A power marketing channel user diversion method and system

Abstract

A method and system for attracting users to electricity marketing channels is disclosed. The method uses the analytic hierarchy process (AHP) to determine the weights of electricity consumption behavior data of users to be attracted and historical users. Based on the weighted sum of the electricity consumption behavior data of users to be attracted, first and second preferred user sets are defined. Based on the weighted sum of the electricity consumption behavior data of historical users, first and second sensitive user sets are defined. Using a weighted sum of the similarity and weights of each preferred user set and each sensitive user set, along with a similarity threshold, first target users are defined from the users to be attracted and historical users. The remaining users (excluding all first target users) are defined as second target users. Different user attraction measures are applied to the first and second target users. This invention improves the effectiveness and reliability of target user identification, matches the business growth needs of the electricity marketing end, and solves the problem of the overly simplistic methods used by the electricity marketing end to achieve business growth in existing technologies.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically, to a method and system for attracting users to power marketing channels. Background Technology

[0002] With the deepening of power system reform, the importance of customer acquisition capabilities in power marketing channels is becoming increasingly prominent. To achieve long-term business growth, it is necessary to conduct in-depth analysis of existing customers to increase business volume and to develop and maintain potential customers. User preferences are reflected in their daily electricity consumption behavior, such as complaints, payment records, and inquiries. How to extract potential engines for business expansion based on users' daily electricity consumption behavior data is a key technical challenge for power marketing.

[0003] Existing technology (CN 107087017 B) provides a method and apparatus for business lead generation. The method includes: for a target business, acquiring historical behavior data of users who use the target business; analyzing the historical behavior data to obtain user characteristics for defining target users for business lead generation; selecting users who meet the user characteristics from users who have not used the target business as target users; and sending business lead generation information to the target users to guide them to use the target business. However, the existing technology only analyzes the historical behavior data of existing customers to guide them to activate different services and achieve the effect of increasing business volume, but it does not have the ability to expand new customers. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method and system for attracting users to power marketing channels. Based on the analytic hierarchy process (AHP), the weights of the electricity consumption behavior data of users to be attracted and the electricity consumption behavior data of historical users are determined. By analyzing the correlation and weighted sum of the electricity consumption behavior data of historical users and users to be attracted, target users with different development potential and prospects are obtained. Different business attraction measures are formulated for different target users, which can improve the effectiveness and reliability of target user identification, further match the needs of power marketing for business growth, and solve the problem that the methods for achieving business growth in power marketing are too singular in existing technologies.

[0005] The present invention adopts the following technical solution.

[0006] This invention proposes a method for attracting users to power marketing channels, which determines the users to be attracted based on the geographical coordinates of the base station coverage area, including:

[0007] Based on the analytic hierarchy process, the weights of the electricity consumption behavior data of the users to be attracted and the electricity consumption behavior data of historical users are determined respectively.

[0008] The user groups are divided into a first preferred user set and a second preferred user set based on the relationship between the weighted sum of the electricity consumption behavior data and corresponding weights of the users to be attracted and the set potential threshold; the user groups are also divided into a first sensitive user set and a second sensitive user set based on the relationship between the weighted sum of the electricity consumption behavior data and corresponding weights of the historical electricity users and the set customer acquisition threshold.

[0009] The first part of the first target users is divided from the users to be attracted and historical electricity users by using the weighted sum of the similarity and corresponding weights of the first preferred user set and the first sensitive user set, and the relationship with the set similarity threshold. The second part of the first target users is divided from the users to be attracted by using the weighted sum of the similarity and corresponding weights of the second preferred user set and the first sensitive user set, and the relationship with the set similarity threshold. The third part of the first target users is divided from historical electricity users by using the weighted sum of the similarity and corresponding weights of the first preferred user set and the second sensitive user set, and the relationship with the set similarity threshold. The users to be attracted and historical electricity users remaining after removing all first target users are considered as second target users.

[0010] Different electricity marketing channels and user acquisition measures are used for the first target user and the second target user.

[0011] The method includes:

[0012] Step 1: Obtain the electricity consumption behavior data of the users to be attracted as the first behavior information, and obtain the electricity consumption behavior data of historical users as the second behavior information;

[0013] Step 2: Perform feature classification on the first behavioral information to obtain the comprehensive behavioral feature vector of the preferred user, and perform feature classification on the second behavioral information to obtain the comprehensive behavioral feature vector of the sensitive user; based on the analytic hierarchy process, obtain the weight of each indicator in the comprehensive behavioral feature vector of the preferred user and the weight of each indicator in the comprehensive behavioral feature vector of the sensitive user respectively.

