Method, device and equipment for classifying express commodities in logistics order

Abstract

The invention discloses a classification method, device and equipment for express commodities in a logistics order, the method is applied to the technical field of logistics, and the method comprises the steps: obtaining the express attribute information of the logistics order from an express number system, and obtaining the commodity attribute information corresponding to the logistics order from a commodity information database; obtaining transportation attribute characteristics of the logistics order and commodity attribute characteristics of the logistics order; training a machine learning algorithm model by adopting the transportation attribute features and the commodity attribute features to obtain an express delivery commodity association model; and inputting the target transportation attribute feature and the target commodity attribute feature into an express delivery commodity association model to obtain a target express delivery emergency degree category and a target commodity category corresponding to the target logistics order. According to the invention, various types of classification are carried out on the logistics orders according to different attributes, and the classification accuracy and the classification efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device and equipment for classifying express goods in a logistics order. Background Art

[0002] The surge in the volume of express parcels, the wide variety of goods, and consumers' demanding requirements for delivery speed and service quality have jointly promoted the industry's urgent need for efficient, accurate, and intelligent management systems. Although the existing classification methods have supported the basic framework of logistics operations to a certain extent, their limitations are becoming increasingly prominent. First, inefficiency is one of the key factors restricting the development of the industry. Traditional manual classification or automated classification systems based on simple rules are often unable to cope with massive amounts of data, resulting in slow processing speeds and failure to meet the needs of rapid response to market changes. Secondly, low accuracy directly affects the quality of logistics operations and customer satisfaction. Incorrect classification may lead to the wrong delivery, delays, or even loss of packages, causing inconvenience to customers and damaging the brand image of logistics companies. Finally, the difficulty in dealing with large amounts of complex data limits the competitiveness of logistics companies in the era of big data. With the widespread application of technologies such as the Internet of Things and cloud computing, logistics data has shown explosive growth, but how to mine valuable information from these data and guide decision-making optimization has become a problem that the industry urgently needs to solve. Summary of the invention

[0003] The present invention provides a method, device and equipment for classifying express goods in a logistics order, which can realize multiple classifications of logistics orders according to different attributes, thereby improving the accuracy and efficiency of classification.

[0004] In one aspect, the present invention provides a method for classifying express goods in a logistics order, the method comprising:

[0005] Obtain the express attribute information of the logistics order from the express order number system, and obtain the commodity attribute information corresponding to the logistics order from the commodity information database;

[0006] Performing feature extraction processing on the express attribute information corresponding to the logistics order to obtain the transportation attribute features of the logistics order; and performing product attribute feature extraction on the product attribute information to obtain the product attribute features of the logistics order;

[0007] Using the transport attribute characteristics and the commodity attribute characteristics, training the machine learning algorithm model to obtain an express commodity association model;

[0008] Obtain target transportation attribute characteristics and target commodity attribute characteristics of the target logistics order;

[0009] The target transportation attribute characteristics and the target commodity attribute characteristics are input into the express commodity association model to obtain the target express urgency category and the target commodity category corresponding to the target logistics order.

[0010] Optionally, the step of performing feature extraction processing on the express attribute information corresponding to the logistics order to obtain the transport attribute features of the logistics order; and performing product attribute feature extraction on the product attribute information to obtain the product attribute features of the logistics order includes:

[0011] Performing data cleaning on the express attribute information and the commodity attribute information corresponding to the logistics order, and converting the cleaned data into data in a preset format to obtain pre-processed data;

[0012] Extracting the transport attribute characteristics of the logistics order from the express attribute information in the pre-processed data;

[0013] The commodity attribute features of the logistics order are extracted from the commodity attribute information in the preprocessed data.

[0014] Optionally, the adopting of the transport attribute features and the commodity attribute features to train a machine learning algorithm model to obtain an express commodity association model includes:

[0015] Obtaining the transport attribute characteristics and the commodity attribute characteristics corresponding to each of the plurality of logistics orders, wherein each logistics order is marked with a sample express urgency category label and a sample commodity category label;

[0016] Input the transport attribute characteristics and commodity attribute characteristics corresponding to each logistics order into the machine learning algorithm model;

[0017] Based on the fast urgency category recognition network in the machine learning algorithm model, the transportation attribute characteristics are identified and processed to obtain a sample urgency category result;

[0018] Based on the commodity category recognition network in the machine learning algorithm model, the commodity attribute features are identified and processed to obtain a sample commodity category result;

[0019] The machine learning algorithm model is trained according to the sample emergency category results, the sample commodity category results, the sample express urgency category labels and the sample commodity category labels to obtain the express commodity association model.

[0020] Optionally, the method further includes:

[0021] According to the transport attribute characteristics corresponding to each logistics order, determine the sample express urgency category label corresponding to each logistics order; the sample express urgency category label includes a sample emergency category label, a sample general category label and a sample non-emergency category label;

[0022] According to the commodity attribute characteristics corresponding to each logistics order, the sample commodity category label corresponding to each logistics order is determined; the sample commodity category label includes a sample high-value commodity label, a sample medium-value commodity label and a sample low-value commodity label.

[0023] Optionally, the training of the machine learning algorithm model according to the sample emergency category results, the sample commodity category results, the sample express urgency category labels, and the sample commodity category labels to obtain the express commodity association model includes:

[0024] Determining first loss data according to a difference between the sample urgency category result and the sample express urgency category label;

[0025] determining second loss data according to a difference between the sample product category result and the sample product category label;

[0026] determining target loss data according to the first loss data and the second loss data;

[0027] According to the target loss data, the parameters of the machine learning algorithm model are adjusted until the model converges to obtain the express product association model.

