An artificial intelligence-based charging pile information determination method and system

Abstract

The application provides a charging pile information determination method and system based on artificial intelligence, and relates to the technical field of charging piles.The method comprises the following steps: acquiring monitoring videos of a current parking lot in a preset time period; determining parking vehicle sequence data of the parking lot, an installation quantity range of charging piles and a parking lot location map based on the monitoring videos of the current parking lot in the preset time period by using a parking lot data processing model; determining a plurality of charging pile simulation installation scheme information and scheme similarity of different charging pile simulation installation schemes based on the parking vehicle sequence data of the parking lot, the installation quantity range of the charging piles and the parking lot location map by using a variational autoencoder; and determining a charging pile target installation scheme based on the plurality of charging pile simulation installation scheme information.The method can accurately determine the arrangement quantity of charging piles.

Description

A method and system for determining charging pile information based on artificial intelligence Technical Field

[0001] This invention relates to the field of charging pile technology, and specifically to a method and system for determining charging pile information based on artificial intelligence. Background Technology

[0002] With the increasing popularity of electric vehicles (EVs), the demand for charging stations is growing rapidly. Rational planning and layout of charging stations is crucial for improving the user experience of EVs, reducing charging wait times, and maximizing the utilization rate of charging facilities. Most existing methods for deploying charging stations rely on manual surveys and experience to determine the installation location and number of stations. This method is highly subjective and easily influenced by personal experience and judgment, making it difficult to guarantee the scientific validity and rationality of the plan. It can easily lead to too many or too few charging stations, resulting in resource waste or a poor user experience.

[0003] Therefore, accurately determining the number of charging stations to be deployed is an urgent problem to be solved. Summary of the Invention

[0004] The main technical problem this invention addresses is how to accurately determine the number of charging stations to be deployed.

[0005] According to a first aspect, the present invention provides a method for determining charging pile information based on artificial intelligence, comprising: acquiring monitoring video of a current parking lot for a preset time period; using a parking lot data processing model to determine parking vehicle sequence data, the range of the number of charging piles to be installed, and a parking lot location map based on the monitoring video of the current parking lot for the preset time period; using a variational autoencoder to determine multiple charging pile simulated installation scheme information and the scheme similarity of different charging pile simulated installation schemes based on the parking vehicle sequence data, the range of the number of charging piles to be installed, and the parking lot location map; and determining a target installation scheme for the charging pile based on the multiple charging pile simulated installation scheme information.

[0006] In one possible implementation, the information on the multiple charging pile simulated installation schemes includes each charging pile simulated installation scheme, the installation cost of each charging pile simulated installation scheme, the charging pile utilization rate, and the user convenience.

[0007] In one possible implementation, determining the target installation scheme for the charging pile based on the multiple simulated installation schemes includes: constructing a charging pile installation graph structure, which includes multiple nodes and multiple edges between the nodes. Each node represents a simulated installation scheme for the charging pile, and the node features of each node include information about a simulated installation scheme for the charging pile and the parking lot location map. The features of the edges between the nodes represent the scheme similarity of the simulated installation schemes for the charging piles. The target installation scheme for the charging pile is then determined by processing the charging pile installation graph structure using a graph convolutional network.

[0008] In one possible implementation, the parking lot data processing model is a gate control loop unit. The input of the parking lot data processing model is the monitoring video of the current parking lot for a preset time period. The output of the parking lot data processing model is the parking vehicle sequence data, the range of the number of charging piles installed, and the parking lot location map.

[0009] According to a second aspect, the present invention provides a charging pile information determination system based on artificial intelligence, comprising:

[0010] The first acquisition module is used to acquire surveillance video of the current parking lot for a preset time period;

[0011] The data processing module is used to determine the parking vehicle sequence data, the range of the number of charging piles installed, and the parking lot location map based on the monitoring video of the current parking lot during a preset time period using the parking lot data processing model.

