Account management method and system in telecom operation management system

Abstract

The invention discloses an account management method and system in a telecom operation management system, and relates to the technical field of telecom operation, and the method comprises the following steps: obtaining the basic information of all accounts in the telecom operation management system, analyzing the activeness data change rate of all accounts at different business operation moments according to the basic information to obtain an account activeness change rate data set; counting business scene type sets corresponding to all the accounts, and extracting association influence coefficients among the accounts under different business scene types to obtain an account association influence coefficient set; screening out target service scene type data from the service scene type set, screening out maximum activeness data of all accounts in each service scene, and screening out a normal activeness change rate from the account activeness change rate data set; the method has the advantages that potential account security problems can be found and processed in time through accurate planning and management of account operation time results.

Description

An account management method and system in a telecommunications operation management system Technical Field

[0001] This invention relates to the field of telecommunications operation technology, and more specifically, to an account management method and system in a telecommunications operation management system. Background Technology

[0002] In today's digital age, telecommunications operation and management systems bear the responsibility of managing massive numbers of accounts, and their efficient and stable operation is crucial. With the diversification of telecommunications services and the increasing complexity of user needs, traditional account management methods face numerous challenges. Traditional account management methods often employ uniform standards and processes, making it difficult to accommodate the differences in various business scenarios. This can lead to either overly lenient account management in some scenarios, failing to promptly detect and handle abnormally active accounts that disrupt normal business operations, or overly strict account management in others, restricting normal user access and reducing user experience.

[0003] Because telecommunications services are not isolated but closely interconnected, for example, increased activity in mobile data traffic can drive the use of value-added services such as video and music; broadband internet access is also interconnected with the network communication services of smart home devices. However, traditional account management does not fully consider this interconnected impact. When account activity changes within a service scenario, it's impossible to accurately assess its ripple effects on related service scenarios, and it's difficult to formulate collaborative management strategies. For instance, when data traffic activity surges due to promotional activities, the potential for changes in video value-added service activity is not considered, leading to disconnects in resource allocation and service assurance, impacting user experience and business revenue. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the purpose of this invention is to provide an account management method and system in a telecommunications operation and management system.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] An account management method in a telecommunications operation and management system, the method comprising the following steps:

[0007] Step S1: Obtain the basic information of all accounts in the telecommunications operation management system, and analyze the rate of change of activity data of all accounts at different business operation times based on the basic information to obtain the account activity rate change data dataset.

[0008] Step S2: Calculate the set of business scenario types corresponding to all accounts, and extract the set of account association influence coefficients by analyzing the association influence coefficients between accounts under different business scenario types.

[0009] Step S3: Filter out the target business scenario type data from the business scenario type set, and filter out the maximum activity data of all accounts in each business scenario. Filter out the normal activity change rate from the account activity change rate dataset.

[0010] Step S4: Based on the target business scenario type data and the normal activity change rate, determine the first duration required to adjust the maximum activity data to the preset reasonable activity range;

[0011] Step S5: Filter out the business scenario type data to be processed from the business scenario type set, predict the association impact activity data one based on the association impact coefficient in the account association impact coefficient set, and determine the second duration required to adjust the association impact activity data one to a preset reasonable activity range based on the business scenario type data to be processed and the association impact activity data one.

[0012] Step S6: Systematically manage all accounts based on the first duration, the second duration, and the business scenario being processed, and output the account management results.

[0013] Preferably, step S1 specifically includes the following steps:

[0014] Obtain basic information of all accounts in the telecommunications operation management system, and divide the telecommunications operation services into corresponding business scenarios based on the basic information of all accounts to obtain a set of business scenario types.

[0015] Based on the business scenario type set, the activity data set of each account under the corresponding business scenario at different historical business operation times is statistically analyzed. The activity change rate is obtained by calculating the activity change magnitude of each data in the activity data set at adjacent times. Based on the activity change rate, the account activity change rate dataset is output.

