Method, device and equipment for continuously evaluating user satisfaction of wireless network and medium

By analyzing and evaluating wireless service signaling data, identifying the user's target service type poor quality events and dividing the satisfaction status, it solves the problem of difficulty in accurately understanding user satisfaction in the prior art, and realizes the authenticity of user satisfaction Reflect and network optimization support.

CN119031403AInactive Publication Date: 2024-11-26TSINGHUA UNIVERSITY +1
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411138398.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art is difficult to fully and truly understand wireless network user satisfaction. The traditional survey method is costly and has a low proportion of users, making it difficult to accurately reflect users' true perception of network functions.

Method used

By analyzing wireless service signaling data, the user's target service type poor quality event is determined, and the user's satisfaction is evaluated with hourly or day-sized granularity, and divided into normal state, unsatisfactory bud state and continuous dissatisfactory state, and the output is continuous For list of unsatisfied users, cluster users according to preset clustering rules to identify unsatisfied communities and users.

Benefits of technology

It realizes a comprehensive and objective assessment of user satisfaction, helps operators discover long-term low-perception users, conduct targeted network optimization and customer care, and improve overall user satisfaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119031403A_ABST
    Figure CN119031403A_ABST
Patent Text Reader

Abstract

The invention provides a method, a device and equipment for continuously evaluating the user satisfaction of a wireless network and a medium, and relates to the technical field of wireless network service operation and maintenance. In the embodiment of the invention, the target service type poor-quality event occurring in the user service process is determined based on the signaling data in the user wireless communication service process, the day-granularity user satisfaction evaluation is carried out, and the satisfaction state of the user is finally determined based on the continuous evaluation of the user satisfaction. Therefore, the user satisfaction can be evaluated comprehensively and objectively. In the embodiment of the invention, the satisfaction degree of the user is continuously evaluated, so that an operator can conveniently care the long-term low-perception user and solve problems, and the satisfaction degree of the whole user is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of wireless network service operation and maintenance, and in particular to a method, device, equipment and medium for continuously evaluating wireless network user satisfaction. Background Art

[0002] In the field of mobile communication network operation and maintenance, user satisfaction is a true reflection of the actual use of network functions by users. Communication network functions are mainly voice calls, video calls and data Internet access, so user perception also revolves around these functions. A comprehensive understanding of user satisfaction is conducive to more effective deployment of network resources to achieve better quality services.

[0003] At present, the main ways for operators to collect user satisfaction are telephone surveys, SMS surveys, offline channel surveys, online application surveys, and users actively reporting complaints and suggestions. These survey methods are costly, user satisfaction is greatly affected by tariffs and services, and the proportion of users covered is low, making it difficult to fully and truly understand user satisfaction. Summary of the invention

[0004] The embodiments of the present invention provide a method, an apparatus, a device and a medium for continuously evaluating user satisfaction of a wireless network, so as to accurately evaluate user satisfaction simply and conveniently.

[0005] A first aspect of an embodiment of the present invention provides a method for continuously evaluating user satisfaction of a wireless network, the method comprising: Analyze the wireless service signaling data of multiple users to determine the target service type quality event of each user; the target service type includes: at least one of voice service, Internet access service, and network coverage service; According to the target service quality deterioration events of each user on a certain day, determine the target service satisfaction of each user on that day; The satisfaction status of each user is determined according to the target business satisfaction of each user for a number of consecutive days.

[0006] Optionally, analyzing wireless service signaling data of multiple users to determine target service type poor quality events of each user includes: Analyze the wireless service signaling data of multiple users, calculate and output the target service type poor quality events of each user, and the output fields include at least: user identification, service type, poor quality event type, poor quality event start time, and poor quality event end time.

[0007] Optionally, according to the target service quality deterioration event of each user on a certain day, the target service satisfaction of each user on that day is determined, including: When the target service type is voice service, the first poor quality period is evaluated based on the output poor quality events of the target service of each user at an hourly granularity, and the first poor quality period is determined when the first preset number or more poor quality events of the voice service of the same user occur within one hour, and the voice service satisfaction of the corresponding user is evaluated based on the number of the first poor quality periods that occur for each user in a certain day; When the target service type is Internet access service, the second poor quality period is evaluated based on the output target service poor quality events of each user at an hourly granularity, and the second poor quality period is determined when the second preset number or more Internet access service poor quality events occur in the same user within one hour, and the Internet access service satisfaction of the corresponding user is evaluated based on the number of second poor quality periods that occur in each user within a certain day; When the target service type is network coverage service, evaluation is performed based on the output of each user's target service type poor quality events, and the network coverage service satisfaction of the corresponding user is evaluated according to the number of network coverage poor quality events that occur to the same user in one day.

