Material distribution optimization method, system, equipment and medium

Abstract

The invention provides a material distribution optimization method, system and device and a medium, and belongs to the technical field of intelligent logistics. The method comprises the steps of collecting material distribution data and key factor data influencing a distribution plan, and performing preprocessing; according to the preprocessed data, extracting an association relationship among key factors influencing the distribution plan, constructing a multi-dimensional collaborative management model, and outputting an influence weight evaluation value of an evaluation index corresponding to the key factor data by using the model; obtaining a distribution demand and distance data of each current material distribution station, performing path planning based on the influence weight evaluation value of the evaluation index, and scheduling a vehicle to execute material distribution according to the planned path; and obtaining a material distribution result, evaluating the distribution result, and optimizing the multi-dimensional collaborative management model based on an evaluation result. According to the invention, material distribution optimization is realized by introducing a multi-dimensional flexible collaboration concept and combining real-time data, an intelligent algorithm and a multi-dimensional evaluation model.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent logistics, and more specifically relates to a method, system, device and medium for optimizing material distribution. Background Art

[0002] In today's rapidly changing logistics industry, material distribution is not only a core element of supply chain management, but also an important bridge connecting production and consumption and driving the efficient operation of the market. The level of its efficiency and the strength of its accuracy are directly reflected in the operating costs of enterprises, market competitiveness, and customer satisfaction, which is the key for enterprises to stand out in the fierce market competition.

[0003] However, with the increasing complexity of market demands and the diversification of distribution scenarios, traditional material distribution methods have gradually revealed their inherent limitations. These traditional methods often focus too much on optimizing a single dimension such as cost minimization or time minimization, simplifying the distribution process into a pure mathematical or economic problem, while ignoring many crucial factors in the distribution process.

[0004] The safety of goods, as one of the basic requirements of distribution services, is related to the reputation of enterprises and the trust of customers. However, in traditional distribution methods, due to the excessive pursuit of efficiency and cost, the safety monitoring and protection measures of goods are often not given enough attention, which undoubtedly increases the risk of goods being damaged or lost during transportation.

[0005] Customer satisfaction, as an important indicator to measure the quality of distribution services, is also not fully reflected in traditional methods. The needs of customers in aspects such as delivery time, service attitude, and information communication are simplified to "the faster the better", while ignoring the personalized needs and expectations of customers, resulting in uneven service quality and difficult to improve customer satisfaction.

[0006] In addition, environmental impact, as a hot issue generally concerned in today's society, is also not given due attention in traditional distribution methods. Excessive vehicle scheduling, unreasonable route planning, etc. not only increase operating costs, but also cause unnecessary burdens on the environment.

[0007] In summary, traditional material distribution methods are difficult to fully meet the requirements of all aspects when facing increasingly complex market demands and diverse distribution scenarios, and there is an urgent need for a new, more comprehensive and flexible distribution optimization strategy to address the challenges. Summary of the Invention

[0008] In view of the above problems, the purpose of the present invention is to provide a material distribution optimization method, system, device and medium. By introducing the concept of multi-dimensional flexible collaboration, combining real-time data, intelligent algorithms and multi-dimensional evaluation models, the optimization of material distribution is achieved, and the distribution efficiency and customer satisfaction are improved.

[0009] To achieve the above object, the present invention is realized through the following technical solutions: In a first aspect, an embodiment of the present application provides a material distribution optimization method, including: Collect material distribution data and key factor data affecting the distribution plan, and preprocess the collected data; According to the preprocessed data, extract the correlation relationship between the key factors affecting the distribution plan, construct a multi-dimensional collaborative management model, and use the multi-dimensional collaborative management model to output the impact weight evaluation value of the evaluation index corresponding to the key factor data; Obtain the distribution demand and the distance data of each current material distribution site, perform path planning based on the impact weight evaluation value of the evaluation index, and dispatch vehicles according to the planned path to execute material distribution; Obtain the material distribution result, evaluate the distribution result, and optimize the multi-dimensional collaborative management model based on the evaluation result.

[0010] In an optional embodiment, the collecting material distribution data and key factor data affecting the distribution plan, and preprocessing the collected data includes: Collect material distribution data and key factor data affecting the distribution plan. The material distribution data includes distribution subject information, distribution warehouse level, distribution route information, distribution vehicle information, distribution cost, distribution time and distribution distance. The key factor data affecting the distribution plan includes demand fluctuation information, inventory level information, and traffic condition information; For the collected data, remove the duplicate, incorrect or invalid data therein, and perform data normalization and standardization processing; Store the processed data in the database.

