define the maturity of the agricultural products when they reach the transportation destination, and the maturity of the target agricultural products is obtained by prediction based on a prediction model.

[0120] It can be seen that by implementing this optional embodiment, a transportation route suggestion and / or a transportation mode suggestion can be given based on the transportation destination, the transportation target, and the maturity of the target agricultural products. Implementing transportation based on the transportation route suggestion and / or the transportation mode suggestion can help improve the utilization rate of transportation resources and reduce the loss rate of agricultural products.

[0121] Specifically, the transportation route suggestion and the transportation mode suggestion are output in any form such as text, image, voice, etc.

[0122] As an optional embodiment, it further includes:

[0123] Step S160: During the transportation of the agricultural products, dynamically adjust the transportation route and / or the transportation mode according to the transportation destination, the transportation target, and the maturity of the target agricultural products; wherein, the transportation target is used to define the maturity of the agricultural products when they reach the transportation destination, and the maturity of the target agricultural products is obtained by prediction based on a prediction model.

[0124] It can be seen that by implementing this optional embodiment, the transportation route and / or the transportation mode can be automatically and dynamically adjusted based on the actual situation, which can help improve the utilization rate of transportation resources and reduce the loss rate of agricultural products.

[0125] Specifically, the manner of dynamically adjusting the transportation route and / or the transportation mode can be: dynamically adjusting the transportation route being applied in the navigation software, and / or, dynamically adjusting any one or more of the transportation temperature, the ventilation volume, the transportation speed, etc. defined within the transportation mode.

[0126] Please refer to Figure 2 , Figure 2 which schematically shows a flowchart of a prediction model construction method according to another embodiment of the present application. As Figure 2 shown, the prediction model construction method includes: step S210 to step S270.

[0127] Step S210: Obtain a type of data for describing the attributes of agricultural products; wherein, the type of data includes at least one of the maturity at the time of loading and the flowering period of agricultural products.

[0128] Step S220: Periodically obtain a second type of data for describing the internal environment of the agricultural product carrier; wherein, the second type of data includes at least one of temperature, humidity, ethylene gas concentration, and the loaded duration.

[0129] Step S230: Construct a maturity label based on the first type of data and the second type of data, and generate sample data based on the first type of data, the second type of data, and the maturity label.

[0130] Step S240: Sample the sample data to obtain a first sampling result, construct a first decision tree model based on the first sampling result, sample the sample data based on the first sampling result to obtain a second sampling result, and construct a second decision tree model based on the second sampling result, until a plurality of decision tree models satisfying a preset quantity are obtained, and integrate the plurality of decision tree models to obtain a prediction model for predicting the maturity of agricultural products.

[0131] Step S250: Input the target agricultural product data into the prediction model to trigger the prediction model to generate the maturity of the target agricultural product; wherein, the maturity of the target agricultural product is expressed as immature, mature, or overripe.

[0132] Step S260: Before transporting agricultural products, generate a transportation route suggestion and / or a transportation mode suggestion according to the transportation destination, the transportation target, and the maturity of the target agricultural product; wherein, the transportation target is used to define the maturity of the agricultural product when it reaches the transportation destination, and the maturity of the target agricultural product is predicted based on the prediction model.

[0133] Step S270: During the transportation of agricultural products, dynamically adjust the transportation route and / or the transportation mode according to the transportation destination, the transportation target, and the maturity of the target agricultural product; wherein, the transportation target is used to define the maturity of the agricultural product when it reaches the transportation destination, and the maturity of the target agricultural product is predicted based on the prediction model.

[0134] It should be noted that steps S210 to S270 correspond to Figure 1 the respective steps and their embodiments shown. For the specific implementation manners of steps S210 to S270, reference can be made to Figure 1 the respective steps and their embodiments shown, and details are not described herein.

