Device for reducing moisture damage rate of express parcels based on big data analysis

Abstract

The invention relates to a device for reducing the moisture loss rate of express parcels based on big data analysis, and the device comprises a logistics moisture loss analysis platform which comprises a real-time processing module which is used for obtaining real-time weather data and real-time order information; the logistics moisture loss management end is used for starting the moisture loss prediction module when the real-time weather data reach a preset weather threshold value, and the moisture loss prediction module is used for processing the real-time weather data and the real-time order information, generating a moisture loss prediction result and sending the moisture loss prediction result to the logistics moisture loss management end; and the query module is connected with the logistics moisture loss management terminal and is used for querying the moisture loss prediction result, so that a risk elimination principal carries out risk elimination on the express parcel according to the moisture loss prediction result. According to the device, a risk elimination responsible person can obtain the moisture loss prediction result, risk elimination is carried out on the express parcel, moisture loss of the parcel is avoided in advance, and the moisture loss rate of the express parcel is effectively reduced.

Description

Technical Field

[0001] The present application relates to the field of logistics management technology, and in particular to a device for reducing the moisture loss rate of express packages based on big data analysis. Background Art

[0002] In the logistics end-to-end delivery scenario, some express parcels often get wet and damaged. For example, express parcels are affected by moisture or humidity during transportation, loading and unloading, or storage, resulting in damage or quality degradation of express parcels. Common causes of wet and damaged express parcels include rainy and snowy weather conditions, packaging material types, transportation vehicle types, or storage conditions.

[0003] In the existing technology, the management system is generally used to evaluate the performance of the delivery personnel by the logistics company to ensure that the express parcels delivered by the delivery personnel are not damaged by moisture. However, there is currently a lack of systematic, effective and pre-emptive technical means to avoid moisture damage to express parcels.

[0004] Therefore, it is necessary to provide a new technical solution to improve one or more problems existing in the above solutions.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0006] The purpose of this application is to provide a device for reducing the moisture loss rate of express parcels based on big data analysis, so that the person in charge of risk elimination can eliminate risks of express parcels according to moisture loss prediction results, so as to avoid moisture damage of express parcels in advance, thereby effectively reducing the moisture loss rate of express parcels.

[0007] According to the present application, a device for reducing the moisture loss rate of express parcels based on big data analysis is provided, including a logistics moisture loss analysis platform, wherein the logistics moisture loss analysis platform includes: Real-time processing module, used to obtain real-time weather data and real-time order information; A logistics wet loss management terminal and a wet loss prediction module, wherein the wet loss prediction module and the real-time processing module are respectively connected to the logistics wet loss management terminal, wherein the logistics wet loss management terminal is used to start the wet loss prediction module when the real-time weather data reaches a preset weather threshold, and the wet loss prediction module is used to process the real-time weather data and the real-time order information, generate a wet loss prediction result, and send the wet loss prediction result to the logistics wet loss management terminal; The query module is connected to the logistics moisture loss management terminal and is used to query the moisture loss prediction result so that the risk elimination person in charge can eliminate the risk of the express parcel according to the moisture loss prediction result.

[0008] In an exemplary embodiment of the present application, the logistics moisture loss management terminal includes: a moisture damage prediction management module, connected to the moisture damage prediction module, for starting the moisture damage prediction module when the real-time weather data reaches the preset weather threshold, and obtaining the moisture damage prediction result; a moisture damage risk management module, connected to the moisture damage prediction management module, for obtaining moisture damage risk information according to the moisture damage prediction result, and managing the moisture damage risk information; A calling module, connected to the real-time processing module, for calling the real-time weather data and the real-time order information; The calling module is also connected to the moisture damage prediction module, and is used to send the called real-time weather data and the real-time order information to the moisture damage prediction module.

[0009] In an exemplary embodiment of the present application, the moisture damage prediction management module includes: A weather threshold management unit, used for managing the start and stop of the moisture damage prediction task of the moisture damage prediction module according to the preset weather threshold; a moisture loss prediction management unit, configured to configure a moisture loss prediction scheme according to logistics site information and real-time order information when the moisture loss prediction task is started, so that the moisture loss prediction module performs the moisture loss prediction task according to the moisture loss prediction scheme; The moisture loss prediction task management unit is used to add the moisture loss prediction task according to the command of the logistics site administrator.