[0011] In an optional embodiment, the extracting the correlation relationship between the key factors affecting the distribution plan according to the preprocessed data and constructing a multi-dimensional collaborative management model includes: According to the key factor data affecting the distribution plan, draw a visualization chart, observe the data distribution of each key factor data, identify the outliers therein, and calculate the statistics of each key factor; the statistics include mean, standard deviation, minimum value, and maximum value; Calculate the Pearson correlation coefficient matrix and mutual information value between each key factor according to the key factor data affecting the distribution plan; Based on the statistics, Pearson correlation coefficient matrix, and mutual information values of the key factors described above, calculate the association strength between the key factors, and identify the factor pairs with an association strength exceeding the preset determination threshold, which are recorded as strong association factor pairs; Select a machine learning model according to the strong association factor pairs and construct a multi-dimensional collaborative management model.

[0012] In an optional implementation manner, the extracting the association relationship between the key factors affecting the distribution plan from the preprocessed data and constructing a multi-dimensional collaborative management model includes: Divide the processed data into a training set, a validation set, and a test set according to the ratio of 70%, 15%, and 15%; Use the training set data to train the selected machine learning model. By adjusting the parameters of the model, enable the model to learn the relationship between the key factors and the evaluation indicators to generate a multi-dimensional collaborative management model; Use the validation set data to evaluate the multi-dimensional collaborative management model and use the pre-audit evaluation indicators to evaluate the prediction performance of the model; Optimize the multi-dimensional collaborative management model according to the evaluation results.

[0013] In an optional implementation manner, the obtaining the distance data between the distribution requirements and the current material distribution sites, performing path planning based on the influence weight evaluation value of the evaluation indicators, and scheduling vehicles to execute material distribution according to the planned path includes: Determine the distance data of the current material distribution sites according to the material distribution data and distribution requirements, and generate a distribution site distance matrix; Generate a distance weighted matrix of the distribution sites according to the influence weight evaluation value of the evaluation indicators; Obtain the information of the trucks performing the distribution task. When the remaining space of the truck is not enough to carry the materials required for the next distribution site, construct a replenishment priority queue according to the current site, the shortage quantity, the replenishment warehouse location with sufficient goods, and the influence factor weight; Based on the distance weighted matrix and the replenishment priority queue, use the Dijkstra algorithm to calculate the optimal distribution path; Schedule vehicles to execute material distribution according to the optimal distribution path.

[0014] In an optional implementation manner, the generating a distance weighted matrix of the distribution sites according to the influence weight evaluation value of the evaluation indicators includes: Generate a one-dimensional array based on the influence weight evaluation value of the evaluation indicators; Traverse each element of the distribution site distance matrix, multiply it by the corresponding influence weight evaluation value in the one-dimensional array to obtain the weighted distance value, and generate a distance weighted matrix of the distribution sites.

[0015] In an optional embodiment, obtaining the material distribution result, evaluating the distribution result, and optimizing the multi-dimensional collaborative management model based on the evaluation result includes: Using a logistics information system, GPS positioning devices, and electronic tags, the trajectory of the distribution vehicle and the cargo status data are collected in real time, and information on distribution time, cost, and material quantity is obtained from the order and warehousing business systems through API interfaces. After format processing, it is stored in a database. In the database, SQL statements are used for aggregation operations to calculate the average distribution time and on-time delivery rate as key evaluation indicators. Regression analysis is used to calculate the quantitative relationship between the key evaluation indicators and the key factors affecting the distribution plan, and the parameters of the multi-dimensional collaborative management model are adjusted according to the quantitative relationship.

[0016] In a second aspect, an embodiment of the present application further provides a material distribution optimization system, including: A data collection and processing module, configured to collect material distribution data and key factor data affecting the distribution plan, and preprocess the collected data. A model construction module, configured to extract the correlation relationship between the key factors affecting the distribution plan according to the preprocessed data, construct a multi-dimensional collaborative management model, and use the multi-dimensional collaborative management model to output the influence weight evaluation value of the evaluation indicators corresponding to the key factor data. A path planning and scheduling module, configured to obtain the distribution requirements and the distance data of each current material distribution site, perform path planning based on the influence weight evaluation value of the evaluation indicators, and dispatch vehicles to perform material distribution according to the planned path. An evaluation and optimization module, configured to obtain the material distribution result, evaluate the distribution result, and optimize the multi-dimensional collaborative management model based on the evaluation result.

