Intelligent express order processing optimization system and method based on big data analysis

Abstract

The invention belongs to the technical field of logistics management, and discloses an intelligent express order processing optimization system and method based on big data analysis, and the method comprises the steps: collecting the data related to an express order in a target express company, and obtaining the corresponding logistics order information; the logistics order information comprises express order information and order auxiliary data; performing data processing on the acquired logistics order information to obtain a corresponding order decision tree diagram; obtaining to-be-processed orders, and making corresponding initial order processing strategies for the to-be-processed orders in combination with the order decision tree diagram; performing strategy verification on the obtained initial order processing strategy, and taking corresponding feedback measures based on a strategy verification result; and efficient management and optimization of the express order information are realized.

Description

Technical Field

[0001] The present invention relates to the field of logistics management technology, and more specifically, to an intelligent express order processing optimization system and method based on big data analysis. Background Art

[0002] With the rapid development of e-commerce and the increasing global trade, the express delivery industry is facing unprecedented challenges and opportunities. The traditional order processing method can no longer meet the needs of modern logistics; Compared with the existing technology, the traditional order processing method has the problems of low efficiency, high error rate, difficulty in adapting to large-scale business needs, and cannot fully consider the personalized needs of users; at the same time, it is difficult to meet the requirements of real-time and accuracy; and there are also many problems such as lack of effective data processing means when processing complex logistics order information, which makes it impossible to deeply explore the hidden information and rules behind the data; in view of this, the present invention proposes an intelligent express order processing optimization system and method based on big data analysis to solve the above problems. Summary of the invention

[0003] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: Intelligent express order processing optimization system based on big data analysis, including: A data collection module is used to collect data related to express orders in the target express company to obtain corresponding logistics order information; the logistics order information includes express order information and order auxiliary data; The data processing module is used to process the collected logistics order information and obtain the corresponding order decision tree diagram; The order processing module is used to obtain pending orders and formulate corresponding initial order processing strategies for the pending orders in combination with the order decision tree diagram; The strategy verification module is used to verify the obtained initial order processing strategy and take corresponding feedback measures based on the strategy verification results.

[0004] Furthermore, the process of collecting data related to express orders in the target express company and obtaining corresponding logistics order information includes: The data collection module is provided with a plurality of data collection nodes, and based on the data collection nodes, data related to express orders stored in the management center of the target express company are collected to obtain a plurality of express order information, wherein the express order information includes user data, order data and delivery data; At the same time, the data collection node is also used to collect data from external data sources to obtain corresponding order auxiliary data; the external data sources include the Meteorological Bureau and social media; The corresponding express order information and the corresponding order auxiliary data in the order processing process are aggregated to obtain the corresponding logistics order information.

[0005] Furthermore, the process of data processing the collected logistics order information includes: Performing data preprocessing on the collected logistics order data to obtain corresponding initial logistics information; the data preprocessing includes data cleaning and data integration; Obtaining the order data in the initial logistics information, and performing data screening on the corresponding order data to obtain corresponding order index data; Classify the corresponding order indicator data based on a pre-built indicator classification function to obtain corresponding order feature data; the order feature data includes a first order feature and a second order feature; Acquire corresponding order data based on the initial logistics information to acquire the order processing time corresponding to the corresponding order processing process, and construct a mapping relationship between the order processing time and the order feature data; Obtaining a flowchart of the order processing, and mapping each characteristic indicator in the order characteristic data to the flowchart of the corresponding order processing, and based on the flowchart, obtaining a correlation relationship between different characteristic indicators; wherein the characteristic indicator is a first order characteristic or a second order characteristic; The number of occurrences of each characteristic indicator in the order data in different initial logistics information is obtained respectively, and the frequency characteristic value corresponding to the corresponding characteristic indicator is obtained based on the number of occurrences of each characteristic indicator in the order data in different initial logistics information; The frequency feature values ​​of the first order feature and the second order feature are sorted respectively, and starting from the root node, the corresponding first order feature and the second order feature are added to the tree according to the sorting of the frequency feature values ​​to obtain corresponding primary index branches and secondary index branches; Furthermore, based on the correlation between the obtained characteristic indicators, the corresponding primary indicator branches and secondary indicator branches are merged to obtain the corresponding order bifurcation tree.

[0006] Furthermore, the process of classifying the corresponding order indicator data based on the pre-built indicator classification function to obtain the corresponding order feature data includes: Define the indicator classification function as: ; In the formula, Indicates normalization processing; Indicates Initial order data The regularization coefficient corresponding to the order indicator data, ; Indicates The regression coefficient of the order indicator data; represents the regularization factor; Indicates Initial order data Order indicator data; Indicates Reference value of order indicator data; and is an integer, Indicates the total number of order data; Represents the index of order data; >0 and is an integer, Indicates the total number of order indicator data in the corresponding order data; Indicates the index of order indicator data; Obtain the regularization coefficient corresponding to each order indicator data in the corresponding order data, and compare it with the pre-set regularization threshold range; If the regularization coefficient is greater than the maximum value of the regularization threshold range, the corresponding order indicator data is marked as the first order feature; if the regularization coefficient is within the regularization threshold range, the corresponding order indicator data is marked as the second order feature; if the regularization coefficient is less than the minimum value of the regularization threshold range, no other operation is performed; Aggregate the corresponding first order features and the second order features to obtain corresponding first order data; Furthermore, the first order data corresponding to the order data in all the initial logistics information is obtained, and the data is merged to obtain the corresponding order feature data.