[0008] Optionally, the satisfaction status includes: a normal state, a dissatisfaction embryonic state, and a persistent dissatisfaction state. The satisfaction status of each user is determined according to the target service satisfaction of each user for a number of consecutive days, including: If the user is satisfied with the target service for two consecutive days, the user's satisfaction status is marked as normal; if the user is dissatisfied with the target service for a certain day, the user's satisfaction status is marked as budding dissatisfied; the user marked as budding dissatisfied is continuously evaluated, and if the user is dissatisfied with the target service for two consecutive days, the user's satisfaction status is determined to be continuously dissatisfied; the user marked as continuously dissatisfied is continuously evaluated, and if the user is satisfied with the target service for four consecutive days, the user's satisfaction status is determined to be normal; Output a list of continuously dissatisfied users, where the output fields include at least: user identity, date when dissatisfaction first emerged, and date of latest dissatisfaction.

[0009] Optionally, the method further comprises: According to the list of continuously dissatisfied users, clustering users whose satisfaction status is continuously dissatisfied according to a preset clustering rule; Output clustering results; the output results at least include: dissatisfied cell identification, dissatisfied user number, dissatisfied voice service user number, dissatisfied Internet service user number, dissatisfied network coverage service user number, voice service poor quality incident number in the past week, Internet service poor quality incident number in the past week, network coverage service poor quality incident number in the past week; The preset clustering rule includes at least one of the following: clustering according to the base station cell to which the user belongs, and clustering according to the geographical location of the user.

[0010] A second aspect of an embodiment of the present invention provides a device for continuously evaluating user satisfaction of a wireless network, the device comprising: An analysis module, used to analyze wireless service signaling data of multiple users to determine the target service type quality event of each user; the target service type includes: at least one of voice service, Internet access service, and network coverage service; The satisfaction determination module is used to determine the target service satisfaction of each user on that day according to the target service poor quality events of each user on that day; The user status determination module is used to determine the satisfaction status of each user according to the target business satisfaction of each user for a number of consecutive days.

[0011] Optionally, the analysis module is specifically used to: Analyze the wireless service signaling data of multiple users, calculate and output the target service type poor quality events of each user, and the output fields include at least: user identification, service type, poor quality event type, poor quality event start time, and poor quality event end time.

[0012] Optionally, the satisfaction determination module is specifically used to: When the target service type is voice service, the first poor quality period is evaluated based on the output poor quality events of the target service of each user at an hourly granularity, and the first poor quality period is determined when the first preset number or more poor quality events of the voice service of the same user occur within one hour, and the voice service satisfaction of the corresponding user is evaluated based on the number of the first poor quality periods that occur for each user in a certain day; When the target service type is Internet access service, the second poor quality period is evaluated based on the output target service poor quality events of each user at an hourly granularity, and the second poor quality period is determined when the second preset number or more Internet access service poor quality events occur in the same user within one hour, and the Internet access service satisfaction of the corresponding user is evaluated based on the number of second poor quality periods that occur in each user within a certain day; When the target service type is network coverage service, evaluation is performed based on the output of each user's target service type poor quality events, and the network coverage service satisfaction of the corresponding user is evaluated according to the number of network coverage poor quality events that occur to the same user in one day.

[0013] Optionally, the satisfaction status includes: a normal status, a dissatisfaction budding status and a continuous dissatisfaction status, and the user status determination module is specifically used to: If the user is satisfied with the target service for two consecutive days, the user's satisfaction status is marked as normal; if the user is dissatisfied with the target service for a certain day, the user's satisfaction status is marked as budding dissatisfied; the user marked as budding dissatisfied is continuously evaluated, and if the user is dissatisfied with the target service for two consecutive days, the user's satisfaction status is determined to be continuously dissatisfied; the user marked as continuously dissatisfied is continuously evaluated, and if the user is satisfied with the target service for four consecutive days, the user's satisfaction status is determined to be normal; Output a list of continuously dissatisfied users, where the output fields include at least: user identity, date when dissatisfaction first emerged, and date of latest dissatisfaction.

[0014] Optionally, the device further comprises: A clustering module, configured to cluster users whose satisfaction status is a continuously dissatisfied state according to the continuously dissatisfied user list according to a preset clustering rule; An output module, used to output clustering results; the output results at least include: dissatisfied cell identification, number of dissatisfied users, number of dissatisfied voice service users, number of dissatisfied Internet service users, number of dissatisfied network coverage service users, number of voice service poor quality events in the past week, number of dissatisfied Internet service poor quality events in the past week, number of dissatisfied network coverage service poor quality events in the past week; The preset clustering rule includes at least one of the following: clustering according to the base station cell to which the user belongs, and clustering according to the geographical location of the user.

[0015] A third aspect of an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes, the steps in the method for continuously evaluating wireless network user satisfaction as described in the first aspect of the present invention are implemented.

[0016] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the method for continuously evaluating wireless network user satisfaction as described in the first aspect of the present invention.

[0017] The signaling data in the mobile network is an objective record of the voice and data service processes of users through the mobile network. By analyzing these signaling data, we can discover the quality of the user's service process and thus evaluate the user's real perception and satisfaction.