[0017] In a third aspect, an embodiment of the present application further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the material distribution optimization method described in any one of the above are implemented.

[0018] In a fourth aspect, an embodiment of the present application further provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the material distribution optimization method described in any one of the above are implemented.

[0019] From the above technical solutions, it can be seen that the present invention has the following advantages: In the material distribution optimization method provided by this application, advanced data collection and preprocessing technologies, powerful machine learning algorithms, and intelligent path planning and vehicle scheduling technologies are integrated. By accurately analyzing the key factors affecting the distribution plan, a multi-dimensional collaborative management model is constructed to achieve efficient and accurate material distribution. At the same time, the process is continuously optimized to reduce costs and improve the overall distribution efficiency.

[0020] By considering multi-dimensional requirements and constraints, this application can optimize the distribution route and plan, improve the distribution efficiency, and reduce the transportation time and cost.

[0021] By reasonably planning the distribution route and considering the requirements and limiting conditions of different dimensions, this application can minimize the transportation mileage and save fuel costs and vehicle operation costs.

[0022] By real-time monitoring and adjusting the distribution process and combining technologies such as GPS for real-time tracking, this application can improve the accuracy of distribution, reduce errors and delays.

[0023] By optimizing the distribution route and improving the distribution efficiency, this application can deliver materials to customers in a timely and accurate manner, improve customer satisfaction, and enhance customer loyalty.

[0024] The optimized distribution route of this application can reduce the vehicle driving mileage and emissions, reduce the impact on the environment, be conducive to energy conservation and emission reduction, and conform to the concept of sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the present invention, the drawings required for description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1 It is a schematic flow chart of the material distribution optimization method provided by this application.

[0027] Figure 2 It is a schematic flow chart of the material distribution path planning and scheduling method provided by this application.

[0028] Figure 3 It is a schematic structural diagram of the material distribution optimization system provided by this application.

[0029] Figure 4 It is a schematic structural diagram of the electronic device provided by this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0030] In the following detailed description of the specific steps of the material distribution optimization method, various embodiments of the present disclosure will be more fully described. The present disclosure can have various embodiments and adjustments and changes can be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but the present disclosure should be understood to cover all adjustments, equivalents, and / or alternative options that fall within the spirit and scope of the various embodiments of the present disclosure.

[0031] Hereinafter, the term "comprising" or "may comprise" that can be used in various embodiments of the present disclosure indicates the presence of the disclosed functions, operations, or elements, and does not limit the addition of one or more functions, operations, or elements. In addition, as used in various embodiments of the present disclosure, the terms "comprising", "having", and their cognates are only intended to indicate a specific feature, number, step, operation, element, component, or combination of the foregoing items, and should not be construed as first excluding the existence of one or more other features, numbers, steps, operations, elements, components, or the possibility of adding one or more features, numbers, steps, operations, elements, components, or combinations of the foregoing items.

[0032] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0033] Please refer to Figure 1 The following is a flowchart of a method for optimizing a material distribution method in a specific embodiment. The method includes: S1: Collect data on material distribution and data on key factors affecting the distribution plan, and preprocess the collected data.

[0034] Among them, the material distribution data includes distribution entity information, distribution warehouse level, distribution route information, distribution vehicle information, distribution cost, distribution time, and distribution distance. The key factor data affecting the distribution plan includes demand fluctuation information, inventory level information, and traffic condition information.

[0035] First, for the collected data, remove the duplicate, incorrect, or invalid data therein, and perform data normalization and standardization processing. Then store the processed data in a database.

[0036] Exemplarily, first, data cleaning, data normalization, and standardization are performed on the collected data. Specifically, it includes: deleting duplicate records by comparing unique identifiers or data features; identifying and correcting incorrect data using methods such as data range verification and logical verification; deleting data with excessive missing values or clearly inconsistent with business logic; scaling the data proportionally to a small specific interval (such as 0 to 1); converting the data into a distribution with a mean of 0 and a standard deviation of 1.

[0037] Then, a relational database (such as MySQL, PostgreSQL) or a NoSQL database (such as MongoDB) is used to store the preprocessed data.

