Intelligent warehouse deployment scheme generation method and device and electronic equipment

Abstract

The invention discloses an intelligent warehouse deployment scheme generation method and device and electronic equipment, and the method comprises the steps: obtaining project basic information which comprises target demand information and target warehouse information; a pre-trained scheme generation model is obtained, the scheme generation model is a generative large model, and the scheme generation model comprises an input layer, an optimization layer and an output layer; the target demand information and the target warehouse information are input into a scheme generation model through an input layer, a target deployment scheme is obtained through processing of an optimization layer, and the target deployment scheme at least comprises goods shelf distribution information and intelligent robot configuration information; and outputting a target deployment scheme through an output layer of the scheme generation model. According to the invention, the intelligent storage deployment scheme generation intelligence and generation efficiency can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent warehousing, in particular to an intelligent warehousing deployment scheme generation method and device and electronic equipment. BACKGROUND

[0002] The current main design process in the field of warehouse automation is artificially guided. Designers need to manually plan robot paths, workstation layouts, and shelf positions based on warehouse CAD drawings provided by customers. The quality of the existing technical solutions is directly related to the experience of the designers (such as the balance between shelf density and robot traffic efficiency), and the output of different designers for the same project also has differences, which has a strong dependence on experience. Moreover, traditional design needs to go through multiple cycles of processes such as demand analysis, scheme design, customer feedback, and design update, which takes several weeks or even months, and the iteration period is long. SUMMARY

[0003] Embodiments of the present application provide an intelligent warehousing deployment scheme generation method and device and electronic equipment to improve the intelligence and generation efficiency of intelligent warehousing deployment scheme generation.

[0004] In a first aspect, embodiments of the present application provide an intelligent warehousing deployment scheme generation method, which includes: obtaining project basic information, the project basic information including target demand information and target warehouse information; obtaining a pre-trained scheme generation model, the scheme generation model being a generative large model, the scheme generation model including an input layer, an optimization layer, and an output layer; inputting the target demand information and the target warehouse information into the scheme generation model through the input layer, and obtaining a target deployment scheme by processing the target demand information and the target warehouse information by the optimization layer, the target deployment scheme including at least shelf distribution information and intelligent robot configuration information; outputting the target deployment scheme through the output layer of the scheme generation model.

[0005] In one possible example of the first aspect, the optimization layer includes a scheme generation module, and the output layer includes a scheme output module, the scheme generation module being deployed with a sub-model of the scheme generation model, the scheme generation module being configured to generate a first deployment scheme according to the target demand information and the target warehouse information, and the target deployment scheme output by the scheme output module being the first deployment scheme or an optimized scheme of the first deployment scheme.

[0006] In one possible example of the first aspect, the input layer or the scheme generation module includes an input analysis module, and the generation of the first deployment scheme according to the target demand information and the target warehouse information includes: The target demand information is input into the input analysis module, and target demand data is obtained by analysis, the target demand data including storage capacity and work efficiency; The target warehouse information is input into the input analysis module, and target warehouse data is obtained by analysis, the target warehouse data including warehouse size and warehouse layout; The target demand data and the target warehouse data are input into the scheme generation module, and the first deployment scheme is obtained.

[0007] In one possible example of the first aspect, the optimization layer includes a scheme evaluation module, and the method further includes: An initial deployment scheme is obtained, the initial deployment scheme being the first deployment scheme generated by the scheme generation module or the second deployment scheme artificially imported; The initial deployment scheme is input into the scheme evaluation module, and first to-be-optimized information of the initial deployment scheme is obtained by evaluation; The initial deployment scheme is optimized according to the first to-be-optimized information, and the target deployment scheme is obtained.

[0008] In one possible example of the first aspect, the optimization layer further includes a scheme optimization module, and the optimization of the initial deployment scheme according to the first to-be-optimized information to obtain the target deployment scheme includes: The initial deployment scheme and the first to-be-optimized information are input into the scheme optimization module for optimization, and a first reference deployment scheme is obtained; The first reference deployment scheme is returned to the scheme evaluation module for evaluation; When second to-be-optimized information of the first reference deployment scheme is obtained after evaluation, the first reference deployment scheme and the second to-be-optimized information are input into the scheme optimization module for optimization, and the first reference deployment scheme after optimization is obtained, and the step of returning the first reference deployment scheme to the scheme evaluation module for evaluation is performed; When the second to-be-optimized information of the first reference deployment scheme is empty after evaluation, the first reference deployment scheme is determined as the target deployment scheme.

[0009] In one possible example of the first aspect, the optimization layer further includes a man-machine collaborative optimization module, and the optimization of the initial deployment scheme according to the first to-be-optimized information to obtain the target deployment scheme includes: The initial deployment scheme and the first to-be-optimized information are output to an external device through the man-machine collaborative optimization module, so as to realize artificial optimization; obtaining a second reference deployment scheme manually input into the man-machine collaborative optimization module by an external device, the second reference deployment scheme being obtained by optimizing the initial deployment scheme according to the first to-be-optimized information; returning the second reference deployment scheme to the scheme evaluation module for evaluation; when the third to-be-optimized information of the second reference deployment scheme is obtained after evaluation, outputting the second reference deployment scheme and the third to-be-optimized information to the external device through the man-machine collaborative module for optimization, obtaining an optimized second reference deployment scheme, and performing the step of returning the second reference deployment scheme to the scheme evaluation module for evaluation; when the third to-be-optimized information of the second reference deployment scheme is empty after evaluation, determining the second reference deployment scheme as the target deployment scheme.

[0010] In one possible example of the first aspect, before the pre-trained scheme generation model is obtained, the method further includes: obtaining a preset model to be trained; calling historical project data from a historical scheme library; calling design rule data from a scheme rule library; generating a training sample set according to the historical project data and the design rule data, the training sample set including a plurality of training samples; inputting the training samples into the preset model to be trained for training, so that when a predicted configuration scheme configured according to configuration information in the training samples is better than or equivalent to a configuration scheme corresponding to the training samples, a sub-model of the scheme generation module is obtained.

[0011] In one possible example of the first aspect, the first deployment scheme is generated according to the target requirement information and the target warehouse information, including: calling historical project data from a historical scheme library; calling design rule data from a scheme rule library; generating model prompt information based on the historical project data and the design rule data; taking the target requirement information, the target warehouse information, and the model prompt information as inputs of the scheme generation module, so as to output the first deployment scheme through the scheme generation module.