[0012] The encoding module is used to determine multiple charging pile simulation installation scheme information and scheme similarity of different charging pile simulation installation schemes based on the parking vehicle sequence data of the parking lot, the installation quantity range of the charging piles, and the parking lot location map using a variational autoencoder.

[0013] The determination module is used to determine the target installation scheme of the charging pile based on the information of the multiple simulated installation schemes of the charging pile.

[0014] In one possible implementation, the information on the multiple charging pile simulated installation schemes includes each charging pile simulated installation scheme, the installation cost of each charging pile simulated installation scheme, the charging pile utilization rate, and the user convenience.

[0015] In one possible implementation, the determining module is further configured to:

[0016] A charging pile installation diagram structure is constructed, which includes multiple nodes and multiple edges between the nodes. Each node represents a charging pile simulation installation scheme. The node features of each node include information on a charging pile simulation installation scheme and the parking lot location map. The features of the edges between nodes represent the scheme similarity of the charging pile simulation installation schemes.

[0017] The target installation scheme for the charging pile is determined by processing the installation diagram structure of the charging pile using a graph convolutional network.

[0018] In one possible implementation, the parking lot data processing model is a gate control loop unit. The input of the parking lot data processing model is the monitoring video of the current parking lot for a preset time period. The output of the parking lot data processing model is the parking vehicle sequence data, the range of the number of charging piles installed, and the parking lot location map.

[0019] According to a third aspect, embodiments of the present invention provide an electronic device, including: a processor; a memory; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method as described above, the method including: acquiring surveillance video of a current parking lot for a preset time period; using a parking lot data processing model to determine parking vehicle sequence data, a range of the number of charging piles to be installed, and a parking lot location map based on the surveillance video of the current parking lot for the preset time period; using a variational autoencoder to determine multiple charging pile simulated installation scheme information and scheme similarity of different charging pile simulated installation schemes based on the parking vehicle sequence data, the range of the number of charging piles to be installed, and the parking lot location map; and determining a target installation scheme for the charging piles based on the multiple charging pile simulated installation scheme information.

[0020] According to the fourth aspect, this embodiment provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the program implements the aforementioned artificial intelligence-based charging pile information determination method. The method includes: acquiring monitoring video of a current parking lot for a preset time period; using a parking lot data processing model to determine parking vehicle sequence data, the range of the number of charging piles installed, and a parking lot location map based on the monitoring video of the current parking lot for the preset time period; using a variational autoencoder to determine multiple charging pile simulated installation scheme information and the scheme similarity of different charging pile simulated installation schemes based on the parking vehicle sequence data, the range of the number of charging piles installed, and the parking lot location map; and determining a target charging pile installation scheme based on the multiple charging pile simulated installation scheme information.

[0021] This invention provides a method and system for determining charging pile information based on artificial intelligence. The method includes: acquiring monitoring video of a parking lot for a preset time period; using a parking lot data processing model to determine the parking vehicle sequence data, the range of the number of charging piles to be installed, and the parking lot location map based on the monitoring video of the parking lot for the preset time period; using a variational autoencoder to determine multiple simulated installation scheme information for charging piles and the scheme similarity of different simulated installation schemes based on the parking vehicle sequence data, the range of the number of charging piles to be installed, and the parking lot location map; and determining a target installation scheme for charging piles based on the multiple simulated installation scheme information. This method can accurately determine the number of charging piles to be deployed. Attached Figure Description

[0022] Figure 1 is a schematic diagram of an application scenario of a charging pile information determination method based on artificial intelligence provided in an embodiment of the present invention;

[0023] Figure 2 is a flowchart illustrating a method for determining charging pile information based on artificial intelligence, provided in an embodiment of the present invention.