[0038] S2: According to the preprocessed data, extract the correlation relationships between the key factors affecting the distribution plan, construct a multi-dimensional collaborative management model, and use the multi-dimensional collaborative management model to output the impact weight evaluation value of the evaluation index corresponding to the key factor data.

[0039] In the specific implementation manner, this step outputs the impact weight evaluation value of the evaluation index corresponding to the key factor data through the optimized multi-dimensional collaborative management model.

[0040] Regarding the construction and optimization of the multi-dimensional collaborative management model, it specifically includes the following processes: 1. According to the key factor data affecting the distribution plan, draw a visualization chart, observe the data distribution of each key factor data, identify the outliers among them, and calculate the statistics of each key factor; the statistics include mean, standard deviation, minimum value, and maximum value.

[0041] Exemplarily, use the Pandas library in Python to read the key factor data, and use the Matplotlib or Seaborn library to draw visualization charts such as histograms and box plots to observe the data distribution of each factor and determine whether there are outliers. At the same time, use the Pandas library in Python to calculate the statistics of each key factor, such as mean, standard deviation, correlation, etc.

[0042] 2. Calculate the Pearson correlation coefficient matrix and mutual information value between each key factor according to the key factor data affecting the distribution plan; based on the statistics, Pearson correlation coefficient matrix, and mutual information value of each key factor, calculate the association strength between the key factors, and identify the factor pairs with an association strength exceeding the preset determination threshold, which are recorded as strong association factor pairs.

[0043] For example, using the correlation analysis method, the Pearson correlation coefficient between key factors is calculated using the corr() method of Pandas to generate a Pearson correlation coefficient matrix to quantify the degree of linear association between factors; for non-linear relationships, the mutual_info_score function in the Scikit-learn library is used to calculate the mutual information for measurement. Based on the calculation results, factor pairs with a relatively high degree of association are selected using a threshold determination method and recorded as strongly associated factor pairs.

[0044] 3. Select a machine learning model based on the strongly associated factor pairs and construct a multi-dimensional collaborative management model.

[0045] Among them, according to the data characteristics and problem nature, a linear regression model, decision tree model, neural network model, etc. can be selected. For example, a linear regression model is suitable for situations where the linear relationship is relatively obvious; a decision tree model can handle non-linear relationships and has strong interpretability; a neural network model is suitable for complex non-linear relationships.

[0046] For the construction of the basic model, the LinearRegression class in the Scikit-learn library can be used to construct a linear regression model, the DecisionTreeRegressor class in the Scikit-learn library can be used to construct a decision tree model, and the Keras or PyTorch framework can be used to construct a neural network model.

[0047] 4. Divide the processed data into a training set, a validation set, and a test set according to the ratio of 70%, 15%, and 15%; use the training set data to train the selected machine learning model, and by adjusting the parameters of the model, enable the model to learn the relationship between the key factors and the evaluation indicators to generate a multi-dimensional collaborative management model.

[0048] Specifically, key factors such as demand fluctuation information, inventory level information, and traffic condition information are used as input features of the model. Before generating the input features, some features need to be encoded (such as one-hot encoding for categorical variables) or transformed (such as logarithmic transformation for numerical variables with skewed distributions).

[0049] Divide the preprocessed data into a training set, a validation set, and a test set. Usually, it is divided according to the ratio of 70%, 15%, and 15% to ensure the generalization ability of the model. Then use the training set data to train the selected model and adjust the parameters of the model so that the model can learn the relationship between the key factors and the evaluation indicators.

[0050] 5. Use the validation set data to evaluate the multi-dimensional collaborative management model, and utilize the pre-evaluation metrics to evaluate the prediction performance of the model; optimize the multi-dimensional collaborative management model according to the evaluation results.

[0051] For example, first use the validation set data to evaluate the trained model, and select appropriate evaluation metrics such as mean squared error (MSE), mean absolute error (MAE), etc. to measure the prediction performance of the model. Specifically, functions such as cross_val_score in the Scikit-learn library can be used for cross-validation evaluation.

[0052] Then, optimize the model according to the evaluation results. For example, if a linear regression model is used, the regularization parameter can be adjusted; for a decision tree model, parameters such as the depth of the tree and the minimum number of samples in the leaf nodes can be adjusted; for a neural network model, tools such as GridSearchCV or RandomizedSearchCV can be used to adjust hyperparameters such as the network structure and learning rate. Repeat the model training and evaluation process until the model performance reaches a satisfactory level.

