Vehicle demand estimation method, device, electronic device and storage medium

Abstract

The embodiments of the present application provide a vehicle demand estimation method, device, electronic device and storage medium, which relate to the technical field of vehicle demand estimation. The method includes: obtaining historical order data within a parking fence, creating a demand estimation model based on the historical order data, wherein the historical order data includes vehicle outflow and vehicle supply; performing valuation calculations on sample data to obtain an outflow estimate; training the demand estimation model based on the outflow estimate to obtain a trained demand estimation model; and obtaining a vehicle demand estimate based on the trained demand estimation model.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the technical field of vehicle demand estimation, and more specifically, to a vehicle demand estimation method, device, electronic device, and storage medium. Background Art

[0002] In the shared bike riding business, there are three supply and demand states: oversupply, undersupply, and supply and demand balance. When supply and demand are in different states, the actions to be taken and the optimization goals are different. Estimating demand is an important part of realizing supply and demand diagnosis, describing the current supply and demand matching status in the operating area, and then guiding the downstream to achieve better scheduling.

[0003] In the scheduling scenario of the bicycle business, it is necessary to estimate the gap in the riding demand of the parking fence in the future. This gap is used as a key factor in scheduling decisions, and the core issue of the gap calculation is the estimation of demand. However, in the electric motorcycle business, due to the particularity of the riding scenario, the demand cannot be fully observed. The existing technology uses the sum of the daily riding outflow of the parking fence and the loss of low power due to multiple code scanning as the demand for the fence. This method is feasible when the vehicle supply is sufficient, but when the vehicle supply is insufficient, the number of riding orders will be limited by supply, because there may be no vehicles in a certain electronic fence, that is, all the vehicles have been ridden out, but at this time there are still users who want to ride vehicles from the electronic fence.

[0004] In summary, the existing vehicle demand calculation method has the possibility of ignoring potential demand, resulting in low accuracy of the calculated demand. Summary of the invention

[0005] An object of the present disclosure is to provide a new technical solution for a vehicle demand estimation method, device, electronic device and storage medium.

[0006] According to a first aspect of the present disclosure, an embodiment of a vehicle demand estimation method is provided, the method comprising: acquiring historical order data within a parking fence, and creating a demand estimation model according to the historical order data, wherein the historical order data comprises a vehicle outflow and a vehicle supply;

[0007] Perform valuation calculation on sample data to obtain estimated outflow volume;

[0008] Training the demand estimation model according to the outflow estimation value to obtain a trained demand estimation model;

[0009] According to the trained demand estimation model, a vehicle demand estimation value is obtained.

[0010] Optionally, creating a demand estimation model according to the historical order data includes:

[0011] Based on historical order data, obtain the vehicle outflow and vehicle supply within a preset time period;

[0012] According to the vehicle outflow and vehicle supply in the preset time period, a normal distribution model is established to obtain the mean and variance of the vehicle outflow, and determine the initial parameters of the demand estimation model.

[0013] Optionally, before performing valuation calculation on the sample data, the method further includes:

[0014] The historical order data is screened to obtain sample data, wherein the vehicle supply of the sample data is equal to the vehicle outflow.

[0015] Optionally, performing valuation calculation on the sample data to obtain an estimated value of the outflow includes:

[0016] According to the initial parameters of the demand estimation model and the vehicle outflow in the sample data, an expectation maximization algorithm is used to obtain the outflow estimation value, and the outflow estimation value is greater than or equal to the vehicle outflow in the sample data.

[0017] Optionally, the training the demand estimation model according to the outflow estimation value to obtain the trained demand estimation model includes:

[0018] The outflow estimation value and the vehicle supply in the sample data are used as inputs of the demand estimation model, and the demand estimation model is trained to obtain a trained demand estimation model, wherein the model parameters of the trained demand estimation model are within a preset range.

[0019] Optionally, obtaining a vehicle demand estimation value according to the trained demand estimation model includes:

[0020] According to the trained demand estimation model, the vehicle outflow is output, and the vehicle outflow data is used as the vehicle demand estimation value.

