CN111210260A

CN111210260A - Electricity price data processing method and device, computer equipment and storage medium

Info

Publication number: CN111210260A
Application number: CN201911357063.1A
Authority: CN
Inventors: 黄腾; 钟文瑜; 黄欣
Original assignee: Shenzhen Power Supply Co ltd
Current assignee: Shenzhen Power Supply Co ltd
Priority date: 2019-12-25
Filing date: 2019-12-25
Publication date: 2020-05-29

Abstract

The application relates to a power price data processing method, a power price data processing device, computer equipment and a storage medium. The method comprises the following steps: acquiring a candidate electricity price calculation scheme set corresponding to a user of a target user type, wherein the candidate electricity price calculation scheme set comprises a plurality of candidate electricity price calculation schemes; acquiring a candidate user set corresponding to the target user type, wherein the candidate user set comprises a plurality of candidate users; screening target users from the candidate user set according to the electricity utilization information of the candidate users; predicting to obtain target predicted power consumption corresponding to the target user according to the historical power consumption data corresponding to the target user in the historical time period; and screening the target electricity price calculation scheme corresponding to the target user from the candidate electricity price calculation scheme set according to each candidate electricity price calculation scheme and the target predicted electricity consumption. By adopting the method, the cost of electricity charge can be reduced and the difficulty in selecting the electricity price scheme can be solved.

Description

Electricity price data processing method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for processing electricity price data, a computer device, and a storage medium.

Background

Along with the development of electric equipment, more and more electric equipment appears in people's life, and people's life can not leave electric equipment almost to the charges of electricity becomes a little expense in people's life. For example, the user needs to pay the electricity rate monthly, so that the electricity rate cost is high.

At present, non-resident users in Shenzhen region can execute single-system electricity price and two-system segmented electricity price according to the size of transformer capacity, single-system industrial users have peak-valley periods, electricity cost paid by different electricity consumption amounts in each period is different, basic electricity price selection problems exist for users executing two-system segmented electricity price according to users with capacity of 101-3000kva (KiloVolt-Ampere, KiloVolt), users executing two-system segmented electricity price have strong requirements for electricity price selection and basic electricity price selection according to users with capacity of 3001 or above, however, non-resident users often do not know electricity price schemes, and electricity price scheme selection is difficult.

Disclosure of Invention

In view of the above, it is desirable to provide a power rate data processing method, a device, a computer device, and a storage medium, which can reduce the power rate cost and solve the difficulty in selecting a power rate scheme, in view of the above technical problems of high power rate cost and difficulty in selecting a power rate scheme.

A power rate data processing method, the method comprising: acquiring a candidate electricity price calculation scheme set corresponding to a user of a target user type, wherein the candidate electricity price calculation scheme set comprises a plurality of candidate electricity price calculation schemes; acquiring a candidate user set corresponding to the target user type, wherein the candidate user set comprises a plurality of candidate users; screening target users from the candidate user set according to the electricity utilization information of the candidate users; predicting to obtain target predicted power consumption corresponding to the target user according to the historical power consumption data corresponding to the target user in the historical time period; and screening the target electricity price calculation scheme corresponding to the target user from the candidate electricity price calculation scheme set according to each candidate electricity price calculation scheme and the target predicted electricity consumption.

In some embodiments, the predicting, according to the historical electricity consumption data corresponding to the historical time period of the target user, a target predicted electricity consumption corresponding to the target user includes: and inputting the historical electricity consumption data into a trained target electricity consumption prediction model, predicting to obtain target predicted electricity consumption corresponding to the target user, and training the target electricity consumption prediction model according to training electricity consumption data of a training user corresponding to the type of the target user to obtain the target predicted electricity consumption.

In some embodiments, the obtaining of the target power consumption prediction model includes: acquiring first electricity quantity data corresponding to a first time period of a training user and second electricity quantity data corresponding to a second time period of the training user, wherein the first time period is before the second time period; obtaining a training feature of the training user according to the first electric quantity data, obtaining a training label of the training user according to the second electric quantity data, and obtaining a training sample by using the training feature and the training label; and carrying out model training according to the training samples to obtain the trained target power consumption prediction model.

In some embodiments, there are a plurality of training samples corresponding to the same training user, and the performing model training according to the training samples to obtain the trained target power consumption prediction model includes: respectively inputting the first electric quantity data in each training sample into a power consumption prediction model to be trained to obtain training predicted power consumption data corresponding to the training user in the second time period; sequencing the training predicted power consumption data corresponding to the same training user according to a time sequence to obtain a training predicted power consumption data sequence; sequencing all the second electric quantity data corresponding to the same training user according to a time sequence to obtain a second electric quantity data sequence; calculating to obtain a model loss value according to the difference between the training predicted power consumption data sequence and the second power consumption data sequence, wherein the model loss value and the difference form a negative correlation relationship; and adjusting parameters of a power consumption prediction model to be trained according to the model loss value to obtain a target power consumption prediction model.

In some embodiments, the obtaining, by screening from the candidate electricity price calculation scheme set according to each candidate electricity price calculation scheme and the target predicted electricity consumption, a target electricity price calculation scheme corresponding to the target user includes: obtaining expected power consumption corresponding to each candidate electricity price calculation scheme, and comparing the expected power consumption with the target predicted power consumption to obtain a comparison result; and screening the candidate power price calculation scheme set according to the comparison result to obtain a target power price calculation scheme corresponding to the target user.

In some embodiments, the obtaining, by screening from the candidate electricity price calculation scheme set according to the comparison result, a target electricity price calculation scheme corresponding to the target user includes: and when the comparison result indicates that the target predicted electricity consumption belongs to the expected electricity consumption, taking the corresponding candidate electricity price calculation scheme as a target electricity price calculation scheme.

