Method, device and equipment for monitoring and analyzing transportation defects of distribution center
Through the combination of Bi-LSTM and WOA whale optimization algorithm, a defect prediction model for distribution center was established, which solved the problem that the logistics information monitoring system could not promptly feedback on the operation and management status, and realized the monitoring and rectification strategy of the transportation timeliness of distribution centers. Formulated to improve operational management efficiency.
Patent Information
- Application Number
- CN202411011958.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-26
- Publication Date
- 2024-12-03
AI Technical Summary
The existing logistics information monitoring system cannot promptly feedback the real-time situation of the distribution center operation and management, and cannot effectively monitor and analyze the transportation timeliness of the distribution center, resulting in low operation and management efficiency.
Bi-LSTM bidirectional long and short-term memory network combined with the improved WOA whale optimization algorithm is used to establish a distribution center defect prediction model. By acquiring and processing historical financial data, the defect status is predicted and rectification strategies are generated, and a database is used for classification acquisition and display.
Accurate prediction and rectification strategy formulation of defects in the distribution center have been achieved, the efficiency of transportation defect analysis has been improved, distribution policies have been adjusted in a timely manner, and operation and management efficiency has been improved.
Smart Images

Figure CN119067539A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of logistics monitoring technology, and in particular to a method, device and equipment for monitoring and analyzing transportation defects in a distribution center. Background Art
[0002] With the continuous development and popularization of Internet technology, the rise of global e-commerce has given birth to many e-commerce giants, such as Alibaba and JD.com in China. Nowadays, most people have changed the traditional way of commodity trading and adopted a new consumption concept of online shopping, which has made online shopping more and more popular; and the transportation of commodity packages and their final delivery to buyers are undertaken by major logistics companies.
[0003] Logistics information monitoring is very important for logistics management. The existing logistics information monitoring can only track and locate logistics, which is convenient for customers and logistics managers to obtain the location of logistics transportation in real time and predict the time to complete logistics transportation.
[0004] With the increasing popularity of online shopping, the timeliness of logistics is becoming more and more important. The operation and management of distribution centers is also related to the timeliness of logistics. Although the existing distribution centers have frequency clearance and upload logistics financial data, they do not monitor the logistics data of each frequency when monitoring the transportation timeliness of the distribution center, and cannot timely feedback the real-time status of the operation and management of the distribution center. The operation and management of the distribution center is to obtain the transportation to the distribution center and then sort and transport it in the distribution center. Therefore, how to analyze the financial settlement data of the distribution center to obtain the status of the operation and management of the distribution center, and rectify the defects of the operation and management of the distribution center to improve the efficiency of the operation and management of the distribution center is a technical problem that needs to be solved at this stage. Summary of the invention
[0005] The present invention provides a method, device and equipment for monitoring and analyzing transportation defects in a distribution center, which can accurately predict the defects of the distribution center, thereby formulating more effective rectification strategies, timely adjusting distribution policy defects, and helping to improve the efficiency of distribution transportation defect analysis.
[0006] In one aspect, the present invention provides a method for monitoring and analyzing transportation defects in a distribution center, the method comprising:
[0007] Acquire historical distribution center financial data in the logistics system, perform data processing on the historical distribution center financial data, and obtain training historical distribution center financial data;
[0008] A Bi-LSTM distribution center defect prediction model is established through a Bi-LSTM bidirectional long short-term memory network. The hyperparameters in the Bi-LSTM distribution center defect prediction model are optimized using the improved WOA whale optimization algorithm to obtain the target Bi-LSTM distribution center defect prediction model.
[0009] Input the training distribution center financial data into the target Bi-LSTM distribution center defect prediction model for training to obtain the distribution center defect status;
[0010] A defect rectification strategy for the distribution center is generated according to the defect status of the distribution center, and the defect rectification strategy is displayed to the corresponding mobile terminal. The rectification strategy is obtained by classification according to historical data in a database.
[0011] Optionally, the acquiring of historical distribution center financial data in the logistics system, and data processing of the historical distribution center financial data to obtain the training historical distribution center financial data include:
[0012] The barcode scanning equipment in the sorting center is used to scan the barcode on each express package and associate the package with the delivery information.
[0013] Based on the dispatch voucher and settlement data, analyze the cost of each distribution according to the settlement rules and obtain the data in the logistics system;
[0014] The transportation cost of each route is allocated to each ticket according to the chargeable weight of the ticket, and the data of each ticket is summarized according to the outlets, distribution, provinces, regions, and regions to obtain the historical financial data of the distribution center;
[0015] After data cleaning and noise reduction processing are performed on the historical distribution center financial data, normalization processing is performed to obtain the training historical distribution center financial data.
[0016] Optionally, the obtaining of historical distribution center financial data in the logistics system further includes:
[0017] Information transmission and tracking are carried out through the logistics information system of the sorting center to record and manage the status, location and delivery information data of each express parcel; the delivery information data includes the ticket, ticket weight, average ticket weight, weight-to-foam ratio reference value, front-end income, internal settlement expenditure, shuttle bus fee expenditure, income and expenditure difference, income slip and cost slip.
