CN111832600A - Data processing method, apparatus, electronic device and computer-readable storage medium - Google Patents

Abstract

Embodiments of the present invention disclose a data processing method, apparatus, electronic device, and computer-readable storage medium. The acquired characteristic data of each grid is input into a pre-trained demand prediction model to obtain the shared equipment of each grid. Demand information, obtain the supply information of the shared equipment of each grid, and determine the resource consumption associated with the shared equipment in each grid in the next time period according to the demand information and supply information of the shared equipment of each grid, thus, The resource utilization of the shared device can be improved.

Description

Data processing method, apparatus, electronic device and computer-readable storage medium

technical field

The present invention relates to the field of the Internet, and more particularly, to a data processing method, apparatus, electronic device and computer-readable storage medium.

Background technique

With the development of the sharing economy and the Internet, shared devices such as shared bicycles, shared cars, and shared power banks are gradually accepted by the majority of Internet users. This way of integrating offline idle items, allowing them to offer products or services at lower prices, has occupied a place in the market with its unique advantages. Therefore, how to improve the resource utilization of shared equipment is an important issue.

SUMMARY OF THE INVENTION

In view of this, embodiments of the present invention provide a data processing method, an apparatus, an electronic device, and a computer-readable storage medium, so as to improve resource utilization of a shared device.

In a first aspect, an embodiment of the present invention provides a data processing method, the method comprising:

Obtain feature data of each grid, the feature data includes grid information, time period information, and demand information of shared equipment of each grid in the same historical period, the grid information includes the identification and environmental information of the corresponding grid, so the grid corresponds to a pre-divided geographic area;

inputting the feature data of each grid into a pre-trained demand prediction model to obtain the demand information of the shared equipment of each grid;

Obtain the supply information of the shared equipment of each grid;

According to the demand information and the supply information, the resource consumption associated with the shared device in each grid in the next period is determined.

Optionally, determining, according to the demand information and the supply information, the resource consumption associated with the shared device in each grid in the next time period includes:

determining a supply-demand ratio according to the supply information and the demand information;

The resource consumption is determined according to the supply and demand ratio.

Optionally, determining the resource consumption according to the supply-demand ratio includes:

The resource consumption is determined according to the supply and demand ratio, the predetermined supply and demand ratio segments, and the weights corresponding to each of the supply and demand ratio segments.

Optionally, acquiring the supply information of the shared devices of each grid includes:

The supply information of the shared devices of each grid is determined according to the location information of each shared device.

Optionally, the location information of the shared device is determined by the report information of the user terminal when the task is completed, or is determined by the report information of the operation and maintenance terminal.

Optionally, the demand prediction model is trained by the following steps:

Obtaining training data, the training data includes each grid information, each time period information, and historical demand information;

The demand forecasting model is obtained by training according to the training data;

Wherein, the historical demand information includes the average and median demand of the shared equipment of each grid in each time period in the first predetermined time, the average and The median demand value, and at least one of the mean demand value and the median demand value of the shared devices of each grid in each time period within the third predetermined time period.

Optionally, the information on each time period includes an identifier of the time period and a date where the time period is located.

Optionally, the demand forecasting model is an XGBoost regression model.

Optionally, the grids are divided according to the GeoHash method.

In a second aspect, an embodiment of the present invention provides a data processing apparatus, and the apparatus includes:

The characteristic data acquisition unit is configured to acquire characteristic data of each grid, the characteristic data includes grid information, time period information, and demand information of the shared equipment of each grid in the same historical period, and the grid information includes corresponding grid information identification and environmental information of a grid, the grid corresponding to a pre-divided geographic area;

a demand information acquisition unit, configured to input the characteristic data of each grid into a pre-trained demand prediction model, and obtain the demand information of the shared equipment of each grid;

a supply information acquisition unit, configured to acquire supply information of the shared equipment of each grid;

A determining unit, configured to determine, according to the demand information and the supply information, the resource consumption associated with the shared device in each grid in the next period.