[0007] Furthermore, the process of obtaining the order decision tree diagram includes: Based on the acquisition process of the order bifurcation tree, the corresponding user bifurcation tree and delivery bifurcation tree are obtained respectively; the mapping relationship between the order data, delivery data and user data and the corresponding order processing time is obtained respectively, and the corresponding user bifurcation tree, delivery bifurcation tree and order bifurcation tree are merged to obtain the corresponding order decision tree diagram.

[0008] Furthermore, the process of obtaining pending orders and formulating corresponding initial order processing strategies for the corresponding pending orders in combination with the order decision tree diagram includes: Based on the data collection node, the pending order information corresponding to the constructed pending order is obtained from the management platform; the pending order information includes order data and user data; Traversing the corresponding order decision tree diagram based on the pending order information, and performing node similarity matching to obtain a root node in the corresponding pending order information that is similar to the corresponding pending order data and user data; Based on the mapping relationship between the corresponding root node and the order processing time, the order processing time of the corresponding to-be-processed order is predicted to obtain the corresponding expected order processing time; The obtained pending order information and expected order processing time are input into a pre-built order decision model to obtain a corresponding initial order processing strategy.

[0009] Furthermore, the construction process of the order decision model includes: Acquire the constructed order decision tree diagram, and construct a plurality of training data sets based on the order decision tree diagram, wherein the training data sets are composed of a plurality of training subsets; The network framework of the order decision model is defined as a convolutional neural network, which is used to learn the mapping relationship between order data, delivery data, and user data; The basic architecture of the convolutional neural network is an input layer, a hidden layer and an output layer; the input layer is used to receive the input training subset and perform a linear transformation on it to obtain a corresponding feature matrix; The hidden layer is used to perform nonlinear transformation on the corresponding feature matrix, extract the features of the feature matrix, learn the rules and patterns in the data, and pass these features to the output layer for decision making; The output layer is used to receive the output of the hidden layer and make decisions on the input data based on the features extracted by the hidden layer and the rules and patterns in the learning data; Define the objective function of the order decision model ; In the formula, express Order processing strategy at the moment; Expressing the expected value of selection The maximum value of express Discount factor for the moment; and Respectively represent the strategy state and strategy action at time t; represents the reward function; ; The total length of time representing the expected order processing time entered; The loss function of the order decision model is defined as ; In the formula, Indicates the input The labels of the training subsets, and is an integer, Represents the total number of training subsets; Indicates The expected result of the output result corresponding to the samples; iteratively train the corresponding order decision model based on the training data set, and The optimizer continuously optimizes the model parameters of the corresponding order decision model during the iterative training process until the difference between the loss function in the order decision model and the corresponding objective function is continuously The training subsets no longer decrease or change, and the model parameters are saved, which completes the construction process of the order decision model; is a constant.

[0010] Furthermore, the process of verifying the obtained initial order processing strategy includes: Obtain the entire process of corresponding order processing and build a corresponding order simulation model based on it; Input the obtained initial order processing strategy and the real-time collected order auxiliary data into the corresponding order simulation model, and record the data of the operation process of the corresponding order simulation model to obtain the corresponding simulation order information; Obtain the entire process of corresponding order processing and divide it into detailed processes; obtain several order processing sub-processes; Based on the simulated order information, process data corresponding to different order sub-processes are respectively obtained, and marked as primary parameters; and sub-data in the corresponding process data are marked as secondary parameters; Constructing a fuzzy process evaluation interval, wherein a plurality of sub-intervals are set in the fuzzy process evaluation interval; Obtain the membership degree of the corresponding secondary parameter data and the corresponding fuzzy process evaluation interval; Obtain the membership between the corresponding secondary parameter data and all sub-intervals, and select the two sub-intervals with the highest membership respectively and , and the membership degree corresponding to the corresponding subinterval is recorded as and ; Then, obtain the corresponding secondary parameters and corresponding sub-intervals The association parameters between Obtain the correlation parameters between all secondary indicators in the corresponding primary indicator and the corresponding fuzzy process evaluation interval, and construct the corresponding secondary correlation matrix based on them; Obtain the product of the weight row vector corresponding to each secondary parameter and the corresponding association matrix, obtain the association factor between the corresponding primary parameter and the corresponding fuzzy level, and construct the primary association matrix based on it; Then, the product of the weight row vector corresponding to each first-level parameter and the corresponding first-level correlation matrix is ​​obtained to obtain the strategy characteristic value corresponding to the corresponding initial order strategy; Set a feature threshold and compare the obtained strategy feature value with the corresponding feature threshold; If the strategy characteristic value is not less than the characteristic threshold, the corresponding initial order processing strategy is used as the optimal order processing strategy, and the corresponding process execution instruction is generated based on it, and the instruction feedback is performed; If the strategy characteristic value is less than the characteristic threshold, the sub-interval corresponding to each secondary parameter is obtained, and based on whether the upper limit value of the corresponding sub-interval is lower than the preset parameter threshold, if not, no other operation is performed; if it is, the corresponding secondary parameter is marked as a parameter to be optimized, and based on the order decision tree diagram, it is determined whether the corresponding parameter to be optimized is a characteristic indicator; if it is a characteristic indicator, the corresponding indicator data to be optimized is input as a constraint condition into the corresponding order decision model to obtain a new initial order processing strategy, and so on; if it is not a characteristic indicator, the corresponding indicator to be optimized is fed back to the management platform for manual intervention.