[0018] In the embodiment of the present invention, based on the signaling data of the user's wireless communication service process, the target service type quality event that occurs in the user's service process is determined, and the user satisfaction evaluation is performed at a daily granularity. Based on the continuous evaluation of user satisfaction, the user's satisfaction status is finally determined, thereby achieving a comprehensive and objective evaluation of user satisfaction. In the embodiment of the present invention, by continuously evaluating user satisfaction, it is also convenient for operators to care for and solve problems for long-term low-perception users, thereby improving overall user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0020] Figure 1 It is a schematic diagram of the steps of the method for continuously evaluating wireless network user satisfaction provided in an embodiment of the present invention; Figure 2 It is a schematic diagram of the steps of the method for continuously evaluating wireless network user satisfaction provided in an embodiment of the present invention; Figure 3 is a state machine diagram of a method for continuously evaluating user satisfaction of a wireless network provided in an embodiment of the present invention; Figure 4 It is a structural diagram of an apparatus for continuously evaluating wireless network user satisfaction provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0022] In order to comprehensively and objectively evaluate user satisfaction, an embodiment of the present invention proposes a method for continuously evaluating wireless network user satisfaction, which can count the poor quality events of the user's service process based on the signaling data of the user's wireless communication service process, and evaluate the user's real perception based on the poor quality events.

[0023] Specifically, an embodiment of the present invention provides a method for continuously evaluating user satisfaction of a wireless network, such as Figure 1 As shown, it shows a schematic flow chart of the steps of the method for continuous evaluation of wireless network user satisfaction provided in an embodiment of the present invention, the method comprising the following steps: S101, analyzing wireless service signaling data of multiple users to determine a target service type quality event of each user.

[0024] Specifically, the target service type includes: at least one of a voice service, an Internet access service, and a network coverage service.

[0025] Specifically, if some abnormal events of low service quality (collectively referred to as poor quality events) occur during the user's wireless service, it will seriously affect the user's perception. The embodiment of the present invention proposes to define the poor quality events of these service processes from three aspects: voice service, Internet service and network coverage service, and use signaling data to determine the poor quality events experienced by each user, so as to provide a basis for subsequent user satisfaction evaluation.

[0026] In the embodiment of the present invention, any mature and feasible method in the relevant technology can be used to obtain the user's wireless service signaling data.

[0027] In the embodiment of the present invention, the method can be applied to any terminal having the service signaling data processing authority and service signaling data processing capability.

[0028] In the embodiment of the present invention, poor quality events refer to service events in which the user can perceive low service quality during the wireless service process. For example, for voice services, poor quality events may include: VOLTE (Voice over Long-Term Evolution) voice call failure, ESRVCC (Enhanced Single RadioVoice Call Continuity) switching failure, VOLTE dropped calls, etc. For Internet access services, poor quality events may include: low rate bitrate ratio for video downloads, high latency for initial video buffering, low rate for video downloads, etc. For network coverage services, poor quality events may include: poor redirection quality, paging timeout, etc.

[0029] In the embodiment of the present invention, the three services of voice service, Internet access service and network coverage service can be analyzed separately, so as to perform operation and maintenance processing on the corresponding services in the later stage, or the three services can be analyzed at the same time, so as to perform operation and maintenance processing on the overall wireless service in the later stage.

[0030] S102, determining the target service satisfaction of each user on that day according to the target service poor quality event of each user on that day.

[0031] In the embodiment of the present invention, based on the target service poor quality events of each user on a certain day determined in step S101, the user's satisfaction with the target service of that day is evaluated, and the satisfaction score can be specifically given on a scale of 0-10.

[0032] In actual applications, technical personnel can set the relationship between the number of target business poor quality events and the target business satisfaction score in a day based on experience.

[0033] In the embodiment of the present invention, after the satisfaction score is determined, the user's satisfaction with the target service on that day may be determined based on the satisfaction score.

[0034] In the embodiment of the present invention, the target service satisfaction can be set as satisfied or dissatisfied. For example, the satisfaction score can be 0 to 10 points, and a score of 7 or above can be determined as satisfied, and 7 or below can be determined as dissatisfied.

[0035] S103, determining the satisfaction status of each user according to the target service satisfaction of each user for a plurality of consecutive days.

[0036] In an embodiment of the present invention, in step S102, the target service satisfaction of each user for each day can be determined based on the target service quality poor events that occur to each user every day, as the user's daily service satisfaction for the target service, and then based on the daily service satisfaction for multiple consecutive days, the user's satisfaction status can be determined. Therefore, the user's real perception can be determined by continuously evaluating the user's satisfaction. Specifically, the user's satisfaction with the target service on a certain day has a certain degree of randomness and cannot accurately reflect the user's real perception. Therefore, an embodiment of the present invention proposes to determine the satisfaction status of each user based on each user's target service satisfaction for multiple consecutive days, in order to discover mobile users with long-term low perception and help operators carry out network optimization and customer care work in a targeted manner.