[0018] Optionally, the Bi-LSTM bidirectional long short-term memory network is used to establish a Bi-LSTM distribution center defect prediction model, and the improved WOA whale optimization algorithm is used to optimize the hyperparameters in the Bi-LSTM distribution center defect prediction model to obtain a target Bi-LSTM distribution center defect prediction model, including:
[0019] A Bi-LSTM distribution center defect prediction model is established through a Bi-LSTM bidirectional long short-term memory network, wherein the model at least includes an input layer, a fully connected layer, and an output layer;
[0020] Use Circle mapping to generate the initial population of the WOA whale optimization algorithm, calculate the fitness value of the individuals in the population, and record the optimal position;
[0021] Update the inertia weight parameter, convergence factor parameter, and coefficient variable parameter of the WOA whale optimization algorithm, compare the absolute value of the convergence factor, and determine the size of the randomly generated probability P value and 0.5;
[0022] If P < 0.5 and the absolute value of the convergence factor is less than 1, the current individual position is updated and prey is searched randomly;
[0023] After elite reverse learning of the current dimension solution, it forms a new feasible solution with other dimension values and evaluates it according to the fitness value of the objective function;
[0024] If the solution is better than the previous solution, the new solution of elite reverse learning is retained; otherwise, the information of the previous solution is retained;
[0025] Determine whether the algorithm has reached the maximum number of iterations. If so, stop the iterative calculation, output the optimal individual position and fitness value, and output the global optimal solution of the WOA whale optimization algorithm;
[0026] The global optimal solution is input as the optimal parameter into the Bi-LSTM distribution center defect prediction model to obtain the target Bi-LSTM distribution center defect prediction model.
[0027] Optionally, a Bi-LSTM bidirectional long short-term memory network is used to establish a Bi-LSTM distribution center defect prediction model, wherein the model includes at least an input layer, a fully connected layer, and an output layer, including:
[0028] The Bi-LSTM bidirectional long short-term memory network uses two independent LSTMs, one in front and one behind, to observe the input sequence from both the forward and reverse directions. Each LSTM unit includes a memory unit and three gates, namely an input gate, a forget gate, and an output gate. The three gates control the flow of information in the LSTM unit. Through the switching mechanism of the gates, the LSTM selectively updates and forgets past information, and decides which information will be passed to the next time step.
[0029] Optionally, a Bi-LSTM distribution center defect prediction model is established through a Bi-LSTM bidirectional long short-term memory network, and the model includes at least an input layer, a fully connected layer and an output layer, and also includes:
[0030] The Bi-LSTM bidirectional long short-term memory network includes two LSTMs, forward and backward. Each LSTM unit includes a memory unit and a gating unit. The bidirectional LSTM processes the input sequence from front to back and from back to front respectively to obtain two hidden state sequences, and concatenates the two hidden state sequences to form a new representation. The new representation includes information in both the forward and backward directions. The context information in the input sequence is captured through the new representation. The Bi-LSTM simultaneously obtains information before and after the current time step, and predicts and understands patterns and relationships in the sequence through context information.
[0031] Optionally, generating a defect rectification strategy for the distribution center according to the defect status of the distribution center, displaying the defect rectification strategy to a corresponding mobile terminal, and obtaining the rectification strategy by classification according to historical data in a database, includes:
[0032] Collect all the distribution center defect data in the database, cluster the distribution center defect data using the K-means clustering algorithm, and obtain a distribution center defect rectification database;
[0033] A defect rectification strategy for the distribution center is generated according to the defect status of the distribution center, and the defect rectification strategy at least includes personnel optimization of the distribution center and sorting line optimization of the distribution center.
[0034] On the other hand, a distribution center transport defect monitoring and analysis device is provided, the device comprising:
[0035] A data processing module is used to obtain historical distribution center financial data in the logistics system, perform data processing on the historical distribution center financial data, and obtain training historical distribution center financial data;
[0036] The model optimization module is used to establish a Bi-LSTM distribution center defect prediction model through a Bi-LSTM bidirectional long short-term memory network, and optimize the hyperparameters in the Bi-LSTM distribution center defect prediction model using the improved WOA whale optimization algorithm to obtain the target Bi-LSTM distribution center defect prediction model;
[0037] A model training module, used to input the training distribution center financial data into the target Bi-LSTM distribution center defect prediction model for training to obtain the distribution center defect status;
[0038] The defect rectification module is used to generate a defect rectification strategy for the distribution center according to the defect status of the distribution center, and display the defect rectification strategy to the corresponding mobile terminal. The rectification strategy is obtained by classification according to historical data in the database.
[0039] Optionally, the data processing module includes:
[0040] The scanning unit is used to scan the barcode on each express package through the barcode scanning device provided in the sorting center, and associate the package with the collection and delivery information;
[0041] The data acquisition unit is used to analyze the cost of each distribution according to the settlement rules based on the dispatch voucher and settlement data, and acquire the data in the logistics system;
[0042] The historical data acquisition unit is used to allocate the transportation costs of each route to a single ticket according to the chargeable weight of the ticket, and summarize the data of the single ticket according to the outlets, distribution, provinces, regions, and regions to obtain the historical distribution center financial data;
[0043] The training data acquisition unit is used to perform data cleaning and noise reduction processing on the historical distribution center financial data, and then perform normalization processing to obtain the training historical distribution center financial data.
[0044] Optionally, the data processing module is also used to transmit and track information through the logistics information system of the sorting center, record and manage the status, location and delivery information data of each express parcel; the delivery information data includes tickets, ticket weight, average ticket weight, weight-to-bubble ratio reference value, front-end income, internal settlement expenditure, shuttle bus fee expenditure, income and expenditure difference, income slip and cost slip.