[0024] Figure 3 is a flowchart illustrating a method for determining a target installation scheme for a charging pile according to an embodiment of the present invention;

[0025] Figure 4 is a schematic diagram of a charging pile information determination system based on artificial intelligence provided in an embodiment of the present invention;

[0026] Figure 5 is a schematic diagram of an electronic device provided in an embodiment of the present invention;

[0027] Figure 6 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0028] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings. Similar elements in different embodiments are referred to by associated similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of the invention. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to the present invention are not shown or described in the specification. This is to avoid obscuring the core parts of the invention with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0029] Figure 1 is a schematic diagram of an application scenario of a charging pile information determination method based on artificial intelligence provided by an embodiment of the present invention. The application scenario of the charging pile information determination method based on artificial intelligence in Figure 1 may include a server 11, a network 12, a terminal 13, and a storage device 14.

[0030] In some embodiments, server 11 may be a single server or a group of servers. Server 11 can access information and / or data stored in terminal 13 or storage device 14 via network 12. In some embodiments, server 11 may be used to perform the AI-based charging pile information determination method shown in FIG2.

[0031] Network 12 can facilitate the exchange of information and / or data. In some embodiments, network 12 can be any form of wired or wireless network, or any combination thereof.

[0032] Terminal 13 may refer to one or more terminal devices used by a user. In some embodiments, terminal 13 may include one or more combinations of mobile devices, tablet computers, laptop computers, etc. For example, the terminal may store surveillance video of the current parking lot for a preset time period.

[0033] Storage device 14 can store data and / or instructions, for example, storage device 14 can store data instructions for a charging pile information determination method based on artificial intelligence.

[0034] In this embodiment of the invention, a method for determining charging pile information based on artificial intelligence is provided, as shown in Figure 2. The method for determining charging pile information based on artificial intelligence includes steps S1 to S4:

[0035] Step S1: Obtain the surveillance video of the current parking lot for a preset time period.

[0036] The current parking lot refers to the specific parking lot where charging pile information is being determined.

[0037] A preset time period refers to a pre-defined time period, typically the peak hours of a parking lot or a specific time period, used to collect data on vehicle entry, exit, and parking. For example, a preset time period could be from 8:00 AM to 8:00 PM.

[0038] The surveillance video is captured by surveillance cameras installed in the parking lot, recording the entry, exit, and parking of vehicles within the parking lot.

[0039] Step S2: Based on the monitoring video of the current parking lot during a preset time period, use the parking lot data processing model to determine the parking vehicle sequence data, the range of the number of charging piles installed, and the parking lot location map.

[0040] The parking lot data processing model is a gate control loop unit. The input of the parking lot data processing model is the monitoring video of the current parking lot for a preset time period. The output of the parking lot data processing model is the parking vehicle sequence data, the range of the number of charging piles installed, and the parking lot location map.

[0041] The Gated Recurrent Unit (GRU) is used to process sequential data and temporal information. The GRU consists of three components: a memory unit, an update gate, and a reset gate. The surveillance video of the current parking lot for a preset time period is sequential data, and the impact of past time points on the current state needs to be considered. Through a gating mechanism, the GRU can better capture long-term dependencies in the sequential data, thereby processing the surveillance video of the current parking lot for the preset time period more accurately.

[0042] The current parking lot's pre-set time-series surveillance video is a continuous time series, recording vehicle entry, exit, and parking. Vehicle entry, exit, and parking behaviors exhibit certain patterns, such as traffic flow variations during peak and off-peak hours. The gate control loop unit, through its gate update and reset mechanisms, can capture these long-term dependencies, thereby accurately extracting the sequence data of parked vehicles, including entry / exit times and parking locations. The surveillance video allows for analysis of parking lot traffic flow at different times. The gate control loop unit can capture these traffic flow trends, thereby inferring a reasonable range for the number of charging stations to be installed. The surveillance video contains not only temporal information but also spatial information, such as vehicle parking locations and parking lot layout. The gate control loop unit can extract a parking lot location map by processing each frame of the video.