[0014] The potential value of the users to be attracted is obtained by weighted summation using the first line of information and the corresponding weight; users whose potential value after normalization is greater than or equal to the set potential threshold are selected to construct the first preferred user set; users whose potential value after normalization is less than the set potential threshold are selected to construct the second preferred user set.

[0015] The customer acquisition energy value of historical electricity users is obtained by weighted summation using the second line information and the corresponding weight; the first sensitive user set is constructed by acquiring historical electricity users whose normalized customer acquisition energy value is greater than or equal to the set customer acquisition threshold; the second sensitive user set is constructed by acquiring users whose normalized customer acquisition energy value is less than the set customer acquisition threshold.

[0016] Step 3: Calculate the similarity of each indicator in the first preferred user set and the first sensitive user set respectively. After weighting the similarity with the corresponding weights, obtain the first similarity. The users to be attracted and the historical electricity users whose first similarity is greater than the set similarity threshold are regarded as the first part of the first target users.

[0017] The similarity of each indicator in the second preferred user set and the first sensitive user set is calculated respectively. The similarity is weighted by the corresponding weights to obtain the second similarity. The users to be attracted in the second preferred user set whose second similarity is greater than the set similarity threshold are taken as the second part of the first target users.

[0018] The similarity of each indicator in the first preferred user set and the second sensitive user set is calculated respectively. The similarity is weighted by the corresponding weights to obtain the third similarity. The historical electricity users included in the second sensitive user set whose third similarity is greater than the set similarity threshold are taken as the third part of the first target users.

[0019] The remaining users after removing all primary target users and historical electricity users are considered as secondary target users.

[0020] Step 4: Use the first type of electricity marketing channel user acquisition measures for the first target user, and use the second type of electricity marketing channel user acquisition measures for the second target user.

[0021] Preferably, the electricity consumption behavior data includes, but is not limited to: frequency of inquiries, package type, payment records, number of complaints, current operator type, and inquiry operator type.

[0022] Preferably, in step 2, the feature classification method is used to determine the preferred user comprehensive behavior feature vector as A = [fre-a, type-a, pay-a, apl-a, ope-a, Cope-a], and the sensitive user comprehensive behavior feature vector as B = [fre-b, type-b, pay-b, apl-b, ope-b, Cope-b];

[0023] Among them, fre-a, type-a, pay-a, apl-a, ope-a, and Cope-a are indicators in the comprehensive behavioral feature vector of preferred users, which correspond to the frequency of consultation services, package type, payment records, number of complaints, current operator type, and consultation operator type of the user to be attracted;

[0024] fre-b, type-b, pay-b, apl-b, ope-b, and Cope-b are indicators in the comprehensive behavioral feature vector of sensitive users, corresponding to the frequency of historical electricity users' consultation services, package type, payment records, number of complaints, current operator type, and consultation operator type, respectively.

[0025] Preferably, the set potential threshold value ranges from greater than or equal to 0.75 to less than or equal to 1.

[0026] Preferably, the set customer acquisition threshold is set to a value range of greater than or equal to 0.75 and less than or equal to 1.

[0027] Preferably, the set similarity threshold is 0.8.

[0028] Preferably, when the first target user is a user to be attracted, a voice-activated inquiry method is used to recommend recharge and value-added services; when the first target user is a user with historical electricity consumption, a voice-activated inquiry method is used to recommend a service that rewards points for changing packages.

[0029] Preferably, when the second target user is a user to be attracted, the recharge and value-added services are recommended via SMS; when the second target user is a user with historical electricity consumption, the service of changing the package and receiving points is recommended via SMS.

[0030] This invention proposes a user acquisition system for power marketing channels, comprising: a weight calculation module, a user set segmentation module, a target user segmentation module, and an acquisition implementation module;

[0031] The weight calculation module is used to determine the weights of the electricity consumption behavior data of the users to be attracted and the electricity consumption behavior data of historical users based on the analytic hierarchy process.

[0032] The user set segmentation module is used to segment a first preferred user set and a second preferred user set based on the relationship between the weighted sum of the electricity consumption behavior data and corresponding weights of the users to be attracted and a set potential threshold; and to segment a first sensitive user set and a second sensitive user set based on the relationship between the weighted sum of the electricity consumption behavior data and corresponding weights of historical electricity users and a set customer acquisition threshold.

