Network complaint processing method, system and medium

Abstract

The present disclosure provides a network complaint processing method, system and medium, relating to the technical field of network, the method comprises: determining the first complaint customer needing to carry out face measurement according to the customer complaint, and obtaining the complaint content, face measurement time and face measurement address of the first complaint customer; sending the complaint content, face measurement time and face measurement address of the first complaint customer to the face measurement unmanned aerial vehicle control system, so that the face measurement unmanned aerial vehicle control system formulates a face measurement task of testing network signal quality according to the complaint content, and calls the unmanned aerial vehicle to fly to the face measurement address to execute the face measurement task at the face measurement time, so as to obtain the face measurement data of the first complaint customer; receiving the face measurement data from the face measurement unmanned aerial vehicle control system, and generating a complaint processing scheme of the first complaint customer according to the face measurement data. The present disclosure realizes the effects of reasonably arranging face measurement, effectively obtaining face measurement data and scientifically formulating a complaint processing scheme.

Description

Online complaint handling methods, systems and media Technical Field

[0001] This disclosure relates at least to the field of network technology, and in particular to a network complaint handling method, a customer complaint handling system, a surface-testing drone control system, a network complaint handling system, and a computer-readable storage medium. Background Technology

[0002] With the further development of 5G (5th Generation Mobile Communication Technology), operators face increasing challenges in network maintenance. In particular, each mobile network customer has unique usage scenarios, and occasional network outages, insufficient coverage, or malfunctions such as lag and latency can all trigger mobile network failures. Due to the large customer base, these failures generate numerous complaints. Operators find it difficult to monitor network status in real-time and prevent and predict network failures. They also cannot monitor the network for each customer's specific usage scenario. For example, network fluctuations may occur at different times of the day, and mobile network signal strength may vary in different rooms within a suite. When there are numerous customer complaints, operators cannot arrange for personnel to conduct on-site testing (visiting each complaining customer's address to test network signal quality) or ascertain the actual network situation for each customer. Therefore, a low-cost method for monitoring customer network conditions is needed. Summary of the Invention

[0003] The technical problem to be solved by this disclosure is to address the above-mentioned shortcomings by providing a method for handling online complaints, a customer complaint handling system, a face-to-face testing drone control system, an online complaint handling framework, and a computer-readable storage medium, so as to solve the problem of how to schedule face-to-face testing based on online customer complaints.

[0004] In a first aspect, this disclosure provides a method for handling online complaints, the method being applied to a customer complaint handling system, and comprising:

[0005] Based on customer complaints, identify the first customer who needs to conduct an in-person interview, and obtain the content of the first customer's complaint, the interview time, and the interview address;

[0006] The complaint content, face-to-face test time, and face-to-face test address of the first complaining customer are sent to the face-to-face test drone control system. The face-to-face test drone control system then formulates a face-to-face test task to test the network signal quality based on the complaint content and calls the drone to fly to the face-to-face test address at the face-to-face test time to perform the face-to-face test task in order to obtain the face-to-face test data of the first complaining customer.

[0007] Receives surface testing data from the surface testing drone control system and generates a complaint handling plan for the first complainant based on the surface testing data.

[0008] Furthermore, based on customer complaints, the first complainant requiring an in-person interview is identified, specifically including:

[0009] Based on customer complaints, we obtain the characteristic parameters of the complaining customers, including the number of complaints at the customer address, the interval between the customer address's historical face-to-face interviews and the current complaint at the customer address, customer value, and customer demands.

[0010] Clustering algorithms are used to classify complaining customers based on their characteristic parameters, in order to identify the first complaining customer who has a high number of complaints at their address, a large interval between the historical face-to-face interviews at their address and the current complaint, high customer value, and whose complaint includes information requiring a face-to-face interview.

[0011] Furthermore, based on customer complaints, characteristic parameters of complaining customers are obtained. These parameters include the number of complaints made at the customer's address, the interval between historical face-to-face interviews at the customer's address and the current complaint, customer value, and customer demands. Specifically, these include:

[0012] Upon receiving a customer complaint, the system obtains the content of the complaint and collects customer complaint information, including the customer's seven-level address, personal information, and complaint request.

[0013] Obtain the fifth-level address corresponding to the seventh-level address of the complaining customer, and obtain the number of complaints without face-to-face testing for the same complaint type as the content of this complaint at the fifth-level address, and use this as the number of complaints at the customer address;

[0014] Obtain the most recent face-to-face interview time for historical customer complaints of the same type as the current complaint at the fifth-level address, and calculate the interval between the most recent historical face-to-face interview time and the current complaint time, as the interval between the historical face-to-face interview at the customer address and the current complaint at the customer address;

[0015] Based on the personal information of complaining customers, we obtain the customer value of complaining customers, including the complaining customer's average monthly contribution ARUP value, customer star rating, and customer's membership duration;

[0016] Analyze the complaints of customers to determine whether they require material compensation or a complete solution to the network problem. If the customer's request is to completely solve the network problem, it includes information that requires face-to-face interview.

[0017] The number of complaints at a customer's address, the interval between the historical face-to-face measurement of the customer's address and the current complaint at the customer's address, customer value, and customer demands are quantified, weighted, and normalized to obtain characteristic parameters of the complaining customer.

[0018] Furthermore, obtain the content of the first complaint from the customer, the interview time and address, specifically including:

[0019] Based on the content of the first complaint, the number of complaints at the customer's address, and / or the face-to-face interviews with historical customers whose complaints of the same type as the current complaint are from the fifth-level address, determine whether the face-to-face interview address is a seventh-level address or a fifth-level address.

[0020] If the face-to-face test address is a level 7 address, an appointment time for the face-to-face test will be agreed upon with the first complainant; otherwise, the time of the first complainant's complaint will be used as the face-to-face test time.

[0021] The complaint content, interview time and interview address of the first complainant are sorted according to the interview time to form a sequence of first complainant customers.

[0022] Furthermore, a complaint handling plan for the first complainant is generated based on the face-to-face assessment data, specifically including:

[0023] Based on the face-to-face test data, determine the cause of the network failure of the first complainant, and determine whether the network failure is a scenario where the operator is responsible.

[0024] In response to scenarios where the operator is responsible, a complaint handling plan is generated for the first customer who complains, including the cause of the network failure, the level of the network failure, the solution to the network failure, the time to resolve the network failure, and the personnel responsible for resolving the network failure.

[0025] Send the complaint handling plan to the customer service department and network management department for implementation, and receive implementation feedback from the customer service department and network management department.

[0026] Secondly, this disclosure provides a method for handling online complaints, the method being applied to a surface-testing unmanned aerial vehicle (UAV) control system, and including:

[0027] Receive the complaint content, face-to-face interview time and address from the first complainant in the customer complaint handling system. The first complainant is the complainant in the customer complaint handling system who is determined to need to conduct a face-to-face interview based on the customer complaint.

[0028] Based on the content of the complaint, a face-to-face test task was formulated to test the network signal quality, and a drone was deployed to fly to the face-to-face test address at the face-to-face test time to perform the face-to-face test task in order to obtain the face-to-face test data of the first complainant.