[0011] Furthermore, the membership degree between the secondary parameter data and the corresponding fuzzy process evaluation interval ; In the formula, Indicates First level parameter The second-level parameters and the fuzzy process evaluation interval The degree of membership between subintervals; and They represent the first The upper and lower limits of the subintervals; Indicates First level parameter Secondary parameters; among them, and is an integer, Indicates the total number of order sub-processes; and is an integer, Indicates the total number of secondary parameters in the corresponding order subprocess; Corresponding secondary parameters and corresponding subintervals The correlation parameters between ; In the formula, Indicates First level parameter Secondary parameters and fuzzy process evaluation interval Correlation parameter between subintervals.

[0012] Furthermore, the intelligent express order processing optimization method based on big data analysis includes: Step 1: Collect data related to express orders in the target express company to obtain corresponding logistics order information; the logistics order information includes express order information and order auxiliary data; Step 2: Process the collected logistics order information to obtain the corresponding order decision tree diagram; Step 3: Obtain pending orders and formulate corresponding initial order processing strategies for the pending orders in combination with the order decision tree diagram; Step 4: Verify the initial order processing strategy obtained and take corresponding feedback measures based on the strategy verification results.

[0013] Technical effects and advantages of the intelligent express order processing optimization system and method based on big data analysis described in the present invention: 1. Generate an order decision tree diagram by performing complex data preprocessing and feature extraction on the collected logistics order information; and classify the order indicator data based on the construction of the indicator classification function to effectively identify the key factors affecting the order processing efficiency; 2. The construction of the order decision tree diagram can provide personalized initial order processing strategies for different order types and user needs; improve the efficiency of resource allocation and reduce operating costs; at the same time, by verifying the order processing strategy, ensure the effectiveness of the strategy, and adjust the strategy based on feedback to continuously improve service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a schematic diagram of the intelligent express order processing optimization system based on big data analysis of the present invention; Figure 2 It is a schematic diagram of the intelligent express order processing optimization method based on big data analysis of the present invention. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0016] Example 1 See also Figure 1 As shown, the intelligent express order processing optimization system based on big data analysis in this embodiment includes: The data collection module is used to collect data related to express orders in the target express company and obtain corresponding logistics order information; the logistics order information includes express order information and order auxiliary data; The data processing module is used to process the collected logistics order information and obtain the corresponding order decision tree diagram; The order processing module is used to obtain pending orders and formulate corresponding initial order processing strategies for the pending orders in combination with the order decision tree diagram; A strategy verification module is used to verify the obtained initial order processing strategy and take corresponding feedback measures based on the strategy verification results; The modules are connected to each other via wired and / or wireless means to achieve data transmission between modules.

[0017] It should be further explained that, in the specific implementation process, the process of collecting data related to express orders in the target express company and obtaining the corresponding logistics order information includes: The data collection module is provided with several data collection nodes, which are connected to the management platform of the target express company through an API interface or a database, and based on the data collection nodes, the data related to the express order stored in the management platform of the target express company is collected to obtain several express order information, wherein the express order information includes user data, order data and delivery data, etc.; wherein the user data includes user preferences, user basic information, etc.; the order data includes commodity type, commodity quantity, etc.; the delivery data includes delivery route, delivery time, etc.; At the same time, the data collection node is also used to collect data from external data sources to obtain corresponding order-assisted data; the external data sources include the Meteorological Bureau and social media; the order-assisted data includes weather forecasts, traffic conditions and other data related to express order processing efficiency; The corresponding express order information and the corresponding order auxiliary data in the order processing process are aggregated to obtain the corresponding logistics order information.