[0021] According to a second aspect of the present disclosure, a vehicle demand estimation device is provided, the device comprising:

[0022] A model creation module, used for acquiring historical order data within the parking fence, and creating a demand estimation model according to the historical order data, wherein the historical data includes vehicle outflow and vehicle supply;

[0023] The estimation module is used to perform valuation calculation on the sample data to obtain the estimated value of the outflow;

[0024] A model training module, used for training the demand estimation model according to the outflow estimation value to obtain a trained demand estimation model;

[0025] The output module is used to obtain the vehicle demand estimation value according to the trained demand estimation model.

[0026] Optionally, the model training module is specifically used for:

[0027] The outflow estimation value and the vehicle supply in the sample data are used as inputs of the demand estimation model, and the demand estimation model is trained to obtain a trained demand estimation model, wherein the model parameters of the trained demand estimation model are within a preset range.

[0028] According to a third aspect of the present disclosure, an embodiment of an electronic device is provided, comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect of this specification.

[0029] According to a fourth aspect of the present disclosure, an embodiment of a readable storage medium is provided, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect of this specification are implemented.

[0030] One beneficial effect of the disclosed embodiment is that the embodiment creates a demand estimation model through historical order data, performs valuation calculation on sample data, and obtains an outflow estimation value; trains the demand estimation model based on the outflow estimation value to obtain a trained demand estimation model; and obtains a vehicle demand estimation value based on the trained demand estimation model. Considering the impact of supply on demand, the outflow of riding when supply is limited can be re-estimated, so that the calculated demand is closer to the demand under sufficient supply conditions.

[0031] Other features and advantages of the present specification will become apparent from the following detailed description of exemplary embodiments of the present specification with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the specification and, together with the description, serve to explain the principles of the specification.

[0033] Figure 1 A system architecture diagram of a vehicle demand estimation method provided by an embodiment of the present disclosure;

[0034] Figure 2 is a flow chart of the vehicle demand estimation method of this embodiment;

[0035] Figure 3 A distribution histogram and an approximate normal distribution diagram of vehicle outflow in the prior art provided for this embodiment;

[0036] Figure 4 The distribution histogram and the approximate normal distribution diagram of the vehicle outflow volume calculated by the method of this embodiment;

[0037] Figure 5 is a functional block diagram of a vehicle demand estimation device according to one embodiment;

[0038] Figure 6 is a block diagram of an electronic device according to an embodiment. DETAILED DESCRIPTION

[0039] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0040] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0041] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0042] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0043] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0044] The embodiments of the present disclosure relate to application scenarios of vehicle riding needs.

[0045] The riding demand of vehicles is an important data to guide the dispatch of bicycles. The current estimation of riding demand is based on the actual number of riding orders. However, the supply of vehicles within a certain electronic fence is certain. When the supply of vehicles is less than the demand for bicycles, the actual number of riding orders can no longer represent the real demand. Therefore, a more reasonable way is needed to estimate the real riding demand of vehicles.

[0046] In view of the technical problems existing in the above implementation methods, the present disclosure provides a vehicle demand estimation method, device, equipment, storage medium and system. By performing demand estimation through the EM algorithm, the gap in riding demand can be better calculated and the scheduling of bicycles can be better guided.

[0047] <Hardware Configuration>

[0048] Figure 1 A system architecture diagram that can be used to implement the vehicle demand estimation method provided in an embodiment of the present disclosure.

[0049] like Figure 1 As shown, the system includes a server 2000 , a terminal device 1000 and a vehicle 3000 .

[0050] The server 2000 and the terminal device 1000, as well as the server 2000 and the vehicle 3000, can be connected to each other through a network 4000. The network 4000 based on which the vehicle 3000 and the server 2000, as well as the terminal device 1000 and the server 2000 communicate can be the same or different. The network 4000 can be a wireless communication network or a wired communication network, and can be a local area network or a wide area network.