An electricity price data processing apparatus, the apparatus comprising: the candidate electricity price calculation scheme set acquisition module is used for acquiring a candidate electricity price calculation scheme set corresponding to a user of a target user type, and the candidate electricity price calculation scheme set comprises a plurality of candidate electricity price calculation schemes; a candidate user set obtaining module, configured to obtain a candidate user set corresponding to the target user type, where the candidate user set includes multiple candidate users; the target user acquisition module is used for screening the candidate user set according to the electricity utilization information of the candidate users to obtain target users; the target predicted power consumption obtaining module is used for predicting and obtaining target predicted power consumption corresponding to the target user according to historical power consumption data corresponding to the target user in a historical time period; and the target electricity price calculation scheme obtaining module is used for screening the target electricity price calculation scheme corresponding to the target user from the candidate electricity price calculation scheme set according to each candidate electricity price calculation scheme and the target predicted electricity consumption.

In some embodiments, the target predicted power consumption obtaining module is further configured to input the historical power consumption data into a trained target power consumption prediction model, and predict to obtain a target predicted power consumption corresponding to the target user, where the target power consumption prediction model is obtained by training according to training power consumption data of a training user corresponding to the target user type.

A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above electricity price data processing method when executing the computer program.

A computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described electricity price data processing method.

According to the electricity price data processing method, the electricity price data processing device, the computer equipment and the storage medium, a candidate electricity price calculation scheme set corresponding to a user of a target user type is obtained, a candidate user set corresponding to the target user type is obtained, a target user is obtained by screening from the candidate user set according to historical electricity consumption of the candidate user, a target predicted electricity consumption corresponding to the target user is obtained by predicting according to historical electricity consumption data corresponding to the target user in a historical time period, and a target electricity price calculation scheme corresponding to the target user is obtained by screening from the candidate electricity price calculation scheme set according to each candidate electricity price calculation scheme and the target predicted electricity consumption. Therefore, the candidate electricity price calculation scheme suitable for the target user can be recommended to the target user, so that the target user can flexibly select the electricity price scheme, and the electricity charge cost of the target user can be reduced.

Drawings

Fig. 1 is a view showing an application scenario of a power rate data processing method in some embodiments;

FIG. 2A is a flow diagram illustrating a method for processing electricity price data in accordance with certain embodiments;

FIG. 2B is a schematic diagram of the determination of the base price of high volume power usage and high demand power usage in some embodiments;

FIG. 3 is a flow diagram illustrating steps in obtaining a target power usage prediction model in some embodiments;

FIG. 4 is a flow diagram illustrating steps in obtaining a target power usage prediction model in some embodiments;

FIG. 5A is a flow chart illustrating a method for processing electricity price data in some embodiments;

FIG. 5B is a flow chart illustrating a method for processing electricity price data according to some embodiments;

FIG. 5C is a system block diagram that illustrates a correspondence of electricity price data processing systems in some embodiments;

fig. 6 is a block diagram showing the structure of an electricity price data processing apparatus in some embodiments;

FIG. 7 is a diagram of the internal structure of a computer device in some embodiments.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The electricity price data processing method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network.

Specifically, the server 104 may analyze the electricity charges of the user under different electricity price schemes according to the electricity data of the user, and recommend an appropriate electricity price scheme for the user. The server 104 may provide a client or a page, and the terminal 102 may obtain data such as the recommended electricity price scheme related information by logging in or accessing the provided client or page. The server can obtain a candidate electricity price calculation scheme set corresponding to a user of a target user type, the candidate electricity price calculation scheme set can comprise a plurality of candidate electricity price calculation schemes, a candidate user set corresponding to the target user type is obtained, the candidate user set comprises a plurality of candidate users, the target user is obtained by screening from the candidate user set according to historical electricity consumption of the candidate users, a target predicted electricity consumption corresponding to the target user is obtained by predicting according to historical electricity consumption data corresponding to the target user in a historical time period, and a target electricity price calculation scheme corresponding to the target user is obtained by screening from the candidate electricity price calculation scheme set according to each candidate electricity price calculation scheme and the target predicted electricity consumption. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.

In some embodiments, as shown in fig. 2A, there is provided an electricity price data processing method, which is described by taking the method as an example applied to the server 104 in fig. 1, and includes the following steps:

s202, acquiring a candidate electricity price calculation scheme set corresponding to the user of the target user type, wherein the candidate electricity price calculation scheme set comprises a plurality of candidate electricity price calculation schemes.

Specifically, the user types may include residential users or non-residential users, the non-residential users may be classified according to the electricity usage types, the electricity usage types may include general electricity usage, large amount of electricity usage, and high demand electricity usage, and the non-residential users may include general electricity usage users, large amount of electricity usage users, and high demand electricity usage users. Wherein, the low-voltage power supply and the power consumption of the transformer with the capacity of 100KVA (KiloVolt-Ampere, unit of current) and the special distribution transformer below are common power consumption. The power is supplied by 10 kilovolts or more, and the power consumption of the transformer with the capacity of 101KVA or more and 3001 kilovolt-ampere is a large amount of power consumption. The power is supplied by 10 kilovolts or more, and the power with the maximum demand of the transformer of 3001 kilovolt-ampere or more is the high-demand power. The candidate electricity price calculation scheme set is a set formed by electricity price calculation schemes selectable by a target user. The target user type may be a non-residential user. The candidate electricity price calculation scheme set is a set formed by electricity price calculation schemes corresponding to the target user type. For non-residential users, the set of candidate electricity rate calculation scenarios includes a scenario calculated in terms of transformer capacity and a scenario calculated in terms of maximum demand.