[0018] It should be further explained that, in the specific implementation process, the process of processing the collected logistics order information and obtaining the corresponding order decision tree diagram includes: Data preprocessing is performed on the collected logistics order data to obtain the corresponding initial logistics information; data preprocessing includes data cleaning and data integration; data cleaning refers to deleting duplicate data in the collected logistics order information, filling in and correcting missing parts and abnormal data in the logistics order information; data integration refers to data standardization of the logistics order information after data cleaning, mapping the corresponding logistics order data into a pre-set data format to facilitate subsequent data processing; Obtain the order data in the initial logistics information, and perform data screening on the corresponding order data to obtain the corresponding order index data. The order index data refers to the index data in the order data that can reflect the corresponding order processing efficiency from different aspects; Then, the corresponding order indicator data is classified based on the pre-built indicator classification function to obtain the corresponding order feature data; The process of classifying the corresponding order indicator data based on the pre-built indicator classification function and obtaining the corresponding order feature data includes: Define the indicator classification function as: ; In the formula, Indicates normalization processing; Indicates Initial order data The regularization coefficient corresponding to the order indicator data, where ; Indicates The regression coefficient of the order indicator data; Represents the regularization factor, which is used to achieve feature selection and dimensionality reduction. Values ​​increase the penalty on the coefficients, causing more regularization coefficients to become zero; Indicates Initial order data Order indicator data; Indicates Reference value of order indicator data; and is an integer, Indicates the total number of order data; Represents the index of order data; >0 and is an integer, Indicates the total number of order indicator data in the corresponding order data; Indicates the index of order indicator data; Taking a certain order data as an example, obtain the regularization coefficient corresponding to each order indicator data in the corresponding order data, and compare it with the pre-set regularization threshold range; If the regularization coefficient is greater than the maximum value of the regularization threshold range, the corresponding order indicator data is marked as the first order feature; if the regularization coefficient is within the regularization threshold range, the corresponding order indicator data is marked as the second order feature; if the regularization coefficient is less than the minimum value of the regularization threshold range, no other operation is performed; The corresponding first order feature and the second order feature are aggregated to obtain the corresponding first order data; wherein the influence degree of the feature index on the order processing of the corresponding order sub-process is: the first order feature is greater than the second order feature, and the larger the regularization coefficient corresponding to the corresponding feature index is, the higher the corresponding influence degree is; Then, the first order data corresponding to the order data in all the initial logistics information is obtained, and the data is merged to obtain the corresponding order feature data; the order feature data includes the first order feature and the second order feature; wherein, the repeated first order feature and the second order feature will be eliminated during the data merging process; Then, based on the initial logistics information, the corresponding order data is obtained to obtain the order processing time corresponding to the corresponding order processing process, and a mapping relationship between the order processing time and the order feature data is constructed; Obtain a flowchart of order processing, and map each characteristic indicator in the order characteristic data to the flowchart of the corresponding order processing, and based on it, obtain the correlation relationship between different characteristic indicators; wherein the characteristic indicator is the first order characteristic or the second order characteristic; The number of occurrences of each characteristic indicator in the order data in different initial logistics information is obtained respectively, and the frequency characteristic value corresponding to the corresponding characteristic indicator is obtained based on the number of occurrences of each characteristic indicator in the order data in different initial logistics information; The frequency feature values ​​of the first order feature and the second order feature are sorted respectively, and starting from the root node, the corresponding first order feature and the second order feature are added to the tree according to the sorting of the frequency feature values, so as to obtain the corresponding first-level index branch and second-level index branch; Then, based on the correlation between the obtained characteristic indicators, the corresponding primary indicator branch and the secondary indicator branch are merged to obtain the corresponding order bifurcation tree; Then, based on the acquisition process of the order bifurcation tree, the corresponding user bifurcation tree and the delivery bifurcation tree are obtained respectively; wherein, the user data corresponds to the user bifurcation tree, and the user bifurcation tree can be used to reflect the preference and satisfaction of the corresponding user to the order processing process; it helps the express company to formulate more personalized marketing strategies and service plans; the delivery data corresponds to the delivery bifurcation tree; Then, the mapping relationships between order data, delivery data, user data and corresponding order processing time are obtained respectively, and the corresponding user bifurcation tree, delivery bifurcation tree and order bifurcation tree are merged to obtain the corresponding order decision tree diagram.