[0037] The embodiment of the present invention also provides a method for continuously evaluating user satisfaction of a wireless network. Figure 2 As shown, it shows a schematic flow chart of another method for continuously evaluating wireless network user satisfaction provided in an embodiment of the present invention, the method comprising the following steps: S201, analyzing wireless service signaling data of multiple users, calculating and outputting the target service type poor quality events of each user, wherein the output fields include at least: user identification, service type, poor quality event type, poor quality event start time, and poor quality event end time.

[0038] Specifically, in an embodiment of the present invention, MR (Measurement Report), HTTP call records, MME (Mobility Management Entity) call records and video service call records of a certain target area can be accessed, and poor quality events are calculated and output for each user included in the area based on Table 1. The output fields specifically include: user identity (desensitized), service type, poor quality event type, poor quality start time, poor quality end time, etc.

[0039] In actual application, the target area can be determined according to operation and maintenance requirements. For example, the target area can be an area divided according to geographical areas, such as a village, a school, a shopping mall, a residential community, etc. It can also be a base station cell divided according to base stations, or it can be a building divided according to buildings.

[0040] Table 1. Definition of low perceived quality events

[0041] S202, determining the target service satisfaction of each user on that day according to the target service poor quality event of each user on that day.

[0042] In the embodiment of the present invention, the target service satisfaction of the user can be determined based on three service types, namely, voice service, Internet access service and network coverage service, with each service type having a day as the granularity.

[0043] In the embodiment of the present invention, the analysis can be specifically performed based on the user identification, service type, poor quality event type, poor quality event start time and poor quality event end time in the poor quality event output field in the above step S201 to determine the target service satisfaction of each user on a certain day. Specifically, the poor quality events generated by a certain user in a day can be obtained based on the user identification, poor quality event start time and poor quality event end time in the poor quality event output field, and then the poor quality events corresponding to the target service type can be determined based on the service type in the poor quality event output field.

[0044] Specifically, the step S202 may include three situations: S202A, S202B and S202C: S202A, when the target service type is voice service, the first poor quality period is evaluated based on the output poor quality events of the target service of each user at an hourly granularity, and the first poor quality period is determined when the first preset number or more of voice service poor quality events occur in the same user within an hour. The voice service satisfaction of the corresponding user is evaluated based on the number of first poor quality periods that occur for each user in a certain day.

[0045] In the embodiment of the present invention, the satisfaction evaluation can be expressed as a score of 0 to 10. In actual applications, the technical personnel can set the corresponding relationship between the number of poor quality time periods and the score according to actual needs.

[0046] In the embodiment of the present invention, the first poor quality period evaluation may be performed based on the poor quality event start time and the poor quality event end time in the poor quality event output field.

[0047] In the embodiment of the present invention, the first preset number is a positive integer and can be determined according to actual needs. For example, the first preset number is determined to be 2. In the process of determining the voice service satisfaction, the first poor quality period can be evaluated at an hourly granularity. Two or more poor quality events for the same user within an hour are defined as a poor quality period. Then, the satisfaction score is scored according to the number of poor quality periods that occur in a day. The specific scoring rules are shown in Table 2: Table 2. Voice satisfaction rating rules

[0048] S202B, when the target service type is Internet access service, a second poor quality period evaluation is performed based on the output of each user's target service poor quality events at an hourly granularity, and a second poor quality period is determined when a second preset number or more of Internet access service poor quality events occur for the same user within an hour. Internet access service satisfaction evaluation is performed on the corresponding user based on the number of second poor quality periods that occur for each user in a certain day.

[0049] In the embodiment of the present invention, the second poor quality period evaluation may be performed based on the poor quality event start time and the poor quality event end time in the poor quality event output field.

[0050] In the embodiment of the present invention, the second poor quality period evaluation can also be first performed at the hourly granularity for the Internet service satisfaction. Specifically, the second preset number (for example, 8) or more poor quality events generated by the same user within one hour, and the proportion greater than the preset value (for example, 3%) (the numerator is the number of poor quality call orders of the user within one hour, and the denominator is the number of all call orders of the user within one hour) can be defined as the poor quality period, and then the satisfaction score is performed according to the number of poor quality periods occurring in a day. The specific scoring rules are shown in Table 3: Table 3. Internet Satisfaction Rating Rules

[0051] S202C, when the target service type is network coverage service, evaluation is performed based on the output target service type poor quality events of each user, and network coverage service satisfaction of the corresponding user is evaluated according to the number of network coverage poor quality events that occur to the same user in one day.

