Charging pile deployment method, apparatus, electronic device, and storage medium

Abstract

The present application relates to the technical field of charging pile deployment, and specifically to a charging pile deployment method, comprising acquiring user information; creating a user demand model according to the user information, the user demand model comprising a first model and a second model, the first model being used for extracting demand information of existing users according to the user information, and the second model being used for predicting demand information of potential users according to the user information; and, on the basis of the user demand model, setting target deployment information of charging piles. The present application determines demands of existing users and potential users according to user information, and then determines reasonable target deployment information according to the demands, thereby providing better final deployment results.

Description

Charging pile deployment method, device, electronic device and storage medium

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on September 7, 2023, with application number 202311159767.4 and application name “Method, device, electronic device and storage medium for deploying charging piles”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the technical field of charging pile deployment, and in particular to a charging pile deployment method, device, electronic device, and storage medium. Background Art

[0003] Charging piles are devices used to charge electric vehicles. In recent years, as the concept of energy conservation and emission reduction has become increasingly popular, electric vehicles have become an increasingly common part of people's daily commutes, driving a growing demand for charging piles. For charging pile operators, the quality of their deployment strategy is a crucial factor in their profitability.

[0004] Currently, when setting charging pile deployment strategies, relevant technologies usually simply estimate customer demand through operational experience, and then determine the deployment strategy based on the estimated user demand. The deployment strategy includes the model and quantity of charging piles that need to be deployed. However, this deployment strategy lacks sufficient data and theoretical support, which can easily lead to resource mismatch.

[0005] Summary of the Invention

[0006] One purpose of the embodiments of the present application is to provide a method for deploying charging piles to solve the problem of resource mismatch that is easily caused in related technologies.

[0007] In a first aspect, the present application proposes a method for deploying charging piles, comprising:

[0008] Get user information;

[0009] Creating a user demand model based on the user information, the user demand model comprising a first model and a second model, the first model being used to extract demand information of existing users based on the user information, and the second model being used to predict demand information of potential users based on the user information;

[0010] Based on the user demand model, target deployment information of charging piles is set.

[0011] In conjunction with the first aspect, in one possible implementation, setting target deployment information of charging piles based on the user demand model includes:

[0012] Outputting first demand information through the first model, where the first demand information is demand information of existing users;

[0013] Inputting the user information into the second model to generate second demand information, where the second demand information is demand information of potential users predicted by the second model;

[0014] The delivery information is set according to the first demand information and the second demand information.

[0015] In conjunction with the first aspect, in one possible implementation, the target delivery information includes first delivery information and second delivery information, and setting the target delivery information according to the first demand information and the second demand information includes:

[0016] Solve a preset charging pile site selection model based on the first demand information to calculate and obtain the first deployment information;

[0017] Solving the charging pile site selection model based on the second demand information to calculate and obtain the second deployment information;

[0018] The target delivery information is determined according to the first delivery information and the second delivery information.

[0019] In conjunction with the first aspect, in one possible implementation, the user information includes existing user information and potential user information, and obtaining the user information includes:

[0020] Collect users' historical orders;

[0021] Preprocessing the historical orders;

[0022] The pre-processing results are classified to determine that the user's historical orders that have been executed are the existing user information, and the user's historical orders that have not been executed are the potential user information.

[0023] In conjunction with the first aspect, in a possible implementation, creating a user demand model based on the user information includes:

[0024] determining existing user information in the user information;

[0025] Creating a behavioral profile of the existing user based on the existing user information;

[0026] Feature extraction is performed on the behavior portrait to construct the first model.

[0027] In conjunction with the first aspect, in one possible implementation, creating a user demand prediction model based on the user information includes:

[0028] The preset initial model is iteratively trained using the user information until the prediction accuracy of the initial model reaches a preset standard, thereby obtaining the second model.

[0029] In combination with the first aspect, in one possible implementation, iteratively training a preset initial model using the user information until the prediction accuracy of the initial model reaches a preset standard to obtain the second model includes:

[0030] Organizing the user information to obtain a training set and a test set;

[0031] Iteratively training the initial model using the training set;

[0032] Evaluating the prediction accuracy of the initial model using the test set to generate an evaluation result;

[0033] When the evaluation result is higher than a preset standard, the iterative training of the initial model is terminated to obtain the second model.

