Methods and devices for predicting parcel locker usage, electronic equipment and storage media

Abstract

This application provides a method, apparatus, electronic device, and storage medium for predicting parcel locker usage. The application first obtains the address information of the order to be predicted by the parcel locker; then, it sends the address information to a constructed prediction model object. The prediction model object is built using an application development framework corresponding to a preset programming language, used to process the input address information and output parcel locker prediction results. The preset programming language includes JAVA. Finally, the parcel locker prediction results output by the prediction model object are used as the parcel locker prediction result for the order. Because JAVA has a well-developed infrastructure, developing and deploying online applications is relatively convenient. Therefore, this application embodiment utilizes an application development framework corresponding to JAVA to construct a prediction model object, and then uses this prediction model object to predict parcel lockers. This overcomes the instability of online applications developed in the prior art and helps improve the accuracy of parcel locker prediction.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method and apparatus for predicting the movement of parcel lockers, electronic equipment and storage medium. Background Technology

[0002] Some existing model computation services, such as the Tensorflow model computation service, run in a Python environment. They use existing Python libraries to load pre-trained Tensorflow model files, then build a web application and call it via the HTTP protocol.

[0003] However, web applications built with Python are rarely used internally within companies due to insufficient infrastructure, inconvenient development and deployment of online applications, and unstable performance. In parcel locker prediction, this instability significantly reduces the accuracy of predictions. Summary of the Invention

[0004] This application provides a method and apparatus for predicting which parcels will be delivered to a parcel locker, as well as an electronic device and a storage medium, to accurately predict the parcels to be delivered to the parcel locker.

[0005] In a first aspect, embodiments of this application provide a method for predicting parcel locker usage, including:

[0006] Obtain the address information of orders to be predicted for use in express delivery lockers;

[0007] The address information is sent to the constructed prediction model object; wherein the prediction model object is constructed using an application development framework corresponding to a preset programming language, and is used to process the input address information and output the express cabinet prediction result information; the preset programming language includes JAVA;

[0008] The parcel locker prediction result information output by the prediction model object is used as the parcel locker prediction result for the order.

[0009] In one possible implementation, the prediction model object includes an object corresponding to a Tensorflow model; the application development framework includes Spring Boot.

[0010] The predicted result information of the express delivery locker includes at least one result sub-information, which includes the identity information of the express delivery locker to which the order is predicted to be delivered and the delivery probability.

[0011] In one possible implementation, sending the address information to the constructed prediction model object includes:

[0012] The application development framework integrates a parcel locker prediction component, which is then used to send the address information to the prediction model object; wherein, the parcel locker prediction component includes Dubbo.

[0013] In one possible implementation, sending the address information to the constructed prediction model object includes:

[0014] Send the address information sent by the message queue component to the constructed prediction model object;

[0015] The message queue component includes the Kafka message queue.

[0016] In one possible implementation, the prediction model object processes the input address information and outputs the parcel locker prediction result information, including:

[0017] The prediction model object performs word segmentation on the address information and maps the segmented information into a two-dimensional array.

[0018] The prediction model object uses the trained prediction model to process the two-dimensional array to obtain the prediction result information of the express cabinet.

[0019] In one possible implementation, the above method further includes the step of generating the prediction model object:

[0020] When the service corresponding to the application development framework is started, the file corresponding to the prediction model is loaded from the preset database;

[0021] Construct a singleton prediction model object using the file; wherein the prediction model includes a Tensorflow model.

[0022] In one possible implementation, the address information includes at least one of the following:

[0023] Order number; Delivery address;

[0024] The receiving address includes the receiving province, city, district / county, detailed address, and latitude and longitude information.

[0025] Secondly, embodiments of this application provide a parcel locker prediction device, comprising:

[0026] The information acquisition module is used to acquire the address information of orders to be predicted for express delivery lockers;

[0027] The prediction module is used to send the address information to the constructed prediction model object; wherein, the prediction model object is constructed using an application development framework corresponding to a preset programming language, and is used to process the input address information and output the express cabinet prediction result information; the preset programming language includes JAVA;

[0028] The result processing module is used to take the express delivery locker prediction result information output by the prediction model object as the express delivery locker prediction result of the order.

[0029] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor, when executing the computer program, implements the method described in any of the above-mentioned embodiments.

[0030] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method described in any of the above-mentioned embodiments.