[0019] It should be further explained that, in the specific implementation process, the process of obtaining pending orders and formulating corresponding initial order processing strategies for the corresponding pending orders in combination with the order decision tree diagram includes: Based on the data collection node, the pending order information corresponding to the constructed pending order is obtained from the management platform; the pending order information includes order data and user data; Based on the pending order information, the corresponding order decision tree is traversed, and node similarity matching is performed to obtain the root node in the corresponding pending order information that is similar to the corresponding pending order data and user data; further, based on the mapping relationship between the corresponding root node and the order processing time, the order processing time of the corresponding pending order is predicted to obtain the corresponding expected order processing time; Then, the obtained pending order information and expected order processing time are input into the pre-built order decision model to obtain the corresponding initial order processing strategy; the order processing strategy refers to the resource allocation method and distribution plan involved in the manpower, vehicles, warehouse space and inventory allocation in the corresponding order processing process; It should be further explained that, in the specific implementation process, the construction process of the order decision model includes: Acquire the constructed order decision tree diagram, and construct several training data sets based on it, wherein the training data set is composed of several training subsets, and the training subsets can be used to reflect the mapping relationship between the feature data corresponding to the corresponding order data, user data and delivery data and the mapping relationship between the feature data and the delivery time; wherein the feature data includes the first user feature, the second user feature and the first delivery feature, the second delivery feature corresponding to the corresponding user data and delivery data; and also includes the first order feature and the second order feature, wherein the acquisition process of the corresponding first user feature, the second user feature and the first delivery feature, the second delivery feature is the same as the corresponding first order feature and the second order feature, and the present invention will not elaborate on it in detail; The network framework of the order decision model is defined as a convolutional neural network, which is used to learn the mapping relationship between order data, delivery data, and user data; The basic architecture of a convolutional neural network is an input layer, a hidden layer, and an output layer. The input layer is used to receive the input training subset and perform a linear transformation on it to obtain the corresponding feature matrix. The hidden layer is used to perform nonlinear transformation on the corresponding feature matrix, extract the features of the feature matrix, learn the rules and patterns in the data, and pass these features to the output layer for decision making; The output layer is used to receive the output of the hidden layer and make decisions on the input data based on the features extracted by the hidden layer and the rules and patterns in the learning data; Define the objective function of the order decision model ; In the formula, express Order processing strategy at the moment; Expressing the expected value of selection The maximum value of express Discount factor for the moment; and Respectively represent the strategy state and strategy action at time t; represents the reward function; ; The total length of time representing the expected order processing time entered; The loss function of the order decision model is defined as ; In the formula, Indicates the input The labels of the training subsets, and is an integer, Represents the total number of training subsets; Indicates The expected result of the output result corresponding to each sample; iteratively train the corresponding order decision model based on the training data set, and The optimizer continuously optimizes the model parameters of the corresponding order decision model during the iterative training process until the difference between the loss function in the order decision model and the corresponding objective function is continuously The training subsets no longer decrease or change, and the model parameters are saved, which completes the construction process of the order decision model; is a constant.

[0020] It should be further explained that, in the specific implementation process, the process of verifying the initial order processing strategy obtained and taking corresponding feedback measures based on the strategy verification results includes: Obtain the entire process of corresponding order processing and build a corresponding order simulation model based on it; the order simulation model refers to The module library is used to create a dynamic model of the workflow order processing system of the logistics distribution center, which is used to explore the relationship between the order processing process and the corresponding various strategies, so as to quickly find the best optimization solution in the corresponding order processing optimization; among them, The construction process of the module library and the order simulation model is prior art, and the present invention will not elaborate on it in detail; Input the obtained initial order processing strategy and the real-time collected order auxiliary data into the corresponding order simulation model, and record the data of the operation process of the corresponding order simulation model to obtain the corresponding simulation order information; Obtain the entire process of corresponding order processing and divide it into detailed processes; obtain several order processing sub-processes; Then, based on the simulated order information, the process data corresponding to the different order sub-processes are obtained respectively, and marked as primary parameters; the sub-data in the corresponding process data are marked as secondary parameters; Construct a fuzzy process evaluation interval, in which a number of sub-intervals are set, and the sub-intervals can be used to express the evaluation level of the corresponding process under different secondary parameters; Then, the membership degree between the corresponding secondary parameter data and the corresponding fuzzy process evaluation interval is obtained. ; In the formula, Indicates First level parameter The second-level parameters and the fuzzy process evaluation interval The degree of membership between subintervals; and They represent the first The upper and lower limits of the subintervals; Indicates First level parameter Secondary parameters; among them, and is an integer, Indicates the total number of order sub-processes; and is an integer, Indicates the total number of secondary parameters in the corresponding order subprocess; Obtain the membership between the corresponding secondary parameter data and all sub-intervals, and select the two sub-intervals with the highest membership respectively and , and the membership degree corresponding to the corresponding subinterval is recorded as and ; Then, obtain the corresponding secondary parameters and corresponding sub-intervals The correlation parameters between ; In the formula, Indicates First level parameter Secondary parameters and fuzzy process evaluation interval The correlation parameter between subintervals; among them, The higher the value, the closer the data attribute of the corresponding secondary parameter is to the subinterval The closer; Then, the correlation parameters between all the secondary indicators in the corresponding primary indicators and the corresponding fuzzy process evaluation intervals are obtained, and the corresponding secondary correlation matrix is ​​constructed based on them; Obtain the product of the weight row vector corresponding to each secondary parameter and the corresponding association matrix, obtain the association factor between the corresponding primary parameter and the corresponding fuzzy level, and construct the primary association matrix based on it; Then, the product between the weight row vector corresponding to each first-level parameter and the corresponding first-level association matrix is ​​obtained to obtain the strategy characteristic value corresponding to the corresponding initial order strategy. The strategy characteristic value is used to measure the level variable characteristic value between the initial order processing strategy and the corresponding order processing evaluation, indicating the degree to which the evaluation of the initial order processing strategy is biased towards a certain fuzzy process evaluation interval; Set a feature threshold and compare the obtained strategy feature value with the corresponding feature threshold; If the strategy feature value is not less than the feature threshold, the corresponding initial order processing strategy is used as the optimal order processing strategy, based on which the corresponding process execution instructions are generated and fed back to the staff or freight robot of the corresponding order sub-process; the process execution instructions include the order processing strategy and expected processing time interval of the corresponding order process; If the strategy characteristic value is less than the characteristic threshold, the sub-interval corresponding to each secondary parameter is obtained, and based on whether the upper limit value of the corresponding sub-interval is lower than the preset parameter threshold, if not, no other operation is performed; if it is lower, the corresponding secondary parameter is marked as a parameter to be optimized, and based on the order decision tree diagram, it is determined whether the corresponding parameter to be optimized is a characteristic indicator; if it is a characteristic indicator, the corresponding indicator data to be optimized is input into the corresponding order decision model as a constraint condition (that is, based on the indicator data to be optimized, the initial order processing strategy generation process of the corresponding order decision model is intervened); a new initial order processing strategy is obtained, and so on; if it is not a characteristic indicator, the corresponding indicator to be optimized is fed back to the management platform, and the corresponding staff manually intervenes in the corresponding original initial order processing strategy.