[0053] S3: Obtain the distribution requirements and the distance data of each current material distribution site, perform route planning based on the impact weight evaluation value of the evaluation metrics, and dispatch vehicles to execute material distribution according to the planned route.

[0054] In the specific implementation, first determine the distance data of each current material distribution site according to the material distribution data and distribution requirements, and generate a distribution site distance matrix.

[0055] Then, generate a distance weighted matrix of the distribution sites according to the impact weight evaluation value of the evaluation metrics. Specifically, first generate a one-dimensional array based on the impact weight evaluation value of the evaluation metrics; then traverse each element of the distribution site distance matrix, multiply it by the corresponding impact weight evaluation value in the one-dimensional array to obtain the weighted distance value, and generate a distance weighted matrix of the distribution sites.

[0056] Next, obtain the information of the trucks performing the distribution tasks. When the remaining space of the truck is not enough to carry the materials required for the next distribution site, construct a replenishment priority queue according to the current site, the shortage quantity, the replenishment warehouse location with sufficient goods, and the impact factor weight.

[0057] At this time, based on the distance weighted matrix and the replenishment priority queue, use the Dijkstra algorithm to calculate the optimal distribution route.

[0058] Finally, dispatch vehicles to execute material distribution according to the optimal distribution route.

[0059] S4: Obtain the material distribution result, evaluate the distribution result, and optimize the multi-dimensional collaborative management model based on the evaluation result.

[0060] In the specific implementation, first, use the logistics information system, GPS positioning equipment, and electronic tags to collect the distribution vehicle trajectory and cargo status data in real time, and obtain the distribution time, cost, and material quantity information from the order and warehousing business systems through the API interface. Then, use ETL tools (such as Talend, Kettle) to extract and integrate data from different sources, convert it into a unified format, and store it in the database to provide a complete data basis for subsequent evaluation.

[0061] Then, use SQL statements in the database for aggregation operations to calculate the average distribution time and on-time delivery rate as key evaluation indicators. For example, calculate the on-time delivery rate through a specific SQL query. After that, use Python combined with data analysis libraries such as Pandas to compare these indicator values with the target values preset in the configuration file to clearly judge the quality of the distribution result.

[0062] Finally, use regression analysis to calculate the quantitative relationship between the key evaluation indicators and the key factors affecting the distribution plan. Determine the model adjustment direction by evaluating the quantitative relationship. After determining the adjustment direction, if it is a parameter adjustment, for the linear regression model, the GridSearchCV of Scikit-learn can be used for cross-validation to optimize the regularization parameter, and for the path planning algorithm, directly modify the heuristic function weight in the code; if it is a structural improvement, such as converting a decision tree model into a random forest through ensemble learning and modifying the tree generation logic; also, update the data source used by the model through database operation statements (such as INSERT, UPDATE). Finally, use the Scikit-learn library to calculate the evaluation indicators of the model on the reserved test data set and compare them with those before optimization to verify the optimization effect.

[0063] In this embodiment, by comprehensively using technical means such as data collection and preprocessing, machine learning modeling, path planning, and vehicle scheduling, collect and preprocess the material distribution data and its key influencing factors, construct a multi-dimensional collaborative management model to evaluate the weights of various factors, then intelligently plan the distribution path and schedule vehicles, and finally continuously optimize the model according to the feedback of the distribution result to achieve efficient, accurate, and cost-optimized material distribution.

[0064] In an embodiment of the present invention, based on step S3, a possible embodiment will be given below to non-restrictively elaborate on its specific implementation scheme.

[0065] Reference Figure 2As shown, this embodiment discloses a method for material distribution route planning and scheduling, and the specific process is as follows: a. According to the distance data of each site collected, form a distribution site distance matrix.

[0066] b. According to the index influence weight evaluation values output by the multi-dimensional evaluation index system, form a distance weighted matrix of distribution sites.

[0067] c. According to the distribution site weighted matrix, construct a distribution priority queue, and add the destination points to the queue according to the distance.

[0068] d. Initialize a truck and set the maximum load capacity.

[0069] e. Starting from the starting point (such as a warehouse), traverse the destinations on the priority queue.