[0031] Compared with the prior art, this application has the following advantages:

[0032] According to the parcel locker prediction method of this application embodiment, the address information of the order to be predicted by the parcel locker is first obtained; then, the address information is sent to a constructed prediction model object; wherein, the prediction model object is constructed using an application development framework corresponding to a preset programming language, used to process the input address information and output parcel locker prediction result information; the preset programming language includes JAVA; finally, the parcel locker prediction result information output by the prediction model object is used as the parcel locker prediction result of the order. Since the infrastructure corresponding to JAVA is well-developed, and the development and deployment of online applications are relatively convenient, this application embodiment utilizes an application development framework corresponding to JAVA to construct a prediction model object, and then uses this prediction model object to perform parcel locker prediction, which can overcome the instability defects of online applications developed in the prior art and is conducive to improving the accuracy of parcel locker prediction.

[0033] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application, it can be implemented according to the contents of the specification. In order to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0034] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments according to this application and should not be construed as limiting the scope of this application.

[0035] Figure 1 This is a flowchart of a parcel locker prediction method according to an embodiment of this application;

[0036] Figure 2 This is a flowchart of a parcel locker prediction method according to another embodiment of this application;

[0037] Figure 3 This is a structural block diagram of a parcel locker prediction device according to an embodiment of this application;

[0038] Figure 4 This is a block diagram of an electronic device used to implement embodiments of this application. Detailed Implementation

[0039] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the concept or scope of this application. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0040] To facilitate understanding of the technical solutions of the embodiments of this application, the relevant technologies of the embodiments of this application are described below. The following relevant technologies are optional solutions and can be combined with the technical solutions of the embodiments of this application in any way, and all of them fall within the protection scope of the embodiments of this application.

[0041] While loading Tensorflow model files is relatively convenient in Python, building applications with Python within a company has an underdeveloped ecosystem, making deployment and release inconvenient and requiring separate handling by operations engineers. Furthermore, subsequent production environment monitoring is inadequate, leading to delayed problem detection and insufficient online application stability. The Sanci framework also requires learning and using a certain level of expertise. Under these circumstances, using Tensorflow models running in a Python environment for parcel locker prediction significantly reduces the accuracy of parcel locker predictions.

[0042] To address the aforementioned shortcomings, this application provides a method, apparatus, electronic device, and storage medium for predicting parcel locker usage. The application first obtains the address information of the order to be predicted for parcel locker use; then, it sends the address information to a pre-constructed prediction model object. This prediction model object is built using an application development framework corresponding to a preset programming language, used to process the input address information and output parcel locker prediction results. The preset programming language includes JAVA. Finally, the parcel locker prediction results output by the prediction model object are used as the parcel locker prediction result for the order. Because JAVA has a well-developed infrastructure, developing and deploying online applications is relatively convenient. Therefore, this application's embodiment utilizes a JAVA-based application development framework to build a prediction model object, and then uses this prediction model object to predict parcel lockers. This overcomes the instability of online applications developed in the prior art and helps improve the accuracy of parcel locker prediction.

[0043] The following is a detailed description of the express delivery locker prediction method and device of this application.

[0044] like Figure 1 The diagram shows a flowchart of a parcel locker prediction method according to an embodiment of this application. This parcel locker prediction method is executed by a device with computing and analytical capabilities and is used to predict which parcel will be delivered to which parcel. Specifically, the parcel locker prediction method of this embodiment may include the following steps:

[0045] S110. Obtain the address information of the orders to be predicted by the express delivery locker.

[0046] For example, the address information mentioned above includes at least one of the following: order number, delivery address, and user identity information. The delivery address includes at least one of the following: delivery province, city, district / county, detailed address, and latitude / longitude information.

[0047] Orders awaiting parcel locker forecasting include those not yet delivered to parcel lockers and those in transit.

[0048] For example, such as Figure 2 As shown, the above address information can be obtained in at least one of the following ways:

[0049] Method 1: Use a parcel locker prediction component integrated into an application development framework, such as Dubbo in Spring Boot, to obtain the above address information.

[0050] Method 2: Use a listening component to obtain the above address information from a message queue component, such as the Kafka message queue.

[0051] S120. Send the address information to the constructed prediction model object; wherein the prediction model object is constructed using an application development framework corresponding to a preset programming language, and is used to process the input address information and output the express cabinet prediction result information.

[0052] The predicted delivery result information for the parcel locker includes at least one sub-information, which includes the identity information and delivery probability of the parcel locker to which the order is predicted to be delivered. The identity information may include at least one of the following: the identifier, name, and address information of the corresponding parcel locker.

[0053] The preset programming language includes JAVA. The application development framework may include Spring Boot. The aforementioned prediction model object can be a singleton bean object, including a runnable TensorFlow model; that is, the prediction model object includes the object corresponding to the TensorFlow model. Thus, by processing the address information using the prediction model object, the prediction result information for the express delivery locker can be obtained.

