A multi-dimensional power marketing analysis method and system based on big data

Abstract

The application relates to the field of power marketing management, and discloses a multi-dimensional power marketing analysis method and system based on big data, which realizes the management and scheduling of power use in a region through a power marketing mode based on individual user power use characteristic behaviors, that is, the power use demand and power use characteristic time period of a user are judged according to the power use habits of the user, so that the group power use demand in the region is managed and planned, the users are encouraged to complete corresponding power use demand actions in the marketing time period of the group demand in the region through preferential marketing, and then the homogenization management of the total power use curve of the region is realized, and the power use peak value of the group power use in the region is reduced or the height of the power use peak value is reduced.

Description

Technical Field

[0001] This invention relates to the field of electricity marketing management, specifically a multi-dimensional electricity marketing analysis method and system based on big data. Background Technology

[0002] With the increasing number of electrical devices and the concentration of population density brought about by community development, some high-density areas are prone to peak electricity consumption at different times during daily life. This can easily lead to peak electricity consumption exceeding the normal stable power supply, reducing power supply security. Excessive power consumption can also accelerate the aging of power supply equipment, and the reduced reserve of power supply caused by peak consumption makes it impossible to carry out timely and effective power dispatch in the event of an emergency.

[0003] To address this phenomenon, existing technologies typically employ peak-valley pricing for electricity marketing, guiding users to engage in non-emergency electricity consumption behaviors such as charging electric vehicles during off-peak hours. However, the existing peak-valley pricing method has poor variability and lacks refined scheduling and marketing effectiveness. Summary of the Invention

[0004] The purpose of this invention is to provide a multi-dimensional electricity marketing analysis method and system based on big data to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: A multi-dimensional electricity marketing analysis method based on big data includes: Electricity consumption data within several historical periods is acquired, and electricity consumption characteristics are analyzed on the electricity consumption data to obtain the user's electricity consumption behavior characteristics. The user behavior characteristics include characteristic behaviors and characteristic time periods, which are used to characterize electricity consumption behavior and its occurrence time intervals, respectively. Select a fixed number of adjacent recording periods, evaluate the total power usage records of the marketing dispatch area within multiple recording periods, and obtain the regional power consumption curve and the corresponding multiple peak power consumption periods; Based on the peak electricity consumption period, user behavior characteristics are retrieved and filtered to obtain several users to be marketed, and marketing periods are set on both sides of the peak electricity consumption period; Based on the misalignment between the characteristic time periods corresponding to the user behavior characteristics and the marketing time periods, the marketing time periods are split into multiple marketing sub-time periods, and corresponding user characteristic marketing plans are established. Each user characteristic marketing plan is associated with a user.

[0006] As a further aspect of the present invention: the step of performing electricity consumption characteristic analysis on several electricity consumption record data to obtain the user's electricity consumption behavior characteristics specifically includes: The user's electricity consumption data within a recording period is continuously evaluated. Based on the power surge phenomenon of the appliance startup, the user's multiple characteristic behaviors based on the appliance's electricity consumption are judged, and the electricity consumption and duration of the characteristic behaviors are recorded. The characteristic behaviors in several electricity consumption records are statistically analyzed over time periods to obtain the characteristic time periods of the characteristic behaviors. The characteristic time periods are then marked based on the trigger probability statistics of the characteristic behaviors in several recording periods. The characteristic time periods also include the main distribution time periods and the occasional time periods.

[0007] As a further aspect of the present invention: the step of retrieving and filtering user behavior characteristics based on the peak electricity consumption period to obtain several users to be marketed specifically includes: Based on the peak electricity consumption period, the characteristic time periods of several users in the marketing dispatch area are matched, and the marketing level of users is divided based on the inclusion ratio of the characteristic time periods during the peak electricity consumption period. The marketing level is highest at the middle ratio and decreases to both sides of the ratio value. Obtain the characteristic behaviors of several users corresponding to the characteristic time periods, and mark several users in the marketing level order list based on electricity consumption; The marketing order list is sorted based on the extra electricity consumption exceeding a preset threshold during the peak electricity consumption period. Several user objects whose total electricity consumption reaches the extra electricity consumption are selected and marked as first-level marketing objects. The first-level marketing objects also include a marketing expectation multiplier, which is greater than one and is used to offset the proportion of marketing failures.