[0135] It can be seen that implementing Figure 2The method shown can overcome the problem that the maturity of agricultural products cannot be predicted. This application takes into account that the factors affecting the maturity of agricultural products include a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the vehicle carrying agricultural products. Based on this, a prediction model for predicting the maturity of agricultural products can be constructed according to the first type of data and the second type of data. Since this prediction model has learned the relationship between the attributes of agricultural products and the internal environment of the vehicle carrying agricultural products, it can realize the prediction of the maturity of agricultural products, which can facilitate relevant personnel to predict the future maturity of agricultural products before transporting them, so that relevant personnel can make corresponding transportation decisions, thereby helping to avoid the problem of excessive maturity of agricultural products during or after transportation. In addition, it can also avoid to a certain extent the problem of deterioration of the quality of agricultural products for sale before sale, ensuring the quality of agricultural products for sale.

[0136] Please refer to Figure 3 , Figure 3 which schematically shows a system structure diagram for implementing a prediction model construction method according to an embodiment of the present application. Figure 3 The system shown may include: a cloud server 310 on which a prediction model 311 is deployed, and a terminal device 320. Among them, the terminal device 320 can be implemented in any entity form, which is not limited in the embodiments of the present application.

[0137] Specifically, in one case, the prediction model 311 can be deployed in the cloud server 310 and provide a call interface to the terminal device 320. A user can send a call request to the cloud server 310 through the terminal device 320 to trigger the cloud server 310 to input the target agricultural product data in the call request into the prediction model 311, so that the prediction model 311 generates the target agricultural product maturity, and the cloud server 310 can return the target agricultural product maturity to the terminal device 320.

[0138] It can be seen that implementing Figure 3 the system shown can overcome the problem that the maturity of agricultural products cannot be predicted. This application takes into account that the factors affecting the maturity of agricultural products include a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the vehicle carrying agricultural products. Based on this, a prediction model for predicting the maturity of agricultural products can be constructed according to the first type of data and the second type of data. Since this prediction model has learned the relationship between the attributes of agricultural products and the internal environment of the vehicle carrying agricultural products, it can realize the prediction of the maturity of agricultural products, which can facilitate relevant personnel to predict the future maturity of agricultural products before transporting them, so that relevant personnel can make corresponding transportation decisions, thereby helping to avoid the problem of excessive maturity of agricultural products during or after transportation. In addition, it can also avoid to a certain extent the problem of deterioration of the quality of agricultural products for sale before sale, ensuring the quality of agricultural products for sale.

[0139] Please refer toFigure 4 , Figure 4 Schematically shows a system structure diagram for implementing a prediction model construction method according to another embodiment of the present application. Figure 4 The system shown may include: a terminal device 410 on which a prediction model 411 is deployed. Among them, the terminal device 410 may be implemented in any entity form, which is not limited in the embodiments of the present application.

[0140] Specifically, in another case, the trained prediction model 411 may also be opened to each terminal device 410 for deployment. The terminal device 410 may input target agricultural product data into the prediction model to trigger the prediction model to generate the maturity of the target agricultural product.

[0141] It can be seen that implementing Figure 4 the system shown can overcome the problem that the maturity of agricultural products cannot be predicted. The present application considers that the factors affecting the maturity of agricultural products include a type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the agricultural product carrier. Based on this, a prediction model for predicting the maturity of agricultural products can be constructed according to the first type of data and the second type of data. Since this prediction model learns the relationship between the attributes of agricultural products and the internal environment of the agricultural product carrier, it can realize the prediction of the maturity of agricultural products, which can facilitate relevant personnel to predict the future maturity of agricultural products before transporting them, so that relevant personnel can make corresponding transportation decisions, thereby helping to avoid the problem of excessive maturity of agricultural products during or after transportation. In addition, it can also avoid to a certain extent the problem of deterioration of the quality of agricultural products for sale before sale, and ensure the quality of agricultural products for sale.

[0142] Please refer to Figure 5 , Figure 5 which schematically shows a structural block diagram of a prediction model construction device according to an embodiment of the present application. The prediction model construction device 500 corresponds to Figure 1 the method shown. As Figure 5 shown, the prediction model construction device 500 includes:

[0143] A data acquisition unit 501, configured to acquire a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the agricultural product carrier;

[0144] A model construction unit 502, configured to construct a prediction model for predicting the maturity of agricultural products based on the first type of data and the second type of data.

