Logistics resource allocation method, apparatus and device, and storage medium

Abstract

The invention relates to the technical field of logistics, in particular to a logistics resource allocation method, device and equipment and a storage medium, and the method comprises the steps: obtaining goods storage basic data of a goods storage area, and carrying out the preprocessing of the goods storage basic data, so as to obtain training data; constructing a cargo state judgment model according to the training data and the time sequence prediction model; acquiring real-time cargo storage data of the cargo storage area, and analyzing a storage state of the real-time cargo storage data through a cargo state judgment model to obtain a storage state result; generating a resource scheduling strategy based on a preset resource allocation model and the storage state result, and generating scheduling display information according to the resource scheduling strategy; the storage state of the goods is autonomously judged by collecting the storage information of the goods, the logistics resources are allocated according to the storage state, and the resource scheduling strategy is generated based on the resource allocation model and the storage state result, so that the storage resources are allocated more reasonably, and the storage efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of logistics technology, and in particular to a logistics resource allocation method, device, equipment and storage medium. Background Art

[0002] The existing storage method of goods usually relies on manual recording and monitoring. Manual measurement of the weight, volume and appearance of goods is inefficient and difficult to achieve real-time and accurate judgment. In addition, there is a lack of scientific prediction methods for judging the storage status of goods. Often, estimates can only rely on empirical values, resulting in the inability to timely discover potential problems, such as unreasonable stacking of goods, abnormal storage environment, etc., making it difficult for managers to quickly and comprehensively understand the specific situation of goods storage, affecting the timeliness and accuracy of decision-making.

[0003] It can be seen that the existing technology still needs to be improved and enhanced. Summary of the invention

[0004] In order to overcome the deficiencies of the prior art, the purpose of the present invention is to provide a logistics resource allocation method, device, equipment and storage medium, which independently judge the storage status of goods by collecting storage information of goods, and allocate logistics resources according to the storage status.

[0005] The first aspect of the present invention provides a logistics resource allocation method, including: obtaining basic cargo storage data of a cargo storage area, and preprocessing the basic cargo storage data to obtain training data; building a cargo status judgment model based on the training data and a time series prediction model; obtaining real-time cargo storage data of the cargo storage area, and analyzing the storage status of the real-time cargo storage data through the cargo status judgment model to obtain a storage status result; generating a resource scheduling strategy based on a preset resource allocation model and the storage status result, and generating scheduling display information according to the resource scheduling strategy.

[0006] Optionally, in a first implementation method of the first aspect of the present invention, the acquiring of basic cargo storage data of a cargo storage area and preprocessing of the basic cargo storage data to obtain training data include: acquiring layout information of the cargo storage area and determining storage coordinates based on the layout information; acquiring basic cargo storage data of a corresponding area based on the storage coordinates; the basic cargo storage data including pressure signals, light signals and image transmission signals; and preprocessing the pressure signals, light signals and image transmission signals to obtain training data.

[0007] Optionally, in a second implementation of the first aspect of the present invention, the preprocessing of the pressure signal, the light signal and the image transmission signal to obtain training data includes: performing data cleaning on the pressure signal, the light signal and the image transmission signal to obtain weight information, volume information and image information; associating and integrating the weight information, volume information and image information to form a cargo feature vector of the corresponding cargo; and generating training data based on all cargo feature vectors.

[0008] Optionally, in a third implementation method of the first aspect of the present invention, constructing a cargo status judgment model based on training data and a time series prediction model includes: dividing the training data into a training set, a validation set, and a test set according to a preset time sequence; constructing a time series prediction model based on an LSTM network; and performing a rolling check on the time series prediction model according to the training set, the validation set, and the test set to obtain a cargo status judgment model.

[0009] Optionally, in a fourth implementation method of the first aspect of the present invention, the real-time cargo storage data of the cargo storage area is obtained, and the storage status of the real-time cargo storage data is analyzed through a cargo status judgment model to obtain a storage status result, including: obtaining a user query instruction, and obtaining corresponding query coordinates according to the user query instruction; determining a signal link of the cargo storage area according to the query coordinates, and obtaining real-time cargo storage data according to the signal link; inputting the real-time cargo storage data into the cargo status judgment model for status judgment to obtain a storage status result.