[0034] In a second aspect, an embodiment of the present application provides a charging pile placement device, comprising:

[0035] Information acquisition module, used to obtain user information;

[0036] A model creation module is used to create a user demand model based on the user information, wherein the user demand model includes a first model and a second model, wherein the first model is used to extract demand information of existing users based on the user information, and the second model is used to predict demand information of potential users based on the user information;

[0037] The strategy setting module is used to set the target deployment information of charging piles based on the user demand model.

[0038] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0039] at least one processor; and,

[0040] a memory communicatively connected to the at least one processor; wherein,

[0041] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the charging pile deployment method as described above.

[0042] In a fourth aspect, an embodiment of the present application provides a non-volatile readable storage medium, wherein the non-volatile readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable an electronic device to execute the charging pile deployment method as described above.

[0043] Compared with the prior art, this application has at least the following beneficial effects:

[0044] This application first obtains user information, and then creates a user demand model based on the user information. The user demand model includes a first model corresponding to existing users and a second model corresponding to potential users, and sets the target deployment information of charging piles based on the user model. The target deployment information is used for the deployment of charging piles. The user model is used to extract features and make reasonable predictions of user information, thereby obtaining demand information of existing users and potential users, and setting the target deployment information of charging piles based on this information. Therefore, the charging piles finally deployed can better meet the needs of users and avoid mismatching of charging pile resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] One or more embodiments are exemplarily illustrated by pictures in the corresponding drawings. These exemplifications do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are represented as similar elements. Unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0046] FIG1 is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0047] FIG2 is a schematic diagram of a flow chart of a method for deploying a charging pile according to an embodiment of the present application;

[0048] FIG3 is a schematic diagram of a charging pile deployment device provided in an embodiment of the present application;

[0049] FIG4 is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0051] It should be noted that, if there is no conflict, the various features in the embodiments of the present application can be combined with each other and are all within the scope of protection of the present application. In addition, although the functional modules are divided in the device schematic and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order than the module division in the device or the order in the flow chart. Furthermore, the words "first", "second", "third", etc. used in this application do not limit the data and execution order, but only distinguish between the same items or similar items with basically the same functions and effects.

[0052] To better explain the present application, reference is made to Figure 1, which is a schematic diagram of an application scenario provided by the present application. As shown in Figure 1, the application scenario includes a waiting area A10, a user set A20, a waiting charging pile set A30, and a terminal A40.

[0053] Among them, the user set A20 includes multiple users x, y, z..., all of whom are users who have been active in the area to be deployed A10 for a long time, and have generated a large amount of user information stored in the terminal A40 during their daily charging behavior; the charging pile set A30 includes multiple charging piles a, b, c..., and the models of each charging pile are different, with their own charging characteristics to meet the charging needs of different users.

[0054] It is easy to understand that in real life, the charging behavior of users who are active in a fixed area for a long time is relatively stable, that is, the charging needs of users x, y, z... are stable in the long term in the area to be deployed 20. Therefore, terminal A40 should meet the charging needs of users x, y, z... when deploying the charging pile set A30.

[0055] Based on this understanding, terminal A40 executes a preset deployment method, processes its stored user information, derives their charging needs, and calculates the deployment information for each charging pile in charging pile set A30. When each charging pile is deployed to area A10 according to this deployment information, it can meet the charging needs of all users in area A10.

[0056] It is understandable that the specific form of the terminal can be any terminal device with data analysis and processing functions, including but not limited to computers, servers, smart phones, tablet computers, etc.

[0057] In some embodiments, when terminal A40 deploys the charging pile set A30, it includes: obtaining user information; creating a user demand model based on the user information, the user demand model includes a first model and a second model, the first model is used to extract the demand information of existing users based on the user information, and the second model is used to predict the needs of potential users based on the user information; based on the user demand model, the target deployment information of the charging pile is set.