In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, where the memory is configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor Execute to implement the method as described above.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium on which computer program instructions are stored, and when the computer program instructions are executed by a processor, implement the method as described above.

In the embodiment of the present invention, the acquired characteristic data of each grid is input into a pre-trained demand prediction model to obtain the demand information of the shared equipment of each grid, and the supply information of the shared equipment of each grid is obtained, and according to each grid The demand information and supply information of the shared device determined by the corresponding grids determine the resource consumption of the shared device in the next time period, thereby improving the resource utilization rate of the shared device.

Description of drawings

The above and other objects, features and advantages of the present invention will become more apparent from the following description of embodiments of the present invention with reference to the accompanying drawings, in which:

1 is a flowchart of a data processing method according to an embodiment of the present invention;

2 is a schematic diagram of a training method of a demand prediction model according to an embodiment of the present invention;

3 is a data flow diagram of a data processing method according to an embodiment of the present invention;

4 is a schematic diagram of an application scenario of a data processing method according to an embodiment of the present invention;

5 is a schematic diagram of a data processing apparatus according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of an electronic device according to an embodiment of the present invention.

Detailed ways

The present invention is described below based on examples, but the present invention is not limited to these examples only. In the following detailed description of the invention, some specific details are described in detail. The present invention can be fully understood by those skilled in the art without the description of these detailed parts. Well-known methods, procedures, procedures, components and circuits have not been described in detail in order to avoid obscuring the essence of the present invention.

Furthermore, those of ordinary skill in the art will appreciate that the drawings provided herein are for illustrative purposes and are not necessarily drawn to scale.

Unless clearly required by the context, words such as "including", "comprising" and the like in the specification should be construed in an inclusive rather than an exclusive or exhaustive sense; that is, in the sense of "including but not limited to".

In the description of the present invention, it should be understood that the terms "first", "second" and the like are used for descriptive purposes only, and should not be construed as indicating or implying relative importance. Also, in the description of the present invention, unless otherwise specified, "plurality" means two or more.

Shared devices have different needs in different geographic areas and time periods. For example, the demand for shared bicycles is large during commuting hours, and the demand for shared charging treasures is large in shopping malls on weekends or in the afternoon. In the following description, the embodiment of the present invention mainly takes a shared bicycle as an example, but it should be understood that the data processing method of this embodiment can be applied to a shared device having the same nature as the shared bicycle.

There is an obvious tidal phenomenon in urban traffic, that is, most people transfer from residential areas to subway stations, bus stations, and from subway stations to office buildings during the morning rush hour, and the opposite is true during the evening rush hour. Therefore, in different time and different space (geographical space) scenarios, the supply and demand relationship of shared bicycles is significantly different. According to this difference, this embodiment provides a data processing method to improve the resource utilization of shared equipment.

FIG. 1 is a flowchart of a data processing method according to an embodiment of the present invention. As shown in Figure 1, the data processing method of this embodiment includes:

Step S110, acquiring characteristic data of each grid. Among them, the characteristic data of the grid includes grid information, time period information, and the demand information of the shared equipment of each grid in the same historical period. The grid information includes the identification and environmental information of the corresponding grid, and the grid corresponds to the pre-divided geographical location. area. Wherein, the environmental information of the grid may include building information in the grid, for example, whether the grid includes residential quarters, subway stations, bus stations, hospitals, schools, office buildings, shopping malls, and other buildings, as well as the included buildings quantity. In this embodiment, the time of the day is equally divided into a plurality of time periods, and each time period has a unique identifier. Optionally, each period is 15 minutes. Assuming that the time length of each time period is 15 minutes, and the time period to be predicted is from 18:00 to 18:15 pm today, then the demand information of the shared equipment of each grid in the same historical period is 18:00 to 18:00 of each historical day of each grid. 18:15 Demand for shared equipment.