[0029] The face-to-face assessment data is sent to the customer complaint handling system so that the system can generate a complaint handling plan for the first complainant based on the face-to-face assessment data.

[0030] Furthermore, based on the content of the complaints, a face-to-face testing task for network signal quality was formulated, and drones were deployed to fly to the test location during the test time to perform the test, specifically including:

[0031] The on-site testing task is formulated based on the content of the complaint. The on-site testing task includes the network signal indicators that need to be collected, as well as the number and location of test points.

[0032] Based on the distance between the drone and the test location during the test period, the drone is allocated, and the flight path of the allocated drone to the test location during the test period is generated and the flight path is submitted for approval.

[0033] The controlled drones fly to the test site according to the flight path during the test period and collect network signal index data at the test point at the test site.

[0034] Furthermore, obtain the face-to-face interview data from the first complainant, specifically including:

[0035] Obtain call quality test (CQT) data for the primary cell and neighboring cells of the primary cell where the first complainant is located. The CQT data includes field strength index data, call quality index data, co-channel index data, and frequency hopping index data.

[0036] Thirdly, this disclosure provides a customer complaint handling system, the system comprising:

[0037] The complaint module is used to identify the first customer who needs to undergo an in-person interview based on customer complaints, and to obtain the content of the first customer's complaint, the interview time, and the interview address.

[0038] The first sending module, connected to the complaint module, is used to send the complaint content, face-to-face test time, and face-to-face test address of the first complaining customer to the face-to-face test drone control system, so that the face-to-face test drone control system can formulate a face-to-face test task to test the network signal quality based on the complaint content, and call the drone to fly to the face-to-face test address at the face-to-face test time to perform the face-to-face test task in order to obtain the face-to-face test data of the first complaining customer.

[0039] The processing module, connected to the first sending module, is used to receive surface test data from the surface test drone control system and generate a complaint handling plan for the first complaining customer based on the surface test data.

[0040] Fourthly, this disclosure provides a control system for surface-mounted unmanned aerial vehicles (UAVs), the system...

[0041] include:

[0042] The second receiving module is used to receive the complaint content, face-to-face test time and face-to-face test address of the first complainant from the customer complaint handling system. The first complainant is the complainant who needs to be tested in face-to-face according to the customer complaint determined by the customer complaint handling system.

[0043] The face test control module, connected to the second receiving module, is used to formulate a face test task to test the network signal quality based on the content of the complaint, and to call the drone to fly to the face test address at the face test time to perform the face test task in order to obtain the face test data of the first complaining customer.

[0044] The second sending module, connected to the face test control module, is used to send face test data to the customer complaint handling system so that the customer complaint handling system can generate a complaint handling plan for the first complainant based on the face test data.

[0045] Fifthly, this disclosure provides an online complaint handling system, the system comprising:

[0046] A customer complaint handling system for implementing the online complaint handling method as described in the first aspect;

[0047] The surface-testing drone control system is connected to the customer complaint handling system to implement the online complaint handling method as described in the second aspect.

[0048] Sixthly, this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the network complaint processing method described above.

[0049] This disclosure provides a network complaint handling method, a customer complaint handling system, a face-to-face testing drone control system, a network complaint handling framework, and a computer-readable storage medium. It identifies customers requiring face-to-face testing and their testing requirements, develops targeted face-to-face testing tasks for these customers, and allows drones to execute these tasks according to the testing requirements. This approach efficiently acquires face-to-face testing data at a low cost and generates targeted complaint handling solutions based on the data. It achieves the effects of rationally scheduling face-to-face testing, effectively acquiring face-to-face testing data, and scientifically developing complaint handling solutions, which is of great significance for improving the quality of network services provided by operators. Attached Figure Description

[0050] Figure 1 is a flowchart of a network complaint handling method according to an embodiment of the present disclosure;

[0051] Figure 2 is a schematic diagram of the structure of a network complaint handling system according to an embodiment of this disclosure;

[0052] Figure 3 is a flowchart of another online complaint handling method according to an embodiment of this disclosure;

[0053] Figure 4 is a flowchart of another online complaint handling method according to an embodiment of this disclosure;

[0054] Figure 5 is a schematic diagram of the structure of a customer complaint handling system according to an embodiment of the present disclosure;

[0055] Figure 6 is a schematic diagram of the structure of a surface-mounted unmanned aerial vehicle control system according to an embodiment of the present disclosure. Detailed Implementation

[0056] To enable those skilled in the art to better understand the technical solutions of this disclosure, the embodiments of this disclosure will be further described in detail below with reference to the accompanying drawings.

[0057] It is understood that the specific embodiments and accompanying drawings described herein are for illustrative purposes only and are not intended to limit the scope of this disclosure.

[0058] It is understood that, without conflict, the various embodiments and features in the embodiments of this disclosure can be combined with each other.

[0059] It is understood that, for ease of description, only the parts relevant to this disclosure are shown in the accompanying drawings, while parts unrelated to this disclosure are not shown in the drawings.

[0060] It is understood that each unit or module involved in the embodiments of this disclosure may correspond to only one entity structure, or may be composed of multiple entity structures, or multiple units or modules may be integrated into one entity structure.

[0061] It is understood that, without conflict, the functions and steps marked in the flowcharts and block diagrams of this disclosure may occur in a different order than that marked in the accompanying drawings.

[0062] It is understood that the flowcharts and block diagrams of this disclosure illustrate the architecture, functions, and operations of possible implementations of systems, apparatuses, devices, and methods according to various embodiments of this disclosure. Each block in a flowchart or block diagram may represent a unit, module, program segment, or code, containing executable instructions for implementing the specified function. Furthermore, each block or combination of blocks in the block diagrams and flowcharts may be implemented using a hardware-based system to implement the specified function, or using a combination of hardware and computer instructions.

[0063] It is understood that the units and modules involved in the embodiments of this disclosure can be implemented by software or by hardware, for example, the units and modules can be located in a processor.

[0064] Example 1:

[0065] As shown in Figures 1 and 2, this disclosure provides a method for handling online complaints. The method is applied to a customer complaint handling system 1 and includes:

[0066] S11. Identify the first complainant who needs to undergo face-to-face testing based on customer complaints, and obtain the content of the first complainant's complaint, the time of face-to-face testing, and the address of face-to-face testing.

[0067] S12. Send the complaint content, face-to-face test time and face-to-face test address of the first complainant to the face-to-face test drone control system 2, so that the face-to-face test drone control system 2 can formulate a face-to-face test task to test the network signal quality according to the complaint content, and call the drone to fly to the face-to-face test address at the face-to-face test time to perform the face-to-face test task, so as to obtain the face-to-face test data of the first complainant.

[0068] S13. Receive surface test data from the surface test drone control system 2, and generate a complaint handling plan for the first complaining customer based on the surface test data.

[0069] Specifically, current handling of customer complaints about network migration by operators primarily relies on explanation, supplemented by in-person testing. Furthermore, processing a single network migration complaint requires significant manpower and resources. The process from the customer service representative's explanation to the on-site network testing appointment with the customer is extremely lengthy and arduous. Without in-person testing, it's impossible to ascertain the veracity of the customer's claims about the network situation; explanations based solely on experience lack persuasive evidence and data. However, conducting in-person testing for every single customer complaint is impractical; the operators cannot dedicate such substantial manpower to perform testing for each complaint. This presents a difficult challenge for operators, presenting them with a dilemma.