[0051] The server 2000 provides a business point for processing, database, and communication facilities. The server 2000 can be an integrated server, a distributed server across multiple computers, a computer data center, a cloud server, or a server cluster deployed in the cloud. The server can be of various types, such as but not limited to a network server, a news server, a mail server, a message server, an advertising server, a file server, an application server, an interactive server, a database server, or a proxy server. In some embodiments, each server may include hardware, software, or an embedded logic component or a combination of two or more such components for executing the appropriate functions supported or implemented by the server. The specific configuration of the server 2000 may include but is not limited to a processor 2100, a memory 2200, an interface device 2300, and a communication device 2400. The processor 2100 is used to execute a computer program written in an instruction set of an architecture such as x86, Arm, RISC, MIPS, SSE, etc. The memory 2200 is, for example, a ROM (read-only memory), a RAM (random access memory), a non-volatile memory such as a hard disk, etc. The interface device 2300 is, for example, a USB interface, a serial interface, a parallel interface, etc. The communication device 2400 is, for example, capable of wired communication or wireless communication, and may include WiFi communication, Bluetooth communication, 2G / 3G / 4G / 5G communication, etc.

[0052] As used in the embodiments of the present disclosure, the memory 2200 of the server 2000 is used to store a computer program, which is used to control the processor 2100 to operate to implement the method according to the embodiments of the present disclosure. A technician can design the computer program according to the scheme disclosed in the present disclosure. How the computer program controls the processor to operate is well known in the art, so it will not be described in detail here.

[0053] It should be understood by those skilled in the art that Figure 1 In addition to the devices shown, the server 2000 may also include other devices, which are not limited here.

[0054] In this embodiment, the terminal device 1000 is, for example, a mobile phone, a portable computer, a tablet computer, a PDA, a wearable device, etc.

[0055] The terminal device 1000 is installed with a vehicle application client, and the user can use the vehicle 3000 by operating the vehicle application client.

[0056] The terminal device 1000 may include but is not limited to a processor 1100, a memory 1200, an interface device 1300, a communication device 1400, a display device 1500, an input device 1600, a speaker 1700, a microphone 1800, and the like. Among them, the processor 1100 may be a central processing unit CPU, a graphics processing unit GPU, a microprocessor MCU, etc., for executing a computer program, and the computer program may be written in an instruction set of an architecture such as x86, Arm, RISC, MIPS, SSE, etc. The memory 1200 may include, for example, a ROM (read-only memory), a RAM (random access memory), a non-volatile memory such as a hard disk, etc. The interface device 1300 may include, for example, a USB interface, a serial interface, a parallel interface, etc. The communication device 1400 may, for example, be capable of wired communication using an optical fiber or cable, or wireless communication, and may specifically include WiFi communication, Bluetooth communication, 2G / 3G / 4G / 5G communication, etc. The display device 1500 may be, for example, a liquid crystal display screen, a touch display screen, etc. The input device 1600 may include, for example, a touch screen, a keyboard, somatosensory input, etc. The speaker 1170 is used to output audio signals, and the microphone 1180 is used to pick up audio signals.

[0057] In the embodiment of the present disclosure, the memory 1200 of the terminal device 1000 is used to store a computer program, which is used to control the processor 1100 to operate to execute the method of the embodiment of the present disclosure. How the computer program controls the processor to operate is well known in the art, so it is not described in detail here. The terminal device 1000 can be installed with an intelligent operating system (such as Windows, Linux, Android, IOS, etc.) and application software.

[0058] It should be understood by those skilled in the art that although Figure 1 Multiple devices of the terminal device 1000 are shown in the figure, but the terminal device 1000 of the embodiment of the present disclosure may only involve some of the devices, for example, only the processor 1100, the memory 1200, etc.

[0059] Vehicle 3000 may be Figure 1 The bicycle shown in the figure may also be in various forms such as a tricycle, an electric power-assisted bicycle, a motorcycle, and a four-wheeled passenger vehicle, and the like, without limitation thereto.