[0145] It can be seen that implementing Figure 5The device shown can overcome the problem of unpredictable maturity of agricultural products. This application takes into account that the factors affecting the maturity of agricultural products include a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the vehicle carrying agricultural products. Based on this, a prediction model for predicting the maturity of agricultural products can be constructed according to the first type of data and the second type of data. Since this prediction model has learned the relationship between the attributes of agricultural products and the internal environment of the vehicle carrying agricultural products, it can realize the prediction of the maturity of agricultural products, which can facilitate relevant personnel to predict the future maturity of agricultural products before transporting them, so that relevant personnel can make corresponding transportation decisions, thus helping to avoid the problem of excessive maturity of agricultural products during or after transportation. In addition, it can also avoid to a certain extent the problem of deterioration of the quality of agricultural products for sale before sale, ensuring the quality of agricultural products for sale.

[0146] In an exemplary embodiment of the present application, it further includes:

[0147] A model calling unit, configured to input target agricultural product data into the prediction model to trigger the prediction model to generate the maturity of the target agricultural product;

[0148] Wherein, the maturity of the target agricultural product is expressed as immature, mature or overripe.

[0149] It can be seen that implementing this optional embodiment can realize the prediction of the future maturity of agricultural products, thus facilitating risk intervention.

[0150] In an exemplary embodiment of the present application, it further includes:

[0151] A suggestion generating unit, configured to generate a transportation route suggestion and / or a transportation method suggestion according to the transportation destination, the transportation target, and the maturity of the target agricultural product before transporting the agricultural product; wherein, the transportation target is used to define the maturity of the agricultural product when it reaches the transportation destination, and the maturity of the target agricultural product is predicted based on the prediction model.

[0152] It can be seen that implementing this optional embodiment can give a transportation route suggestion and / or a transportation method suggestion based on the transportation destination, the transportation target, and the maturity of the target agricultural product. Implementing transportation based on the transportation route suggestion and / or the transportation method suggestion can help improve the utilization rate of transportation resources and reduce the loss rate of agricultural products.

[0153] In an exemplary embodiment of the present application, it further includes:

[0154] A dynamic adjustment unit, configured to dynamically adjust the transportation route and / or the transportation method according to the transportation destination, the transportation target, and the maturity of the target agricultural product during the transportation of the agricultural product; wherein, the transportation target is used to define the maturity of the agricultural product when it reaches the transportation destination, and the maturity of the target agricultural product is predicted based on the prediction model.

[0155] It can be seen that implementing this optional embodiment can automatically and dynamically adjust the transportation route and / or transportation mode based on the actual situation, thereby facilitating the improvement of the utilization rate of transportation resources and reducing the loss rate of agricultural products.

[0156] In an exemplary embodiment of the present application, the data acquisition unit 501 acquires a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the agricultural product carrier, including:

[0157] Acquire a first type of data for describing the attributes of agricultural products; wherein, the first type of data includes at least one of the maturity at the time of loading and the flowering period of agricultural products;

[0158] Periodically acquire a second type of data for describing the internal environment of the agricultural product carrier; wherein, the second type of data includes at least one of temperature, humidity, ethylene gas concentration, and the loaded duration.

[0159] It can be seen that implementing this optional embodiment can achieve differentiated acquisition of the first type of data and the second type of data, thereby obtaining accurate and sufficient data for constructing the model.

[0160] In an exemplary embodiment of the present application, the model construction unit 502 constructs a prediction model for predicting the maturity of agricultural products based on the first type of data and the second type of data, including:

[0161] Construct a maturity label based on the first type of data and the second type of data;

[0162] Generate sample data based on the first type of data, the second type of data, and the maturity label;

[0163] Construct a prediction model for predicting the maturity of agricultural products through the sample data.

[0164] It can be seen that implementing this optional embodiment can achieve the model construction process based on the factors affecting the maturity of agricultural products, thereby obtaining a model that can facilitate relevant personnel to predict the maturity of agricultural products in advance.

[0165] In an exemplary embodiment of the present application, the model construction unit 502 constructs a prediction model for predicting the maturity of agricultural products through the sample data, including:

[0166] Sample the sample data to obtain a first sampling result, and construct a first decision tree model based on the first sampling result;

[0167] Sample the sample data based on the first sampling result to obtain a second sampling result, and construct a second decision tree model based on the second sampling result until a plurality of decision tree models meeting the preset quantity are obtained; wherein, the plurality of decision tree models include the first decision tree model and the second decision tree model.