[0070] f. For each destination, check whether the remaining space of the truck is sufficient to carry the quantity of materials to be distributed at this destination. If not, construct a replenishment priority queue according to the current site, the shortage quantity, the replenishment warehouse location with sufficient goods, and the influence factor weight, and drive the truck to the nearest warehouse for replenishment to ensure complete loading.

[0071] g. According to the real-time road conditions between destination cities, use the Dijkstra algorithm to calculate the optimal route to ensure that the distribution is completed in the shortest time and at the lowest cost.

[0072] h. Deliver to each destination in sequence according to the route and update the truck status information.

[0073] i. Return to the starting point or the nearest warehouse to re-plan the route for the next round of distribution until all materials are delivered.

[0074] Based on the method provided in this embodiment, the relevant algorithm pseudocode description is as follows: Init_M(P); / / Initialize the influence factor weight set P Init(); / / Initialize the replenishment warehouse matrix H Init_S(I); / / Initialize the distribution site matrix I Computer_S_Q(I,P); / / Construct the distribution priority queue Q Init_Car(S); / / Initialize vehicle information For(i:1~m){ / / Loop through the queue Q If( !Check_Car()){ / / Check whether the vehicle's load meets the cargo demand of the next distribution site / / Not satisfied Computer_S(S, P, H); / / Calculate the priority queue of the supply warehouse Supply(); / / Supply goods } Find_route(P); / / Plan the delivery route according to the influencing factors Distribution(); / / Deliver Modify_Q(); / / Modify the delivery queue Q Modify_Car(); / / Modify the cargo capacity of the vehicle if (!findNext(Q)) { / / All delivery stations have been delivered return; } } As Figure 3 shown, the following is an embodiment of the material distribution optimization system provided by the present disclosure. This system and the material distribution optimization methods of the above embodiments belong to the same inventive concept. For the details not described in detail in the embodiment of the material distribution optimization system, reference can be made to the embodiments of the above material distribution optimization methods.

[0075] A material distribution optimization system includes: a data collection and processing module, a model construction module, a path planning and scheduling module, and an evaluation and optimization module.

[0076] The data collection and processing module is used to collect material distribution data and key factor data affecting the distribution plan, and preprocess the collected data.

[0077] The model construction module is used to extract the correlation relationships between the key factors affecting the distribution plan according to the preprocessed data, construct a multi-dimensional collaborative management model, and use the multi-dimensional collaborative management model to output the influence weight evaluation values of the evaluation indicators corresponding to the key factor data.

[0078] The path planning and scheduling module is used to obtain the distribution requirements and the distance data of each current material distribution station, plan the path based on the influence weight evaluation value of the evaluation indicator, and dispatch vehicles to perform material distribution according to the planned path.

[0079] The evaluation and optimization module is used to obtain the material distribution result, evaluate the distribution result, and optimize the multi-dimensional collaborative management model based on the evaluation result.

[0080] The material distribution optimization system provided in this embodiment realizes precise analysis of distribution data, effective identification of key factors, and intelligent planning of distribution routes by integrating advanced technical means such as data collection and preprocessing, machine learning modeling, and path planning and vehicle scheduling, thus significantly improving the efficiency and accuracy of material distribution.

[0081] Figure 4 Schematic diagram of the hardware structure of an electronic device for implementing each embodiment of the present invention.

[0082] The material distribution optimization method provided in the embodiments of this application can be applied to an electronic device. Those skilled in the art can understand that the structure of the electronic device involved in the embodiments of the present invention does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements. In the embodiments of the present invention, the electronic device includes, but is not limited to, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described herein and / or claimed.

[0083] The electronic device may include a processor, an external memory interface, an internal memory, a universal serial bus (USB) interface, a charging management module, a power management module, a battery, a wireless communication module, an audio module, a speaker, a microphone, a sensor module, a key, a camera, a display screen, and a SIM card interface, etc.

[0084] The processor may include one or more processing units. For example: the processor may include a central processing unit (CPU), etc., an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0085] Among them, the processor can be the nerve center and command center of the electronic device. The controller can generate operation control signals according to the instruction operation code and timing signal to complete the control of fetching and executing instructions.

[0086] A memory can also be set in the processor for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can save the instructions or data that the processor has just used or recycled. If the processor needs to use the instruction or data again, it can directly call it from this memory. This avoids repeated accesses, reduces the waiting time of the processor, and thus improves the system efficiency.