[0010] Optionally, in a fifth implementation of the first aspect of the present invention, the resource scheduling strategy is generated based on the preset resource allocation model and storage status results, including: forming a model framework based on a hybrid construction of the Q-learning algorithm and the policy gradient algorithm; defining the environment state and action space of the model framework to form a model definition framework; constructing a reward function according to a preset reward strategy, and configuring the reward function into the model definition framework to obtain a resource scheduling strategy.

[0011] Optionally, in a sixth implementation method of the first aspect of the present invention, generating scheduling display information according to the resource scheduling strategy includes: obtaining user individual demand information, and building a display model based on JavaScript and the user individual demand information; extracting cargo status information from the scheduling display information, and converting the cargo status information into a chart to obtain chart data; synchronizing the cargo status information and the chart data to the display model to generate scheduling display information.

[0012] The second aspect of the present invention provides a logistics resource allocation device, including: a preprocessing module, used to obtain basic cargo storage data of a cargo storage area, and preprocess the basic cargo storage data to obtain training data; a construction module, used to construct a cargo status judgment model based on the training data and a time series prediction model; an analysis module, used to obtain real-time cargo storage data of a cargo storage area, and analyze the storage status of the real-time cargo storage data through the cargo status judgment model to obtain a storage status result; a scheduling module, used to generate a resource scheduling strategy based on a preset resource allocation model and storage status results, and generate scheduling display information according to the resource scheduling strategy.

[0013] Optionally, in a first implementation method of the second aspect of the present invention, the preprocessing module includes: a layout unit, used to obtain layout information of the cargo storage area and determine the storage coordinates based on the layout information; an acquisition unit, used to obtain basic cargo storage data of the corresponding area based on the storage coordinates; a preprocessing unit, used to preprocess the pressure signal, light signal and image transmission signal to obtain training data.

[0014] Optionally, in a second implementation of the second aspect of the present invention, the preprocessing unit includes: a cleaning unit, used to perform data cleaning on the pressure signal, the light signal and the image transmission signal to obtain weight information, volume information and image information; a vector unit, used to associate and integrate the weight information, volume information and image information to form a cargo feature vector of the corresponding cargo; and a generation unit, used to generate training data based on all cargo feature vectors.

[0015] Optionally, in a third implementation of the second aspect of the present invention, the construction module includes: a division unit, used to divide the training data into a training set, a verification set and a test set according to a preset time sequence; a construction unit, used to build a time series prediction model based on the LSTM network; a verification unit, used to perform a rolling verification on the time series prediction model according to the training set, the verification set and the test set to obtain a cargo status judgment model.

[0016] Optionally, in a fourth implementation of the second aspect of the present invention, the analysis module includes: a query unit, used to obtain a user query instruction, and obtain corresponding query coordinates according to the user query instruction; a link unit, used to determine a signal link of a cargo storage area according to the query coordinates, and obtain real-time cargo storage data according to the signal link; a judgment unit, used to input the real-time cargo storage data into a cargo status judgment model for status judgment to obtain a storage status result.

[0017] Optionally, in a fifth implementation of the second aspect of the present invention, the scheduling module includes: a mixing unit, used to form a model framework based on a mixed construction of a Q-learning algorithm and a policy gradient algorithm; a definition unit, used to define the environment state and action space of the model framework to form a model definition framework; a reward unit, used to construct a reward function according to a preset reward strategy, and configure the reward function into the model definition framework to obtain a resource scheduling strategy.

[0018] Optionally, in a sixth implementation of the second aspect of the present invention, the scheduling module also includes: a personality unit, used to obtain user personality demand information, and build a display model based on JavaScript and user personality demand information; a chart unit, used to extract cargo status information from the scheduling display information, and convert the cargo status information into a chart to obtain chart data; a display unit, used to synchronize the cargo status information and chart data to the display model to generate scheduling display information.