[0010] In an exemplary embodiment of the present application, the moisture damage risk management module includes: A moisture damage risk warning unit, used to push the moisture damage risk information to the risk elimination person in charge; The risk elimination activity unit is used to generate a risk elimination task according to the moisture damage risk information and push the risk elimination task to the risk elimination person in charge.

[0011] In an exemplary embodiment of the present application, the logistics wet loss management end also includes a basic information management module, which is connected to the wet loss prediction management module and is used to manage logistics site information, order category information and package packaging type information.

[0012] In an exemplary embodiment of the present application, the logistics moisture damage analysis platform further includes a receiving module, and the receiving module is used to receive the actual moisture damage of the package; The logistics wet damage management terminal also includes a business management module, which is connected to the receiving module and is used to generate a real-time wet damage document according to the actual wet damage situation.

[0013] In an exemplary embodiment of the present application, the device further comprises a data storage platform connected to the logistics moisture loss analysis platform, the data storage platform comprising a real-time database, a historical database, a material library and a configuration library; Wherein, the real-time database is used to store the real-time weather data, the real-time order information and the real-time moisture loss receipt; The historical database is used to store historical weather data, historical order information and historical moisture loss documents; The material library is used to store material data; The configuration library is used to store configuration items of the logistics moisture loss analysis platform.

[0014] In an exemplary embodiment of the present application, the logistics moisture loss analysis platform further comprises an offline processing module connected to the data storage platform, and the offline processing module comprises an extraction unit and a processing unit; Wherein, the extraction unit is used to extract the data stored in the real-time database and store the extracted data in the historical database; The processing unit is used to process the data in the historical database and store the processed data in the material library.

[0015] In an exemplary embodiment of the present application, the moisture damage prediction module includes a sample processing unit, a model training unit and a moisture damage prediction unit; Wherein, the sample processing unit is connected to the data storage platform, and is used to extract the material data stored in the material library, and pre-process the extracted material data to obtain pre-processed sample data; The model training unit is connected to the sample processing unit and is used to train the SVR model according to the pre-processed sample data to obtain a moisture damage prediction model; The moisture loss prediction unit is connected to the logistics moisture loss management terminal and is used to obtain the real-time weather data and the real-time order information; The moisture loss prediction unit and the model training unit are used to predict the moisture loss rate of the express package based on the real-time weather data and the real-time order information and using the moisture loss prediction model to obtain the moisture loss prediction result.

[0016] In an exemplary embodiment of the present application, the real-time processing module includes: A weather data access module, used to obtain the real-time weather data; The real-time order processing module is used to obtain the real-time order information.

[0017] The technical solution provided by this application may have the following beneficial effects: In an embodiment of the present application, real-time weather data and real-time order information are obtained through the real-time processing module of the logistics wet loss analysis platform, and the wet loss prediction module can be started under the condition that the real-time weather data reaches a preset weather threshold through the logistics wet loss management terminal, and then the real-time weather data and real-time order information are analyzed and processed by the wet loss prediction module to generate a wet loss prediction result, and the wet loss prediction result is sent to the logistics wet loss management terminal; this makes it convenient for the risk elimination person in charge to obtain the wet loss prediction result through the query module, so that the risk elimination person in charge can eliminate the risk of express parcels according to the wet loss prediction result, so as to avoid wet damage of express parcels in advance, thereby effectively reducing the wet loss rate of express parcels.