[0008] As a further aspect of the present invention: the marketing period and the peak electricity consumption period do not overlap in any time; the marketing discount for the primary marketing target is higher than that for other marketing targets; and the specific correlation between the multiple marketing sub-periods and the user characteristic marketing scheme is as follows: When the marketing sub-period overlaps with the characteristic period and the marketing period, the user characteristic marketing plan is a guiding discount plan; When the marketing sub-period is adjacent to but does not overlap with the characteristic period, the user characteristic marketing plan is a promotional discount plan; When the marketing sub-period is far from the characteristic period, the user characteristic marketing plan is an inducement discount plan. The inducement discount plan, promotion discount plan and inducement discount plan are arranged sequentially and do not overlap on the time axis. The marketing discount of the inducement discount plan is higher than that of the inducement discount plan and the inducement discount plan in turn.

[0009] As a further aspect of the present invention, a user feature correction step is also included: When the characteristic time period corresponding to a user's characteristic behavior does not have a clear main distribution time period within multiple recording periods, the user's electricity consumption start node corresponding to each of the electricity consumption record data is determined. The characteristic behavior in each of the electricity consumption records is determined based on the relative time interval of the electricity consumption start node. Multiple relative time intervals are aligned based on the electricity consumption start node to obtain the relative characteristic time period corresponding to the characteristic behavior.

[0010] This invention aims to provide a multi-dimensional electricity marketing analysis system based on big data, comprising: The feature statistics module is used to acquire electricity consumption record data within several historical period and perform electricity consumption feature analysis on the electricity consumption record data to obtain the user's electricity consumption behavior characteristics. The user behavior characteristics include characteristic behaviors and characteristic time periods, which are used to characterize electricity consumption behavior and its occurrence time interval, respectively. The peak assessment module is used to select a rated number of adjacent recording periods, assess the total power usage records of the marketing dispatch area within multiple recording periods, and obtain the regional power consumption curve and the corresponding multiple peak power consumption periods. The marketing matching module is used to retrieve and filter user behavior characteristics based on the peak electricity consumption period, obtain several users to be marketed, and set marketing periods on both sides of the peak electricity consumption period. The marketing execution module is used to split the marketing period into multiple marketing sub-periods based on the misalignment between the characteristic time period corresponding to the user behavior characteristics and the marketing period, and to establish user characteristic marketing plans accordingly. The user characteristic marketing plans are associated with users one by one.

[0011] As a further aspect of the present invention: the feature statistics module includes: The feature recognition unit is used to continuously evaluate the user's electricity consumption record data within a recording period, determine multiple characteristic behaviors of the user based on the power surge phenomenon of the appliance, and record the power consumption and duration of the characteristic behaviors. The feature statistics unit is used to perform time period statistics on the feature behavior in several electricity consumption record data, obtain the feature time period of the feature behavior, and mark the feature time period based on the trigger probability statistics of the feature behavior in several recording periods. The feature time period also includes the main distribution time period and the occasional time period.

[0012] As a further embodiment of the present invention: the marketing matching module includes: The marketing time period matching unit is used to match the characteristic time periods of several users in the marketing scheduling area according to the peak electricity consumption period, and to classify users into marketing levels based on the inclusion ratio of the characteristic time periods during the peak electricity consumption period. The marketing level is highest at the middle ratio and decreases to both sides of the ratio value. The marketing group matching unit is used to obtain the characteristic behaviors of several users corresponding to the characteristic time period, and to mark several users in the marketing level order list based on electricity consumption; The marketing group sorting unit is used to sort the marketing order list based on the extra electricity consumption exceeding a preset threshold during the peak electricity consumption period, select several user objects whose total electricity consumption reaches the extra electricity consumption, and mark them as first-level marketing objects. The first-level marketing objects also include a marketing expectation ratio, which is greater than one, and is used to offset the marketing failure rate.

