Efficiency prediction method and device for warehousing system

Abstract

The invention relates to the technical field of warehouse logistics, and discloses an efficiency prediction method and device for a warehousing system, and the method comprises the steps: obtaining the initial parameter information of the warehousing system; wherein the initial parameter information comprises warehouse size, sorting efficiency information and business demand information corresponding to the warehousing system; preprocessing the initial parameter information, and determining target input information; processing the target input information based on the target efficiency prediction model to obtain multiple groups of system configuration parameters of the warehousing system; wherein each group of system configuration parameters comprises the number of carrying equipment and / or the number of workstations; and processing the multiple groups of system configuration parameters based on the target efficiency prediction model to obtain prediction efficiency indexes corresponding to the groups of system configuration parameters. The efficiency index of the warehousing system can be predicted in advance through the target efficiency prediction model, and the accuracy of efficiency prediction is improved.

Description

Technical Field

[0001] The present application relates to the technical field of warehousing and logistics, and in particular to a method and device for predicting the efficiency of a warehousing system. Background Art

[0002] With the rapid development of the logistics industry, warehouse automation and intelligence have become the key to improving the efficiency of warehousing systems and reducing costs. In order to improve the operating efficiency of the warehousing system, the efficiency of the warehousing system can be predicted, and the deployment of the warehousing system can be adjusted according to the results of the efficiency prediction to meet user needs. Usually, the efficiency of the warehousing system can be predicted in combination with the operating parameters of the warehousing system after the warehousing system is deployed, or the efficiency of the warehousing system can be predicted based on empirical data and manual judgment before the warehousing system is deployed. However, the above prediction method is difficult to adapt to complex and changeable warehousing scenarios, and it is impossible to obtain more accurate working efficiency of the warehousing system in different scenarios. Therefore, how to accurately predict the efficiency of the warehousing system in different scenarios before the warehousing system is deployed has become a technical problem that needs to be solved in the warehousing field. Summary of the invention

[0003] In order to solve the above problems, the embodiments of the present application provide a method and device for predicting the efficiency of a warehousing system, which can predict the working efficiency of the warehousing system before the warehousing system is deployed and improve the accuracy of the efficiency prediction of the warehousing system. Specifically, the embodiments of the present application disclose the following technical solutions:

[0004] According to a first aspect of an embodiment of the present application, there is provided an efficiency prediction method for a warehousing system, comprising: first, obtaining initial parameter information of the warehousing system; wherein the initial parameter information includes warehouse size, picking efficiency information and business demand information corresponding to the warehousing system. Secondly, preprocessing the initial parameter information to determine the target input information. Then, based on the target efficiency prediction model, the target input information is processed to obtain multiple groups of system configuration parameters of the warehousing system; wherein each group of system configuration parameters includes the number of handling equipment and / or the number of workstations. Finally, based on the target efficiency prediction model, multiple groups of system configuration parameters are processed to obtain prediction efficiency indicators corresponding to each group of system configuration parameters; wherein each group of prediction efficiency indicators includes at least one of the workstation utilization rate, handling equipment utilization rate, task cycle time and number of vehicles of the warehousing system.

[0005] In some embodiments, the initial parameter information is preprocessed to determine the target input information, including: converging the warehouse size, picking efficiency information and the business demand information through a preset algorithm to obtain the type of handling equipment and the carrier handling efficiency corresponding to the warehousing system; wherein the target input information includes the warehouse size, handling equipment type and carrier handling efficiency, and the carrier handling efficiency includes the number of carrier handling times and the carrier dwell time.

[0006] In some embodiments, before processing the target input information based on the target efficiency prediction model to obtain multiple sets of system configuration parameters for the warehousing system, the method also includes: determining the warehouse type corresponding to the warehousing system based on the warehouse size; determining the target efficiency prediction model corresponding to the target input information based on the warehouse type; wherein different warehouse types correspond to different target efficiency prediction models.

[0007] In some embodiments, the target efficiency prediction model includes a first prediction sub-model, and the target input information is processed based on the target efficiency prediction model to obtain multiple sets of system configuration parameters of the warehousing system, including: processing the target input information based on the first prediction sub-model to obtain the target configuration parameters of the warehousing system; wherein the target configuration parameters include a first number of various types of handling equipment and / or a second number of workstations. The target configuration parameters are processed for similarity using a preset similarity algorithm to obtain the multiple sets of system configuration parameters of the warehousing system; wherein the multiple sets of system configuration parameters include the target configuration parameters, and the number of various types of handling equipment in each set of system configuration parameters other than the target configuration parameters in the multiple sets of system configuration parameters is different from the corresponding first number, and / or the number of workstations is different from the second number.

[0008] In some embodiments, the target configuration parameters are processed for similarity through a preset similarity algorithm to obtain multiple sets of system configuration parameters for the warehousing system, including: determining the warehouse type corresponding to the warehousing system based on the warehouse size; and determining the number of each type of handling equipment in the multiple sets of system configuration parameters through a preset similarity algorithm based on the warehouse type and the type of handling equipment in the target input information.

[0009] In some embodiments, the target efficiency prediction model includes a second prediction sub-model, and multiple groups of system configuration parameters are processed based on the target efficiency prediction model to obtain prediction efficiency indicators corresponding to each group of system configuration parameters, including: processing each group of system configuration parameters in turn through the second prediction sub-model to determine the prediction efficiency indicators corresponding to each group of system configuration parameters.

[0010] In some embodiments, the target efficiency prediction model includes a second prediction sub-model and an optimization sub-model; multiple groups of system configuration parameters are processed based on the target efficiency prediction model to obtain prediction efficiency indicators corresponding to each group of system configuration parameters, including: processing each group of system configuration parameters in turn through the second prediction sub-model to determine the initial efficiency indicators corresponding to each group of system configuration parameters; optimizing each group of initial efficiency indicators through the optimization sub-model to obtain prediction efficiency indicators corresponding to each group of system configuration parameters.

[0011] In some embodiments, after processing multiple groups of system configuration parameters based on the target efficiency prediction model and obtaining the prediction efficiency index corresponding to each group of system configuration parameters, the method further includes: determining the prediction result corresponding to the warehousing system based on the prediction efficiency index corresponding to each group of system configuration parameters; controlling the user interaction interface to display the prediction result; obtaining the satisfaction information input by the user in the user interaction interface for the prediction result; if the satisfaction information does not meet the preset conditions, controlling the user interaction interface to display prompt information, or re-determining multiple groups of system configuration parameters; wherein the prompt information is used to prompt the user to optimize the initial parameter information. If the satisfaction information meets the preset conditions, the target efficiency prediction model is optimized based on the prediction efficiency index.

[0012] In some embodiments, the method also includes: obtaining multiple sample parameter information and a sample efficiency indicator set corresponding to each sample parameter information, the sample efficiency indicator set including sample efficiency indicators corresponding to each group of sample configuration parameters; processing the sample parameter information based on the initial efficiency prediction model to obtain prediction efficiency indicators corresponding to each group of prediction configuration parameters; using the prediction efficiency indicators corresponding to each group of prediction configuration parameters as the initial training output information of the initial efficiency prediction model, and the sample efficiency indicators corresponding to each group of sample configuration parameters as supervision information, iterating the initial efficiency prediction model to obtain the target efficiency prediction model.

[0013] In some embodiments, obtaining initial parameter information of a warehousing system includes: obtaining a pending task input by a user in a user interaction interface; splitting the pending task through a warehousing planning model to obtain at least one subtask; wherein at least one subtask includes an efficiency prediction subtask; analyzing and processing each subtask through a warehousing planning model to obtain at least one request information corresponding to each subtask, and controlling the user interaction interface to display each request information; obtaining at least one feedback information input by the user for at least one request information corresponding to each subtask; wherein the initial parameter information includes at least one feedback information corresponding to the efficiency prediction subtask.

[0014] In some embodiments, the method also includes: determining the processing results corresponding to each subtask through a warehouse planning model based on at least one feedback information inputted from at least one request information corresponding to each subtask; determining the planning results corresponding to the tasks to be processed through a warehouse planning model based on the processing results corresponding to each subtask in at least one subtask, and controlling the user interaction interface to display the planning results.

[0015] In some embodiments, the warehouse planning model includes a task splitting sub-model, which splits the task to be processed through the warehouse planning model to obtain at least one sub-task, including: based on the complexity of the task to be processed and a preset splitting principle, splitting the task to be processed into at least one sub-task through the task splitting sub-model; wherein the preset splitting principle includes that the number of tasks of at least one sub-task is less than or equal to a preset number threshold and / or the correlation between any two sub-tasks in at least one sub-task is less than or equal to a preset correlation threshold.

[0016] In some embodiments, the user interaction interface includes a progress bar; the method also includes: determining the progress information of each subtask in response to at least one feedback information input by the user for at least one request information corresponding to each subtask; and displaying the task completion degree of the task to be processed through a progress bar based on the progress information of each subtask.

[0017] In some embodiments, the user interaction interface includes a feedback window, and the method also includes: obtaining at least one question and answer information regarding the planning results input by the user in the feedback window; processing the at least one question and answer information through the warehouse planning model, and controlling the feedback window to display the interaction results corresponding to the question and answer information.

[0018] The second aspect of the embodiment of the present application provides an efficiency prediction device for a warehousing system, comprising: an acquisition module, a determination module and a processing module. The acquisition module is configured to: acquire the initial parameter information of the warehousing system; wherein the initial parameter information includes the warehouse size, picking efficiency information and business demand information corresponding to the warehousing system. The determination module is configured to: pre-process the initial parameter information and determine the target input information. The processing module is configured to: process the target input information based on the target efficiency prediction model to obtain multiple groups of system configuration parameters for the warehousing system; wherein each group of system configuration parameters includes the number of handling equipment and / or the number of workstations; process multiple groups of system configuration parameters based on the target efficiency prediction model to obtain prediction efficiency indicators corresponding to each group of system configuration parameters; wherein each group of prediction efficiency indicators includes at least one of the workstation utilization rate, handling equipment utilization rate, task cycle time and number of carriers of the warehousing system.

[0019] A third aspect of an embodiment of the present application provides an electronic device, comprising: a processor and a memory, the memory being used to store computer executable instructions; the processor being used to read the instructions from the memory and execute the instructions to implement the efficiency prediction method for the warehousing system described in the first aspect above.

[0020] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the storage medium stores computer program instructions. When a computer reads the instructions, the efficiency prediction method for a warehousing system described in the first aspect is executed.

[0021] A fifth aspect of an embodiment of the present application provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the efficiency prediction method for the warehousing system described in the first aspect above.

[0022] A sixth aspect of an embodiment of the present application provides a computer program, which, when executed by a processor, can implement the efficiency prediction method for the warehousing system described in the first aspect above.

[0023] The efficiency prediction method of the warehousing system provided in the embodiment of the present application obtains the target input information by preprocessing the initial parameter information of the warehousing system; the target input information is input into the trained target efficiency prediction model, and after being processed by the target efficiency prediction model, multiple groups of system configuration parameters and the predicted efficiency index corresponding to each group of system configuration parameters are obtained, thereby realizing the efficiency prediction of the warehousing system. Compared with the efficiency prediction method in the related art, the efficiency prediction method of the warehousing system provided in the embodiment of the present application can realize the prediction of the efficiency index of the warehousing system under different system configuration parameters before the warehousing system is deployed, and improve the accuracy of the efficiency prediction of the warehousing system, providing a reasonable basis for the subsequent deployment of the warehousing system. At the same time, since the present application can provide users with efficiency indexes corresponding to multiple groups of system configuration parameters, it provides users with more choices and comparisons. Users can compare and choose according to actual needs, which improves the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 A schematic diagram of an efficiency prediction method for a warehousing system provided in an embodiment of the present application;

[0026] Figure 2 A schematic diagram of another method for predicting the efficiency of a storage system provided in an embodiment of the present application;

[0027] Figure 3 A schematic diagram of another method for predicting the efficiency of a storage system provided in an embodiment of the present application;

[0028] Figure 4 A schematic diagram of another method for predicting the efficiency of a storage system provided in an embodiment of the present application;

[0029] Figure 5 A schematic diagram of a user interaction interface provided in an embodiment of the present application;

[0030] Figure 6 A schematic diagram of a warehouse planning system provided in an embodiment of the present application;

[0031] Figure 7 A schematic diagram of another method for predicting the efficiency of a storage system provided in an embodiment of the present application;

[0032] Figure 8 A schematic diagram of another method for predicting the efficiency of a storage system provided in an embodiment of the present application;

[0033] Fig. 9 A schematic diagram of another method for predicting the efficiency of a storage system provided in an embodiment of the present application;

[0034] Fig.10 A schematic diagram of another user interaction interface provided in an embodiment of the present application;

[0035] Fig.11 A schematic diagram of another user interaction interface provided in an embodiment of the present application;

[0036] Fig.12 A schematic diagram of an efficiency prediction device for a warehousing system provided in an embodiment of the present application;

[0037] Fig.13 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention and to make the above-mentioned purposes, features and advantages of the embodiments of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention are further described in detail below with reference to the accompanying drawings.