[0070] Therefore, the mobile network complaint handling method and system based on a low-altitude economic drone flight communication network provided in this embodiment is very important. This method and system discloses the execution actions and methods of drone flight commands using low-altitude economic technology. Essentially, through a dispatch system, the drone automatically performs a point-based task, collecting mobile network signal data in the network coverage area and returning this data to the complaint handling work order. The system then provides a scientific interpretation of the mobile network signal based on the customer's complaint. This method and system screens customers requiring in-person testing and their testing requirements, formulates targeted in-person testing tasks for these customers, and has the drone execute these tasks according to the requirements. This efficiently acquires in-person testing data at a low cost and generates a targeted complaint handling plan based on the data. This achieves the effects of rationally arranging in-person testing, effectively acquiring in-person testing data, and scientifically formulating complaint handling plans, which is of great significance for improving the quality of operator network services.

[0071] More specifically, as shown in Figure 2, this complaint handling method and system (architecture) comprises two main systems: the customer complaint handling system 1 and the face-to-face testing drone control system 2. Correspondingly, the counterpart method executed by the face-to-face testing drone control system 2 is shown in Figure 3, including:

[0072] S21. Receive the complaint content, face-to-face test time and face-to-face test address from the first complainant of the customer complaint handling system 1. The first complainant is the complainant who needs to be tested in face-to-face test as determined by the customer complaint handling system 1 based on the customer complaint.

[0073] S22. Based on the complaint, formulate a face-to-face test task to test the network signal quality, and call a drone to fly to the face-to-face test address at the face-to-face test time to perform the face-to-face test task in order to obtain the face-to-face test data of the first complainant.

[0074] S23. Send the face-to-face test data to the customer complaint handling system 1 so that the customer complaint handling system 1 can generate a complaint handling plan for the first complainant based on the face-to-face test data.

[0075] In one implementation, S11 involves identifying the first complainant who requires an in-person interview based on the customer complaint, specifically including:

[0076] Based on customer complaints, we obtain the characteristic parameters of the complaining customers, including the number of complaints at the customer address, the interval between the customer address's historical face-to-face interviews and the current complaint at the customer address, customer value, and customer demands.

[0077] Clustering algorithms are used to classify complaining customers based on their characteristic parameters, in order to identify the first complaining customer who has a high number of complaints at their address, a large interval between the historical face-to-face interviews at their address and the current complaint, high customer value, and whose complaint includes information requiring a face-to-face interview.

[0078] In this embodiment, as shown in Figure 4, the functions of 14 modules together constitute the method and system for handling network migration complaints of low-altitude economic unmanned aerial vehicle (UAV) flight communication networks. Modules S100 to S106 are located in the customer complaint handling system 1, and modules S201 to S207 are located in the UAV control system 2. The method and system handle network migration complaints of flight communication networks according to the following steps:

[0079] Firstly, in the customer complaint handling system:

[0080] S100 indicates that it receives customer complaints by collecting customer complaint information from the official website and hotline. This information mainly includes three items: customer address, customer information, and customer request. It also collects the content of the customer complaint, namely the network problem reflected by the customer. This step automatically filters and removes non-standard complaint tickets, retains customer complaint tickets containing the three items, and transmits them to the customer complaint processing system.

[0081] S101 represents the customer complaint issue classification. This module classifies customer complaints based on their content, assigning the three items to the next step module. This step can use keyword matching or text content recognition for classification. The number of customer complaints, customer value, and the number of complaints against the corresponding level 5 address are used as criteria to determine whether an in-person interview is required. The level 7 address corresponds to the house number in the customer complaint, while the level 5 address is further refined to the building unit.

[0082] S102 represents the seventh-level address corresponding to the customer complaint. Retrieve the fifth-level address corresponding to the seventh-level address. This address contains an address database. If the customer complaint address is new, it is added to the address database. If the customer complaint address is a multiple complaint address, the number of complaints is tagged. For example, register the address corresponding to the business number of the customer complaint. Each time a complaint is made, the corresponding number is accumulated. This information table exists in the point tracking system database.

[0083] S103 indicates a customer complaint. This complaint may include whether the customer requests material compensation or a solution to the network signal issue. If the request is for a complete solution to the poor mobile signal problem, a drone-based on-site assessment is required. To resolve the mobile signal quality issue, the problem needs to be identified first, which means verifying what factors are causing the poor signal, such as the user terminal, base station, and the number of current connected users. Different factors require different solutions, hence the need for drones to survey the area and clarify the cause of the poor mobile signal quality. Other situations, such as those requiring material compensation, do not require on-site testing. Customer complaints can be obtained through customer service follow-ups. In the complaint handling process, after a customer complaint is accepted, a complaint handling specialist will follow up with the customer and propose compensation suggestions, which are based on customer satisfaction. These suggestions may include a grant, compensation of a certain amount, or repair of the mobile signal at that address.

[0084] S104 indicates whether surface testing is required. This step is a judgment based on a comprehensive consideration of the information from S101, S102, and S103 above.

[0085] In one embodiment, customer complaint characteristic parameters are obtained based on customer complaints. These parameters include the number of complaints made at the customer's address, the interval between historical face-to-face interviews at the customer's address and the current complaint at the customer's address, customer value, and customer demands. Specifically, these parameters include:

[0086] Upon receiving a customer complaint, the system obtains the content of the complaint and collects customer complaint information, including the customer's seven-level address, personal information, and complaint request.

[0087] Obtain the fifth-level address corresponding to the seventh-level address of the complaining customer, and obtain the number of complaints without face-to-face testing for the same complaint type as the content of this complaint at the fifth-level address, and use this as the number of complaints at the customer address;

[0088] Obtain the most recent face-to-face interview time for historical customer complaints of the same type as the current complaint at the fifth-level address, and calculate the interval between the most recent historical face-to-face interview time and the current complaint time, as the interval between the historical face-to-face interview at the customer address and the current complaint at the customer address;

[0089] Based on the personal information of complaining customers, we obtain the customer value of complaining customers, including the complaining customer's average monthly contribution ARUP value, customer star rating, and customer's membership duration;

[0090] Analyze the complaints of customers to determine whether they require material compensation or a complete solution to the network problem. If the customer's request is to completely solve the network problem, it includes information that requires face-to-face interview.

[0091] The number of complaints at a customer's address, the interval between the historical face-to-face measurement of the customer's address and the current complaint at the customer's address, customer value, and customer demands are quantified, weighted, and normalized to obtain characteristic parameters of the complaining customer.

[0092] In this embodiment, the method for determining whether a complaining customer needs an in-person interview can be as follows:

[0093] Assuming we have customer data as shown in Table 1 (for simplicity, we use hypothetical data here), that is, assuming the following customer complaint characteristic parameters were obtained through steps S101-S103, where ARUP stands for Average User Purchases Average, which is the average monthly contribution value per user; network access duration is the length of time since the customer opened their account; the number of complaints for the fifth-level address is the number of times the mobile network type for that address has been complained about in the system; historical face-to-face test report data needs to be calculated, and this parameter is a time-related variable that can be obtained based on the time interval of the most recent processed historical complaint or the time interval of multiple historical complaints; customer star rating is obtained by querying the service level purchased by the customer based on their identity information.