[0028] Optionally, the logistics order is further marked with a sample express delivery requirement label and a sample commodity characteristic label; the machine learning algorithm model further includes an express delivery requirement prediction network and a commodity characteristic prediction network; the method further includes:

[0029] Based on the express transportation requirement prediction network, the express transportation requirement prediction processing is performed on the transportation attribute characteristics to obtain a sample express transportation requirement result;

[0030] Based on the commodity characteristic prediction network, the commodity attribute features are processed for commodity characteristic prediction to obtain a sample commodity characteristic result;

[0031] The step of training the machine learning algorithm model according to the sample emergency category result, the sample commodity category result, the sample express urgency category label, and the sample commodity category label to obtain the express commodity association model includes:

[0032] According to the sample emergency category results, the sample commodity category results, the sample express urgency category labels, the sample commodity category labels, the sample express transportation requirements results, the sample commodity characteristic results, the sample express transportation requirements labels and the sample commodity characteristic labels, the machine learning algorithm model is trained to obtain the express commodity association model.

[0033] Optionally, the method further includes:

[0034] determining third loss data according to a difference between the sample express transportation requirement result and the sample express transportation requirement label;

[0035] determining fourth loss data according to a difference between the sample product characteristic result and the sample product characteristic label;

[0036] The target loss data is determined according to the first loss data, the second loss data, the third loss data, and the fourth loss data.

[0037] On the other hand, a device for classifying express goods in a logistics order is provided, the device comprising:

[0038] The attribute information acquisition module is used to obtain the express attribute information of the logistics order from the express order number system, and obtain the commodity attribute information corresponding to the logistics order from the commodity information database;

[0039] A feature extraction module is used to perform feature extraction processing on the express attribute information corresponding to the logistics order to obtain the transportation attribute features of the logistics order; and to perform product attribute feature extraction on the product attribute information to obtain the product attribute features of the logistics order;

[0040] A model training module, used to train a machine learning algorithm model using the transport attribute characteristics and the commodity attribute characteristics to obtain an express commodity association model;

[0041] A target feature acquisition module is used to acquire target transport attribute features and target commodity attribute features of a target logistics order;

[0042] The target category determination module is used to input the target transportation attribute characteristics and the target commodity attribute characteristics into the express commodity association model to obtain the target express urgency category and the target commodity category corresponding to the target logistics order.

[0043] Optionally, the feature extraction module includes:

[0044] A data processing unit, used to perform data cleaning on the express attribute information and the commodity attribute information corresponding to the logistics order, and convert the cleaned data into data in a preset format to obtain pre-processed data;

[0045] A transport feature extraction unit, used to extract the transport attribute features of the logistics order from the express attribute information in the pre-processed data;

[0046] The commodity feature extraction unit is used to extract the commodity attribute features of the logistics order from the commodity attribute information in the preprocessed data.

[0047] Optionally, the model training module includes:

[0048] A feature acquisition unit, used to acquire the transport attribute features and the commodity attribute features corresponding to each of the plurality of logistics orders, each logistics order being marked with a sample express urgency category label and a sample commodity category label;

[0049] A feature input unit, used to input the transport attribute features and commodity attribute features corresponding to each logistics order into the machine learning algorithm model;

[0050] A first recognition unit is used to recognize and process the transport attribute features based on a fast urgency category recognition network in the machine learning algorithm model to obtain a sample urgency category result;

[0051] A second identification unit is used to identify the commodity attribute features based on the commodity category identification network in the machine learning algorithm model to obtain a sample commodity category result;

[0052] A training unit is used to train the machine learning algorithm model according to the sample emergency category results, the sample commodity category results, the sample express urgency category labels and the sample commodity category labels to obtain the express commodity association model.

[0053] Optionally, the device further comprises:

[0054] The first label determination module is used to determine the sample express urgency category label corresponding to each logistics order according to the transportation attribute characteristics corresponding to each logistics order; the sample express urgency category label includes a sample emergency category label, a sample general category label and a sample non-emergency category label;

[0055] The second label determination module is used to determine the sample product category label corresponding to each logistics order according to the product attribute characteristics corresponding to each logistics order; the sample product category label includes a sample high-value product label, a sample medium-value product label and a sample low-value product label.

[0056] Optionally, the training unit includes:

[0057] A first loss determination unit, configured to determine first loss data according to a difference between the sample urgency category result and the sample express urgency category label;

[0058] a second loss determination unit, configured to determine second loss data according to a difference between the sample commodity category result and the sample commodity category label;

[0059] a target loss determination unit, configured to determine target loss data according to the first loss data and the second loss data;

[0060] A model determination unit is used to adjust the parameters of the machine learning algorithm model according to the target loss data until the model converges to obtain the express product association model.

[0061] Optionally, the logistics order is further marked with a sample express delivery requirement label and a sample commodity characteristic label; the machine learning algorithm model further includes an express delivery requirement prediction network and a commodity characteristic prediction network; the device further includes:

[0062] A sample transportation requirement determination module, used for performing express transportation requirement prediction processing on the transportation attribute characteristics based on the express transportation requirement prediction network to obtain a sample express transportation requirement result;

[0063] A sample commodity characteristic determination module is used to perform commodity characteristic prediction processing on the commodity attribute features based on the commodity characteristic prediction network to obtain a sample commodity characteristic result;

[0064] The training unit is also used to train the machine learning algorithm model according to the sample emergency category results, the sample commodity category results, the sample express urgency category labels, the sample commodity category labels, the sample express transportation requirements results, the sample commodity characteristic results, the sample express transportation requirements labels and the sample commodity characteristic labels to obtain the express commodity association model.

[0065] Optionally, the device further comprises:

[0066] A third loss determination module, configured to determine third loss data according to a difference between the sample express transportation requirement result and the sample express transportation requirement label;

[0067] a fourth loss determination module, configured to determine fourth loss data according to a difference between the sample commodity characteristic result and the sample commodity characteristic label;

[0068] A target loss determination module is used to determine the target loss data according to the first loss data, the second loss data, the third loss data and the fourth loss data.

[0069] On the other hand, an electronic device is provided, comprising a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the method for classifying express goods in logistics orders as described above.

[0070] On the other hand, a computer storage medium is provided, which stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by a processor to implement the method for classifying express goods in logistics orders as described above.

[0071] On the other hand, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes to implement the above-mentioned method for classifying express goods in the logistics order.