In some embodiments, the corresponding power rate calculations may be different for the same user type. For example, in Shenzhen region, users using electricity in general can include electricity used in general industry, electricity used in general commerce, and other electricity. Common industrial power performs peak-to-valley time-of-use electricity rates, common commercial and other power performs non-time-of-use electricity rates. Wherein, a peak in a peak-to-valley refers to a peak period, a flat refers to a flat period, and a valley refers to a valley period. Peak periods include time periods of, for example, 9:00-11:30, 14:00-16:30, and 19:00-21: 00; the flat period includes, for example, periods of time: 7:00-9:00, 11:30-14:00, 16: 30-19: 00 and 21:00-23: 00; the valley period includes a time period of, for example, 23:00 of the day to 7:00 of the next day. The peak-to-valley time-of-use electricity prices, the peak time period, the normal time period, and the valley time period may be different. The non-time-of-use electricity prices can be understood as the same electricity prices in the peak period, the normal period, and the valley period. Therefore, the electricity cost of commercial and other electricity consumption is the electricity reading amount x unit price; the electricity charge for industrial use is the electricity read in peak period x peak period unit price + electricity read in flat period x flat period unit price + electricity read in valley period x valley period unit price. The peak period, the plateau period, and the valley period refer to a peak period, a plateau period, and a valley period, respectively.

In some embodiments, the corresponding electricity price calculation method may be different for different user types. For example, the general electricity consumer executes a general electricity price algorithm. And a large number of power utilization users and high-demand power utilization users execute two power price making algorithms. Wherein, the two part electricity prices comprise the electricity price and the basic electricity price. The peak-to-valley electricity price of large amount of electricity and high demand electricity is composed of three parts of electricity fee, which are respectively adjusted for basic electricity fee, electric quantity and electricity fee and power factor.

In some embodiments, the basic electricity rate is calculated in a manner calculated by the transformer capacity and in a manner calculated by the maximum demand. Wherein, the maximum demand is the maximum reading maximum demand row degree per month multiplied by multiplying power. The method for calculating the capacity of the transformer comprises the following steps: the basic electricity charge is the transformer capacity multiplied by the basic electricity price, the basic electricity price of a large amount of electricity is 22 yuan/kVA, and the basic electricity price of high-demand electricity is 32 yuan/kVA. The way of calculation according to the maximum demand is: comparing the maximum demand of the user with the contract approval demand of the user, and when the maximum demand is less than or equal to the contract approval demand multiplied by 105 percent, the basic electricity fee is the contract approval demand multiplied by the basic electricity price; when the maximum demand > contract approval demand × 105%, the basic electricity rate is (contract approval demand × basic electricity rate) + (maximum demand-contract approval demand × 105%) × basic electricity rate × 2. As shown in fig. 2B, basic electricity prices corresponding to the transformer capacity calculation manner and the maximum demand calculation manner are shown.

In some embodiments, the electric quantity and the electric charge are calculated by the following method: the electric quantity and the electric charge are peak period electric charge, flat period electric charge and valley period electric charge. The peak-period electricity charge is calculated according to the peak-period electricity quantity, the flat-period electricity charge is calculated according to the flat-period electricity quantity, and the valley-period electricity charge is calculated according to the valley-period electricity quantity. Peak power may include a manner calculated by transformer capacity and a manner calculated by maximum demand. The method for calculating the capacity of the transformer comprises the following steps: peak power 1-the metering point operating transformer capacity and x 250 x 7 hours/24 hours. The way of calculation according to the maximum demand is: the peak electricity quantity is 1, the reading demand is multiplied by 400 multiplied by 7 hours/24 hours. If the electric quantity at the peak period is 1< the electric quantity read at the peak period, the electric charge at the peak period is 1 multiplied by the unit price at the peak period 1+ (the electric quantity read at the peak period-the electric quantity at the peak period 1) multiplied by the unit price at the peak period 2; and if the peak electricity quantity 1 is larger than the peak electricity quantity, the peak electricity charge is equal to the peak electricity quantity read multiplied by the peak electricity price of 1. The flat-term charge may include a manner of calculation by transformer capacity and a manner of calculation by maximum demand. The method for calculating the capacity of the transformer comprises the following steps: the flat-period electricity quantity is 1, namely the capacity of the transformer is calculated at a metering point, and the operation time is multiplied by 250 multiplied by 9 hours/24 hours; the way of calculation according to the maximum demand is: the average electricity quantity is 1, namely the reading demand is multiplied by 400 multiplied by 9 hours/24 hours. If the flat-period electric quantity 1 is less than the flat-period reading electric quantity, the flat-period electric charge is equal to the flat-period electric quantity 1 multiplied by the flat-period unit price 1+ (the flat-period reading electric quantity-the flat-period electric quantity 1 multiplied by the flat-period unit price 2); if the average electricity quantity 1 is larger than the average reading electricity quantity, the average electricity charge is equal to the average reading electricity quantity multiplied by the electricity price of the average electricity quantity 1. The off-peak electricity may include in terms of transformer capacity and in terms of maximum demand. The method for calculating the capacity of the transformer comprises the following steps: the valley period electricity quantity 1 is the capacity of the transformer operated at the metering point and is multiplied by 250 multiplied by 8 hours/24 hours, and the mode calculated according to the maximum demand quantity is as follows: the valley electric quantity 1 is the demand of reading x 400 x 8 hours/24 hours. If the valley period electricity quantity is 1< the electricity quantity read in the valley period, the valley period electricity fee is 1 multiplied by the valley period unit price 1+ (the electricity quantity read in the valley period is 1 multiplied by the valley period unit price 2); if the valley period electricity amount is 1 and the valley period electricity amount is more than the valley period electricity amount, the valley period electricity fee is equal to the valley period electricity amount multiplied by the valley period electricity amount 1.

In some embodiments, the power factor adjustment electricity rate is calculated by: the power factor adjusts the electricity rate (electricity rate + basic electricity rate) x Y%, where the electricity rate is the electricity rate without the fund surcharge, i.e., the electricity rate is the electricity rate-total fund surcharge (total fund surcharge is 0.02766875 yuan/degree). Wherein Y% is a force adjustment integer.

S204, a candidate user set corresponding to the target user type is obtained, and the candidate user set comprises a plurality of candidate users.