[0094] Table 1 Examples of Customer Characteristic Parameters for Complaints

[0095] Historical data on complaints at Level 5 addresses, customer rating, ARUP value, and network access duration: 23.54501214.03452452.0530603.82553633.044015 surface

[0096] The above information is used as parameters in the clustering process. A single parameter cannot directly affect the clustering result; it merely serves as input to obtain two clustering results from the output. The clustering algorithm is an unsupervised learning algorithm that determines the specific clustering class based on the geometric spatial distribution of each point. Specifically, this step can be:

[0097] Select K=2 initial points, calculate the distance from each point to these initial points, forming 2 classes. Based on the formed classes, recalculate the cluster center point of each cluster, which is the average distance from all points in the class to the center point of the class. Repeat the process of assigning new clusters and calculating the average distance of the cluster center points until the center points no longer change. At this point, you can separate 2 different classes, one that requires face-to-face testing and the other that does not.

[0098] The formula used to calculate distance can be:

[0099]

[0100] Where, x ik It is data point x i The kth feature, c jk It is the center point c j The kth feature.

[0101] As shown in Table 1, choosing K=2 means we want to divide customers into two categories. We initialize two cluster centers, for example, by randomly selecting the first and second customers as cluster centers. We then use a binary clustering algorithm iteratively until the cluster centers stabilize. The final clustering results may be as follows:

[0102] Cluster 1, which requires face testing: includes Customer 1, Customer 2 and Customer 3;

[0103] Cluster 2, no face testing required: includes Customer 4 and Customer 5;

[0104] The feature vector of each cluster will be the average of the feature vectors of all customers within that cluster.

[0105] Understandably, during clustering calculations, based on the impact of each column of data in Table 1 on the clustering results, different weights can be set for each column of data according to experience, and the data can be normalized, for example, normalized to data between 0 and 1. Customer complaints generally take two values, 0 and 1, where 1 indicates the customer requests in-person testing and 0 indicates the customer accepts compensation. This dimension has the most direct impact on the clustering results, and users can be directly classified according to their complaints before or after clustering, or a larger weight can be set. The actual customer base of the address database should be in the tens of millions or more. The above is a simplified example table. Based on this information, the conclusion of S104 is derived: whether in-person testing is needed. The output of this algorithm is data with two classes. The class that needs in-person testing will proceed to subsequent steps. For users with the same level 5 address, one or more can be selected for in-person testing, while those that do not need in-person testing are removed.

[0106] In one implementation, S11 involves obtaining the complaint content, interview time, and interview address of the first complainant, specifically including:

[0107] Based on the content of the first complaint, the number of complaints at the customer's address, and / or the face-to-face interviews with historical customers whose complaints of the same type as the current complaint are from the fifth-level address, determine whether the face-to-face interview address is a seventh-level address or a fifth-level address.

[0108] If the face-to-face test address is a level 7 address, an appointment time for the face-to-face test will be agreed upon with the first complainant; otherwise, the time of the first complainant's complaint will be used as the face-to-face test time.

[0109] The complaint content, interview time and interview address of the first complainant are sorted according to the interview time to form a sequence of first complainant customers.

[0110] In this embodiment, the level 5 address is the same as the building unit corresponding to the level 7 address, and the level 7 address can correspond to a specific house number. Ultimately, the test address needs to be determined based on the address of the mobile network signal complained about by the user. If the area complained by the customer is the entire building, it corresponds to the level 5 address. If the customer complains about a specific room in their home, it corresponds to the level 7 address, and it is necessary to enter the customer's home for testing.

[0111] In one implementation, as shown in S22 of Figure 3, a face-to-face testing task for testing network signal quality is formulated based on the content of the complaint, and a drone is called to fly to the face-to-face testing address at the face-to-face testing time to perform the face-to-face testing task, specifically including:

[0112] The on-site testing task is formulated based on the content of the complaint. The on-site testing task includes the network signal indicators that need to be collected, as well as the number and location of test points.

[0113] Based on the distance between the drone and the test location during the test period, the drone is allocated, and the flight path of the allocated drone to the test location during the test period is generated and the flight path is submitted for approval.

[0114] The controlled drones fly to the test site according to the flight path during the test period and collect network signal index data at the test point at the test site.

[0115] In one embodiment, as shown in S22 of FIG3, the acquisition of the face-to-face interview data of the first complaining customer specifically includes:

[0116] Obtain call quality test (CQT) data for the primary cell and neighboring cells of the primary cell where the first complainant is located. The CQT data includes field strength index data, call quality index data, co-channel index data, and frequency hopping index data.

[0117] In this embodiment, as shown in Figure 4, in the surface-measurement UAV control system 2:

[0118] The S201 module indicates the face test time, which is generally determined based on the drone's scheduling time. Unless the customer's complaint mentions a specific time requirement, the face test time for the Level 7 address is determined according to the normal scheduling time, which is the face test priority. If the customer's request does not specify that expedited processing is needed or emphasize that the mobile network should be handled within a certain time frame, then the testing will be carried out in the normal order. If the customer requests expedited processing, then these testing addresses need to be prioritized, and their priority is higher than testing addresses for which no time is specified.

[0119] S202 represents the face-to-face test sequence, which corresponds to the customer complaint sequence. There is a correspondence between the face-to-face test sequence and the customer complaint sequence so that the generated face-to-face test results can be fed back into the complaint sequence. The information processing work generates the face-to-face test sequence according to the priority order, and finally feeds back the face-to-face test results into the complaint sequence. It can be a table containing the following fields. The face-to-face test sequence should at least contain drone number, address number information and face-to-face test time information. At least one column in the two tables can match each other. The customer complaint sequence and the face-to-face test sequence have a one-to-one correspondence. It is mainly used to transmit the face-to-face test report generated after the face-to-face test into the customer complaint processing system 1 for the corresponding customer complaint.

[0120] S203 indicates an application for in-person testing, which is mainly used for manual approval within the operator. This step will automatically generate a workflow in the system and pass it to the corresponding approver. The corresponding processing steps can be set, and the system will automatically execute the flow. For example, a fixed format of steps from the applicant to the security officer to the department leader to the company-level leader. The system only needs to obtain the consent of the corresponding approver before it can pass it to the next processor. This process includes customer complaint content and in-person testing sequence.

[0121] S204 indicates that the system will allocate the drone closest to the surface measurement address. The corresponding level 5 address will correspond to a latitude and longitude information. There will be a flight path between the latitude and longitude information of the deployed drone hangar and the latitude and longitude information of the surface measurement point. Generally, it can be a straight line. If it is a straight line, only the distance between the two points needs to be calculated to compare the distance. The address data can be obtained from Baidu Maps, or Baccarat coordinates, or the location information of the base station deployment and the latitude and longitude information of the corresponding level 5 address.