[0060] The vehicle 3000 may include, but is not limited to, a processor 3100, a memory 3200, an interface device 3300, a communication device 3400, a display device 3500, an input device 3600, a speaker 3700, a microphone 3800, and the like. The processor 3100 may be a microprocessor MCU, and the like. The memory 3200 may include, for example, a ROM (read-only memory), a RAM (random access memory), a non-volatile memory such as a hard disk, and the like. The interface device 3300 may include, for example, a USB interface, a serial interface, a parallel interface, and the like. The communication device 3400 may, for example, be capable of performing wired communication using optical fiber or cable, or performing wireless communication, and may specifically include WiFi communication, Bluetooth communication, 2G / 3G / 4G / 5G communication, and the like. The display device 3500 may, for example, be a liquid crystal display screen, a touch display screen, and the like. The input device 3600 may, for example, include a touch screen, a keyboard, and the like, or may be a microphone for inputting voice information. The vehicle 3000 may output audio signals through a speaker 3700, and collect audio signals through a microphone 3800.

[0061] In the embodiment of the present disclosure, the memory 3200 of the vehicle 3000 is used to store a computer program, and the computer program is used to control the processor 3100 to operate to perform information interaction with the server 2000, such as uploading the location information of the vehicle to the server so that the server determines whether the vehicle exceeds the limited range of the electronic fence. How the computer program controls the processor to operate is well known in the art, so it will not be described in detail here.

[0062] Despite Figure 1 , multiple devices of the vehicle 3000 are shown; however, the present invention may only involve some of the devices, for example, the vehicle 3000 only involves the processor 3100 , the memory 3200 and the communication device 3400 .

[0063] It should be understood that although Figure 1Only one server 2000, terminal device 1000, and vehicle 3000 are shown, but this does not mean that their respective numbers are limited. The system may include multiple servers 2000, multiple terminal devices 1000, and multiple vehicles 3000.

[0064] Hereinafter, various embodiments and examples according to the present invention are described with reference to the accompanying drawings.

[0065] <Method Example>

[0066] Figure 2 is a flow chart of a vehicle demand estimation method according to an embodiment, which can be implemented by the server 2000 .

[0067] like Figure 2 As shown, the vehicle demand estimation method of this embodiment may include the following steps:

[0068] S210: Obtain historical order data within the parking fence, and create a demand estimation model based on the historical order data.

[0069] Optionally, the parking fence may be a defined area with an area identification, for example, an area defined by a white fence line on the roadside used to define a parking area, or the parking fence may be an electronic fence.

[0070] Optionally, the historical order data includes the vehicle supply and vehicle outflow within any parking fence. The vehicle supply can be pre-stored in the server's own database, and the vehicle outflow can be determined based on the vehicle riding orders within the fence. The vehicle riding orders can be obtained by sending vehicle usage information to the server through the electronic terminal used by the user.

[0071] In an example, a demand estimation model is created based on historical order data. The vehicle outflow and vehicle supply within a preset time period can be obtained based on the historical order data. A normal distribution model is established based on the vehicle outflow and vehicle supply within the preset time period to obtain the mean and variance of the vehicle outflow, and determine the initial parameters of the demand estimation model.

[0072] For example, the historical time window length and time period in the historical order data are obtained to obtain the vehicle outflow and vehicle supply in the corresponding time period within the time window length. The time window length represents N consecutive working days or N non-working days, and the time period represents a specific hour interval T.

[0073] In an example, ignoring the demand of a small number of users who are lost due to multiple scans, when the vehicle supply is always sufficient, the vehicle outflow is only controlled by the vehicle demand. It can be understood that the distribution of vehicle outflow at this time can be directly approximated to the distribution of vehicle demand. Therefore, by using the existing vehicle outflow data for maximum likelihood estimation, the mean and variance of the vehicle demand distribution can be obtained, thereby calculating the actual vehicle demand.

[0074] However, when the vehicle supply is insufficient, the vehicle outflow is limited by the vehicle supply, which is equal to the vehicle supply and less than the vehicle demand. At this time, the real vehicle demand is hidden, so it is necessary to estimate the vehicle demand. This embodiment uses a normal distribution model to characterize the distribution state of vehicle demand when the vehicle supply is sufficient.

[0075] Therefore, this embodiment establishes a normal distribution model based on historical order data, obtains the mean and variance of vehicle outflow, and determines the initial parameters of the demand estimation model. When the vehicle supply is greater than the vehicle demand, the output result is accurate, but it is not applicable to the case where the vehicle supply is less than or equal to the vehicle demand. Therefore, it is necessary to optimize the demand estimation model based on sample data.