Specifically, the candidate user set is a set composed of users of the target user type. The candidate users may include at least one of general electricity users, large-volume electricity users, and high-demand electricity users.

And S206, screening the candidate user set according to the electricity utilization information of the candidate users to obtain the target users.

Specifically, the target users may include a large number of power utilization users and high-demand power utilization users, that is, the large number of power utilization users and the high-demand power utilization users may be obtained by screening from the candidate user set as the target users. The power utilization information includes information of a transformer of a candidate user or historical power utilization information of the user. And screening the target user from the candidate user set according to the information of the transformer of the candidate user. For example, users with the transformer capacity greater than 100KVA can be obtained from the candidate user set by screening according to the transformer capacity of the candidate users, and the users are used as target users. The target user may be a user with a power consumption larger than a preset threshold, for example, the preset threshold may be 1000 degrees.

And S208, predicting to obtain the target predicted power consumption corresponding to the target user according to the historical power consumption data corresponding to the target user in the historical time period.

Specifically, the historical electricity consumption data refers to actual electricity consumption data corresponding to a historical time period, and the historical time period may be, for example, from the beginning of the last month to the end of the last month. The target predicted power usage is a prediction of power usage for a future time period. For example, a prediction of electricity usage for a month in the future.

And S210, screening the candidate electricity price calculation schemes from the candidate electricity price calculation scheme set to obtain a target electricity price calculation scheme corresponding to the target user according to the candidate electricity price calculation schemes and the target predicted electricity consumption.

Specifically, the electricity price calculation scheme corresponding to the target user may be selected from the candidate electricity price calculation schemes, assuming that the candidate electricity price calculation scheme includes a scheme a and a scheme B, the predicted electricity price corresponding to the scheme a may be obtained by calculation according to the scheme a and the target predicted electricity consumption, the predicted electricity price corresponding to the scheme B may be obtained by calculation according to the scheme B and the target predicted electricity consumption, and the scheme with the lowest predicted electricity price in the candidate electricity price calculation scheme set may be used as the target electricity price calculation scheme. For a large number of power utilization users and high-demand power utilization users, the power fee can be calculated according to a transformer capacity calculation mode or a maximum demand calculation mode. Therefore, when a scheme corresponding to the lowest predicted electricity rate in the transformer capacity calculation mode and the maximum demand calculation mode is determined, the scheme can be used as a target electricity rate calculation scheme.

In some embodiments, a target electricity price calculation scheme can be obtained by combining the peak-to-valley electric quantity of the user, the load prediction and the stop-reporting and start-reporting service, and a scheme for saving the electricity cost is recommended for the user.

The electricity price data processing method includes the steps of obtaining a candidate electricity price calculation scheme set corresponding to a user of a target user type, obtaining a candidate user set corresponding to the target user type, screening the candidate user set according to historical electricity consumption of the candidate user to obtain a target user, predicting target predicted electricity consumption corresponding to the target user according to historical electricity consumption data of the target user in a historical time period, and screening the candidate electricity price calculation scheme set according to each candidate electricity price calculation scheme and the target predicted electricity consumption to obtain a target electricity price calculation scheme corresponding to the target user. Therefore, the candidate electricity price calculation scheme suitable for the target user can be recommended to the target user, so that the target user can flexibly select the electricity price scheme, and the electricity charge cost of the target user can be reduced.

In some embodiments, the step S208 of predicting the target predicted power consumption amount corresponding to the target user according to the historical power consumption data corresponding to the target user in the historical time period includes: and inputting the historical electricity consumption data into a trained target electricity consumption prediction model, predicting to obtain target predicted electricity consumption corresponding to a target user, and training the target electricity consumption prediction model according to training electricity consumption data of a training user corresponding to the type of the target user to obtain the target electricity consumption.

Specifically, a training user refers to a user to whom data for model training belongs. The training electricity consumption data is historical electricity consumption data corresponding to a training user. The target user type can be a non-resident user, can include ordinary power consumption, a large amount of power consumption and high demand power consumption, and can train the model according to the training power consumption data corresponding to ordinary power consumption users, a large amount of power consumption users and high demand power consumption users to obtain the target power quantity prediction model. The model can also be trained according to training electricity utilization data corresponding to the ordinary electricity utilization users to obtain a target electricity quantity prediction model corresponding to the ordinary electricity utilization users, the model is trained according to the training electricity utilization data corresponding to a large number of electricity utilization users to obtain a target electricity quantity prediction model corresponding to the large number of electricity utilization users, and the model is trained according to the training electricity utilization data corresponding to the high-demand electricity utilization users to obtain a target electricity quantity prediction model corresponding to the high-demand electricity utilization users.

In some embodiments, as shown in fig. 3, the method further includes a step of obtaining a target power consumption prediction model, and the step of obtaining the target power consumption prediction model includes:

s302, acquiring first electricity quantity data corresponding to a first time period of a training user and second electricity quantity data corresponding to a second time period of the training user, wherein the first time period is before the second time period.

Specifically, the training user may refer to a resident user to which data for training the model belongs, that is, the model is trained by acquiring data related to the training user. The first time period and the second time period may be contemporaneous historical time periods, for example, the first time period is from 2017 year 1 month No. 1 to 2017 year 1 month No. 31, and the second time period is from 2018 year 1 month No. 1 to 2018 year 1 month No. 31. The first time period and the second time period may also be historical time periods of the same duration, for example, the first time period is from number 1 month 1 of 2017 to number 31 month 1 of 2017, and the second time period is from number 1 month 3 of 2017 to number 31 month 3 of 2018. The first electric quantity data is the electric quantity corresponding to the first time period, and the second electric quantity data is the electric quantity corresponding to the second time period. When the first time period is one hour, the first electric quantity data is the electric quantity corresponding to one hour. Of course, the training user may also be other types of users than residential users.

S304, obtaining training characteristics of the training user according to the first electric quantity data, obtaining a training label of the training user according to the second electric quantity data, and obtaining a training sample by the training characteristics and the training label.