[0045] Optionally, the model optimization module includes:
[0046] A model building unit, used to build a Bi-LSTM distribution center defect prediction model through a Bi-LSTM bidirectional long short-term memory network, wherein the model at least includes an input layer, a fully connected layer, and an output layer;
[0047] The fitness calculation unit is used to generate the initialization population of the WOA whale optimization algorithm using Circle mapping, calculate the fitness values of individuals in the population, and record the optimal position;
[0048] The parameter updating unit is used to update the inertia weight parameter, convergence factor parameter, and coefficient variable parameter of the WOA whale optimization algorithm, compare the absolute value of the convergence factor, and determine the size of the randomly generated probability P value and 0.5;
[0049] A position updating unit, used to update the current individual position and randomly search for prey if P < 0.5 and the absolute value of the convergence factor is less than 1;
[0050] The evaluation unit is used to perform elite reverse learning on the current dimension solution and form a new feasible solution with other dimension values, and evaluate it according to the fitness value of the objective function;
[0051] A solution information determination unit, used to retain the new solution of elite reverse learning if the solution is better than the previous solution; otherwise, retain the information of the previous solution;
[0052] The judgment unit is used to judge whether the algorithm has reached the maximum number of iterations. If so, the iterative calculation is stopped, and the optimal individual position and fitness value are output, and the global optimal solution of the WOA whale optimization algorithm is output;
[0053] The target model determination unit is used to input the global optimal solution as the optimal parameter into the Bi-LSTM distribution center defect prediction model to obtain the target Bi-LSTM distribution center defect prediction model.
[0054] Optionally, the Bi-LSTM bidirectional long short-term memory network uses two independent LSTMs, one in front and one behind, to observe the input sequence from both forward and reverse directions. Each LSTM unit includes a memory unit and three gates, namely an input gate, a forget gate, and an output gate. The three gates control the flow of information in the LSTM unit. Through the switching mechanism of the gates, the LSTM selectively updates and forgets past information, and decides which information will be passed to the next time step.
[0055] Optionally, the Bi-LSTM bidirectional long short-term memory network includes two LSTMs, forward and backward, each LSTM unit includes a memory unit and a gating unit, and the bidirectional LSTM processes the input sequence from front to back and from back to front, respectively, to obtain two hidden state sequences, and concatenates the two hidden state sequences to form a new representation, wherein the new representation includes information in both the forward and backward directions, and the contextual information in the input sequence is captured through the new representation. The Bi-LSTM simultaneously obtains information before and after the current time step, and predicts and understands patterns and relationships in the sequence through the contextual information.
[0056] Optionally, the defect rectification module includes:
[0057] A data collection unit, used to collect all the distribution center defect data in the database, cluster the distribution center defect data using a K-means clustering algorithm, and obtain a defect rectification database of the distribution center;
[0058] A strategy generating unit is used to generate a defect rectification strategy for the distribution center according to the defect status of the distribution center, wherein the defect rectification strategy at least includes personnel optimization and sorting line optimization of the distribution center.
[0059] On the other hand, an electronic device is provided, 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 the at least one program is loaded and executed by the processor to implement the distribution center transportation defect monitoring and analysis method as described above.
[0060] 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 distribution center transportation defect monitoring and analysis method as described above.
[0061] 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. A processor of a 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 distribution center transportation defect monitoring and analysis method as described above.
[0062] The distribution center transportation defect monitoring and analysis method, device and equipment provided by the present invention have the following technical effects:
[0063] The present invention obtains the historical distribution center financial data in the system, processes the historical distribution center financial data, and obtains the historical distribution center financial data that can be used for training; establishes a Bi-LSTM distribution center defect prediction model through a Bi-LSTM bidirectional long short-term memory network, and optimizes the Bi-LSTM distribution center defect prediction model using an improved whale optimization algorithm; inputs the historical distribution center financial data used for training into the optimized Bi-LSTM distribution center defect prediction model for training to obtain the distribution center defect status; a distribution center defect rectification strategy can be made according to the distribution center defect status, and the distribution center rectification strategy can also be obtained by big data analysis based on previous databases. The present invention not only facilitates distribution financial operators to timely understand the transportation profit and loss situation, but also can more accurately predict the distribution center's defect situation through big data analysis, thereby formulating more effective rectification strategies, timely adjusting distribution policy defects, and helping to improve the efficiency of distribution transportation defect analysis. BRIEF DESCRIPTION OF THE DRAWINGS
[0064] 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.
[0065] Figure 1 It is a schematic diagram of a distribution center transportation defect monitoring and analysis system provided by an embodiment of this specification;
[0066] Figure 2 It is a flow chart of a method for monitoring and analyzing transportation defects in a distribution center provided in an embodiment of this specification;
[0067] Figure 3 It is a flowchart of a method for obtaining historical distribution center financial data in a logistics system, performing data processing on the historical distribution center financial data, and obtaining training historical distribution center financial data, provided by an embodiment of this specification;
[0068] Figure 4 It is a flowchart of a method for optimizing the hyperparameters in the Bi-LSTM distribution center defect prediction model by using the improved WOA whale optimization algorithm to obtain a target Bi-LSTM distribution center defect prediction model provided by an embodiment of this specification;
[0069] Figure 5 It is a flowchart of a method provided by an embodiment of this specification for generating a defect rectification strategy for a distribution center according to a defect condition of the distribution center and displaying the defect rectification strategy to a corresponding mobile terminal;
[0070] Figure 6 It is a structural schematic diagram of a distribution center transportation defect monitoring and analysis device provided in an embodiment of this specification;
[0071] Figure 7 It is a structural diagram of a server provided in an embodiment of this specification. DETAILED DESCRIPTION
[0072] 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.
[0073] 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.
[0074] See also Figure 1 , Figure 1 Schematic diagram of a distribution center transportation defect monitoring and analysis system provided by an embodiment of this specification, such as Figure 1 As shown, the distribution center transportation defect monitoring and analysis system may include at least a server 01 and a client 02 .
[0075] 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, a memory, and the like. Specifically, the server 01 can be used to train a target Bi-LSTM distribution center defect prediction model.
[0076] 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 query the defect status of the distribution center online.