[0072] The method, device and equipment for classifying express goods in logistics orders provided by the present invention have the following technical effects:

[0073] The present invention obtains the express attribute information of the logistics order from the express order number system, and obtains the commodity attribute information corresponding to the logistics order from the commodity information database; performs feature extraction processing on the express attribute information corresponding to the logistics order to obtain the transportation attribute characteristics of the logistics order; and extracts the commodity attribute characteristics of the commodity attribute information to obtain the commodity attribute characteristics of the logistics order; uses the transportation attribute characteristics and the commodity attribute characteristics to train the machine learning algorithm model to obtain the express commodity association model; obtains the target transportation attribute characteristics and the target commodity attribute characteristics of the target logistics order; inputs the target transportation attribute characteristics and the target commodity attribute characteristics into the express commodity association model to obtain the target express urgency category and the target commodity category corresponding to the target logistics order. The present invention realizes multiple classification of logistics orders according to different attributes, and improves the accuracy and efficiency of classification. The present invention significantly improves the efficiency and accuracy of express and commodity information classification, reduces manual intervention, and reduces the error rate; can more effectively optimize the allocation of logistics resources, improve the overall efficiency of logistics operations; provide customers with more accurate logistics services, and improve customer satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the technical solutions and advantages of the embodiments of this specification or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0075] Figure 1 It is a schematic diagram of a classification system for express goods in a logistics order provided by an embodiment of this specification;

[0076] Figure 2 It is a flow chart of a method for classifying express goods in a logistics order provided by an embodiment of this specification;

[0077] Figure 3 It is a flowchart of a method provided by an embodiment of this specification for performing feature extraction processing on the express attribute information corresponding to the logistics order to obtain the transportation attribute characteristics of the logistics order; and performing product attribute feature extraction on the product attribute information to obtain the product attribute characteristics of the logistics order;

[0078] Figure 4 It is a flowchart of a method provided in an embodiment of this specification for training a machine learning algorithm model by using the transport attribute characteristics and the commodity attribute characteristics to obtain an express commodity association model;

[0079] Figure 5 It is a flowchart of a method provided by an embodiment of this specification for training the machine learning algorithm model according to the sample emergency category result, the sample commodity category result, the sample express urgency category label and the sample commodity category label to obtain the express commodity association model;

[0080] Figure 6 It is a structural schematic diagram of a classification device for express goods in a logistics order provided by an embodiment of this specification;

[0081] Figure 7 It is a structural diagram of a server provided in an embodiment of this specification. DETAILED DESCRIPTION

[0082] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0083] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0084] See also Figure 1 , Figure 1 is a schematic diagram of a classification system for express goods in a logistics order provided by an embodiment of this specification, such as Figure 1 As shown, the classification system for express goods in the logistics order may include at least a server 01 and a client 02 .

[0085] Specifically, in the embodiments of this specification, the server 01 may include an independently operated server, or a distributed server, or a server cluster composed of multiple servers, and may also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Server 01 may include a network communication unit, a processor, and a memory, etc. Specifically, the server 01 can be used to determine an express commodity association model; the target transportation attribute characteristics and the target commodity attribute characteristics are input into the express commodity association model to obtain the target express urgency category and the target commodity category corresponding to the target logistics order.

[0086] Specifically, in the embodiments of this specification, the client 02 may include physical devices such as smart phones, desktop computers, tablet computers, laptop computers, digital assistants, smart wearable devices, smart speakers, vehicle terminals, smart TVs, etc., and may also include software running in physical devices, such as web pages provided by some service providers to users, or applications provided by these service providers to users. Specifically, the client 02 may be used to display the target express urgency category and target commodity category corresponding to the target logistics order.

[0087] The following describes a method for classifying express goods in a logistics order of the present invention. Figure 2It is a flow chart of a method for classifying express goods in a logistics order provided in an embodiment of this specification. This specification provides method operation steps as described in the embodiment or flow chart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many orders, and does not represent the only order of execution. When the actual system or server product is executed, it can be executed in sequence or in parallel (for example, in a parallel processor or multi-threaded processing environment) according to the method shown in the embodiment or the accompanying drawings. Specifically, Figure 2 As shown, the method may include:

[0088] S201: Acquire the express attribute information of the logistics order from the express order number system, and acquire the commodity attribute information corresponding to the logistics order from the commodity information database.

[0089] In the embodiments of this specification, relevant data can be comprehensively collected from the express order number system and the commodity information database. For the express order number, not only the order number itself is obtained, but also the corresponding logistics status, transportation company and other information are extracted. The recipient information covers the name, contact number, detailed address and collection preferences (such as whether to require door-to-door delivery, designated collection point, etc.). The sender information includes the sender's name, phone number, address and time of shipment. In terms of commodities, in addition to the commodity name, specifications, and category, the commodity attribute information also collects detailed information such as the production date, shelf life, and place of origin of the commodity.

[0090] S203: Perform feature extraction processing on the express attribute information corresponding to the logistics order to obtain the transportation attribute features of the logistics order; and perform product attribute feature extraction on the product attribute information to obtain the product attribute features of the logistics order.

[0091] In the embodiments of this specification, Figure 3 As shown, the feature extraction process is performed on the express attribute information corresponding to the logistics order to obtain the transportation attribute features of the logistics order; and the commodity attribute feature extraction is performed on the commodity attribute information to obtain the commodity attribute features of the logistics order, including:

[0092] S2031: performing data cleaning on the express attribute information and the commodity attribute information corresponding to the logistics order, and converting the cleaned data into data in a preset format to obtain pre-processed data;

[0093] S2033: Extracting the transport attribute characteristics of the logistics order from the express attribute information in the pre-processed data;

[0094] S2035: Extracting commodity attribute features of the logistics order from the commodity attribute information in the preprocessed data.

[0095] In the embodiments of this specification, after data collection is completed, strict data cleaning and sorting are performed. Use data duplication checking algorithms to accurately identify and remove duplicate data to avoid repeated calculations and analysis. Detect and correct erroneous data through preset logical verification rules, such as incorrect address format, inconsistent phone number digits, etc. For incomplete data, reasonable supplements or markings are made based on the common patterns and logical relationships of related fields. At the same time, data from different data sources and in different formats are uniformly converted into a standard data format for subsequent processing and analysis.

