Method and device for accurately identifying potential complaint user
By obtaining and analyzing the B-domain characteristics of complaining users, identifying and handling potential complaining users and network pain points, the problem of inaccurate identification of potential complaining users in the existing technology has been solved, and user satisfaction and corporate reputation have been improved.
Patent Information
- Application Number
- CN202411061049.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-26
AI Technical Summary
The existing technology is difficult to accurately identify potential complaint users and network pain points, resulting in the inability to effectively reduce user complaints, affecting user satisfaction and corporate reputation.
By obtaining the B-domain features of the complaining user, setting up training templates and feature recognition models for potential complaining users, identifying users who are prone to complaining, and prioritizing potential complaining users and network pain points based on community CGI statistics.
It has achieved accurate identification of potential complaint users and network pain points, improved user satisfaction and corporate reputation, and optimized network resource allocation and problem handling.
Smart Images

Figure CN119027190A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of communication technology, and specifically provides a method and device for accurately identifying potential complaining users. Background Art
[0002] Corporate reputation is closely related to user satisfaction. User complaints are the benchmark for measuring user satisfaction. Discovering potential complaining users and the network pain points of complaining users in advance is a key strategy to reduce user complaints and improve user satisfaction.
[0003] Since the network is large and complex, existing monitoring methods cannot cover every user, and there is a lack of accurate means of identifying potential users and potential pain points. How to accurately identify potential complaining users and network pain point communities is an urgent problem to be solved by technical personnel in this field. Summary of the invention
[0004] The present invention aims to address the deficiencies of the above-mentioned prior art and provides a method for accurately identifying potential complaining users with strong practicality.
[0005] A further technical task of the present invention is to provide a device that is reasonably designed, safe and applicable and can accurately identify potential complaining users.
[0006] The technical solution adopted by the present invention to solve its technical problem is:
[0007] A method for accurately identifying potential complaining users has the following steps:
[0008] S1, domain feature acquisition of complaining user B;
[0009] S2, setting of training template for potential complaint user B domain;
[0010] S3, potential complaint user B domain feature recognition model;
[0011] S4, identification of users prone to complaints;
[0012] S5. Accurate identification of potential complaining users and network pain points;
[0013] S6. Handle the problem of poor quality in the residential area where potential users complain based on priority.
[0014] Furthermore, in step S1, wireless complaint users are identified based on online company complaint user data, and B-domain features of the complaining users are generated by associating the user numbers with the B-domain feature data pushed by the DACP big data platform.
[0015] Furthermore, in step S2, different feature training intervals are set according to the domain features of user B, evaluation dimensions are configured, and the user sets different recognition models.
[0016] Furthermore, when setting different feature training areas, the features include labels, label features and whether label features are enabled, and the labels include age, star rating, network age, number of secondary cards, whether the customer is a secondary card customer, number of failed network hall services, download traffic, upload traffic, maximum network support for the terminal, terminal brand, total payment amount, data service fee, voice service fee, SMS service fee, package usage, number of package changes, number of promotional activities participated in, monthly total traffic, out-of-package traffic fee, number of days per month using traffic, 2G DOU, 4G DOU, 4G network duration, monthly total call billing duration, number of local calls, video call duration, number of times the network hall inquires about the balance of phone bills, number of times the network hall inquires about the traffic, and number of single stops.
[0017] Furthermore, in step S3, based on the B-domain features associated with the complaining users, feature intervals where the complaint proportion of each B-domain feature of the complained users is greater than 30% are calculated, and each interval is interactively combined to form a B-domain feature recognition model for potential complaining users.
[0018] Furthermore, in step S4, based on the B-domain data of users in the entire network, the data is matched with the B-domain feature recognition model of potential complaining users to identify qualified users who are prone to complaints.
[0019] Further, in step S5, based on the association with the users prone to complaints, the cells where the users with domain B characteristics reside are identified, and according to the cell CGI statistics, the cells with many users prone to complaints are marked with a priority of 1 and filled in descending order;
[0020] Based on the community CGI, we further screen out communities with poor quality. These communities and the associated users prone to complaints are accurate potential complaint users and network pain points.
[0021] A device for accurately identifying potential complaining users, comprising: at least one memory and at least one processor;
[0022] The at least one memory is used to store a machine-readable program;
[0023] The at least one processor is used to call the machine-readable program to execute a method for accurately identifying potential complaining users.
[0024] Compared with the prior art, the method and device for accurately identifying potential complaining users of the present invention have the following outstanding beneficial effects:
[0025] The present invention can accurately identify potential complaining users and network pain points, so as to accurately deliver network resources, handle network problems, prevent complaints, and improve user satisfaction and corporate reputation. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0027] Attached Figure 1 It is a flowchart of a method for accurately identifying potential complaining users. DETAILED DESCRIPTION
[0028] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention is further described in detail below in conjunction with specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0029] A best embodiment is given below:
[0030] like Figure 1 As shown, a method for accurately identifying potential complaining users in this embodiment has the following steps:
[0031] S1, domain feature acquisition of complaining user B;
[0032] Based on the online company complaint user data, wireless complaint users are identified, and the B-domain characteristics of the complaining users are generated by associating the user numbers with the B-domain characteristic data pushed by the DACP big data platform.