[0018] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A simplified schematic diagram showing a device for reducing the moisture loss rate of express parcels based on big data analysis in an exemplary embodiment of the present application; Figure 2 A simplified schematic diagram showing a logistics moisture loss management end in an exemplary embodiment of the present application; Figure 3 A schematic diagram showing a real-time moisture damage analysis and early warning process of an express package in an exemplary embodiment of the present application is shown; Figure 4 A schematic diagram showing the training process of the moisture damage prediction model in an exemplary embodiment of the present application is shown; Figure 5 A schematic flow chart showing the steps of preprocessing the extracted material data in an exemplary embodiment of the present application; Figure 6 A schematic diagram showing the steps of training the SVR model in an exemplary embodiment of the present application is shown; Figure 7 A simplified schematic diagram showing a courier's PDA terminal and a device for reducing the moisture loss rate of express parcels based on big data analysis in an exemplary embodiment of the present application; Figure 8 A schematic flow chart showing the steps of interaction between a courier's PDA terminal and a device for reducing the moisture loss rate of express packages based on big data analysis in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0021] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of 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 comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0022] 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 figures represent the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the accompanying 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 implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0023] In this example implementation, a device for reducing the moisture loss rate of express parcels based on big data analysis is first provided. Figure 1 As shown in , the device includes a logistics moisture loss analysis platform, and the logistics moisture loss analysis platform includes: Real-time processing module, used to obtain real-time weather data and real-time order information; The logistics wet loss management end and the wet loss prediction module, the wet loss prediction module and the real-time processing module are respectively connected to the logistics wet loss management end, the logistics wet loss management end is used to start the wet loss prediction module when the real-time weather data reaches the preset weather threshold, the wet loss prediction module is used to process the real-time weather data and real-time order information, generate a wet loss prediction result, and send the wet loss prediction result to the logistics wet loss management end; The query module is connected to the logistics moisture loss management end and is used to query the moisture loss prediction results so that the risk elimination person in charge can eliminate the risks of express parcels based on the moisture loss prediction results.

[0024] In an embodiment of the present application, real-time weather data and real-time order information are obtained through the real-time processing module of the logistics wet loss analysis platform, and the wet loss prediction module can be started under the condition that the real-time weather data reaches a preset weather threshold through the logistics wet loss management terminal, and then the real-time weather data and real-time order information are analyzed and processed by the wet loss prediction module to generate a wet loss prediction result, and the wet loss prediction result is sent to the logistics wet loss management terminal; this makes it convenient for the risk elimination person in charge to obtain the wet loss prediction result through the query module, so that the risk elimination person in charge can eliminate the risk of express parcels according to the wet loss prediction result, so as to avoid wet damage of express parcels in advance, thereby effectively reducing the wet loss rate of express parcels.

[0025] Next, we will refer to Figure 1 and Figure 2 As shown in , each part of the above-mentioned device in this example embodiment is described in more detail.

[0026] In one embodiment, the logistics moisture loss management terminal includes: A moisture damage prediction management module is connected to the moisture damage prediction module and is used to start the moisture damage prediction module and obtain moisture damage prediction results when the real-time weather data reaches a preset weather threshold; A moisture damage risk management module is connected to the moisture damage prediction management module and is used to obtain moisture damage risk information according to moisture damage prediction results and manage the moisture damage risk information; The calling module is connected with the real-time processing module and is used to call the real-time weather data and real-time order information; The calling module is also connected to the moisture damage prediction module and is used to send the called real-time weather data and real-time order information to the moisture damage prediction module.

[0027] The setting of the above-mentioned logistics wet loss management terminal can realize the wet loss prediction management function, the wet loss risk management function and the calling engine function to enable the logistics wet loss analysis platform to operate normally.

[0028] Furthermore, the logistics moisture damage analysis platform also includes a receiving module, which is used to receive the actual moisture damage of the package; The logistics wet damage management end also includes a business management module, which is connected to the receiving module and is used to generate a real-time wet damage document based on the actual wet damage situation of the package.

[0029] Specifically, the above-mentioned business management module includes a wet damage statistics unit, a wet damage document reporting unit, a wet damage document reporting and verification unit and a monitoring unit. The wet damage statistics unit is used to count the actual wet damage of the package to generate a real-time wet damage document. The wet damage document reporting unit is used to report the real-time wet damage document to the wet damage document reporting and verification unit. The wet damage document reporting and verification unit is used to review the reported real-time wet damage document. The monitoring unit is used to monitor the actual wet damage of the package.

[0030] Furthermore, the logistics moisture loss management end also includes a basic information management module, which is connected to the moisture loss prediction management module and is used to manage logistics site information, order category information and package packaging type information.