[0096] In the feature extraction process, a feature extraction network may be used, or a trained feature extraction model may be used for feature extraction; wherein the feature extraction model may include a transportation attribute feature extraction model and a commodity attribute feature extraction model;

[0097] Among them, the training method of the transportation attribute feature extraction model includes:

[0098] Obtain sample express attribute information of a sample logistics order; the sample express attribute information is marked with a sample transportation attribute label;

[0099] Input the sample express attribute information into the transportation attribute extraction network of the first preset model to extract the transportation attribute features, and obtain the sample transportation attribute features; input the sample transportation attribute features into the transportation category prediction network of the first preset model to perform transportation category prediction processing, and obtain the sample transportation attribute results;

[0100] According to the difference between the sample transport attribute result and the sample transport attribute label, the first preset model is trained until the training end condition is met;

[0101] The transportation attribute extraction network in the first preset model at the end of training is determined as the feature extraction model.

[0102] Among them, the training method of the product attribute feature extraction model includes:

[0103] Obtaining sample commodity attribute information of a sample logistics order; the sample commodity attribute information is marked with a sample commodity category label;

[0104] Inputting the sample product attribute information into the product feature extraction network of the second preset model to perform product feature extraction processing to obtain sample product features;

[0105] Inputting the sample product features into a product category prediction network of a second preset model to perform product category prediction processing to obtain a sample product category result;

[0106] Training the second preset model according to the difference between the sample product category result and the sample product category label until a training end condition is met;

[0107] The product feature extraction network in the second preset model at the end of the training is determined as the product attribute feature extraction model.

[0108] S205: Using the transport attribute characteristics and the commodity attribute characteristics, a machine learning algorithm model is trained to obtain an express commodity association model.

[0109] In the embodiments of this specification, Figure 4 As shown, the transport attribute characteristics and the commodity attribute characteristics are used to train the machine learning algorithm model to obtain the express commodity association model, including:

[0110] S2051: Obtaining the transport attribute characteristics and the commodity attribute characteristics corresponding to each of the plurality of logistics orders, wherein each logistics order is marked with a sample express urgency category label and a sample commodity category label;

[0111] S2053: Inputting the transport attribute characteristics and the commodity attribute characteristics corresponding to each logistics order into the machine learning algorithm model;

[0112] S2055: performing identification processing on the transport attribute features based on the fast urgency category identification network in the machine learning algorithm model to obtain a sample urgency category result;

[0113] S2057: Based on the commodity category recognition network in the machine learning algorithm model, the commodity attribute features are recognized and processed to obtain a sample commodity category result;

[0114] S2059: According to the sample emergency category results, the sample commodity category results, the sample express urgency category labels and the sample commodity category labels, the machine learning algorithm model is trained to obtain the express commodity association model.

[0115] In an embodiment of the present specification, the machine learning algorithm may include a decision tree, a support vector machine, etc.; the transportation attribute characteristics corresponding to each of the multiple logistics orders and the commodity attribute characteristics may be obtained, and each logistics order is marked with a sample express urgency category label and a sample commodity category label; thereby constructing training sample data and training the machine learning algorithm model; based on the fast urgency category recognition network in the machine learning algorithm model, the transportation attribute characteristics are identified and processed to obtain a sample urgency category result; based on the commodity category recognition network in the machine learning algorithm model, the commodity attribute characteristics are identified and processed to obtain a sample commodity category result; finally, according to the sample urgency category result, the sample commodity category result, the sample express urgency category label and the sample commodity category label, the machine learning algorithm model is trained to obtain the express commodity association model.

[0116] In the embodiment of this specification, the method further includes:

[0117] According to the transport attribute characteristics corresponding to each logistics order, determine the sample express urgency category label corresponding to each logistics order; the sample express urgency category label includes a sample emergency category label, a sample general category label and a sample non-emergency category label;

[0118] According to the commodity attribute characteristics corresponding to each logistics order, the sample commodity category label corresponding to each logistics order is determined; the sample commodity category label includes a sample high-value commodity label, a sample medium-value commodity label and a sample low-value commodity label.

[0119] In the embodiments of this specification, an association model between express information and commodity information is established using advanced machine learning algorithms, such as decision trees and support vector machines. When constructing a decision tree model, the optimal splitting features and splitting points are selected according to indicators such as information gain and Gini coefficient, and a decision tree structure with clear hierarchy, easy to understand and explain is gradually generated. For the support vector machine model, by cleverly selecting kernel functions (such as linear kernel functions, Gaussian kernel functions, etc.), the data is mapped to a high-dimensional space, and the optimal hyperplane is found to distinguish different categories. According to the output results of the association model, a sophisticated classification strategy is formulated. According to the value of the commodity, different categories such as high value, medium value and low value are divided. For the urgency of express delivery, it is divided into emergency, ordinary and non-emergency levels according to customer needs and preset time standards.

[0120] In the embodiments of this specification, Figure 5As shown, the machine learning algorithm model is trained according to the sample emergency category results, the sample commodity category results, the sample express urgency category labels and the sample commodity category labels to obtain the express commodity association model, including:

[0121] S20591: Determine first loss data according to a difference between the sample urgency category result and the sample express urgency category label;

[0122] S20593: Determine second loss data according to the difference between the sample product category result and the sample product category label;

[0123] S20595: Determine target loss data according to the first loss data and the second loss data;

[0124] S20597: According to the target loss data, adjust the parameters of the machine learning algorithm model until the model converges to obtain the express product association model.

[0125] In an embodiment of the present specification, the first loss data can be determined based on the difference between the sample emergency category result and the sample express urgency category label; the second loss data can be determined based on the difference between the sample commodity category result and the sample commodity category label; the sum or weighted sum of the first loss data and the second loss data is calculated to obtain the target loss data; finally, according to the target loss data, the parameters of the machine learning algorithm model are adjusted until the model converges, and the machine learning algorithm model at the end of training is determined as the express commodity association model.