[0033] S2, setting of training template for potential complaint user B domain;
[0034] According to the characteristics of user B domain, different feature training intervals are set, supporting flexible configuration of evaluation dimensions, and users setting different recognition models;
[0035] When setting different feature training areas, the features include labels, label features, and whether to enable label features, as follows:
[0036]
[0037]
[0038]
[0039]
[0040]
[0041]
[0042]
[0043]
[0044]
[0045]
[0046]
[0047] S3, potential complaint user B domain feature recognition model;
[0048] According to the B-domain features associated with the complaining users, the feature intervals where the complaint proportion of each B-domain feature of the complained users is greater than 30% are calculated, and the B-domain feature identification model of potential complaining users is formed by interactive combination of each interval.
[0049] S4, identification of users prone to complaints;
[0050] Based on the B-domain data of users across the entire network, it is matched with the B-domain feature recognition model of potential complaining users to identify eligible users who are prone to complaints.
[0051] S5. Accurate identification of potential complaining users and network pain points;
[0052] Based on the association of users prone to complaints, identify the communities where these users with domain B characteristics reside. According to the CGI statistics of the communities, communities with many users prone to complaints are marked with a priority of 1 and filled in descending order.
[0053] Based on the community CGI, we further screen out communities with poor quality. These communities and the associated users prone to complaints are accurate potential complaint users and network pain points.
[0054] S6. Handle the problem of poor quality in the residential area where potential users complain based on priority.
[0055] Based on the above method, a device for accurately identifying potential complaining users in this embodiment includes: at least one memory and at least one processor;
[0056] The at least one memory is used to store a machine-readable program;
[0057] The at least one processor is used to call the machine-readable program to execute a method for accurately identifying potential complaining users.
[0058] The above-mentioned specific implementations are only specific cases of the present invention. The patent protection scope of the present invention includes but is not limited to the above-mentioned specific implementations. Any technical solutions that comply with the claims of the present invention and any appropriate changes or substitutions made by ordinary technicians in the relevant technical field shall fall within the patent protection scope of the present invention.
[0059] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A method for accurately identifying potential complaining users. It is characterized in that The steps are as follows: S1, domain feature acquisition of complaining user B; S2, setting of training template for potential complaint user B domain; S3, potential complaint user B domain feature recognition model; S4, identification of users prone to complaints; S5. Accurate identification of potential complaining users and network pain points; S6. Handle the problem of poor quality in the residential area where potential users complain based on priority.
2. According to the method of claim 1, It is characterized in that In step S1, wireless complaint users are identified based on online company complaint user data, and the B-domain characteristics of the complaining users are generated by associating the user numbers with the B-domain characteristic data pushed by the DACP big data platform.
3. According to the method for accurately identifying potential complaining users according to claim 2, It is characterized in that In step S2, according to the domain characteristics of user B, different feature training intervals are set, evaluation dimensions are configured, and the user sets different recognition models.
4. According to claim 3, a method for accurately identifying potential complaining users, It is characterized in that When setting different feature training areas, the features include labels, label features and whether to enable label features. The labels include age, star rating, network age, number of secondary cards, whether a secondary card customer, number of failed online business processing, download traffic, upload traffic, maximum network support for the terminal, terminal brand, total payment amount, data service fee, voice service fee, SMS service fee, package usage, number of package changes, number of promotional activities participated in, monthly total traffic, out-of-package traffic fee, number of days per month using traffic, 2G DOU, 4GDOU, 4G network duration, monthly total call billing duration, number of local calls, video call duration, number of times the online hall inquires about the balance of phone bills, number of times the online hall inquires about the traffic, and number of single stops.
5. According to the method for accurately identifying potential complaining users according to claim 4, It is characterized in that In step S3, based on the B-domain features associated with the complaining users, feature intervals where the complaint proportion of each B-domain feature of the complained users is greater than 30% are calculated, and each interval is interactively combined to form a B-domain feature recognition model for potential complaining users.
6. According to claim 5, a method for accurately identifying potential complaining users, It is characterized in that In step S4, based on the B-domain data of users in the entire network, it is matched with the B-domain feature recognition model of potential complaining users to identify qualified users who are prone to complaints.
7. According to claim 5, a method for accurately identifying potential complaining users, It is characterized in that In step S5, based on the association with users prone to complaints, the B-domain characteristics of these users are identified as resident cells, and according to the cell CGI statistics, cells with many users prone to complaints are marked with a priority of 1 and filled in descending order; Based on the community CGI, we further screen out communities with poor quality. These communities and the associated users prone to complaints are accurate potential complaint users and network pain points.
8. A device for accurately identifying potential complaining users, It is characterized in that include: at least one memory and at least one processor; The at least one memory is used to store a machine-readable program; The at least one processor is configured to call the machine-readable program to execute the method according to any one of claims 1 to 7.