[0016] Preferably, step S2 specifically includes the following steps:

[0017] Obtain the account activity dataset for each business scenario type at the current business operation time based on the business scenario type set;

[0018] After calculating the proportion of each business scenario type in the total system business, output the business scenario type proportion dataset.

[0019] Based on the business scenario type proportion dataset and the business scenario type set, the correlation coefficients between account activity under each business scenario are extracted, and then the set of account correlation coefficients is output.

[0020] Preferably, step S3 specifically includes the following steps:

[0021] A first activity warning threshold is preset, and an activity dataset to be processed is selected from the account activity dataset that is greater than or equal to the first activity warning threshold;

[0022] Based on the pending activity dataset, a set of pending business scenarios is selected from the corresponding business scenario type set;

[0023] When there are business relationships between the business scenarios to be processed in the set of business scenarios to be processed, the data with the highest activity level is selected from the data of activity levels to be processed.

[0024] Based on the maximum activity data, select the corresponding priority processing business scenarios from the set of pending business scenarios;

[0025] Based on the priority business scenarios, filter out the target business scenario type data from the corresponding business scenario type set;

[0026] Based on the priority business scenario, normal activity change rates are selected from the corresponding account activity change rate dataset.

[0027] Preferably, step S4 specifically includes the following steps:

[0028] Preset account management strategies based on the first activity warning threshold;

[0029] The system presets reasonable upper and lower limits for activity levels. Based on the target business scenario type data and the normal activity change rate, it calculates the time required for the maximum activity data to be adjusted to the preset reasonable activity range under the account management strategy, and then outputs the first duration. The reasonable upper limit for activity is greater than the maximum activity data, and the reasonable lower limit for activity is less than the maximum activity data.

[0030] Preferably, step S5 specifically includes the following steps:

[0031] Based on the priority processing business scenarios, the delayed processing business scenarios that are related to the priority processing business scenarios are selected from the set of pending business scenarios.

[0032] Based on the delayed processing business scenario, extract the pending activity data from the pending activity dataset, and extract the pending business scenario type percentage data from the business scenario type percentage dataset.

[0033] Based on the operational information of all accounts in delayed and priority processing business scenarios, the corresponding association impact coefficients are filtered out from the account association impact coefficient set.

[0034] Based on the first activity warning threshold and the correlation influence coefficient, the activity value of the activity data to be processed after the first time period is predicted to have an impact on the change of activity value, thus obtaining the first correlation influence activity data;

[0035] Based on the proportion of business scenario types to be processed and the associated impact activity data, the predicted duration of the associated impact activity data is then adjusted to a preset reasonable activity range under the influence of account management strategies, and the second duration is output.

[0036] Preferably, step S6 specifically includes the following steps:

[0037] The predicted duration set is output after predicting the time required for the activity level of accounts in other business scenarios within the scope of the business scenarios to be processed to be adjusted to a preset reasonable activity level range under the effect of account management strategies.

[0038] The first time point is the operation time point of the first account corresponding to the priority processing business scenario for all accounts; where the first account is the operation account involved in the priority processing business scenario.

[0039] The required duration is obtained by summing the first duration and the second duration. The second time point is calculated after the required duration has elapsed from the first time point. The second time point is the second account operation time point corresponding to all accounts in the delayed processing business scenario. The second account is the operation account involved in the delayed processing business scenario.

[0040] The third time point is obtained by predicting the operation time point of the third account corresponding to all accounts in other business scenarios based on the prediction duration set; wherein, the third account is the operation account involved in business scenarios other than priority processing business scenarios and delayed processing business scenarios in the business scenario type set.

[0041] The first time point, the second time point, and the third time point are combined to form the account operation time result;

[0042] Based on the account operation time results and account management strategies, the system manages all accounts in the telecommunications operation management system and outputs the account management results.