[0013] As a further aspect of the present invention: the marketing period and the peak electricity consumption period do not overlap in any time; the marketing discount for the primary marketing target is higher than that for other marketing targets; and the specific correlation between the multiple marketing sub-periods and the user characteristic marketing scheme is as follows: When the marketing sub-period overlaps with the characteristic period and the marketing period, the user characteristic marketing plan is a guiding discount plan; When the marketing sub-period is adjacent to but does not overlap with the characteristic period, the user characteristic marketing plan is a promotional discount plan; When the marketing sub-period is far from the characteristic period, the user characteristic marketing plan is an inducement discount plan. The inducement discount plan, promotion discount plan and inducement discount plan are arranged sequentially and do not overlap on the time axis. The marketing discount of the inducement discount plan is higher than that of the inducement discount plan and the inducement discount plan in turn.

[0014] As a further embodiment of the present invention, it also includes a user correction module, specifically comprising: The feature point selection unit is used to determine the user's electricity consumption start node corresponding to each electricity consumption record data when the feature time period corresponding to the user's feature behavior has no clear main distribution time period in multiple recording periods. The feature correction unit is used to determine the relative time interval of the feature behavior based on the electricity consumption start node in each of the electricity consumption record data, and to align multiple relative time intervals based on the electricity consumption start node to obtain the relative feature time period corresponding to the feature behavior.

[0015] Compared with the prior art, the beneficial effects of the present invention are: by using an electricity marketing method based on the electricity consumption characteristics of individual users, the management and scheduling of electricity use within a region is realized. That is, the electricity demand of users and the characteristic time periods of electricity consumption are judged according to the users' electricity consumption habits, thereby managing and planning the group electricity demand within the region. Through preferential marketing, users are encouraged to complete the corresponding electricity demand actions within the marketing period of the group demand in the region, thereby realizing the equalization management of the total electricity consumption curve in the region, reducing the peak electricity consumption of the group in the region or lowering the peak electricity consumption height. Attached Figure Description

[0016] Figure 1 This is a flowchart of a multi-dimensional electricity marketing analysis method based on big data.

[0017] Figure 2 This is a flowchart illustrating the steps involved in acquiring potential customers in a multi-dimensional power marketing analysis method based on big data.

[0018] Figure 3 This is a block diagram of a multi-dimensional power marketing analysis system based on big data.

[0019] Figure 4 This is a block diagram of the feature statistics module in a multi-dimensional power marketing analysis system based on big data. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0021] The specific implementation of the present invention will be described in detail below with reference to specific embodiments.

[0022] like Figure 1 The above-described multi-dimensional electricity marketing analysis method based on big data, provided as an embodiment of the present invention, includes the following steps: S10, acquire electricity consumption record data within several historical period, and perform electricity consumption feature analysis on several electricity consumption record data to obtain the user's electricity consumption behavior characteristics. The user behavior characteristics include characteristic behaviors and characteristic time periods, which are used to characterize electricity consumption behavior and its occurrence time interval, respectively. S20: Select a number of adjacent recording periods, evaluate the total power usage records of the marketing dispatch area within multiple recording periods, and obtain the regional power consumption curve and the corresponding multiple peak power consumption periods; S30, based on the peak electricity consumption period, the user behavior characteristics are retrieved and filtered to obtain several users to be marketed, and marketing periods are set on both sides of the peak electricity consumption period; S40, the marketing period is split into multiple marketing sub-periods based on the misalignment between the characteristic time period corresponding to the user behavior characteristics and the marketing period, and user characteristic marketing plans are established accordingly. The user characteristic marketing plans are associated with users one by one.