[0052] In the embodiment of the present invention, the satisfaction rating of the network coverage service can be directly scored at the daily granularity. The specific scoring rules are shown in Table 4: Table 4. Network coverage satisfaction rating rules Network coverage service satisfaction Number of poor quality events 10 [0,3] 9 (3,8] 8 (8,15] 7 (15,20] 6 (20,25] 5 (25,30] 4 (30,35] 3 (35,40] 2 (40,45] 1 (45,∞] In the embodiment of the present invention, considering that the service quality of voice services and Internet services may be affected by accidental factors and cause large fluctuations, if the voice services and Internet services are simply evaluated at a daily granularity, the evaluation results are easily affected by accidental factors. For example, suppose that due to sudden factors in a certain hour, a large number of poor quality events are generated for the relevant users in this period, but the corresponding problems have been solved in time on the same day, and only a small number of poor quality events are generated in the subsequent business processes of the same day. If the user satisfaction is simply evaluated based on the number of poor quality events in a day at a daily granularity, the user satisfaction will be evaluated too low due to the large number of poor quality events generated in one hour, and it will not accurately reflect the user's true perception. The method proposed in the embodiment of the present invention is used to evaluate the voice service satisfaction and Internet service satisfaction at an hourly granularity, which can effectively prevent the evaluation results from being affected by similar accidental factors.

[0053] In the embodiment of the present invention, it is also considered that the network coverage service is usually not affected by accidental factors and is not prone to large fluctuations. Therefore, it is proposed that user satisfaction evaluation can be directly performed on a daily basis for the network coverage service to simplify the evaluation process. Of course, a method similar to the voice service satisfaction evaluation and the Internet service satisfaction evaluation can also be used to evaluate the network coverage service satisfaction on an hourly basis.

[0054] In the embodiment of the present invention, user satisfaction can be evaluated based on each service type to obtain the corresponding satisfaction, so as to perform targeted maintenance on the corresponding service type in the subsequent operation and maintenance process. The three service types can also be combined to obtain a comprehensive user satisfaction evaluation to find users with low comprehensive perception, so as to help operators carry out targeted network optimization and customer care work.

[0055] For example, for the three individual satisfaction evaluations of voice service satisfaction, Internet service satisfaction, and network coverage service satisfaction, if the satisfaction score is 7 points or below, it is considered unsatisfied, otherwise it is considered satisfied.

[0056] In the embodiment of the present invention, the scoring results of the three dimensions of voice service satisfaction, Internet service satisfaction, and network coverage service satisfaction can also be summarized, and the total satisfaction score of each user is obtained by summing them up, and the satisfaction degree is divided according to the total satisfaction score. Specifically, the rules for evaluating user satisfaction by comprehensively evaluating the three service types are shown in Table 5 below: Table 5. Comprehensive satisfaction evaluation rules

[0057] In the embodiment of the present invention, the user satisfaction rating results can be divided according to actual needs. The user satisfaction can be simply divided into satisfied and dissatisfied, or divided into very satisfied, satisfied, dissatisfied and extremely dissatisfied.

[0058] In the embodiment of the present invention, after determining the target service satisfaction of the user on a certain day, the user satisfaction can be output, and the output fields at least include: user identification, target service satisfaction and date.

[0059] S203: Determine the satisfaction status of each user according to the target service satisfaction of each user for a number of consecutive days.

[0060] Specifically, the satisfaction status includes: a normal state, a budding state of dissatisfaction, and a persistent state of dissatisfaction.

[0061] In the embodiment of the present invention, the satisfaction status of each user may be determined according to the user identification, target service satisfaction and date output in step S202 and the target service satisfaction of each user for a number of consecutive days.

[0062] Specifically, step S203 includes the following sub-steps: S2031, when the user is satisfied with the target service for two consecutive days, mark the user's satisfaction status as normal; when the user is dissatisfied with the target service for a certain day, mark the user's satisfaction status as dissatisfied budding; continuously evaluate the user marked as dissatisfied budding, and when the user is dissatisfied with the target service for two consecutive days, determine the user's satisfaction status as continuously dissatisfied; continuously evaluate the user marked as continuously dissatisfied, and when the user is satisfied with the target service for four consecutive days, determine the user's satisfaction status as normal.

[0063] From the perspective of long-term analysis of user satisfaction in the embodiments of the present invention, the user satisfaction status can be divided into a normal state, a budding state of dissatisfaction, and a continuously dissatisfied state. The normal state indicates that the user continuously perceives well and is satisfied with the wireless network; the budding state of dissatisfaction indicates that the user occasionally has poor network perception in the last one or two days, and the continuously dissatisfied state indicates that the user has poor network perception for many consecutive days. Operators need to attach great importance to it, take corresponding measures to solve network problems, improve user perception, and improve the user satisfaction status to a normal state.

[0064] For example, the satisfaction results of users for the target service include: extremely dissatisfied, dissatisfied, satisfied, and very satisfied. For example, the state machine of the three states is as follows: Figure 3As shown, specifically, for the target business type, if the satisfaction level of user A on a certain day is dissatisfied or extremely dissatisfied, the satisfaction status of user A is marked as dissatisfied budding state; if the satisfaction level of user A marked as dissatisfied budding state is very satisfied or satisfied for two consecutive days, the satisfaction status of user A is marked as normal state; if the satisfaction level of user A marked as dissatisfied budding state is dissatisfied or extremely dissatisfied for two consecutive days, the satisfaction status of user A is marked as continuously dissatisfied state; after being marked as continuously dissatisfied state, the satisfaction level of user A continues to be evaluated; if the satisfaction level of user A marked as continuously dissatisfied state is very satisfied or satisfied for 4 consecutive days, the satisfaction status of user A is marked as normal state.