[0043] An account management system in a telecommunications operation management system includes:

[0044] Acquisition Module: Acquires basic information of all accounts in the telecommunications operation management system, and analyzes the rate of change of activity data of all accounts at different business operation times based on the basic information to obtain the account activity rate change data dataset;

[0045] Extraction module: Statistically analyzes the business scenario type set corresponding to all accounts, and extracts the association influence coefficient between accounts under different business scenario types to obtain the account association influence coefficient set;

[0046] Filtering module: Filters out target business scenario type data from the business scenario type set, filters out the maximum activity data of all accounts in each business scenario, and filters out the normal activity change rate from the account activity change rate dataset.

[0047] First judgment module: Based on the target business scenario type data and the normal activity change rate, determine the first duration required to adjust the maximum activity data to a preset reasonable activity range;

[0048] The second judgment module: filters out the business scenario type data to be processed from the business scenario type set, predicts the association impact activity data one based on the association impact coefficient set of the account association impact coefficient set, and judges the second time required to adjust the association impact activity data one to a preset reasonable activity range based on the business scenario type data to be processed and the association impact activity data one.

[0049] Management module: Systematically manages all accounts based on the first duration, the second duration, and the business scenario, and outputs the account management results.

[0050] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement an account management method in a telecommunications operation management system.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] This technical solution acquires basic information about all accounts in the telecommunications operation management system and deeply analyzes the rate of change of account activity data at different business operation times, forming an account activity change rate dataset. This allows managers to accurately understand the activity dynamics of each account in different business scenarios, moving beyond a general understanding of account status. The solution statistically analyzes the business scenario types corresponding to all accounts and extracts the correlation coefficients between accounts under different business scenario types, resulting in an account correlation coefficient set. This helps to discover potential relationships between business scenarios and accounts. By setting activity warning thresholds, key information such as target business scenario type data, maximum activity data, and normal activity change rate can be filtered out, and the initial time required to adjust the maximum activity data to a preset reasonable activity range can be determined. This data-driven approach to accurately predict adjustment time allows managers to rationally allocate the timing and intensity of management resource investment. For example, if an abnormal increase in the activity of a certain account is predicted and a period of adjustment to a reasonable range is needed, human and technical resources can be planned in advance for monitoring and intervention during that period to avoid blind resource allocation and waste, thus improving resource utilization efficiency. For data related to activity levels, the system can also predict the second duration required to adjust it to a preset reasonable activity range. When handling delayed business scenarios associated with priority business scenarios, it can coordinate the allocation of management resources for different business scenarios based on accurate duration predictions. For example, when adjusting the activity levels associated with call services and related value-added services, resources can be allocated reasonably to ensure efficient use of resources to achieve reasonable control of account activity in different business scenarios.

[0053] This application, through precise planning and management of account operation time results, can promptly identify and address potential account security issues. For example, when it is predicted that changes in the activity of certain accounts may pose security risks, corresponding security policies can be set in advance, such as strengthening identity verification and restricting certain operational permissions of abnormally active accounts, thereby improving system security. The multi-dimensional data and precise analysis results provided by this technical solution offer a scientific basis for telecommunications operators to make decisions. Managers can rationally plan business development directions and resource allocation strategies based on information such as the rate of change in account activity, correlation coefficients, and management duration for various business scenarios. Attached Figure Description

[0054] Figure 1 is a flowchart illustrating an account management method in a telecommunications operation management system proposed in this invention;

[0055] Figure 2 is a schematic diagram of the modules of the account management system in the telecommunications operation management system proposed in this invention;

[0056] Figure 3 is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0057] Referring to Figure 1, Embodiment 1 further illustrates an account management method in a telecommunications operation management system proposed in this invention.

[0058] An account management method in a telecommunications operation and management system, the method comprising the following steps:

[0059] Step S1: Obtain the basic information of all accounts in the telecommunications operation management system, and analyze the rate of change of activity data of all accounts at different business operation times based on the basic information to obtain the account activity rate change data dataset.

[0060] Step S2: Calculate the set of business scenario types corresponding to all accounts, and extract the set of account association influence coefficients by analyzing the association influence coefficients between accounts under different business scenario types.