[0122] S205 indicates the generation of the drone's flight path from the warehouse to the test site. This path can be formulated in conjunction with relevant standards, such as the need for drones to avoid restricted flight areas, no-fly zones, and temporary restricted flight areas according to laws and regulations. In terms of altitude, different areas also have different requirements for flight altitude, which must comply with the "Interim Regulations on the Flight Management of Unmanned Aerial Vehicles" and the relevant regulations of the flight location. The drone automatically and synchronously generates a flight log. The most important data in the flight log is the flight speed, altitude, latitude and longitude information, elevation angle, wind speed, weather and other factors that affect flight safety. Its purpose is to ensure that the drone can return to the hangar after completing the test task, avoiding problems such as signal loss or interception during the journey, which would cause economic losses to the drone.

[0123] S206 represents the face test data returned by the drone after it arrives at the face test address. This data mainly includes CQT (call quality test), which mainly includes field strength (received level value, including the master cell and neighboring cells), call quality (eight levels from 0 to 7), co-frequency and adjacent frequency (master cell and neighboring cells), frequency hopping, CI (cell identity), and other indicators.

[0124] S207 indicates the generation of customized surface test reports. Based on the actual measurement data of the drone, customized reports are generated, such as: level 0 with poor call quality, no coverage or poor coverage, and verbal reports such as base station overload during peak hours requiring capacity expansion.

[0125] The entire surface testing drone control system 2 is now complete. Finally, all that is needed is to transmit the customized report to the customer complaint handling system 1.

[0126] In one embodiment, step S13 generates a complaint handling plan for the first complaining customer based on the face-to-face measurement data, specifically including:

[0127] Based on the face-to-face test data, determine the cause of the network failure of the first complainant, and determine whether the network failure is a scenario where the operator is responsible.

[0128] In response to scenarios where the operator is responsible, a complaint handling plan is generated for the first customer who complains, including the cause of the network failure, the level of the network failure, the solution to the network failure, the time to resolve the network failure, and the personnel responsible for resolving the network failure.

[0129] Send the complaint handling plan to the customer service department and network management department for implementation, and receive implementation feedback from the customer service department and network management department.

[0130] In this embodiment, the customer complaint handling system 1 continues to execute:

[0131] S105 generates a complaint handling plan. This step combines customer complaints and the actual results of the face-to-face test to generate a reasonable handling report. This step requires categorizing customer complaints, which can be divided into scenarios where the operator is responsible or not, based on the test report data. Whether the operator is responsible is determined based on the face-to-face test results, ruling out client-side malfunctions, property factors, normal face-to-face test results with no abnormalities found, and SIM (Subscriber Identity) issues. After considering several reasons, such as module (user identification card) damage, these are all scenarios where the operator is responsible. If the actual test data does indeed show a mobile network signal problem, the data collected by the drone mainly simulates the detection indicators included in manual face-to-face testing to determine this. These indicators mainly include the base station's upload and download speeds, signal strength, signal-to-noise ratio, bit error rate, and signal latency. These parameters are physical factors affecting the quality of the mobile network signal. Therefore, if these parameters are abnormal, it can be determined that there is a mobile network signal problem at that address. If not, then it is necessary to determine the number of base station connections, the user's upload and download speeds at the time of the customer complaint, and whether there is signal amplifier interference, etc., which are also mobile network signal problems. Of course, the drone is only responsible for measuring these parameters. If none of these apply, further comprehensive analysis is needed to draw a conclusion. Here, there can be a process branch: if the tested physical parameters are problematic, then it is determined that there is a mobile network signal problem; if the tested parameters are not problematic, then manual intervention is needed to determine the signal problem. If the operator is not responsible, then the report should mainly focus on explanation and reassurance.

[0132] When responsible, a report in the following fixed format can be generated:

[0133] 1) Major Warning Conditions / Ordinary Warning Conditions (Complaint Type):

[0134] 2) Complaint address (accurate to the specific building, floor, and room number):

[0135] 3) Whether it was tested (self-tested, interviewed, not tested):

[0136] 4) Causes of the problem (weak coverage, fault, high load, interference, other):

[0137] 5) Location status:

[0138] 6) Solutions (troubleshooting, adding indoor distribution systems, adding base stations, interference troubleshooting, capacity expansion, sharing telecommunications services, load balancing, optimization and adjustment):

[0139] 7) Has the problem been resolved (resolved, cannot be resolved in the short term, expected to be resolved):

[0140] 8) Expected resolution timeframe (specifying the timeframe):

[0141] This report summarizes the test results and is intended for both customers and customer service personnel. It eliminates jargon and technical information to reduce the burden of comprehension. Based on the customer service personnel's understanding, this report is then relayed to the customer. The solution implementation involves referring the test results, such as physical parameters like signal strength and latency, to the network management department for resolution. For the customer, customer service is responsible for handling the issues.

[0142] S106 indicates that the contents of the complaint handling report will be fed back to the customer. This can be done by phone, email, or by submitting a complaint form on the official website. The network management department can resolve network signal issues, and the customer service department can address customer complaints. After generating the complaint handling report, customer service can inform the user during a follow-up call that the network problem is expected to be resolved within three months. The customer is advised to check back, and if the problem persists, they can continue to file complaints.

[0143] In this embodiment 1, drones are used to track mobile network activity, employing clustering algorithms to identify complainants requiring face-to-face testing and generating reports with fixed-format complaint handling solutions. This serves as a crucial function within the intelligent customer service operation platform, handling complaints related to significant public opinion and hot-button issues on the customer's mobile network. It utilizes low-altitude economic drone flight communication networks for mobile network complaint processing, ensuring timely handling and preventing escalation. This approach plays a vital role in practical applications. Since customer service possesses a large amount of customer complaint information, stored and archived in text format, historical complaint information can be leveraged to determine mobile network complaint handling solutions. Combined with the efficient and low-cost characteristics of low-altitude economic tracking, each mobile network complaint can be handled more appropriately, making it a crucial element in the digital transformation of customer service. In the actual implementation of the solution, relevant customer complaint information is used to extract key issues. Deep learning-enhanced algorithms are then used to generate processing reports for these key issues.

[0144] Example 2:

[0145] As shown in Figure 3, this disclosure provides a method for handling online complaints. The method is applied to a surface-testing unmanned aerial vehicle (UAV) control system and includes:

[0146] S21. Receive the complaint content, face-to-face test time and address from the first complainant in the customer complaint handling system. The first complainant is the complainant in the customer complaint handling system who is determined to need to undergo face-to-face testing based on the customer complaint.

[0147] S22. Based on the complaint, formulate a face-to-face test task to test the network signal quality, and call a drone to fly to the face-to-face test address at the face-to-face test time to perform the face-to-face test task in order to obtain the face-to-face test data of the first complainant.

[0148] S23. Send the face-to-face test data to the customer complaint handling system so that the customer complaint handling system can generate a complaint handling plan for the first complainant based on the face-to-face test data.

[0149] In one implementation, step S22 involves creating a face-to-face testing task for network signal quality based on the complaint, and then calling a drone to fly to the face-to-face testing address during the testing time to perform the test. Specifically, this includes:

[0150] The on-site testing task is formulated based on the content of the complaint. The on-site testing task includes the network signal indicators that need to be collected, as well as the number and location of test points.

[0151] Based on the distance between the drone and the test location during the test period, the drone is allocated, and the flight path of the allocated drone to the test location during the test period is generated and the flight path is submitted for approval.