[0012] In one possible example of the first aspect, the target requirement information and the target warehouse information correspond to at least two different forms of information carriers, and the forms of the information carriers include image data, audio data, perception data, and natural language text data.

[0013] In a second aspect, the embodiments of the present application provide an intelligent warehouse deployment scheme generation apparatus, the intelligent warehouse deployment scheme generation apparatus comprises: a first obtaining unit, configured to obtain basic information, the basic information comprising target demand information and target warehouse information; a second obtaining unit, configured to obtain a pre-trained scheme generation model, the scheme generation model being a generative large model, the scheme generation model comprising an input layer, an optimization layer and an output layer; a generation unit, configured to input the target demand information and the target warehouse information into the scheme generation model through the input layer, and obtain a target deployment scheme by processing of the optimization layer, the target deployment scheme comprising at least shelf distribution information and intelligent robot configuration information; an output unit, configured to output the target deployment scheme through the output layer of the scheme generation model.

[0014] In a third aspect, the embodiments of the present application provide an electronic device, comprising a processor, a memory, a communication interface, and one or more programs, the one or more programs are stored in the memory and configured to be executed by the processor, and the program comprises instructions for executing the steps in the first aspect of the embodiments of the present application.

[0015] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, which stores a computer program for electronic data exchange, wherein the computer program causes a computer to execute some or all of the steps described in the first aspect of the embodiments.

[0016] In a fifth aspect, the embodiments of the present application provide a computer program product, wherein the above computer program product includes a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiments. The computer program product can be a software installation package.

[0017] It can be seen that the application obtains project basic information, the project basic information includes target demand information and target warehouse information; obtains a pre-trained scheme generation model, the scheme generation model is a generative large model, the scheme generation model includes an input layer, an optimization layer and an output layer; the target demand information and the target warehouse information are input into the scheme generation model through the input layer, and the target deployment scheme is obtained by processing of the optimization layer, the target deployment scheme at least includes shelf distribution information and intelligent robot configuration information; and the target deployment scheme is output through the output layer of the scheme generation model. It can be seen that the scheme generation model is automatically designed to deploy the scheme, which can shorten the design cycle from weeks to hours, and the target deployment scheme generated by the scheme generation model can reduce the dependence on manual experience. Compared with the manually designed scheme, the target deployment scheme generated by the application has higher standardization and robustness, which can reduce the errors of manual design and solve the problem of unstable scheme effect, thereby ensuring the efficiency and effect of the target deployment scheme generation. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0019] Figure 1 is a schematic diagram of an architecture of a warehouse management system provided by an embodiment of the present application; Figure 2 is a schematic diagram of a flow of a smart warehouse deployment scheme generation method provided by an embodiment of the present application; Figure 3 is a partial component schematic diagram of a scheme generation model provided by an embodiment of the present application; Figure 4 is a component schematic diagram of a scheme generation model provided by an embodiment of the present application; Figure 5 is a partial component schematic diagram of another scheme generation model provided by an embodiment of the present application; Figure 6 is a component schematic diagram of another scheme generation model provided by an embodiment of the present application; Figure 7 is a schematic diagram of a flow of another smart warehouse deployment scheme generation method provided by an embodiment of the present application; Figure 8 is a functional unit component block diagram of a smart warehouse deployment scheme generation device provided by an embodiment of the present application; Figure 9is a functional unit composition block diagram of another intelligent warehouse deployment scheme generation device provided by an embodiment of the present application. Figure 10 is a structural block diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to enable personnel in the technical field to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0021] The terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, and are not used to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device.

[0022] In this document, the term "embodiment" means that the specific features, structures or characteristics described in connection with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily mean the same embodiment, nor is it independent or alternative to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0024] The scheme generation model in the technical solution of the present application can be deployed on a local device or a server in a warehouse management system. For example, as shown in the figure, Figure 1 The technical solution of the present application can be applied to a server 100 in a warehouse management system 10, which includes the server 100 and a user terminal device 200. The server 100 and the user terminal device 200 are in communication connection.

[0025] The server 100 refers to a remote computer for processing a large amount of computing tasks and storing data. For example, the server 100 can be an outsourcing server, a cloud server, an edge server, etc., which is not limited herein. The user terminal device 200 can include various types of computer devices, such as a portable handheld device, a general-purpose computer (such as a personal computer or a laptop computer), a workstation computer, a wearable device, etc. These computer devices can run various types and versions of software applications and operating systems, such as Microsoft Windows, Apple IOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as Google Chrome OS); or various mobile operating systems, such as Microsoft Windows Mobile OS, Windows phone, Android, iPhone OS, etc. The portable handheld device can include a cellular phone, a smartphone, a tablet computer, a personal digital assistant (PDA), etc. The wearable device can include a head-mounted display and a smartwatch, etc. The user terminal device 200 can run one or more services or software applications capable of executing the intelligent warehouse deployment scheme generation method.

[0026] Please refer to Figure 2 , Figure 2 is a flowchart of an intelligent warehouse deployment scheme generation method provided by an embodiment of the present application. The present application scheme can be applied to a server 100 in a warehouse management system as described in Figure 1 , as shown in Figure 2 , the intelligent warehouse deployment scheme generation method comprises the following steps. Step S210, obtaining project basic information, the project basic information comprising target requirement information and target warehouse information.

[0027] The target requirement information is used to represent the design requirements of the user for the current target warehouse. For example, the target requirement information can be used to represent at least the storage capacity requirements, the storage goods type requirements and the daily throughput efficiency requirements of the user for the target warehouse.

[0028] The target warehouse information is used to represent the shape, size and area of the current target warehouse.

[0029] Specifically, the target demand information and the target warehouse information correspond to at least two different forms of information carriers, including image data, audio data, sensory data, and natural language text data. Image data includes images, videos, or graphics; for example, target warehouse information can be represented as image data. Sensory data refers to data collected by sensors, such as the shape and dimensions of the target warehouse collected by sensors. Natural language text data includes documents or natural language statements (such as interactive statements used to express demands) generated in natural language. For example, target demand information can be documents, natural language statements, images, or audio files; for example, target demand information can be represented as files in formats such as TXT, DOC, DOCX, PDF, JPG, or AAC. For example, target demand information can be meeting documents or recordings of offline communication. Alternatively, target demand information can also be documents collected through questionnaires. The target warehouse information can be in the form of images or DWG drawings.

[0030] Specifically, users can upload target basic information to the server through their client devices.

[0031] Step S220: Obtain a pre-trained scheme generation model, wherein the scheme generation model is a generative large model.