[0061] Step S3: Filter out the target business scenario type data from the business scenario type set, and filter out the maximum activity data of all accounts in each business scenario. Filter out the normal activity change rate from the account activity change rate dataset.

[0062] Step S4: Based on the target business scenario type data and the normal activity change rate, determine the first duration required to adjust the maximum activity data to the preset reasonable activity range;

[0063] Step S5: Filter out the business scenario type data to be processed from the business scenario type set, predict the association impact activity data one based on the association impact coefficient in the account association impact coefficient set, and determine the second duration required to adjust the association impact activity data one to a preset reasonable activity range based on the business scenario type data to be processed and the association impact activity data one.

[0064] Step S6: Systematically manage all accounts based on the first duration, the second duration, and the business scenario being processed, and output the account management results.

[0065] This application first obtains basic information on all accounts in the telecommunications operation management system. Based on this, it categorizes business scenario types, statistically analyzes the activity level of each account in the corresponding scenario at different business operation times, and calculates the rate of change of activity between adjacent time periods to obtain a dataset of account activity change rates. For example, scenarios are categorized based on account registration information, service types used, etc., such as call service scenarios and data service scenarios. The application then statistically analyzes the number of logins and service usage frequency of each account at different times in these scenarios and calculates the rate of change.

[0066] Next, the system collects data on the business scenario types corresponding to all accounts, obtains the account activity dataset for each business scenario type at the current business operation moment, calculates the proportion of each business scenario type in the total system business volume, and then extracts the correlation coefficients between accounts under different business scenario types to obtain the account correlation coefficient set. For example, frequent use of call services may have a certain correlation with data usage; this correlation coefficient is calculated through data analysis.

[0067] A preset first activity warning threshold is established, and the dataset of activity levels greater than or equal to this threshold is selected to determine the set of business scenarios to be processed. When there is business correlation among the business scenarios to be processed, the data with the highest activity level is selected to determine the priority business scenario to be processed, thereby obtaining the target business scenario type data and the normal rate of activity change. For example, if some accounts in the call service have abnormally high activity levels, exceeding the warning threshold, their related business scenarios are identified as scenarios to be processed, and the business scenario corresponding to the highest activity level is identified as the priority processing object.

[0068] Based on the target business scenario type data and the normal activity rate of change, combined with preset reasonable upper and lower limits for activity and account management strategies, the first time required to adjust the maximum activity data to a reasonable range is predicted. Simultaneously, delayed-processing business scenarios associated with priority-processing business scenarios are identified, relevant data is extracted, and the second time required to adjust the associated activity data to a reasonable range is predicted based on the correlation impact coefficient. For example, based on the target scenario data for call services and the activity rate of change, the time to reduce excessively high activity to a reasonable range is predicted; for data traffic services affected by call services (delayed-processing scenarios), the time to adjust their associated activity is predicted.

[0069] The predicted duration set is obtained by forecasting the time required to adjust account activity to a reasonable range in other business scenarios within the target business scenario set. The account operation time points for priority processing business scenarios (first time point) are determined. The first and second durations are summed to obtain the required duration. The account operation time points for delayed processing business scenarios (second time point) are then calculated. Finally, the predicted duration set is used to predict the account operation time points for other business scenarios (third time point). Based on these time points and account management strategies, all accounts are systematically managed, and the account management results are output.

[0070] Step S1 specifically includes the following steps:

[0071] Obtain basic information of all accounts in the telecommunications operation management system, and divide telecommunications operation services into corresponding business scenarios based on the basic information of all accounts to obtain a set of business scenario types.

[0072] Based on the business scenario type set, the activity dataset of each account under the corresponding business scenario at different historical business operation times is statistically analyzed. The activity change rate is obtained by calculating the activity change magnitude of each data in the activity dataset at adjacent times. Based on the activity change rate, the account activity change rate dataset is output.