[0021] It should be further explained that, in the specific implementation process, the weight row vectors corresponding to the primary parameters and the secondary parameters are set in advance by the staff in this field according to the expert entropy weight algorithm; the specific setting process is not elaborated in detail in the present invention; The present invention realizes intelligent optimization of express orders through modules such as data collection, data processing, order processing and strategy verification; and by constructing an order decision tree diagram and an order decision model, it is possible to predict order processing time and formulate an initial order processing strategy. The strategy verification module ensures the effectiveness and feasibility of the initial order processing strategy, providing strong support for the express company's order processing.

[0022] Example 2

[0023] See also Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1, which provides an intelligent express order processing optimization method based on big data analysis, including: Step 1: Collect data related to express orders in the target express company to obtain corresponding logistics order information; logistics order information includes express order information and order auxiliary data; Step 2: Process the collected logistics order information to obtain the corresponding order decision tree diagram; Step 3: Obtain pending orders and formulate corresponding initial order processing strategies for the pending orders in combination with the order decision tree diagram; Step 4: Verify the initial order processing strategy obtained and take corresponding feedback measures based on the strategy verification results.

[0024] Example 3

[0025] This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the operation mode of the intelligent express order processing optimization system and method based on big data analysis provided above is implemented.

[0026] Since the electronic device introduced in this embodiment is an electronic device used to implement the intelligent express order processing optimization system and method based on big data analysis in the embodiment of the present application, based on the intelligent express order processing optimization system and method based on big data analysis introduced in the embodiment of the present application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present application is not described in detail here. As long as the technical personnel of this field implement the electronic device used by the intelligent express order processing optimization system and method based on big data analysis in the embodiment of the present application, it belongs to the scope of protection of this application.

[0027] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0028] The above are only preferred embodiments of the present invention. The protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. Intelligent express order processing optimization system based on big data analysis, characterized by: include: The data collection module is used to collect data related to express orders in the target express company and obtain corresponding logistics order information; The logistics order information includes express order information and order auxiliary data; The data processing module is used to process the collected logistics order information and obtain the corresponding order decision tree diagram; The order processing module is used to obtain pending orders and formulate corresponding initial order processing strategies for the pending orders in combination with the order decision tree diagram; The strategy verification module is used to verify the obtained initial order processing strategy and take corresponding feedback measures based on the strategy verification results.

2. According to the intelligent express order processing optimization system based on big data analysis according to claim 1, it is characterized in that: The process of collecting data related to express orders from the target express company and obtaining the corresponding logistics order information includes: The data collection module is provided with a plurality of data collection nodes, and based on the data collection nodes, data related to express orders stored in the management center of the target express company are collected to obtain a plurality of express order information, wherein the express order information includes user data, order data and delivery data; The data collection node is also used to collect data from external data sources to obtain corresponding order auxiliary data; the external data sources include the Meteorological Bureau and social media; The corresponding express order information and the corresponding order auxiliary data in the order processing process are aggregated to obtain the corresponding logistics order information.