[0019] The third aspect of the present invention provides a logistics resource allocation device, which includes: a memory and at least one processor, wherein the memory stores instructions; at least one of the processors calls the instructions in the memory to enable the logistics resource allocation device to execute each step of the logistics resource allocation method described in any one of the above items.

[0020] A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored thereon, and the instructions, when executed by a processor, implement the various steps of any of the above-mentioned logistics resource allocation methods.

[0021] In the technical solution of the present invention, by obtaining the basic data of cargo storage in the cargo storage area and performing preprocessing, the data quality used for training the model can be ensured, thereby improving the accuracy of the prediction; constructing a cargo status judgment model based on the time series prediction model can more accurately analyze the storage status of the cargo and promptly discover potential problems; by acquiring the data of the cargo storage area in real time and using the cargo status judgment model to analyze the storage status, real-time monitoring and management of the cargo storage situation can be achieved; the resource scheduling strategy generated based on the resource allocation model and the storage status results helps to more reasonably allocate warehousing resources and improve warehousing efficiency; the scheduling display information generated according to the resource scheduling strategy can provide intuitive scheduling guidance for warehousing management personnel, speed up the decision-making process, and improve the overall scheduling efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A first flow chart of the logistics resource allocation method provided by an embodiment of the present invention;

[0023] Figure 2A second flow chart of the logistics resource allocation method provided by an embodiment of the present invention;

[0024] Figure 3 A third flow chart of the logistics resource allocation method provided by an embodiment of the present invention;

[0025] Figure 4 A fourth flow chart of the logistics resource allocation method provided by an embodiment of the present invention;

[0026] Figure 5 A fifth flow chart of the logistics resource allocation method provided by an embodiment of the present invention;

[0027] Figure 6 A sixth flow chart of the logistics resource allocation method provided by an embodiment of the present invention;

[0028] Figure 7 A seventh flow chart of the logistics resource allocation method provided by an embodiment of the present invention;

[0029] Figure 8 A schematic diagram of the structure of a logistics resource allocation device provided in an embodiment of the present invention;

[0030] Fig. 9 Another structural schematic diagram of the logistics resource allocation device provided by an embodiment of the present invention;

[0031] Fig.10 A schematic diagram of the structure of a logistics resource allocation device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The present invention provides a logistics resource allocation method, device, equipment and storage medium. The present invention can ensure the data quality used for training models by obtaining basic cargo storage data of cargo storage areas and performing preprocessing, thereby improving the accuracy of predictions; constructing a cargo status judgment model based on a time series prediction model, which can more accurately analyze the storage status of cargo and timely discover potential problems; by acquiring data of cargo storage areas in real time and using the cargo status judgment model to analyze the storage status, real-time monitoring and management of cargo storage conditions can be achieved; a resource scheduling strategy generated based on a resource allocation model and storage status results helps to more reasonably allocate warehousing resources and improve warehousing efficiency; the scheduling display information generated according to the resource scheduling strategy can provide intuitive scheduling guidance for warehousing management personnel, speed up the decision-making process, and improve overall scheduling efficiency.

[0033] The terms "first", "second", "third", "fourth", etc. (if any) 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 interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of the logistics resource allocation method in the embodiment of the present invention includes:

[0035] 101. Obtain basic cargo storage data of the cargo storage area, and pre-process the basic cargo storage data to obtain training data;

[0036] 102. Construct a cargo status judgment model based on training data and time series prediction model;

[0037] In this embodiment, by obtaining the basic data of cargo storage in the cargo storage area and performing preprocessing, the data quality used to train the model can be ensured, thereby improving the accuracy of the prediction; building a cargo status judgment model based on the time series prediction model can more accurately analyze the storage status of the cargo, timely discover potential problems, and optimize the judgment of the cargo status.

[0038] 103. Acquire real-time cargo storage data of the cargo storage area, and analyze the storage status of the real-time cargo storage data through the cargo status judgment model to obtain a storage status result;

[0039] 104. Generate a resource scheduling strategy based on a preset resource allocation model and storage status results, and generate scheduling display information according to the resource scheduling strategy.