In particular, the first usage electrical quantity data may be used as a training feature. Data features can also be extracted according to the first electric quantity data to serve as training features. The second electrical quantity data may be used as a training label. The training features may be combined with training labels as training samples.

In some embodiments, the training characteristics may include one or more of contemporaneous period power usage, recent N days contemporaneous period power usage, contemporaneous regional temperature, recent N days contemporaneous regional temperature, contemporaneous holiday data, and contemporaneous blackout data.

In some embodiments, training characteristics of the training user may be derived from the first power data and other data, wherein the other data may include one or more of weather data, holiday data, and power outage data. The weather data may be, for example, daily weather data of an area where the residential user is located, which is acquired from a weather website. Holiday data can include, for example, saturday, sunday, and legal holidays, among others.

In some embodiments, the data associated with the constituent training samples may be obtained from various business systems under construction. For example, 24 electricity readings at a time by a residential user may be obtained from a metering automation system, including: power supply unit number, user number, data time, asset number, table code and comprehensive multiplying power; obtaining weather data from a weather website, comprising: area name, data time, and average air temperature; synchronizing power supply scheme data from a marketing system, comprising: the method comprises the following steps of (1) user number, power utilization type, contract capacity, running capacity, stop and stop reporting date, start and stop reporting date, power price scheme, power price and user state; from synchronous resident's user power failure data of all-round system of customer, include: power supply unit number, user number, power failure time and power restoration time. The user number of the power supply scheme standing book or the user number of the 24-time electric energy indicating number can be used as a query condition to query and output the power utilization information.

In some embodiments, data related to the formation of training samples may be obtained from various platforms and processed to retain available data. For example, the 24-hour electricity metering readings, weather data, power supply scheme data and power failure data of the residential users synchronized by the metering automation system, the weather website, the marketing system and the client comprehensive system can be screened and filtered, invalid abnormal data can be deleted, available data can be retained, and data information which can be used for the characteristic model can be calculated. The data of the power supply scheme with incomplete information and unreasonable data filling can be removed, for example, if the obtained operation capacity of the user is 0, the user data can be removed. According to the holiday and the power failure data, the user electric quantity of the corresponding date can be removed and is not used as training data of the model.

In some embodiments, the data filtering process may be performed on the power data of the user. Specifically, the missing 0 point data may be supplemented, so that the residential users with less than 24 0 point data per day may be removed or automatically supplemented (for example, supplemented by 0 electric quantity), and 0 electric quantity abnormal data may be removed, where 0 electric quantity abnormal data is: the data of the next 0 point is read smaller than the data of the 0 point today.

In some embodiments, the time-sharing electricity consumption, the daily electricity consumption and the monthly electricity consumption of the residential users can be calculated according to the processed electricity quantity data. Specifically, the processed electric quantity data may be summarized in whole hours. For example, the calculation method of the time-sharing power consumption may be: the time-sharing electricity consumption is the 24 time point electricity quantity data of the day-23 time point electricity quantity data of the day. The processed electric quantity data can be summarized according to daily electric quantity. For example, the daily electricity consumption may be calculated by: the daily electric quantity is the electric quantity at 0 point of the next day-the electric quantity at 0 point of this day. The multi-meter resident users are combined and summarized according to the day, namely the daily electric quantity of the resident users is single data. The processed electric quantity data can be summarized according to daily electric quantity. For example, the method of calculating the monthly power usage may be: the monthly electricity consumption is 0 point electricity quantity of the next month No. 1-0 point electricity quantity of the month No. 1.

In some embodiments, the contemporaneous temperature difference value and the recent N-day temperature change trend may be calculated from the collected weather temperature data.

And S306, performing model training according to the training samples to obtain a trained target power consumption prediction model.

Specifically, the model used in the model training may be a big data analysis algorithm such as a neural network algorithm and a genetic algorithm. The output of the target power consumption prediction model may include the amount of power corresponding to each day of the month, or may include the amount of power corresponding to each hour of the day.

In some embodiments, the residential users may be classified, or the electricity consumption data and other data corresponding to users of the same category may be analyzed and calculated to obtain the overall characteristics of users of the same electricity consumption attribute group, and a target electricity consumption prediction model corresponding to the users of the category may be obtained through training. Of course, the power consumption characteristics of the single user can be analyzed and calculated by using the power consumption data and other data corresponding to the single user, and a target power consumption prediction model corresponding to the single user can be obtained through training.

In some embodiments, the electricity quantity data output by the target electricity consumption quantity prediction model may be acquired, a historical electricity consumption quantity prediction curve may be calculated according to the electricity quantity data, and the historical electricity consumption quantity prediction curve may be compared with the historical actual electricity consumption quantity curve to verify the accuracy of the model. Therefore, a suitable big data analysis algorithm and a suitable feature model are analyzed. The historical electricity consumption prediction curve is a curve obtained according to the predicted electricity quantity of the historical electricity consumption, and the historical actual electricity consumption curve is a curve obtained according to the actual electricity quantity of the historical electricity. For example, the historical actual power usage curve may be a curve derived from actual power usage on a daily basis over the last month. The historical power consumption prediction curve may be a curve obtained from the predicted power consumption of the previous month per day output by the target power consumption prediction model. When the similarity between the historical power consumption prediction curve and the historical actual power consumption curve is high, the accuracy of the model can be considered to be high; when the similarity between the historical power consumption prediction curve and the historical actual power consumption curve is small, the accuracy of the model can be considered to be low.