[0058] As one aspect of the embodiments of the present application, the embodiments of the present application provide a method for placing charging piles. Please refer to Figure 2, which is a schematic flow chart of the method, and the method includes:

[0059] Step S10, obtaining user information;

[0060] It should be noted that the deployment method referred to in this embodiment is a method of deploying charging piles in a target area. The user information in this embodiment mainly refers to the information generated by users who have been charging in the target area for a long time in their historical charging behavior.

[0061] If there are charging piles in the target area, the source of user information is mainly through collecting the user's charging information when the user charges through the charging pile and reporting it to the terminal for storage. Specifically, for any user, their charging information may include: charging method information. Currently, charging methods are mainly divided into DC charging and AC charging. AC charging uses an AC power supply to transmit electrical energy to the battery of the electric vehicle, while DC charging directly transmits electrical energy to the battery of the electric vehicle to adapt to different charging devices; charging power information. The charging power of a charging device is mainly determined by the battery model and battery status of the charging device. At certain times, the charging power is also actively regulated by the charging station; charging time information, such as the start and end time and duration of a charging device when using the charging pile; charging frequency information, which is the number of times a user charges within a fixed time period. Under normal circumstances, this time period is set to one week or one month; user vehicle model information, which is the vehicle model information when a user uses the charging pile to charge a new energy vehicle; battery capacity information, which is the capacity information of the vehicle battery when a user uses the charging pile to charge.

[0062] Furthermore, the step of obtaining user information includes: collecting the user's historical orders; preprocessing the historical orders; classifying the preprocessing results, and determining that the user's historical orders that have been executed are the existing user information, and the user's historical orders that have not been executed are the potential user information.

[0063] It should be noted that, depending on the target of user information, users can be divided into two categories: existing users and potential users. Existing users refer to users who already have certain charging needs in the target area and whose charging needs are met by charging piles in the target area; potential users refer to users who already have certain charging needs in the target area but whose charging needs are not met by charging piles in the target area.

[0064] Specifically, the preprocessing of historical orders includes data cleaning, missing value processing and outlier processing. Data cleaning includes checking and repairing errors in the data, such as removing duplicate data, repairing format errors or missing values, and ensuring data consistency and integrity; missing value processing includes deleting user orders to which individual missing values ​​belong, replacing them with the corresponding average or median values ​​in other user orders, etc.; outlier processing is used for data points that are too different from other data values ​​to ensure that individual erroneous orders do not affect the accuracy of the final results.

[0065] In some embodiments, users in the target area submit historical orders through mobile phone APP or on-site operations. The historical orders usually include the above-mentioned multiple charging information. The historical orders that are executed after the user selects the order are regarded as orders of existing users. Correspondingly, historical orders that are not executed after the user selects the order are regarded as orders of potential users, that is, the potential user puts forward his charging demand, but does not choose to execute due to other factors (such as price inappropriateness, etc.). Afterwards, the historical orders submitted by the user are stored in the terminal for subsequent analysis and processing.

[0066] In some embodiments, a user's mobile app or the interactive program of an interactive device operated on-site by the user is equipped with a historical operation tracking point to record the user's operation information. This allows the user to record and store the order generation information when the user places an order but the order is ultimately not completed. For example, a user's mobile phone has a mobile app for charging installed on it. The app is equipped with a historical operation tracking point. When the user searches for charging orders through the app, the charging information submitted by the user at that time will be recorded. The implementation program of the app is embedded with tracking code to implement the above-mentioned historical operation tracking function.

[0067] Step S20: creating a user demand model based on the user information, wherein the user demand model includes a first model and a second model, wherein the first model aims to extract demand information of existing users based on the user information, and the second model aims to predict demand information of potential users based on the user information;

[0068] The first model is a model used to extract features from user information and obtain user demand information, and the second model is a model used to predict user demand information in the future based on current user information.

[0069] Furthermore, creating a user demand model includes: determining existing user information in the user information; creating a behavior profile of the existing user based on the existing user information; and performing feature extraction on the behavior profile to construct the first model.

[0070] Specifically, a user's behavioral profile is a comprehensive analysis of user behavior and characteristics to reveal the user's needs, preferences, and corresponding behavioral models. It is created by mining, organizing, and analyzing user information. In this embodiment, the behavioral profile refers mainly to the user's needs and behaviors.