[0168] Integrate multiple decision tree models to obtain a prediction model for predicting the maturity of agricultural products.

[0169] It can be seen that by implementing this optional embodiment, a prediction model for predicting the maturity of agricultural products can be constructed based on the decision tree model, and thus relevant personnel can conveniently predict the maturity of agricultural products at any time, so as to predict in advance the maturity of agricultural products at future times to assist in making decisions on the transportation of agricultural products.

[0170] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0171] Since each functional module of the prediction model construction device in the exemplary embodiments of the present application corresponds to the steps in the exemplary embodiments of the above prediction model construction method, for details not disclosed in the device embodiments of the present application, please refer to the embodiments of the above prediction model construction method of the present application.

[0172] Please refer to Figure 6 , Figure 6 schematically shows a flowchart of a prediction model construction method according to an embodiment of the present application. As Figure 6 shown, the prediction model construction method may include: step S610.

[0173] Step S610: During the transportation of agricultural products, dynamically adjust the transportation route and / or transportation method according to the transportation destination, transportation target, and target agricultural product maturity; wherein, the transportation target is used to define the maturity of the agricultural products when they reach the transportation destination, and the target agricultural product maturity is predicted based on the prediction model.

[0174] Specifically, the way to dynamically adjust the transportation route and / or transportation method may be: dynamically adjust the transportation route being applied in the navigation software, and / or, dynamically adjust any one or more of the transportation temperature, ventilation volume, transportation speed, etc. defined within the transportation method.

[0175] Implement Figure 6 the method shown, and the transportation route and / or transportation method can be automatically and dynamically adjusted based on the actual situation, which can help improve the utilization rate of transportation resources and reduce the loss rate of agricultural products.

[0176] In an exemplary embodiment of the present application, it further includes:

[0177] Before transporting agricultural products, generate transportation route suggestions and / or transportation mode suggestions based on the transportation destination, transportation target, and maturity of the target agricultural products.

[0178] Specifically, the transportation route suggestions and transportation mode suggestions are output in any form such as text, image, voice, etc.

[0179] It can be seen that implementing this optional embodiment can give transportation route suggestions and / or transportation mode suggestions based on the transportation destination, transportation target, and maturity of the target agricultural products. Implementing transportation based on the transportation route suggestions and / or transportation mode suggestions can help improve the utilization rate of transportation resources and reduce the loss rate of agricultural products.

[0180] In an exemplary embodiment of the present application, it further includes:

[0181] In response to the input operation of the transit location, dynamically adjust the transportation route according to the transit location, transportation destination, transportation target, and maturity of the target agricultural products; wherein, the adjusted transportation route includes a first sub-route composed of the current location and the transit location, and a second sub-route composed of the transit location and the transportation destination.

[0182] It can be seen that implementing this optional embodiment can timely adjust the transportation route when a new transit location is added during the user's transportation to meet the user's personalized needs.

[0183] Specifically, in one case, it can respond to eligible transit locations. When detecting the input operation of the transit location and after generating a new transportation route according to the transit location, transportation destination, transportation target, and maturity of the target agricultural products, it can compare the route deviation degree and the deviation of the journey time consumption between the new transportation route and the original transportation route. When both the route deviation degree and the deviation of the journey time consumption are within the preset threshold range, it is determined that the transit location is eligible, and then the transportation route can be dynamically adjusted according to the transit location, transportation destination, transportation target, and maturity of the target agricultural products.

[0184] In another case, it can respond to any transit location. When detecting the input operation of the transit location and after generating a new transportation route according to the transit location, transportation destination, transportation target, and maturity of the target agricultural products, it can update the maturity of the target agricultural products based on the new transportation route. If the maturity of the target agricultural products does not meet the preset conditions, an over-ripeness risk prompt is output. After detecting the confirmation operation for the over-ripeness risk prompt, the transportation route can be dynamically adjusted according to the transit location, transportation destination, transportation target, and maturity of the target agricultural products.