[0039] With the rapid development of the logistics industry, warehouse automation and intelligence have become the key to improving the efficiency of warehouse systems and reducing costs. As the core of automated warehouse systems (hereinafter referred to as warehouse systems), the performance of handling equipment (such as warehouse robots) directly affects the overall logistics efficiency. Therefore, it is particularly important to accurately predict the working efficiency of warehouse robots in different scenarios. In other words, accurately predicting the efficiency of warehouse systems in different scenarios has also become a problem that needs to be solved in the warehousing field.

[0040] In related technologies, the efficiency prediction of warehousing systems often relies on empirical data, manual judgment or real machine testing, etc. These prediction methods are difficult to adapt to complex and changeable warehousing scenarios in the pre-sales stage or before the deployment of the warehousing system, and therefore cannot predict the working efficiency of the warehousing system in different scenarios. For example, the efficiency prediction of the warehousing system can also be achieved by using a simulation system, using a robot simulation simulator to simulate and predict the efficiency of the warehousing system under different warehousing environments, but this kind of simulation requires a large amount of equipment performance, takes a long time, and the credibility of the prediction results needs to be improved.

[0041] In order to solve the above problems, the embodiments of the present application provide an efficiency prediction method and device for a warehousing system. By obtaining the efficiency indicators corresponding to multiple groups of system configuration parameters of the warehousing system through a trained efficiency prediction model (i.e., a target efficiency prediction model), the working efficiency of the warehousing system in different warehousing environments (such as different deployment schemes) can be predicted more accurately, providing a scientific basis for the subsequent deployment and optimization of the warehousing system.

[0042] The efficiency prediction method of the warehousing system provided in the embodiment of the present application is described below with reference to the accompanying drawings.

[0043] Figure 1 This is a schematic diagram of an efficiency prediction method for a warehousing system provided in an embodiment of the present application. The efficiency prediction method for the warehousing system can be implemented by a warehousing planning system. Figure 1 As shown, the method includes steps 110 to 140 as shown below.

[0044] Step 110, obtaining initial parameter information of the warehousing system.

[0045] Exemplarily, the initial parameter information may include warehouse size, picking efficiency information, and business demand information corresponding to the warehousing system.

[0046] Among them, warehouse dimensions include the length, width and height of the warehouse; picking efficiency information includes user requirements for picking efficiency and picking time; business types include B2B (Business-to-Business) and B2C (Business-to-Consumer).

[0047] In some examples, the picking efficiency information in the initial parameter information also includes carrier size information and load information of the transport equipment, wherein the load information of the transport equipment may be the maximum load of the transport equipment required by the user.

[0048] For example, the handling equipment may be a handling robot, such as an automated guided vehicle (AGV), and the handling equipment may include a carrier handling device that can be used to carry a carrier, and may also include a container handling device for carrying to a container. The carrier may be a shelf, a turnover vehicle, a cage vehicle, etc. For example, the carrier may be a movable shelf or a non-movable carrier. The embodiments of the present application do not specifically limit the form of the handling equipment and the carrier.

[0049] In some examples, the warehouse planning system may obtain initial parameter information of the warehouse system for which the user needs to perform efficiency prediction by interacting with the user.

[0050] For example, the warehouse planning system may display a user interaction interface, which includes an interaction window, through which the user may input the project information of the warehouse system, wherein the initial parameter information may be all or part of the project information of the warehouse system input by the user.

[0051] It should be noted that the above initial parameter information can be obtained through Figure 7 The steps of the embodiment shown (such as step 710 to step 730) are implemented.

[0052] Step 120, preprocessing the initial parameter information to determine the target input information.

[0053] Exemplarily, the preprocessing of the initial parameter information may include two processing processes, namely, the first processing and the second processing. The first processing obtains more accurate and reasonable input information by performing data cleaning, feature engineering and data standardization on the initial parameter information. The second processing may convert the input information obtained by the first processing into information suitable for input into the target efficiency prediction model (i.e., target input information).

[0054] In some examples, the data cleaning process is mainly used to correct identifiable errors in the initial parameter information to improve the quality, accuracy and reliability of the information to be input. For example, data cleaning can correct the initial parameter information by processing missing values, processing outliers, checking data consistency and deleting one or more of the duplicate data. Feature engineering is the process of extracting useful features from input data (such as initial parameter information after data cleaning). Data standardization can remove unit restrictions from data and convert it into dimensionless pure values, so that indicators of different units or magnitudes can be compared and weighted, thereby further ensuring the reliability of the results.

[0055] For example, after relatively accurate and reasonable information to be input is obtained through the first processing, the information to be input is subjected to the second processing.

[0056] In some embodiments, step 120 includes: performing convergence processing on warehouse size, picking efficiency information and business demand information through a preset algorithm to obtain the handling equipment type and carrier handling efficiency corresponding to the warehousing system.

[0057] Exemplarily, the target input information includes warehouse size, handling equipment type and carrier handling efficiency, wherein the carrier handling efficiency includes carrier handling times and carrier dwell time.

[0058] In some examples, the type of handling equipment in the target input information may be determined based on the warehouse size, carrier size, and maximum load weight of the handling equipment in the initial parameter information (or the information to be input after the first processing).

[0059] For example, since different types of handling equipment have different sizes, heights, and load-bearing capacity, the type of handling equipment suitable for the user's storage system needs to be determined based on the user's warehouse size, carrier size, and the maximum load of the required handling equipment. It should be noted that a storage system may include at least one (such as one or more) types of handling equipment, and this embodiment of the application is not limited to this.

[0060] In some examples, the vehicle handling efficiency in the target input information, such as the number of vehicle handling times and the vehicle dwelling time, can be determined based on the picking efficiency information and business type in the initial parameter information.

[0061] For example, when users have different requirements for picking efficiency, the corresponding carrier handling efficiency is also different. For example, when users have higher requirements for picking efficiency, the determined carrier handling efficiency will be higher. Therefore, the carrier handling efficiency suitable for the warehousing system can be determined based on the user's requirements for picking efficiency. At the same time, different business types correspond to different order volumes, delivery requirements, and timeliness requirements. Therefore, this application can also determine the optimal carrier handling efficiency corresponding to the warehousing system based on the specific business type.

[0062] In some examples, a preset algorithm (such as a warehouse experience calculation algorithm) may also be pre-set in the warehouse planning system. The preset algorithm may perform convergence processing on the initial parameter information or the information to be processed, so as to determine the target input information corresponding to the target efficiency prediction model.

[0063] For example, the preset algorithm may include a matching relationship between multiple groups of data to be processed and multiple groups of input data. After determining the initial parameter information (or information to be input), it can be determined whether the initial parameter information (or information to be input) exists in the multiple data to be processed with the matching relationship. If so, the input data matching the initial parameter information (or information to be input) is determined as the target input information.

[0064] It should be noted that the multiple groups of data to be processed and the multiple groups of input data can be determined based on historical data, and the embodiment of the present application does not limit the specific form of the preset algorithm.

[0065] Step 130 , processing the target input information based on the target efficiency prediction model to obtain multiple groups of system configuration parameters of the warehousing system.

[0066] Exemplarily, each of the plurality of system configuration parameters includes the number of handling equipment and / or the number of workstations. The number of handling equipment may include the number of various types of handling equipment. In other words, the plurality of system configuration parameters includes the number of various types of handling equipment and / or the number of workstations.

[0067] In some examples, when each set of system configuration parameters includes the number of handling devices and the number of workstations, the number of handling devices in each set of system configuration parameters is different, or the number of workstations in each set of system configuration parameters is different, or both the number of handling devices and the number of workstations in each set of system configuration parameters are different. When each set of system configuration parameters includes the number of handling devices (or the number of workstations), the number of handling devices (or the number of workstations) in each set of system configuration parameters is different.

[0068] Exemplarily, the warehouse planning system includes a target efficiency prediction model, which is pre-trained and stored. The target efficiency prediction model includes a first prediction sub-model and a second prediction sub-model. The first prediction sub-model and the second prediction sub-model are pre-trained and stored.

[0069] Figure 2 A schematic diagram of another method for predicting the efficiency of a storage system provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the method further includes steps 210 to 220 as shown below. It should be noted that step 210 can be performed after step 120 and before step 130.

[0070] Step 210, based on the warehouse size, determine the warehouse type corresponding to the warehousing system.

[0071] In some examples, multiple warehouse types may be preset, each warehouse type corresponding to a different preset size range. For example, warehouses may be divided into three different types: large, medium, and small according to their sizes.

[0072] For example, a first correspondence between each warehouse type in multiple warehouse types and its corresponding preset size range can be pre-set. After determining the warehouse size in the target input information, the preset size range and the first correspondence of the warehouse size are determined to determine the warehouse type of the warehousing system.

[0073] Step 220, based on the warehouse type, determine the target efficiency prediction model corresponding to the target input information.

[0074] Exemplarily, different warehouse types correspond to different target efficiency prediction models.

[0075] In some examples, the warehouse planning system (such as the backend of the warehouse planning system) may store multiple different efficiency prediction models, and may determine the efficiency prediction model corresponding to the target input information (ie, the target efficiency prediction model) based on the warehouse type.

[0076] In some embodiments, the target efficiency prediction model includes a first prediction sub-model and a second prediction sub-model. The first prediction sub-models in different efficiency prediction models may be different. That is, the first prediction sub-model corresponding to the target input information may be determined based on the warehouse type.

[0077] In some examples, a second correspondence between each warehouse type in the plurality of warehouse types and each first prediction sub-model may be set. For example, the first prediction sub-model corresponding to the target input information may be determined according to the warehouse type determined in step 210 and the second correspondence.

[0078] For example, warehouses can be divided into three types of warehouses, namely large warehouses, medium warehouses and small warehouses, according to their sizes. When the warehouse types are divided into three types, three different first prediction sub-models can be pre-set, namely the first prediction sub-model A, the first prediction sub-model B and the first prediction sub-model C. Among them, the three first prediction sub-models correspond to the three warehouse types one by one. When the warehouse size is large and belongs to a large warehouse, it can be determined that the target input information corresponds to the first prediction sub-model A. When the warehouse size is regular and belongs to a medium-sized warehouse, it can be determined that the target input information corresponds to the first prediction sub-model B. When the warehouse size is small and belongs to a small warehouse, it can be determined that the target input information corresponds to the first prediction sub-model C.

[0079] It should be noted that the number of the first prediction sub-models may be more or less, and the embodiment of the present application does not limit this. For example, the number of the first prediction sub-models may be related to the number of warehouse types.

[0080] Figure 3 A schematic diagram of another method for predicting the efficiency of a storage system provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the above step 130 includes steps 1310 to 1320 as shown below.

[0081] Step 1310: Process the target input information based on the first prediction sub-model to obtain target configuration parameters of the warehousing system.

[0082] Exemplarily, the target configuration parameters include a first number of each type of handling equipment and / or a second number of workstations.

[0083] It should be noted that the first number of each type of handling equipment and / or the second number of workstations in the target configuration parameters is the most suitable number of each type of handling equipment and / or the number of workstations for the warehousing system determined by the first prediction sub-model according to the target input information.

[0084] In some examples, the target input information is input into the first prediction sub-model, and after being processed by the first prediction sub-model, the first quantity of each type of handling equipment corresponding to the warehousing system, or the second quantity of workstations corresponding to the warehousing system, or the first quantity of each type of handling equipment and the second quantity of workstations corresponding to the warehousing system can be output.