[0071] More specifically, the first model is a model that can analyze data and extract features. As an implementation method, it can be a PCA (Principal Component Analysis) model, that is, a feature model created by the PCA method. For example, for user information, each user's user information includes multiple charging information, and each charging information represents a feature of the user. However, in order to better analyze the user's needs, it is necessary to perform dimensionality reduction processing on multiple related features so that the user demand information finally obtained is the most representative feature information, thereby achieving the effect of data dimensionality reduction and reducing redundant information.

[0072] In some embodiments, existing user information is processed through cluster analysis to construct the aforementioned behavioral profile. Cluster analysis is a commonly used data analysis technique whose basic principle is to group data points with similar characteristics into the same group to better understand and gain insights into problems.

[0073] As an implementation, existing user information includes historical orders from multiple different users, each of which includes multiple pieces of charging information. This large amount of charging information is then divided into similar groups, such that the charging information within a group has high similarity, while the similarity between different groups is low. For example, the grouping method can employ a hierarchical clustering approach, whereby charging information is grouped according to different hierarchies. The grouping criteria are determined by a distance metric (e.g., Euclidean distance, Manhattan distance, etc.) between the information, and are implemented using merge / split rules.

[0074] Furthermore, creating a user demand model also includes: iteratively training a preset initial model using the user information until the prediction accuracy of the initial model reaches a preset standard, thereby obtaining the second model.

[0075] It is easy to understand that a variety of different artificial neural network models can be selected for training according to actual application scenarios, so that the final second model can predict future user demand information based on historical user information.

[0076] Specifically, the steps of iteratively training the preset initial model through the user information until the prediction accuracy of the initial model reaches the preset standard specifically include: organizing the user information to obtain a training set and a test set; iteratively training the initial model through the training set; evaluating the prediction accuracy of the initial model through the test set to generate an evaluation result; when the evaluation result is higher than the preset standard, ending the iterative training of the initial model to obtain the second model.

[0077] More specifically, the initial model is an artificial neural network, such as RNN (Recurrent Neural Network). RNN is a recursive neural network that takes sequence data as input, recursively in the direction of sequence evolution, and all nodes are connected in a chain.

[0078] When choosing RUN as the initial model, user information is first organized, arranging multiple charging records of multiple users in chronological order to obtain a total data set. This data is then partitioned into training and test sets, with a 1:1 data partition ratio. Typically, an RNN includes multiple neural units, such as long-short-term memory units and gating units, which together form a multi-layered network structure. The number of layers and the size of the hidden layers can be determined by the implementer based on the amount of user demand information to be predicted.

[0079] Before training the initial RNN, it is necessary to determine the network's loss function and the model's initial weights and biases. The loss function can use the mean square error function or the cross entropy loss function, and the model's initial weights and biases can be selected by random initialization.

[0080] During model training, the organized training set is input into the input layer of the initial RNN. Multiple neural units in the RNN perform forward propagation on the training set, processing the input of each time step in the training set in turn. By recursively transferring information and state, the predicted result is output. This result is then compared with the actual result in the training set to calculate the value of the loss function. Based on the value of the loss function, the gradient of the parameters in the model is calculated through the backpropagation algorithm to update the model's weights and biases, so that the model's output tends to the direction of continuously decreasing error, that is, the degree of fit between the model and the test set is getting higher and higher. Through multiple iterations of the above forward propagation, calculation of the loss function, backpropagation, and updating of weights and biases, the final output of the model achieves the desired effect.

[0081] Among them, the test set is used for verification to evaluate the model, the results output by the model are compared with the test set, and the prediction accuracy of the model is statistically analyzed. When the evaluation result is higher than a preset standard, it is considered that the output result of the model has achieved the predetermined effect.

[0082] In other embodiments, the prediction of user demand can be regarded as a linear regression problem, and the second model can be in the form of a linear regression model. The linear regression model establishes a linear relationship between the independent variable and the dependent variable, and obtains an optimal fitting straight line by minimizing the difference between the predicted value and the true value, which is used to predict future user demand information.