In an optional implementation manner, this embodiment divides a region into multiple grids according to the GeoHash method. GeoHash is an address encoding method that can encode two-dimensional latitude and longitude data into a string. That is, GeoHash uses a string to represent two coordinates of longitude and latitude, which is used to characterize an area, and the length of the string is used to characterize the range of the area. That is, the smaller the range of representation, on the contrary, the shorter the length of the string, the larger the range of its representation. Optionally, in this embodiment, the granularity of GeoHash7 is used to divide a region into multiple grids, that is, a string with a length of 7 is used to represent the longitude and latitude of each grid.

In step S120, the characteristic data of each grid is input into the pre-trained demand prediction model, and the demand information of the shared equipment of each grid is obtained.

FIG. 2 is a schematic diagram of a training method of a demand prediction model according to an embodiment of the present invention. In an optional implementation, as shown in Figure 2, the demand forecasting model is trained through the following steps:

Step S121 , acquiring training data, where the training data includes information about each grid, information about each time period, and historical demand information. In this embodiment, in the spatial dimension, a region is divided into a plurality of grids in advance by the GeoHash method according to a predetermined granularity, and each grid is given a unique identifier. In the time dimension, the time of the day is divided into multiple periods, and each period is given a unique identifier. Optionally, each time period is 15min, then each grid has 96 time periods per day. Assuming that there are N (N>1) grids in total, in space and time dimensions, there are 96*N grid time periods per day. slice. Thus, in the acquired training data, the grid information includes the identification and environment information of the corresponding grid. In an embodiment, the time period information includes an identification of the time period, and the date of the time period (eg, weekdays, weekends, holidays, months, etc.).

The historical demand information includes the mean value and median demand value of the shared devices in each grid period within the first predetermined period, the average demand value and the median demand value of the shared equipment in each grid period within the second predetermined period, and the third predetermined period. At least one of the mean value and the median value of the demand of the shared equipment for each grid period in time. Optionally, the first predetermined time is the last 56 days, the second predetermined time is the last 28 days, and the third predetermined time is the last 14 days. For example, the average demand of the shared equipment of grid 1 in the period of 18:00-18:15 in the last 14 days is: the average of the demand of each day in the last 14 days in the period of 18:00-18:15.

Wherein, for each grid period, the demand in the grid period is the number that the user wants to associate with the shared device, such as the number of scanning the shared bicycle QR code. Optionally, multiple scans of the code by the same user are recorded as one demand, and as long as the scan code is completed or not, it can be recorded as one demand. In this way, the demand for the shared device in the grid period can be obtained relatively accurately.

Step S122, a demand prediction model is obtained by training according to the training data. In an optional implementation manner, the demand forecasting model is an XGBoost regression model. The XGBoost model is a supervised model, which can construct and optimize the objective function, and can also customize some loss functions. Therefore, the demand forecasting model in this embodiment adopts the XGBoost regression model, which can more accurately obtain the value of each grid in the next The demand for shared equipment during the time period.

In step S130, the supply information of the shared devices of each grid is acquired. Wherein, the supply information of the shared devices of the grid includes the number of shared devices that function normally and are not in use in the grid. Optionally, the supply information of the shared devices of each grid is determined according to the location information of each shared device.

In an optional implementation manner, the location information of the shared device is determined by the information reported by the user terminal when the task is completed. That is to say, when the user ends renting the shared device, the user terminal reports the lease end message, and obtains the current location information of the shared device (that is, the location where the user ends the lease) according to the lease end message reported by the user terminal. In addition, when the terminal of the operation and maintenance personnel moves the shared device, the relevant information of the mobile shared device will be reported through the operation and maintenance terminal. Therefore, the location information of the relevant shared device can also be obtained according to the information reported by the operation and maintenance terminal. In another optional implementation manner, the current location information of each sharing device may be acquired by controlling the sharing device to periodically report its own location information. It should be understood that this embodiment is not limited to the above-mentioned method for acquiring the location information of the shared device, and other methods capable of realizing the above-mentioned functions can be applied to this embodiment.