[0085] It should be noted that if there are multiple types of handling equipment in the target input information, the first prediction sub-model can be used to determine the quantity of each type of handling equipment, that is, multiple first quantities. For example, when the types of handling equipment include two types, namely, first handling equipment and second handling equipment, the target configuration parameters determined by the first prediction sub-model include the first quantity of the first handling equipment and the first quantity of the second handling equipment; wherein, the first quantity of the first handling equipment and the first quantity of the second handling equipment may be different.

[0086] Step 1320 , performing similarity processing on the target configuration parameters using a preset similarity algorithm to obtain multiple groups of system configuration parameters of the warehousing system.

[0087] Exemplarily, the multiple groups of system configuration parameters include target configuration parameters, and in each group of system configuration parameters other than the target configuration parameters in the multiple groups of system configuration parameters, the number of each type of handling equipment is different from the corresponding first number, and / or the number of workstations is different from the second number. That is, one group of system configuration parameters in the multiple groups of system configuration parameters is the target configuration parameters.

[0088] For example, when the plurality of groups of system configuration parameters include a first group of system configuration parameters, a second group of system configuration parameters (target configuration parameters) and a third group of system configuration parameters, and the types of handling equipment include two types, namely, first handling equipment and second handling equipment, the number of first handling equipment in the first group of system configuration parameters is different from the first number of first handling equipment in the target configuration parameters, and the number of second handling equipment in the first group of system configuration parameters is different from the first number of second handling equipment in the target configuration parameters. In addition, the number of first handling equipment in the third group of system configuration parameters may be different from both the first number of first handling equipment in the target configuration parameters and the number of first handling equipment in the first group of system configuration parameters; the number of second handling equipment in the third group of system configuration parameters may be different from both the second number of second handling equipment in the target configuration parameters and the number of second handling equipment in the first group of system configuration parameters.

[0089] In some embodiments, step 1320 includes: determining the warehouse type corresponding to the warehousing system based on the warehouse size; determining the quantity of each type of handling equipment in multiple sets of system configuration parameters through a preset similarity algorithm based on the warehouse type and the type of handling equipment in the target input information.

[0090] Exemplarily, after the storage type is determined in the manner of step 210, the quantity of each type of handling equipment in the multiple sets of system configuration parameters can be determined based on the warehouse type and the type of handling equipment by a preset similarity algorithm.

[0091] For example, in the preset similarity algorithm, different types of handling equipment correspond to different first change factors, wherein the first change factor may be an absolute value of the difference between the number of handling equipment in each group of system configuration parameters.

[0092] In some examples, the first change factor between the number of each type of handling equipment in the multiple sets of system configuration parameters can be determined based on the type of handling equipment. For example, the first change factor corresponding to different types of handling equipment can be different. The number of the multiple sets of system configuration parameters expanded by the similarity algorithm can be adjusted according to the needs.

[0093] Exemplarily, under different warehouse types, the first change factors corresponding to the same type of handling equipment in each group of system configuration parameters may be different.

[0094] For example, the first change factor corresponding to the first handling equipment in a large warehouse may be greater than the first change factor corresponding to the first handling equipment in a medium-sized warehouse, and the first change factor corresponding to the first handling equipment in a medium-sized warehouse may be greater than the first change factor corresponding to the first handling equipment in a small warehouse.

[0095] In some examples, after determining the first change factor corresponding to each type of handling equipment, the quantity of each type of handling equipment in other groups of system configuration parameters can be determined according to the first quantity of each type of handling equipment in the target configuration parameters and the first change factor corresponding to each type of handling equipment.

[0096] For example, taking the warehouse type as a large warehouse, the multiple groups of system configuration parameters include the first group of system configuration parameters to the fifth group of system configuration parameters, and the handling equipment type includes two types, namely, the first handling equipment and the second handling equipment. When it is determined that the first quantity of the first handling equipment in the target configuration parameters is 50, the first change factor of the first handling equipment is 5, the first quantity of the second handling equipment is 100, and the second change factor of the second handling equipment is 10, the system configuration parameters of each group can be obtained as follows: the number of the first handling equipment in the first group of system configuration parameters is 40, and the number of the second handling equipment is 80; the number of the first handling equipment in the second group of system configuration parameters is 45, and the number of the second handling equipment is 90; the number of the first handling equipment in the third group of system configuration parameters (i.e., the target configuration parameters) is 50, and the number of the second handling equipment is 100; the number of the first handling equipment in the fourth group of system configuration parameters is 55, and the number of the second handling equipment is 110; the number of the first handling equipment in the fifth group of system configuration parameters is 60, and the number of the second handling equipment is 120.

[0097] For another example, when the warehouse type is a medium-sized warehouse, the first change factor of the first handling equipment may be 3, and the second change factor of the second handling equipment may be 6.

[0098] Therefore, for different types of warehouses, the first variation factor between the same type of handling equipment is different. For the same warehouse type, the first variation factor between different types of handling equipment may be different.

[0099] Exemplarily, the second variation factor between the numbers of workstations in the multiple sets of system configuration parameters may be determined based on the warehouse type. Under different warehouse types, the second variation factor corresponding to the workstations in each set of system configuration parameters may be different. The second variation factor may be the absolute value of the difference between the numbers of workstations in each set of system configuration parameters.

[0100] For example, the second change factor corresponding to the workstation in a large warehouse may be greater than the second change factor corresponding to the workstation in a medium-sized warehouse, and the second change factor corresponding to the workstation in the medium-sized warehouse may be greater than the second change factor corresponding to the workstation in a small warehouse.

[0101] In some examples, after determining the second change factor corresponding to the workstation, the number of workstations in other groups of system configuration parameters may be determined according to the second number of workstations in the target configuration parameter and the second change factor corresponding to the workstation.

[0102] For example, taking the warehouse type as a medium-sized warehouse, and multiple groups of system configuration parameters including the first group of system configuration parameters to the fifth group of system configuration parameters as an example, when the number of workstations in the target configuration parameters is determined to be 10, and the second change factor corresponding to the workstation is 2, the number of workstations in the first group of system configuration parameters is 6, the number of workstations in the second group of system configuration parameters is 8, the number of workstations in the third group of system configuration parameters (i.e., the target configuration parameters) is 10, the number of workstations in the fourth group of system configuration parameters is 12, and the number of workstations in the fifth group of system configuration parameters is 14.

[0103] For another example, when the warehouse type is a large warehouse, the second change factor corresponding to the workstation may be 2, which is greater than the second change factor corresponding to the workstation in a medium-sized warehouse.

[0104] The efficiency prediction method of the warehousing system provided in the embodiment of the present application determines the number of each type of handling equipment and / or the number of workstations in multiple groups of system configuration parameters according to the differences in warehouse types and handling equipment types. Through the classification of types, the subsequent predicted efficiency of the warehousing system is more accurate.

[0105] Step 140 , processing multiple groups of system configuration parameters based on the target efficiency prediction model to obtain prediction efficiency indicators corresponding to each group of system configuration parameters.

[0106] In some embodiments, step 140 includes: processing each group of system configuration parameters in turn through the second prediction sub-model to determine the prediction efficiency index corresponding to each group of system configuration parameters.

[0107] Exemplarily, each group of predicted efficiency indicators includes at least one of workstation utilization, handling equipment utilization, task cycle time and number of carriers of the warehousing system, wherein the task cycle time may be the time required to complete an order line.

[0108] In some examples, after determining multiple sets of system configuration parameters, each set of system configuration parameters can be input into the second prediction sub-model in turn, and after being processed by the second prediction sub-model, the efficiency index corresponding to each set of system parameters is obtained. The second prediction sub-model is pre-trained and stored.

[0109] The efficiency prediction method of the warehousing system provided in the embodiment of the present application obtains the target input information by preprocessing the initial parameter information of the warehousing system; the target input information is input into the trained target efficiency prediction model, and after being processed by the target efficiency prediction model, multiple groups of system configuration parameters and the predicted efficiency index corresponding to each group of system configuration parameters are obtained, thereby realizing the efficiency prediction of the warehousing system. Compared with the efficiency prediction method in the related art, the efficiency prediction method of the warehousing system provided in the embodiment of the present application can realize the prediction of the efficiency index of the warehousing system under different system configuration parameters in advance before the warehousing system is deployed, and improve the accuracy of the efficiency prediction of the warehousing system, providing a reasonable basis for the subsequent deployment of the warehousing system. At the same time, since the present application can provide users with efficiency indexes corresponding to multiple groups of system configuration parameters, it provides users with more choices and comparisons. Users can compare and choose according to actual needs, which improves the user experience.

[0110] In some embodiments, the target efficiency prediction model may further include an optimization sub-model, wherein the optimization sub-model may be a fitting model, and the optimization sub-model may realize the conversion between the predicted value and the true value of the target efficiency prediction model.

[0111] In some embodiments, the above step 140 includes: processing each group of system configuration parameters in turn through the second prediction sub-model to determine the initial efficiency index corresponding to each group of system configuration parameters; optimizing each group of initial efficiency index through the optimization sub-model to obtain the predicted efficiency index corresponding to each group of system configuration parameters.

[0112] In some examples, the optimization sub-model can be pre-trained and stored in the warehouse planning system. For example, the optimization sub-model can be trained with multiple sets of predicted values ​​and multiple sets of true values ​​to obtain the relationship between the predicted values ​​and the true values.

[0113] For example, in an actual warehousing system, the efficiency index (i.e., predicted value) corresponding to each group of system configuration parameters of the warehousing system can be obtained through the above steps 110 to 140, and the actual efficiency index (true value) of the warehousing system can be determined, and the optimization sub-model can be trained with multiple predicted values ​​and multiple true values ​​as training samples. The trained optimization sub-model can convert the predicted efficiency index output by the target efficiency prediction model into a more reasonable true value, which is closer to the efficiency index in the actual scenario.

[0114] In some examples, after the initial efficiency index corresponding to each group of system configuration parameters is determined by the second prediction sub-model, each group of initial efficiency index can be fitted through the optimization sub-model to determine the predicted efficiency index corresponding to each group of system configuration parameters.

[0115] The efficiency prediction method for the warehousing system provided in the embodiment of the present application optimizes the prediction efficiency index output by the second prediction sub-model in the target efficiency prediction model by optimizing the sub-model, so that the result output by the target efficiency prediction model is more accurate and reasonable, and the accuracy of the efficiency prediction is further improved.

[0116] Figure 4 A schematic diagram of another method for predicting the efficiency of a storage system provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, after the above step 140, the method further includes the following steps:

[0117] Step 150, based on the prediction efficiency indicators corresponding to each group of system configuration parameters, determine the prediction results corresponding to the warehousing system, and control the user interaction interface to display the prediction results.

[0118] In some examples, the prediction result may be a predicted efficiency index corresponding to each group of system configuration parameters of the warehousing system displayed in a graphical form; or the prediction result may also be an initial deployment plan of the warehousing system determined based on the predicted efficiency index. For example, the initial deployment plan of the warehousing system may include the number of handling equipment, the number of workstations, and the number of carriers, etc. This embodiment of the application is not limited to this.

[0119] Figure 5 A schematic diagram of a user interaction interface provided in an embodiment of the present application, such as Figure 5 As shown, the user interaction interface 500 displays the prediction results of the warehousing system.

[0120] like Figure 5 As shown, the user interaction interface 500 can display the prediction results of the warehousing system (i.e., the prediction efficiency index corresponding to each group of system configuration parameters) in the form of a chart. For example, the chart above the user interaction interface 500 displays the efficiency indexes corresponding to four groups of system configuration parameters, namely, the utilization rate of the handling equipment, the utilization rate of the workstation, and the picking efficiency corresponding to the number of handling equipment and the number of workstations in each group. Among them, the number of handling equipment in each group of system configuration parameters is different, the number of workstations is the same, and the efficiency indexes corresponding to each group of system configuration parameters are different. Users can select the most appropriate efficiency index according to their needs, and continue to plan the warehousing plan according to the system configuration parameters corresponding to the efficiency index.

[0121] For example, the processing result of the subtask also includes the initial deployment plan of the warehousing system determined based on the predicted efficiency index. Figure 5 A deployment diagram of the warehousing system is shown below the user interaction interface 500.

[0122] Step 160: Obtain satisfaction information input by the user in the user interaction interface for the prediction result.