[0076] S220: Perform valuation calculation on the sample data to obtain an estimated value of the outflow.

[0077] It can be seen from the above step S210 that when the vehicle supply in the historical order data is greater than the vehicle outflow, the result output by the demand estimation model is accurate. When the vehicle supply is less than or equal to the vehicle outflow, there may be potential vehicle demand. Therefore, in order to improve the prediction ability of the model. Before performing valuation calculations on the sample data, this embodiment needs to select appropriate sample data first, and obtain sample data by screening the historical order data, wherein the vehicle supply of the sample data is equal to the vehicle outflow. There are two possibilities for the vehicle outflow to be equal to the vehicle supply. One is that the vehicle supply can just meet the vehicle demand, and at this time the vehicle outflow is the vehicle demand. The other is that the vehicle supply is insufficient, resulting in the vehicle outflow can only be equal to the vehicle supply. Therefore, this embodiment trains the demand estimation model through sample data in which the vehicle outflow is equal to the vehicle supply.

[0078] This embodiment uses an expectation maximization algorithm based on the initial parameters of the demand estimation model and the vehicle outflow in the sample data to obtain an outflow estimation value, wherein the outflow estimation value is greater than or equal to the vehicle outflow in the sample data.

[0079] In one example, let the sample set [x0, x1, ..., x n ], for each sample point x i, there is demand i , supply i and outflow i , the following shows the relationship between the three, as well as the mathematical abstraction of the problem:

[0080] When demand i <supply i outflow i ≈demand i ;

[0081] When demand i ≥supply i outflow i ≈supply i ;

[0082] But when supply i > demand i , outflow cannot be calculated i , assuming that the outflow distribution under sufficient supply is known, that is, the demand distribution is known, the simulated value of vehicle outflow under sufficient supply can be estimated by the following formula:

[0083]

[0084] Among them, outflow′ i is the estimated value of outflow, x is the sample point, θ is the mean μ and variance σ of the normal distribution 2 However, since the demand distribution is unknown, as a hidden variable, the demand distribution cannot be known in advance. Therefore, this embodiment re-estimates the outflow of the sample with limited supply by maximizing the expectation, that is, solving the expectation maximization under the current parameters to obtain the outflow estimate, which is the value of expectation maximization.

[0085] S230: Train the demand estimation model according to the outflow estimation value to obtain a trained demand estimation model.

[0086] In this embodiment, the outflow estimation value and the vehicle supply in the sample data are used as inputs of the demand estimation model, and the demand estimation model is trained to obtain a trained demand estimation model.

[0087] In one embodiment, since the outflow estimation value is an estimated value, it needs to be repeatedly verified, and the outflow estimation value obtained from each sample is used as the input of the model, and the model is iterated until the iteration stop criterion is met. In one example, the iteration stop criterion is that the model parameters of the trained demand estimation model are within a preset range.

[0088] The trained model also satisfies the normal distribution. Therefore, the model parameters of the trained demand estimation model can be recalculated by the maximum likelihood estimation method, that is, the mean μ and variance σ of the normal distribution function satisfied by the vehicle outflow. 2 When the changes in the mean and variance are within the range of δ for two consecutive times, it means that the trained demand estimation model meets the standard.

[0089] S240: Obtain vehicle demand estimation values ​​according to the trained demand estimation model.

[0090] It can be understood that the vehicle outflow estimation value obtained in step S220 of this embodiment is greater than the total number of vehicles. If this estimation is established, the vehicle supply should be sufficient. In other words, when the total number of vehicles is sufficient, the vehicle outflow obtained according to the model of this embodiment is achievable, and when the vehicle supply is sufficient, the vehicle outflow is equal to the vehicle demand. Therefore, this embodiment can output the vehicle outflow according to the trained demand estimation model, and use the vehicle outflow data as the vehicle demand estimation value.