[0126] In the embodiment of this specification, the logistics order is also marked with a sample express delivery requirement label and a sample commodity characteristic label; the machine learning algorithm model also includes an express delivery requirement prediction network and a commodity characteristic prediction network; the method also includes:

[0127] Based on the express transportation requirement prediction network, the express transportation requirement prediction processing is performed on the transportation attribute characteristics to obtain a sample express transportation requirement result;

[0128] Based on the commodity characteristic prediction network, the commodity attribute features are processed for commodity characteristic prediction to obtain a sample commodity characteristic result;

[0129] The step of training the machine learning algorithm model according to the sample emergency category result, the sample commodity category result, the sample express urgency category label, and the sample commodity category label to obtain the express commodity association model includes:

[0130] According to the sample emergency category results, the sample commodity category results, the sample express urgency category labels, the sample commodity category labels, the sample express transportation requirements results, the sample commodity characteristic results, the sample express transportation requirements labels and the sample commodity characteristic labels, the machine learning algorithm model is trained to obtain the express commodity association model.

[0131] In the embodiment of the present specification, the sample express delivery requirement characteristics and sample commodity characteristic characteristics corresponding to the logistics order can also be extracted, and the machine learning algorithm model also includes an express delivery requirement prediction network and a commodity characteristic prediction network; based on the express delivery requirement prediction network, the transport attribute characteristics are processed for express delivery requirement prediction to obtain the sample express delivery requirement result; based on the commodity characteristic prediction network, the commodity attribute characteristics are processed for commodity characteristic prediction to obtain the sample commodity characteristic result; thus, the model can be trained for multi-task learning, and the target loss data is determined according to the sample emergency category result, the sample commodity category result, the sample express urgency category label, the sample commodity category label, the sample express delivery requirement result, the sample commodity characteristic result, the sample express delivery requirement label and the sample commodity characteristic label, and the machine learning algorithm model is trained to obtain the express commodity association model. According to the classification strategy formulated in advance, the model can quickly associate and classify the new data. After the classification is completed, pay close attention to the actual classification results and compare and analyze them with the expected results. According to the feedback of the actual classification results, the adaptive learning algorithm and parameter adjustment mechanism are used to continuously optimize the structure and parameters of the association model. For the classification strategy, flexible adjustments and improvements are made according to actual business needs and changes in data distribution.

[0132] In the embodiment of this specification, the method further includes:

[0133] determining third loss data according to a difference between the sample express transportation requirement result and the sample express transportation requirement label;

[0134] determining fourth loss data according to a difference between the sample product characteristic result and the sample product characteristic label;

[0135] The target loss data is determined according to the first loss data, the second loss data, the third loss data, and the fourth loss data.

[0136] In an embodiment of the present specification, the third loss data can be determined based on the difference between the sample express transportation requirement result and the sample express transportation requirement label; the fourth loss data can be determined based on the difference between the sample product characteristic result and the sample product characteristic label; the target loss data can be determined based on the first loss data, the second loss data, the third loss data and the fourth loss data, thereby comprehensively considering the characteristics of the product (such as fragile, perishable, etc.) and the express transportation requirements (such as refrigeration, special packaging, etc.), and further subdividing the classification strategy to achieve more accurate and efficient classification management.

[0137] S207: Obtain target transportation attribute characteristics and target commodity attribute characteristics of the target logistics order.

[0138] In the embodiments of the present specification, new express and commodity information can be input into the established classification model and associated and classified according to the established classification strategy.

[0139] S209: Input the target transportation attribute characteristics and the target commodity attribute characteristics into the express commodity association model to obtain the target express urgency category and the target commodity category corresponding to the target logistics order.

[0140] In the embodiments of this specification, the association model and classification strategy are continuously adjusted and optimized based on the feedback of the actual classification results. New express and commodity information is input into the established classification model in real time. During the input process, the data is preprocessed and feature extracted in real time to ensure the quality and consistency of the data. For example, when market demand changes and the commodity value assessment criteria change, the value division threshold in the classification strategy is updated in a timely manner. Through continuous adjustment and optimization, the classification model and strategy always maintain a high degree of accuracy and adaptability to better meet the ever-changing logistics business needs.

[0141] In an embodiment of the present specification, the target loss data can be determined based on the first loss data, the second loss data, the third loss data, and the fourth loss data, and then the machine learning algorithm model can be trained based on the target loss data to obtain an express commodity association model. The target transportation attribute characteristics and the target commodity attribute characteristics can be input into the express commodity association model to obtain the target express urgency category, target commodity category, target express transportation requirements, and target commodity characteristics corresponding to the target logistics order. Therefore, multiple classification results of logistics orders can be predicted based on the model, and the classification accuracy and efficiency can be improved, thereby achieving accurate monitoring of logistics orders.

[0142] In an exemplary embodiment, the method for classifying express goods in the logistics order of this embodiment includes:

[0143] Step 1: Collect relevant data from the express tracking number system and product information database, including the express tracking number, recipient information, sender information, product name, product specification, product category, etc.; clean and organize the collected data, remove duplicate, erroneous and incomplete data, and convert the data format uniformly;

[0144] Comprehensively collect relevant data from the express delivery number system and product information database. For express delivery number, not only the number itself is obtained, but also the corresponding logistics status, transportation company and other information. The recipient information includes name, contact number, detailed address and collection preferences (such as whether to require door-to-door delivery, designated collection point, etc.). The sender information includes the sender's name, phone number, address and time of shipment. In terms of goods, in addition to the product name, specifications, and category, detailed information such as the product's production date, shelf life, and place of origin are also collected.

[0145] After data collection is completed, strict data cleaning and sorting work is carried out. Use data duplication detection algorithms to accurately identify and remove duplicate data to avoid repeated calculations and analysis. Through preset logical verification rules, detect and correct incorrect data, such as incorrect address format, inconsistent phone number digits, etc. For incomplete data, reasonable supplements or markings are made based on the common patterns and logical relationships of related fields. At the same time, data from different data sources and in different formats are uniformly converted into a standard data format for subsequent processing and analysis.