[0083] For example, user information includes multiple charging information items, and each charging information item includes multiple numerical values ​​distributed according to a time series. Linear regression analysis is performed on each numerical value, and multiple linear regression models can be established. Each linear regression model predicts a charging information item at a future moment. Accordingly, the multiple predicted results include multiple charging information items, which are future user demand information.

[0084] Step S30: setting target deployment information of charging piles based on the user demand model;

[0085] It should be noted that the target deployment information of charging piles includes the deployment strategy within the target area to be deployed. The deployment strategy includes the model information of multiple charging piles and the target deployment point information corresponding to the multiple charging piles. The target deployment point information of the multiple charging piles is all within the target area to be deployed.

[0086] Specifically, the above-mentioned user demand model includes a first model and a second model. When setting the deployment information of the charging pile according to the user demand model, the first demand information is output through the first model, and the first demand information is the demand information of the existing user; the user information is input into the second model to generate the second demand information, and the second demand information is the demand information of the potential user; the deployment information is calculated based on the first demand information and the second demand information.

[0087] It should be noted that the preset charging pile site selection model refers to a site selection model that is pre-created by collecting public information in the target area to be deployed. Compared with the user demand model, the site selection model is mainly created with reference to factors that are not related to the user, such as environmental factors in the area, grid prices, grid parameters, etc. For example, the site selection model is a general network analysis model, such as a graph theory model, which includes multiple nodes and edges. Each node can represent the target deployment point of a charging pile, and each edge can represent the coverage range of a charging pile. Based on the collected public information, the basic topology of the model can be set, and the model can be solved according to user needs in subsequent steps.

[0088] In some embodiments, the forms of collecting public information include, but are not limited to, determining grid prices and grid parameters through third-party data service providers and market research, collecting the number of new energy vehicles in the area, local consumption levels, and collecting information related to local charging stations (the location of the charging station, the number of charging guns at each station, the classification of each station (on the way, office, home, etc.), the traffic characteristics of each station (highway entrances, rest areas, highway exits, near supermarkets, etc.), the number of service users, etc.) as general public information.

[0089] Furthermore, the calculation of the deployment information based on the first demand information and the second demand information includes: solving a preset charging pile site selection model based on the first demand information to calculate the first deployment information; solving the charging pile site selection model based on the second demand information to calculate the second deployment information; and determining the target deployment information based on the first deployment information and the second deployment information.

[0090] The target deployment information consists of first and second deployment information. The first deployment information includes deployment strategies that meet the needs of existing users, while the second deployment information includes deployment strategies that meet the needs of potential users. By calculating deployment strategies for existing and potential users separately, different strategies can be set for different users, reducing the risk of the overall solution. For example, if the charging pile site selection model is a graph theory model, solving the model can be viewed as a node centrality problem. The model's constraints include charging pile capacity, grid parameters, and prices. The result of solving the model is a model structure.

[0091] It's easy to understand that the current needs of existing users are more stable than those of potential users. Furthermore, for charging station operators, the deployment strategy should ensure stable profitability. Based on this understanding, the deployment process should prioritize meeting the needs of existing users and, while maintaining this, address the needs of potential users.

[0092] In some embodiments, placing charging piles according to target placement information includes: placing charging piles in the target area according to first placement information, which is the first stage of charging pile placement; after the first stage of placement is completed, based on the results of the first stage of placement, the second stage of charging pile placement is carried out, and this stage is mainly carried out according to the second placement information.

[0093] Based on the method provided in the above embodiment, a user demand model is created mainly based on user information, thereby determining the needs of existing and potential users, and planning and solving the charging pile location model based on the needs of existing and potential users, and finally obtaining and executing the charging pile deployment information. Compared with the existing technology, this application determines user needs through multi-model planning based on a large amount of user information. Therefore, the rationality of user needs is higher, the mismatch of charging pile resources is avoided, and the feasibility of the deployment results is further ensured through the multi-stage implementation of the deployment information.

[0094] The method of the present application is introduced above, and the device and electronic device of the present application are introduced below.