[0091] It is understandable that after creating the vehicle demand estimation model, the model needs to be validated, refer to Figure 3 , which shows the distribution histogram and approximate normal distribution of the vehicle outflow of a subway station during the evening peak hours of N consecutive working days. It can be seen that the initial mean and variance are 180.43 and 103.73 respectively. According to the relationship between outflow and supply, the outflow of the sample points with limited supply is determined to be [154, 102, 143, 175, 128, 145, 94, 113, 111]. The algorithm of this embodiment is used to re-estimate the outflow of these points, and update the parameters μ and σ until the iteration stop condition is reached. The distribution histogram after re-estimating the outflow of cycling is shown in the figure. Figure 4 As shown in Figure 2, the final estimated cycling outflow has a mean of 196.78 and a variance of 102.95, and is Figure 4 It can be seen that after re-estimation, the approximate normal distribution of cycling outflow is closer to the actual distribution, indicating that the data has become more complete and in line with expectations.

[0092] This embodiment creates a demand estimation model through historical order data, performs valuation calculation on sample data, and obtains an outflow estimation value; trains the demand estimation model based on the outflow estimation value to obtain a trained demand estimation model; and obtains a vehicle demand estimation value based on the trained demand estimation model. Taking into account the impact of supply on demand, the outflow of riding when supply is limited can be re-estimated, so that the calculated demand is closer to the demand under sufficient supply conditions.

[0093] <Device Example>

[0094] Figure 5 is a functional block diagram of an apparatus according to an embodiment. Figure 5 As shown, the vehicle demand estimation device 500 may include:

[0095] The model creation module 501 is used to obtain historical order data within the parking fence and create a demand estimation model based on the historical order data, wherein the historical data includes vehicle outflow and vehicle supply.

[0096] The estimation module 502 is used to perform estimation calculation on the sample data to obtain an estimated value of the outflow.

[0097] The model training module 503 is used to train the demand estimation model according to the outflow estimation value to obtain a trained demand estimation model.

[0098] The output module 504 is used to obtain a vehicle demand estimation value according to the trained demand estimation model.

[0099] In a feasible example, the model creation module 501 is used to obtain the vehicle outflow and vehicle supply within a preset time period based on the historical order data;

[0100] According to the vehicle outflow and vehicle supply in the preset time period, a normal distribution model is established to obtain the mean and variance of the vehicle outflow, and determine the initial parameters of the demand estimation model.

[0101] In a feasible example, the estimation module 502 is used to filter the historical order data to obtain sample data, and the vehicle supply of the sample data is equal to the vehicle outflow.

[0102] In a feasible example, the estimation module 502 is used to obtain the outflow estimation value based on the initial parameters of the demand estimation model and the vehicle outflow in the sample data using an expectation maximization algorithm, and the outflow estimation value is greater than or equal to the vehicle outflow in the sample data.

[0103] In a feasible example, the model training module 503 is used to use the outflow estimation value and the vehicle supply in the sample data as inputs of the demand estimation model, train the demand estimation model, and obtain a trained demand estimation model, wherein the model parameters of the trained demand estimation model are within a preset range.

[0104] In a feasible example, the output module 504 is used to output the vehicle outflow according to the trained demand estimation model, and use the vehicle outflow data as the vehicle demand estimation value.

[0105] The specific functions of each module have been described in the above method embodiments and will not be repeated here.

[0106] This embodiment creates a demand estimation model through historical order data, performs valuation calculation on sample data, and obtains an outflow estimation value; trains the demand estimation model based on the outflow estimation value to obtain a trained demand estimation model; and obtains a vehicle demand estimation value based on the trained demand estimation model. Taking into account the impact of supply on demand, the outflow of riding when supply is limited can be re-estimated, so that the calculated demand is closer to the demand under sufficient supply conditions.

[0107] <Equipment Embodiment>

[0108] Figure 6 is a schematic diagram of the hardware structure of an electronic device according to another embodiment.

[0109] like Figure 6 As shown, the electronic device 600 includes a processor 610 and a memory 620, wherein the memory 620 is used to store an executable computer program, and the processor 610 is used to execute a method such as any of the above method embodiments under the control of the computer program.

[0110] The electronic device 600 may be Figure 1 Processor 2100 in.

[0111] Each module of the above electronic device 600 may be implemented by the processor 610 in this embodiment executing a computer program stored in the memory 620, or may be implemented by other circuit structures, which is not limited here.