[0033] The target user segmentation module is used to segment a first part of the first target users from the users to be attracted and historical electricity users by using the weighted sum of the similarity and corresponding weights of the first preferred user set and the first sensitive user set and the set of similarity, and the set of similarity, to divide the first target users from the users to be attracted; to segment a second part of the first target users from the users to be attracted by using the weighted sum of the similarity and corresponding weights of the second preferred user set and the first sensitive user set and the set of similarity, and the set of similarity, to divide the first target users from the historical electricity users; and to segment the users to be attracted and historical electricity users after removing all the first target users are considered as the second target users.

[0034] The lead generation implementation module is used to employ different lead generation measures for the first target user and the second target user through different electricity marketing channels.

[0035] The beneficial effect of this invention is that, compared with the prior art, developing different business lead generation measures for different target users can effectively improve customer acquisition efficiency, thereby matching the needs of the power marketing end for business growth.

[0036] By conducting correlation analysis on the electricity consumption behavior data of historical electricity users and users to be attracted, we can identify target users with different development potential and prospects. By developing different business attraction measures for different target users, we can improve the effectiveness and reliability of target user identification and further match the needs of the electricity marketing end for business growth. Attached Figure Description

[0037] Figure 1 This is a flowchart of a user acquisition method for electricity marketing channels according to the present invention. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of this invention. The embodiments described in this application are merely some embodiments of this invention, and not all embodiments. Based on the spirit of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of this invention.

[0039] This invention proposes a method for attracting users to power marketing channels, which determines the users to be attracted based on the geographical coordinates of the base station coverage area, including:

[0040] Based on the analytic hierarchy process, the weights of the electricity consumption behavior data of the users to be attracted and the electricity consumption behavior data of historical users are determined respectively.

[0041] The user groups are divided into a first preferred user set and a second preferred user set based on the relationship between the weighted sum of the electricity consumption behavior data and corresponding weights of the users to be attracted and the set potential threshold; the user groups are also divided into a first sensitive user set and a second sensitive user set based on the relationship between the weighted sum of the electricity consumption behavior data and corresponding weights of the historical electricity users and the set customer acquisition threshold.

[0042] The first part of the first target users is divided from the users to be attracted and historical electricity users by using the weighted sum of the similarity and corresponding weights of the first preferred user set and the first sensitive user set, and the relationship with the set similarity threshold. The second part of the first target users is divided from the users to be attracted by using the weighted sum of the similarity and corresponding weights of the second preferred user set and the first sensitive user set, and the relationship with the set similarity threshold. The third part of the first target users is divided from historical electricity users by using the weighted sum of the similarity and corresponding weights of the first preferred user set and the second sensitive user set, and the relationship with the set similarity threshold. The users to be attracted and historical electricity users remaining after removing all first target users are considered as second target users.

[0043] Different electricity marketing channels and user acquisition measures are used for the first target user and the second target user.

[0044] Specifically, such as Figure 1 As shown, the method includes:

[0045] Step 1: Obtain the electricity consumption behavior data of the users to be attracted as the first behavior information, and obtain the electricity consumption behavior data of historical users as the second behavior information.

[0046] Specifically, the scope of users to be attracted is planned based on the geographical coordinates of the base station coverage area. By conducting correlation analysis on the electricity consumption behavior data of historical electricity users and users to be attracted, target users with different development potential and prospects are obtained. Different business attraction measures are formulated for different target users, which can improve the effectiveness and reliability of target user identification and further match the needs of the power marketing end for business growth.

[0047] Specifically, electricity usage behavior data includes, but is not limited to: consultation frequency (fre), package type (type), payment record (pay), number of complaints (apl), current operator type (ope), and consultation operator type (Cope).

[0048] Specifically, the frequency of inquiries includes the number of inquiries made by users to be acquired through various channels (online or offline) within a unit of time (such as quarterly or annually). Inquiries include, but are not limited to, consultation package fees, consultation data quality consultation value-added services, etc. Package types include, but are not limited to, monthly packages, quarterly packages, annual packages, or time-domain packages, etc. Payment records include arrears, prepaid fees, or fees paid on behalf of others, etc. The number of complaints is the number of complaint records within a unit of time. The current operator type is determined based on the frequency band of the communication base station. The consultation operator type is operators other than the user's own operator and their related tariff services. All the indicator data contained in the first row of information can reflect the activity level and potential development qualifications of the users to be acquired.