[0095] As another aspect of the embodiments of the present application, the embodiments of the present application provide a device for charging pile deployment, which can be a software module, and the software module includes several instructions, which are stored in a memory. The processor can access the memory and call the instructions for execution to complete the charging pile deployment method described in each of the above embodiments. In some embodiments, the device can also be built by hardware devices. For example, the device can be built by one or more chips, and each chip can work in coordination with each other to generate the charging pile deployment information described in each of the above embodiments. For another example, the device can also be built by various logic devices, such as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination of these components. It should be noted that the above-mentioned device can execute the method provided in the embodiments of the present application, and has the corresponding functional modules and beneficial effects for executing the method. For technical details not fully described in the embodiments of the present device, please refer to the charging pile deployment method provided in the embodiments of the present application.

[0096] Specifically, referring to FIG3 , a device 30 for deploying a charging pile includes:

[0097] Information acquisition module 301, used to obtain user information;

[0098] A model creation module 302 is configured to create a user demand model based on the user information. The user demand model includes a first model and a second model. The first model is configured to extract the needs of existing users based on the user information. The second model is configured to predict the needs of potential users based on the user information.

[0099] The strategy setting module 303 is used to set target deployment information of charging piles based on the user demand model.

[0100] In one possible design, the strategy setting module 303, when setting the target deployment information of the charging pile based on the user demand model, is specifically used to: output first demand information through the first model, where the first demand information is the demand information of existing users; input the user information into the second model to generate second demand information, where the second demand information is the demand information of potential users; and set the target deployment information based on the first demand information and the second demand information.

[0101] In one possible design, the strategy setting module 303 is used to set the target deployment information based on the first demand information and the second demand information, and is specifically used to: solve the preset charging pile site selection model according to the first demand information, and calculate the first deployment information; solve the charging pile site selection model according to the second demand information, and calculate the second deployment information; determine the deployment information based on the first deployment information and the second deployment information.

[0102] In one possible design, when the information acquisition module 301 is used to acquire user information, the acquired user information includes existing user information and potential user information. The information acquisition module 301 is specifically used to: collect the user's historical orders; pre-process the historical orders; classify the pre-processing results, and determine that the user's historical orders that have been executed are the existing user information, and the user's historical orders that have not been executed are the potential user information.

[0103] In one possible design, the model creation module 302, when used to create a user demand model based on the user information, is specifically used to: determine existing user information in the user information; create a behavior profile of the existing user based on the existing user information; and perform feature extraction on the behavior profile to construct the first model.

[0104] In one possible design, the model creation module 302, when used to create a user demand model based on the user information, is also used to: iteratively train a preset initial model based on the user information until the prediction accuracy of the initial model reaches a preset standard, thereby obtaining the second model.

[0105] In one possible design, the model creation module 302, when used to iteratively train a preset initial model using the user information until the prediction accuracy of the initial model reaches a preset standard and the second model is obtained, is specifically used to: organize the user information to obtain a training set and a test set; iteratively train the initial model using the training set; evaluate the prediction accuracy of the initial model using the test set to generate an evaluation result; when the evaluation result is higher than the preset standard, end the iterative training of the initial model to obtain the second model.

[0106] In addition, it should be noted that in each of the above-mentioned embodiments, there is not necessarily a certain order between the above-mentioned steps. A person skilled in the art can understand, based on the description of the embodiments of this application, that in different embodiments, the above-mentioned steps may have different execution orders, that is, they may be executed in parallel, or may be executed interchangeably, etc.

[0107] Further, please refer to Figure 4, which is a schematic diagram of the circuit structure of an electronic device provided in an embodiment of the present application. The electronic device can be any suitable type of device or electronic product, for example, a tablet computer, a smart terminal, or a mobile phone, etc., which has logical computing and analysis capabilities. As shown in Figure 4, electronic device 40 includes one or more processors 41 and memory 42. Figure 4 uses one processor 41 as an example.

[0108] The processor 41 and the memory 42 may be connected via a bus or other means. FIG4 takes the bus connection as an example.