[0112] This embodiment provides a computer-readable storage medium, in which executable commands are stored. When the executable commands are executed by a processor, the method described in any method embodiment of this specification is executed.

[0113] One or more embodiments of the present specification may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present specification.

[0114] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0115] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0116] The computer program instructions for performing the operation of the embodiments of this specification may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, executed as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In certain embodiments, by utilizing the state information of a computer-readable program instruction to customize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA) or a programmable logic array (PLA), the electronic circuit may execute a computer-readable program instruction, thereby realizing various aspects of this specification.

[0117] Various aspects of this specification are described herein with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of this specification. It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0118] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0119] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0120] The flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to the multiple embodiments of this specification. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of an instruction, and a part of a module, a program segment or an instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.

[0121] The embodiments of the present specification have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the marketplace, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of this application is defined by the appended claims.

Claims

1. A vehicle demand estimation method, characterized in that: The method comprises: Acquire historical order data within the parking fence, and create a demand estimation model based on the historical order data, wherein the historical order data includes vehicle outflow and vehicle supply; Perform valuation calculation on sample data to obtain estimated outflow volume; Training the demand estimation model according to the outflow estimation value to obtain a trained demand estimation model; Obtaining a vehicle demand estimation value according to the trained demand estimation model; The step of creating a demand estimation model according to the historical order data comprises: Based on historical order data, obtain the vehicle outflow and vehicle supply within a preset time period; According to the vehicle outflow and vehicle supply in the preset time period, a normal distribution model is established to obtain the mean and variance of the vehicle outflow, and determine the initial parameters of the demand estimation model; Before performing valuation calculation on the sample data, the method further includes: The historical order data is screened to obtain sample data, wherein the vehicle supply of the sample data is equal to the vehicle outflow; The method of performing valuation calculation on the sample data to obtain an estimated value of the outflow includes: According to the initial parameters of the demand estimation model and the vehicle outflow in the sample data, an expectation maximization algorithm is used to obtain the outflow estimation value, and the outflow estimation value is greater than or equal to the vehicle outflow in the sample data; The step of training the demand estimation model according to the outflow estimation value to obtain the trained demand estimation model includes: Using the outflow estimation value and the vehicle supply in the sample data as inputs of the demand estimation model, training the demand estimation model to obtain a trained demand estimation model, wherein the model parameters of the trained demand estimation model are within a preset range; The step of obtaining a vehicle demand estimation value according to the trained demand estimation model includes: According to the trained demand estimation model, the vehicle outflow is output, and the vehicle outflow data is used as the vehicle demand estimation value.

2. A vehicle demand estimation device, characterized in that: The device comprises: A model creation module, used for acquiring historical order data within the parking fence, and creating a demand estimation model according to the historical order data, wherein the historical order data includes vehicle outflow and vehicle supply; An estimation module is used to filter the historical order data to obtain sample data, wherein the vehicle supply of the sample data is equal to the vehicle outflow, and to perform valuation calculation on the sample data to obtain an outflow estimation value, wherein the valuation calculation on the sample data to obtain the outflow estimation value includes: According to the initial parameters of the demand estimation model and the vehicle outflow in the sample data, an expectation maximization algorithm is used to obtain the outflow estimation value, and the outflow estimation value is greater than or equal to the vehicle outflow in the sample data; A model training module, used for training the demand estimation model according to the outflow estimation value to obtain a trained demand estimation model, wherein the training of the demand estimation model according to the outflow estimation value to obtain a trained demand estimation model comprises: Using the outflow estimation value and the vehicle supply in the sample data as inputs of the demand estimation model, training the demand estimation model to obtain a trained demand estimation model, wherein the model parameters of the trained demand estimation model are within a preset range; An output module is used to obtain a vehicle demand estimation value according to the trained demand estimation model, wherein obtaining the vehicle demand estimation value according to the trained demand estimation model includes: According to the trained demand estimation model, the vehicle outflow is output, and the vehicle outflow data is used as the vehicle demand estimation value.

3. An electronic device, characterized in that: The method comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction implements the steps of the method according to claim 1 when executed by the processor.

4. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the method according to claim 1 are implemented.

Images