3. The intelligent express order processing optimization system based on big data analysis according to claim 2 is characterized in that: The process of data processing of the collected logistics order information includes: Performing data preprocessing on the collected logistics order data to obtain corresponding initial logistics information; the data preprocessing includes data cleaning and data integration; Obtaining the order data in the initial logistics information, and performing data screening on the corresponding order data to obtain corresponding order index data; Classify the corresponding order indicator data based on a pre-built indicator classification function to obtain corresponding order feature data; the order feature data includes a first order feature and a second order feature; Acquire corresponding order data based on the initial logistics information to acquire the order processing time corresponding to the corresponding order processing process, and construct a mapping relationship between the order processing time and the order feature data; Obtaining a flowchart of the order processing, and mapping each characteristic indicator in the order characteristic data to the flowchart of the corresponding order processing, and based on the flowchart, obtaining a correlation relationship between different characteristic indicators; the characteristic indicator is a first order characteristic or a second order characteristic; The number of occurrences of each characteristic indicator in the order data in different initial logistics information is obtained respectively, and the frequency characteristic value corresponding to the corresponding characteristic indicator is obtained based on the number of occurrences of each characteristic indicator in the order data in different initial logistics information; The frequency feature values ​​of the first order feature and the second order feature are sorted respectively, and starting from the root node, the corresponding first order feature and the second order feature are added to the tree according to the sorting of the frequency feature values ​​to obtain corresponding primary index branches and secondary index branches; Based on the correlation between the obtained characteristic indicators, the corresponding first-level indicator branches and second-level indicator branches are merged to obtain the corresponding order bifurcation tree.

4. The intelligent express order processing optimization system based on big data analysis according to claim 3 is characterized in that: The process of classifying the corresponding order indicator data based on the pre-built indicator classification function and obtaining the corresponding order feature data includes: Define the indicator classification function as: ; In the formula, Indicates normalization processing; Indicates Initial order data The regularization coefficient corresponding to the order indicator data, ; Indicates The regression coefficient of the order indicator data; represents the regularization factor; Indicates Initial order data Order indicator data; Indicates Reference value of order indicator data; and is an integer, Indicates the total number of order data; Represents the index of order data; >0 and is an integer, Indicates the total number of order indicator data in the corresponding order data; Represents the index of order indicator data; Obtain the regularization coefficient corresponding to each order indicator data in the corresponding order data, and compare it with the pre-set regularization threshold range; If the regularization coefficient is greater than the maximum value of the regularization threshold range, the corresponding order indicator data is marked as the first order feature; if the regularization coefficient is within the regularization threshold range, the corresponding order indicator data is marked as the second order feature; if the regularization coefficient is less than the minimum value of the regularization threshold range, no other operation is performed; Aggregate the corresponding first order features and the second order features to obtain corresponding first order data; The first order data corresponding to the order data in all the initial logistics information is obtained, and the data is merged to obtain the corresponding order feature data.

5. The intelligent express order processing optimization system based on big data analysis according to claim 3 is characterized in that: The process of obtaining the order decision tree diagram includes: Based on the acquisition process of the order bifurcation tree, the corresponding user bifurcation tree and delivery bifurcation tree are obtained respectively; the mapping relationship between the order data, delivery data and user data and the corresponding order processing time is obtained respectively, and the corresponding user bifurcation tree, delivery bifurcation tree and order bifurcation tree are merged to obtain the corresponding order decision tree diagram.

6. The intelligent express order processing optimization system based on big data analysis according to claim 5 is characterized in that: The process of obtaining pending orders and formulating corresponding initial order processing strategies for the pending orders in combination with the order decision tree diagram includes: Based on the data collection node, the pending order information corresponding to the constructed pending order is obtained from the management platform; the pending order information includes order data and user data; Traversing the corresponding order decision tree diagram based on the pending order information, and performing node similarity matching to obtain a root node in the corresponding pending order information that is similar to the corresponding pending order data and user data; Based on the mapping relationship between the corresponding root node and the order processing time, the order processing time of the corresponding to-be-processed order is predicted to obtain the corresponding expected order processing time; The obtained pending order information and expected order processing time are input into a pre-built order decision model to obtain a corresponding initial order processing strategy.