[0123] In some examples, after the user interaction interface is controlled to display the prediction result, a reminder message asking the user whether he is satisfied with the prediction result can also be displayed through the user interaction interface. The user can enter the corresponding satisfaction information in the user interaction interface according to actual needs.

[0124] For example, the satisfaction information can be a confirmed reply message of "satisfied" or "unsatisfied"; or, it can also be a satisfaction score, such as a satisfaction score of 0 (very unsatisfied) to 10 (very full score), and the user can select the satisfaction score according to the prediction result. The specific form of the satisfaction information is not limited in the embodiment of the present application.

[0125] It should be noted that further actions can be determined based on whether the satisfaction information meets preset conditions.

[0126] In some examples, the preset condition is used to indicate the condition for the user to be satisfied with the prediction result, and the preset condition can be determined according to the satisfaction information. For example, when the satisfaction information satisfies the preset condition, it indicates that the user is satisfied with the prediction result, and when the satisfaction information does not meet the preset condition, it indicates that the user is dissatisfied with the prediction result.

[0127] For example, when the satisfaction information is "satisfied" or "unsatisfied", the preset condition is that the user replies that he is satisfied. That is, when the satisfaction information input by the user for the prediction result is "satisfied", it indicates that the satisfaction information meets the preset condition; when the satisfaction information input by the user for the prediction result is "unsatisfied", it indicates that the satisfaction information does not meet the preset condition.

[0128] For another example, if the satisfaction information is a satisfaction score, the preset condition may be a score value, such as 8. That is, when the user's satisfaction score for the prediction result reaches 8 or more, it indicates that the satisfaction information meets the preset condition, and when the user's satisfaction score for the prediction result is less than 8, it indicates that the satisfaction information does not meet the preset condition.

[0129] Step 170: If the satisfaction information does not meet the preset conditions, the user interaction interface is controlled to display a prompt message, or multiple groups of system configuration parameters are re-determined.

[0130] Exemplarily, the prompt information is used to prompt the user to optimize the initial parameter information.

[0131] In some examples, if the satisfaction information does not meet the preset conditions, the user interaction interface can be controlled to display prompt information prompting the user to optimize the initial parameter information. For example, the prompt information can prompt the user to adjust the picking efficiency information in the initial parameters, or prompt the user to adjust the carrier size or the maximum load of the handling equipment. The embodiment of the present application is not limited to this, and the specific prompt information can be determined according to the actual situation.

[0132] In other examples, if the satisfaction information does not meet the preset conditions, multiple sets of system configuration parameters can be re-determined based on the target input information and the prediction similarity algorithm. In other words, the number of each type of handling equipment and / or the number of workstations in each set of system configuration parameters can be adjusted. After adjusting each set of system configuration parameters, the adjusted sets of system configuration parameters can be input into the second prediction sub-model in sequence, and the prediction efficiency index corresponding to each set of system configuration parameters can be re-determined.

[0133] Step 180: If the satisfaction information meets the preset conditions, the target efficiency prediction model is optimized based on the prediction efficiency index.

[0134] In some examples, if the satisfaction information meets preset conditions, the target input data and the prediction efficiency indicators corresponding to each group of configuration parameters determined based on the target input data can be saved and used for subsequent optimization and updating of the target efficiency prediction model, thereby improving the accuracy of the target efficiency prediction model.

[0135] The efficiency prediction method of the warehousing system provided in the embodiment of the present application obtains the user's satisfaction information on the prediction result, and determines whether the user is satisfied with the prediction result based on the satisfaction information and the preset conditions. If it is determined that the user is not satisfied with the prediction result, the efficiency of the warehousing system can be re-predicted according to the user's needs until the user is satisfied. If it is determined that the user is satisfied with the prediction result, the target efficiency prediction model can be optimized and updated according to the prediction efficiency index to improve the subsequent prediction accuracy.

[0136] In some examples, the embodiments of the present application also provide a model training method, by training the initial efficiency prediction model to obtain a trained target efficiency prediction model, and implementing the above steps 110 to 140 through the target efficiency prediction model to obtain the predicted efficiency indicators corresponding to each group of system configuration parameters of the warehousing system.

[0137] In some embodiments, the efficiency prediction method of the warehousing system further includes: obtaining multiple sample parameter information and a sample efficiency index set corresponding to each sample parameter information; wherein the sample efficiency index set includes sample efficiency indexes corresponding to each group of sample configuration parameters. The sample parameter information is processed based on the initial efficiency prediction model to obtain prediction efficiency indexes corresponding to each group of prediction configuration parameters; the prediction efficiency indexes corresponding to each group of prediction configuration parameters are used as the initial training output information of the initial efficiency prediction model, and the sample efficiency indexes corresponding to each group of sample configuration parameters are used as supervision information, and the initial efficiency prediction model is iterated to obtain the target efficiency prediction model.

[0138] In some examples, the training data of the initial efficiency prediction model includes multiple sample parameter information and sample efficiency indicator sets corresponding to each version of the parameter information. Each sample parameter information may be pre-processed information, that is, each sample parameter information may include warehouse size, handling equipment type, and carrier handling efficiency. The sample efficiency indicator set corresponding to each sample parameter information includes multiple groups of sample configuration parameters corresponding to each sample parameter information, and sample efficiency indicators corresponding to each group of sample configuration parameters.

[0139] For example, multiple sample parameter information and a sample efficiency indicator set corresponding to each sample parameter information can be obtained based on historical data.

[0140] In some examples, each sample parameter information in a plurality of sample parameter information is input into the initial efficiency prediction model, such as inputting the first sample parameter information into the initial efficiency prediction model, and obtaining a plurality of groups of first prediction configuration parameters corresponding to the first sample parameter information, and a first prediction efficiency index (such as called a predicted value) corresponding to each group of first prediction configuration parameters. The prediction efficiency index corresponding to each group of first prediction configuration parameters is used as the initial training output information of the initial efficiency prediction model, and the first sample efficiency index corresponding to the first sample parameter is set, and the first sample efficiency index (such as called an actual value) corresponding to each group of first sample configuration parameters is used as the supervision information of the initial efficiency prediction model, and the initial efficiency prediction model is iterated. After multiple iterations of the initial efficiency prediction model, the target efficiency prediction model is obtained.

[0141] For example, the training loss value can be determined based on the first prediction efficiency index corresponding to each group of first prediction configuration parameters and the first sample efficiency index corresponding to each group of first sample configuration parameters, and the initial efficiency prediction model can be iterated based on the loss value. The model obtained after multiple iterations until the preset iteration conditions are met is the target efficiency prediction model.

[0142] In some examples, the initial efficiency prediction model includes a first initial prediction sub-model and a second initial prediction sub-model. Training the initial efficiency prediction model includes training the first initial prediction sub-model and the second initial prediction sub-model.

[0143] The efficiency prediction method for a warehousing system provided in an embodiment of the present application trains an initial efficiency prediction model through multiple sample parameter information and a sample efficiency indicator set corresponding to each sample parameter information to obtain a target efficiency prediction model, which is then used to perform efficiency prediction of the warehousing system.

[0144] Figure 6 A schematic diagram of a warehouse planning system provided in an embodiment of the present application is shown in FIG. Figure 6As shown, the warehouse planning system 1 includes a front end 10 and a back end 20. The front end 10 may be a display end for displaying a user interface. The back end 20 may be a server end for performing information processing and controlling the front end 10 to display a corresponding user interface. It should be noted that steps 110 to 140 in the above embodiment may be implemented by the back end 20 in the warehouse planning system 1.

[0145] In some examples, the front end 10 and the back end 20 may be deployed on the same device or on different devices, which is not limited in the embodiments of the present application.

[0146] For example, the front end 10 and the back end 20 may both be deployed on a server or a terminal device; or, the front end 10 may be deployed on a terminal device, and the back end 20 may be deployed on a server. The terminal device may include at least one of a personal computer, a laptop, a smart phone, a tablet computer, and a portable wearable device; the server may include an independent server or a server cluster composed of multiple servers, which is not limited in the present embodiment.

[0147] Figure 7 A schematic diagram of another method for predicting the efficiency of a storage system provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the method further includes steps 710 to 740 as shown below. It should be noted that steps 710 to 720 can be performed before the above step 110, and step 730 includes the above step 110.

[0148] Step 710: Obtain the to-be-processed tasks input by the user in the user interaction interface.

[0149] In some examples, the front end 10 of the warehouse planning system 1 may display a user interaction interface, which may receive information input by the user and display information output by the back end, thereby realizing interaction between the user and the warehouse planning system 1. For example, the user interaction interface may be a GPT (Generative Pre-trained Transformer) interaction interface, which may include an interaction window, which may display information output by the back end 20 and information input by the user.

[0150] For example, Figure 6 As shown, the backend 20 of the warehouse planning system 1 may be deployed with a warehouse planning model 200. The warehouse planning model 200 may be pre-trained and stored in the backend 20, and the warehouse planning model 200 may include multiple sub-models. For example, the warehouse planning model 200 includes a task splitting sub-model 210 and a task execution sub-model 220.

[0151] In some examples, after the user inputs information through the user interaction interface, the input module 111 of the front end 10 can send the input information to the back end 20, and the back end 20 determines the input information as a task to be processed, or the back end 20 processes the input information and determines the task to be processed.

[0152] That is, the task to be processed may be user input information or processed input information. For example, the backend 20 may pre-process the user input information, such as performing data identification, data cleaning, data conversion, and data correction on the user input information in sequence, and then determine the task to be processed. For example, the task to be processed determined by the backend 20 may be "planning a warehousing plan."

[0153] Step 720: split the task to be processed by using the warehouse planning model to obtain at least one subtask.

[0154] For example, after determining the pending tasks, the pending tasks can be split through the warehouse planning model, and after splitting the pending tasks into at least one subtask, each subtask can be further analyzed and processed.

[0155] In some embodiments, Figure 6 As shown, after the tasks to be processed are obtained, the tasks to be processed can be split by the task splitting submodel 210 in the warehouse planning model 200.

[0156] Exemplarily, after obtaining the task to be processed, the task splitting sub-model 210 can first determine whether the task to be processed needs to be split. If the task to be processed does not need to be split, the task to be processed is sent to the task execution sub-model 220 for further processing; if the task to be processed needs to be split, after the task to be processed is split, the multiple sub-tasks after splitting are sent to the task execution sub-model 220 for further processing.

[0157] That is to say, the number of at least one subtask corresponding to the pending task can be one or more. When the number of at least one subtask is one, the subtask is a pending task. The embodiment of the present application takes the number of at least one subtask as more than one, that is, the task splitting submodel 210 splits the pending task to obtain multiple subtasks as an example for illustrative description.

[0158] In some embodiments, the above step 120 includes: based on the complexity of the task to be processed and a preset splitting principle, splitting the task to be processed into at least one subtask through a task splitting sub-model.

[0159] Exemplarily, the preset splitting principle includes that the number of tasks of at least one subtask is less than or equal to a preset number threshold and / or the correlation between any two subtasks in at least one subtask is less than or equal to a preset correlation threshold.

[0160] In some examples, if the task to be processed is relatively complex (i.e., the complexity of the task to be processed is relatively high), it is necessary to split the task to be processed; if the task to be processed is relatively simple (i.e., the complexity of the task to be processed is relatively low), it is not necessary to split the task to be processed. Among them, the complexity of the task to be processed can be used to indicate the complexity of completing the task to be processed. For example, the complexity of the task to be processed can be related to the amount and difficulty of parameter information required to be collected to perform the task to be processed. When the parameter information required to be collected to perform the task to be processed is large and complex, it can be determined that the complexity of the task to be processed is large; when the parameter information required to be collected for the task to be processed is small and simple, it can be determined that the complexity of the task to be processed is small.

[0161] In some examples, a preset complexity threshold may be set. After obtaining the task to be processed, the task splitting sub-model 210 may score the complexity of the task to be processed according to the amount and difficulty of parameter information required to collect for executing the task to be processed. When the complexity of the task to be processed is greater than the preset complexity threshold, the task to be processed may be split into multiple sub-tasks by the task splitting sub-model 210, and the complexity of each sub-task obtained after the splitting is less than or equal to the preset complexity threshold. When the complexity of the task to be processed is less than or equal to the preset complexity threshold, there is no need to perform splitting processing on the task to be processed.