[0023] This embodiment presents a multi-dimensional electricity marketing analysis method based on big data. By using electricity marketing methods based on individual user electricity consumption characteristics, it achieves management and scheduling of electricity use within a region. Specifically, it determines users' electricity demand and peak consumption periods based on their electricity usage habits, thereby managing and planning the group electricity demand within the region. Through preferential marketing, it encourages users to fulfill their corresponding electricity consumption needs during the marketing periods of the regional group demand, thus achieving the equalization management of the total regional electricity consumption curve, reducing peak electricity consumption or lowering the peak value. Specifically, in existing technologies, smart IoT meters have become widespread. These meters can record user electricity consumption behavior, including... When users start consuming electricity, their electricity demand characteristics at different times, and the corresponding electricity activities, can be analyzed. If the electricity consumption curve in a certain area typically experiences high peaks during a certain period, leading to increased power supply pressure, then the electricity demand time periods of users within that time period can be shifted to either side of the peak. Electricity consumption discounts can be set during the time periods on either side of the peak to guide users to engage in corresponding electricity activities earlier or later. This achieves the goal of regional electricity consumption management through precise electricity marketing down to the user's behavior. Compared to the generalized off-peak electricity pricing guidance management method used in existing technologies, the marketing cycle is more refined and dynamic. The short-cycle, follow-up marketing cycle can achieve more precise electricity marketing management and achieve better power dispatch management results.

[0024] In another preferred embodiment of the present invention, the step of performing electricity consumption characteristic analysis on several electricity consumption record data to obtain the user's electricity consumption behavior characteristics specifically includes: The user's electricity consumption data within a recording period is continuously evaluated. Based on the power surge phenomenon of the appliance startup, the user's multiple characteristic behaviors based on the appliance's electricity consumption are judged, and the electricity consumption and duration of the characteristic behaviors are recorded. The characteristic behaviors in several electricity consumption records are statistically analyzed over time periods to obtain the characteristic time periods of the characteristic behaviors. The characteristic time periods are then marked based on the trigger probability statistics of the characteristic behaviors in several recording periods. The characteristic time periods also include the main distribution time periods and the occasional time periods.

[0025] In this embodiment, the steps for judging user characteristic behavior are broken down and explained, mainly including two parts. First, the judgment of the user's characteristic electricity consumption behavior, that is, the type of electrical appliances used by the user in daily electricity use (here, the type of electrical appliance is mainly considered from the perspective of power consumption, that is, the power consumption determines the type, rather than the type of use for the user, and here we mainly consider high power consumption appliances), such as the type of 1 kilowatt appliance. Second, the usage time of different types of electrical appliances (i.e., characteristic time periods). For example, if the type of 1 kilowatt appliance used by the user is a small electric kettle, he / she usually boils two to three kettles of hot water for cooking and household drinking between 7 pm and 8 pm. Therefore, through judgment and statistics, the characteristic time period of this 1 kilowatt characteristic behavior is between 7 pm and 8 pm. Here, the surge phenomenon is used to judge the electrical appliance instead of judging the increase in power consumption. In fact, there is a transitional increase in power consumption for different appliances. Therefore, the rise in the power consumption curve cannot be completely determined as the start-up of a new appliance. However, the surge phenomenon is a brief peak phenomenon that accompanies the appliance during the start-up process. Therefore, this feature is used as an auxiliary judgment.

[0026] like Figure 2 As shown, in another preferred embodiment of the present invention, the step of retrieving and filtering user behavior characteristics based on the peak electricity consumption period to obtain several users to be marketed specifically includes: S31, Match the characteristic time periods of several users in the marketing dispatch area according to the peak electricity consumption period, and classify the users into marketing levels based on the inclusion ratio of the characteristic time periods during the peak electricity consumption period, wherein the marketing level is highest at the middle ratio and decreases to both sides of the ratio value. S32, obtain the characteristic behaviors of several users corresponding to the characteristic time period, and mark several users in the marketing level order list based on electricity consumption; S33, based on the additional electricity consumption exceeding a preset threshold during the peak electricity consumption period, the marketing order list is sorted, and several user objects whose total electricity consumption reaches the additional electricity consumption are selected and marked as first-level marketing objects. The first-level marketing objects also include a marketing expectation multiple, which is greater than one and is used to offset the marketing failure rate.