[0031] Specifically, the above-mentioned basic information management module may further include a site information management unit, an order category management unit, a packaging type management unit and a parameter management unit, wherein the site information management unit is used to manage logistics site information, which includes but is not limited to site location information, site contact information and site business hours; the order category management unit is used to manage order category information, which includes but is not limited to package commodity types, package commodity quantities and package commodity specifications; the packaging type management unit is used to manage package packaging type information, which includes but is not limited to box packaging, bag packaging and bottle packaging; the parameter management unit is used to manage parameters, which includes but is not limited to the user login account, login password, order code and document code of the logistics moisture loss management terminal.

[0032] For example, the moisture damage prediction management module includes: A weather threshold management unit, used to manage the start and stop of the moisture damage prediction task of the moisture damage prediction module according to a preset weather threshold; A wet loss prediction management unit is used to configure a wet loss prediction scheme according to logistics site information and real-time order information when a wet loss prediction task is started, so that the wet loss prediction module performs the wet loss prediction task according to the wet loss prediction scheme; The moisture loss prediction task management unit is used to add moisture loss prediction tasks according to the command of the logistics site administrator.

[0033] The weather threshold management unit can timely start the wet loss prediction task of the wet loss prediction module when the real-time weather data reaches the preset weather threshold; the wet loss prediction management unit can configure the wet loss prediction scheme according to the logistics site information and real-time order information after the wet loss prediction task is started, so that the wet loss prediction module can perform the wet loss prediction task according to the wet loss prediction scheme. In addition, the wet loss prediction task management unit can also receive commands from the logistics site administrator so that the logistics site administrator can selectively add wet loss prediction tasks when necessary, obtain the wet loss rate of express parcels, and take measures in advance to avoid wet loss of express parcels.

[0034] The preset weather thresholds include a rainfall threshold, a snowfall threshold, a wind force threshold, a wind direction threshold, a humidity threshold, a duration threshold, etc. The factors to be considered when configuring the moisture loss prediction scheme also include the type of packaged goods and the type of package packaging, etc.

[0035] It should be noted that the preset weather threshold may be set to one or more of a rainfall threshold, a snowfall threshold, a wind force threshold, a wind direction threshold, a humidity threshold and a duration threshold.

[0036] For example, the moisture damage risk management module includes: Moisture damage risk warning unit, used to push moisture damage risk information to the person in charge of risk elimination; The risk elimination activity unit is used to generate risk elimination tasks based on moisture damage risk information and push the risk elimination tasks to the person in charge of risk elimination.

[0037] Through the setting of the moisture loss risk warning unit and the risk elimination activity unit in the above-mentioned moisture loss risk management module, moisture loss risk information of express parcels with high moisture loss risks can be pushed to the person in charge of risk elimination in a timely manner, so that risk elimination operations can be performed in advance for express parcels with high moisture loss risks, which is conducive to preventing express parcels from being damaged due to moisture loss and reducing the moisture loss rate of express parcels.

[0038] It should be noted that logistics site administrators can also add wet loss prediction plans through the wet loss prediction management unit. Specifically, they need to select the logistics site information and can select multiple logistics sites at the same time. They also need to select the type of parcel goods, parcel packaging type, execution time of the wet loss prediction task, and person responsible for risk elimination.

[0039] In one embodiment, the device for reducing the moisture loss rate of express parcels based on big data analysis also includes a data storage platform connected to the logistics moisture loss analysis platform, and the data storage platform includes a real-time database, a historical database, a material library, and a configuration library; Among them, the real-time database is used to store real-time weather data, real-time order information and real-time moisture loss documents; The historical database is used to store historical weather data, historical order information and historical moisture loss documents; The material library is used to store material data; The configuration library is used to store configuration items of the logistics moisture loss analysis platform, such as software, hardware, etc.

[0040] Through the above data storage platform, the function of classified storage of various data information can be provided, so that the logistics moisture loss analysis platform can retrieve the required data in real time. It should also be noted that the calling module in the logistics moisture loss management terminal can also be used to cooperate with various functional modules in the logistics moisture loss analysis platform to call the data stored in the data storage platform.

[0041] An example, real-time processing module includes: Weather data access module, used to obtain real-time weather data; Real-time order processing module, used to obtain real-time order information.

[0042] The weather data access module can access the meteorological service system platform of the National Meteorological Information Center in real time and cache the weather data of the current time period to the data storage platform. The real-time order processing module can access order detail data and order routing data, etc., and form a document wide table, and store the document wide table to the data storage platform to provide data support for the moisture damage prediction task.