[0162] For example, when the pending task is "design a warehousing plan", since the execution of this task requires the collection of a large amount of parameter information of the warehousing system, the pending task can be split. When the pending task is "what are the storage methods of the warehousing system", the pending task is relatively simple and may not require the collection of parameter information of the warehousing system. Therefore, there is no need to split the pending task.

[0163] For example, when it is determined that the task to be processed needs to be split according to the complexity of the task to be processed, the task to be processed can be further split according to a preset splitting principle. The preset splitting principle may include that the number of subtasks after splitting does not exceed a preset number threshold, and / or that similar or identical tasks are divided into the same subtask as much as possible.

[0164] That is, the number of subtasks after splitting cannot be too large, and / or the correlation between any two subtasks is small, such as smaller than a preset correlation threshold.

[0165] In some examples, the complexity of any subtask after splitting is relatively small, such as less than or equal to a preset complexity threshold.

[0166] Exemplarily, a preset task splitting library may be pre-set in the warehouse planning system, and the preset task splitting library stores the correspondence between multiple tasks to be split and the subtasks after splitting corresponding to each task to be split. After receiving the task to be processed, it can be determined whether there is a task to be processed in the preset task splitting library according to the task to be processed and the preset task splitting library. If there is a task to be processed in the preset task splitting library, at least one subtask matching the task to be processed is determined.

[0167] That is to say, the present application can also store the splitting situations corresponding to the planning results that satisfy the user based on the historical splitting experience, so that the corresponding subtasks can be directly obtained when the same or similar tasks to be processed are encountered in the future.

[0168] For example, the task to be processed can be split into two subtasks, namely the first subtask and the second subtask. It should be noted that the present embodiment of the application takes the splitting of the task to be processed into two subtasks as an example for illustrative description, and the task to be processed can also be split into a larger number of subtasks, which is not limited in the present embodiment of the application.

[0169] The efficiency prediction method of the warehousing system provided in the embodiment of the present application realizes the splitting processing of the tasks to be processed through the task splitting sub-model in the warehousing planning model, and splits the more complex tasks to be processed into multiple simple and easy-to-process sub-tasks, thereby facilitating further processing of subsequent task execution sub-models.

[0170] In some examples, the split multiple subtasks may include a first subtask. For example, the first subtask may be an efficiency prediction subtask, and the efficiency prediction subtask is used to determine an efficiency index corresponding to the warehousing system.

[0171] Step 730, analyze and process each subtask through the warehouse planning model to obtain at least one request information corresponding to each subtask, and control the user interaction interface to display each request information; in response to at least one feedback information input by the user for the at least one request information corresponding to each subtask, determine the processing result corresponding to each subtask through the warehouse planning model.

[0172] Exemplarily, step 730 includes: analyzing and processing each subtask through a warehouse planning model to obtain at least one request information corresponding to each subtask, and obtaining at least one feedback information input by a user for the at least one request information corresponding to each subtask.

[0173] In some examples, at least one subtask may include a first subtask, and the first subtask may be an efficiency prediction subtask. When the first subtask is an efficiency prediction subtask, the initial parameter information of the first subtask obtained in step 110 may include at least one feedback information corresponding to the first subtask obtained in step 730.

[0174] For example, the initial parameter information of the first subtask may be all feedback information corresponding to the first subtask, or may be part of the feedback information corresponding to the first subtask. This embodiment of the present application is not limited to this. That is, the embodiment of the present application may collect the initial parameter information required for the efficiency prediction subtask through multiple interactions.

[0175] In some embodiments, Figure 6 As shown, the warehouse planning model 200 includes a task execution sub-model 220. After the task splitting sub-model 210 splits the task to be processed into multiple sub-tasks, the multiple sub-tasks can be sent to the task execution sub-model 220 respectively, and the task execution sub-model 220 analyzes and processes each sub-task.

[0176] In some examples, after receiving multiple subtasks, the task execution sub-model 220 may determine the execution order of each of the multiple subtasks, and analyze and process each of the subtasks in sequence according to the order of each subtask.

[0177] In some examples, there may be mutual influence between the subtasks, that is, the processing result of the previous subtask (such as the first subtask) may affect the processing of the next adjacent subtask (such as the second subtask). For example, after the task execution submodel 220 determines the first processing result corresponding to the first subtask, it can analyze and process the second subtask based on the first subtask to determine the second processing result corresponding to the second subtask.

[0178] Combine the following Figure 8 , taking at least one subtask including a first subtask and a second subtask as an example, the analysis and processing process of each subtask (ie, the first subtask and the second subtask) by the task execution submodel 220 is explained.

[0179] Figure 8 A schematic diagram of another method for predicting the efficiency of a storage system provided in an embodiment of the present application. Figure 8 As shown, the above step 730 includes steps 7311 to 7315 as shown below.

[0180] Step 7311: Analyze and process the first subtask based on the task execution submodel, determine the first request information corresponding to the first subtask, and control the user interaction interface to display the first request information.

[0181] In some examples, after receiving the first subtask, the task execution submodel 220 may determine the first request information corresponding to the first subtask, wherein the request information corresponding to each subtask may be the project information or other information of the storage system required to be collected to solve each subtask.

[0182] For example, the request information may be at least one question information, and the project information of the storage system can be collected by the user answering the question information; or the request information may also be at least one reply information, and the reply information may be reply information to the question raised by the user. The specific form of the request information is not limited in the embodiments of the present application.

[0183] In some examples, each subtask may correspond to one request information or multiple request information. The number of request information corresponding to each subtask may be the same or different.

[0184] Exemplarily, after determining the request information corresponding to each subtask (such as the first subtask), the backend 20 can control the output module 112 of the frontend 10 to display each request information (such as the first request information) on the user interaction interface. For example, the first request information corresponding to the first subtask can be "How many meters are the length, width and height of your warehouse?".

[0185] Step 7312, in response to the first feedback information input by the user for the first request information corresponding to the first subtask, determine the second request information corresponding to the first subtask through the task execution submodel, and control the user interaction interface to display the second request information.

[0186] In some examples, after the user interaction interface displays the first request information, the user may input first feedback information in the user interaction interface to reply to the first request information.

[0187] For example, when the first request information is question information, the feedback information may be the user's reply information to the question information. When the first request information is reply information, the first feedback information may be question information or other question information to the reply information; or the feedback information may be other information. In other words, the feedback information may be different depending on the request information.

[0188] For example, when the first request information is "How long, wide and high are your warehouse? What storage method do you need? What type of business do you need?", the first feedback information can be the answer information "The length, width and height of the warehouse are 50, 60 and 4 respectively", or it can be the question information "What is the storage method".

[0189] Exemplarily, after obtaining the first feedback information, the task execution sub-model 220 can determine the second request information corresponding to the first sub-task according to the first feedback information. In other words, the second request information is determined based on the first feedback information, that is, the subsequent request information (i.e., the second request information) of the same sub-task is affected by the feedback information (i.e., the first feedback information) of the previous request information (i.e., the first request information).

[0190] In some examples, the second request information may be question information different from the first request information, or may be answer information to the first feedback information, which is not limited in this embodiment of the present application.

[0191] For example, when the first feedback information is "The length, width and height of the warehouse are 50, 60 and 4 respectively", the second request information may be "The units of the warehouse length, width and height you provided are not clear. Is the unit in meters?"; or, when the first feedback information is "What is the storage method", the second request information may be "The storage method refers to the storage unit in logistics warehousing, mainly including..." and other reply information to the storage method; or, the second request information may also be "Do you need to provide the type of business you need?" and other information.

[0192] That is, after obtaining the first feedback information input by the user for the first request information, the second request information can be generated according to the first feedback information, and the user interaction interface can be controlled to display the second request information.

[0193] Step 7313: In response to the second feedback information input by the user in response to the second request information, based on the first feedback information and the second feedback information, determine the first processing result corresponding to the first subtask through the task execution sub-model.

[0194] In some examples, after the backend 20 controls the user interaction interface to display the second request information, the user may continue to input second feedback information for the second request information through the user interaction interface.

[0195] For example, when the second request information may be "The units of the warehouse length, width and height you provided are not clear. Is the unit in meter?", the second feedback information may be "Yes"; when the second request information may be "The storage method refers to the storage unit in logistics warehousing, mainly including...", the second feedback information may be "Storage on shelves"; when the second request information may be "Do you need to provide the type of business you need? B2B, B2C or B2B&B2C", the second feedback information may be "B2B".

[0196] Exemplarily, after completing the information collection of the first subtask, there is no need to generate request information. The collected information of the first subtask includes first feedback information and second feedback information. That is, when the first subtask is an efficiency prediction subtask, the collected initial parameter information can be the first feedback information, or the second feedback information, or the first feedback information and the second feedback information. That is to say, the first feedback information and / or the second feedback information include the warehouse size, picking efficiency information and business demand information corresponding to the warehousing system.

[0197] Exemplarily, based on the first feedback information and the second feedback information, the first processing result corresponding to the first subtask is determined by the task execution submodel 220. That is, the processing result of each subtask can be determined according to all the feedback information corresponding to each subtask. After obtaining the first processing result of the first subtask, the user interaction interface can be controlled to display the first processing result.

[0198] For example, when the first subtask is an efficiency prediction subtask, the first processing result is the prediction result corresponding to the warehousing system (i.e., the prediction efficiency index corresponding to each group of system configuration parameters). Controlling the user interaction interface to display the first processing result includes controlling the user interaction interface to display the prediction result of the warehousing system.

[0199] In some examples, the first processing result corresponding to the first subtask may be summary information of the collected information (including the first feedback information and the second feedback information), so that the summary information can be displayed to the user for confirmation through the user interaction interface; or, the first processing result of the first subtask can also be displayed through the user interaction interface in a combination of text and graphics. For example, the first processing result may be related to the task objective of the first subtask. For example, when the task objective of the first subtask is to determine the efficiency index of the warehousing system (that is, the first subtask is an efficiency prediction subtask), the first processing result of the first subtask may be information generated based on the first feedback information and the second feedback information to display the efficiency prediction result of the warehousing system.

[0200] It should be noted that the process of determining the first processing result corresponding to the first subtask through the task execution sub-model 220 is described in detail in the following embodiments (such as steps 7321 to 7323).

[0201] In some examples, some of the multiple subtasks may not need to determine the corresponding processing results, which is not limited in the present embodiment. For example, the processing result corresponding to the subtask may also be the feedback information collected last time, or the processing result may also be all feedback information.

[0202] Step 7314, based on at least one feedback information corresponding to the first subtask, analyze and process the second subtask through the warehouse planning model, determine at least one request information corresponding to the second subtask, and control the user interaction interface to display at least one request information corresponding to the second subtask.

[0203] The second subtask is the next subtask of the first subtask.

[0204] In some examples, after obtaining the first processing result corresponding to the first subtask, the second subtask can be analyzed and processed based on at least one feedback information corresponding to the first subtask through the task execution submodel 220 to determine at least one request information corresponding to the second subtask. In other words, the task execution submodel 220 can determine the information collection of the second subtask based on the information collection of the first subtask.

[0205] In some embodiments, the above-mentioned step 7314 includes: analyzing and processing the second subtask through the task execution sub-model to obtain at least one request information corresponding to the second subtask; if there is feedback information corresponding to the third request information in at least one feedback information corresponding to the first subtask, and there is no feedback information corresponding to the fourth request information in at least one feedback information corresponding to the first subtask, then controlling the user interaction interface not to display the third request information and to display the fourth request information; if there is no feedback information corresponding to the third request information in at least one feedback information corresponding to the first subtask, then controlling the user interaction interface to display the third request information.

[0206] Exemplarily, the at least one request information corresponding to the second subtask may include third request information. After determining the third request information, the task execution submodel 220 may compare the third request information with the first request information and the second request information corresponding to the first subtask.

[0207] In some examples, if the third request information is the same as the first request information or the second request information, it indicates that the feedback information corresponding to the third request information is also the same as the first feedback information or the second feedback information. In this case, the first feedback information and the second feedback information corresponding to the first subtask include the feedback information corresponding to the third request information. In other words, the feedback information required for the third request information has been collected during the processing of the first subtask, so there is no need to collect it repeatedly. Therefore, there is no need to control the user interaction interface to display the third request.

[0208] It should be noted that the multiple request information involved in the present application is not necessarily the same as the multiple request information, but the multiple request information may also express the same meaning or the same requirements.