[0077] The following describes a distribution center transportation defect monitoring and analysis method of the present invention. Figure 2It is a flow chart of a distribution center transportation defect monitoring and analysis method 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 sequence of steps listed in the embodiment is only one way of executing the steps among many sequences, and does not represent the only execution sequence. 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:
[0078] S201: Acquire historical distribution center financial data in the logistics system, and perform data processing on the historical distribution center financial data to obtain training historical distribution center financial data.
[0079] In the embodiments of this specification, Figure 3 As shown, the acquisition of historical distribution center financial data in the logistics system, data processing of the historical distribution center financial data, and obtaining training historical distribution center financial data include:
[0080] S20101: Scan the barcode on each express package through the barcode scanning device provided in the sorting center to associate the package with the collection and delivery information;
[0081] S20103: Based on the dispatch voucher and settlement data, analyze the cost of each distribution according to the settlement rules and obtain the data in the logistics system;
[0082] S20105: Allocate the transportation cost of each route to a single ticket according to the chargeable weight of the ticket, and summarize the data of the single ticket according to the outlets, distribution, provinces, regions, and regions to obtain the historical financial data of the distribution center;
[0083] S20107: After data cleaning and noise reduction processing are performed on the historical distribution center financial data, normalization processing is performed to obtain the training historical distribution center financial data.
[0084] In an embodiment of the present specification, obtaining historical distribution center financial data in the system, performing data processing on the historical distribution center financial data, and obtaining historical distribution center financial data that can be used for training may include: obtaining historical distribution center financial data in the system, performing data processing on the historical distribution center financial data, and obtaining historical distribution center financial data that can be used for training; based on the departure certificate and settlement data, allocating the transportation cost of each route to a single ticket according to the charged weight of the ticket, and then summarizing the data of the single ticket according to outlets, distribution, provinces, and regions; analyzing the cost of each distribution from the perspective of settlement.
[0085] Exemplarily, the query conditions are as follows:
[0086] Region query: query according to the region of the settlement system, optional; province query: query according to the business province, optional; distribution query: query according to the settlement system, optional; company name query: query according to the branch code (including the marketing company code), optional; settlement date query: the query date is limited to one year (366 days), required; when the query of region, province, distribution, and company is empty, the national data is returned; express type: all by default, and you can choose "branch express" or "marketing express" (not added in this period) by pulling down; branches belong to superiors, and service departments belong to themselves; data includes: tickets, ticket weight, average ticket weight, weight-to-foam ratio reference value, front-end income, internal settlement expenses, shuttle bus expenses, income and expenditure difference, income slip, and cost slip.
[0087] In the embodiment of this specification, the acquisition of historical distribution center financial data in the logistics system also includes:
[0088] Information transmission and tracking are carried out through the logistics information system of the sorting center to record and manage the status, location and delivery information data of each express parcel; the delivery information data includes the ticket, ticket weight, average ticket weight, weight-to-foam ratio reference value, front-end income, internal settlement expenditure, shuttle bus fee expenditure, income and expenditure difference, income slip and cost slip.
[0089] S203: A Bi-LSTM bidirectional long short-term memory network is used to establish a Bi-LSTM distribution center defect prediction model, and the improved WOA whale optimization algorithm is used to optimize the hyperparameters in the Bi-LSTM distribution center defect prediction model to obtain a target Bi-LSTM distribution center defect prediction model.
[0090] In the embodiments of this specification, Figure 4 As shown, the Bi-LSTM bidirectional long short-term memory network is used to establish a Bi-LSTM distribution center defect prediction model, and the improved WOA whale optimization algorithm is used to optimize the hyperparameters in the Bi-LSTM distribution center defect prediction model to obtain the target Bi-LSTM distribution center defect prediction model, including:
[0091] S401: Establishing a Bi-LSTM distribution center defect prediction model through a Bi-LSTM bidirectional long short-term memory network, wherein the model at least includes an input layer, a fully connected layer, and an output layer;
[0092] S403: Generate an initial population of the WOA whale optimization algorithm using Circle mapping, calculate the fitness values of individuals in the population, and record the optimal position;
[0093] S405: Update the inertia weight parameter, convergence factor parameter, and coefficient variable parameter of the WOA whale optimization algorithm, compare the absolute value of the convergence factor, and determine the value of the randomly generated probability P and 0.5;
[0094] S407: According to the comparison result, the Bi-LSTM distribution center defect prediction model is updated to obtain a target Bi-LSTM distribution center defect prediction model.
[0095] In the embodiments of this specification, a Bi-LSTM distribution center defect prediction model is established through a Bi-LSTM bidirectional long short-term memory network, and some algorithms are used to optimize the Bi-LSTM distribution center defect prediction model; the BiLSTM network uses two independent LSTMs, one in front and one behind, to "observe" the input sequence from both the forward and reverse directions. Each LSTM unit has a memory unit and three gates inside: an input gate, a forget gate, and an output gate. These gates control the flow of information in the LSTM unit. Through the switching mechanism of these gates, the LSTM can selectively update and forget past information, and decide which information will be passed to the next time step.
[0096] For example, for a unidirectional LSTM network, it can only "see" the information in the sequence from the front to the back, and cannot use the later information to correct the prediction of the current time step. Therefore, the prediction ability of the unidirectional LSTM is limited to the information before the current time step. The bidirectional LSTM processes the input sequence from front to back and from back to front respectively, and obtains two hidden state sequences. Then, these two hidden state sequences are spliced together to form a new representation. This new representation includes information from both the front and back directions, so it can better capture the contextual information in the input sequence and improve the modeling ability of the sequence.