It should be understood that step S120 and step S130 do not have a sequential execution order, and step S130 may be executed before step S120, may be executed after step S120, or may be executed simultaneously with step S120, which is not limited in this embodiment.

Step S140: Determine the resource consumption of the associated shared devices in each grid in the next time period according to the demand information and the supply information.

In an optional implementation manner, step S140 may include: determining the supply and demand ratio of each grid in the next time period according to the supply information and demand information of each grid in the next time period, and determining the next time period according to the supply and demand ratio. Resource consumption of associated shared devices in each grid. Optionally, in this embodiment, the resource consumption is determined according to the supply-demand ratio, a predetermined supply-demand ratio segment, and a weight corresponding to each supply-demand ratio segment.

For example, assuming that the reference resource consumption is x (x>0), the corresponding table of each supply-demand ratio segment and the corresponding weight is shown in table (1). It should be understood that table (1) is only exemplary, and can be Adjust the supply-demand ratio segment, the corresponding weight, and the corresponding relationship between the supply-demand ratio segment and the corresponding weight according to the actual application scenario.

supply and demand ratio Weights Adjusted resource consumption ≥1 1.0 1.0*x [0.75,1) 1.25 1.25*x [0.5,0.75) 1.5 1.5*x [0.25,0.5) 2.0 2.0*x [0,0.25) 3.0 3.0*x

Therefore, assuming that the supply-demand ratio obtained by the calculation in the grid 1 is 0.55, the resource consumption of the associated shared device in the grid 1 in the next period can be adjusted to 1.5*x. Thereby, the resource utilization rate of the shared device can be effectively improved.

In the embodiment of the present invention, the acquired characteristic data of each grid is input into a pre-trained demand prediction model to obtain the demand information of the shared equipment of each grid, and the supply information of the shared equipment of each grid is obtained, and according to each grid The demand information and supply information of the shared device determined by the corresponding grids determine the resource consumption of the shared device in the next time period, thereby improving the resource utilization rate of the shared device.

FIG. 3 is a data flow diagram of a data processing method according to an embodiment of the present invention. As shown in FIG. 3 , the acquired characteristic data of each grid is input into the pre-trained demand prediction model 31 to obtain the demand information of the shared equipment of each grid. Among them, the characteristic data of the grid includes grid information, time period information, and the demand information of the shared equipment of each grid in the same historical period. The grid information includes the identification and environmental information of the corresponding grid, and the grid corresponds to the pre-divided geographical location. area. Wherein, the environmental information of the grid may include building information in the grid, for example, whether the grid includes residential quarters, subway stations, bus stations, hospitals, schools, office buildings, shopping malls, and other buildings, as well as the included buildings quantity. In this embodiment, the time of a day is equally divided into a plurality of time periods. Optionally, each time period is 15 minutes. Assuming that the time length of each time period is 15 minutes, and the time period to be predicted is from 18:00 to 18:15 pm today, then the demand information of the shared equipment of each grid in the same historical period is 18:00 to 18:00 of each historical day of each grid. 18:15 Demand for shared equipment.

Optionally, the demand prediction model is trained by the acquired training data, and the training data includes information of each grid, information of each period, and historical demand information. Optionally, the demand forecasting model is an XGBoost regression model. Wherein, the historical demand information includes the average and median demand of the shared equipment of each grid in each time period in the first predetermined time, and the average and demand of the shared equipment of each grid in each time period in the second predetermined time. value, and at least one of a demand mean value and a demand median value of the shared equipment of each grid in each time period within the third predetermined time. Optionally, the first predetermined time is the last 56 days, the second predetermined time is the last 28 days, and the third predetermined time is the last 14 days. For example, the average demand of the shared equipment of grid 1 in the period of 18:00-18:15 in the last 14 days is: the average of the demand of each day in the last 14 days in the period of 18:00-18:15. Wherein, for each grid period, the demand in the grid period is the number that the user wants to associate with the shared device, such as the number of scanning the shared bicycle QR code. Optionally, multiple scans of the code by the same user are recorded as one demand, and as long as the scan code is completed or not, it can be recorded as one demand. In this way, the demand for the shared device in the grid period can be obtained relatively accurately. It should be understood that in urban traffic, the demand for shared equipment on working days and rest days (weekends and holidays) is different, therefore, when performing model training, the date information of the time period (such as date, working day identifier, rest day identifier) can be introduced. etc.) to further improve the accuracy of demand forecasting.