[0032] The scheme generation model includes an input layer, an optimization layer, and an output layer.

[0033] Specifically, the output of the solution generation model can be documents in formats such as DOC, DOCX, PDF, and PPT.

[0034] It should be noted that step S220 of this application is not limited to being completed after step S210. Step S220 can be completed simultaneously with step S210, or step S220 can be completed before step S210.

[0035] Step S230: Input the target demand information and the target warehouse information into the scheme generation model through the input layer, and process them by the optimization layer to obtain the target deployment scheme. The target deployment scheme includes at least shelf distribution information and intelligent robot configuration information.

[0036] The shelf distribution information includes shelf types, quantities, and locations. The intelligent robot configuration information includes robot types, allocation methods (such as robot distribution areas and density), and working methods (such as robot work paths). Specifically, the target deployment plan may also include workstation configuration information, deployment and construction period, and deployment and construction costs.

[0037] In a specific implementation, after the server receives the target demand information and the target warehouse information uploaded by the user-side device, the target demand information and the target warehouse information can be input into the scheme generation model. The input layer of the scheme generation model can input the target demand information and the target warehouse information into the scheme generation model, so that the optimization layer of the scheme generation model processes the target demand information and the target warehouse information, thereby obtaining the target deployment scheme, and the output layer of the scheme generation model outputs the target deployment scheme, so as to feed back the generated target deployment scheme to the user-side device. Specifically, the output target deployment scheme can include one or more files, for example, it can include corresponding CAD drawings and documents including at least shelf distribution information and intelligent robot configuration information.

[0038] Specifically, before the optimization layer of the scheme generation model processes the target demand information and the target warehouse information, the target demand information and the target warehouse information need to be converted into the design language of the scheme generation model, so as to unify the data format when the server processes data through the scheme generation model, which is beneficial to realize data fusion. This language conversion step can be completed before the input layer is obtained, or this language conversion step can also be completed by the function module corresponding to the deployment of the input layer or the optimization layer.

[0039] In step S240, the output layer of the scheme generation model outputs the target deployment scheme.

[0040] It can be seen that, by obtaining project basic information including target demand information and target warehouse information, obtaining a pre-trained scheme generation model, the scheme generation model being a generative large model, the scheme generation model including an input layer, an optimization layer, and an output layer, inputting the target demand information and the target warehouse information into the scheme generation model through the input layer, and obtaining a target deployment scheme through the optimization layer, the target deployment scheme including at least shelf distribution information and intelligent robot configuration information, and outputting the target deployment scheme through the output layer of the scheme generation model. It can be seen that, by constructing the scheme generation model to automatically design and deploy the scheme, the design cycle can be shortened from weeks to hours, and the target deployment scheme generated by the scheme generation model can reduce the dependence on manual experience. Compared with manually designed schemes, the target deployment scheme generated by the present application has higher standardization and robustness, which can reduce the errors of manual design and solve the problem of unstable scheme effect, thereby ensuring the efficiency and effect of generating the target deployment scheme.

[0041] For reference Figure 3In a possible example, the optimization layer includes a scheme generation module, the output layer includes a scheme output module, the scheme generation module is deployed with a sub-model of the scheme generation model, and the scheme generation module is configured to generate a first deployment scheme according to the target demand information and the target warehouse information; and the target deployment scheme output by the scheme output module is the first deployment scheme or an optimized scheme of the first deployment scheme.

[0042] The scheme generation module can be a sub-model of the scheme generation model deployed in the optimization layer.

[0043] Specifically, the training sample of the sub-model deployed by the scheme generation module includes configuration information and a configuration scheme, and the configuration information includes demand information and warehouse information. The demand information and the warehouse information are change data. Specifically, the demand information can include at least one of the storage capacity requirement, the outbound efficiency requirement, or the inbound efficiency requirement for different warehouses. The warehouse information can include at least one of the shape layout, the entrance and exit position, and the length, width, and height of different warehouses.

[0044] It can be understood that, since the training sample contains various feature information related to the deployment scheme, the application uses the above type of information data as the training sample of the sub-model deployed by the scheme generation module, so that the sub-model obtained by training has rich experience. Therefore, the first deployment scheme generated by the scheme generation module based on the target demand information and the target warehouse information can meet the design requirements of the target warehouse.

[0045] Specifically, the scheme output module is configured to output a target deployment scheme. The target deployment scheme can be the first deployment scheme, or the target deployment scheme can be an optimized scheme generated based on the first deployment scheme, so that the target deployment scheme is more suitable for the design requirements or standards.

[0046] It can be seen that, in this example, the scheme generation model can meet the basic design requirements of the target warehouse by configuring the scheme generation module and the scheme output module for the scheme generation model.

[0047] In a possible example, before the pre-trained scheme generation model is obtained, the method further includes: obtaining a preset model to be trained; retrieving historical project data from a historical scheme library; retrieving design rule data from a scheme rule library; generating a training sample set according to the historical project data and the design rule data, the training sample set including a plurality of training samples; inputting the training samples into the preset model to be trained for training, so as to obtain the sub-model configured by the scheme generation module when the predicted configuration scheme trained according to the configuration information in the training sample is better than or equal to the configuration scheme corresponding to the training sample.

[0048] The preset model is a neural network model.

[0049] The historical project data includes historical data of multiple projects, and the historical data of a single project includes all or part of data for a warehouse design, such as design requirements and deployment schemes. The design rule data includes design standards for warehouse deployment, which can include industry specifications or design experience, such as the arrangement direction and arrangement density of shelves.

[0050] The output prediction configuration scheme is better than or equal to the configuration scheme corresponding to the training sample, that is, the return amount of the demand information corresponding to the output prediction configuration scheme is better than or equal to the return amount of the configuration scheme corresponding to the training sample. The return amount can be understood as data corresponding to the demand information, such as storage capacity or work efficiency. The better the return amount, the better the data corresponding to the demand information.

[0051] In a specific implementation, the multiple steps of training the sub-model of the scheme generation module can be performed before the obtaining step S220. Specifically, when training the sub-model of the scheme generation module, the training sample set can be generated according to the historical project data and the design rule data by using a feature cross method, a label check method, or a stratified sampling method. Then, the training samples in the training sample set are input into the preset model to be trained in batches. Specifically, each training sample outputs a set of predicted deployment schemes after being input into the preset model to be trained. Then, the predicted deployment schemes can be compared with the configuration scheme corresponding to the training sample to compare the return amounts under different configuration schemes. If the return amount of the predicted deployment scheme is less than the return amount of the configuration scheme corresponding to the training sample, the preset model needs to be trained in reverse. Through repeated training of multiple training samples, when the trained prediction configuration scheme is better than or equal to the configuration scheme corresponding to the training sample, the training of the preset model is completed, and the trained preset model can be determined as the sub-model of the scheme generation module.