[0097] In some embodiments, the updating of the Bi-LSTM distribution center defect prediction model according to the comparison result to obtain the target Bi-LSTM distribution center defect prediction model includes:
[0098] If P < 0.5 and the absolute value of the convergence factor is less than 1, the current individual position is updated and prey is searched randomly;
[0099] After elite reverse learning of the current dimension solution, it forms a new feasible solution with other dimension values and evaluates it according to the fitness value of the objective function;
[0100] If the solution is better than the previous solution, the new solution of elite reverse learning is retained; otherwise, the information of the previous solution is retained;
[0101] Determine whether the algorithm has reached the maximum number of iterations. If so, stop the iterative calculation, output the optimal individual position and fitness value, and output the global optimal solution of the WOA whale optimization algorithm;
[0102] The global optimal solution is input as the optimal parameter into the Bi-LSTM distribution center defect prediction model to obtain the target Bi-LSTM distribution center defect prediction model.
[0103] In the embodiment of the present specification, the historical distribution center financial data used for training is input into the optimized Bi-lstm distribution center defect prediction model for training to obtain the distribution center defect status.
[0104] Input and output: The input of BiLSTM is a sequence data, which can be text, audio or other continuous data. The output can be a fixed-length vector representation, or a sequence label or other forms required by the application.
[0105] Parameters and structure: The parameters of BiLSTM include weight matrix and bias vector, which are learned and optimized during the training process. BiLSTM consists of two LSTMs, forward and backward. Each LSTM unit is composed of memory units and gating units. These gating mechanisms ensure effective information flow.
[0106] In the embodiment of this specification, the Bi-LSTM bidirectional long short-term memory network is used to establish a Bi-LSTM distribution center defect prediction model, and the improved WOA whale optimization algorithm is used to optimize the hyperparameters in the Bi-LSTM distribution center defect prediction model to obtain a target Bi-LSTM distribution center defect prediction model, including:
[0107] A Bi-LSTM distribution center defect prediction model is established through a Bi-LSTM bidirectional long short-term memory network, wherein the model at least includes an input layer, a fully connected layer, and an output layer;
[0108] Use Circle mapping to generate the initial population of the WOA whale optimization algorithm, calculate the fitness value of the individuals in the population, and record the optimal position;
[0109] Update the inertia weight parameter, convergence factor parameter, and coefficient variable parameter of the WOA whale optimization algorithm, compare the absolute value of the convergence factor, and determine the size of the randomly generated probability P value and 0.5;
[0110] If P < 0.5 and the absolute value of the convergence factor is less than 1, the current individual position is updated and prey is searched randomly;
[0111] After elite reverse learning of the current dimension solution, it forms a new feasible solution with other dimension values and evaluates it according to the fitness value of the objective function;
[0112] If the solution is better than the previous solution, the new solution of elite reverse learning is retained; otherwise, the information of the previous solution is retained;
[0113] Determine whether the algorithm has reached the maximum number of iterations. If so, stop the iterative calculation, output the optimal individual position and fitness value, and output the global optimal solution of the WOA whale optimization algorithm;
[0114] The global optimal solution is input as the optimal parameter into the Bi-LSTM distribution center defect prediction model to obtain the target Bi-LSTM distribution center defect prediction model.
[0115] In an embodiment of the present specification, Circle mapping can be used to generate an initialization population of the WOA whale optimization algorithm, calculate the fitness value of the individuals in the population, and record the optimal position; then update the inertia weight parameter, convergence factor parameter, and coefficient variable parameter of the WOA whale optimization algorithm, compare the absolute value of the convergence factor, and determine the size of the randomly generated probability P value and 0.5; illustratively, if P < 0.5 and the absolute value of the convergence factor is less than 1, update the current individual position and randomly search for prey; perform elite reverse learning on the current dimensional solution and form a new feasible solution with other dimensional values, and evaluate it according to the fitness value of the objective function; if the solution is better than the previous solution, retain the new solution of the elite reverse learning; otherwise, retain the information of the previous solution; determine whether the algorithm has reached the maximum number of iterations, if so, stop the iterative calculation, and output the optimal individual position and fitness value, and output the global optimal solution of the WOA whale optimization algorithm; input the global optimal solution as the optimal parameter into the Bi-LSTM distribution center defect prediction model, so as to determine the target Bi-LSTM distribution center defect prediction model by the number of iterations.
[0116] In the embodiment of this specification, the Bi-LSTM bidirectional long short-term memory network is used to establish a Bi-LSTM distribution center defect prediction model, and the model includes at least an input layer, a fully connected layer and an output layer, including:
[0117] The Bi-LSTM bidirectional long short-term memory network uses two independent LSTMs, one in front and one behind, to observe the input sequence from both the forward and reverse directions. Each LSTM unit includes a memory unit and three gates, namely an input gate, a forget gate, and an output gate. The three gates control the flow of information in the LSTM unit. Through the switching mechanism of the gates, the LSTM selectively updates and forgets past information, and decides which information will be passed to the next time step.
[0118] In the embodiment of this specification, the Bi-LSTM bidirectional long short-term memory network is used to establish a Bi-LSTM distribution center defect prediction model, and the model includes at least an input layer, a fully connected layer and an output layer, and also includes:
[0119] The Bi-LSTM bidirectional long short-term memory network includes two LSTMs, forward and backward. Each LSTM unit includes a memory unit and a gating unit. The bidirectional LSTM processes the input sequence from front to back and from back to front respectively to obtain two hidden state sequences, and concatenates the two hidden state sequences to form a new representation. The new representation includes information in both the forward and backward directions. The context information in the input sequence is captured through the new representation. The Bi-LSTM simultaneously obtains information before and after the current time step, and predicts and understands patterns and relationships in the sequence through context information.