[0152] The controlled drones fly to the test site according to the flight path during the test period and collect network signal index data at the test point at the test site.

[0153] In one implementation, obtaining the face-to-face interview data of the first complaining customer in S22 specifically includes:

[0154] Obtain call quality test (CQT) data for the primary cell and neighboring cells of the primary cell where the first complainant is located. The CQT data includes field strength index data, call quality index data, co-channel index data, and frequency hopping index data.

[0155] Example 3:

[0156] As shown in Figure 5, this disclosure provides a customer complaint handling system, characterized in that the system includes:

[0157] The complaint module 11 is used to identify the first customer who needs to undergo face-to-face testing based on customer complaints, and to obtain the complaint content, face-to-face testing time and face-to-face testing address of the first customer.

[0158] The first sending module 12, connected to the complaint module 11, is used to send the complaint content, face-to-face test time, and face-to-face test address of the first complaining customer to the face-to-face test drone control system, so that the face-to-face test drone control system can formulate a face-to-face test task to test the network signal quality based on the complaint content, and call the drone to fly to the face-to-face test address at the face-to-face test time to perform the face-to-face test task, so as to obtain the face-to-face test data of the first complaining customer.

[0159] The processing module 13, connected to the first sending module 12, is used to receive surface measurement data from the surface measurement UAV control system and generate a complaint handling plan for the first complaining customer based on the surface measurement data.

[0160] In one embodiment, the complaint module 11 specifically includes:

[0161] The parameter unit is used to obtain the characteristic parameters of the complaining customer based on the customer complaint. The characteristic parameters of the complaining customer include the number of complaints at the customer address, the interval between the historical face-to-face measurement of the customer address and the current complaint at the customer address, the customer value, and the customer's demands.

[0162] The classification unit, connected to the parameter unit, is used to classify complaining customers according to the characteristic parameters of the complaining customers using a clustering algorithm, in order to identify the first complaining customer with a high number of complaints at the customer address, a large interval between the historical face-to-face test at the customer address and the current complaint at the customer address, high customer value, and customer requests containing information that require face-to-face testing.

[0163] In one embodiment, the parameter unit specifically includes:

[0164] The complaint information subunit is used to respond to customer complaints, obtain the content of the complaint from the complainant and collect customer complaint information, which includes the complainant's seven-level address, the complainant's personal information and the complainant's complaint request.

[0165] The complaint count subunit is used to obtain the fifth-level address corresponding to the seventh-level address of the complaining customer, and to obtain the number of non-face-to-face-tested complaints of the same type as the content of this complaint at the fifth-level address, which is used as the number of complaints at the customer address.

[0166] The complaint interval subunit is used to obtain the most recent historical interview time of historical customer complaints with the same complaint type as the current complaint at the fifth-level address, and calculate the interval between the most recent historical interview time and the current complaint time, which is used as the interval between the historical interview at the customer address and the current complaint at the customer address.

[0167] The Customer Value sub-unit is used to obtain the customer value of a complaining customer based on the complaining customer's personal information, including the complaining customer's average monthly contribution ARUP value, customer star rating, and customer's membership duration.

[0168] The Customer Requests subunit is used to analyze the complaints of complaining customers to determine whether the customer's request is to provide material compensation or to completely resolve the network problem. If the customer's request is to completely resolve the network problem, it includes information that requires face-to-face testing.

[0169] The numerical processing subunit is used to quantify, weight, and normalize the number of complaints at the customer address, the interval between the historical face-to-face measurement of the customer address and the current complaint at the customer address, customer value, and customer demands to obtain characteristic parameters of the complaining customer.

[0170] In one embodiment, the complaint module 11 further includes:

[0171] The face-to-face testing address unit is used to determine whether the face-to-face testing address is a level 7 address or a level 5 address based on the content of the first complaint from the customer, the number of complaints made at the customer's address, and / or historical customer complaints of the same type as the current complaint at a level 5 address.

[0172] The face-to-face testing time unit is used to respond when the face-to-face testing address is a level 7 address and to agree on a face-to-face testing time with the first complaining customer; otherwise, the time of the first complaining customer's current complaint is used as the face-to-face testing time.

[0173] The face-to-face testing sequence unit, connected to the face-to-face testing address unit and the face-to-face testing time unit, is used to sort the complaint content, face-to-face testing time and face-to-face testing address of the first complaining customer according to the face-to-face testing time, so as to form the first complaining customer sequence.

[0174] In one embodiment, the processing module 13 specifically includes:

[0175] The responsibility delineation unit is used to determine the cause of the network failure for the first complainant based on the face test data, and to determine whether the network failure is a scenario in which the operator is responsible.

[0176] The solution unit, connected to the responsibility allocation unit, is used to respond to scenarios where the operator is responsible, and to generate a complaint handling solution for the first complainant, including the cause of the network failure, the level of the network failure, the solution to the network failure, the time to resolve the network failure, and the personnel responsible for resolving the network failure.

[0177] The processing unit, connected to the solution unit, is used to send complaint handling solutions to the customer service department and network management department for execution, and to receive execution feedback from the customer service department and network management department.

[0178] Example 4:

[0179] As shown in Figure 6, this disclosure provides a surface-based unmanned aerial vehicle (UAV) control system, the system comprising:

[0180] The second receiving module 21 is used to receive the complaint content, face-to-face test time and face-to-face test address of the first complainant from the customer complaint handling system. The first complainant is the complainant who needs to be tested in face-to-face according to the customer complaint determined by the customer complaint handling system.

[0181] The face test control module 22 is connected to the second receiving module 21. It is used to formulate a face test task to test the network signal quality based on the content of the complaint, and call the drone to fly to the face test address at the face test time to perform the face test task in order to obtain the face test data of the first complaining customer.

[0182] The second sending module 23 is connected to the face test control module 22 and is used to send face test data to the customer complaint handling system so that the customer complaint handling system can generate a complaint handling plan for the first complaining customer based on the face test data.

[0183] In one embodiment, the surface measurement control module 22 specifically includes:

[0184] Task units are defined to develop face-to-face testing tasks based on the content of complaints. Face-to-face testing tasks include network signal indicators that need to be collected, as well as the number and location of test points.

[0185] The path generation unit is used to allocate drones based on the distance between the drone and the location during the surface test, generate the flight path of the allocated drone to the location during the surface test, and submit the flight path for approval.

[0186] The control unit, connected to the task designation unit and path generation unit, is used to control the dispatched UAV to fly to the test address according to the flight path during the test time, and to collect network signal index data at the test point of the test address.

[0187] In one embodiment, the surface measurement control module 22 further includes:

[0188] The face test data acquisition unit is used to acquire call quality test (CQT) data of the main control cell and neighboring cells of the main control cell where the first complaining customer is located. The CQT data includes field strength index data, call quality index data, co-channel index data, and frequency hopping index data.

[0189] Example 5:

[0190] As shown in Figure 2, this disclosure provides an online complaint handling system, the system comprising:

[0191] Customer complaint handling system 1 is used to implement the online complaint handling method as described in Example 1;

[0192] The surface-testing drone control system 2 is connected to the customer complaint handling system 1 to implement the online complaint handling method as described in Example 2.