[0073] This application comprehensively collects basic account information from the telecommunications operation and management system. This basic information includes registration information (registration time, location, method, etc.), user identity information (age, gender, occupation, etc.), and package information (call duration, data allowance, value-added services, etc.). Based on this information, and according to factors such as service nature and user behavior patterns, telecommunications services are categorized into different service scenario types, such as voice calls, mobile data traffic, value-added services (e.g., ringback tones, mobile newspapers), and broadband internet access, thus forming a set of service scenario types. For example, if a user's package includes a large proportion of voice call time, the scenario where they use voice call services can be separated out.

[0074] For the defined business scenario types, at different historical business operation times (such as daily, weekly, and monthly business usage periods), the activity data of each account in the corresponding business scenario is collected using technologies such as system log recording and database statistics. The activity measurement indicators vary from business scenario to business scenario. For example, voice call scenarios are measured by the number of calls and call duration; mobile data traffic scenarios are measured by data usage and internet access time; and value-added service scenarios are measured by service usage frequency and customization duration, etc., thereby constructing an activity dataset.

[0075] The activity rate is calculated by using the formula (activity level at the next moment - activity level at the previous moment) ÷ activity level at the previous moment to represent the activity level between adjacent time points in the activity dataset. The calculated rates of change for each account under different business scenarios are then integrated to output an account activity rate of change dataset. This dataset visually demonstrates the speed and trend of account activity changes over different time periods.

[0076] Step S2 specifically includes the following steps:

[0077] Obtain the account activity dataset for each business scenario type at the current business operation time based on the business scenario type set;

[0078] After calculating the proportion of each business scenario type in the total system business, output the business scenario type proportion dataset.

[0079] Based on the business scenario type proportion dataset and the business scenario type set, the correlation coefficients between account activity under each business scenario are extracted, and then the account correlation coefficient set is output.

[0080] At any given moment during business operations, activity data for each account under each business scenario is obtained through database queries and log analysis within the telecommunications operations management system. For example, in the voice call scenario, call duration and number of calls for each account are recorded; in the data traffic scenario, data traffic usage and internet access time for each account are recorded, thus forming an account activity dataset for each business scenario. This data reflects the real-time activity status of accounts in each business scenario.

[0081] By combining transaction records and usage frequency data from various services, the proportion of each service scenario type in the total system service volume is calculated. For example, the proportion of indicators such as total call duration for voice services and total data usage for data services in the total telecommunications operation service volume over a period of time is statistically analyzed. This proportional data is then compiled and output as a service scenario type proportion dataset. This dataset reflects the relative importance and scale of each service scenario in the overall service volume.

[0082] By combining a dataset of business scenario type proportions and a set of business scenario types, statistical methods (such as correlation analysis and regression analysis) are used to analyze the correlation between account activity under different business scenarios. Taking traffic business and video business as examples, if the activity of traffic business increases, the activity of video business also increases accordingly. The correlation coefficient is obtained by calculating the degree of correlation between the changes in the activity of the two. The correlation coefficients calculated for each business scenario are summarized and output as a set of account correlation coefficients to quantify the degree of mutual influence of account activity between different business scenarios.

[0083] Step S3 specifically includes the following steps:

[0084] A first activity warning threshold is preset, and an activity dataset to be processed is selected from the account activity dataset that is greater than or equal to the first activity warning threshold;

[0085] Based on the pending activity dataset, a set of pending business scenarios is selected from the corresponding business scenario type set;

[0086] When there are business relationships between the business scenarios to be processed in the set of business scenarios to be processed, the data with the highest activity level is selected from the data of activity levels to be processed.

[0087] Based on the maximum activity data, select the corresponding priority processing business scenarios from the set of pending business scenarios;

[0088] Based on the priority business scenarios, filter out the target business scenario type data from the corresponding business scenario type set;

[0089] Based on the priority business scenario, normal activity change rates are selected from the corresponding account activity change rate dataset.