[0040] In this embodiment, the storage status of real-time cargo storage data is analyzed using a cargo status judgment model, so that real-time monitoring and management of cargo storage conditions can be achieved; and the resource scheduling strategy generated based on the resource allocation model and storage status results helps to more reasonably allocate storage resources, improve storage efficiency, and achieve dynamic adjustment of resource allocation strategies and intelligent scheduling of trucks, personnel and distribution centers.

[0041] In an embodiment of the present invention, by acquiring basic cargo storage data of a cargo storage area and performing preprocessing, the data quality used for training a model can be ensured, thereby improving the accuracy of predictions; a cargo status judgment model based on a time series prediction model is constructed, which can more accurately analyze the storage status of cargo and promptly discover potential problems; by acquiring data of a cargo storage area in real time and analyzing the storage status using a cargo status judgment model, real-time monitoring and management of cargo storage conditions can be achieved; a resource scheduling strategy generated based on a resource allocation model and storage status results can help to more reasonably allocate warehousing resources and improve warehousing efficiency; the scheduling display information generated based on the resource scheduling strategy can provide intuitive scheduling guidance for warehousing management personnel, speed up the decision-making process, and improve overall scheduling efficiency.

[0042] See also Figure 2 The second embodiment of the logistics resource allocation method in the embodiment of the present invention includes:

[0043] 201. Obtain layout information of a cargo storage area, and determine storage coordinates according to the layout information;

[0044] 202. Acquire basic cargo storage data of a corresponding area based on the storage coordinates; the basic cargo storage data includes a pressure signal, an optical signal, and an image transmission signal;

[0045] 203. Preprocess the pressure signal, the light signal and the image transmission signal to obtain training data.

[0046] In this embodiment, by acquiring the layout information of the cargo storage area and determining the storage coordinates, the cargo position can be quickly located, thereby improving the efficiency of cargo management, and based on the storage coordinates, the monitoring signal of the area can be quickly acquired (by deploying multiple high-precision sensors in the cargo storage area to collect data such as the weight, volume and appearance of the cargo in real time), that is, the pressure signal, light signal and image transmission signal are acquired, and by analyzing the pressure signal and the light signal, abnormal conditions in the cargo storage environment, such as overload or insufficient light, can be discovered in time, so that preventive maintenance measures can be taken to avoid potential losses. The use of image transmission signals can realize real-time monitoring of the cargo storage area and respond to any abnormal conditions in time to ensure the safety of the cargo; the pressure signal, light signal and image transmission signal are converted into training data, which can be used for the training of machine learning models, thereby providing more accurate decision support for inventory management, cargo scheduling, etc.

[0047] See also Figure 3 The third embodiment of the logistics resource allocation method in the embodiment of the present invention includes:

[0048] 301. Perform data cleaning on the pressure signal, the light signal and the image transmission signal to obtain weight information, volume information and image information;

[0049] 302. Associating and integrating the weight information, volume information and image information to form a cargo feature vector corresponding to the cargo;

[0050] 303. Generate training data based on all cargo feature vectors.

[0051] In this embodiment, the pressure signal, light signal and image transmission signal are cleaned to remove abnormal values ​​and noise of the pressure signal, light signal and image transmission signal, which can effectively improve the accuracy and reliability of the data, thereby obtaining more accurate weight information, volume information and image information. By associating and integrating this information, a cargo feature vector corresponding to the cargo can be formed, which helps to more comprehensively understand and describe the characteristics of the cargo. Finally, training data is generated based on all cargo feature vectors, which can be used for training machine learning models to improve the prediction accuracy and generalization ability of the model.

[0052] See also Figure 4 The fourth embodiment of the logistics resource allocation method in the embodiment of the present invention includes:

[0053] 401. Divide the training data into a training set, a validation set, and a test set according to a preset time sequence;

[0054] 402. Constructing a time series prediction model based on LSTM network;

[0055] 403. Perform rolling verification on the time series prediction model according to the training set, the validation set, and the test set to obtain a cargo status judgment model.