[0043] In some embodiments, the parking lot data processing model includes a video processing layer, a vehicle data processing layer, a charging pile information determination layer, and a charging pile range determination layer. The input to the video processing layer is the monitoring video of the current parking lot for a preset time period, and the output is the parking vehicle sequence data and the parking lot location map. The input to the vehicle data processing layer is the parking vehicle sequence data, and the output is the electric vehicle parking quantity sequence data, the average parking time of electric vehicles, and the average charging time of electric vehicles. The input to the charging pile information determination layer is the electric vehicle parking quantity sequence data, the average parking time of electric vehicles, and the average charging time of electric vehicles. The output of the charging pile information determination layer is the number of multiple recommended charging piles and the recommendation degree of each recommended charging pile. The input to the charging pile range determination layer is the number of multiple recommended charging piles, the recommendation degree of each recommended charging pile, and the parking lot location map. The output of the charging pile range determination layer is the range of the number of charging piles to be installed.

[0044] By dividing the parking lot data processing model into a video processing layer, a vehicle data processing layer, a charging pile information determination layer, and a charging pile range determination layer, this layered design not only makes system development and maintenance more efficient but also ensures the progressive refinement and accuracy of data processing, enabling a better determination of the range of charging pile installations. The video processing layer extracts basic vehicle entry, exit, and parking information from surveillance video, providing foundational data for subsequent processing. The vehicle data processing layer identifies electric vehicles from parking vehicle sequence data, counting their number and parking time. The charging pile information determination layer generates multiple recommended charging pile numbers and calculates the recommendation degree for each number, providing a reference for the final determination of the charging pile quantity. The charging pile range determination layer combines the multiple recommended charging pile numbers and recommendation degrees with the parking lot location map to comprehensively evaluate the range of charging pile installations.

[0045] Parking vehicle sequence data is a time-series record of vehicles entering, exiting, and parking in a parking lot, including vehicle license plate number, entry and exit time, parking location, etc.

[0046] The parking lot floor plan includes markings of key locations such as parking spaces, entrances, and exits.

[0047] The electric vehicle parking quantity sequence data records the number of electric vehicles in the parking lot at each time.

[0048] The average parking time of an electric vehicle is the average time that an electric vehicle spends in a parking lot.

[0049] The average charging time for an electric vehicle is the average time it takes for an electric vehicle to charge in a parking lot.

[0050] The recommended number of charging stations is based on the number of electric vehicles parked, the parking time, and the charging time.

[0051] The recommendation score is the recommendation score for each recommended number of charging stations, which indicates the rationality and feasibility of the recommended number of charging stations.

[0052] Step S3: Based on the parking vehicle sequence data of the parking lot, the range of the number of charging piles installed, the parking lot location map, a variational autoencoder is used to determine the information of multiple charging pile simulation installation schemes and the similarity of different charging pile simulation installation schemes.

[0053] The information on the multiple charging pile simulation installation schemes includes each charging pile simulation installation scheme, the installation cost of each charging pile simulation installation scheme, the charging pile utilization rate, and the user convenience.

[0054] The information on multiple charging pile simulated installation schemes consists of a series of hypothetical charging pile installation plans generated by a variational autoencoder. Each simulated installation scheme includes the specific scheme, its installation cost, charging pile utilization rate, and user convenience.

[0055] Each charging pile simulation installation plan includes, but is not limited to, information such as the specific location and quantity of the charging piles.

[0056] Installation cost refers to the total financial investment required to implement a charging pile installation plan.

[0057] Charging pile utilization rate can be used to measure the frequency with which charging piles are actually used.

[0058] User convenience reflects whether the layout of charging stations is convenient for users. For example, the shorter the distance between the charging station and the parking lot entrance, the higher the user convenience.

[0059] The similarity of different charging pile installation schemes is used to evaluate the differences between the schemes and help the graph convolutional network determine the optimal scheme.