[0049] Step 2: Perform feature classification on the first behavioral information to obtain the comprehensive behavioral feature vector of the preferred user, and perform feature classification on the second behavioral information to obtain the comprehensive behavioral feature vector of the sensitive user; based on the analytic hierarchy process, obtain the weight of each indicator in the comprehensive behavioral feature vector of the preferred user and the weight of each indicator in the comprehensive behavioral feature vector of the sensitive user respectively.

[0050] The potential value of the users to be attracted is obtained by weighted summation using the first line of information and the corresponding weight; users whose potential value after normalization is greater than or equal to the set potential threshold are selected to construct the first preferred user set; users whose potential value after normalization is less than the set potential threshold are selected to construct the second preferred user set.

[0051] The customer acquisition energy value of historical electricity users is obtained by weighted summation using the second line information and the corresponding weight; the first sensitive user set is constructed by acquiring historical electricity users whose normalized customer acquisition energy value is greater than or equal to the set customer acquisition threshold; and the second sensitive user set is constructed by acquiring users whose normalized customer acquisition energy value is less than the set customer acquisition threshold.

[0052] Specifically, step 2 includes:

[0053] Step 2.1: Using the feature classification method, the comprehensive behavioral feature vector of preferred users is determined as A = [fre-a, type-a, pay-a, apl-a, ope-a, Cope-a], and the comprehensive behavioral feature vector of sensitive users is determined as B = [fre-b, type-b, pay-b, apl-b, ope-b, Cope-b]; where fre-a, type-a, pay-a, apl-a, ope-a, and Cope-a are the indicators in the comprehensive behavioral feature vector of preferred users A, corresponding to the electricity consumption behavior data of the users to be attracted; fre-b, type-b, pay-b, apl-b, ope-b, and Cope-b are the indicators in the comprehensive behavioral feature vector of sensitive users B, corresponding to the electricity consumption behavior data of historical electricity users.

[0054] Step 2.2: Based on the analytic hierarchy process (AHP), obtain the weights of each indicator in the comprehensive behavioral feature vector A of the preferred user, and empower each indicator of the first behavioral information in turn; based on the AHP, obtain the weights of each indicator in the comprehensive behavioral feature vector B of the sensitive user, and empower each indicator of the second behavioral information in turn.

[0055] Specifically, the Analytic Hierarchy Process (AHP) decomposes the decision problem into different hierarchical structures according to the overall goal, sub-goals at each level, evaluation criteria, and finally specific alternative solutions. Then, by solving the eigenvectors of the judgment matrix, the priority weight of each element at each level relative to a certain element at the previous level is obtained. Finally, a weighted sum method is used to hierarchically merge the final weights of each alternative solution relative to the overall goal. The solution with the largest final weight is the optimal solution. In the implementation example, on the one hand, the frequency of consultation services and the type of operator consulted indicate that potential customers have a tendency to switch operators, indicating development potential. Additionally, payment records and the number of complaints can be used as criteria for judging the quality of potential customers. On the other hand, the frequency of consultation services, the type of service plan, and the type of operator consulted indicate that historical electricity users have a tendency to switch operators, indicating development potential. Additionally, payment records and the number of complaints can be used as criteria for judging the quality of historical electricity users.

[0056] Step 2.3: Use the first line of information and the corresponding weight to perform a weighted summation to obtain the potential value of the users to be attracted; obtain the users to be attracted whose normalized potential value is greater than or equal to the set potential threshold, and construct the first preferred user set; obtain the users to be attracted whose normalized potential value is less than the set potential threshold, and construct the second preferred user set.

[0057] The potential threshold is set to a value range of greater than or equal to 0.75 and less than or equal to 1.

[0058] The customer acquisition energy value of historical electricity users is obtained by weighted summation using the second line information and the corresponding weight; the first sensitive user set is constructed by acquiring historical electricity users whose normalized customer acquisition energy value is greater than or equal to the set customer acquisition threshold; and the second sensitive user set is constructed by acquiring users whose normalized customer acquisition energy value is less than the set customer acquisition threshold.

[0059] The customer acquisition threshold ranges from 0.75 to 1.

[0060] Step 3: Calculate the similarity of each indicator in the first preferred user set and the first sensitive user set respectively. After weighting the similarity with the corresponding weights, obtain the first similarity. The users to be attracted and the historical electricity users whose first similarity is greater than the set similarity threshold are regarded as the first part of the first target users.

[0061] The similarity of each indicator in the second preferred user set and the first sensitive user set is calculated respectively. The similarity is weighted by the corresponding weights to obtain the second similarity. The users to be attracted in the second preferred user set whose second similarity is greater than the set similarity threshold are taken as the second part of the first target users.