[0054] S130. The express delivery locker prediction result information output by the prediction model object is used as the express delivery locker prediction result of the order.

[0055] Here, the parcel locker prediction result information can be directly used as the parcel locker prediction result for the order, or the parcel locker prediction result information can be processed to obtain the parcel locker prediction result. For example, the identity information of the parcel locker with the highest delivery probability can be used as the parcel locker prediction result; or the identity information of the N parcel lockers with the highest delivery probability can be used as the parcel locker prediction result; where N is a positive integer.

[0056] In some embodiments, sending the address information to the constructed prediction model object can be achieved by the following steps: calling the express delivery locker prediction component Dubbo integrated by the application development framework Spring Boot, and using the express delivery locker prediction component Dubbo to send the address information to the prediction model object.

[0057] like Figure 2 As shown, the Dubbo consumer sends the address information of the order to be predicted by the express locker to Dubbo. Then, the Dubbo express locker prediction component is called to send the address information to the prediction model object. The prediction model object is then run, and the prediction model is run by the prediction model object. The algorithm in the prediction model is executed to obtain the express locker prediction result information. Finally, the express locker prediction result or the express locker prediction result information is fed back as a Dubbo service response.

[0058] To build a Dubbo service, you can use the out-of-the-box Dubbo components based on Spring Boot. First, configure a parcel locker prediction interface using annotations, marking the interface as a Spring bean. Simultaneously, construct and maintain a Bert object in the bean's `afterPropertiesSet` lifecycle hook. When a Dubbo service consumer calls the parcel locker prediction service, it passes the input parameters to the Bert object, calculates the result, and returns it. The aforementioned Bert object is contained within the prediction model object.

[0059] Dubbo is a Java-based application integrated with Spring Boot. Spring Boot boasts a mature framework, robust infrastructure, convenient development and deployment, and excellent performance. It also allows for easy integration with other middleware, expanding the application's scope. Loading TensorFlow models into the Java environment and then building Dubbo services effectively improves development efficiency, application functionality, and application performance.

[0060] Dubbo is an open-source, high-performance, lightweight Java RPC service framework with features such as remote method invocation, load balancing, service fault tolerance, and automatic service registration and discovery. Developing a Dubbo service interface requires defining the interface method signature, publishing the interface JAR file, writing the interface implementation code, adding relevant configurations, and then deploying it to the production environment for other consumers to call.

[0061] Spring Boot is an open-source framework for rapidly developing Java applications. It uses specific configuration methods, eliminating the need to define boilerplate configurations. Spring Boot provides a large number of out-of-the-box dependency modules, enabling the rapid setup of a Dubbo service and the integration of other third-party components.

[0062] In some embodiments, sending the address information to the constructed prediction model object can also be achieved using the following steps:

[0063] Send the address information sent by the message queue component, such as the Kafka message queue, to the constructed prediction model object.

[0064] like Figure 2 As shown, the Kafka message consumer sends the address information of the order to be predicted by the express locker to the listening component. Then, the listening component sends the address information to the prediction model object, runs the prediction model object, and uses the prediction model object to run the prediction model. By executing the algorithm in the prediction model, the prediction result information of the express locker is obtained. Finally, the prediction result of the express locker or the prediction result information of the express locker is fed back as a Kafka feedback message.

[0065] A Kafka message queue was integrated using Spring Boot. In the parcel locker prediction interface, Kafka message listeners were registered using annotations. Kafka message consumers can send address information via Kafka messages. After receiving the message, the prediction model object calls the prediction model's calculation method and then sends the calculation result via Kafka message. The user obtains the calculation result through Kafka feedback messages, thereby achieving asynchronous processing and traffic shaping.

[0066] In some embodiments, the prediction model object processes the input address information and outputs the prediction result information for the express delivery locker. This can be achieved through the following steps:

[0067] The prediction model object performs word segmentation on the address information and maps the segmented information into a two-dimensional array; then, the prediction model object uses the trained prediction model to process the two-dimensional array to obtain the prediction result information of the express cabinet.

[0068] In this embodiment, the input address information is segmented according to rules and combined with the configuration file to obtain a set of input sequences in the form of a two-dimensional array, which is then input into the prediction model.

[0069] The above-mentioned operation of segmenting the address information into words and mapping the segmented information into a two-dimensional array can be implemented by the pre-packaged Bert algorithm.

[0070] In some embodiments, the prediction model object may be generated using the following steps:

[0071] When the service corresponding to the application development framework is started, the file corresponding to the prediction model, such as a TensorFlow model file, is loaded from a preset database. A singleton prediction model object is then constructed using this file; wherein the prediction model includes a TensorFlow model. The preset database includes a Tensor library, which stores TensorFlow model files.