In this embodiment, the supply information of the shared equipment of each grid in the next period is acquired according to the supply information acquisition unit 32 . Wherein, the supply information of the shared devices of the grid includes the number of shared devices that function normally and are not in use in the grid. Optionally, the supply information of the shared devices of each grid is determined according to the location information of each shared device.

In an optional implementation manner, the location information of the shared device is determined by the information reported by the user terminal when the task is completed. That is to say, when the user ends renting the shared device, the user terminal reports the lease end message, and obtains the current location information of the shared device (that is, the location where the user ends the lease) according to the lease end message reported by the user terminal. Moreover, after the terminal of the operation and maintenance personnel moves the shared device, the relevant information of the mobile shared device will be reported through the operation and maintenance terminal. Therefore, the location information of the relevant shared device can also be obtained according to the report information of the exercise terminal. In another optional implementation manner, the current location information of each sharing device may be acquired by controlling the sharing device to periodically report its own location information. It should be understood that this embodiment is not limited to the above-mentioned method for acquiring the location information of the shared device, and other methods capable of realizing the above-mentioned functions can be applied to this embodiment.

The determining unit 33 determines, according to the acquired demand information and supply information, the resource consumption of the associated shared devices in each grid in the next time period. Optional: determine the supply and demand ratio of each grid in the next period according to the supply information and demand information of each grid in the next period, and determine the resource consumption of the associated shared equipment in each grid in the next period according to the supply and demand ratio . Optionally, in this embodiment, the resource consumption is determined according to the supply-demand ratio, a predetermined supply-demand ratio segment, and a weight corresponding to each supply-demand ratio segment.

In the embodiment of the present invention, the acquired characteristic data of each grid is input into a pre-trained demand prediction model to obtain the demand information of the shared equipment of each grid, and the supply information of the shared equipment of each grid is obtained, and according to each grid The demand information and supply information of the shared device determined by the corresponding grids determine the resource consumption of the shared device in the next time period, thereby improving the resource utilization rate of the shared device.

FIG. 4 is a schematic diagram of a scene of a data processing method according to an embodiment of the present invention. As shown in FIG. 4, the regional area 4 is divided into a plurality of grids in advance according to the GeoHash method. The grid 41 includes cell A, and the grid 42 includes subway B. Assuming that the current time is 07:59 in the morning, if the resource consumption corresponding to the grid 41 and the grid 42 in the next time period (that is, 08:00-08:15 in the morning) is to be determined by the data processing method of this embodiment, then Input the obtained grid information, time period information of grid 41 and grid 42 and the demand information of shared bicycles in the same historical period into the pre-trained demand prediction model to predict grid 41 and grid 42 in the next time period. Demand information, and determine the supply information of shared bicycles in grid 41 and grid 42 based on the information reported by the user terminal and the operation and maintenance terminal, and based on the pre-determined supply and demand ratio segments, the corresponding weights of the supply and demand ratio segments and calculating the obtained supply-demand ratio to determine the resource consumption of the grid 41 and the grid 42 in the next period. Taking the reference resource consumption as 1 yuan, the supply-demand ratio segments and corresponding weights in Table (1) as an example, assuming that the supply-demand ratio corresponding to grid 41 is 0.3, and the supply-demand ratio corresponding to grid 42 is 2.0, then in the next During the period, the resource consumption corresponding to the grid 41 is 2 yuan, and the resource consumption corresponding to the grid 42 is 1 yuan. That is, if the initial resource consumption for renting a shared bicycle in cell A of grid 41 is 2 yuan, the initial resource consumption for renting a shared bicycle in subway B in grid 42 is 1 yuan. Therefore, the corresponding resource consumption can be determined according to the supply and demand ratio of the shared bicycles, which improves the resource utilization rate of the shared equipment.