[0120] In this embodiment, the context information is that BiLSTM can simultaneously obtain information before and after the current time step, so the context information can be used to more accurately predict and understand the patterns and relationships in the sequence. This is very important for some tasks that need to consider the global context.
[0121] Training and optimization: The training process of BiLSTM usually uses the back-propagation algorithm and gradient descent method to minimize the prediction error. Common loss functions include cross entropy loss and mean square error. Through back-propagation, the network can continuously adjust the weights and biases according to the training data to optimize the performance of the model.
[0122] S205: Input the training distribution center financial data into the target Bi-LSTM distribution center defect prediction model for training to obtain the distribution center defect status.
[0123] In the embodiments of the present specification, the target Bi-LSTM distribution center defect prediction model can be used to predict the distribution center defect status corresponding to the training distribution center financial data, thereby determining whether the distribution center has defects.
[0124] S207: Generate a defect rectification strategy for the distribution center according to the defect status of the distribution center, and display the defect rectification strategy to the corresponding mobile terminal. The rectification strategy is obtained by classification according to historical data in the database.
[0125] In the embodiments of this specification, Figure 5 As shown, the defect rectification strategy of the distribution center is generated according to the defect status of the distribution center, and the defect rectification strategy is displayed to the corresponding mobile terminal. The rectification strategy is obtained by classification according to the historical data in the database, including:
[0126] S501: Collect all the distribution center defect data in the database, cluster the distribution center defect data using the K-means clustering algorithm, and obtain a defect rectification database of the distribution center;
[0127] S503: generating a defect rectification strategy for the distribution center according to the defect status of the distribution center, wherein the defect rectification strategy at least includes personnel optimization of the distribution center and sorting line optimization of the distribution center.
[0128] In the embodiment of this specification, all the distribution center defect data in the database are collected, and the distribution center defect data are clustered using the K-means clustering algorithm, and the data corresponding to the same defect are clustered into one category, so that corresponding strategies are formulated according to the category.
[0129] It can be seen from the technical solutions provided by the above embodiments of this specification that the embodiments of this specification obtain the historical financial data of the distribution center in the system, perform data processing on the historical financial data of the distribution center, and obtain the historical financial data of the distribution center that can be used for training; establish a Bi-LSTM distribution center defect prediction model through a Bi-LSTM bidirectional long short-term memory network, and optimize the Bi-LSTM distribution center defect prediction model using an improved whale optimization algorithm; input the historical distribution center financial data used for training into the optimized Bi-LSTM distribution center defect prediction model for training to obtain the distribution center defect status; a distribution center defect rectification strategy can be made according to the distribution center defect status, and the distribution center rectification strategy can also be obtained by big data analysis based on previous databases. The present invention not only facilitates distribution financial operators to timely understand the transportation profit and loss situation, but also can more accurately predict the defect situation of the distribution center through big data analysis, thereby formulating more effective rectification strategies, timely adjusting distribution policy defects, and helping to improve the efficiency of distribution transportation defect analysis.
[0130] The embodiment of this specification also provides a distribution center transportation defect monitoring and analysis device, such as Figure 6 As shown, the device comprises:
[0131] The data processing module 610 is used to obtain the historical distribution center financial data in the logistics system, and perform data processing on the historical distribution center financial data to obtain the training historical distribution center financial data;
[0132] The model optimization module 620 is used to establish a Bi-LSTM distribution center defect prediction model through a Bi-LSTM bidirectional long short-term memory network, and optimize the hyperparameters in the Bi-LSTM distribution center defect prediction model using an improved WOA whale optimization algorithm to obtain a target Bi-LSTM distribution center defect prediction model;
[0133] Model training module 630, used for inputting the training distribution center financial data into the target Bi-LSTM distribution center defect prediction model for training to obtain the distribution center defect status;
[0134] The defect rectification module 640 is used to generate a defect rectification strategy for the distribution center according to the defect status of the distribution center, and display the defect rectification strategy to the corresponding mobile terminal. The rectification strategy is obtained by classification according to historical data in the database.
[0135] Optionally, the data processing module includes:
[0136] The scanning unit is used to scan the barcode on each express package through the barcode scanning device provided in the sorting center, and associate the package with the collection and delivery information;
[0137] The data acquisition unit is used to analyze the cost of each distribution according to the settlement rules based on the dispatch voucher and settlement data, and acquire the data in the logistics system;
[0138] The historical data acquisition unit is used to allocate the transportation costs of each route to a single ticket according to the chargeable weight of the ticket, and summarize the data of the single ticket according to the outlets, distribution, provinces, regions, and regions to obtain the historical distribution center financial data;
[0139] The training data acquisition unit is used to perform data cleaning and noise reduction processing on the historical distribution center financial data, and then perform normalization processing to obtain the training historical distribution center financial data.
[0140] Optionally, the data processing module is also used to transmit and track information through the logistics information system of the sorting center, record and manage the status, location and delivery information data of each express parcel; the delivery information data includes tickets, ticket weight, average ticket weight, weight-to-bubble ratio reference value, front-end income, internal settlement expenditure, shuttle bus fee expenditure, income and expenditure difference, income slip and cost slip.