[0027] In this embodiment, the principle behind the selection process for marketing users is explained in detail. The purpose of marketing scheduling is to reduce the occurrence of peak electricity consumption in the region. Therefore, marketing users are selected through peak time periods. Only by dispersing the concentration of users' electricity consumption behavior during peak periods can the probability or height of peaks be reduced. The reason for selecting users with a proportion of peak periods as primary marketing targets is as follows: For users with a large proportion, their electricity consumption behavior is relatively fixed and related to their lifestyle and rhythm (or the electricity consumption behavior is a necessary behavior with a special purpose), so the marketing success rate is low. For users with a small proportion, their characteristic time periods may be relatively broad, or the main distribution period of their characteristic time periods may be different from the peak period. Therefore, in reality, the electricity consumption time periods of these users are likely to be different from the peak period, so there is no need to allocate more marketing, and timely direct marketing will be effective, ultimately having a small impact on peaks. The middle proportion has a high degree of overlap in characteristic time periods, and at the same time, there is a high possibility of adjustment in the lifestyle habits corresponding to the characteristic behaviors (corresponding to the non-overlapping time periods). Therefore, this group of people is set as primary marketing targets.

[0028] In another preferred embodiment of the present invention, the marketing period and the peak electricity consumption period do not overlap in any time period, the marketing discount for the primary marketing target is higher than that for other marketing targets, and the specific association between the multiple marketing sub-periods and the user characteristic marketing scheme is as follows: When the marketing sub-period overlaps with the characteristic period and the marketing period, the user characteristic marketing plan is a guiding discount plan; When the marketing sub-period is adjacent to but does not overlap with the characteristic period, the user characteristic marketing plan is a promotional discount plan; When the marketing sub-period is far from the characteristic period, the user characteristic marketing plan is an inducement discount plan. The inducement discount plan, promotion discount plan and inducement discount plan are arranged sequentially and do not overlap on the time axis. The marketing discount of the inducement discount plan is higher than that of the inducement discount plan and the inducement discount plan in turn.

[0029] In this embodiment, the user characteristic marketing scheme is further explained, which mainly includes two parts. First, the first-level marketing target has higher marketing discounts, that is, the corresponding electricity discount price is greater. Second, for marketing targets of the same level, there are multiple marketing sub-time periods, and the marketing intensity is greater the further away from the peak time period, so as to guide users to complete their corresponding electricity needs at a time further away from the peak time period.

[0030] As another preferred embodiment of the present invention, a user feature correction step is also included: When the characteristic time period corresponding to a user's characteristic behavior does not have a clear main distribution time period within multiple recording periods, the user's electricity consumption start node corresponding to each of the electricity consumption record data is determined. The characteristic behavior in each of the electricity consumption records is determined based on the relative time interval of the electricity consumption start node. Multiple relative time intervals are aligned based on the electricity consumption start node to obtain the relative characteristic time period corresponding to the characteristic behavior.

[0031] In this embodiment, the electricity consumption characteristics of different users may not be determined entirely by a fixed time period within a daily cycle. They may also be determined by the time they return home (e.g., users with irregular work hours or even shift work). The difference in the time they finish work in different cycles is large, so the time they start using electricity each day also varies greatly. However, the electricity consumption behaviors they perform after returning home each day should be similar. For example, if they finish work at 7 pm, they might use kitchen appliances to cook at 8 pm and use the electric water heater to heat water for a shower at 9 pm. If they finish get off work at 9 pm, they might use kitchen appliances to cook at 9:50 pm and use the electric water heater to shower at 10:30 pm. Therefore, using the time they start using appliances after returning home as the starting point for cycle judgment also has a certain degree of regularity, and their relative characteristic time periods can be obtained based on this characteristic.