[0109] Memory 42, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the charging pile deployment method in the embodiments of the present application. Processor 41 executes the non-volatile software programs, instructions, and modules stored in memory 42 to execute the various functional applications and data processing of the above-mentioned device, thereby implementing the charging pile deployment method provided in the above-mentioned method embodiment and the functions of the various modules or units in the above-mentioned device embodiment.

[0110] The memory 42 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state memory device. In some embodiments, the memory 42 may optionally include a memory remotely located relative to the processor 41, and such remote memory may be connected to the processor 41 via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0111] The program instructions / modules are stored in the memory 42 , and when executed by the one or more processors 41 , the charging pile deployment method in any of the above method embodiments is executed.

[0112] An embodiment of the present application also provides a non-volatile computer storage medium, which stores computer-executable instructions. The computer-executable instructions are executed by one or more processors, such as a processor 41 in Figure 4, so that the one or more processors can execute the charging pile deployment method in any of the above method embodiments.

[0113] An embodiment of the present application also provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by an electronic device, the electronic device executes any one of the charging pile deployment methods described.

[0114] The above-described device or apparatus embodiments are merely illustrative. The unit modules described as separate components may or may not be physically separate, and the components shown as module units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network module units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment.

[0115] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, or of course, by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the relevant technology, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiment.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Based on the concept of the present application, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the present application as described above. For the sake of simplicity, they are not provided in detail. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for placing a charging pile, characterized in that: include: Get user information; Creating a user demand model based on the user information, the user demand model comprising a first model and a second model, the first model being used to extract demand information of existing users based on the user information, and the second model being used to predict demand information of potential users based on the user information; Based on the user demand model, target placement information of charging piles is set.

2. The method according to claim 1, characterized in that The step of setting target placement information of charging piles based on the user demand model includes: Outputting first demand information through the first model, where the first demand information is demand information of existing users; Inputting the user information into the second model to generate second demand information, where the second demand information is demand information of potential users predicted by the second model; The target delivery information is set according to the first demand information and the second demand information.

3. The method according to claim 2, characterized in that The target delivery information includes first delivery information and second delivery information, and the target delivery information is set according to the first demand information and the second demand information, including: According to the first demand information, a preset charging pile site selection model is solved to calculate and obtain the first placement information; Solving the charging pile site selection model according to the second demand information to calculate and obtain the second placement information; The target delivery information is determined according to the first delivery information and the second delivery information.

4. The method according to claim 1, characterized in that The user information includes existing user information and potential user information, and obtaining user information includes: Collect users' historical orders; Preprocessing the historical orders; The preprocessing results are classified to determine that the historical orders that have been executed by the user are the existing user information, and the historical orders that have not been executed by the user are the potential user information.

5. The method according to claim 1, characterized in that The step of creating a user demand model according to the user information includes: Determining existing user information in the user information; Creating a behavior profile of the existing user based on the existing user information; Feature extraction is performed on the behavior portrait to construct the first model.

6. The method according to claim 1, characterized in that The step of creating a user demand model according to the user information includes: The preset initial model is iteratively trained using the user information until the prediction accuracy of the initial model reaches a preset standard, thereby obtaining the second model.

7. The method according to claim 6, characterized in that The method of iteratively training a preset initial model by using the user information until the prediction accuracy of the initial model reaches a preset standard to obtain the second model comprises: Organizing the user information to obtain a training set and a test set; Iteratively training the initial model using the training set; Evaluating the prediction accuracy of the initial model using the test set to generate an evaluation result; When the evaluation result is higher than a preset standard, the iterative training of the initial model is terminated to obtain the second model.

8. A device, characterized in that: The device comprises: Information acquisition module, used to obtain user information; A model creation module, used to create a user demand model according to the user information, wherein the user demand model includes a first model and a second model, wherein the first model is used to extract demand information of existing users according to the user information, and the second model is used to predict demand information of potential users according to the user information; The strategy setting module is used to set the target deployment information of charging piles based on the user demand model.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the charging pile deployment method as described in any one of claims 1 to 7.

10. A non-volatile readable storage medium, characterized in that: The non-volatile readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable an electronic device to execute the method for placing a charging pile as described in any one of claims 1 to 7.

Images