[0052] It can be seen that, in the present example, training the sub-model of the scheme generation module according to the historical project data and the design rule data is more advantageous than directly training the sub-model of the scheme generation module according to the historical project data, which can improve the adaptability of the first deployment scheme generated by the sub-model of the scheme generation module to user demand and industry standards, improve the accuracy and reliability of the generated scheme, and optimize the sub-model.

[0053] In a possible example, the input layer or the scheme generation module includes an input analysis module, and the generating the first deployment scheme according to the target demand information and the target warehouse information includes: inputting the target demand information into the input analysis module to obtain target demand data, the target demand data including storage capacity and work efficiency; inputting the target warehouse information into the input analysis module to obtain target warehouse data, the target warehouse data including warehouse size and warehouse layout; and inputting the target demand data and the target warehouse data into the scheme generation module to obtain the first deployment scheme.

[0054] The input analysis module is configured to analyze the target demand information and the target warehouse information. Figure 4 As shown in FIG. 6, the input analysis module can be deployed in the input layer. Alternatively, a sub-model configured by the scheme generation module can be configured with a data analysis function. Figure 5 As shown in FIG. 6, the input analysis module can also be deployed in the scheme generation module in the optimization layer.

[0055] In specific implementation, the input analysis module can be configured to analyze the target demand information to extract target demand data associated with user demand from the target demand information. The input analysis module can also be configured to analyze the target warehouse information to extract target warehouse data. Thus, it is beneficial to subsequently generate the first deployment scheme by a sub-model configured by the scheme generation module. Alternatively, the input analysis module can also be configured to analyze historical project data in the historical scheme library and design rule data in the scheme rule library to generate a sub-model configured by the scheme generation module. Specifically, the input analysis module can implement data analysis by a rule algorithm, or the input analysis module can implement data analysis by a configured sub-model, which is not limited herein.

[0056] In specific implementation, the language conversion step described above can also be performed by the input analysis module.

[0057] As can be seen, in the example, by deploying the input analysis module in the input layer, the complexity of a sub-model configured by the scheme generation module can be reduced while achieving analysis of input data, and the difficulty of configuring the scheme generation model can be reduced.

[0058] In a possible example, the inputting the target demand data and the target warehouse data into the scheme generation module to obtain the first deployment scheme includes: calling historical project data from a historical scheme library; calling design rule data from a scheme rule library; generating model prompt information based on the historical project data and the design rule data; and inputting the target demand data, the target warehouse data, and the model prompt information as inputs of the scheme generation module to generate the first deployment scheme by the scheme generation module.

[0059] The contents of the historical project data and the design rule data can be referred to the above, and will not be described here again.

[0060] The model prompt information is an instruction, a question or a context description input to a sub-model of the scheme generation module, used to guide and control the content output by the sub-model configured by the scheme generation module. The model prompt information can include a use scenario requirement (such as an e-commerce warehouse paying more attention to high-frequency picking requirements), a data logic requirement (such as the adaptability of partition and dynamic line, the adaptability of equipment selection and goods, etc.), and a prohibitive rule, etc. For example, the model prompt information can be as follows: “Please output the first deployment scheme according to the following constraint rules, and all outputs must meet all the rules: rule 1, the functional partition needs to match the dynamic line design (such as the in-warehouse area needs to be adjacent to the buffer area, the buffer area needs to be connected to the storage area, and the goods need to be avoided to be transported in a detour); rule 2, it is prohibited to appear a design conflicting with industry specifications (such as the width of the fire exit is less than 1.8m, and dangerous goods are mixed with ordinary goods); rule 3, it is prohibited to ignore the ‘scalability’ design (such as the extensible shelf area and the equipment upgrade interface need to be reserved for business growth space in the next 3-5 years). Please generate complete design content based on the above rules, combined with the target requirement data and the target warehouse data provided by the user.

[0061] In a specific implementation, the sub-model configured by the scheme generation module can be trained according to the project data in the project data set. The project data in the project data set can include at least one of the historical project data or the preset project data. The preset project data is simulation data configured for generating the sub-model.

[0062] Specifically, when generating the model prompt information, the historical project data can be parsed first to determine the key information in the historical project data through feature extraction and statistical analysis operations. At the same time, the design rule data can be parsed to determine the constraint conditions when the sub-model deployed by the scheme generation module generates the first deployment scheme. Then, the contents parsed from the historical project data and the design rule data can be fused to construct a prompt structure, so as to obtain the model prompt information, and the model prompt information is determined as the input content of the sub-model deployed by the scheme generation module. On this basis, when the target requirement information and the target warehouse information are obtained, the target requirement information, the target warehouse information and the model prompt information can be input into the sub-model deployed by the scheme generation module as inputs to obtain the first deployment scheme. Specifically, in combination with the foregoing content, the target requirement information and the target warehouse information input into the scheme generation module can also be the target requirement data and the target warehouse data parsed by the input parsing module deployed in the input layer.

[0063] It can be seen that, in the present example, by generating model prompt information according to historical project data and design rule data and taking the model prompt information as input of the scheme generation module configuration, the content output by the scheme generation module configuration can be guided and controlled, so that the output content responds to the rules, logic or constraint conditions described in the design rule data and the historical project data, thereby guiding and controlling the first deployment scheme generated by the sub-model of the scheme generation module configuration to be more in line with business requirements and standards, which is conducive to improving the accuracy and reliability of generating the first deployment scheme and realizing model optimization.

[0064] In one possible example, the optimization layer includes a scheme evaluation module, and the method further includes: obtaining an initial deployment scheme, the initial deployment scheme being a first deployment scheme generated by the scheme generation module or a second deployment scheme artificially imported; inputting the initial deployment scheme into the scheme evaluation module to obtain first to-be-optimized information of the initial deployment scheme; and optimizing the initial deployment scheme according to the first to-be-optimized information to obtain the target deployment scheme.

[0065] In the present example, the first deployment scheme is a scheme generated by the server according to target requirement information and target warehouse information. The second deployment scheme is a scheme artificially designed by a designer. Specifically, the second deployment scheme can be input into a user terminal device, and then reported to the server by the user terminal device, so that the server obtains the second deployment scheme, thereby realizing artificial import.