[0032] like Figure 3 As shown, the present invention also provides a multi-dimensional power marketing analysis system based on big data, which includes: The feature statistics module 100 is used to acquire electricity consumption record data within several historical period and perform electricity consumption feature analysis on several electricity consumption record data to obtain the user's electricity consumption behavior characteristics. The user behavior characteristics include characteristic behaviors and characteristic time periods, which are used to characterize electricity consumption behavior and its occurrence time interval, respectively. Peak assessment module 200 is used to select a rated number of adjacent recording periods, assess the total power usage records of the marketing dispatch area within multiple recording periods, and obtain the regional power consumption curve and the corresponding multiple power consumption peak periods. The marketing matching module 300 is used to retrieve and filter user behavior characteristics based on the peak electricity consumption period, obtain several users to be marketed, and set marketing periods on both sides of the peak electricity consumption period. The marketing execution module 400 is used to split the marketing period into multiple marketing sub-periods based on the misalignment between the characteristic time period corresponding to the user behavior characteristics and the marketing period, and to establish user characteristic marketing plans accordingly. The user characteristic marketing plans are associated with users one by one.

[0033] like Figure 4As shown, in another preferred embodiment of the present invention, the feature statistics module includes: The feature recognition unit 110 is used to continuously evaluate the user's electricity consumption record data within a recording period, determine multiple feature behaviors of the user based on the power surge phenomenon of the appliance, and record the power consumption and duration of the feature behaviors. The feature statistics unit 120 is used to perform time period statistics on the feature behavior in several electricity consumption record data, obtain the feature time period of the feature behavior, and mark the feature time period based on the trigger probability statistics of the feature behavior in several recording periods. The feature time period also includes the main distribution time period and the occasional time period.

[0034] In another preferred embodiment of the present invention, the marketing matching module includes: The marketing time period matching unit is used to match the characteristic time periods of several users in the marketing scheduling area according to the peak electricity consumption period, and to classify users into marketing levels based on the inclusion ratio of the characteristic time periods during the peak electricity consumption period. The marketing level is highest at the middle ratio and decreases to both sides of the ratio value. The marketing group matching unit is used to obtain the characteristic behaviors of several users corresponding to the characteristic time period, and to mark several users in the marketing level order list based on electricity consumption; The marketing group sorting unit is used to sort the marketing order list based on the extra electricity consumption exceeding a preset threshold during the peak electricity consumption period, select several user objects whose total electricity consumption reaches the extra electricity consumption, and mark them as first-level marketing objects. The first-level marketing objects also include a marketing expectation ratio, which is greater than one, and is used to offset the marketing failure rate.

[0035] In another preferred embodiment of the present invention, the marketing period and the peak electricity consumption period do not overlap in any time period, the marketing discount for the primary marketing target is higher than that for other marketing targets, and the specific association between the multiple marketing sub-periods and the user characteristic marketing scheme is as follows: When the marketing sub-period overlaps with the characteristic period and the marketing period, the user characteristic marketing plan is a guiding discount plan; When the marketing sub-period is adjacent to but does not overlap with the characteristic period, the user characteristic marketing plan is a promotional discount plan; When the marketing sub-period is far from the characteristic period, the user characteristic marketing plan is an inducement discount plan. The inducement discount plan, promotion discount plan and inducement discount plan are arranged sequentially and do not overlap on the time axis. The marketing discount of the inducement discount plan is higher than that of the inducement discount plan and the inducement discount plan in turn.

[0036] In another preferred embodiment of the present invention, a user correction module is also included, specifically comprising: The feature point selection unit is used to determine the user's electricity consumption start node corresponding to each electricity consumption record data when the feature time period corresponding to the user's feature behavior has no clear main distribution time period in multiple recording periods. The feature correction unit is used to determine the relative time interval of the feature behavior based on the electricity consumption start node in each of the electricity consumption record data, and to align multiple relative time intervals based on the electricity consumption start node to obtain the relative feature time period corresponding to the feature behavior.