[0141] Optionally, the model optimization module includes:
[0142] A model building unit, used to build a Bi-LSTM distribution center defect prediction model through a Bi-LSTM bidirectional long short-term memory network, wherein the model at least includes an input layer, a fully connected layer, and an output layer;
[0143] The fitness calculation unit is used to generate the initialization population of the WOA whale optimization algorithm using Circle mapping, calculate the fitness values of individuals in the population, and record the optimal position;
[0144] The parameter updating unit is used to update the inertia weight parameter, convergence factor parameter, and coefficient variable parameter of the WOA whale optimization algorithm, compare the absolute value of the convergence factor, and determine the size of the randomly generated probability P value and 0.5;
[0145] A position updating unit, used to update the current individual position and randomly search for prey if P < 0.5 and the absolute value of the convergence factor is less than 1;
[0146] The evaluation unit is used to perform elite reverse learning on the current dimension solution and form a new feasible solution with other dimension values, and evaluate it according to the fitness value of the objective function;
[0147] A solution information determination unit, used to retain the new solution of elite reverse learning if the solution is better than the previous solution; otherwise, retain the information of the previous solution;
[0148] The judgment unit is used to judge whether the algorithm has reached the maximum number of iterations. If so, the iterative calculation is stopped, and the optimal individual position and fitness value are output, and the global optimal solution of the WOA whale optimization algorithm is output;
[0149] The target model determination unit is used to input the global optimal solution as the optimal parameter into the Bi-LSTM distribution center defect prediction model to obtain the target Bi-LSTM distribution center defect prediction model.
[0150] Optionally, the Bi-LSTM bidirectional long short-term memory network uses two independent LSTMs, one in front and one behind, to observe the input sequence from both forward and reverse directions. Each LSTM unit includes a memory unit and three gates, namely an input gate, a forget gate, and an output gate. The three gates control the flow of information in the LSTM unit. Through the switching mechanism of the gates, the LSTM selectively updates and forgets past information, and decides which information will be passed to the next time step.
[0151] Optionally, the Bi-LSTM bidirectional long short-term memory network includes two LSTMs, forward and backward, each LSTM unit includes a memory unit and a gating unit, and the bidirectional LSTM processes the input sequence from front to back and from back to front, respectively, to obtain two hidden state sequences, and concatenates the two hidden state sequences to form a new representation, wherein the new representation includes information in both the forward and backward directions, and the contextual information in the input sequence is captured through the new representation. The Bi-LSTM simultaneously obtains information before and after the current time step, and predicts and understands patterns and relationships in the sequence through the contextual information.
[0152] Optionally, the defect rectification module includes:
[0153] A data collection unit, used to collect all the distribution center defect data in the database, cluster the distribution center defect data using a K-means clustering algorithm, and obtain a defect rectification database of the distribution center;
[0154] A strategy generating unit is used to generate a defect rectification strategy for the distribution center according to the defect status of the distribution center, wherein the defect rectification strategy at least includes personnel optimization and sorting line optimization of the distribution center.
[0155] The device and method embodiments in the described device embodiments are based on the same inventive concept.
[0156] 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 the distribution center transportation defect monitoring and analysis method provided in the above method embodiment.
[0157] 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 distribution center transportation defect monitoring and analysis method in a method embodiment. The at least one instruction or at least one program is loaded and executed by the processor to implement the distribution center transportation defect monitoring and analysis method provided in the above method embodiment.
[0158] 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 distribution center transportation defect monitoring and analysis method provided by the above method embodiment.
[0159] 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.
[0160] 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.
[0161] The distribution center transportation defect monitoring and analysis method embodiment 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 1 is a hardware structure block diagram of a server of a distribution center transportation defect monitoring and analysis method provided in 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.
[0162] 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.
[0163] 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.
[0164] It can be seen from the embodiments of the distribution center transportation defect monitoring and analysis method, device, electronic device or storage medium provided by the present invention that the present invention obtains the historical distribution center financial data in the system, processes the historical distribution center financial data, and obtains the historical distribution center financial data that can be used for training; establishes a Bi-LSTM distribution center defect prediction model through a Bi-LSTM bidirectional long short-term memory network, and optimizes the Bi-LSTM distribution center defect prediction model using an improved whale optimization algorithm; inputs the historical distribution center financial data used for training into the optimized Bi-LSTM distribution center defect prediction model for training to obtain the distribution center defect status; a distribution center defect rectification strategy can be made according to the distribution center defect status, and the distribution center rectification strategy can also be obtained by big data analysis based on previous databases. The present invention not only facilitates distribution financial operators to understand the transportation profit and loss situation in a timely manner, but also can more accurately predict the defect situation of the distribution center through big data analysis, thereby formulating more effective rectification strategies, timely adjusting distribution policy defects, and helping to improve the efficiency of distribution transportation defect analysis.
[0165] 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.
[0166] 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.
[0167] 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.
[0168] 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 monitoring and analyzing transportation defects in a distribution center, characterized in that: The distribution center transportation defect monitoring and analysis method comprises the following steps: Acquire historical distribution center financial data in the logistics system, perform data processing on the historical distribution center financial data, and obtain training historical distribution center financial data; A Bi-LSTM distribution center defect prediction model is established through a Bi-LSTM bidirectional long short-term memory network. The hyperparameters in the Bi-LSTM distribution center defect prediction model are optimized using the improved WOA whale optimization algorithm to obtain the target Bi-LSTM distribution center defect prediction model. Input the training distribution center financial data into the target Bi-LSTM distribution center defect prediction model for training to obtain the distribution center defect status; A defect rectification strategy for the distribution center is generated according to the defect status of the distribution center, and the defect rectification strategy is displayed to the corresponding mobile terminal. The rectification strategy is obtained by classification according to historical data in a database.