This embodiment is described by taking a shared bicycle as an example, and it should be understood that the data processing method of this embodiment can be applied to other shared devices, such as a shared car, a shared power bank, and the like.

In the embodiment of the present invention, the acquired characteristic data of each grid is input into a pre-trained demand prediction model to obtain the demand information of the shared equipment of each grid, and the supply information of the shared equipment of each grid is obtained, and according to each grid The demand information and supply information of the shared device determined by the corresponding grids determine the resource consumption of the shared device in the next time period, thereby improving the resource utilization rate of the shared device.

FIG. 5 is a schematic diagram of a data processing apparatus according to an embodiment of the invention. As shown in FIG. 5 , the data processing apparatus of this embodiment includes a characteristic data acquisition unit 51 , a demand information acquisition unit 52 , a supply information acquisition unit 53 and a determination unit 54 .

The characteristic data acquisition unit 51 is configured to acquire characteristic data of each grid, the characteristic data includes grid information, time period information, and demand information of the shared equipment of each grid in the same historical period, and the grid information includes the corresponding grid information. identification and environmental information of a grid corresponding to a pre-divided geographic area. Optionally, each grid is divided according to the GeoHash method.

The demand information obtaining unit 52 is configured to input the characteristic data of each grid into the pre-trained demand prediction model, and obtain the demand information of the shared equipment of each grid. Optionally, the demand forecasting model is an XGBoost regression model.

The supply information acquisition unit 53 is configured to acquire supply information of the shared devices of each grid in the next period. Optionally, the information acquisition unit 53 is further configured to determine the supply information of the shared devices of each grid according to the location information of each shared device. Optionally, the location information of the shared device is determined by the report information of the user terminal when the task is completed, or is determined by the report information of the operation and maintenance terminal.

The determining unit 54 is configured to determine, according to the demand information and the supply information, the resource consumption amount associated with the shared device in each grid in the next period. In an optional implementation manner, the determining unit 54 is further configured to determine a supply-demand ratio according to the supply information and the demand information, and determine the resource consumption amount according to the supply-demand ratio. Optionally, the determining unit 54 further determines the resource consumption according to the supply-demand ratio, a predetermined supply-demand ratio segment, and a weight corresponding to each supply-demand ratio segment.

In the embodiment of the present invention, the acquired characteristic data of each grid is input into a pre-trained demand prediction model to obtain the demand information of the shared equipment of each grid, and the supply information of the shared equipment of each grid is obtained, and according to each grid The demand information and supply information of the shared device determined by the corresponding grids determine the resource consumption of the shared device in the next time period, thereby improving the resource utilization rate of the shared device.

FIG. 6 is a schematic diagram of an electronic device according to an embodiment of the present invention. As shown in FIG. 6 , the electronic device shown in FIG. 6 is a general-purpose data processing apparatus, which includes a general-purpose computer hardware structure, which at least includes a processor 61 and a memory 62 . The processor 61 and the memory 62 are connected by a bus 63 . The memory 62 is adapted to store instructions or programs executable by the processor 61 . The processor 61 may be an independent microprocessor, or may be a set of one or more microprocessors. Thus, the processor 61 executes the instructions stored in the memory 62 to execute the above-described method flow of the embodiments of the present invention to process data and control other devices. The bus 63 connects the above-mentioned various components together, while connecting the above-mentioned components to the display controller 64 and the display device and the input/output (I/O) device 65 . The input/output (I/O) device 65 may be a mouse, keyboard, modem, network interface, touch input device, somatosensory input device, printer, and other devices known in the art. Typically, input/output devices 65 are connected to the system through input/output (I/O) controllers 66 .