[0185] In an exemplary embodiment of the present application, it further includes:

[0186] In response to supplementary transported agricultural products with the transfer location as the starting point of transportation, based on the interaction between the supplementary transported agricultural products and the target agricultural products, update the maturity of the target agricultural products;

[0187] Based on the updated maturity of the target agricultural products, update the second sub-route and / or the transportation mode.

[0188] It can be seen that by implementing this optional embodiment, the interaction between the agricultural products supplemented at the transfer location and the original agricultural products can be taken into account, and then the route can be updated in a timely manner to avoid the problem of over-ripe agricultural products.

[0189] Specifically, the transfer location can be used as a midway rest location or as a location for supplementing agricultural products. When it is used as a location for supplementary transporting agricultural products, based on the interaction (such as ethylene ripening effect) between the supplementary transported agricultural products (such as apples) and the target agricultural products (such as mangoes), update the maturity of the target agricultural products and accordingly update the second sub-route and / or the transportation mode.

[0190] Please refer to Figure 7 , Figure 7 which schematically shows the structural block diagram of a transportation route adjustment device in an embodiment according to the present application. The transportation route adjustment device 700 corresponds to the Figure 6 method shown. As Figure 7 shown, the prediction model construction device 700 includes:

[0191] A route adjustment unit 701, configured to dynamically adjust the transportation route and / or the transportation mode during the transportation of agricultural products according to the transportation destination, the transportation target, and the maturity of the target agricultural products; wherein, the transportation target is used to define the maturity of the agricultural products when they reach the transportation destination, and the maturity of the target agricultural products is predicted based on a prediction model.

[0192] Implement the Figure 7 device shown, which can automatically and dynamically adjust the transportation route and / or the transportation mode based on the actual situation, thereby being beneficial to improving the utilization rate of transportation resources and reducing the loss rate of agricultural products.

[0193] In an exemplary embodiment of the present application, it further includes:

[0194] An information generation unit, configured to generate transportation route suggestions and / or transportation mode suggestions according to the transportation destination, the transportation target, and the maturity of the target agricultural products before transporting the agricultural products.

[0195] It can be seen that by implementing this optional embodiment, transportation route suggestions and / or transportation mode suggestions can be given based on the transportation destination, the transportation target, and the maturity of the target agricultural products. Implementing transportation based on the transportation route suggestions and / or transportation mode suggestions can be beneficial to improving the utilization rate of transportation resources and reducing the loss rate of agricultural products.

[0196] In an exemplary embodiment of the present application, the route adjustment unit is further configured to:

[0197] In response to the transit location input operation, dynamically adjust the transportation route according to the transit location, the transportation destination, the transportation target, and the maturity of the target agricultural product; wherein, the adjusted transportation route includes a first sub-route composed of the current location and the transit location, and a second sub-route composed of the transit location and the transportation destination.

[0198] It can be seen that by implementing this optional embodiment, when a new transit location is added during the user's transportation, the transportation route can be adjusted in a timely manner to meet the user's personalized needs.

[0199] In an exemplary embodiment of the present application, the route adjustment unit is further configured to:

[0200] In response to the supplementary transportation of agricultural products with the transit location as the starting point of transportation, update the maturity of the target agricultural product based on the interaction between the supplementary transportation of agricultural products and the target agricultural product;

[0201] Based on the updated maturity of the target agricultural product, update the second sub-route and / or the transportation mode.

[0202] It can be seen that by implementing this optional embodiment, the interaction between the agricultural products replenished at the transit location and the original agricultural products can be considered, and then the route can be updated in a timely manner to avoid the problem of over-ripe agricultural products.

[0203] Since each functional module of the transportation route adjustment device in the exemplary embodiment of the present application corresponds to the steps in the exemplary embodiment of the above-mentioned transportation route adjustment method, for the details not disclosed in the device embodiment of the present application, please refer to the embodiment of the above-mentioned transportation route adjustment method of the present application.

[0204] Please refer to Figure 8 , Figure 8 which shows a schematic structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application.

[0205] It should be noted that Figure 8 the computer system 800 of the electronic device shown is only an example, and should not impose any limitation on the functions and usage scope of the embodiments of the present application.