[0043] In one embodiment, reference Figure 3 As shown in , combined with the above-mentioned device for reducing the moisture loss rate of express parcels based on big data analysis, a real-time moisture loss analysis and early warning process for express parcels is given: The real-time order information is obtained through the real-time order processing module, and the Kafka processing unit in the real-time order processing module is used to process the real-time order information; The Flink processing unit in the real-time order processing module is used to further process the real-time order information processed by the Kafka processing unit, and the data processed by the Flink processing unit is stored as a document wide table; Acquire real-time weather data through the weather data access module, and store the acquired real-time weather data in the real-time database of the data storage platform; When the real-time weather data reaches the preset weather threshold, the moisture damage prediction task of the moisture damage prediction module is started, the moisture damage prediction task is performed according to the moisture damage prediction scheme, and the moisture damage prediction result is saved; According to the moisture damage prediction results, the moisture damage risk information is pushed to the risk elimination person in charge, and the generated risk elimination tasks are pushed to the risk elimination person in charge; The risk elimination manager performs risk elimination operations and updates the completion status of risk elimination operations in real time.

[0044] It should be noted that based on the real-time updated order information, the document wide table and information such as the operation time of each processing link will be continuously updated in real time; the real-time weather data includes but is not limited to the real-time weather data shared by the National Meteorological Information Center; the person responsible for risk elimination includes but is not limited to the logistics site administrator and the courier; the risk elimination operations include but are not limited to changing the delivery time, waterproofing the package, etc.

[0045] It should also be noted that Flink is a stream computing framework that is mainly used to process streaming data. Kafka, as a stream processing platform, can be used in combination with other data processing tools (such as Flink) to achieve real-time collection, processing, and transformation of unstructured data.

[0046] Further, the moisture damage prediction module includes a sample processing unit, a model training unit and a moisture damage prediction unit; The sample processing unit is connected to the data storage platform, and is used to extract material data stored in the material library, and pre-process the extracted material data to obtain pre-processed sample data; The model training unit is connected to the sample processing unit and is used to train the SVR model according to the pre-processed sample data to obtain a moisture damage prediction model; The moisture loss prediction unit is connected to the logistics moisture loss management end to obtain real-time weather data and real-time order information; The moisture loss prediction unit and the model training unit are used to predict the moisture loss rate of express packages based on real-time weather data and real-time order information and use the moisture loss prediction model to obtain moisture loss prediction results.

[0047] The above-mentioned moisture loss prediction module can train the SVR model by utilizing the material data stored in the material library, wherein the SVR model can be understood as a model based on a support vector machine, which can map the data to a high-dimensional feature space through nonlinear mapping, so that the independent variables and dependent variables in the high-dimensional space have good linear regression characteristics.

[0048] Optionally, the moisture damage prediction module also includes a model updating unit, and the model updating unit is used to iteratively update the moisture damage prediction model.

[0049] Furthermore, the logistics moisture loss analysis platform also includes an offline processing module connected to the data storage platform, and the offline processing module includes an extraction unit and a processing unit; The extraction unit is used to extract the data stored in the real-time database and store the extracted data in the historical database; The processing unit is used to process the data in the historical database and store the processed data in the material library.

[0050] The above-mentioned offline processing module can extract corresponding real-time weather data, real-time order information and real-time moisture loss documents in real time. The data extracted on the day will be stored in the historical database. The data in the historical database will be processed to form material data. The material data can be stored in the material library. The material data obtained through the offline processing module can be used to support the iterative update of the moisture loss prediction model.

[0051] Optionally, the offline processing module further includes an offline data warehouse unit, which is used to temporarily store data extracted from the real-time database, including but not limited to real-time weather data, real-time order information, and real-time moisture loss documents extracted on the day. After the extraction on the day is completed, all the data extracted on the day are stored in the historical database.

[0052] In one embodiment, reference Figure 4 As shown in , combined with the above-mentioned device for reducing the moisture loss rate of express packages based on big data analysis, the training process of the moisture loss prediction model is given: The real-time weather data, real-time order information and real-time moisture loss documents extracted from the real-time database are stored in the historical database; Process the data in the historical database to obtain material data; Store material data in the material library of the data storage platform; Extracting material data stored in the material library, and preprocessing the extracted material data to obtain preprocessed sample data; The SVR model for moisture damage prediction is trained based on the preprocessed sample data.