In some embodiments, the query condition may be input through the interface, the target power consumption prediction model may return the predicted power consumption result to the interface through the query condition input through the interface, and the interface may further accept and display the corresponding historical power consumption data. The query conditions may include, for example: the system comprises a power supply unit, a unit where a power supply person is located by default, a user number, a user unit and the like. The query can be limited by authority, for example, the upper unit has authority to query the lower unit data, and the lower unit has no authority to query the upper unit data; the superior unit has the authority to inquire the inferior unit user, and the inferior unit has no authority to inquire the superior unit user. The queried results may include historical daily electricity data as well as model predicted daily electricity data at the same time. The interface can display the historical daily electricity data and the model prediction daily electricity data at the same time through a table, and can also display the historical daily electricity data and the model prediction daily electricity data at the same time through a curve. The comparison between the historical daily electricity consumption data and the model prediction daily electricity consumption data at the same time is realized, and therefore the accuracy of the model is verified. For example, if the difference in power usage between the curves is small, there are no unusual points or scatter points that are particularly prominent, and the model accuracy is high if the power usage is uniformly distributed.

In some embodiments, the query condition may be input through the interface, the date in the query condition may be a future date, and the target power consumption prediction model may obtain the query condition input from the interface and return a prediction result of the power amount on the future date according to the query condition. For example, the query conditions may include: the power supply unit defaults a unit where a person is located, a user number, a user unit and a predicted electricity utilization month, wherein the predicted electricity utilization month is a month needing predicted electricity utilization data, such as the next month. The response result of the query condition may include user information, which may include, for example, a user basic profile, a user number, a user name, a power usage type, a contract capacity, and an operation capacity, and a power amount prediction result. The power prediction result may include predicted daily power data for each predicted month and day, and the like. The interface may present the results of the response to the query.

In the embodiment of the application, the training characteristics of the training user are obtained through the first electricity consumption data corresponding to the first time period of the training user, the training labels of the training user are obtained according to the second electricity consumption data corresponding to the second time period of the training user, the training samples are obtained according to the training characteristics and the training labels, so that the model can be trained according to historical electricity consumption data, the accuracy of the model can be verified through the historical electricity consumption data, and the target electricity consumption prediction model with high accuracy is obtained.

In some embodiments, there are a plurality of training samples corresponding to the same training user, as shown in fig. 4, the step S306 performs model training according to the training samples, and obtaining the trained target power consumption prediction model includes:

s402, the first electric quantity data in each training sample are respectively input into the electric quantity prediction model to be trained, and training predicted electric quantity data corresponding to the training user in the second time period are obtained.

Specifically, the power consumption prediction model to be trained may be a neural network model, and the trained target power consumption prediction model may be obtained by training the power consumption prediction model to be trained through a plurality of training samples. The first electric quantity data in each training sample can be respectively input into the electric quantity prediction model to be trained, the electric quantity prediction model to be trained respectively calculates each first electric quantity data, and the corresponding training predicted electric quantity data corresponding to the second time period is output. A training sample may be used to obtain a training predicted power usage data. For example, if the first electricity consumption data is the time-sharing electricity consumption, the predicted electricity consumption data is trained to be the predicted value of the electricity consumption corresponding to the time-sharing.

S404, sequencing the training predicted power consumption data corresponding to the same training user according to a time sequence to obtain a training predicted power consumption data sequence.

Specifically, the training predicted power consumption data have a time sequence relationship, for example, each training predicted power consumption data is a prediction of power consumption corresponding to different time divisions. The training predicted power consumption data can be sorted according to the time sequence to form a training predicted power consumption data sequence.

S406, sequencing the second electric quantity data corresponding to the same training user according to a time sequence to obtain a second electric quantity data sequence.

Specifically, the second electricity quantity data have a time sequence relationship, for example, each second electricity quantity data is an actual electricity consumption corresponding to different time divisions. The second electric quantity data can be sequenced according to the time sequence to form a second electric quantity data sequence. Therefore, the second electricity quantity data sequence is an actual value, and the training predicted electricity consumption data sequence is a predicted value of the second electricity quantity data sequence predicted by the model.

And S408, calculating to obtain a model loss value according to the difference between the training predicted power consumption data sequence and the second power consumption data sequence, wherein the model loss value and the difference form a negative correlation relationship.

Specifically, a distance, such as a euclidean distance, between the training predicted power usage data sequence and the second power usage data sequence may be calculated as a loss value for the model.

And S410, adjusting parameters of the power consumption prediction model to be trained according to the model loss value to obtain the target power consumption prediction model.

Specifically, a gradient descent method may be used to adjust parameters of the power consumption prediction model to be trained in the direction of the model loss value, so as to obtain parameters of the power consumption prediction model to be trained that minimize the model loss value, and the power consumption prediction model to be trained corresponding to the parameters is used as the target power consumption prediction model.

In the embodiment of the present application, the second electric quantity data sequence is an actual value, and the training predicted electric quantity data sequence is a predicted value of the second electric quantity data sequence predicted by the model, so that a model loss value can be obtained according to the second electric quantity data sequence and the training predicted electric quantity data sequence, and a target electric quantity prediction model with high accuracy is obtained.

Of course, when the model training is performed, the 24 historical power consumptions corresponding to the time divisions respectively may be simultaneously input into the power consumption prediction model to be trained, and the model may be trained to obtain the 24 predicted power consumption values corresponding to the time divisions respectively.

In some embodiments, as shown in fig. 5A, the step S210 of obtaining the target electricity price calculation scheme corresponding to the target user from the candidate electricity price calculation scheme set by filtering according to each candidate electricity price calculation scheme and the target predicted electricity consumption includes:

and S502, obtaining expected power consumption corresponding to each candidate electricity price calculation scheme, and comparing the expected power consumption with the target predicted power consumption to obtain a comparison result.

Specifically, the expected power consumption may be a power consumption range in which the electricity rate calculated using the corresponding candidate electricity rate calculation scheme is smaller than that of the other schemes. The target predicted power consumption may be compared with expected power consumption corresponding to each candidate electricity price calculation scheme to obtain a comparison result. The comparison result may be that the target predicted power usage is within the expected power usage range or the target predicted power usage is not within the expected power usage range.

And S504, screening the candidate electricity price calculation scheme set according to the comparison result to obtain a target electricity price calculation scheme corresponding to the target user.