[0060] A variational autoencoder (VAE) is a generative model used to learn latent representations of data and generate new data samples. A VAE consists of an encoder and a decoder. The encoder maps the input data to a latent space, and the decoder maps points in the latent space back to the data space. The inputs to the VAE are the parking vehicle sequence data of the parking lot, the range of the number of charging piles installed, and the parking lot location map. The outputs of the VAE are information on multiple simulated charging pile installation schemes and the similarity between different simulated installation schemes. The encoder maps these input data to the latent space, generating multiple latent representations. The decoder maps points in the latent space back to the data space, generating multiple simulated charging pile installation schemes. Each scheme includes information such as installation location, installation cost, charging pile utilization rate, and user convenience.

[0061] Step S4: Determine the target installation scheme for the charging pile based on the information of the multiple simulated installation schemes for charging piles.

[0062] In some embodiments, Figure 3 is a flowchart illustrating a method for determining a target installation scheme for a charging pile according to an embodiment of the present invention. The method for determining the target installation scheme for the charging pile includes steps S21-S22:

[0063] Step S21: Construct a charging pile installation diagram structure. The charging pile installation diagram structure includes multiple nodes and multiple edges between the nodes. Each node represents a charging pile simulation installation scheme. The node features of each node include information on a charging pile simulation installation scheme and the parking lot location map. The features of the edges between nodes represent the scheme similarity of the charging pile simulation installation schemes.

[0064] The charging pile installation diagram structure is a graph structure, where each node represents a charging pile simulation installation scheme. The node features of each node include information on a charging pile simulation installation scheme and a parking lot location map. The features of the edges between nodes represent the scheme similarity of the charging pile simulation installation schemes.

[0065] Step S22: Process the charging pile installation diagram structure based on graph convolutional network to determine the target installation scheme of the charging pile.

[0066] Graph Convolutional Network (GCN) is a neural network architecture specifically designed for processing graph-structured data. The input to a GCN is the charging pile installation graph structure, and the output is the target installation scheme for the charging pile.

[0067] Constructing a charging pile installation graph structure can effectively organize and represent multiple simulated charging pile installation schemes and their interrelationships. This graph structure not only clearly displays the specific information of each installation scheme but also expresses the similarity between these schemes through edges between nodes. Graph convolutional networks (GCNNs) can effectively learn features on the graph structure, capturing the dependencies between nodes. This is particularly important for selecting charging pile installation schemes, as different schemes have complex mutual influences. GCNNs can simultaneously consider the features of a node itself (such as the number, type, and location of charging piles) as well as information from its neighboring nodes. This means that when processing the charging pile installation graph structure, GCNNs can consider not only the characteristics of individual schemes but also the influence of other similar or related schemes, thus providing a more comprehensive evaluation of the merits of each scheme.

[0068] The optimal target installation scheme for charging piles is obtained through graph convolutional network decision-making.

[0069] Based on the same inventive concept, Figure 4 is a schematic diagram of an artificial intelligence-based charging pile information determination system provided by an embodiment of the present invention. The artificial intelligence-based charging pile information determination system includes:

[0070] The first acquisition module 41 is used to acquire the monitoring video of the current parking lot for a preset time period;

[0071] Data processing module 42 is used to determine the parking vehicle sequence data, the range of the number of charging piles installed, and the parking lot location map of the parking lot based on the monitoring video of the current parking lot during a preset time period using the parking lot data processing model.

[0072] The encoding module 43 is used to determine multiple charging pile simulation installation scheme information and scheme similarity of different charging pile simulation installation schemes based on the parking vehicle sequence data of the parking lot, the installation quantity range of the charging piles, and the parking lot location map using a variational autoencoder.

[0073] The determination module 44 is used to determine the target installation scheme of the charging pile based on the information of the multiple simulated installation schemes of the charging pile.