[0090] This application pre-sets a first activity warning threshold based on historical data and business needs. Each data point in the account activity dataset is compared to this threshold, and data points greater than or equal to the threshold are selected to form the activity dataset to be processed. These data represent accounts with relatively high or abnormal activity levels, potentially indicating underlying risks.

[0091] Based on the business scenario information corresponding to the data in the activity dataset to be processed, the corresponding set of business scenarios to be processed is selected from the set of business scenario types. That is, the business scenarios with accounts exhibiting abnormal activity levels are identified.

[0092] Check for business relationships between the various business scenarios in the pending business scenario set, such as call services and caller ID services. If a relationship exists, find the activity data with the highest value in the pending activity dataset. The account corresponding to this data has the highest activity in the relevant business scenario and may have a significant impact on the business system.

[0093] Based on the highest activity data, the business scenario corresponding to this one in the set of pending business scenarios is identified as a priority processing scenario. This scenario, due to its exceptionally high activity and potential connection to other businesses, requires priority management and control to ensure system stability or to unlock business value.

[0094] By prioritizing business scenarios, the system filters out the target business scenario type data from the set of business scenario types, further clarifying the specific business scenario types targeted by management and making management more targeted.

[0095] In the dataset of account activity change rates corresponding to the priority business scenarios, normal activity change rates that conform to the normal fluctuation range of the business are selected. This rate is used as a reference standard for subsequent judgment and adjustment of whether the account activity is reasonable.

[0096] Step S4 specifically includes the following steps:

[0097] Pre-set account management strategies based on the first activity warning threshold;

[0098] The system presets reasonable upper and lower limits for activity levels. Based on the target business scenario type data and the normal activity change rate, it calculates the time required for the maximum activity data to be adjusted to the preset reasonable activity range under the account management strategy, and then outputs the first duration. The reasonable upper limit for activity is greater than the maximum activity data, and the reasonable lower limit for activity is less than the maximum activity data.

[0099] Based on the primary activity warning threshold and combined with the business characteristics and historical data of the telecommunications operation management system, corresponding account management strategies are formulated. These strategies may include various methods such as limiting the frequency of account operations, adjusting service permissions, and sending reminder notifications. For example, if an account's activity exceeds the warning threshold due to frequent performance of a certain service operation, the management strategy could be to limit the frequency of that service operation to reduce account activity.

[0100] Reasonable upper and lower limits for account activity should be set by comprehensively considering factors such as the normal operation requirements of telecommunications services, user experience, and system capacity. The reasonable upper limit should be greater than the maximum activity level to ensure that account activity does not exceed a reasonable range under normal circumstances; the reasonable lower limit should be less than the maximum activity level to ensure that account activity is not too low and affects the normal operation of services. For example, for voice call services, a reasonable range of call frequency or duration should be set as the reasonable activity range based on historical call data and service requirements.

[0101] By leveraging data from the target business scenario, we gain a deep understanding of its characteristics, patterns, and factors influencing account activity. Combining the normal activity rate change rate with the predicted timeframe for adjusting maximum activity data to a pre-defined reasonable activity range under a pre-set account management strategy, we ultimately output the first estimated timeframe. For example, by establishing a time-series analysis model, we can combine historical activity change data and current maximum activity data for the target business scenario to predict the specific time required to adjust it to a reasonable range.

[0102] Step S5 specifically includes the following steps:

[0103] Based on the priority processing business scenarios, the delayed processing business scenarios that are related to the priority processing business scenarios are selected from the set of pending business scenarios.

[0104] Based on the delayed processing business scenario, extract the pending activity data from the pending activity dataset, and extract the pending business scenario type percentage data from the business scenario type percentage dataset.

[0105] Based on the operational information of all accounts in delayed and priority processing business scenarios, the corresponding association impact coefficients are filtered out from the account association impact coefficient set.