[0065] S2032, output a list of continuously dissatisfied users, where the output fields include at least: user identity, dissatisfaction initiation date, and latest dissatisfaction date.

[0066] In the embodiment of the present invention, outputting a list of continuously dissatisfied users can help operators find users with continuously low perception, so as to carry out operation and maintenance work in a targeted manner. In the embodiment of the present invention, outputting the dissatisfaction embryonic date and the latest dissatisfaction date can also help operators find users with long-term low perception, so as to carry out customer care work in a targeted manner.

[0067] S204: Based on the list of continuously dissatisfied users, cluster the users whose satisfaction status is continuously dissatisfied according to a preset clustering rule.

[0068] Specifically, the preset clustering rule includes at least one of the following: clustering according to the base station cell to which the user belongs, and clustering according to the geographical location of the user.

[0069] In the embodiment of the present invention, the identity of the dissatisfied user can be determined according to the dissatisfied user list output in step S2032, and then the base station cell to which the user belongs and / or the geographical location of the user (for example, the building where the user is located) can be obtained. Then, the continuously dissatisfied users can be clustered based on the base station cell to which the user belongs and / or the geographical location of the user.

[0070] In the embodiment of the present invention, the operator can directly take the continuously dissatisfied users as the starting point and carry out network optimization work on a user-by-user basis.

[0071] In the embodiment of the present invention, considering that there are a huge number of continuously dissatisfied users and the network optimization resources are relatively limited, it is difficult to cover all the continuously dissatisfied users at one time. It is further proposed to aggregate and cluster the continuously dissatisfied users. Specifically, the aggregation and clustering can be performed based on the top three base station cells with the largest number of poor quality events. The clustering algorithm is described as follows using SQL statements: select eci as Unsatisfied Cell ECI, count(1) as Unsatisfied Users, sum(Is Coverage Unsatisfied) as Unsatisfied Coverage Users, sum(Is Internet Access Unsatisfied) as Unsatisfied Internet Users, sum(Is Voice Unsatisfied) as Unsatisfied Voice Users, sum(Poor Coverage Quality Events in the Last Week) as Poor Coverage Quality Events in the Last Week, sum(Poor Voice Quality Events in the Last Week) as Poor Voice Quality Events in the Last Week, sum(Poor Internet Quality Events in the Last Week) as Poor Internet Quality Events in the Last Week from ( select user identity, case when the average voice satisfaction score in the last week is <8 then 1else 0 as whether the voice is dissatisfied, case when the average Internet satisfaction score in the last week is <8 then 1 else 0as whether the Internet is dissatisfied, case when the average coverage satisfaction score in the last week is <8 then 1 else 0 as whether the coverage is dissatisfied, number of abnormal events top1 cell ECI as eci, number of poor coverage events in the last week in the top1 cell as number of poor coverage events in the last week, number of poor voice events in the last week in the top1 cell as number of poor coverage events in the last week, number of poor Internet access events in the last week in the top1 cell as number of poor coverage events in the last week union all select user identity, case when the average voice satisfaction score in the last week is <8 then 1else 0 as whether the voice is not satisfied, case when the average Internet satisfaction score in the last week is <8 then 1 else 0as whether the Internet is not satisfied, case when the average coverage satisfaction score in the last week is <8 then 1 else 0 as whether the coverage is not satisfied, number of abnormal events top2 cells ECI as eci, number of poor coverage events in the top2 cells in the last week, number of poor voice events in the top2 cells in the last week, number of poor Internet quality events in the top2 cells in the last week union all select user identity, case when the average voice satisfaction score in the last week is <8 then 1else 0 as whether the voice is not satisfied, case when the average Internet satisfaction score in the last week is <8 then 1 else 0as whether the Internet is not satisfied, case when the average coverage satisfaction score in the last week is <8 then 1 else 0 as whether the coverage is not satisfied, number of abnormal events top3 cells ECI as eci, number of poor coverage events in the top3 cells in the last week, number of poor voice events in the top3 cells in the last week, number of poor Internet quality events in the top3 cells in the last week ) group by eci.

[0072] S205: Output the clustering result.

[0073] Specifically, the output results include at least: dissatisfied cell identification, number of dissatisfied users, number of dissatisfied voice service users, number of dissatisfied Internet service users, number of dissatisfied network coverage service users, number of poor voice service quality events in the past week, number of poor Internet service quality events in the past week, and number of poor network coverage service quality events in the past week.