[0066] In specific implementation, the scheme evaluation module can also be deployed with a sub-model, which can be trained according to evaluation rule data. Specifically, when training the scheme generation model, the historical project data, the design rule data and the evaluation rule data can be determined as training data of the scheme generation model.

[0067] Specifically, after obtaining the initial deployment scheme, the scheme generation model can input the initial deployment scheme into the sub-model deployed by the scheme evaluation module, so as to score each dimension of the initial deployment scheme by the sub-model deployed by the scheme evaluation module, thereby determining the dimensions that can be optimized of the initial deployment scheme based on the scores to obtain the first to-be-optimized information. Each dimension used for scoring is determined according to the evaluation rule data. The first to-be-optimized information is used to provide an optimization direction for the initial deployment scheme. For example, the first to-be-optimized information can indicate errors and design defects (such as incomplete output content, parameter calculation error, logical conflict in dynamic line and partition design, etc.) of the initial deployment scheme. The initial deployment scheme is further optimized according to the first to-be-optimized information, which is conducive to improving the quality of the optimized target deployment scheme output by the scheme generation model.

[0068] It can be seen that, in the present example, the scheme evaluation module is configured for the scheme generation model, and the first deployment scheme or the second deployment scheme is optimized according to the first to-be-optimized information obtained from the evaluation result, so as to obtain the target deployment scheme for the scheme generation model output, which is beneficial to improve the quality of the target deployment scheme output by the scheme generation model and optimize the model effect. At the same time, by determining the first deployment scheme or the second deployment scheme as the initial deployment scheme that can be used for optimization, the performance of the scheme generation model is improved, and the flexibility of the application of the scheme generation model is improved.

[0069] In some embodiments, the scheme generation model further comprises at least one of a scheme optimization module and a man-machine collaborative optimization module.

[0070] For reference Figure 6 In one possible example, the optimization layer further comprises a scheme optimization module, and the optimizing the initial deployment scheme according to the first to-be-optimized information to obtain the target deployment scheme comprises: inputting the initial deployment scheme and the first to-be-optimized information into the scheme optimization module for optimization to obtain a first reference deployment scheme; returning the first reference deployment scheme to the scheme evaluation module for evaluation; when the second to-be-optimized information of the first reference deployment scheme is obtained after the evaluation, inputting the first reference deployment scheme and the second to-be-optimized information into the scheme optimization module for optimization to obtain an optimized first reference deployment scheme, and performing the step of returning the first reference deployment scheme to the scheme evaluation module for evaluation; when the second to-be-optimized information of the first reference deployment scheme is empty after the evaluation, determining the first reference deployment scheme as the target deployment scheme.

[0071] The scheme optimization module is configured to autonomously optimize the initial deployment scheme according to the first to-be-optimized information.

[0072] In a specific implementation, after the initial deployment scheme is input into the scheme evaluation module, if the first to-be-optimized information obtained is not empty, the initial deployment scheme and the first to-be-optimized information can be input into the scheme optimization module, so that the scheme optimization module optimizes and improves the initial deployment scheme according to the first to-be-optimized information, to obtain an updated first reference deployment scheme. For example, the scheme optimization module can be deployed with a scheme generation sub-model, which can be generated by training according to historical project data and design rule data, and the like. Specifically, the model supplement prompt information of the scheme generation sub-model can be obtained according to the first to-be-optimized information, and the scheme generation sub-model can adjust the prompt strategy, training data or model parameters according to the first to-be-optimized information, to finally improve the output quality of the model. For example, if the first to-be-optimized information is “missing ‘safety passage planning’ in warehouse design”, the model supplement prompt information of the sub-model of the scheme optimization module can be generated according to the first to-be-optimized information: “design the warehouse layout of the initial deployment scheme, which must include: 1) the positional relationship between the storage area and the picking area; 2) the width and direction of the safety passage; 3) the placement position of the fire-fighting equipment”. The scheme generation sub-model can input the initial deployment scheme and the above model supplement prompt information as input, to output the optimized first reference deployment scheme.

[0073] Specifically, after the scheme optimization module outputs the first reference deployment scheme, the first reference deployment scheme can be returned and input into the scheme evaluation module, so that the first reference deployment scheme is compared with the initial deployment scheme as described above, and the first reference deployment scheme is input into the scheme evaluation module as an input, to evaluate the first reference deployment scheme to obtain second to-be-optimized information. Then, the updated first reference deployment scheme and the second to-be-optimized information are input into the scheme optimization module, and the above steps are executed in a loop, so that the deployment scheme is iteratively optimized by the scheme evaluation module and the scheme optimization module, until the second to-be-optimized information is empty, the scheme currently evaluated by the scheme evaluation module is determined as the target deployment scheme, and is transmitted to the scheme output module for output.

[0074] As can be seen, in the present example, the initial deployment scheme is actively optimized by the scheme optimization module according to the to-be-optimized information, which is beneficial to improve the efficiency of scheme optimization and improve the efficiency of the scheme generation model.

[0075] For reference Figure 6In one possible example, the optimization layer further includes a man-machine collaborative optimization module, and the optimization of the initial deployment scheme according to the first to-be-optimized information to obtain the target deployment scheme includes: outputting the initial deployment scheme and the first to-be-optimized information to an external device through the man-machine collaborative optimization module for manual optimization; obtaining a second reference deployment scheme manually input into the man-machine collaborative optimization module by the external device, the second reference deployment scheme being obtained by optimizing the initial deployment scheme according to the first to-be-optimized information; returning the second reference deployment scheme to the scheme evaluation module for evaluation; when third to-be-optimized information of the second reference deployment scheme is obtained after the evaluation, outputting the second reference deployment scheme and the third to-be-optimized information to the external device through the man-machine collaborative module for optimization to obtain an optimized second reference deployment scheme, and performing the step of returning the second reference deployment scheme to the scheme evaluation module for evaluation; when the third to-be-optimized information of the second reference deployment scheme is empty after the evaluation, determining the second reference deployment scheme as the target deployment scheme.

[0076] The man-machine collaborative optimization module is configured to optimize the initial deployment scheme according to the first to-be-optimized information through a man-machine interaction mode.

[0077] The external device can be a user terminal device, which can be a terminal device used by a designer.