[0193] Example 6:

[0194] Embodiment 6 of this disclosure provides a computer-readable storage medium storing a computer program. When the computer program is run by a processor, it implements the network complaint handling method as described in Embodiment 1 or 2, or the customer complaint handling system as described in Embodiment 3, or the surface-testing drone control system as described in Embodiment 4, or the network complaint handling system as described in Embodiment 5.

[0195] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program modules, or other data). Computer-readable storage media include, but are not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory or other memory technologies, CD-ROM (Compact Disc Read-Only Memory), DVD or other optical disc storage, cartridges, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer.

[0196] In addition, this disclosure may also provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the network complaint handling method as described in Embodiment 1 or 2. The computer device may be the customer complaint handling system as described in Embodiment 3, the surface-mounted drone control system as described in Embodiment 4, or the network complaint handling system as described in Embodiment 5.

[0197] The memory is connected to the processor. The memory can be flash memory, read-only memory or other types of memory. The processor can be a central processing unit or a microcontroller.

[0198] Embodiments 1-6 of this disclosure provide a network complaint handling method, a customer complaint handling system, a face-to-face testing drone control system, a network complaint handling framework, and a computer-readable storage medium. The method involves screening customers requiring face-to-face testing and their testing requirements, developing targeted face-to-face testing tasks for these customers, and having a drone execute these tasks according to the testing requirements. This approach efficiently acquires face-to-face testing data at a low cost and generates targeted complaint handling solutions based on the data. This achieves the effects of rationally scheduling face-to-face testing, effectively acquiring face-to-face testing data, and scientifically developing complaint handling solutions, which is of great significance for improving the quality of network services provided by operators.

[0199] It is understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of this disclosure, and this disclosure is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of this disclosure, and these modifications and improvements are also considered to be within the scope of protection of this disclosure.

Claims

1. A method for handling online complaints, characterized in that, The method is applied to a customer complaint handling system and includes: determining the first complainant who needs to undergo face-to-face testing based on the customer complaint, and obtaining the complaint content, face-to-face testing time, and face-to-face testing address of the first complainant. Specifically, it includes: in response to receiving a customer complaint, obtaining the complaint content of the complainant and collecting customer complaint information, including the complainant's seventh-level address, the complainant's personal information, and the complainant's complaint request; obtaining the fifth-level address corresponding to the seventh-level address of the complainant, and obtaining the number of non-face-to-face testing complaints of the same complaint type as the current complaint content at the fifth-level address, as the number of complaints at the customer address; obtaining the most recent historical face-to-face testing time for historical customer complaints of the same complaint type as the current complaint content at the fifth-level address, calculating the interval between the most recent historical face-to-face testing time and the current complaint time, as the interval between the historical face-to-face testing at the customer address and the current complaint at the customer address; obtaining the customer value of the complainant based on the complainant's personal information, including the complainant's average monthly contribution (ARUP) value, customer star rating, and customer network membership duration; analyzing the complainant's complaint request to determine whether the customer's request is to provide material compensation or to completely resolve the network problem; if the customer's request is to completely resolve the network problem, it includes information requiring face-to-face testing, and includes the number of complaints at the customer address, the interval between the historical face-to-face testing at the customer address and the current complaint at the customer address, and the customer's complaint request. Value and customer demands are quantified, weighted, and normalized to obtain characteristic parameters of complaining customers. A clustering algorithm is then used to classify complaining customers based on these parameters. The primary complaining customer is identified based on the following criteria: a high number of complaints at the customer's address, a large interval between the historical face-to-face interview and the current complaint, high customer value, and requests containing information requiring a face-to-face interview. Face-to-face interviews are conducted based on the content of the primary complaining customer's complaint, the number of complaints at the customer's address, and / or historical complaints of the same type as the current complaint at a level 5 address. The interview address is then determined to be either a level 7 or level 5 address. If the interview address is a level 7 address, a face-to-face interview time is scheduled with the primary complaining customer. Otherwise, the time of the first complaint from the customer is taken as the face-to-face test time. The complaint content, face-to-face test time, and face-to-face test address of the first customer are sorted according to the face-to-face test time to form a sequence of first customers. The complaint content, face-to-face test time, and face-to-face test address of the first customer are sent to the face-to-face test drone control system, so that the face-to-face test drone control system can formulate a face-to-face test task to test the network signal quality according to the complaint content, and call the drone to fly to the face-to-face test address at the face-to-face test time to perform the face-to-face test task to obtain the face-to-face test data of the first customer. The face-to-face test data from the face-to-face test drone control system is received, and a complaint handling plan for the first customer is generated according to the face-to-face test data.

2. The method according to claim 1, characterized in that, The process involves generating a complaint handling plan for the first complainant based on the face-to-face testing data. Specifically, this includes: determining the cause of the network failure for the first complainant based on the face-to-face testing data; determining whether the network failure is a scenario where the operator is responsible; responding to the scenario where the operator is responsible; generating a complaint handling plan for the first complainant that includes the cause of the network failure, the level of the network failure, the solution to the network failure, the time to resolve the network failure, and the personnel responsible for resolving the network failure; sending the complaint handling plan to the customer service department and the network management department for execution; and receiving execution feedback from the customer service department and the network management department.

3. A method for handling online complaints, characterized in that, The method is applied to a face-to-face testing drone control system and includes: receiving the complaint content, face-to-face testing time, and face-to-face testing address of a first complainant from a customer complaint handling system. The first complainant is a customer whose face-to-face testing is required based on the customer complaint. Specifically, the customer complaint handling system, upon receiving a customer complaint, obtains the complaint content and collects customer complaint information, including the complainant's seventh-level address, personal information, and complaint request. It obtains the fifth-level address corresponding to the seventh-level address and the number of non-face-to-face testing complaints of the same type as the current complaint content at the fifth-level address, using this as the number of customer address complaints. It obtains the most recent historical face-to-face testing time for historical customer complaints of the same type as the current complaint content at the fifth-level address, calculates the interval between the most recent historical face-to-face testing time and the current complaint time, using this as the interval between the customer address's historical face-to-face testing and the current complaint. It obtains the complainant's customer value based on their personal information, including the complainant's average monthly contribution (ARUP), customer star rating, and customer network membership duration. It analyzes the complainant's complaint request to determine whether the request is for material compensation or a complete solution to the network problem. A request for a complete solution to the network problem includes the requirement for face-to-face testing. Information is processed by quantifying, weighting, and normalizing the number of customer address complaints, the interval between historical face-to-face interviews at the customer address and the current complaint, customer value, and customer requests to obtain characteristic parameters of complaining customers. A clustering algorithm is then used to classify complaining customers based on these parameters. The first complaining customer is identified based on the number of complaints at the customer address, the large interval between historical face-to-face interviews at the customer address and the current complaint, high customer value, and requests containing information requiring face-to-face interviews. The face-to-face interview address is determined based on the content of the first complaining customer's complaint, the number of complaints at the customer address, and / or historical customer complaints of the same type as the current complaint at the fifth-level address. It is either a Level 7 or Level 5 address. If the test address is a Level 7 address, a test time is agreed upon with the first complainant. Otherwise, the time of the first complainant's complaint is used as the test time. The first complainant's complaint content, test time, and test address are sorted according to the test time to form a sequence of first complainant customers. A test task to test network signal quality is formulated based on the complaint content, and a drone is deployed to fly to the test address at the test time to perform the test task, thereby obtaining the first complainant's test data. The test data is then sent to the customer complaint processing system so that the system can generate a complaint handling plan for the first complainant based on the test data.