[0053] It should be noted that the trained SVR model is the moisture damage prediction model. It should be explained that support vector regression (SVR) is a regression algorithm based on support vector machine, which is suitable for continuous numerical prediction tasks. Using data in the historical database to construct material data for training the SVR model can improve the training accuracy to ensure that the obtained moisture damage prediction model has good generalization.

[0054] For further reference, Figure 5 As shown in , the material data stored in the material library is extracted, and the extracted material data is preprocessed to obtain preprocessed sample data, which may specifically include the following steps: Extract material data from the material library involving factors such as rainfall, snowfall, rainfall intensity, wind speed, wind direction, humidity, packaged product type, and package packaging type; The MinMax algorithm is used to normalize the material data to ensure that the characteristic values ​​of the material data are within the same range. The MinMax algorithm can be expressed by formula (1): (1) in, x is the original data value, is the minimum value in the data set, is the maximum value in the data set, is the standardized data value; The normalized material data are organized into time series data according to the time dimension to capture the dynamic impact of time on the moisture loss rate of the package.

[0055] The time series data obtained above is the preprocessed sample data. It should be noted that the MinMax algorithm is a recursive algorithm that decomposes the problem into sub-problems and finds the optimal solution for each sub-problem. The above-mentioned normalization of material data by the MinMax algorithm can eliminate the dimensional differences between different features, which is conducive to the training and convergence of the SVR model.

[0056] For further reference, Figure 6 As shown in , the above-mentioned training of the SVR model for moisture damage prediction based on the preprocessed sample data may specifically include the following steps: The radial basis kernel function is selected as the kernel function of the SVR model. The radial basis kernel function can be expressed as: (2) in, Indicates Samples and Samples The kernel function value between Representation sample and samples The square of the Euclidean distance, is a hyperparameter used to control the width of the radial basis kernel function. represents an exponential function with the natural constant e as the base, and Indicates the serial number of the sample; Use cross-validation method to select the optimal hyperparameters; Determine the loss function of the SVR model, which can be expressed as: (3) in, is the actual moisture loss rate, To predict the moisture loss value, is the insensitive threshold; The mean square error indicator is used to evaluate the performance of the SVR model, and the model parameters are further adjusted by analyzing the mean square error. The mean square error can be expressed as: (4) in, is the sample size, For the Samples The actual moisture loss rate value, For the Samples The predicted moisture loss rate value, represents the mean square error.

[0057] The above SVR model uses an insensitive threshold to predict the error Less than the insensitivity threshold Sample No loss is calculated to reduce the sensitivity of the SVR model to small errors.

[0058] The above-mentioned radial basis kernel function is selected as the kernel function of the SVR model, which can effectively handle the nonlinear relationship in high-dimensional space and is suitable for the complex changes of the package moisture loss rate.

[0059] It should be noted that the hyperparameters in formula (2) The larger the value of is, the more sensitive the SVR model is to the local information of the preprocessed sample data; the hyperparameter The smaller the value of , the more the SVR model pays attention to the global information of the preprocessed sample data. The optimal hyperparameters are selected by using the cross-validation method. , which can optimize the performance of the SVR model.

[0060] It should also be noted that by inputting real-time weather data and real-time order information into the trained SVR model, the moisture loss rate of the package can be predicted, and the predicted moisture loss rate obtained is the moisture loss prediction result mentioned in this embodiment. The SVR model can be iteratively updated using the continuously updated data in the data storage platform. The accuracy of the SVR model is evaluated using the residual of the SVR model. If the residual exceeds the preset residual threshold, the SVR model is retrained to achieve fine-tuning and optimization of the SVR model.

[0061] It should be noted that the setting of the receiving module facilitates the courier to send the actual moisture damage condition of the package to the logistics moisture damage management terminal, so that the logistics site administrator can obtain the actual moisture damage condition of the package through the logistics moisture damage management terminal, so as to understand the actual moisture damage condition of the package and cooperate with the courier to take remedial measures for the damaged express package.