[0037] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. 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 various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0038] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the disclosure in the specification and embodiments. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0039] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A multi-dimensional electricity marketing analysis method based on big data, characterized in that, Include: Electricity consumption data within several historical periods is acquired, and electricity consumption characteristics are analyzed on the electricity consumption data to obtain the user's electricity consumption behavior characteristics. The user behavior characteristics include characteristic behaviors and characteristic time periods, which are used to characterize electricity consumption behavior and its occurrence time intervals, respectively. Select a fixed number of adjacent recording periods, evaluate the total power usage records of the marketing dispatch area within multiple recording periods, and obtain the regional power consumption curve and the corresponding multiple peak power consumption periods; Based on the peak electricity consumption period, user behavior characteristics are retrieved and filtered to obtain several users to be marketed, and marketing periods are set on both sides of the peak electricity consumption period; Based on the misalignment between the characteristic time periods corresponding to the user behavior characteristics and the marketing time periods, the marketing time periods are split into multiple marketing sub-time periods, and corresponding user characteristic marketing plans are established. Each user characteristic marketing plan is associated with a user.

2. The multi-dimensional electricity marketing analysis method based on big data according to claim 1, characterized in that, The step of performing electricity consumption characteristic analysis on several electricity consumption record data to obtain the user's electricity consumption behavior characteristics specifically includes: The user's electricity consumption data within a recording period is continuously evaluated. Based on the power surge phenomenon of the appliance startup, the user's multiple characteristic behaviors based on the appliance's electricity consumption are judged, and the electricity consumption and duration of the characteristic behaviors are recorded. The characteristic behaviors in several electricity consumption records are statistically analyzed over time periods to obtain the characteristic time periods of the characteristic behaviors. The characteristic time periods are then marked based on the trigger probability statistics of the characteristic behaviors in several recording periods. The characteristic time periods also include the main distribution time periods and the occasional time periods.

3. The multi-dimensional electricity marketing analysis method based on big data according to claim 2, characterized in that, The step of retrieving and filtering user behavior characteristics based on the peak electricity consumption period to obtain several users to be marketed specifically includes: Based on the peak electricity consumption period, the characteristic time periods of several users in the marketing dispatch area are matched, and the marketing level of users is divided based on the inclusion ratio of the characteristic time periods during the peak electricity consumption period. The marketing level is highest at the middle ratio and decreases to both sides of the ratio value. Obtain the characteristic behaviors of several users corresponding to the characteristic time periods, and mark several users in the marketing level order list based on electricity consumption; The marketing order list is sorted based on the extra electricity consumption exceeding a preset threshold during the peak electricity consumption period. Several user objects whose total electricity consumption reaches the extra electricity consumption are selected and marked as first-level marketing objects. The first-level marketing objects also include a marketing expectation multiplier, which is greater than one and is used to offset the proportion of marketing failures.

4. The multi-dimensional electricity marketing analysis method based on big data according to claim 3, characterized in that, The marketing period and the peak electricity consumption period do not overlap in any way. The marketing discounts for the primary marketing target are higher than those for other marketing targets. The specific relationship between the multiple marketing sub-periods and the user characteristic marketing plan is as follows: When the marketing sub-period overlaps with the characteristic period and the marketing period, the user characteristic marketing plan is a guiding discount plan; When the marketing sub-period is adjacent to but does not overlap with the characteristic period, the user characteristic marketing plan is a promotional discount plan; When the marketing sub-period is far from the characteristic period, the user characteristic marketing plan is an inducement discount plan. The inducement discount plan, promotion discount plan and inducement discount plan are arranged sequentially and do not overlap on the time axis. The marketing discount of the inducement discount plan is higher than that of the inducement discount plan and the inducement discount plan in turn.

5. The multi-dimensional electricity marketing analysis method based on big data according to claim 2, characterized in that, It also includes user feature correction steps: When the characteristic time period corresponding to a user's characteristic behavior does not have a clear main distribution time period within multiple recording periods, the user's electricity consumption start node corresponding to each of the electricity consumption record data is determined. The characteristic behavior in each of the electricity consumption records is determined based on the relative time interval of the electricity consumption start node. Multiple relative time intervals are aligned based on the electricity consumption start node to obtain the relative characteristic time period corresponding to the characteristic behavior.