Specifically, when the comparison result is that the target predicted power consumption is the expected power consumption, the corresponding candidate power price calculation scheme is used as the target power price calculation scheme.

In the embodiment of the application, the expected power consumption corresponding to each candidate electricity price calculation scheme is obtained, the target predicted power consumption is compared with each expected power consumption, and when the target predicted power consumption belongs to the expected power consumption, the expected power consumption is used as the target electricity price calculation scheme.

In some embodiments, the step S504 of screening the candidate electricity price calculation scheme set according to the comparison result to obtain the target electricity price calculation scheme corresponding to the target user includes: and when the comparison result is that the target predicted electricity consumption belongs to the expected electricity consumption, taking the corresponding candidate electricity price calculation scheme as the target electricity price calculation scheme.

In some embodiments, as shown in fig. 5B, there is provided an electricity price data processing method including:

step 1, preparing data.

Specifically, user electric quantity data, weather data, user power supply scheme data, holiday data and user power failure data are extracted from each associated service system;

and 2, processing data.

Specifically, time-sharing electricity consumption, daily electricity consumption and monthly electricity consumption of a user are calculated according to the electricity data, and a contemporaneous temperature difference value is calculated according to weather data; processing the power supply scheme data and eliminating invalid data; processing the holiday data; processing power failure data; and outputting the processed effective data set.

And 3, constructing a characteristic model.

Specifically, model construction factors are defined, a power consumption prediction special diagnosis model is built, and predicted power consumption of a user is output.

And 4, verifying the model.

Specifically, the historical power consumption curve and the actual power consumption curve are compared according to the characteristic model, and the model accuracy is verified.

And 5, predicting the electric quantity.

Specifically, a historical power consumption prediction curve and a historical actual power consumption curve are calculated according to the characteristic model and compared, and model accuracy is verified.

And 6, analyzing the influence factors of the electricity price.

Specifically, the electricity price marketing factors of ordinary electricity consumption, large amount of electricity consumption and high-demand electricity consumption are analyzed, and users capable of optimally adjusting the electricity prices are output.

And 7, analyzing the optimal electricity price of the large-amount electricity utilization and the high-demand electricity utilization.

Specifically, a large amount of industrial and commercial and other power utilization (101-3000kVA) users and high-demand industrial and commercial and other power utilization (3000kVA and above) users forecast power consumption as input parameters, a large amount of power utilization rates and high-demand power utilization rate electricity charges are analyzed and calculated, and an optimal scheme is output by comparing results.

And 8, ending.

Specifically, the non-residential user electricity rate data processing ends. And completing closed-loop management of non-resident user electricity price data processing.

As shown in fig. 5C, there is provided an electricity rate data processing system including: the system comprises a data preparation module, a characteristic model construction module, a model verification module, an electric quantity prediction module, an electricity price influence factor analysis module and a large-amount electricity utilization and high-demand electricity utilization optimal electricity price analysis module. The background business system in the figure refers to a collection of business management systems which provide background information support for the electricity price data processing system.

It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts of the above embodiments may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or the stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least a part of the sub-steps or the stages of other steps.

In some embodiments, as shown in fig. 6, there is provided an electricity price data processing apparatus including: a candidate electricity price calculation scheme set obtaining module 602, a candidate user set obtaining module 604, a target user obtaining module 606, a target predicted electricity consumption obtaining module 608, and a target electricity price calculation scheme obtaining module 610, where:

a candidate electricity price calculation scheme set obtaining module 602, configured to obtain a candidate electricity price calculation scheme set corresponding to a user of a target user type, where the candidate electricity price calculation scheme set includes multiple candidate electricity price calculation schemes.

The candidate user set obtaining module 604 is configured to obtain a candidate user set corresponding to the target user type, where the candidate user set includes multiple candidate users.

And the target user obtaining module 606 is configured to filter the candidate user set according to the power consumption information of the candidate user to obtain a target user.

And a target predicted power consumption obtaining module 608, configured to obtain a target predicted power consumption corresponding to the target user according to the historical power consumption data corresponding to the target user in the historical time period.

And a target electricity price calculation scheme obtaining module 610, configured to filter a target electricity price calculation scheme corresponding to the target user from the candidate electricity price calculation scheme set according to each candidate electricity price calculation scheme and the target predicted electricity consumption.

In some embodiments, the target electricity consumption prediction model is further configured to input historical electricity consumption data into a trained target electricity consumption prediction model, predict and obtain a target electricity consumption prediction corresponding to a target user, and train the target electricity consumption prediction model according to training electricity consumption data of a training user corresponding to a target user type.

In some embodiments, the apparatus further includes a module for obtaining a target power consumption prediction model, where the module for obtaining a target power consumption prediction model includes:

the power consumption data acquisition unit is used for acquiring first power consumption data corresponding to a first time period of a training user and second power consumption data corresponding to a second time period of the training user, wherein the first time period is before the second time period.

And the training sample obtaining unit is used for obtaining the training characteristics of the training user according to the first electric quantity data, obtaining the training labels of the training user according to the second electric quantity data, and obtaining the training samples by the training characteristics and the training labels.

And the target power consumption prediction model obtaining unit is used for carrying out model training according to the training samples to obtain a trained target power consumption prediction model.

In some embodiments, the number of training samples corresponding to the same training user is multiple, and the target power consumption prediction model obtaining unit is further configured to input the first power consumption data in each training sample into the power consumption prediction model to be trained, so as to obtain the training predicted power consumption data corresponding to the training user in the second time period. And sequencing the training predicted power consumption data corresponding to the same training user according to a time sequence to obtain a training predicted power consumption data sequence. And sequencing all the second electric quantity data corresponding to the same training user according to a time sequence to obtain a second electric quantity data sequence. And calculating to obtain a model loss value according to the difference between the training predicted power consumption data sequence and the second power consumption data sequence, wherein the model loss value and the difference form a negative correlation relationship. And adjusting parameters of the power consumption prediction model to be trained according to the model loss value to obtain the target power consumption prediction model.