[0078] In a specific implementation, after the initial deployment scheme is input into the scheme evaluation module, if the first to-be-optimized information obtained is not empty, the initial deployment scheme and the first to-be-optimized information can be transmitted to the man-machine collaborative optimization module, so as to forward the initial deployment scheme and the first to-be-optimized information to the user terminal device through the man-machine collaborative optimization module, and display the initial deployment scheme and the first to-be-optimized information through the user terminal device. The designer can optimize the initial deployment scheme according to the first to-be-optimized information to obtain a second reference deployment scheme, and then upload the optimized second reference deployment scheme to the server through the user terminal device. The server can input the second reference deployment scheme into the man-machine collaborative optimization module, and use the second reference deployment scheme as feedback information of the man-machine collaborative optimization module, return transmission to the scheme optimization module, and use the second reference deployment scheme as the initial deployment scheme, and use the second reference deployment scheme as the input of the scheme evaluation module to evaluate the second reference deployment scheme and obtain third to-be-optimized information. Through the cyclic execution of the foregoing steps, the initial deployment scheme is iteratively optimized through the scheme evaluation module and the man-machine collaborative optimization module, and when the third to-be-optimized information output by the scheme evaluation module is empty, the scheme corresponding to the evaluation at this time is determined as the target deployment scheme, and is transmitted to the scheme output module for visualization output. Alternatively, in some embodiments, when the designer uploads the second reference deployment scheme to the server through the user terminal device, the server can input the second reference deployment scheme as the initial deployment scheme of the second deployment scheme into the scheme evaluation module of the scheme generation model, and evaluate it through the scheme evaluation module of the scheme generation model, until the first to-be-optimized information output is empty, the scheme evaluated at the current time is transmitted to the scheme output module, and is output and displayed through the scheme output module.

[0079] In a specific implementation, when the scheme generation model is configured with the scheme optimization module and the man-machine collaborative optimization module, the user can flexibly select one of the functions of the scheme optimization module and the man-machine collaborative optimization module to optimize the scheme.

[0080] As can be seen, in the present example, the initial deployment scheme is optimized according to the to-be-optimized information through the man-machine collaborative optimization module, which is beneficial to improve the flexibility of optimization of the initial deployment scheme, and can make up for the limitations of machine design.

[0081] Referring to Figure 7, with specific examples, the project basic information can be taken as the input of the scheme generation model, after inputting the scheme generation model, the project basic information can be parsed by the input analysis module, and then the parsed content can be input into the scheme generation module to generate the first deployment scheme through the scheme generation module. The first deployment scheme can be input into the scheme evaluation module to evaluate the quality of the first deployment scheme and obtain the corresponding first optimization information. After evaluation by the scheme evaluation module, the first optimization information and the first deployment scheme obtained by evaluation can be input into the scheme optimization module or the man-machine collaborative optimization module to iteratively optimize the first deployment scheme through the scheme evaluation module and the scheme optimization module or the scheme evaluation module and the man-machine collaborative optimization module, so as to obtain the target deployment scheme. After the scheme evaluation module determines the target deployment scheme, the target deployment scheme can be transmitted to the scheme output module and output by the scheme output module.

[0082] Alternatively, referring to Figure 7 , with specific examples, the second deployment scheme can be taken as the input of the scheme generation model, and the second deployment scheme input into the scheme generation model can be directly input into the scheme evaluation module for evaluation. After evaluation by the scheme evaluation module, the target deployment scheme can be obtained by optimization in the above-mentioned iterative optimization manner, and can be output and displayed through the scheme output module.

[0083] The present application can divide the server into functional units according to the above-mentioned method examples. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The integrated unit can be realized in the form of hardware or software functional unit. It should be noted that the division of units in the present application is illustrative, and is only a logical functional division. When actually implemented, another division method can be used.

[0084] Consistent with the above-mentioned embodiments, please refer to Figure 8 , Figure 8 is a functional unit composition block diagram of an intelligent warehouse deployment scheme generation device provided by an embodiment of the present application. The intelligent warehouse deployment scheme generation device is the above-mentioned server or a part of the server. The intelligent warehouse deployment scheme generation device 80 comprises: A first acquisition unit 810 is configured to acquire basic information, wherein the basic information comprises target demand information and target warehouse information. A second acquisition unit 820 is configured to acquire a pre-trained scheme generation model, wherein the scheme generation model is a generative large model, and the scheme generation model comprises an input layer, an optimization layer and an output layer. The generating unit 830 is configured to input the target demand information and the target warehouse information into the scheme generating model through the input layer, and obtain a target deployment scheme by processing of the optimization layer, wherein the target deployment scheme at least includes shelf distribution information and intelligent robot configuration information. The output unit 840 is configured to output the target deployment scheme through the output layer of the scheme generating model.

[0085] In one possible example, the optimization layer includes a scheme generating module, and the output layer includes a scheme output module. The scheme generating module is deployed with a sub-model of the scheme generating model, and is configured to generate a first deployment scheme according to the target demand information and the target warehouse information. The target deployment scheme output by the scheme output module is the first deployment scheme or an optimized scheme of the first deployment scheme.

[0086] In one possible example, the input layer or the scheme generating module includes an input analysis module. In the aspect of generating the first deployment scheme according to the target demand information and the target warehouse information, the generating unit is specifically configured to input the target demand information into the input analysis module, and analyze to obtain target demand data, wherein the target demand data includes storage capacity and work efficiency. The generating unit is specifically configured to input the target warehouse information into the input analysis module, and analyze to obtain target warehouse data, wherein the target warehouse data includes warehouse size and warehouse layout. The generating unit is specifically configured to input the target demand data and the target warehouse data into the scheme generating module, and obtain the first deployment scheme.

[0087] In one possible example, the optimization layer includes a scheme evaluation module, and the intelligent warehouse deployment scheme generating apparatus further includes an optimization unit. The optimization unit is configured to obtain an initial deployment scheme, wherein the initial deployment scheme is a first deployment scheme generated by the scheme generating module or a second deployment scheme artificially imported. The optimization unit is configured to input the initial deployment scheme into the scheme evaluation module, and evaluate to obtain first to-be-optimized information of the initial deployment scheme. The optimization unit is configured to optimize the initial deployment scheme according to the first to-be-optimized information, and obtain the target deployment scheme.