[0062] The similarity of each indicator in the first preferred user set and the second sensitive user set is calculated respectively. The similarity is weighted by the corresponding weights to obtain the third similarity. The historical electricity users included in the second sensitive user set whose third similarity is greater than the set similarity threshold are taken as the third part of the first target users.

[0063] Users to be attracted and historical electricity users, excluding the first target users, are considered as the second target users.

[0064] In a non-limiting preferred embodiment, the weight values ​​of each indicator are obtained through the analytic hierarchy process (AHP). Based on the weight values, the first similarity, second similarity, and third similarity can be calculated by weighting. The similarity is compared with a set similarity threshold, which can be manually set based on the intensity of business development. The similarity threshold is set to 0.8, which avoids the inaccuracy caused by single-factor evaluation and makes the identification of target users more accurate and reliable.

[0065] Step 4: When the first target user is a user to be acquired, use voice prompts to recommend recharge and value-added services; when the first target user is a user with historical electricity consumption, use voice prompts to recommend a service that rewards points for changing plans.

[0066] When the second target user is a user to be acquired, recommend recharge and value-added services via SMS; when the second target user is a user with a history of electricity consumption, recommend the service of changing plans and receiving points via SMS.

[0067] Specifically, after the base station server detects that a user has entered the service coverage area, it determines the target user type and adopts corresponding traffic diversion measures to serve the first target user and the second target user; if it is the first target user, the first response strategy is adopted; if it is the second target user, the second response strategy is adopted.

[0068] The method proposed in this invention can effectively improve customer acquisition efficiency by developing different business lead generation measures for different target users, thereby matching the needs of the power marketing end for business growth.

[0069] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0070] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0071] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0072] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A method for attracting users to an electricity marketing channel, characterized in that: include: Based on the analytic hierarchy process, the weights of the electricity consumption behavior data of the users to be attracted and the electricity consumption behavior data of historical users are determined respectively. The user groups are divided into a first preferred user set and a second preferred user set based on the relationship between the weighted sum of the electricity consumption behavior data and corresponding weights of the users to be attracted and the set potential threshold; the user groups are also divided into a first sensitive user set and a second sensitive user set based on the relationship between the weighted sum of the electricity consumption behavior data and corresponding weights of the historical electricity users and the set customer acquisition threshold. The first part of the first target users is divided from the users to be attracted and the historical electricity users by using the weighted sum of the similarity and corresponding weights of the first preferred user set and the first sensitive user set and the set similarity threshold. The second part of the first target users is divided from the users to be attracted by using the weighted sum of the similarity and corresponding weights of the second preferred user set and the first sensitive user set and the set of similarity thresholds; the third part of the first target users is divided from the historical electricity users by using the weighted sum of the similarity and corresponding weights of the first preferred user set and the second sensitive user set and the set of similarity thresholds. The remaining users after removing all primary target users and historical electricity users are considered as secondary target users. Different electricity marketing channels and user acquisition measures are used for the first target user and the second target user.

2. The method for attracting users to power marketing channels according to claim 1, characterized in that, Step 1: Obtain the electricity consumption behavior data of the users to be attracted as the first behavior information, and obtain the electricity consumption behavior data of historical users as the second behavior information; Step 2: Perform feature classification on the first behavioral information to obtain the comprehensive behavioral feature vector of the preferred user, and perform feature classification on the second behavioral information to obtain the comprehensive behavioral feature vector of the sensitive user; based on the analytic hierarchy process, obtain the weight of each indicator in the comprehensive behavioral feature vector of the preferred user and the weight of each indicator in the comprehensive behavioral feature vector of the sensitive user respectively. The potential value of the users to be attracted is obtained by weighted summation using the first line of information and the corresponding weight; users whose potential value after normalization is greater than or equal to the set potential threshold are selected to construct the first preferred user set; users whose potential value after normalization is less than the set potential threshold are selected to construct the second preferred user set. The customer acquisition energy value of historical electricity users is obtained by weighted summation using the second line information and the corresponding weight; the first sensitive user set is constructed by acquiring historical electricity users whose normalized customer acquisition energy value is greater than or equal to the set customer acquisition threshold; the second sensitive user set is constructed by acquiring users whose normalized customer acquisition energy value is less than the set customer acquisition threshold. Step 3: Calculate the similarity of each indicator in the first preferred user set and the first sensitive user set respectively. After weighting the similarity with the corresponding weights, obtain the first similarity. The users to be attracted and the historical electricity users whose first similarity is greater than the set similarity threshold are regarded as the first part of the first target users. The similarity of each indicator in the second preferred user set and the first sensitive user set is calculated respectively. The similarity is weighted by the corresponding weights to obtain the second similarity. The users to be attracted in the second preferred user set whose second similarity is greater than the set similarity threshold are taken as the second part of the first target users. The similarity of each indicator in the first preferred user set and the second sensitive user set is calculated respectively. The similarity is weighted by the corresponding weights to obtain the third similarity. The historical electricity users included in the second sensitive user set whose third similarity is greater than the set similarity threshold are taken as the third part of the first target users. The remaining users after removing all primary target users and historical electricity users are considered as secondary target users. Step 4: Use the first type of electricity marketing channel user acquisition measures for the first target user, and use the second type of electricity marketing channel user acquisition measures for the second target user.