[0209] For example, when there is feedback information corresponding to the third request information in at least one feedback information corresponding to the first subtask, the fourth request information corresponding to the second subtask is further determined, and the fourth request is compared with at least one request information corresponding to the first subtask. The processing process of the fourth request information is similar to that of the third request, and will not be repeated here to avoid repetition.

[0210] In other examples, if the third request information is different from the first request information and the second request information, it indicates that the feedback information corresponding to the third request information may also be different from the first feedback information and the second feedback information. In this case, the first feedback information and the second feedback information corresponding to the first subtask may not include the feedback information corresponding to the third request information. Therefore, it is necessary to control the user interaction interface to display the third request to obtain the third feedback information corresponding to the third request information.

[0211] The efficiency prediction method for the warehousing system provided in the embodiment of the present application is such that when the information involved in the subsequent subtask (such as the second subtask) to be executed has been collected during the execution of the previous subtask (such as the first subtask), there is no need to collect it again and it can be used directly.

[0212] Step 7315: In response to at least one feedback information input by the user for at least one request information corresponding to the second subtask, determine a second processing result corresponding to the second subtask through the warehouse planning model.

[0213] For example, when it is determined that there is no feedback information corresponding to the fourth request information in the at least one feedback information corresponding to the first subtask, the user interaction interface is controlled to display the fourth request information, and feedback information (such as the fourth feedback information) input by the user for the fourth request information is received.

[0214] In some examples, after determining at least one piece of feedback information (such as all feedback information) corresponding to the second subtask, a second processing result corresponding to the second subtask is determined based on the at least one piece of feedback information. The at least one piece of feedback information corresponding to the second subtask includes feedback information corresponding to the third request information (such as obtained from at least one piece of feedback information corresponding to the first subtask) and feedback information corresponding to the fourth request information.

[0215] Step 740, based on the processing results corresponding to each subtask in at least one subtask, determine the planning results corresponding to the task to be processed through the warehouse planning model, and control the user interaction interface to display the planning results.

[0216] In some embodiments, based on the first processing result of the first subtask and the second processing result of the second subtask, the planning result corresponding to the task to be processed is determined through the task execution submodel in the warehouse planning model, and the user interaction interface is controlled to display the planning result.

[0217] In some examples, the planning result corresponding to the pending task may be the deployment and planning of the storage system corresponding to the pending task. For example, the planning result may be displayed in the form of simulation data, pictures, text, etc., which is not limited in the embodiments of the present application. The user can understand the specific deployment of the storage system in advance through the display of the planning results. When the user is not satisfied with the current deployment, the user can also adjust the project parameters to obtain new planning results.

[0218] The efficiency prediction method of the warehousing system provided in the embodiment of the present application is to split the acquired pending tasks into at least one subtask through a trained warehousing planning model, and then analyze and process each subtask to obtain at least one request information corresponding to each subtask, and the request information can be used to prompt the user to input the relevant project information of the warehousing system required to execute the pending tasks; after the user inputs the corresponding feedback information according to the request information, the warehousing planning model can determine the processing results of each subtask according to the acquired feedback information, and determine the planning results corresponding to the pending tasks according to the processing results of each subtask, and display the final planning results on the user interaction interface, thereby completing the planning of the warehousing system. The efficiency prediction method of the warehousing system provided in the present application can be realized by the warehousing planning model before deploying the warehousing system, through multiple interactions with users to collect the project information required for warehousing system planning, and provide users with instant warehousing planning solutions, and can also answer questions related to the warehousing system for users, improve the planning efficiency of the warehousing system, reduce the manpower cost of planning, and improve user experience.

[0219] The following is combined with Fig. 9 The process of determining the processing result corresponding to the subtask (such as the first subtask or the second subtask) through the task execution submodel is described.

[0220] Fig. 9 A schematic diagram of another method for predicting the efficiency of a storage system provided in an embodiment of the present application. Fig. 9 As shown, the above step 730 includes the following steps 7321 to 7323. It should be noted that the above steps 7313 and 7315 can be implemented by the following steps 7321 to 7323.

[0221] Step 7321, determine the task objectives and preset algorithm library of the subtask.

[0222] In some examples, after obtaining each subtask, the task execution submodel 220 can determine the task objectives of each subtask. For example, when at least one subtask includes a first subtask and a second subtask, if the first subtask is an efficiency prediction subtask, the task objective of the first subtask is to determine the efficiency index of the warehousing system, and the task objective of the second subtask can be to provide a planning scheme for the warehousing system. The result obtained by achieving the task objective of the subtask is the processing result corresponding to the subtask.

[0223] It should be noted that when the task to be processed is divided into multiple subtasks, the task objective of the last subtask to be executed may be to determine the planning scheme of the warehousing system, and the processing result of the last subtask is the planning result of the warehousing system.

[0224] In some examples, the backend of the warehouse planning system may store a preset algorithm library, which may include multiple algorithms. The algorithm may be a function or a pre-trained neural network model (such as the target efficiency prediction in the above embodiment). For example, the function may be a network search function, a code execution function, and a subtask submission function, etc., which is not limited in the embodiments of the present application.

[0225] Step 7322: Based on the task objective of the subtask, the preset algorithm library, and at least one piece of feedback information corresponding to the subtask, determine the task execution information corresponding to the subtask through the first execution network.

[0226] In some examples, after determining the task objective of the first subtask, a preset algorithm library may be obtained, and the task objective of the first subtask, the preset algorithm library, and at least one feedback information of the first subtask (such as the first feedback information and the second information) may be sent to the task execution submodel 220. The at least one feedback information of the first subtask may also be referred to as the collected information corresponding to the first subtask.

[0227] In some embodiments, Figure 6 As shown, the task execution sub-model 220 includes a first execution network 221 and a second execution network 222. The first execution network 221 is used to determine the task execution information corresponding to the sub-task according to the task target of the sub-task, the preset algorithm library, and at least one feedback information corresponding to the sub-task, and send the task execution information to the second execution network 222. The second execution network 222 executes the sub-task according to the task execution information determined by the first execution network 221, and determines the processing result of the sub-task.

[0228] Exemplarily, the task execution information is used to indicate a target execution method for achieving the task goal of the subtask. In other words, the task execution information is used to indicate that the task goal of the subtask is achieved through a target execution method. Among them, the target execution method includes calling at least one algorithm in a preset algorithm library. For example, among multiple subtasks, some subtasks can be achieved by calling one algorithm, and some subtasks may need to call multiple algorithms to be achieved. The algorithms called when achieving the task goals of each subtask can be the same or different, and the embodiments of the present application do not limit this.

[0229] It should be noted that the task goal of implementing the above subtasks is to determine the processing results of the subtasks.

[0230] In some examples, the first execution network 221 can determine that the task goal of the first subtask can be achieved by calling the target algorithm in the preset algorithm library, so as to obtain the first processing result, based on the task goal of the first subtask, the preset algorithm library, and at least one feedback information corresponding to the first subtask. In other words, the first execution network 221 can generate task execution information for calling the target algorithm to achieve the task goal, and send the task execution information to the second execution network 222.

[0231] For example, the preset algorithm library includes Algorithm 1 and Algorithm 2, wherein Algorithm 1 is a network search function, and Algorithm 2 is a trained efficiency prediction model (i.e., a target efficiency prediction model). The task execution information generated by the first execution network 221 may include: calling Algorithm 1 to determine "what is the storage method", or the task execution information generated by the first execution network 221 may also include: calling Algorithm 2 to predict the efficiency index of the warehousing system.

[0232] Step 7323: Based on the task execution information, determine the processing result corresponding to the subtask through the second execution network.

[0233] In some embodiments, step 1323 includes: based on the task execution information and at least one feedback information corresponding to the subtask, calling the target efficiency prediction model through the second execution network to generate a processing result corresponding to the subtask.

[0234] For example, after receiving the execution information of the first subtask, the second execution network 222 can call at least one algorithm in the preset algorithm library to achieve the task goal of the first subtask based on the task execution information and at least one feedback information corresponding to the first subtask, and obtain the first processing result corresponding to the first subtask.

[0235] In some examples, when the first subtask is an efficiency prediction subtask, the task objective of the first subtask is to predict the efficiency index of the warehousing system, and the target execution method is to call the target efficiency prediction model in the preset algorithm library. The first processing result includes multiple sets of prediction information, and the multiple sets of prediction information are used to indicate the efficiency indexes corresponding to multiple sets of system configuration parameters in the warehousing system.

[0236] The planning method of the warehousing system provided in the embodiment of the present application further determines the processing result corresponding to each subtask by setting a preset algorithm library and collecting feedback information of each subtask and the preset algorithm library. Different algorithms are used for different subtasks to improve execution efficiency.

[0237] In some embodiments, the warehouse planning model also includes a task correction sub-model.

[0238] In some embodiments, after the above-mentioned step 730, the efficiency prediction method of the warehousing system also includes: if the first processing result corresponding to the first subtask cannot be determined through the task execution submodel, or if the first processing result corresponding to the first subtask is determined to be abnormal through the task execution submodel, then the first subtask is optimized through the task correction submodel to obtain the optimized first subtask.

[0239] Exemplarily, the optimization process includes further splitting the first subtask, or adjusting the first subtask to redetermine at least one request information corresponding to the optimized first subtask through the task execution submodel.

[0240] In some examples, the task correction sub-model in the warehouse planning model is used to optimize the sub-tasks (such as the first sub-task) whose processing results cannot be determined by the task execution sub-model, and resend the optimized first sub-task to the task execution sub-model for re-processing by the task execution sub-model. The process of re-analyzing and processing the optimized first sub-task by the task execution sub-model is similar to the process of determining the first sub-task in the above embodiment (such as steps 1311 to 1313), and will not be repeated here to avoid repetition.

[0241] In some embodiments, if the confirmation information entered by the user on the user interaction interface for the first processing result does not meet the end trigger condition corresponding to the first subtask, it is determined that there is an abnormality in the first processing result; or, if the number of abnormal information entered by the user on the user interaction interface for the first processing result exceeds a preset number threshold, it is determined that there is an abnormality in the first processing result.

[0242] In some embodiments, if the confirmation information input by the user on the user interaction interface for the first processing result corresponding to the first subtask meets the end trigger condition corresponding to the first subtask, the second subtask continues to be analyzed and processed through the warehouse planning model.

[0243] In some examples, each subtask (such as the first subtask) corresponds to an end trigger condition, and when the user interaction interface displays the first processing result of the first subtask, the user can enter confirmation information for the first processing result in the user interaction interface. The confirmation information for the first processing result can be used to indicate that the user approves the first processing result, or does not approve the first processing result.

[0244] For example, when the confirmation information input by the user meets the end trigger condition of the first subtask, it indicates that the user approves the first processing result; when the confirmation information input by the user does not meet the end trigger condition of the first subtask, it indicates that the user does not approve the first processing result. When the user does not approve the first processing result, it indicates that there is an abnormality in the first processing result, and the first subtask needs to be optimized through the task correction submodel.

[0245] For example, after the user interaction interface displays the first processing result, the user can be asked whether he is satisfied with the first processing result. If the user enters affirmative expression information such as satisfaction, the end trigger condition corresponding to the first subtask is met, and the task execution submodel continues to execute the second subtask; if the user enters negative expression information such as dissatisfaction, the first subtask is sent to the task correction submodel for optimization processing.

[0246] In other examples, when the user interaction interface displays the first processing result of the first subtask, the user enters exception information for the first processing result in the user interaction interface, and the number of consecutive inputs of the exception information exceeds a preset threshold, it can also be determined that there is an exception in the first processing result.

[0247] For example, when the user interaction interface displays the first processing result and asks the user whether he is satisfied with the first processing result, if the user successively enters three abnormal information unrelated to the first processing result, such as "the weather is very good today", "I have eaten" and "I don't know", then it is considered that there is an abnormality in the first processing result, and the first subtask can be sent to the task correction submodel for optimization processing.

[0248] The efficiency prediction method of the warehousing system provided in the embodiment of the present application adds a task correction sub-model to the warehousing planning model. After determining the processing results of each sub-task, it can be determined whether the confirmation information of the processing result by the user meets the end trigger condition of the sub-task, and whether the sub-task needs to be optimized. When the user is not satisfied with the processing result, the task correction sub-model can be used to optimize the sub-task in time until a processing result satisfactory to the user is obtained, thereby improving the user's satisfaction.