[0088] In a possible example, the optimization layer further includes a scheme optimization module, and the optimization unit is specifically configured to: input the initial deployment scheme and the first to-be-optimized information into the scheme optimization module for optimization to obtain a first reference deployment scheme; return the first reference deployment scheme to the scheme evaluation module for evaluation; when second to-be-optimized information of the first reference deployment scheme is obtained after the evaluation, input the first reference deployment scheme and the second to-be-optimized information into the scheme optimization module for optimization to obtain an optimized first reference deployment scheme, and perform the step of returning the first reference deployment scheme to the scheme evaluation module for evaluation; and when the second to-be-optimized information of the first reference deployment scheme is empty after the evaluation, determine the first reference deployment scheme as the target deployment scheme.

[0089] In a possible example, the optimization layer further includes a human-computer collaborative optimization module, and the optimization unit is specifically configured to: output the initial deployment scheme and the first to-be-optimized information to an external device through the human-computer collaborative optimization module, to realize manual optimization; obtain a second reference deployment scheme manually imported into the human-computer collaborative optimization module by the external device, the second reference deployment scheme being obtained by optimizing the initial deployment scheme according to the first to-be-optimized information; return the second reference deployment scheme to the scheme evaluation module for evaluation; when third to-be-optimized information of the second reference deployment scheme is obtained after the evaluation, output the second reference deployment scheme and the third to-be-optimized information to the external device through the human-computer collaborative module for optimization to obtain an optimized second reference deployment scheme, and perform the step of returning the second reference deployment scheme to the scheme evaluation module for evaluation; and when the third to-be-optimized information of the second reference deployment scheme is empty after the evaluation, determine the second reference deployment scheme as the target deployment scheme.

[0090] In a possible example, the intelligent warehouse deployment scheme generation apparatus further includes a model generation unit, which is configured to: before the pre-trained scheme generation model is obtained, obtain a preset model to be trained; retrieve historical project data from a historical scheme library; retrieve design rule data from a scheme rule library; generate a training sample set according to the historical project data and the design rule data, the training sample set including a plurality of training samples; and input the training samples into the preset model to be trained, to obtain a sub-model of the scheme generation module when a predicted configuration scheme obtained by training according to configuration information in the training samples is superior to or equivalent to a configuration scheme corresponding to the training samples.

[0091] In one possible example, in generating the first deployment plan based on the target requirement information and the target repository information, the generation unit is further configured to: retrieve historical project data from the historical plan library; retrieve design rule data from the plan rule library; generate model hint information based on the historical project data and the design rule data; and use the target requirement information, the target repository information, and the model hint information as input to the plan generation module to output the first deployment plan through the plan generation module.

[0092] In one possible example, the target demand information and the target warehouse information correspond to at least two different forms of information carriers, including image data, audio data, sensory data, and natural language text data.

[0093] It is understood that since the method embodiments and the device embodiments are different presentations of the same technical concept, the content of the method embodiment section in this application should be adapted to the device embodiment section in a synchronous manner, and will not be repeated here.

[0094] In the case of using integrated units, the functional unit composition block diagram of another intelligent warehouse deployment scheme generation device provided in this application embodiment is as follows: Figure 9 As shown. In Figure 9 The intelligent warehouse deployment scheme generation device 80 includes a processing module 920 and a communication module 910. The processing module 920 controls and manages the actions of the intelligent warehouse deployment scheme generation device 80, such as the steps performed by the first acquisition unit 810, the second acquisition unit 820, the generation unit 830, and the output unit 840, and / or other processes for performing the techniques described herein. The communication module 910 supports interaction between the intelligent warehouse deployment scheme generation device 80 and other devices. Figure 9 As shown, the intelligent warehouse deployment scheme generation device 80 may also include a storage module 930, which is used for the program code and data of the intelligent warehouse deployment scheme generation device 80.

[0095] The processing module 920 can be a processor or a controller, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an ASIC, an FPGA, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The processing module 920 can implement or execute the various exemplary logical blocks, modules, and circuits described in combination with the disclosure of the embodiments of the present application. The processing module 920 can also be a combination of computing functions, for example, a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 910 can be a transceiver, an RF circuit, a communication interface, or the like. The storage module 930 can be a memory.

[0096] All related content of each scenario involved in the above method embodiments can be cited to the functional description of the corresponding functional module, and will not be repeated here. The above intelligent warehouse deployment scheme generation device 80 can execute the above method embodiments. Figure 2 The intelligent warehouse deployment scheme generation method shown in the above method embodiments.

[0097] Figure 10 is a structural block diagram of an electronic device provided by an embodiment of the present application. As shown in Figure 10 The electronic device 1000 can be a server or a user terminal in the above warehouse management system. The electronic device can include a processor 1010, a memory 1020, a communication interface 1030, and one or more programs 1021, wherein the processor 1010, the memory 1020, and the communication interface 1030 are connected to each other and complete the communication work between each other. The one or more programs 1021 are stored in the above memory 1020 and are configured to be executed by the above processor 1010, and the one or more programs 1021 include instructions for executing any step in the above method embodiments.

[0098] The communication interface 1030 is configured to support communication between the electronic device 1000 and other devices. The processor 1010 can be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, transistor logic device, hardware component or any combination thereof. The processor can implement or execute various exemplary logical blocks, units and circuits described in combination with the disclosure of the embodiments of the present application. The processor can also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0099] The memory 1020 can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memory. The non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, and not limitation, many forms of random access memory can be used, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct Rambus RAM (DRRAM).

[0100] In specific implementations, the processor 1010 is configured to perform any of the steps of the above method embodiments, and when performing data transmission such as sending, the communication interface 1030 can be selectively invoked to complete the corresponding operation.

[0101] It should be noted that the structural schematic diagram of the electronic device 1000 described above is only an example, and the specific devices contained can be more or less, which is not limited herein.

[0102] The present application can divide the functional units of the electronic device according to the method examples described above, for example, each functional unit can be divided according to each function, or two or more functions can be integrated in one processing unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit. It should be noted that the division of units in the embodiments of the present application is illustrative, and is only a logical function division. When actually implemented, there can be another division method.

[0103] The embodiments of the present application also provide a computer readable storage medium, wherein the computer readable storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to execute part or all steps of any method described in the above method embodiments, and the computer includes a server.

[0104] The embodiments of the present application also provide a computer program product, which includes a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all steps of any intelligent warehouse deployment scheme generation method described in the above method embodiments. The computer program product can be a software installation package.

[0105] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a combination of a series of actions, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0106] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0107] In several embodiments provided in the present application, it should be understood that the disclosed apparatus can be implemented in other manners. For example, the division of the apparatus embodiments described above is merely a logical division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, and can be electrical or other forms.