7. The intelligent express order processing optimization system based on big data analysis according to claim 6 is characterized in that: The construction process of the order decision model includes: Acquire the constructed order decision tree diagram, and construct a plurality of training data sets based on the order decision tree diagram, wherein the training data sets are composed of a plurality of training subsets; The network framework of the order decision model is defined as a convolutional neural network; The basic architecture of the convolutional neural network is an input layer, a hidden layer and an output layer; the input layer is used to receive the input training subset and perform a linear transformation on it to obtain a corresponding feature matrix; The hidden layer is used to perform nonlinear transformation on the corresponding feature matrix, extract the features of the feature matrix, learn the rules and patterns in the data, and pass them to the output layer for decision making; The output layer is used to receive the output of the hidden layer and make decisions on the input data based on the features extracted by the hidden layer and the rules and patterns in the learning data; Define the objective function of the order decision model ; In the formula, express Order processing strategy at the moment; Expressing the expected value of selection The maximum value of express Discount factor for the moment; and Respectively represent the strategy state and strategy action at time t; represents the reward function; ; The total length of time representing the expected order processing time entered; The loss function of the order decision model is defined as ; In the formula, Indicates the input The labels of the training subsets, and is an integer, Represents the total number of training subsets; Indicates The expected result of the output result corresponding to the samples; iteratively train the corresponding order decision model based on the training data set, and The optimizer continuously optimizes the model parameters of the corresponding order decision model during the iterative training process until the difference between the loss function in the order decision model and the corresponding objective function is continuously The training subsets no longer decrease or change, and the model parameters are saved, which completes the construction process of the order decision model; is a constant.

8. The intelligent express order processing optimization system based on big data analysis according to claim 6 is characterized in that: The process of strategy verification for the obtained initial order processing strategy includes: Obtain the entire process of corresponding order processing and build a corresponding order simulation model based on it; Input the obtained initial order processing strategy and the real-time collected order auxiliary data into the corresponding order simulation model, and record the data of the operation process of the corresponding order simulation model to obtain the corresponding simulation order information; Obtain the entire process of corresponding order processing and divide it into detailed processes; obtain several order processing sub-processes; Based on the simulated order information, process data corresponding to different order sub-processes are respectively obtained, and marked as primary parameters; and sub-data in the corresponding process data are marked as secondary parameters; Constructing a fuzzy process evaluation interval, wherein the fuzzy process evaluation interval is provided with a plurality of sub-intervals; Obtain the membership degree of the corresponding secondary parameter data and the corresponding fuzzy process evaluation interval; Obtain the membership between the corresponding secondary parameter data and all sub-intervals, and select the two sub-intervals with the highest membership respectively and , and the membership degree corresponding to the corresponding subinterval is recorded as and ; Get the corresponding secondary parameters and corresponding sub-intervals The association parameters between Obtain the correlation parameters between all secondary indicators in the corresponding primary indicator and the corresponding fuzzy process evaluation interval, and construct the corresponding secondary correlation matrix based on them; Obtain the product of the weight row vector corresponding to each secondary parameter and the corresponding association matrix, obtain the association factor between the corresponding primary parameter and the corresponding fuzzy level, and construct the primary association matrix based on it; Obtain the product of the weight row vector corresponding to each first-level parameter and the corresponding first-level correlation matrix to obtain the strategy characteristic value corresponding to the corresponding initial order strategy; Set a feature threshold and compare the obtained strategy feature value with the corresponding feature threshold; If the strategy characteristic value is not less than the characteristic threshold, the corresponding initial order processing strategy is used as the optimal order processing strategy, and the corresponding process execution instruction is generated based on it, and the instruction feedback is performed; If the strategy characteristic value is less than the characteristic threshold, the sub-interval corresponding to each secondary parameter is obtained, and based on whether the upper limit value of the corresponding sub-interval is lower than the preset parameter threshold, if not, no other operation is performed; if it is, the corresponding secondary parameter is marked as a parameter to be optimized, and based on the order decision tree diagram, it is determined whether the corresponding parameter to be optimized is a characteristic indicator; if it is a characteristic indicator, the corresponding indicator data to be optimized is input as a constraint condition into the corresponding order decision model to obtain a new initial order processing strategy, and so on; if it is not a characteristic indicator, the corresponding indicator to be optimized is fed back to the management platform for manual intervention.

9. The intelligent express order processing optimization system based on big data analysis according to claim 8 is characterized in that: The membership degree of the secondary parameter data and the corresponding fuzzy process evaluation interval ; In the formula, Indicates First level parameter The second-level parameters and the fuzzy process evaluation interval The degree of membership between subintervals; and They represent the first The upper and lower limits of the subintervals; Indicates First level parameter Secondary parameters; among them, and is an integer, Indicates the total number of order sub-processes; and is an integer, Indicates the total number of secondary parameters in the corresponding order sub-process; Corresponding secondary parameters and corresponding subintervals The correlation parameters between ; In the formula, Indicates First level parameter Secondary parameters and fuzzy process evaluation interval Correlation parameter between subintervals.

10. An intelligent express order processing optimization method based on big data analysis, which is implemented based on the intelligent express order processing optimization system based on big data analysis according to any one of claims 1 to 9, characterized in that: include: Step 1: Collect data related to express orders in the target express company to obtain corresponding logistics order information; The logistics order information includes express order information and order auxiliary data; Step 2: Process the collected logistics order information to obtain the corresponding order decision tree diagram; Step 3: Obtain pending orders and formulate corresponding initial order processing strategies for the pending orders in combination with the order decision tree diagram; Step 4: Verify the initial order processing strategy obtained and take corresponding feedback measures based on the strategy verification results.

Images