[0072] TensorFlow model files are a file format for machine learning models that can be read by Java and used for predictive computations. Machine learning models are typically generated by data analysts using Python, through multiple iterations on offline data.

[0073] When the Spring Boot service starts, the Tensor library in the Java environment can be used to load the TensorFlow model file and construct a singleton model file bean object, namely the aforementioned prediction model object. This object contains the pre- and post-methods required for model computation. When the Dubbo consumer calls this method or consumes Kafka messages, it uses the methods of the prediction model object to perform computation and return the result.

[0074] The TensorFlow model files are pre-trained by the analyst using the BERT algorithm. When loading a model in Java, in addition to loading the model itself, a BERT algorithm needs to be constructed to obtain the aforementioned two-dimensional array. This application constructs a singleton object to encapsulate these methods, namely the prediction model object. When the application starts, the object dynamically loads the model files and related configuration files and holds them until the application stops.

[0075] This application combines Tensorflow model loading with a Java environment and implements the BERT algorithm. Then, by building Dubbo services and message queue services, the model prediction service can be quickly applied to production. The development speed is fast, the generated application has rich functions, and it has great production benefits.

[0076] Loading TensorFlow models into files is already supported in Java. By integrating Dubbo services through Spring Boot, a production-ready application can be quickly built. It can also be easily combined with third-party components, such as Kafka message queues, to extend the service's usage. Once deployed, the application can be used for logging, monitoring, alerting, and other company infrastructure functions.

[0077] Corresponding to the application scenarios and methods provided in the embodiments of this application, the embodiments of this application also provide a parcel locker prediction device. For example... Figure 3 The diagram shown is a structural block diagram of a parcel locker prediction device according to an embodiment of this application. The parcel locker prediction device may include:

[0078] The information acquisition module 301 is used to acquire the address information of orders to be predicted by the express locker.

[0079] The prediction module 302 is used to send the address information to the constructed prediction model object; wherein the prediction model object is constructed using an application development framework corresponding to a preset programming language, and is used to process the input address information and output the express cabinet prediction result information; the preset programming language includes JAVA.

[0080] The result processing module 303 is used to take the express delivery locker prediction result information output by the prediction model object as the express delivery locker prediction result of the order.

[0081] In some embodiments, the prediction model object includes an object corresponding to a Tensorflow model; the application development framework includes Spring Boot. The parcel locker prediction result information includes at least one result sub-information, which includes the identity information of the parcel locker to which the order is predicted to be delivered and the delivery probability.

[0082] In some embodiments, when the prediction module 302 sends the address information to the constructed prediction model object, it is used to:

[0083] The application development framework integrates a parcel locker prediction component, which is then used to send the address information to the prediction model object; wherein, the parcel locker prediction component includes Dubbo.

[0084] In some embodiments, when the prediction module 302 sends the address information to the constructed prediction model object, it is used to:

[0085] Send the address information sent by the message queue component to the constructed prediction model object;

[0086] The message queue component includes the Kafka message queue.

[0087] In some embodiments, when the prediction model object in the prediction module 302 processes the input address information and outputs the prediction result information for the express delivery locker, it is used for:

[0088] The prediction model object performs word segmentation on the address information and maps the segmented information into a two-dimensional array.

[0089] The prediction model object uses the trained prediction model to process the two-dimensional array to obtain the prediction result information of the express cabinet.

[0090] In some embodiments, the prediction module 302 is further configured to generate the prediction model object:

[0091] When the service corresponding to the application development framework is started, the file corresponding to the prediction model is loaded from the preset database;

[0092] Construct a singleton prediction model object using the file; wherein the prediction model includes a Tensorflow model.

[0093] In some embodiments, the address information includes at least one of an order number and a delivery address;

[0094] The receiving address includes at least one of the following: receiving province, city, district / county, detailed address, and latitude / longitude information.

[0095] The functions of each module in each device in the embodiments of this application can be found in the corresponding description in the above method, and they have corresponding beneficial effects, which will not be repeated here.

[0096] Figure 4 This is a block diagram of an electronic device used to implement embodiments of this application. For example... Figure 4 As shown, the electronic device includes a memory 410 and a processor 420. The memory 410 stores a computer program that can run on the processor 420. When the processor 420 executes the computer program, it implements the method described in the above embodiments. The number of memories 410 and processors 420 can be one or more.

[0097] The electronic device also includes:

[0098] The communication interface 430 is used to communicate with external devices and perform data exchange and transmission.