[0087] The external memory interface can be used to connect to an external memory card, such as a MicroSD card, to implement the storage capacity expansion of the electronic device. The external memory card communicates with the processor through the external memory interface to achieve the data storage function. For example, files such as music and videos are saved in the external memory card.

[0088] The internal memory can be used to store computer-executable program codes, and the computer-executable program codes include instructions. The processor executes various functional applications and data processing of the electronic device by running the instructions stored in the internal memory. The internal memory can include a program storage area and a data storage area. The internal memory can include a high-speed random access memory and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0089] The wireless communication function of the electronic device can be implemented through an antenna, a wireless communication module, a modulation and demodulation processor, a baseband processor, etc.

[0090] The wireless communication module can provide wireless communication solutions applied to the electronic device, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite systems (GNSSs), frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc.

[0091] The electronic device can implement audio functions, etc. through an audio module, a speaker, a receiver, a microphone, a headphone interface, an application processor, etc.

[0092] An electronic device can implement a shooting function through an ISP, a camera, a video codec, a GPU, a display screen, an application processor, etc.

[0093] An electronic device can implement a display function through a GPU, a display screen, an application processor, etc.

[0094] The GPU is a microprocessor for image processing, connecting the display screen and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor may include one or more GPUs, which execute program instructions to generate or change display information.

[0095] The display screen is used to display images, videos, etc. The display screen includes a display panel.

[0096] The above-mentioned electronic device realizes the material distribution optimization method of this application. By integrating multi-dimensional data, constructing a collaborative management model, intelligent path planning and vehicle scheduling, and real-time feedback of distribution results and model optimization, it significantly improves the efficiency of material distribution, reduces costs, and achieves the beneficial effect of enhancing the flexibility and response speed of the distribution system.

[0097] In the storage medium provided by this application, there is a program product capable of realizing the material distribution optimization method.

[0098] The material distribution optimization method includes: collecting material distribution data and key factor data affecting the distribution plan, and preprocessing the collected data; according to the preprocessed data, extracting the correlation relationship between the key factors affecting the distribution plan, constructing a multi-dimensional collaborative management model, and using the multi-dimensional collaborative management model to output the influence weight evaluation value of the evaluation index corresponding to the key factor data; obtaining the distribution demand and the distance data of each current material distribution site, performing path planning based on the influence weight evaluation value of the evaluation index, and scheduling vehicles to perform material distribution according to the planned path; obtaining the material distribution result, evaluating the distribution result, and optimizing the multi-dimensional collaborative management model based on the evaluation result.

[0099] In some possible implementation manners, the material distribution optimization method of the present disclosure can be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of this specification.

[0100] The storage medium of the present disclosure may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0101] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An optimization method for material distribution, characterized in that, Including: Collecting material distribution data and key factor data affecting the distribution plan, and preprocessing the collected data; According to the preprocessed data, extracting the correlation relationships between the key factors affecting the distribution plan, constructing a multi-dimensional collaborative management model, and using the multi-dimensional collaborative management model to output the impact weight evaluation value of the evaluation index corresponding to the key factor data; Obtaining the distribution demand and the distance data of each current material distribution site, performing route planning based on the impact weight evaluation value of the evaluation index, and dispatching vehicles to execute material distribution according to the planned route; Obtaining the material distribution result, evaluating the distribution result, and optimizing the multi-dimensional collaborative management model based on the evaluation result.

2. The material distribution optimization method according to claim 1, wherein The collecting material distribution data and key factor data affecting the distribution plan, and preprocessing the collected data includes: Collecting material distribution data and key factor data affecting the distribution plan. The material distribution data includes distribution subject information, distribution warehouse level, distribution route information, distribution vehicle information, distribution cost, distribution time, and distribution distance. The key factor data affecting the distribution plan includes demand fluctuation information, inventory level information, and traffic condition information; For the collected data, removing the duplicate, incorrect or invalid data therein, and performing data normalization and standardization processing; Storing the processed data in a database.