[0206] As Figure 8As shown, computer system 800 includes a central processing unit (CPU) 801, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 802 or programs loaded from a storage section 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for system operation are also stored. The CPU 801, ROM 802, and RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0207] The following components are connected to the I / O interface 805: an input section 806 including a keyboard, a mouse, etc.; an output section 807 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, a modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed so that a computer program read from it can be installed into the storage section 808 as needed.

[0208] Specifically, according to an embodiment of the present application, the process described with reference to the above flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 809, and / or installed from the removable medium 811. When the computer program is executed by the central processing unit (CPU) 801, various functions defined in the method and apparatus of the present application are executed.

[0209] The exemplary embodiment of the present disclosure also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the above-described prediction model construction method or transportation route adjustment method is implemented.

[0210] In one embodiment, a computer program product may be a tangible product containing a computer program, such as a computer-readable storage medium storing the computer program. The readable storage medium may be a storage medium based on signals such as electricity, magnetism, light, electromagnetic, infrared, etc., including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory, hard disk drive (HDD), solid state drive (SSD), and so on. Exemplarily, the computer program product may be implemented as a non-volatile storage medium storing the computer program, such as read-only memory, NAND flash memory, etc.

[0211] In one embodiment, a computer program product may be an intangible product containing a computer program. Exemplarily, the computer program product may be implemented as a virtual digital product, such as an executable file storing the computer program, digital files such as installation packages.

[0212] The code of the computer program can be written in one or more programming languages. Programming languages such as C language, Java, C++, etc. The program code can be executed entirely on the user's computing device, or partially on the user's computing device, or executed as an independent software package, or partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case involving a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, such as a local area network (LAN), wide area network (WAN), etc., or can be connected to an external computing device (for example, through the Internet connection provided by an operator).

[0213] The computer program can be carried or transmitted by signals such as electricity, magnetism, light, electromagnetic, infrared, etc. The electronic device can convert the signal carrying the computer program into a digital signal and then run the computer program. When the computer program runs on the electronic device, its code is used to cause the electronic device to execute (more specifically, can cause the processor of the electronic device to execute) the method steps of various exemplary embodiments of the present disclosure. For example, it can execute the above-mentioned prediction model construction method, which includes the following steps: obtaining a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the agricultural product carrier; constructing a prediction model for predicting the maturity of agricultural products based on the first type of data and the second type of data.

[0214] Executing the above method steps through a computer program can overcome the problem that the maturity of agricultural products cannot be predicted. This application takes into account that the factors affecting the maturity of agricultural products include a type of data used to describe the attributes of agricultural products and a second type of data used to describe the internal environment of the agricultural product carrier. Based on this, a prediction model for predicting the maturity of agricultural products can be constructed according to the first type of data and the second type of data. Since this prediction model learns the relationship between the attributes of agricultural products and the internal environment of the agricultural product carrier, it can realize the prediction of the maturity of agricultural products, which can facilitate relevant personnel to predict the future maturity of agricultural products before transporting them, so that relevant personnel can make corresponding transportation decisions, thereby helping to avoid the problem of excessive maturity of agricultural products during or after transportation. In addition, it can also avoid to a certain extent the problem of the decline in the quality of agricultural products for sale before sale, and ensure the quality of agricultural products for sale.

[0215] When the computer program runs on an electronic device, its code is used to cause the electronic device to execute (more specifically, to cause the processor of the electronic device to execute) the method steps of various exemplary embodiments of the present disclosure. For example, it can execute the above-mentioned transportation route adjustment method, which includes the following steps: during the transportation of agricultural products, dynamically adjust the transportation route and / or transportation mode according to the transportation destination, transportation target, and target agricultural product maturity; wherein, the transportation target is used to define the maturity of the agricultural product when it reaches the transportation destination, and the target agricultural product maturity is predicted based on the prediction model.

[0216] Executing the above method steps through a computer program can automatically and dynamically adjust the transportation route and / or transportation mode based on the actual situation, which can help improve the utilization rate of transportation resources and reduce the loss rate of agricultural products.

[0217] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or part of the code includes one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0218] The units involved in the embodiments described in this application can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not constitute a limitation to the unit itself in some cases.