[0099] If the memory 410, processor 420, and communication interface 430 are implemented independently, they can be interconnected via a bus to communicate with each other. This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0100] Optionally, in a specific implementation, if the memory 410, processor 420 and communication interface 430 are integrated on a single chip, the memory 410, processor 420 and communication interface 430 can communicate with each other through an internal interface.

[0101] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method provided in this application.

[0102] This application also provides a chip including a processor for calling and executing instructions stored in a memory, causing a communication device with the chip installed to perform the method provided in this application.

[0103] This application also provides a chip, including: an input interface, an output interface, a processor, and a memory. The input interface, output interface, processor, and memory are connected through an internal connection path. The processor is used to execute code in the memory. When the code is executed, the processor is used to execute the method provided in the application embodiment.

[0104] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that the processor can be a processor supporting Advanced Reduced Instruction Set Machines (ARM) architecture.

[0105] Further, optionally, the aforementioned memory may include read-only memory and random access memory. The memory may be volatile memory or non-volatile memory, or may include both. Non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available. Examples include Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DR RAM).

[0106] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.

[0107] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0108] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0109] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process. Furthermore, the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functionality involved.

[0110] The logic and / or steps described in the flowchart or otherwise herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a processor-included system or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0111] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. All or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware, the program being stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiments.

[0112] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. This storage medium can be a read-only memory, a disk, or an optical disk, etc.

[0113] The above description is merely an exemplary embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope described in this application, and these should all be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for predicting express delivery locker usage, characterized in that, include: Obtain the address information of orders to be predicted for use in express delivery lockers; The address information is sent to the constructed prediction model object; wherein the prediction model object is constructed using an application development framework corresponding to a preset programming language, and is used to process the input address information and output the express cabinet prediction result information; the preset programming language includes JAVA; The express delivery locker prediction result information output by the prediction model object is used as the express delivery locker prediction result for the order. It also includes the step of generating the prediction model object: When the service corresponding to the application development framework is started, the file corresponding to the prediction model is loaded from the preset database; Construct a singleton prediction model object using the file; wherein the prediction model includes a Tensorflow model; The prediction model object includes objects corresponding to Tensorflow models; the application development framework includes Spring Boot. The predicted result information of the express delivery locker includes at least one result sub-information, which includes the identity information and delivery probability of the express delivery locker to which the order is predicted to be delivered; Sending the address information to the constructed prediction model object includes: calling the express delivery locker prediction component integrated in the application development framework, and using the express delivery locker prediction component to send the address information to the prediction model object; wherein, the express delivery locker prediction component includes Dubbo.

2. The method according to claim 1, characterized in that, The prediction model object processes the input address information and outputs the prediction result information for the express delivery locker, including: The prediction model object performs word segmentation on the address information and maps the segmented information into a two-dimensional array. The prediction model object uses the trained prediction model to process the two-dimensional array to obtain the prediction result information of the express cabinet.

3. The method according to claim 1, characterized in that, The address information includes at least one of the order number and the delivery address; The receiving address includes at least one of the following: receiving province, city, district / county, detailed address, and latitude / longitude information.

4. A predictive device for express delivery lockers, characterized in that, include: The information acquisition module is used to acquire the address information of orders to be predicted for express delivery lockers; The prediction module is used to call the express locker prediction component integrated into the application development framework, and use the express locker prediction component to send the address information to the prediction model object; wherein, the express locker prediction component includes Dubbo; the prediction model object is built using the application development framework corresponding to a preset programming language, and is used to process the input address information and output the express locker prediction result information; the preset programming language includes JAVA; the application development framework includes Spring Boot; The result processing module is used to take the express delivery locker prediction result information output by the prediction model object as the express delivery locker prediction result of the order; it is also used to load the file corresponding to the prediction model from a preset database when the service corresponding to the application development framework is started; and to construct a singleton prediction model object using the file; wherein the prediction model includes a Tensorflow model; wherein the prediction model object includes an object corresponding to the Tensorflow model; and the application development framework includes Spring Boot. The predicted result information of the express delivery locker includes at least one result sub-information, which includes the identity information and delivery probability of the express delivery locker to which the order is predicted to be delivered; Sending the address information to the constructed prediction model object includes: calling the express delivery locker prediction component integrated in the application development framework, and using the express delivery locker prediction component to send the address information to the prediction model object; wherein, the express delivery locker prediction component includes Dubbo.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory, wherein the processor, when executing the computer program, implements the method of any one of claims 1-3.

6. A computer-readable storage medium storing a computer program that, when executed by a processor, implements the method of any one of claims 1-3.

Images