[0146] Step 2: Extract key features from the preprocessed data, such as the express delivery route, transportation time, the value, weight, volume, etc. of the goods;

[0147] From the preprocessed data, key features are extracted using a variety of data analysis techniques and feature engineering methods. For express delivery routes, not only the starting point and the end point are considered, but also the main transit stations, modes of transportation (road, rail, air, etc.), and the distance and estimated transportation time of each section of the route are analyzed. In terms of transportation timeliness, the actual time from shipment to receipt is accurately calculated and compared with the estimated timeliness. The value of the goods is accurately quantified through the market price evaluation system, while considering the impact of factors such as the brand and scarcity of the goods on the value. The measurement of weight and volume not only uses directly obtained data, but also makes reasonable estimates and corrections for irregularly shaped goods. In addition, characteristics such as the popularity and fragility of the goods are extracted to more comprehensively describe the characteristics of the goods.

[0148] Step 3: Use machine learning algorithms, such as decision trees and support vector machines, to establish a correlation model between express information and product information; formulate a classification strategy based on the results of the correlation model, such as classifying products according to their value and the urgency of the delivery;

[0149] Using advanced machine learning algorithms, such as decision trees and support vector machines, we build an association model between express information and product information. When building a decision tree model, we select the optimal splitting features and splitting points based on information gain, Gini coefficient and other indicators, and gradually generate a decision tree structure with clear hierarchy, easy to understand and explain. For the support vector machine model, we map the data to a high-dimensional space by cleverly selecting kernel functions (such as linear kernel functions, Gaussian kernel functions, etc.), and find the optimal hyperplane to distinguish different categories. According to the output results of the association model, we formulate a refined classification strategy. According to the value of the goods, we divide them into different categories such as high value, medium value and low value. For the urgency of express delivery, we divide it into emergency, ordinary and non-emergency levels according to customer needs and preset time standards. On this basis, we comprehensively consider the characteristics of the goods (such as fragile, perishable, etc.) and the transportation requirements of express delivery (such as refrigeration, special packaging, etc.), and further subdivide the classification strategy to achieve more accurate and efficient classification management.

[0150] Step 4: Input the new express and product information into the established classification model, and perform associated classification according to the formulated classification strategy; based on the feedback from the actual classification results, continuously adjust and optimize the association model and classification strategy.

[0151] New express and commodity information is input into the established classification model in real time. During the input process, the data is preprocessed and feature extracted in real time to ensure the quality and consistency of the data. According to the classification strategy formulated in advance, the model quickly associates and classifies the new data. After the classification is completed, pay close attention to the actual classification results and compare and analyze them with the expected results. According to the feedback of the actual classification results, the adaptive learning algorithm and parameter adjustment mechanism are used to continuously optimize the structure and parameters of the association model. For the classification strategy, flexible adjustments and improvements are made according to the actual business needs and changes in data distribution. For example, when the market demand changes and the commodity value assessment standards change, the value division threshold in the classification strategy is updated in a timely manner. Through continuous adjustment and optimization, the classification model and strategy always maintain a high degree of accuracy and adaptability to better meet the ever-changing logistics business needs.

[0152] It can be seen from the technical solutions provided by the above embodiments of this specification that the embodiments of this specification obtain the express attribute information of the logistics order from the express order number system, and obtain the commodity attribute information corresponding to the logistics order from the commodity information database; perform feature extraction processing on the express attribute information corresponding to the logistics order to obtain the transportation attribute characteristics of the logistics order; and perform commodity attribute feature extraction on the commodity attribute information to obtain the commodity attribute characteristics of the logistics order; use the transportation attribute characteristics and the commodity attribute characteristics to train the machine learning algorithm model to obtain the express commodity association model; obtain the target transportation attribute characteristics and target commodity attribute characteristics of the target logistics order; input the target transportation attribute characteristics and the target commodity attribute characteristics into the express commodity association model to obtain the target express urgency category and the target commodity category corresponding to the target logistics order. The present invention realizes multiple classification of logistics orders according to different attributes, and improves the accuracy and efficiency of classification. The present invention significantly improves the efficiency and accuracy of express and commodity information classification, reduces manual intervention, and reduces the error rate; can more effectively optimize the allocation of logistics resources and improve the overall efficiency of logistics operations; provides customers with more accurate logistics services and improves customer satisfaction.

[0153] The embodiment of this specification also provides a classification device for express goods in a logistics order, such as Figure 6 As shown, the device comprises:

[0154] The attribute information acquisition module 610 is used to acquire the express attribute information of the logistics order from the express order number system, and acquire the commodity attribute information corresponding to the logistics order from the commodity information database;

[0155] The feature extraction module 620 is used to perform feature extraction processing on the express attribute information corresponding to the logistics order to obtain the transportation attribute features of the logistics order; and to perform product attribute feature extraction on the product attribute information to obtain the product attribute features of the logistics order;

[0156] A model training module 630 is used to train a machine learning algorithm model using the transport attribute characteristics and the commodity attribute characteristics to obtain an express commodity association model;

[0157] The target feature acquisition module 640 is used to acquire the target transportation attribute features and target commodity attribute features of the target logistics order;

[0158] The target category determination module 650 is used to input the target transportation attribute characteristics and the target commodity attribute characteristics into the express commodity association model to obtain the target express urgency category and the target commodity category corresponding to the target logistics order.

[0159] Optionally, the feature extraction module includes:

[0160] A data processing unit, used to perform data cleaning on the express attribute information and the commodity attribute information corresponding to the logistics order, and convert the cleaned data into data in a preset format to obtain pre-processed data;

[0161] A transport feature extraction unit, used to extract the transport attribute features of the logistics order from the express attribute information in the pre-processed data;

[0162] The commodity feature extraction unit is used to extract the commodity attribute features of the logistics order from the commodity attribute information in the preprocessed data.