3. The material distribution optimization method according to claim 2, wherein The extracting the correlation relationships between the key factors affecting the distribution plan according to the preprocessed data and constructing a multi-dimensional collaborative management model includes: According to the key factor data affecting the distribution plan, drawing a visualization chart, observing the data distribution of each key factor data, identifying the outliers therein, and calculating the statistics of each key factor; The statistics include mean, standard deviation, minimum value, and maximum value; Calculating the Pearson correlation coefficient matrix and the mutual information value between each key factor according to the key factor data affecting the distribution plan; Based on the statistics, Pearson correlation coefficient matrix, and mutual information value of each key factor, calculating the correlation strength between the key factors, and identifying the factor pairs with the correlation strength exceeding the preset determination threshold, which are recorded as strong correlation factor pairs; Selecting a machine learning model according to the strong correlation factor pairs and constructing a multi-dimensional collaborative management model.

4. The material distribution optimization method according to claim 3, wherein The extracting the correlation relationships between the key factors affecting the distribution plan according to the preprocessed data and constructing a multi-dimensional collaborative management model includes: Dividing the processed data into a training set, a validation set, and a test set according to the ratio of 70%, 15%, and 15%; Using the training set data to train the selected machine learning model, and by adjusting the parameters of the model, enabling the model to learn the relationship between the key factors and the evaluation index to generate a multi-dimensional collaborative management model; Using the validation set data to evaluate the multi-dimensional collaborative management model, and using the pre-audit evaluation index to evaluate the prediction performance of the model; Optimizing the multi-dimensional collaborative management model according to the evaluation result.

5. The material distribution optimization method according to claim 4, characterized in that Obtaining the distance data between the distribution requirements and each current material distribution site, performing path planning based on the impact weight evaluation value of the evaluation index, and scheduling vehicles to execute material distribution according to the planned path, including: Determining the distance data of each current material distribution site according to the material distribution data and distribution requirements, and generating a distribution site distance matrix; Generating a distance weighted matrix of distribution sites according to the impact weight evaluation value of the evaluation index; Obtaining the information of the trucks performing the distribution task. When the remaining space of the truck is not enough to carry the materials required by the next distribution site, constructing a replenishment priority queue according to the current site, the shortage quantity, the replenishment warehouse location with sufficient goods, and the impact factor weight; Based on the distance weighted matrix and the replenishment priority queue, using the Dijkstra algorithm to calculate the optimal distribution path; Scheduling vehicles to execute material distribution according to the optimal distribution path.

6. The material distribution optimization method according to claim 5, characterized in that The generating a distance weighted matrix of distribution sites according to the impact weight evaluation value of the evaluation index includes: Generating a one-dimensional array based on the impact weight evaluation value of the evaluation index; Traversing each element of the distribution site distance matrix, multiplying it by the corresponding impact weight evaluation value in the one-dimensional array to obtain the weighted distance value, and generating a distance weighted matrix of distribution sites.

7. The material distribution optimization method according to claim 6, characterized in that Obtaining the material distribution result, evaluating the distribution result, and optimizing the multi-dimensional collaborative management model based on the evaluation result, including: Using the logistics information system, GPS positioning equipment and electronic tags to collect the distribution vehicle trajectory and cargo status data in real time, and obtaining the distribution time, cost and material quantity information from the order and warehouse business systems through the API interface, and storing it in the database after format processing; Performing aggregation operations in the database using SQL statements to calculate the average distribution time and on-time delivery rate as key evaluation indicators; Using regression analysis to calculate the quantitative relationship between the key evaluation indicators and the key factors affecting the distribution plan, and adjusting the parameters of the multi-dimensional collaborative management model according to the quantitative relationship.

8. An optimized material distribution system, characterized in that, The system adopts the material distribution optimization method described in any one of claims 1 to 7; The system includes: A data collection and processing module for collecting material distribution data and key factor data affecting the distribution plan, and preprocessing the collected data; A model construction module for extracting the correlation relationship between the key factors affecting the distribution plan according to the preprocessed data, constructing a multi-dimensional collaborative management model, and using the multi-dimensional collaborative management model to output the impact weight evaluation value of the evaluation index corresponding to the key factor data; A path planning and scheduling module for obtaining the distance data between the distribution requirements and each current material distribution site, performing path planning based on the impact weight evaluation value of the evaluation index, and scheduling vehicles to execute material distribution according to the planned path; An evaluation and optimization module for obtaining the material distribution result, evaluating the distribution result, and optimizing the multi-dimensional collaborative management model based on the evaluation result.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the material distribution optimization method described in any one of claims 1 to 7.

10. A storage medium, on which a computer program is stored, characterized in that, When the computer program is executed by a processor, it implements the steps of the material distribution optimization method according to any one of claims 1 to 7.

Images