[0074] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, as shown in FIG5, comprising:

[0075] The system includes: a processor 51; a memory 52; and a computer program; wherein the computer program is stored in the memory 52 and configured to be executed by the processor 51 to implement the artificial intelligence-based charging pile information determination method provided above, the method including: acquiring monitoring video of the current parking lot for a preset time period; using a parking lot data processing model to determine the parking vehicle sequence data, the range of the number of charging piles installed, and the parking lot location map of the parking lot based on the monitoring video of the current parking lot for the preset time period; using a variational autoencoder to determine multiple charging pile simulated installation scheme information and the scheme similarity of different charging pile simulated installation schemes based on the parking vehicle sequence data, the range of the number of charging piles installed, and the parking lot location map of the parking lot; and determining the target installation scheme of the charging pile based on the multiple charging pile simulated installation scheme information.

[0076] Based on the same inventive concept, this embodiment provides a computer-readable storage medium storing a computer program. When executed by processor 51, the program implements the aforementioned artificial intelligence-based charging pile information determination method. The method includes: acquiring monitoring video of a current parking lot for a preset time period; using a parking lot data processing model to determine parking vehicle sequence data, the range of the number of charging piles installed, and a parking lot location map based on the monitoring video of the current parking lot for the preset time period; using a variational autoencoder to determine multiple charging pile simulated installation scheme information and the scheme similarity of different charging pile simulated installation schemes based on the parking vehicle sequence data, the range of the number of charging piles installed, and the parking lot location map; and determining a target charging pile installation scheme based on the multiple charging pile simulated installation scheme information.

[0077] The AI-based charging pile information determination method provided in this application can be applied to terminal devices (such as mobile phones), tablets, laptops, ultra-mobile personal computers (UMPCs), handheld computers, netbooks, personal digital assistants (PDAs), wearable devices (such as smartwatches, smart glasses, or smart helmets), augmented reality (AR) / virtual reality (VR) devices, smart home devices, in-vehicle computers, and other electronic devices. This application does not impose any limitations on this.

[0078] Taking mobile phone 100 as an example of the above-mentioned electronic device, Figure 6 shows a schematic diagram of the structure of mobile phone 100.

[0079] As shown in Figure 6, the mobile phone 100 may include a processing module 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone jack 170D, a sensor module 180, buttons 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0080] The processing module 110 may include one or more processing units, such as an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). These different processing units may be independent devices or integrated into one or more processors.

[0081] The processing module 110 can be used to: acquire monitoring video of the current parking lot for a preset time period; determine the parking vehicle sequence data, the range of the number of charging piles to be installed, and the parking lot location map using a parking lot data processing model based on the monitoring video of the current parking lot for the preset time period; determine multiple charging pile simulated installation scheme information and the scheme similarity of different charging pile simulated installation schemes using a variational autoencoder based on the parking vehicle sequence data, the range of the number of charging piles to be installed, and the parking lot location map; and determine the target installation scheme of the charging piles based on the multiple charging pile simulated installation scheme information.

[0082] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0083] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0084] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0085] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0086] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method for determining charging pile information based on artificial intelligence, characterized in that, include: Obtain surveillance video of the current parking lot for a preset time period; Based on the monitoring video of the current parking lot during a preset time period, a parking lot data processing model is used to determine the parking vehicle sequence data, the range of the number of charging piles installed, and the parking lot location map. The parking lot data processing model is a gate control loop unit. The input of the parking lot data processing model is the monitoring video of the current parking lot during the preset time period, and the output of the parking lot data processing model is the parking vehicle sequence data, the range of the number of charging piles installed, and the parking lot location map. The parking lot data processing model includes a video processing layer, a vehicle data processing layer, a charging pile information determination layer, and a charging pile range determination layer. The input of the video processing layer is the monitoring video of the current parking lot during the preset time period, and the output of the video processing layer is the parking vehicle sequence data and the parking lot location map. The input of the vehicle data processing layer is the parking vehicle sequence data, and the output of the vehicle data processing layer is the electric vehicle parking quantity sequence data, the average parking time of electric vehicles, and the average charging time of electric vehicles. The input of the charging pile information determination layer is the electric vehicle parking quantity sequence data, the average parking time of electric vehicles, and the average charging time of electric vehicles. The output of the charging pile information determination layer is multiple recommended charging pile numbers and the recommendation degree of each recommended charging pile number. The input of the charging pile range determination layer is multiple recommended charging pile numbers. The number of charging piles, the recommendation rate of each recommended number of charging piles, and the parking lot location map are used to determine the range of charging pile installation quantities. Based on the parking vehicle sequence data of the parking lot, the range of charging pile installation quantities, and the parking lot location map, a variational autoencoder is used to determine information on multiple simulated charging pile installation schemes and the similarity of different simulated charging pile installation schemes. This information includes the installation cost, utilization rate, and user convenience of each simulated charging pile installation scheme. Each simulated charging pile installation scheme includes the specific location and number of charging piles. The process involves: determining a target installation scheme for a charging pile based on the information of multiple simulated installation schemes for charging piles. This determination includes: constructing a charging pile installation graph structure, which comprises multiple nodes and multiple edges between nodes. Each node represents a simulated installation scheme for a charging pile. The node features of each node include information about a simulated installation scheme for a charging pile and the parking lot location map. The features of the edges between nodes represent the scheme similarity of the simulated installation schemes for the charging piles. The process also involves processing the charging pile installation graph structure using a graph convolutional network to determine the target installation scheme for the charging pile.