[0056] In this embodiment, by dividing the training data into a training set, a validation set, and a test set according to a preset time sequence, it is possible to ensure that the model is learned and validated on different data subsets, thereby evaluating the generalization ability of the model. The time series prediction model constructed based on the LSTM network can capture the long-term dependencies in the time series data and is suitable for predicting the dynamic changes in the state of goods; the model is trained using the training set, and the model parameters such as the number of neurons, learning rate, etc. are adjusted to enable the model to learn the time patterns and laws in the data. The trained model is evaluated and adjusted using the validation set, and the model with the best performance is selected. Finally, the final model is verified using the test set. The real-time collected data is input into the trained model to predict the storage status of the goods, and compared with the set normal range to determine whether the current status is normal.

[0057] See also Figure 5 The fifth embodiment of the logistics resource allocation method in the embodiment of the present invention includes:

[0058] 501. Obtain a user query instruction, and obtain corresponding query coordinates according to the user query instruction;

[0059] 502. Determine a signal link of the cargo storage area according to the query coordinates, and obtain real-time cargo storage data according to the signal link;

[0060] 503. Input the real-time cargo storage data into the cargo status judgment model for status judgment to obtain a storage status result.

[0061] In this embodiment, by automatically obtaining user query instructions and quickly locating the goods storage area, the time required for manual search for goods can be significantly reduced, thereby improving query efficiency; real-time acquisition of goods storage data ensures the timeliness of goods status information, which helps to promptly discover and deal with storage problems; through the goods status judgment model, the storage status of goods can be automatically analyzed, thereby preventing potential storage risks in advance and ensuring the safety of goods; real-time data input and status judgment results provide data support for warehouse management, which helps to make more scientific and reasonable inventory management decisions; the automated process reduces the links of manual operation, thereby reducing errors caused by human errors and improving overall accuracy and reliability.

[0062] See also Figure 6 The sixth embodiment of the logistics resource allocation method in the embodiment of the present invention includes:

[0063] 601. The model framework is formed based on the hybrid construction of Q-learning algorithm and policy gradient algorithm;

[0064] 602. Define the environment state and action space of the model framework to form a model definition framework;

[0065] 603. Construct a reward function according to a preset reward strategy, and configure the reward function into a model definition framework to obtain a resource scheduling strategy.

[0066] In this embodiment, the model framework based on the hybrid construction of the Q-learning algorithm and the policy gradient algorithm can combine the advantages of the two algorithms, and use the policy gradient algorithm to fill the shortcomings of the Q-learning algorithm in continuous actions, so as to meet the processing requirements of continuous actions and discrete actions, and improve learning efficiency and decision-making quality. By defining the environmental state and action space, the model can better understand and adapt to environmental changes, so as to make more accurate decisions. Define the environmental state, including the storage status of goods, the location and load of trucks, the working status of personnel, the busyness of the distribution center, etc.; define the action space, such as dispatching different numbers of trucks, arranging different numbers of personnel, and allocating goods to different distribution centers; set a reward function to encourage actions that reduce waiting time and operating costs. The agent constantly tries different actions in the environment and updates the strategy based on the rewards obtained. Through continuous learning and optimization, find the optimal resource allocation strategy. Monitor the changes in the environment in real time, and execute the optimal scheduling decision based on the latest prediction results and accumulation conditions; construct the preset reward strategy as a reward function and configure it into the model framework, which helps the model optimize the goals in the resource scheduling process, realize the effective allocation and utilization of resources, and improve the performance and efficiency of the overall system. The goal of the policy gradient algorithm is to find an optimal policy π(θ), where θ is the policy parameter. The algorithm updates the policy parameters by sampling in a given environment and calculating the cumulative reward. Specifically, the algorithm records the state and action sequence of each time step, calculates the cumulative reward based on this data, and then uses gradient ascent or descent to update the policy parameters.