4. The method according to claim 3, characterized in that, Based on the complaint, a face-to-face testing task for network signal quality is formulated, and drones are deployed to fly to the face-to-face testing location during the testing period to perform the task. Specifically, this includes: formulating the face-to-face testing task based on the complaint, which includes network signal indicators requiring data collection, as well as the number and location of test points; allocating drones according to the distance between the drones and the face-to-face testing location during the testing period, generating flight paths for the allocated drones to fly to the face-to-face testing location during the testing period, and submitting the flight paths for approval; controlling the allocated drones to fly to the face-to-face testing location according to the flight paths during the testing period, and collecting network signal indicator data at the test points at the face-to-face testing location.

5. The method according to any one of claims 3-4, characterized in that, Obtain face-to-face test data from the first complainant customer, specifically including: obtaining call quality test (CQT) data from the main cell and neighboring cells of the main cell where the first complainant customer is located. The CQT data includes field strength index data, call quality index data, co-channel index data, and frequency hopping index data.

6. A customer complaint handling system, characterized in that, The system includes a complaint module, used to determine the first complainant requiring an in-person interview based on customer complaints, and to obtain the complaint content, interview time, and interview address of the first complainant. Specifically, this includes: in response to receiving a customer complaint, obtaining the complaint content and collecting customer complaint information, including the complainant's seventh-level address, personal information, and complaint request; obtaining the fifth-level address corresponding to the seventh-level address; obtaining the number of non-in-person interview complaints with the same complaint type as the current complaint content at the fifth-level address, which is used as the number of customer address complaints; and obtaining historical customer complaints with the same complaint type as the current complaint content at the fifth-level address. The most recent historical face-to-face interview time is used to calculate the interval between the most recent historical face-to-face interview time and the current complaint time, which is used as the interval between the historical face-to-face interview time and the current complaint time for the customer address. Based on the complainant's personal information, the customer value of the complainant is obtained, including the complainant's Average Monthly Return on Investment (ARUP), customer star rating, and customer's network tenure. The complainant's demands are analyzed to determine whether the customer's demand is for material compensation or a complete solution to the network problem. If the customer's demand is for a complete solution to the network problem, then information requiring a face-to-face interview is included. The number of complaints for the customer address, the interval between the historical face-to-face interview time and the current complaint time for the customer address, the customer value, and the customer's demands are quantified, weighted, and normalized. The process involves obtaining characteristic parameters of complaining customers, and using a clustering algorithm to classify them based on these parameters. The first complaining customer is identified based on the following criteria: a high number of complaints about the customer's address, a large interval between the current complaint and the previous in-person interview at that address, high customer value, and information in their complaint requiring an in-person interview. The first complaining customer is then selected for in-person interviews based on their complaint content, the number of complaints about their address, and / or historical complaints of the same type as the current complaint at a level 5 address. The interview address is determined to be either a level 7 or level 5 address. If the interview address is level 7, an in-person interview time is scheduled with the first complaining customer; otherwise, the time of the current complaint is used as the interview time. The testing time is used to sort the complaint content, face-to-face testing time, and face-to-face testing address of the first complaining customer to form a sequence of first complaining customers; the first sending module, connected to the complaint module, is used to send the complaint content, face-to-face testing time, and face-to-face testing address of the first complaining customer to the face-to-face testing drone control system, so that the face-to-face testing drone control system can formulate a face-to-face testing task to test the network signal quality based on the complaint content, and call the drone to fly to the face-to-face testing address at the face-to-face testing time to perform the face-to-face testing task to obtain the face-to-face testing data of the first complaining customer; the processing module, connected to the first sending module, is used to receive the face-to-face testing data from the face-to-face testing drone control system, and generate a complaint handling plan for the first complaining customer based on the face-to-face testing data.

7. A surface-mounted unmanned aerial vehicle (UAV) control system, characterized in that, The system includes: a second receiving module, used to receive the complaint content, face-to-face interview time, and face-to-face interview address of a first complainant from the customer complaint handling system. The first complainant is a customer for whom the customer complaint handling system determines a face-to-face interview is required based on the customer complaint. Specifically, the customer complaint handling system, upon receiving a customer complaint, obtains the complaint content and collects customer complaint information, including the complainant's seventh-level address, personal information, and complaint request. It also obtains the fifth-level address corresponding to the seventh-level address and the number of times a complaint of the same type as the current complaint has not been interviewed, using this information as the customer's... The system retrieves the most recent face-to-face interview time for historical customer complaints of the same type as the current complaint, based on the number of address-related complaints. It calculates the interval between this most recent face-to-face interview time and the current complaint time, using this interval as the time between historical face-to-face interviews and the current complaint. Based on the complainant's personal information, it obtains the complainant's customer value, including the complainant's Average Monthly Return on Investment (ARUP), customer star rating, and customer subscription duration. It analyzes the complainant's demands to determine whether the demand is for material compensation or a complete resolution of the network problem. If the demand is for a complete resolution of the network problem, then information requiring a face-to-face interview is included. This analysis considers the number of customer address complaints and historical face-to-face interviews for each customer address. The customer's address, the interval between the current complaint and the address, customer value, and customer requests are quantified, weighted, and normalized to obtain characteristic parameters of the complaining customer. A clustering algorithm is then used to classify complaining customers based on these parameters. The first complaining customer is identified based on the number of complaints to their address, the large interval between the current and past face-to-face interviews at that address, high customer value, and requests containing information requiring face-to-face interviews. Based on the first complaining customer's complaint content, the number of complaints to their address, and / or historical customer complaints with the same complaint type as the current complaint at a level 5 address, the face-to-face interview address is determined to be either a level 7 or level 5 address. If the face-to-face interview address is a level 7 address, it is compared with the first complaining customer's complaint. The customer agrees on a face-to-face testing time; otherwise, the time of the first complainant's complaint is used as the face-to-face testing time. The complaint content, testing time, and testing address of the first complainant are sorted according to the face-to-face testing time to form a sequence of first complainant customers. The face-to-face testing control module, connected to the second receiving module, is used to formulate a face-to-face testing task to test network signal quality based on the complaint content, and to call a drone to fly to the testing address at the testing time to perform the face-to-face testing task, thereby obtaining the face-to-face testing data of the first complainant customer. The second sending module, connected to the face-to-face testing control module, is used to send the face-to-face testing data to the customer complaint processing system, so that the customer complaint processing system can generate a complaint handling plan for the first complainant customer based on the face-to-face testing data.

8. A network complaint handling system, characterized in that, The system includes: a customer complaint handling system for implementing the online complaint handling method as described in any one of claims 1-2; and a surface-mounted unmanned aerial vehicle (UAV) control system connected to the customer complaint handling system for implementing the online complaint handling method as described in any one of claims 3-5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the network complaint handling method as described in any one of claims 1-2 or 3-5.

Images