[0074] In the embodiment of the present invention, the number of continuously dissatisfied users in each cell can be obtained by clustering and counting the cells, and the output results include: dissatisfied cell ECI, number of dissatisfied users, number of dissatisfied coverage users, number of dissatisfied Internet users, number of dissatisfied voice users, number of poor coverage quality events in the last week, number of poor voice quality events in the last week, and number of poor Internet quality events in the last week. Then, in units of weeks, the number of continuously dissatisfied users is sorted in descending order, and a certain number of cells are selected each week to carry out network optimization work. It is also possible to refer to the algorithm for cell clustering, and further cluster dissatisfied users according to buildings (property points) according to the corresponding relationship between buildings (property points) and base station cells, and then use buildings (property points) as a starting point to solve the problems of all continuously dissatisfied users in a property point at one time, greatly improving the pertinence and work efficiency of network optimization work.

[0075] Based on the same inventive concept, an eight-base Huffman compression rotary encoding device is also provided in the embodiment of the present invention. Figure 4 As shown, it shows a schematic diagram of the structure of a device for continuously evaluating wireless network user satisfaction, the device comprising: The analysis module 401 is used to analyze the wireless service signaling data of multiple users to determine the target service type quality event of each user; the target service type includes: at least one of voice service, Internet access service, and network coverage service; The satisfaction determination module 402 is used to determine the target service satisfaction of each user on that day according to the target service quality deterioration events of each user on that day; The user status determination module 403 is used to determine the satisfaction status of each user according to the target service satisfaction of each user for a number of consecutive days.

[0076] Optionally, the analysis module 401 is specifically used to: Analyze the wireless service signaling data of multiple users, calculate and output the target service type poor quality events of each user, and the output fields include at least: user identification, service type, poor quality event type, poor quality event start time, and poor quality event end time.

[0077] Optionally, the satisfaction determination module 402 is specifically configured to: When the target service type is voice service, the first poor quality period is evaluated based on the output poor quality events of the target service of each user at an hourly granularity, and the first poor quality period is determined when the first preset number or more poor quality events of the voice service of the same user occur within one hour, and the voice service satisfaction of the corresponding user is evaluated based on the number of the first poor quality periods that occur for each user in a certain day; When the target service type is Internet access service, the second poor quality period is evaluated based on the output target service poor quality events of each user at an hourly granularity, and the second poor quality period is determined when the second preset number or more Internet access service poor quality events occur in the same user within one hour, and the Internet access service satisfaction of the corresponding user is evaluated based on the number of second poor quality periods that occur in each user within a certain day; When the target service type is network coverage service, evaluation is performed based on the output of each user's target service type poor quality events, and the network coverage service satisfaction of the corresponding user is evaluated according to the number of network coverage poor quality events that occur to the same user in one day.

[0078] Optionally, the satisfaction status includes: a normal status, a dissatisfaction budding status and a continuous dissatisfaction status. The user status determination module 403 is specifically used to: If the user is satisfied with the target service for two consecutive days, the user's satisfaction status is marked as normal; if the user is dissatisfied with the target service for a certain day, the user's satisfaction status is marked as budding dissatisfied; the user marked as budding dissatisfied is continuously evaluated, and if the user is dissatisfied with the target service for two consecutive days, the user's satisfaction status is determined to be continuously dissatisfied; the user marked as continuously dissatisfied is continuously evaluated, and if the user is satisfied with the target service for four consecutive days, the user's satisfaction status is determined to be normal; Output a list of continuously dissatisfied users, where the output fields include at least: user identity, date when dissatisfaction first emerged, and date of latest dissatisfaction.

[0079] Optionally, the device further comprises: A clustering module, configured to cluster users whose satisfaction status is a continuously dissatisfied state according to the continuously dissatisfied user list according to a preset clustering rule; An output module, used to output clustering results; the output results at least include: dissatisfied cell identification, number of dissatisfied users, number of dissatisfied voice service users, number of dissatisfied Internet service users, number of dissatisfied network coverage service users, number of voice service poor quality events in the past week, number of dissatisfied Internet service poor quality events in the past week, number of dissatisfied network coverage service poor quality events in the past week; The preset clustering rule includes at least one of the following: clustering according to the base station cell to which the user belongs, and clustering according to the geographical location of the user.

[0080] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0081] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0082] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (apparatus), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0083] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0084] These computer program instructions can also be loaded onto a computer or other programmable terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0085] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0086] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0087] The above is a detailed introduction to a method, device, equipment and medium for continuous evaluation of wireless network user satisfaction provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for continuously evaluating user satisfaction of a wireless network, characterized in that: The method comprises: Analyze the wireless service signaling data of multiple users to determine the target service type quality event of each user; the target service type includes: at least one of voice service, Internet access service, and network coverage service; According to the target service quality deterioration events of each user on a certain day, determine the target service satisfaction of each user on that day; The satisfaction status of each user is determined according to the target business satisfaction of each user for a number of consecutive days.

2. The method for continuously evaluating wireless network user satisfaction according to claim 1, characterized in that: Analyze the wireless service signaling data of multiple users to determine the target service type quality events of each user, including: Analyze the wireless service signaling data of multiple users, calculate and output the target service type poor quality events of each user, and the output fields include at least: user identification, service type, poor quality event type, poor quality event start time, and poor quality event end time.