3. The method for attracting users to power marketing channels according to claim 2, characterized in that, Electricity usage behavior data includes, but is not limited to: frequency of inquiries, package type, payment records, number of complaints, current operator type, and operator type of inquiries.

4. The method for attracting users to power marketing channels according to claim 3, characterized in that, In step 2, the feature classification method is used to determine the preferred user comprehensive behavior feature vector as A = [fre-a, type-a, pay-a, apl-a, ope-a, Cope-a], and the sensitive user comprehensive behavior feature vector as B = [fre-b, type-b, pay-b, apl-b, ope-b, Cope-b]. Among them, fre-a, type-a, pay-a, apl-a, ope-a, and Cope-a are indicators in the comprehensive behavioral feature vector of preferred users, which correspond to the frequency of consultation services, package type, payment records, number of complaints, current operator type, and consultation operator type of the user to be attracted; fre-b, type-b, pay-b, apl-b, ope-b, and Cope-b are indicators in the comprehensive behavioral feature vector of sensitive users, corresponding to the frequency of historical electricity users' consultation services, package type, payment records, number of complaints, current operator type, and consultation operator type, respectively.

5. The method for attracting users to power marketing channels according to claim 2, characterized in that, The set potential threshold value ranges from greater than or equal to 0.75 to less than or equal to 1.

6. The method for attracting users to power marketing channels according to claim 2, characterized in that, The set customer acquisition threshold ranges from 0.75 to 1.

7. The method for attracting users to power marketing channels according to claim 2, characterized in that, The set similarity threshold is 0.

8.

8. The method for attracting users to power marketing channels according to claim 2, characterized in that, When the primary target user is a user to be acquired, proactive voice inquiry is used to recommend recharge and value-added services; when the primary target user is a user with historical electricity consumption, proactive voice inquiry is used to recommend services such as changing plans to earn points.

9. The method for attracting users to power marketing channels according to claim 2, characterized in that, When the second target user is a user to be acquired, recommend recharge and value-added services via SMS; when the second target user is a user with a history of electricity consumption, recommend the service of changing plans and receiving points via SMS.

10. A user lead generation system for electricity marketing channels, used to implement the method described in any one of claims 1 to 9, characterized in that, The system includes: a weight calculation module, a user set segmentation module, a target user segmentation module, and a traffic acquisition implementation module; The weight calculation module is used to determine the weights of the electricity consumption behavior data of the users to be attracted and the electricity consumption behavior data of historical users based on the analytic hierarchy process. The user set segmentation module is used to segment a first preferred user set and a second preferred user set based on the relationship between the weighted sum of the electricity consumption behavior data and corresponding weights of the users to be attracted and a set potential threshold; and to segment a first sensitive user set and a second sensitive user set based on the relationship between the weighted sum of the electricity consumption behavior data and corresponding weights of historical electricity users and a set customer acquisition threshold. The target user segmentation module is used to segment a first part of the first target users from the users to be attracted and historical electricity users by using the weighted sum of the similarity and corresponding weights of the first preferred user set and the first sensitive user set and the set of similarity, and the set of similarity, to divide the first target users from the users to be attracted; to segment a second part of the first target users from the users to be attracted by using the weighted sum of the similarity and corresponding weights of the second preferred user set and the first sensitive user set and the set of similarity, and the set of similarity, to divide the first target users from the historical electricity users; and to segment the users to be attracted and historical electricity users after removing all the first target users are considered as the second target users. The lead generation implementation module is used to employ different lead generation measures for the first target user and the second target user through different electricity marketing channels.

Images