[0163] Optionally, the model training module includes:

[0164] A feature acquisition unit, used to acquire the transport attribute features and the commodity attribute features corresponding to each of the plurality of logistics orders, each logistics order being marked with a sample express urgency category label and a sample commodity category label;

[0165] A feature input unit, used to input the transport attribute features and commodity attribute features corresponding to each logistics order into the machine learning algorithm model;

[0166] A first recognition unit is used to recognize and process the transport attribute features based on a fast urgency category recognition network in the machine learning algorithm model to obtain a sample urgency category result;

[0167] A second identification unit is used to identify the commodity attribute features based on the commodity category identification network in the machine learning algorithm model to obtain a sample commodity category result;

[0168] A training unit is used to train the machine learning algorithm model according to the sample emergency category results, the sample commodity category results, the sample express urgency category labels and the sample commodity category labels to obtain the express commodity association model.

[0169] Optionally, the device further comprises:

[0170] The first label determination module is used to determine the sample express urgency category label corresponding to each logistics order according to the transportation attribute characteristics corresponding to each logistics order; the sample express urgency category label includes a sample emergency category label, a sample general category label and a sample non-emergency category label;

[0171] The second label determination module is used to determine the sample product category label corresponding to each logistics order according to the product attribute characteristics corresponding to each logistics order; the sample product category label includes a sample high-value product label, a sample medium-value product label and a sample low-value product label.

[0172] Optionally, the training unit includes:

[0173] A first loss determination unit, configured to determine first loss data according to a difference between the sample urgency category result and the sample express urgency category label;

[0174] a second loss determination unit, configured to determine second loss data according to a difference between the sample commodity category result and the sample commodity category label;

[0175] a target loss determination unit, configured to determine target loss data according to the first loss data and the second loss data;

[0176] A model determination unit is used to adjust the parameters of the machine learning algorithm model according to the target loss data until the model converges to obtain the express product association model.

[0177] Optionally, the logistics order is further marked with a sample express delivery requirement label and a sample commodity characteristic label; the machine learning algorithm model further includes an express delivery requirement prediction network and a commodity characteristic prediction network; the device further includes:

[0178] A sample transportation requirement determination module, used for performing express transportation requirement prediction processing on the transportation attribute characteristics based on the express transportation requirement prediction network to obtain a sample express transportation requirement result;

[0179] A sample commodity characteristic determination module is used to perform commodity characteristic prediction processing on the commodity attribute features based on the commodity characteristic prediction network to obtain a sample commodity characteristic result;

[0180] The training unit is also used to train the machine learning algorithm model according to the sample emergency category results, the sample commodity category results, the sample express urgency category labels, the sample commodity category labels, the sample express transportation requirements results, the sample commodity characteristic results, the sample express transportation requirements labels and the sample commodity characteristic labels to obtain the express commodity association model.

[0181] Optionally, the device further comprises:

[0182] A third loss determination module, configured to determine third loss data according to a difference between the sample express transportation requirement result and the sample express transportation requirement label;

[0183] a fourth loss determination module, configured to determine fourth loss data according to a difference between the sample commodity characteristic result and the sample commodity characteristic label;

[0184] A target loss determination module is used to determine the target loss data according to the first loss data, the second loss data, the third loss data and the fourth loss data.

[0185] The device and method embodiments in the described device embodiments are based on the same inventive concept.

[0186] An embodiment of the present specification provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement a method for classifying express goods in a logistics order as provided in the above method embodiment.

[0187] An embodiment of the present invention also provides a computer storage medium, which can be set in a terminal to store at least one instruction or at least one program related to a method for classifying express goods in a logistics order in a method embodiment. The at least one instruction or at least one program is loaded and executed by the processor to implement the method for classifying express goods in a logistics order provided in the above method embodiment.

[0188] The embodiment of the present invention also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes to implement the method for classifying express goods in the logistics order provided by the above method embodiment.

[0189] Optionally, in the embodiments of this specification, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0190] The memory described in the embodiments of this specification can be used to store software programs and modules, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, application programs required for functions, etc.; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.

[0191] The method for classifying express goods in a logistics order provided in the embodiments of this specification can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking running on a server as an example, Figure 7 This is a hardware structure block diagram of a server for a method for classifying express goods in a logistics order provided by an embodiment of this specification. Figure 7 As shown, the server 700 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 710 (the central processing unit 710 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 730 for storing data, and one or more storage media 720 (such as one or more mass storage devices) for storing application programs 723 or data 722. Among them, the memory 730 and the storage medium 720 can be short-term storage or permanent storage. The program stored in the storage medium 720 may include one or more modules, each of which may include a series of instruction operations on the server. Furthermore, the central processing unit 710 can be configured to communicate with the storage medium 720 and execute a series of instruction operations in the storage medium 720 on the server 700. The server 700 may also include one or more power supplies 760, one or more wired or wireless network interfaces 750, one or more input and output interfaces 740, and / or one or more operating systems 721, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0192] The input / output interface 740 may be used to receive or send data via a network. The specific example of the network may include a wireless network provided by a communication provider of the server 700. In one example, the input / output interface 740 includes a network adapter (Network Interface Controller, NIC), which may be connected to other network devices via a base station so as to communicate with the Internet. In one example, the input / output interface 740 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0193] It can be understood by those skilled in the art that Figure 7 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 7 More or fewer components as shown, or with Figure 7 Different configurations are shown.

[0194] It can be seen from the embodiments of the method, device, electronic device or storage medium for classifying express goods in the logistics order provided by the present invention that the present invention obtains the express attribute information of the logistics order from the express order number system, and obtains the commodity attribute information corresponding to the logistics order from the commodity information database; performs feature extraction processing on the express attribute information corresponding to the logistics order to obtain the transportation attribute characteristics of the logistics order; and extracts the commodity attribute characteristics of the commodity attribute information to obtain the commodity attribute characteristics of the logistics order; uses the transportation attribute characteristics and the commodity attribute characteristics to train the machine learning algorithm model to obtain the express commodity association model; obtains the target transportation attribute characteristics and the target commodity attribute characteristics of the target logistics order; inputs the target transportation attribute characteristics and the target commodity attribute characteristics into the express commodity association model to obtain the target express urgency category and the target commodity category corresponding to the target logistics order. The present invention realizes multiple classifications of logistics orders according to different attributes, and improves the accuracy and efficiency of classification. The present invention significantly improves the efficiency and accuracy of express and commodity information classification, reduces manual intervention, and reduces the error rate; can more effectively optimize the allocation of logistics resources, improve the overall efficiency of logistics operations; provide customers with more accurate logistics services, and improve customer satisfaction.