[0067] It should be noted that the basic idea of ​​the Q-learning algorithm is to estimate a behavior value function Q(s,a), which represents the maximum expected reward that can be obtained by performing action a in state s. The algorithm uses the Bellman optimal equation to update the action value function Q(s,a), which describes the relationship between the action value function under the optimal strategy and the action value function of the next state. Specifically, the Q-learning algorithm maintains a Q-value table (Q-table), the dimensions of which are all possible states S and all possible actions A. The content of the table is called the Q value, which reflects the expected future reward for taking the current action in this state. Every time the agent chooses an action, it will query the Q-value table to find out which action will give the maximum future reward in the current state.

[0068] See also Figure 7 The seventh embodiment of the logistics resource allocation method in the embodiment of the present invention includes:

[0069] 701. Obtain user individual demand information, and build a display model based on JavaScript and the user individual demand information;

[0070] 702. Extracting cargo status information from the scheduling display information, and converting the cargo status information into a chart to obtain chart data;

[0071] 703. Synchronize the cargo status information and chart data to the display model to generate scheduling display information.

[0072] In this embodiment, by obtaining the user's individual demand information and using JavaScript to build a display model, a more personalized and dynamic user interface can be achieved. This helps to improve the user experience, because the display content can be adjusted according to the user's specific needs and preferences, thereby improving user satisfaction and interactivity. The relevant data of the goods is stored in a database or data warehouse, and the front-end technology (such as HTML, CSS, JavaScript) interacts with the back-end data to obtain the latest data in real time; the cargo status information is extracted from the scheduling display information and converted into a chart form, which can make complex data more intuitive and easy to understand. The chart data can quickly convey the current status and trend of the goods, help users make decisions quickly, and improve work efficiency; synchronize the cargo status information and chart data to the display model, generate the scheduling display information, and ensure the real-time update and accuracy of the information; this synchronization mechanism ensures that users always view the latest scheduling information, which helps to improve the accuracy and efficiency of logistics scheduling.

[0073] The above describes the logistics resource allocation method in the embodiment of the present invention. The following describes the logistics resource allocation device in the embodiment of the present invention. Figure 8 In one embodiment of the present invention, a logistics resource allocation device includes:

[0074] A preprocessing module 801 is used to obtain basic cargo storage data of a cargo storage area and preprocess the basic cargo storage data to obtain training data;

[0075] A construction module 802 is used to construct a cargo status judgment model based on the training data and the time series prediction model;

[0076] The analysis module 803 is used to obtain the real-time cargo storage data of the cargo storage area, and analyze the storage status of the real-time cargo storage data through the cargo status judgment model to obtain the storage status result;

[0077] The scheduling module 804 is used to generate a resource scheduling strategy based on a preset resource allocation model and storage status results, and generate scheduling display information according to the resource scheduling strategy.

[0078] In this embodiment, the preprocessing module 801 can ensure the data quality used for training the model by obtaining the basic data of cargo storage in the cargo storage area and performing preprocessing, thereby improving the accuracy of the prediction; the construction module 802 constructs a cargo status judgment model based on the time series prediction model, which can more accurately analyze the storage status of the cargo and promptly discover potential problems; the analysis module 803 can achieve real-time monitoring and management of the cargo storage situation by obtaining data of the cargo storage area in real time and using the cargo status judgment model to analyze the storage status; the scheduling module 804 generates a resource scheduling strategy based on the resource allocation model and the storage status results, which helps to allocate warehousing resources more reasonably and improve warehousing efficiency, and the scheduling display information generated according to the resource scheduling strategy can provide intuitive scheduling guidance for warehousing managers, speed up the decision-making process, and improve overall scheduling efficiency.

[0079] See also Fig. 9 Another embodiment of the logistics resource allocation device in the embodiment of the present invention includes:

[0080] A preprocessing module 801 is used to obtain basic cargo storage data of a cargo storage area and preprocess the basic cargo storage data to obtain training data;

[0081] A construction module 802 is used to construct a cargo status judgment model based on the training data and the time series prediction model;

[0082] The analysis module 803 is used to obtain the real-time cargo storage data of the cargo storage area, and analyze the storage status of the real-time cargo storage data through the cargo status judgment model to obtain the storage status result;

[0083] The scheduling module 804 is used to generate a resource scheduling strategy based on a preset resource allocation model and storage status results, and generate scheduling display information according to the resource scheduling strategy.