[0062] It should be noted that the courier can carry a courier PDA terminal with him, refer to Figure 7 As shown in , the courier PDA terminal includes a moisture loss prediction query module and a moisture loss result reporting module; Among them, the moisture loss prediction query module can be connected to the query module of the logistics moisture loss analysis platform so that the courier can obtain the moisture loss prediction result through the moisture loss prediction query module; The moisture damage result reporting module can be connected to the receiving module of the logistics moisture damage analysis platform for communication, so that the courier can send the actual moisture damage result to the receiving module through the moisture damage result reporting module.

[0063] Through the moisture loss prediction query module and moisture loss result reporting module set in the courier's PDA terminal, the courier can obtain the predicted moisture loss rate of the current package in time at the final delivery link of the express package, so that the courier can perform risk elimination operations in time; in addition, it is also convenient for the courier to use the courier's PDA terminal to feedback the actual moisture damage situation of the package to the logistics moisture loss analysis platform.

[0064] For a more detailed understanding of the device for reducing the moisture loss rate of express parcels based on big data analysis provided in this embodiment, refer to Figure 8 As shown in , the following describes how the courier uses the courier PDA terminal to interact with the device for reducing the moisture loss rate of express packages based on big data analysis: Obtain moisture damage prediction results and moisture damage risk information through the courier's PDA; The courier selects the following operation procedures according to the prompts on the courier's PDA: "Confirmed moisture damage risk and delivery in progress", "Completed risk elimination task", "Delayed delivery due to moisture damage risk" and so on; When delivering an express package, if it is not delivered normally, the courier's PDA will report the delivery exception information to the logistics moisture and damage management end. If it is a moisture damage scenario, the courier's PDA will report the actual moisture damage situation of the package to the logistics moisture and damage management end. The actual moisture damage situation includes but is not limited to the moisture damage time, photos of the moisture damage of the package, and the severity of the moisture damage.

[0065] It should be noted that the above-mentioned moisture damage prediction results may be high moisture damage rate, medium moisture damage rate, and low moisture damage rate, and the corresponding moisture damage risks may be high risk, medium risk, and low risk. No prompt will be given if there is no risk. That is, when the moisture damage risk is no risk, the moisture damage risk information may not be pushed to the courier's PDA.

[0066] It should also be noted that while the courier is making the above-mentioned delivery operation on the courier's PDA, the logistics site administrator can log in to the logistics wet damage management terminal to promptly review the actual wet damage situation; if the review is passed, the real-time wet damage document will be stored in the real-time database of the data storage platform so that the offline processing module can extract the real-time wet damage document every day.

[0067] It also needs to be explained that a personal digital assistant (PDA) can also be called a handheld terminal, which is essentially a portable mobile computing device with an independent operating system and user interface.

[0068] Regarding the system in the above embodiment, the specific manner in which each unit performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0069] It should be noted that although several units of the system for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the implementation mode of the present application, the features and functions of two or more units described above can be concretized in one unit. Conversely, the features and functions of a unit described above can be further divided into multiple units for concretization. Some or all of the units can be selected according to actual needs to achieve the purpose of the present application scheme. Those of ordinary skill in the art can understand and implement it without paying creative work.

[0070] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary technical means in the art that are not disclosed in the present application.

Claims

1. A device for reducing the moisture loss rate of express parcels based on big data analysis, characterized in that: It includes a logistics moisture loss analysis platform, and the logistics moisture loss analysis platform includes: Real-time processing module, used to obtain real-time weather data and real-time order information; A logistics wet loss management terminal and a wet loss prediction module, wherein the wet loss prediction module and the real-time processing module are respectively connected to the logistics wet loss management terminal, wherein the logistics wet loss management terminal is used to start the wet loss prediction module when the real-time weather data reaches a preset weather threshold, and the wet loss prediction module is used to process the real-time weather data and the real-time order information, generate a wet loss prediction result, and send the wet loss prediction result to the logistics wet loss management terminal; The query module is connected to the logistics moisture loss management terminal and is used to query the moisture loss prediction result so that the risk elimination person in charge can eliminate the risk of the express parcel according to the moisture loss prediction result.