[0219] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include the known common general knowledge or conventional technical means in the art not disclosed in the present application. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present application are pointed out by the claims.

Claims

1. A method for constructing a prediction model, characterized in that, Including: Obtaining a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the agricultural product carrier; Constructing a prediction model for predicting the maturity of agricultural products based on the first type of data and the second type of data.

2. The method according to claim 1, wherein Further including: Inputting target agricultural product data into the prediction model to trigger the prediction model to generate the maturity of the target agricultural product; Wherein, the maturity of the target agricultural product is expressed as immature, mature or over-ripe.

3. The method according to claim 1, characterized in that, Obtaining a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the agricultural product carrier includes: Obtaining a first type of data for describing the attributes of agricultural products; wherein, the first type of data includes at least one of the maturity at the time of loading and the flowering period of the agricultural products; Periodically obtaining a second type of data for describing the internal environment of the agricultural product carrier; wherein, the second type of data includes at least one of temperature, humidity, ethylene gas concentration, and the loaded duration.

4. The method according to claim 1, wherein Constructing a prediction model for predicting the maturity of agricultural products based on the first type of data and the second type of data includes: Constructing a maturity label based on the first type of data and the second type of data; Generating sample data based on the first type of data, the second type of data, and the maturity label; Constructing a prediction model for predicting the maturity of agricultural products through the sample data.

5. The method according to claim 4, characterized in that, Constructing a prediction model for predicting the maturity of agricultural products through the sample data includes: Sampling the sample data to obtain a first sampling result, and constructing a first decision tree model based on the first sampling result; Sampling the sample data based on the first sampling result to obtain a second sampling result, and constructing a second decision tree model based on the second sampling result until a plurality of decision tree models meeting a preset quantity are obtained; wherein, the plurality of decision tree models include the first decision tree model and the second decision tree model; Integrating the plurality of decision tree models to obtain a prediction model for predicting the maturity of agricultural products.

6. A prediction model construction device, characterized in that, Including: A data acquisition unit for obtaining a first type of data for describing the attributes of agricultural products and a second type of data for describing the internal environment of the agricultural product carrier; A model construction unit for constructing a prediction model for predicting the maturity of agricultural products based on the first type of data and the second type of data.

7. A transportation route adjustment method, characterized in that, Including: During the transportation of agricultural products, dynamically adjusting the transportation route and / or transportation method according to the transportation destination, transportation target, and the maturity of the target agricultural product; wherein, the transportation target is used to define the maturity of the agricultural product when it reaches the transportation destination, and the maturity of the target agricultural product is predicted based on the prediction model.

8. The method according to claim 7, wherein Further including: Before transporting agricultural products, generating a transportation route suggestion and / or a transportation method suggestion according to the transportation destination, the transportation target, and the maturity of the target agricultural product.

9. The method according to claim 7, characterized in that, Further including: In response to a transit location input operation, dynamically adjusting the transportation route according to the transit location, transportation destination, transportation target, and the maturity of the target agricultural product; wherein, the adjusted transportation route includes a first sub-route composed of the current location and the transit location, and a second sub-route composed of the transit location and the transportation destination.

10. The method according to claim 9, characterized in that, Further including: In response to supplementary transported agricultural products with the transfer location as the starting point of transportation, based on the interaction between the supplementary transported agricultural products and the target agricultural products, update the maturity of the target agricultural products; Based on the updated maturity of the target agricultural products, update the second sub-route and / or the transportation mode.

11. A transportation route adjustment device, characterized in that, Comprising: A route adjustment unit, configured to dynamically adjust the transportation route and / or the transportation mode during the transportation of agricultural products according to the transportation destination, the transportation target, and the maturity of the target agricultural products; wherein, the transportation target is used to define the maturity of the agricultural products when they reach the transportation destination, and the maturity of the target agricultural products is obtained by prediction based on a prediction model.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method according to any one of claims 1-5 or the method according to any one of claims 7-10.

13. An electronic device, characterized in that, Comprising: A processor; And A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to execute the method according to any one of claims 1-5 or the method according to any one of claims 7-10 by executing the executable instructions.

Images