In some embodiments, the target electricity rate calculation scheme obtaining module 610 includes:

and the comparison result obtaining unit is used for obtaining expected power consumption corresponding to each candidate electricity price calculation scheme, and comparing the expected power consumption with the target predicted power consumption to obtain a comparison result.

And the target electricity price calculation scheme obtaining unit is used for screening the candidate electricity price calculation scheme set according to the comparison result to obtain a target electricity price calculation scheme corresponding to the target user.

In some embodiments, the target electricity price calculation scheme obtaining unit is further configured to take the corresponding candidate electricity price calculation scheme as the target electricity price calculation scheme when the comparison result is that the target predicted used electricity amount belongs to the expected used electricity amount.

For specific definition of the electricity price data processing device, reference may be made to the above definition of the electricity price data processing method, which is not described herein again. Each module in the above electricity price data processing apparatus may be wholly or partially implemented by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In some embodiments, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a power rate data processing method.

Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In some embodiments, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the steps of the above-mentioned electricity price data processing method when executing the computer program.

In some embodiments, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the above-described electricity price data processing method.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A power rate data processing method, the method comprising:

acquiring a candidate electricity price calculation scheme set corresponding to a user of a target user type, wherein the candidate electricity price calculation scheme set comprises a plurality of candidate electricity price calculation schemes;

acquiring a candidate user set corresponding to the target user type, wherein the candidate user set comprises a plurality of candidate users;

screening target users from the candidate user set according to the electricity utilization information of the candidate users;

predicting to obtain target predicted power consumption corresponding to the target user according to the historical power consumption data corresponding to the target user in the historical time period;

and screening the target electricity price calculation scheme corresponding to the target user from the candidate electricity price calculation scheme set according to each candidate electricity price calculation scheme and the target predicted electricity consumption.

2. The method of claim 1, wherein the predicting the target predicted power consumption corresponding to the target user according to the historical power consumption data corresponding to the target user in the historical time period comprises:

and inputting the historical electricity consumption data into a trained target electricity consumption prediction model, predicting to obtain target predicted electricity consumption corresponding to the target user, and training the target electricity consumption prediction model according to training electricity consumption data of a training user corresponding to the type of the target user to obtain the target predicted electricity consumption.

3. The method of claim 2, wherein the step of deriving the target power usage prediction model comprises:

acquiring first electricity quantity data corresponding to a first time period of a training user and second electricity quantity data corresponding to a second time period of the training user, wherein the first time period is before the second time period;

obtaining a training feature of the training user according to the first electric quantity data, obtaining a training label of the training user according to the second electric quantity data, and obtaining a training sample by using the training feature and the training label;

and carrying out model training according to the training samples to obtain the trained target power consumption prediction model.

4. The method according to claim 3, wherein there are a plurality of training samples corresponding to the same training user, and the performing model training according to the training samples to obtain the trained target power consumption prediction model comprises:

respectively inputting the first electric quantity data in each training sample into a power consumption prediction model to be trained to obtain training predicted power consumption data corresponding to the training user in the second time period;

sequencing the training predicted power consumption data corresponding to the same training user according to a time sequence to obtain a training predicted power consumption data sequence;

sequencing all the second electric quantity data corresponding to the same training user according to a time sequence to obtain a second electric quantity data sequence;

calculating to obtain a model loss value according to the difference between the training predicted power consumption data sequence and the second power consumption data sequence, wherein the model loss value and the difference form a negative correlation relationship;

and adjusting parameters of a power consumption prediction model to be trained according to the model loss value to obtain a target power consumption prediction model.

5. The method according to claim 1, wherein the obtaining of the target electricity price calculation scheme corresponding to the target user by screening from the candidate electricity price calculation scheme set according to each candidate electricity price calculation scheme and the target predicted electricity consumption comprises:

obtaining expected power consumption corresponding to each candidate electricity price calculation scheme, and comparing the expected power consumption with the target predicted power consumption to obtain a comparison result;

and screening the candidate power price calculation scheme set according to the comparison result to obtain a target power price calculation scheme corresponding to the target user.

6. The method according to claim 5, wherein the screening of the target electricity price calculation scheme corresponding to the target user from the candidate electricity price calculation scheme set according to the comparison result comprises:

and when the comparison result indicates that the target predicted electricity consumption belongs to the expected electricity consumption, taking the corresponding candidate electricity price calculation scheme as a target electricity price calculation scheme.

7. An electricity price data processing apparatus, characterized in that the apparatus comprises:

the candidate electricity price calculation scheme set acquisition module is used for acquiring a candidate electricity price calculation scheme set corresponding to a user of a target user type, and the candidate electricity price calculation scheme set comprises a plurality of candidate electricity price calculation schemes;

a candidate user set obtaining module, configured to obtain a candidate user set corresponding to the target user type, where the candidate user set includes multiple candidate users;

the target user acquisition module is used for screening the candidate user set according to the electricity utilization information of the candidate users to obtain target users;

the target predicted power consumption obtaining module is used for predicting and obtaining target predicted power consumption corresponding to the target user according to historical power consumption data corresponding to the target user in a historical time period;

and the target electricity price calculation scheme obtaining module is used for screening the target electricity price calculation scheme corresponding to the target user from the candidate electricity price calculation scheme set according to each candidate electricity price calculation scheme and the target predicted electricity consumption.

8. The device of claim 7, wherein the target predicted power consumption obtaining module is further configured to input the historical power consumption data into a trained target power consumption prediction model, and predict a target predicted power consumption corresponding to the target user, where the target power consumption prediction model is obtained by training according to training power consumption data of a training user corresponding to the target user type.

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the electricity price data processing method according to any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium on which a computer program is stored, the computer program, when being executed by a processor, implementing the steps of the electricity price data processing method according to any one of claims 1 to 6.