2. The device for reducing the moisture loss rate of express packages based on big data analysis according to claim 1 is characterized in that: The logistics moisture loss management terminal includes: a moisture damage prediction management module, connected to the moisture damage prediction module, for starting the moisture damage prediction module when the real-time weather data reaches the preset weather threshold, and obtaining the moisture damage prediction result; a moisture damage risk management module, connected to the moisture damage prediction management module, for obtaining moisture damage risk information according to the moisture damage prediction result, and managing the moisture damage risk information; A calling module, connected to the real-time processing module, for calling the real-time weather data and the real-time order information; The calling module is also connected to the moisture damage prediction module, and is used to send the called real-time weather data and the real-time order information to the moisture damage prediction module.

3. The device for reducing the moisture loss rate of express packages based on big data analysis according to claim 2 is characterized in that: The moisture damage prediction management module includes: A weather threshold management unit, used for managing the start and stop of the moisture damage prediction task of the moisture damage prediction module according to the preset weather threshold; a moisture loss prediction management unit, configured to configure a moisture loss prediction scheme according to logistics site information and real-time order information when the moisture loss prediction task is started, so that the moisture loss prediction module performs the moisture loss prediction task according to the moisture loss prediction scheme; The moisture loss prediction task management unit is used to add the moisture loss prediction task according to the command of the logistics site administrator.

4. The device for reducing the moisture loss rate of express packages based on big data analysis according to claim 2 is characterized in that: The moisture damage risk management module includes: A moisture damage risk warning unit, used to push the moisture damage risk information to the risk elimination person in charge; The risk elimination activity unit is used to generate a risk elimination task according to the moisture damage risk information and push the risk elimination task to the risk elimination person in charge.

5. The device for reducing the moisture loss rate of express packages based on big data analysis according to claim 2 is characterized in that: The logistics wet loss management end also includes a basic information management module, which is connected to the wet loss prediction management module and is used to manage logistics site information, order category information and package packaging type information.

6. The device for reducing the moisture loss rate of express packages based on big data analysis according to claim 2 is characterized in that: The logistics moisture damage analysis platform also includes a receiving module, which is used to receive the actual moisture damage of the package; The logistics wet damage management terminal also includes a business management module, which is connected to the receiving module and is used to generate a real-time wet damage document according to the actual wet damage situation.

7. The device for reducing the moisture loss rate of express packages based on big data analysis according to claim 6 is characterized in that: The device also includes a data storage platform connected to the logistics moisture loss analysis platform, and the data storage platform includes a real-time database, a historical database, a material library, and a configuration library; Wherein, the real-time database is used to store the real-time weather data, the real-time order information and the real-time moisture loss receipt; The historical database is used to store historical weather data, historical order information and historical moisture loss documents; The material library is used to store material data; The configuration library is used to store configuration items of the logistics moisture loss analysis platform.

8. The device for reducing the moisture loss rate of express packages based on big data analysis according to claim 7 is characterized in that: The logistics moisture loss analysis platform also includes an offline processing module connected to the data storage platform, and the offline processing module includes an extraction unit and a processing unit; Wherein, the extraction unit is used to extract the data stored in the real-time database and store the extracted data in the historical database; The processing unit is used to process the data in the historical database and store the processed data in the material library.

9. The device for reducing the moisture loss rate of express packages based on big data analysis according to claim 7 is characterized in that: The moisture damage prediction module includes a sample processing unit, a model training unit and a moisture damage prediction unit; Wherein, the sample processing unit is connected to the data storage platform, and is used to extract the material data stored in the material library, and pre-process the extracted material data to obtain pre-processed sample data; The model training unit is connected to the sample processing unit and is used to train the SVR model according to the pre-processed sample data to obtain a moisture damage prediction model; The moisture loss prediction unit is connected to the logistics moisture loss management terminal and is used to obtain the real-time weather data and the real-time order information; The moisture loss prediction unit and the model training unit are used to predict the moisture loss rate of the express package based on the real-time weather data and the real-time order information and using the moisture loss prediction model to obtain the moisture loss prediction result.

10. The device for reducing the moisture loss rate of express packages based on big data analysis according to any one of claims 1 to 9, characterized in that: The real-time processing module includes: A weather data access module, used to obtain the real-time weather data; The real-time order processing module is used to obtain the real-time order information.

Images