3. The method for continuously evaluating wireless network user satisfaction according to claim 2, characterized in that: Based on the target service quality deterioration events of each user on a certain day, determine the target service satisfaction of each user on that day, including: When the target service type is voice service, the first poor quality period is evaluated based on the output poor quality events of the target service of each user at an hourly granularity, and the first poor quality period is determined when the first preset number or more poor quality events of the voice service of the same user occur within one hour, and the voice service satisfaction of the corresponding user is evaluated based on the number of the first poor quality periods that occur for each user in a certain day; When the target service type is Internet access service, the second poor quality period is evaluated based on the output target service poor quality events of each user at an hourly granularity, and the second poor quality period is determined when the second preset number or more Internet access service poor quality events occur in the same user within one hour, and the Internet access service satisfaction of the corresponding user is evaluated based on the number of second poor quality periods that occur in each user within a certain day; When the target service type is network coverage service, evaluation is performed based on the output of each user's target service type poor quality events, and the network coverage service satisfaction of the corresponding user is evaluated according to the number of network coverage poor quality events that occur to the same user in one day.

4. The method for continuously evaluating wireless network user satisfaction according to claim 3, characterized in that: The satisfaction status includes: normal status, budding dissatisfaction status and persistent dissatisfaction status. The satisfaction status of each user is determined according to the target service satisfaction of each user for multiple consecutive days, including: If the user is satisfied with the target service for two consecutive days, the user's satisfaction status is marked as normal; if the user is dissatisfied with the target service for a certain day, the user's satisfaction status is marked as budding dissatisfied; the user marked as budding dissatisfied is continuously evaluated, and if the user is dissatisfied with the target service for two consecutive days, the user's satisfaction status is determined to be continuously dissatisfied; the user marked as continuously dissatisfied is continuously evaluated, and if the user is satisfied with the target service for four consecutive days, the user's satisfaction status is determined to be normal; Output a list of continuously dissatisfied users, where the output fields include at least: user identity, date when dissatisfaction first emerged, and date of latest dissatisfaction.

5. The method for continuously evaluating wireless network user satisfaction according to claim 4, characterized in that: The method further comprises: According to the list of continuously dissatisfied users, clustering users whose satisfaction status is continuously dissatisfied according to a preset clustering rule; Output clustering results; the output results at least include: dissatisfied cell identification, dissatisfied user number, dissatisfied voice service user number, dissatisfied Internet service user number, dissatisfied network coverage service user number, voice service poor quality incident number in the past week, Internet service poor quality incident number in the past week, network coverage service poor quality incident number in the past week; The preset clustering rule includes at least one of the following: clustering according to the base station cell to which the user belongs, and clustering according to the geographical location of the user.

6. A device for continuously evaluating user satisfaction of a wireless network, characterized in that: The device comprises: An analysis module, used to analyze wireless service signaling data of multiple users to determine the target service type quality event of each user; the target service type includes: at least one of voice service, Internet access service, and network coverage service; The satisfaction determination module is used to determine the target service satisfaction of each user on that day according to the target service poor quality events of each user on that day; The user status determination module is used to determine the satisfaction status of each user according to the target business satisfaction of each user for a number of consecutive days.

7. The device for continuously evaluating wireless network user satisfaction according to claim 6, characterized in that: The analysis module is specifically used for: Analyze the wireless service signaling data of multiple users, calculate and output the target service type poor quality events of each user, and the output fields include at least: user identification, service type, poor quality event type, poor quality event start time, and poor quality event end time.

8. The device for continuously evaluating wireless network user satisfaction according to claim 7, characterized in that: The satisfaction determination module is specifically used for: When the target service type is voice service, the first poor quality period is evaluated based on the output poor quality events of the target service of each user at an hourly granularity, and the first poor quality period is determined when the first preset number or more poor quality events of the voice service of the same user occur within one hour, and the voice service satisfaction of the corresponding user is evaluated based on the number of the first poor quality periods that occur for each user in a certain day; When the target service type is Internet access service, the second poor quality period is evaluated based on the output target service poor quality events of each user at an hourly granularity, and the second poor quality period is determined when the second preset number or more Internet access service poor quality events occur in the same user within one hour, and the Internet access service satisfaction of the corresponding user is evaluated based on the number of second poor quality periods that occur in each user within a certain day; When the target service type is network coverage service, evaluation is performed based on the output of each user's target service type poor quality events, and the network coverage service satisfaction of the corresponding user is evaluated according to the number of network coverage poor quality events that occur to the same user in one day.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for continuously evaluating wireless network user satisfaction described in any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for continuously evaluating wireless network user satisfaction described in any one of claims 1 to 5 are implemented.

Citation Information

Patent Citations

  • Mobile network user communication quality monitoring system

    CN103002479A

  • Method and system for positioning wireless quality problem

    CN105873113A

  • Service optimization method and device based on user perception, equipment and storage medium

    CN113543178A

  • Early warning user determination method and device for 5G voice service, equipment and storage medium

    CN116582867A

  • User perception evaluation method and device and computer readable storage medium

    CN116634485A