[0249] In some embodiments, the warehouse planning model also includes a result validation sub-model.

[0250] In some embodiments, after the above-mentioned step 730, the efficiency prediction method of the warehousing system also includes: based on at least one feedback information corresponding to the first subtask, verifying the first processing result corresponding to the first subtask through a result verification submodel to obtain a verification result; if the verification result is abnormal, re-analyzing and processing the first subtask through the task execution submodel, and re-determining the processing result corresponding to the first subtask.

[0251] In some examples, after determining the first processing result corresponding to the first subtask, the task execution submodel may further verify the first processing result through the result verification submodel to ensure the accuracy of the first processing result.

[0252] For example, when the verification result of the result verification sub-model for the first processing result is normal, the user interaction interface can be controlled to display the first processing result; when the verification result of the result verification sub-model for the first processing result is abnormal, the first subtask is re-analyzed and processed through the task execution sub-model, and the processing result corresponding to the first subtask is re-determined.

[0253] In some examples, the task execution sub-model may send at least one feedback information corresponding to the first sub-task (i.e., the collected information corresponding to the first sub-task) and the first processing result to the result verification sub-model, and the result verification sub-model redetermines the processing result of the first sub-task based on the at least one feedback information. If the redetermined processing result is the same as the first processing result, the verification result is determined to be normal; if the redetermined processing result is different from the first processing result, the verification result is determined to be abnormal.

[0254] The efficiency prediction method of the warehousing system provided in the embodiment of the present application can perform a second verification on the processing results corresponding to each subtask by adding a result verification submodel in the warehousing planning model, thereby ensuring the accuracy of the processing results corresponding to each subtask and further improving user satisfaction.

[0255] In some embodiments, the user interaction interface corresponding to the warehouse planning system includes a progress bar.

[0256] Fig.10 A schematic diagram of another user interaction interface provided in an embodiment of the present application. Fig.10 As shown in (a) in FIG. 1 , the user interaction interface a may include multiple windows, such as three windows, which may be an interaction window 1010 , an information input window 1020 , and a progress bar window 1030 .

[0257] like Fig.10 As shown in (a) of FIG. 1 , the interactive window 1010 is used to realize the interaction between the warehouse planning system and the user, that is, the interactive window 1010 is used to display the request information corresponding to each subtask, and the feedback information input by the user for the request information. The request information and the feedback information can be displayed in the form of a dialogue. For example, the user can input the task to be processed or the feedback information for the request information through the information input window 1020.

[0258] In some examples, the progress bar window 1030 includes a progress bar, which is used to display the completion of the task to be processed. The completion of the task to be processed can be determined by the completion of each subtask in the multiple subtasks. The progress bar window 730 can clearly show the user the completion of the task, further improving the user experience.

[0259] In some embodiments, the efficiency prediction method of the warehousing system also includes: determining the progress information of each subtask in response to at least one feedback information input by the user for at least one request information corresponding to each subtask; and displaying the task completion degree of the task to be processed through a progress bar based on the progress information of each subtask.

[0260] In some examples, the task to be processed can be divided into multiple subtasks, and the backend executes each subtask in sequence. When a subtask is completed, the display of the progress bar of the user interaction interface can be controlled. Alternatively, when multiple feedback information needs to be collected during the execution of each subtask, the backend can control the display of the progress bar of the user interaction interface when a feedback information of each subtask is obtained.

[0261] For example, taking the task to be processed as being divided into the first subtask, the second subtask, the third subtask and the fourth subtask, if the backend processes each subtask in sequence, after determining the first processing result corresponding to the first subtask and after the user confirms the first processing result, the display of the progress bar can be adjusted, such as adjusting the display of the progress bar to 25% (such as Fig.10 After the fourth subtask is completed, that is, when the planning result corresponding to the final task to be processed is obtained, the progress bar can be adjusted to 100% (as shown in (a)). Fig.10 , as shown in (b) in the figure).

[0262] For another example, a task to be processed is divided into a first subtask and a second subtask, wherein the first subtask may include a first request information and a second request information, and the second subtask includes a third request information and a fourth request information. When the user inputs the first feedback information for the first request information in the user interaction interface, and the backend generates the second request information, the display of the progress bar can be adjusted, such as adjusting the display of the progress bar to 25%; after obtaining the fourth feedback information corresponding to the second subtask, the display of the progress bar can be adjusted to 100%. It should be noted that when the last feedback information of the last subtask is obtained, it indicates that all information for implementing the task to be processed has been collected. In this case, the display of the progress bar can also be adjusted to 100%.

[0263] The efficiency prediction method of the warehousing system provided in the embodiment of the present application sets a progress bar on the user interaction interface, which can provide a more intuitive display of the execution status of the tasks to be processed, thereby facilitating the user to more clearly understand the completion degree of the tasks to be processed and improving the user experience.

[0264] In some embodiments, the user interaction interface includes a feedback window.

[0265] In some embodiments, after the above step 740, the efficiency prediction method of the warehousing system also includes: obtaining at least one question and answer information regarding the planning results input by the user in the interactive window; processing at least one question and answer information through the warehousing planning model, and controlling the feedback window to display the results corresponding to the question and answer information.

[0266] In some examples, when a planning result of a warehousing system is determined and the planning result is displayed on a user interaction interface, the user interaction interface may include a result display window and a feedback window.

[0267] For example, the result display window can display the planning results, and the feedback window is used to receive the user's question and answer information regarding the feedback results. The question and answer information may include the user's satisfaction information regarding the planning results, and may also include the user's consultation information regarding the planning results. For example, when the user is not satisfied with the planning results, the user may input the corresponding requirements, and the warehouse planning model may redeploy the planning scheme of the warehouse system according to the user's input requirements.

[0268] Fig.11 A schematic diagram of another user interaction interface provided in an embodiment of the present application is shown as follows: Fig.11 As shown, an assistant control can be set on the user interaction interface 1100 of the planning results. The user can trigger the assistant control to open the feedback window and enter question and answer information in the feedback window. The backend outputs corresponding result information based on the question and answer information.

[0269] The efficiency prediction method for the warehousing system provided in the embodiment of the present application can receive user satisfaction information, suggestion information and other needs corresponding to the final planning results by setting a feedback window on the user interaction interface, so as to provide users with more appropriate planning solutions and further improve user experience.

[0270] Fig.12 A schematic diagram of an efficiency prediction device for a warehousing system provided in an embodiment of the present application is shown in FIG. Fig.12 As shown, the efficiency prediction device 1200 of the warehousing system includes an acquisition module 1210, a determination module 1220 and a processing module 1230. Among them:

[0271] The acquisition module 1210 is configured to: acquire initial parameter information of the warehousing system; wherein the initial parameter information includes warehouse size, picking efficiency information and business demand information corresponding to the warehousing system.

[0272] The determination module 1220 is configured to: pre-process the initial parameter information and determine the target input information.

[0273] The processing module 1230 is configured to: process the target input information based on the target efficiency prediction model to obtain multiple groups of system configuration parameters of the warehousing system; wherein each group of system configuration parameters includes the number of handling equipment and / or the number of workstations; process the multiple groups of system configuration parameters based on the target efficiency prediction model to obtain prediction efficiency indicators corresponding to each group of system configuration parameters; wherein each group of prediction efficiency indicators includes at least one of the workstation utilization rate, handling equipment utilization rate, task cycle time and number of carriers of the warehousing system.

[0274] In some embodiments, the determination module 1220 is configured to: perform convergence processing on the warehouse size, picking efficiency information and the business demand information through a preset algorithm to obtain the handling equipment type and vehicle handling efficiency corresponding to the warehousing system; wherein, the target input information includes the warehouse size, handling equipment type and vehicle handling efficiency, and the vehicle handling efficiency includes the number of vehicle handling times and the vehicle dwelling time.

[0275] In some embodiments, the determination module 1220 is further configured to: determine the warehouse type corresponding to the warehousing system based on the warehouse size; determine the target efficiency prediction model corresponding to the target input information based on the warehouse type; wherein different warehouse types correspond to different target efficiency prediction models.

[0276] In some embodiments, the target efficiency prediction model includes a first prediction sub-model; the processing module 1230 is configured to: process the target input information based on the first prediction sub-model to obtain the target configuration parameters of the warehousing system; wherein the target configuration parameters include the first number of various types of handling equipment and / or the second number of workstations. The target configuration parameters are processed for similarity by a preset similarity algorithm to obtain the multiple sets of system configuration parameters of the warehousing system; wherein the multiple sets of system configuration parameters include the target configuration parameters, and the number of various types of handling equipment in each set of system configuration parameters other than the target configuration parameters in the multiple sets of system configuration parameters is different from the corresponding first number, and / or the number of workstations is different from the second number.

[0277] In some embodiments, the processing module 1230 is configured to: determine the warehouse type corresponding to the warehousing system based on the warehouse size; determine the number of each type of handling equipment in multiple sets of system configuration parameters through a preset similarity algorithm based on the warehouse type and the type of handling equipment in the target input information.

[0278] In some embodiments, the target efficiency prediction model includes a second prediction sub-model; the processing module 1230 is configured to: process each group of system configuration parameters in turn through the second prediction sub-model to determine the prediction efficiency index corresponding to each group of system configuration parameters.

[0279] In some embodiments, the target efficiency prediction model includes a second prediction sub-model and an optimization sub-model; the processing module 1230 is configured to: process each group of system configuration parameters in turn through the second prediction sub-model to determine the initial efficiency index corresponding to each group of system configuration parameters; optimize each group of initial efficiency indicators through the optimization sub-model to obtain the prediction efficiency index corresponding to each group of system configuration parameters.

[0280] In some embodiments, the efficiency prediction device 1200 of the warehousing system also includes a control module and an optimization module; the determination module 1220 is also configured to: determine the prediction result corresponding to the warehousing system based on the prediction efficiency index corresponding to each group of system configuration parameters. The acquisition module 1210 is also configured to: obtain the satisfaction information input by the user in the user interaction interface for the prediction result. The control module is configured to: control the user interaction interface to display the prediction result, and if the satisfaction information does not meet the preset conditions, control the user interaction interface to display prompt information. The determination module is also configured to: if the satisfaction information does not meet the preset conditions, re-determine multiple groups of system configuration parameters; wherein the prompt information is used to prompt the user to optimize the initial parameter information. The optimization module is configured to: if the satisfaction information meets the preset conditions, optimize the target efficiency prediction model based on the prediction efficiency index.

[0281] In some embodiments, the efficiency prediction device 1200 of the warehousing system also includes a training module; the acquisition module 1210 is also configured to: obtain multiple sample parameter information, and a sample efficiency index set corresponding to each sample parameter information; wherein the sample efficiency index set includes sample efficiency indicators corresponding to each group of sample configuration parameters. The processing module 1230 is also configured to: process the sample parameter information based on the initial efficiency prediction model to obtain the prediction efficiency indicators corresponding to each group of prediction configuration parameters. The training module is configured to: use the prediction efficiency indicators corresponding to each group of prediction configuration parameters as the initial training output information of the initial efficiency prediction model, and the sample efficiency indicators corresponding to each group of sample configuration parameters as the supervision information, iterate the initial efficiency prediction model, and obtain the target efficiency prediction model.

[0282] In some embodiments, the acquisition module 1210 is configured to: acquire the pending tasks input by the user in the user interaction interface; split the pending tasks through the warehouse planning model to obtain at least one subtask; wherein at least one subtask includes an efficiency prediction subtask. The processing module 1230 is configured to: analyze and process each subtask through the warehouse planning model to obtain at least one request information corresponding to each subtask. The control module is configured to: control the user interaction interface to display each request information. The acquisition module 1210 is configured to: acquire at least one feedback information input by the user for at least one request information corresponding to each subtask; wherein the initial parameter information includes at least one feedback information corresponding to the efficiency prediction subtask.

[0283] In some embodiments, the determination module 1220 is further configured to: determine the processing result corresponding to each subtask through the warehouse planning model based on at least one feedback information inputted by at least one request information corresponding to each subtask; determine the planning result corresponding to the task to be processed through the warehouse planning model based on the processing result corresponding to each subtask in at least one subtask. The control module is further configured to: control the user interaction interface to display the planning result.