It should be understood by those skilled in the art that the embodiments of the present application may be provided as a method, an apparatus (apparatus) or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may employ a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations of methods, apparatus (apparatus) and computer program products according to embodiments of the present application. It will be understood that each process in the flowchart can be implemented by computer program instructions.

These computer program instructions may be stored in a computer readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory result in an article of manufacture comprising instruction means, the instruction means Implements the function specified in a flow chart or flows.

These computer program instructions may also be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flows of a flowchart.

Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program, the computer-readable program being used for a computer to execute some or all of the above method embodiments.

That is, those skilled in the art can understand that all or part of the steps in the method for implementing the above embodiments can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium and includes several instructions to make a device ( It may be a single chip microcomputer, a chip, etc.) or a processor (processor) to execute all or part of the steps of the methods described in the embodiments of the present application. The aforementioned storage medium includes: U disk, removable hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims (12)

1. a data processing method, is characterized in that, described method comprises: Obtain feature data of each grid, the feature data includes grid information, time period information, and demand information of shared equipment of each grid in the same historical period, the grid information includes the identification and environmental information of the corresponding grid, so the grid corresponds to a pre-divided geographic area; inputting the feature data of each grid into a pre-trained demand prediction model to obtain the demand information of the shared equipment of each grid; Obtain the supply information of the shared equipment of each grid; According to the demand information and the supply information, the resource consumption associated with the shared device in each grid in the next period is determined. 2 . The method according to claim 1 , wherein determining, according to the demand information and the supply information, the resource consumption associated with the shared devices in each grid in the next time period comprises: 2 . determining a supply-demand ratio according to the supply information and the demand information; The resource consumption is determined according to the supply and demand ratio. 3. The method according to claim 2, wherein determining the resource consumption according to the supply-demand ratio comprises: The resource consumption is determined according to the supply and demand ratio, the predetermined supply and demand ratio segments, and the weights corresponding to each of the supply and demand ratio segments. 4. The method according to claim 1, wherein acquiring the supply information of the shared devices of each grid comprises: The supply information of the shared devices of each grid is determined according to the location information of each shared device. 5 . The method according to claim 4 , wherein the location information of the shared device is determined by the report information of the user terminal when the task is completed, or by the report information of the operation and maintenance terminal. 6 . 6. The method according to claim 1, wherein the demand forecasting model is trained by the following steps: Obtaining training data, the training data includes each grid information, each time period information, and historical demand information; The demand forecasting model is obtained by training according to the training data; Wherein, the historical demand information includes the average and median demand of the shared equipment of each grid in each time period in the first predetermined time, the average and The median demand value, and at least one of the mean demand value and the median demand value of the shared devices of each grid in each time period within the third predetermined time period. 7 . The method according to claim 6 , wherein the information of each time period includes an identifier of the time period and a date of the time period. 8 . 8. The method according to claim 1, wherein the demand prediction model is an XGBoost regression model. 9 . The method according to claim 1 , wherein the grids are divided according to the GeoHash method. 10 . 10. A data processing device, characterized in that the device comprises: The characteristic data acquisition unit is configured to acquire characteristic data of each grid, the characteristic data includes grid information, time period information, and demand information of the shared equipment of each grid in the same historical period, and the grid information includes corresponding grid information identification and environmental information of a grid, the grid corresponding to a pre-divided geographic area; a demand information acquisition unit, configured to input the characteristic data of each grid into a pre-trained demand prediction model, and obtain the demand information of the shared equipment of each grid; a supply information acquisition unit, configured to acquire supply information of the shared equipment of each grid; A determining unit, configured to determine, according to the demand information and the supply information, the resource consumption associated with the shared device in each grid in the next period. 11. An electronic device comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to achieve The method of any one of claims 1-9. 12. A computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the method of any one of claims 1-9.

Images