[0084] In this embodiment, in the first implementation method of the second aspect of the present invention, the preprocessing module 801 includes: a layout unit 8011, which is used to obtain the layout information of the cargo storage area and determine the storage coordinates according to the layout information; an acquisition unit 8012, which is used to obtain the basic data of cargo storage in the corresponding area based on the storage coordinates; a preprocessing unit 8013, which is used to preprocess the pressure signal, the light signal and the image transmission signal to obtain training data.

[0085] In this embodiment, in a second implementation of the second aspect of the present invention, the preprocessing unit 8013 includes: a cleaning unit 80131, used to perform data cleaning on the pressure signal, the light signal and the image transmission signal to obtain weight information, volume information and image information; a vector unit 80132, used to associate and integrate the weight information, volume information and image information to form a cargo feature vector corresponding to the cargo; a generating unit 80133, used to generate training data according to all cargo feature vectors.

[0086] In this embodiment, in a third implementation of the second aspect of the present invention, the construction module 802 includes: a division unit 8021, used to divide the training data into a training set, a validation set and a test set according to a preset time sequence; a construction unit 8022, used to build a time series prediction model based on an LSTM network; a verification unit 8023, used to perform a rolling verification on the time series prediction model according to the training set, the validation set and the test set to obtain a cargo status judgment model.

[0087] In this embodiment, in a fourth implementation of the second aspect of the present invention, the analysis module 803 includes: a query unit 8031, used to obtain a user query instruction, and obtain corresponding query coordinates according to the user query instruction; a link unit 8032, used to determine a signal link of a cargo storage area according to the query coordinates, and obtain real-time cargo storage data according to the signal link; a judgment unit 8033, used to input the real-time cargo storage data into a cargo status judgment model for status judgment to obtain a storage status result.

[0088] In this embodiment, in the fifth implementation method of the second aspect of the present invention, the scheduling module 804 includes: a mixing unit 8041, which is used to form a model framework based on a mixed construction of the Q-learning algorithm and the policy gradient algorithm; a definition unit 8042, which is used to define the environment state and action space of the model framework to form a model definition framework; a reward unit 8043, which is used to construct a reward function according to a preset reward strategy, and configure the reward function into the model definition framework to obtain a resource scheduling strategy.

[0089] In this embodiment, in the sixth implementation method of the second aspect of the present invention, the scheduling module 804 also includes: a personality unit 8044, which is used to obtain user personality demand information and build a display model based on JavaScript and user personality demand information; a chart unit 8045, which is used to extract cargo status information from the scheduling display information, and convert the cargo status information into a chart to obtain chart data; a display unit 8046, which is used to synchronize the cargo status information and the chart data to the display model to generate scheduling display information.

[0090] above Figure 8and Fig. 9 The logistics resource allocation device in the embodiment of the present invention is described in detail from the perspective of modular functional entities, and the logistics resource allocation device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0091] Fig.10 : is a structural diagram of a logistics resource allocation device provided by an embodiment of the present invention. The logistics resource allocation device 900 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 910 (for example, one or more processors) and a memory 920, and one or more storage media 930 (for example, one or more mass storage devices) storing application programs 933 or data 932. Among them, the memory 920 and the storage medium 930 can be temporary storage or permanent storage. The program stored in the storage medium 930 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the logistics resource allocation device 900. Furthermore, the processor 910 can be configured to communicate with the storage medium 930, and execute a series of instruction operations in the storage medium 930 on the logistics resource allocation device 900 to implement the steps of the logistics resource allocation method provided by the above-mentioned method embodiments.

[0092] The logistics resource allocation device 900 may also include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input and output interfaces 960, and / or one or more operating systems 931, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that Fig.10 The structure of the logistics resource allocation equipment shown does not constitute a limitation on the logistics resource allocation equipment, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0093] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the logistics resource allocation method.