[0284] In some embodiments, the warehouse planning model includes a task splitting sub-model; the processing module 1230 is configured to: based on the complexity of the task to be processed and the preset splitting principle, split the task to be processed into at least one sub-task through the task splitting sub-model; wherein the preset splitting principle includes that the number of tasks of at least one sub-task is less than or equal to a preset number threshold and / or the correlation between any two sub-tasks in at least one sub-task is less than or equal to a preset correlation threshold.

[0285] In some embodiments, the user interaction interface includes a progress bar; the determination module 1220 is also configured to: determine the progress information of each subtask in response to at least one feedback information input by the user for at least one request information corresponding to each subtask; and based on the progress information of each subtask, display the task completion degree of the task to be processed through a progress bar.

[0286] In some embodiments, the user interaction interface includes a feedback window; the acquisition module 1210 is further configured to: acquire at least one question and answer information input by the user in the feedback window for the planning result. The processing module 1230 is further configured to: process the at least one question and answer information through the warehouse planning model. The control module is further configured to: control the feedback window to display the interaction result corresponding to the question and answer information.

[0287] Fig.13 A schematic diagram of an electronic device provided in an embodiment of the present application. In some embodiments, the electronic device includes one or more processors and a memory. The memory is configured to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the efficiency prediction method of the warehousing system in the above embodiment.

[0288] like Fig.13 As shown, the electronic device 1000 includes: a processor (processor) 1001 and a memory 1002. Exemplarily, the electronic device 1000 may also include: a communication interface (Communications Interface) 1003 and a communication bus 1004.

[0289] The processor 1001, the memory 1002 and the communication interface 1003 communicate with each other via the communication bus 1004. The communication interface 1003 is used to communicate with other devices such as client or other server network elements.

[0290] In some embodiments, the processor 1001 is used to execute the program 1005, and specifically can execute the relevant steps in the above-mentioned storage system efficiency prediction method embodiment. Specifically, the program 1005 can include program code, and the program code includes computer executable instructions.

[0291] Exemplarily, the processor 1001 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The electronic device 1000 may include one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0292] In some embodiments, the memory 1002 is used to store the program 1005. The memory 1002 may include a high-speed RAM memory, and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0293] Program 1005 can be specifically called by processor 1001 to enable electronic device 1000 to execute the operation of the efficiency prediction method of the warehousing system.

[0294] An embodiment of the present application provides a computer-readable storage medium, which stores at least one executable instruction. When the executable instruction is executed on the electronic device 1000, the electronic device 1000 executes the efficiency prediction method of the warehousing system in the above embodiment.

[0295] The executable instructions can be specifically used to enable the electronic device 1000 to execute the operations of the efficiency prediction method for the warehousing system.

[0296] For example, the computer readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0297] In some embodiments, an embodiment of the present application provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the efficiency prediction method for the warehousing system described in any of the above embodiments.

[0298] In some embodiments, the embodiments of the present application further provide a computer program, which, when executed by a processor, can implement the efficiency prediction method for the warehousing system described in any of the above embodiments.

[0299] The beneficial effects that can be achieved by the efficiency prediction device, electronic device, computer-readable storage medium, computer program product and computer program for the warehousing system provided in the embodiments of the present application can be referred to the beneficial effects of the efficiency prediction method for the warehousing system provided above, and will not be repeated here.

[0300] It should be noted that, in the application, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0301] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0302] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0303] For the purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by an instruction execution system, apparatus, or device or in conjunction with such instruction execution system, apparatus, or device.

[0304] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection having one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM).

[0305] In addition, the computer readable medium can even be a paper or other suitable medium on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, and then editing, interpreting or processing in other suitable ways as necessary, and then storing it in the computer memory. It should be understood that various parts of the present application can be implemented in hardware, software, firmware or a combination thereof.

[0306] In the above embodiments, multiple steps or methods may be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it may be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0307] The above-described embodiments of the present application do not constitute a limitation on the protection scope of the present application.

Claims

1. A method for predicting the efficiency of a warehousing system, characterized in that: The method comprises: Acquire initial parameter information of the warehousing system; wherein the initial parameter information includes warehouse size, picking efficiency information and business demand information corresponding to the warehousing system; Preprocessing the initial parameter information to determine target input information; The target input information is processed based on the target efficiency prediction model to obtain multiple groups of system configuration parameters of the warehousing system; wherein each group of system configuration parameters includes the number of handling equipment and / or the number of workstations; The multiple groups of system configuration parameters are processed based on the target efficiency prediction model to obtain prediction efficiency indicators corresponding to each group of system configuration parameters; wherein each group of prediction efficiency indicators includes at least one of the workstation utilization rate, handling equipment utilization rate, task cycle time and number of vehicles of the warehousing system.

2. The method according to claim 1, characterized in that The preprocessing of the initial parameter information to determine the target input information includes: The warehouse size, the picking efficiency information and the business demand information are converged through a preset algorithm to obtain the handling equipment type and the carrier handling efficiency corresponding to the warehousing system; wherein the target input information includes the warehouse size, the handling equipment type and the carrier handling efficiency, and the carrier handling efficiency includes the number of carrier handling times and the carrier dwell time.

3. The method according to claim 1, characterized in that Before the target input information is processed based on the target efficiency prediction model to obtain multiple groups of system configuration parameters of the warehousing system, the method further includes: Based on the warehouse size, determining the warehouse type corresponding to the warehousing system; Based on the warehouse type, the target efficiency prediction model corresponding to the target input information is determined; wherein different warehouse types correspond to different target efficiency prediction models.

4. The method according to claim 1, characterized in that: The target efficiency prediction model includes a first prediction sub-model, and the target input information is processed based on the target efficiency prediction model to obtain multiple groups of system configuration parameters of the warehousing system, including: Processing the target input information based on the first prediction sub-model to obtain target configuration parameters of the warehousing system; wherein the target configuration parameters include a first number of various types of handling equipment and / or a second number of workstations; The target configuration parameters are processed for similarity by a preset similarity algorithm to obtain the multiple groups of system configuration parameters of the warehousing system; wherein the multiple groups of system configuration parameters include the target configuration parameters, and the number of each type of handling equipment in each group of system configuration parameters other than the target configuration parameters in the multiple groups of system configuration parameters is different from the corresponding first number, and / or the number of workstations is different from the second number.

5. The method according to claim 4, characterized in that The performing similarity processing on the target configuration parameters by using a preset similarity algorithm to obtain the multiple groups of system configuration parameters of the storage system includes: Based on the warehouse size, determining the warehouse type corresponding to the warehousing system; Based on the warehouse type and the type of handling equipment in the target input information, the quantity of each type of handling equipment in the multiple groups of system configuration parameters is determined by the preset similarity algorithm.

6. The method according to claim 1, characterized in that The target efficiency prediction model includes a second prediction sub-model, and the multiple groups of system configuration parameters are processed based on the target efficiency prediction model to obtain prediction efficiency indicators corresponding to each group of system configuration parameters, including: Each group of system configuration parameters is processed in turn through the second prediction sub-model to determine the prediction efficiency index corresponding to each group of system configuration parameters.

7. The method according to claim 1, characterized in that The target efficiency prediction model includes a second prediction sub-model and an optimization sub-model; the multiple groups of system configuration parameters are processed based on the target efficiency prediction model to obtain prediction efficiency indicators corresponding to each group of system configuration parameters, including: Processing each group of system configuration parameters in turn through the second prediction sub-model to determine an initial efficiency index corresponding to each group of system configuration parameters; Each group of initial efficiency indicators is optimized through the optimization sub-model to obtain the predicted efficiency indicators corresponding to each group of system configuration parameters.

8. The method according to any one of claims 1 to 7, characterized in that After the plurality of groups of system configuration parameters are processed based on the target efficiency prediction model to obtain prediction efficiency indicators corresponding to each group of system configuration parameters, the method further includes: Based on the prediction efficiency indicators corresponding to each group of system configuration parameters, determine the prediction results corresponding to the warehousing system, and control the user interaction interface to display the prediction results; Obtaining satisfaction information input by a user on the user interaction interface for the prediction result; If the satisfaction information does not meet the preset conditions, the user interaction interface is controlled to display prompt information, or multiple sets of system configuration parameters are re-determined; wherein the prompt information is used to prompt the user to optimize the initial parameter information; If the satisfaction information meets the preset conditions, the target efficiency prediction model is optimized based on the prediction efficiency index.

9. The method according to any one of claims 1 to 7, further comprising: Acquire multiple sample parameter information and a sample efficiency indicator set corresponding to each of the sample parameter information, wherein the sample efficiency indicator set includes sample efficiency indicators corresponding to each group of sample configuration parameters; Processing the sample parameter information based on the initial efficiency prediction model to obtain prediction efficiency indicators corresponding to each group of prediction configuration parameters; The prediction efficiency indicators corresponding to the respective groups of prediction configuration parameters are used as the initial training output information of the initial efficiency prediction model, and the sample efficiency indicators corresponding to the respective groups of sample configuration parameters are used as supervision information, and the initial efficiency prediction model is iterated to obtain the target efficiency prediction model.

10. The method according to any one of claims 1 to 7, characterized in that The obtaining of initial parameter information of the storage system includes: Obtaining a task to be processed input by a user in the user interaction interface; Splitting the to-be-processed task through a warehouse planning model to obtain at least one subtask; wherein the at least one subtask includes an efficiency prediction subtask; Analyzing and processing each of the subtasks through the warehouse planning model to obtain at least one request information corresponding to each of the subtasks, and controlling the user interaction interface to display each of the request information; Acquire at least one feedback information input by the user for the at least one request information corresponding to each of the subtasks; wherein the initial parameter information includes at least one feedback information corresponding to the efficiency prediction subtask.

11. The method according to claim 10, characterized in that The method further comprises: Based on at least one feedback information inputted from at least one request information corresponding to each of the subtasks, determining a processing result corresponding to each of the subtasks through the warehouse planning model; Based on the processing results corresponding to each of the at least one subtask, the planning results corresponding to the task to be processed are determined through the warehouse planning model, and the user interaction interface is controlled to display the planning results.

12. The method according to claim 10, characterized in that The warehouse planning model includes a task splitting sub-model, and the warehouse planning model is used to split the task to be processed to obtain at least one sub-task, including: Based on the complexity of the task to be processed and a preset splitting principle, splitting the task to be processed into the at least one subtask through the task splitting submodel; The preset splitting principle includes that the number of tasks of the at least one subtask is less than or equal to a preset number threshold and / or the correlation between any two subtasks in the at least one subtask is less than or equal to a preset correlation threshold.

13. The method according to claim 10, characterized in that The user interaction interface includes a progress bar; the method further includes: In response to at least one feedback information input by a user for at least one request information corresponding to each of the subtasks, determining progress information of each of the subtasks; Based on the progress information of each of the subtasks, the task completion degree of the task to be processed is displayed through the progress bar.

14. The method according to claim 10, characterized in that The user interaction interface includes a feedback window, and the method further includes: Acquire at least one question and answer information regarding the planning result input by the user in the feedback window; The at least one question and answer information is processed through the warehouse planning model, and the feedback window is controlled to display the interaction result corresponding to the question and answer information.

15. An efficiency prediction device for a warehousing system, characterized in that: include: The acquisition module is configured to: acquire initial parameter information of the warehousing system; wherein the initial parameter information includes warehouse size, picking efficiency information and business demand information corresponding to the warehousing system; A determination module is configured to: pre-process the initial parameter information to determine target input information; The processing module is configured to: process the target input information based on the target efficiency prediction model to obtain multiple groups of system configuration parameters of the warehousing system; wherein each group of the system configuration parameters includes the number of handling equipment and / or the number of workstations; process the multiple groups of system configuration parameters based on the target efficiency prediction model to obtain prediction efficiency indicators corresponding to each group of system configuration parameters; wherein each group of the prediction efficiency indicators includes at least one of the workstation utilization rate, handling equipment utilization rate, task cycle time and number of vehicles of the warehousing system.

16. An electronic device, characterized in that: include: one or more processors and memory; The memory is configured to: store one or more programs; Wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the efficiency prediction method for the warehousing system according to any one of claims 1-14.

17. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the efficiency prediction method for a warehousing system according to any one of claims 1-14 is implemented.

18. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the efficiency prediction method for a warehousing system according to any one of claims 1-14.

Images