2. A distribution center transportation defect monitoring and analysis method according to claim 1, characterized in that: The acquiring of historical distribution center financial data in the logistics system, and data processing of the historical distribution center financial data to obtain training historical distribution center financial data, includes: The barcode scanning equipment in the sorting center is used to scan the barcode on each express package and associate the package with the delivery information. Based on the dispatch voucher and settlement data, analyze the cost of each distribution according to the settlement rules and obtain the data in the logistics system; The transportation cost of each route is allocated to each ticket according to the chargeable weight of the ticket, and the data of each ticket is summarized according to the outlets, distribution, provinces, regions, and regions to obtain the historical financial data of the distribution center; After data cleaning and noise reduction processing are performed on the historical distribution center financial data, normalization processing is performed to obtain the training historical distribution center financial data.
3. A distribution center transportation defect monitoring and analysis method according to claim 2, characterized in that: The obtaining of historical distribution center financial data in the logistics system also includes: Information transmission and tracking are carried out through the logistics information system of the sorting center to record and manage the status, location and delivery information data of each express parcel; the delivery information data includes the ticket, ticket weight, average ticket weight, weight-to-foam ratio reference value, front-end income, internal settlement expenditure, shuttle bus fee expenditure, income and expenditure difference, income slip and cost slip.
4. A distribution center transportation defect monitoring and analysis method according to claim 1, characterized in that: The Bi-LSTM bidirectional long short-term memory network is used to establish a Bi-LSTM distribution center defect prediction model, and the improved WOA whale optimization algorithm is used to optimize the hyperparameters in the Bi-LSTM distribution center defect prediction model to obtain the target Bi-LSTM distribution center defect prediction model, including: A Bi-LSTM distribution center defect prediction model is established through a Bi-LSTM bidirectional long short-term memory network, wherein the model at least includes an input layer, a fully connected layer, and an output layer; Use Circle mapping to generate the initial population of the WOA whale optimization algorithm, calculate the fitness value of the individuals in the population, and record the optimal position; Update the inertia weight parameter, convergence factor parameter, and coefficient variable parameter of the WOA whale optimization algorithm, compare the absolute value of the convergence factor, and determine the size of the randomly generated probability P value and 0.5; If P < 0.5 and the absolute value of the convergence factor is less than 1, the current individual position is updated and prey is searched randomly; After elite reverse learning of the current dimension solution, it forms a new feasible solution with other dimension values and evaluates it according to the fitness value of the objective function; If the solution is better than the previous solution, the new solution of elite reverse learning is retained; otherwise, the information of the previous solution is retained; Determine whether the algorithm has reached the maximum number of iterations. If so, stop the iterative calculation, output the optimal individual position and fitness value, and output the global optimal solution of the WOA whale optimization algorithm; The global optimal solution is input as the optimal parameter into the Bi-LSTM distribution center defect prediction model to obtain the target Bi-LSTM distribution center defect prediction model.
5. A distribution center transportation defect monitoring and analysis method according to claim 4, characterized in that: The Bi-LSTM bidirectional long short-term memory network is used to establish a Bi-LSTM distribution center defect prediction model, and the model includes at least an input layer, a fully connected layer and an output layer, including: The Bi-LSTM bidirectional long short-term memory network uses two independent LSTMs, one in front and one behind, to observe the input sequence from both the forward and reverse directions. Each LSTM unit includes a memory unit and three gates, namely an input gate, a forget gate, and an output gate. The three gates control the flow of information in the LSTM unit. Through the switching mechanism of the gates, the LSTM selectively updates and forgets past information, and decides which information will be passed to the next time step.
6. A distribution center transportation defect monitoring and analysis method according to claim 4, characterized in that: The Bi-LSTM bidirectional long short-term memory network is used to establish a Bi-LSTM distribution center defect prediction model, which includes at least an input layer, a fully connected layer and an output layer, and also includes: The Bi-LSTM bidirectional long short-term memory network includes two LSTMs, forward and backward. Each LSTM unit includes a memory unit and a gating unit. The bidirectional LSTM processes the input sequence from front to back and from back to front respectively to obtain two hidden state sequences, and concatenates the two hidden state sequences to form a new representation. The new representation includes information in both the forward and backward directions. The context information in the input sequence is captured through the new representation. The Bi-LSTM simultaneously obtains information before and after the current time step, and predicts and understands patterns and relationships in the sequence through context information.
7. A distribution center transportation defect monitoring and analysis method according to claim 1, characterized in that: The defect rectification strategy of the distribution center is generated according to the defect status of the distribution center, and the defect rectification strategy is displayed to the corresponding mobile terminal. The rectification strategy is obtained by classification according to the historical data in the database, including: Collect all the distribution center defect data in the database, cluster the distribution center defect data using the K-means clustering algorithm, and obtain a distribution center defect rectification database; A defect rectification strategy for the distribution center is generated according to the defect status of the distribution center, and the defect rectification strategy at least includes personnel optimization of the distribution center and sorting line optimization of the distribution center.
8. A distribution center transport defect monitoring and analysis device, characterized in that: The device comprises: A data processing module is used to obtain historical distribution center financial data in the logistics system, perform data processing on the historical distribution center financial data, and obtain training historical distribution center financial data; The model optimization module is used to establish a Bi-LSTM distribution center defect prediction model through a Bi-LSTM bidirectional long short-term memory network, and optimize the hyperparameters in the Bi-LSTM distribution center defect prediction model using the improved WOA whale optimization algorithm to obtain the target Bi-LSTM distribution center defect prediction model; A model training module, used to input the training distribution center financial data into the target Bi-LSTM distribution center defect prediction model for training to obtain the distribution center defect status; The defect rectification module is used to generate a defect rectification strategy for the distribution center according to the defect status of the distribution center, and display the defect rectification strategy to the corresponding mobile terminal. The rectification strategy is obtained by classification according to historical data in the database.
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 distribution center transportation defect monitoring and analysis method 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 distribution center transportation defect monitoring and analysis method as described in any one of claims 1-7.