[0094] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, or unit can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0095] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0096] Finally, it should be noted that the above description is only a preferred example of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A logistics resource allocation method, characterized in that: include: Obtaining basic cargo storage data of the cargo storage area, and preprocessing the basic cargo storage data to obtain training data; Build a cargo status judgment model based on training data and time series prediction model; Acquire real-time cargo storage data of the cargo storage area, and analyze the storage status of the real-time cargo storage data through the cargo status judgment model to obtain the storage status result; Generate a resource scheduling strategy based on the preset resource allocation model and storage status results, and generate scheduling display information according to the resource scheduling strategy.

2. The logistics resource allocation method according to claim 1, characterized in that: The obtaining of cargo storage basic data of the cargo storage area and preprocessing of the cargo storage basic data to obtain training data includes: Obtaining the layout information of the cargo storage area and determining the storage coordinates based on the layout information; Acquire basic cargo storage data of the corresponding area based on the storage coordinates; the basic cargo storage data includes pressure signals, light signals and image transmission signals; The pressure signal, light signal and image transmission signal are preprocessed to obtain training data.

3. The method for allocating logistics resources according to claim 2, characterized in that: The preprocessing of the pressure signal, the light signal and the image transmission signal to obtain training data includes: Perform data cleaning on pressure signals, optical signals and image transmission signals to obtain weight information, volume information and image information; The weight information, volume information and image information are associated and integrated to form a cargo feature vector corresponding to the cargo; Generate training data based on all cargo feature vectors.

4. The method for allocating logistics resources according to claim 2, characterized in that: The method of constructing a cargo status judgment model based on training data and a time series prediction model includes: Divide the training data into training set, validation set and test set according to the preset time sequence; Build a time series prediction model based on LSTM network; The time series prediction model is rolled out based on the training set, validation set, and test set to obtain a cargo status judgment model.

5. The method for allocating logistics resources according to claim 1, characterized in that: The acquiring of real-time cargo storage data of the cargo storage area and analyzing the storage status of the real-time cargo storage data by the cargo status judgment model to obtain a storage status result includes: Obtaining a user query instruction, and obtaining corresponding query coordinates according to the user query instruction; Determine the signal link of the cargo storage area according to the query coordinates, and obtain real-time cargo storage data according to the signal link; The real-time cargo storage data is input into the cargo status judgment model for status judgment to obtain the storage status result.

6. The method for allocating logistics resources according to claim 1, characterized in that: The generating of resource scheduling strategy based on the preset resource allocation model and storage status result includes: The model framework is formed based on the hybrid construction of Q-learning algorithm and policy gradient algorithm; Define the environment state and action space of the model framework to form a model definition framework; Construct a reward function according to the preset reward strategy, and configure the reward function into the model definition framework to obtain the resource scheduling strategy.

7. The method for allocating logistics resources according to claim 1, characterized in that: The generating of scheduling display information according to the resource scheduling strategy includes: Obtain user individual demand information and build a display model based on JavaScript and user individual demand information; Extracting cargo status information from the scheduling display information, and converting the cargo status information into a chart to obtain chart data; Synchronize cargo status information and chart data to the display model to generate scheduling display information.

8. A logistics resource allocation device, characterized in that: include: A preprocessing module, used for acquiring basic cargo storage data of a cargo storage area, and preprocessing the basic cargo storage data to obtain training data; A construction module is used to construct a cargo status judgment model based on training data and a time series prediction model; An analysis module is used to obtain real-time cargo storage data of the cargo storage area, and analyze the storage status of the real-time cargo storage data through a cargo status judgment model to obtain a storage status result; The scheduling module is used to generate a resource scheduling strategy based on a preset resource allocation model and storage status results, and generate scheduling display information according to the resource scheduling strategy.

9. A logistics resource allocation device, characterized in that: The logistics resource allocation device comprises: a memory and at least one processor, wherein instructions are stored in the memory; At least one of the processors calls the instructions in the memory to enable the logistics resource allocation device to execute each step of the logistics resource allocation method as described in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the various steps of the logistics resource allocation method as described in any one of claims 1-7 are implemented.

Images