2. A charging pile information determination system based on artificial intelligence, characterized in that, include: The first acquisition module is used to acquire surveillance video of the current parking lot for a preset time period; The data processing module is used to determine the parking vehicle sequence data, the range of the number of charging piles installed, and the parking lot location map based on the monitoring video of the current parking lot during a preset time period using a parking lot data processing model. The parking lot data processing model is a gate control loop unit. The input to the parking lot data processing model is the monitoring video of the current parking lot during the preset time period, and the output of the parking lot data processing model is the parking vehicle sequence data, the range of the number of charging piles installed, and the parking lot location map. The parking lot data processing model includes a video processing layer, a vehicle data processing layer, a charging pile information determination layer, and a charging pile range determination layer. The input to the video processing layer is the monitoring video of the current parking lot during the preset time period. The output of the frequency processing layer is the parking vehicle sequence data and the parking lot location map. The input of the vehicle data processing layer is the parking vehicle sequence data and the output of the vehicle data processing layer is the electric vehicle parking quantity sequence data, the average parking time of electric vehicles, and the average charging time of electric vehicles. The input of the charging pile information determination layer is the electric vehicle parking quantity sequence data, the average parking time of electric vehicles, and the average charging time of electric vehicles. The output of the charging pile information determination layer is the number of multiple recommended charging piles and the recommendation degree of each recommended charging pile. The input of the charging pile range determination layer is the number of multiple recommended charging piles, the recommendation degree of each recommended charging pile, and the parking lot location map. The output of the charging pile range determination layer is the range of the number of charging piles to be installed. An encoding module is used to determine multiple simulated installation schemes for charging piles based on the parking vehicle sequence data of the parking lot, the installation quantity range of the charging piles, and the parking lot location map using a variational autoencoder. The similarity between different simulated installation schemes is also considered. The information on the multiple simulated installation schemes includes each scheme, its installation cost, utilization rate, and user convenience. Each scheme includes the specific location and quantity of the charging piles. A determination module is used to determine a target installation scheme for the charging piles based on the information on the multiple simulated installation schemes. This module is further used to: construct a charging pile installation graph structure, which includes multiple nodes and multiple edges between nodes. Each node represents a simulated installation scheme for the charging piles. The node features of each node include information on a simulated installation scheme for the charging piles and the parking lot location map. The features of the edges between nodes represent the similarity between the simulated installation schemes. Finally, a graph convolutional network is used to process the charging pile installation graph structure to determine the target installation scheme for the charging piles.

3. An electronic device, characterized in that, include: processor; Memory; And a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the artificial intelligence-based charging pile information determination method as described in claim 1.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the artificial intelligence-based charging pile information determination method as described in claim 1.

Images