[0195] It should be noted that the above sequence of the embodiments of this specification is for description only and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0196] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0197] A person skilled in the art will appreciate that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0198] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for classifying express goods in a logistics order, characterized in that: The method comprises: Acquire the express attribute information of the logistics order from the express order number system, and acquire the commodity attribute information corresponding to the logistics order from the commodity information database; Performing feature extraction processing on the express attribute information corresponding to the logistics order to obtain the transportation attribute features of the logistics order; and performing product attribute feature extraction on the product attribute information to obtain the product attribute features of the logistics order; Using the transport attribute characteristics and the commodity attribute characteristics, training the machine learning algorithm model to obtain an express commodity association model; Obtain target transportation attribute characteristics and target commodity attribute characteristics of the target logistics order; The target transportation attribute characteristics and the target commodity attribute characteristics are input into the express commodity association model to obtain the target express urgency category and the target commodity category corresponding to the target logistics order.

2. The method according to claim 1, characterized in that The feature extraction process is performed on the express attribute information corresponding to the logistics order to obtain the transportation attribute features of the logistics order; and the commodity attribute feature extraction is performed on the commodity attribute information to obtain the commodity attribute features of the logistics order, including: Performing data cleaning on the express attribute information and the commodity attribute information corresponding to the logistics order, and converting the cleaned data into data in a preset format to obtain pre-processed data; Extracting the transport attribute characteristics of the logistics order from the express attribute information in the pre-processed data; The commodity attribute features of the logistics order are extracted from the commodity attribute information in the preprocessed data.

3. The method according to claim 1, characterized in that The method of using the transport attribute features and the commodity attribute features to train the machine learning algorithm model to obtain the express commodity association model includes: Obtaining the transport attribute characteristics and the commodity attribute characteristics corresponding to each of the plurality of logistics orders, wherein each logistics order is marked with a sample express urgency category label and a sample commodity category label; Input the transport attribute characteristics and commodity attribute characteristics corresponding to each logistics order into the machine learning algorithm model; Based on the fast urgency category recognition network in the machine learning algorithm model, the transportation attribute characteristics are identified and processed to obtain a sample urgency category result; Based on the commodity category recognition network in the machine learning algorithm model, the commodity attribute features are identified and processed to obtain a sample commodity category result; The machine learning algorithm model is trained according to the sample emergency category results, the sample commodity category results, the sample express urgency category labels and the sample commodity category labels to obtain the express commodity association model.

4. The method according to claim 3, characterized in that The method further comprises: According to the transport attribute characteristics corresponding to each logistics order, determine the sample express urgency category label corresponding to each logistics order; the sample express urgency category label includes a sample emergency category label, a sample general category label and a sample non-emergency category label; According to the commodity attribute characteristics corresponding to each logistics order, the sample commodity category label corresponding to each logistics order is determined; the sample commodity category label includes a sample high-value commodity label, a sample medium-value commodity label and a sample low-value commodity label.

5. The method according to claim 3, characterized in that: The step of training the machine learning algorithm model according to the sample emergency category result, the sample commodity category result, the sample express urgency category label, and the sample commodity category label to obtain the express commodity association model includes: Determining first loss data according to a difference between the sample urgency category result and the sample express urgency category label; determining second loss data according to a difference between the sample product category result and the sample product category label; determining target loss data according to the first loss data and the second loss data; According to the target loss data, the parameters of the machine learning algorithm model are adjusted until the model converges to obtain the express product association model.

6. The method according to claim 5, characterized in that The logistics order is also marked with a sample express delivery requirement label and a sample commodity characteristic label; the machine learning algorithm model also includes an express delivery requirement prediction network and a commodity characteristic prediction network; the method also includes: Based on the express transportation requirement prediction network, the express transportation requirement prediction processing is performed on the transportation attribute characteristics to obtain a sample express transportation requirement result; Based on the commodity characteristic prediction network, the commodity attribute features are processed for commodity characteristic prediction to obtain a sample commodity characteristic result; The step of training the machine learning algorithm model according to the sample emergency category result, the sample commodity category result, the sample express urgency category label, and the sample commodity category label to obtain the express commodity association model includes: According to the sample emergency category results, the sample commodity category results, the sample express urgency category labels, the sample commodity category labels, the sample express transportation requirements results, the sample commodity characteristic results, the sample express transportation requirements labels and the sample commodity characteristic labels, the machine learning algorithm model is trained to obtain the express commodity association model.

7. The method according to claim 6, characterized in that The method further comprises: determining third loss data according to a difference between the sample express transportation requirement result and the sample express transportation requirement label; determining fourth loss data according to a difference between the sample product characteristic result and the sample product characteristic label; The target loss data is determined according to the first loss data, the second loss data, the third loss data, and the fourth loss data.

8. A device for classifying express goods in a logistics order, characterized in that: The device comprises: The attribute information acquisition module is used to obtain the express attribute information of the logistics order from the express order number system, and obtain the commodity attribute information corresponding to the logistics order from the commodity information database; A feature extraction module is used to perform feature extraction processing on the express attribute information corresponding to the logistics order to obtain the transportation attribute features of the logistics order; and to perform product attribute feature extraction on the product attribute information to obtain the product attribute features of the logistics order; A model training module, used to train a machine learning algorithm model using the transport attribute characteristics and the commodity attribute characteristics to obtain an express commodity association model; A target feature acquisition module is used to acquire target transport attribute features and target commodity attribute features of a target logistics order; The target category determination module is used to input the target transportation attribute characteristics and the target commodity attribute characteristics into the express commodity association model to obtain the target express urgency category and the target commodity category corresponding to the target logistics order.

9. An electronic device, characterized in that: The device includes: a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the method for classifying express goods in a logistics order as described in any one of claims 1-7.

10. A computer storage medium, characterized in that: The computer storage medium stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the method for classifying express goods in a logistics order as described in any one of claims 1-7.

Images