6. A multi-dimensional electricity marketing analysis system based on big data, characterized in that, Include: The feature statistics module is used to acquire electricity consumption record data within several historical period and perform electricity consumption feature analysis on the electricity consumption record data to obtain the user's electricity consumption behavior characteristics. The user behavior characteristics include characteristic behaviors and characteristic time periods, which are used to characterize electricity consumption behavior and its occurrence time interval, respectively. The peak assessment module is used to select a rated number of adjacent recording periods, assess the total power usage records of the marketing dispatch area within multiple recording periods, and obtain the regional power consumption curve and the corresponding multiple peak power consumption periods. The marketing matching module is used to retrieve and filter user behavior characteristics based on the peak electricity consumption period, obtain several users to be marketed, and set marketing periods on both sides of the peak electricity consumption period. The marketing execution module is used to split the marketing period into multiple marketing sub-periods based on the misalignment between the characteristic time period corresponding to the user behavior characteristics and the marketing period, and to establish user characteristic marketing plans accordingly. The user characteristic marketing plans are associated with users one by one.

7. A multi-dimensional electricity marketing analysis system based on big data as described in claim 6, characterized in that, The feature statistics module includes: The feature recognition unit is used to continuously evaluate the user's electricity consumption record data within a recording period, determine multiple characteristic behaviors of the user based on the power surge phenomenon of the appliance, and record the power consumption and duration of the characteristic behaviors. The feature statistics unit is used to perform time period statistics on the feature behavior in several electricity consumption record data, obtain the feature time period of the feature behavior, and mark the feature time period based on the trigger probability statistics of the feature behavior in several recording periods. The feature time period also includes the main distribution time period and the occasional time period.

8. The multi-dimensional electricity marketing analysis system based on big data according to claim 7, characterized in that, The marketing matching module includes: The marketing time period matching unit is used to match the characteristic time periods of several users in the marketing scheduling area according to the peak electricity consumption period, and to classify users into marketing levels based on the inclusion ratio of the characteristic time periods during the peak electricity consumption period. The marketing level is highest at the middle ratio and decreases to both sides of the ratio value. The marketing group matching unit is used to obtain the characteristic behaviors of several users corresponding to the characteristic time period, and to mark several users in the marketing level order list based on electricity consumption; The marketing group sorting unit is used to sort the marketing order list based on the extra electricity consumption exceeding a preset threshold during the peak electricity consumption period, select several user objects whose total electricity consumption reaches the extra electricity consumption, and mark them as first-level marketing objects. The first-level marketing objects also include a marketing expectation ratio, which is greater than one, and is used to offset the marketing failure rate.

9. A multi-dimensional electricity marketing analysis system based on big data as described in claim 8, characterized in that, The marketing period and the peak electricity consumption period do not overlap in any way. The marketing discounts for the primary marketing target are higher than those for other marketing targets. The specific relationship between the multiple marketing sub-periods and the user characteristic marketing plan is as follows: When the marketing sub-period overlaps with the characteristic period and the marketing period, the user characteristic marketing plan is a guiding discount plan; When the marketing sub-period is adjacent to but does not overlap with the characteristic period, the user characteristic marketing plan is a promotional discount plan; When the marketing sub-period is far from the characteristic period, the user characteristic marketing plan is an inducement discount plan. The inducement discount plan, promotion discount plan and inducement discount plan are arranged sequentially and do not overlap on the time axis. The marketing discount of the inducement discount plan is higher than that of the inducement discount plan and the inducement discount plan in turn.

10. A multi-dimensional electricity marketing analysis system based on big data according to claim 7, characterized in that, It also includes a user correction module, specifically including: The feature point selection unit is used to determine the user's electricity consumption start node corresponding to each electricity consumption record data when the feature time period corresponding to the user's feature behavior has no clear main distribution time period in multiple recording periods. The feature correction unit is used to determine the relative time interval of the feature behavior based on the electricity consumption start node in each of the electricity consumption record data, and to align multiple relative time intervals based on the electricity consumption start node to obtain the relative feature time period corresponding to the feature behavior.

Images