[0108] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0109] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0110] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable memory. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art that contributes to the technical solutions or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a memory and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the above-mentioned method of the various embodiments of the present application. The aforementioned memory includes: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0111] A person of ordinary skill in the art can understand that all or part of the steps of the various methods of the above-described embodiments can be completed by a program instructing relevant hardware, and the program can be stored in a computer readable memory, which can include a flash disk, a ROM, a RAM, a magnetic disk or an optical disk, etc.

[0112] The above has carried out the detailed introduction to the embodiment of the application, the principle and implementation mode of the application have been described by applying specific examples in this paper, the above embodiment explanation is only for helping understanding the method of the application and its core idea; at the same time, for the general technical personnel in the art, according to the idea of the application, there will be changes in specific implementation mode and application range, and the above-mentioned, the content of the specification should not be understood as the limitation of the application.

Claims

1. A method for generating an intelligent warehousing deployment plan, characterized in that, The method comprises: acquiring project basic information, the project basic information comprising target demand information and target warehouse information; acquiring a pre-trained scheme generation model, the scheme generation model being a generative large model, the scheme generation model comprising an input layer, an optimization layer, and an output layer; inputting the target demand information and the target warehouse information into the scheme generation model through the input layer, and obtaining a target deployment scheme from the optimization layer, the target deployment scheme comprising at least shelf distribution information and intelligent robot configuration information; outputting the target deployment scheme from the output layer of the scheme generation model.

2. The method of claim 1, wherein, The optimization layer comprises a scheme generation module, and the output layer comprises a scheme output module, the scheme generation module being deployed with a sub-model of the scheme generation model, and the scheme generation module being configured to generate a first deployment scheme according to the target demand information and the target warehouse information; and the target deployment scheme output by the scheme output module being the first deployment scheme or an optimized scheme of the first deployment scheme.

3. The method of claim 2, wherein, The input layer or the scheme generation module comprises an input analysis module, and the first deployment scheme is generated according to the target demand information and the target warehouse information, comprising: inputting the target demand information into the input analysis module to obtain target demand data, the target demand data comprising storage capacity and work efficiency; inputting the target warehouse information into the input analysis module to obtain target warehouse data, the target warehouse data comprising warehouse size and warehouse layout; inputting the target demand data and the target warehouse data into the scheme generation module to obtain the first deployment scheme.

4. The method according to claim 2 or 3, characterized in that, The optimization layer comprises a scheme evaluation module, and the method further comprises: acquiring an initial deployment scheme, the initial deployment scheme being the first deployment scheme generated by the scheme generation module or a second deployment scheme artificially imported; inputting the initial deployment scheme into the scheme evaluation module to obtain first to-be-optimized information of the initial deployment scheme; optimizing the initial deployment scheme according to the first to-be-optimized information to obtain the target deployment scheme.

5. The method of claim 4, wherein, The optimization layer further comprises a scheme optimization module, and the optimization of the initial deployment scheme according to the first to-be-optimized information to obtain the target deployment scheme comprises: inputting the initial deployment scheme and the first to-be-optimized information into the scheme optimization module to obtain a first reference deployment scheme; returning the first reference deployment scheme to the scheme evaluation module for evaluation; when second to-be-optimized information of the first reference deployment scheme is obtained after the evaluation, inputting the first reference deployment scheme and the second to-be-optimized information into the scheme optimization module to obtain an optimized first reference deployment scheme, and performing the step of returning the first reference deployment scheme to the scheme evaluation module for evaluation; when the second to-be-optimized information of the first reference deployment scheme is empty after the evaluation, determining the first reference deployment scheme as the target deployment scheme.

6. The method of claim 4, wherein, The optimization layer further comprises a man-machine collaborative optimization module, and the optimization of the initial deployment scheme according to the first to-be-optimized information comprises: outputting the initial deployment scheme and the first to-be-optimized information to an external device through the man-machine collaborative optimization module for manual optimization; obtaining a second reference deployment scheme manually imported into the man-machine collaborative optimization module through an external device, the second reference deployment scheme being obtained by optimizing the initial deployment scheme according to the first to-be-optimized information; returning the second reference deployment scheme to the scheme evaluation module for evaluation; when third to-be-optimized information of the second reference deployment scheme is obtained after evaluation, outputting the second reference deployment scheme and the third to-be-optimized information to the external device through the man-machine collaborative module for optimization to obtain an optimized second reference deployment scheme, and performing the step of returning the second reference deployment scheme to the scheme evaluation module for evaluation; when the third to-be-optimized information of the second reference deployment scheme is empty after evaluation, determining the second reference deployment scheme as the target deployment scheme.

7. The method of claim 2, wherein, Before the pre-trained scheme generation model is obtained, the method further comprises: obtaining a preset model to be trained; calling historical project data from a historical scheme library; calling design rule data from a scheme rule library; generating a training sample set according to the historical project data and the design rule data, the training sample set comprising a plurality of training samples; inputting the training samples into the preset model to be trained for training, so that when a predicted configuration scheme obtained by training configuration information in the training samples is better than or equivalent to a configuration scheme corresponding to the training samples, a sub-model configured by the scheme generation module is obtained.

8. The method of claim 2, wherein, The generation of the first deployment scheme according to the target requirement information and the target warehouse information comprises: calling historical project data from a historical scheme library; calling design rule data from a scheme rule library; generating model prompt information based on the historical project data and the design rule data; taking the target requirement information, the target warehouse information and the model prompt information as inputs of the scheme generation module, so that the first deployment scheme is output by the scheme generation module.

9. The method of claim 1, wherein, The target requirement information and the target warehouse information correspond to at least two different forms of information carriers, and the forms of the information carriers include image data, audio data, perception data and natural language text data.

10. An intelligent warehousing deployment scheme generation apparatus, characterized by, The intelligent warehouse deployment scheme generation device comprises: a first obtaining unit configured to obtain basic information, the basic information comprising target requirement information and target warehouse information; a second obtaining unit configured to obtain a pre-trained scheme generation model, the scheme generation model being a generative large model, and the scheme generation model comprising an input layer, an optimization layer and an output layer; The generating unit is configured to input the target demand information and the target warehouse information into the scheme generating model through the input layer, and obtain a target deployment scheme by processing of the optimization layer, the target deployment scheme at least including shelf distribution information and intelligent robot configuration information. The output unit is configured to output the target deployment scheme through an output layer of the scheme generating model.

11. An electronic device, comprising: A computer program product including a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps in the method of any one of claims 1 to 9.

Images