[0106] Based on the first activity warning threshold and the correlation influence coefficient, the activity value of the activity data to be processed after the first time period is predicted to have an impact on the change of activity value, thus obtaining the first correlation influence activity data;

[0107] Based on the proportion of business scenario types to be processed and the associated impact activity data, the predicted duration of the associated impact activity data is then adjusted to a preset reasonable activity range under the influence of account management strategies, and the second duration is output.

[0108] This application selects delayed processing business scenarios from a set of pending business scenarios based on business logic and association rules (such as the order of business processes and complementary relationships between functions). For example, if the priority business scenario is an abnormally high activity issue in voice call services, then related value-added service scenarios such as caller ID and voicemail may be identified as delayed processing business scenarios.

[0109] For the selected delayed processing business scenarios, the corresponding pending activity data is extracted from the pending activity dataset. This data reflects the activity of accounts in this business scenario. The pending business scenario type proportion data is extracted from the business scenario type proportion dataset to clarify the proportion of this business scenario in the total system business and measure its importance and scale.

[0110] Based on the operational information (such as operation time, operation type, operation frequency, etc.) of all accounts in the delayed processing business scenario and the priority processing business scenario, the correlation influence coefficient between these two business scenarios is filtered out from the account correlation influence coefficient set to quantify the degree of mutual influence between their activity levels.

[0111] Combining the first activity warning threshold and the selected correlation influence coefficients, a mathematical model is used to predict the change in activity value of the activity data to be processed after a first duration (the duration obtained in step S4), resulting in the first correlation influence activity data. This data reflects the impact of the priority processing business scenario management strategy on the activity of the related delayed processing business scenarios after a period of implementation.

[0112] Define the first activity warning threshold. This threshold is a key indicator for measuring whether account activity is abnormal, and it has already been set in the previous steps. It represents a boundary; when account activity reaches or exceeds this value, it requires special attention and action. For example, in a data traffic service, if the first activity warning threshold is set to exceed 100GB of monthly data usage, then when an account's monthly data usage reaches or exceeds this value, it will be included in the pending action range.

[0113] The correlation coefficient reflects the degree of mutual influence between account activity levels under different business scenarios. The data analysis in previous steps has already yielded the correlation coefficients between various business scenarios. For example, there is a correlation coefficient between voice call service and caller ID value-added service, indicating the degree to which changes in voice call service activity affect caller ID service activity. Assuming that for every unit increase in voice call service activity, caller ID service activity increases by 0.2 units, this 0.2 is the correlation coefficient between them.

[0114] Pending activity data refers to the activity data of accounts that exceed the first activity warning threshold in a specific business scenario. This data forms the basis for subsequent predictions and records the actual activity of accounts in the business scenario. For example, in a certain value-added service scenario, some accounts may exceed the warning threshold in terms of activity metrics such as usage frequency or duration; these specific values ​​constitute the pending activity data.

[0115] A predictive model can be constructed using the approach of linear regression. Linear regression models assume a linear relationship between the dependent variable (in this case, the activity value of the associated business scenario after the first time period, i.e., the data affecting activity) and the independent variables (the activity data to be processed, the correlation coefficient, etc.). Although the actual situation may be more complex, linear models can provide a relatively effective preliminary prediction in many cases.

[0116] The model variables are determined, with the independent variables mainly including the activity data to be processed and the correlation influence coefficients. The activity data to be processed reflects the initial activity level of the account in the current business scenario, while the correlation influence coefficients reflect the influence weights of other business scenarios related to this business scenario on its activity level.

[0117] The dependent variable is the data on the associated impact on activity that we want to predict, which is the activity value of the account in the associated business scenario after the first period of time.

[0118] In terms of model parameter settings, we can use the first activity warning threshold as an adjustment parameter during this prediction process. It can affect the direction and extent of the model's prediction. For example, if the activity data to be processed is much higher than the first activity warning threshold, it indicates that the account activity level is abnormally high. When predicting changes in activity in related business scenarios, it may be necessary to increase the weight of the correlation influence coefficient to more accurately reflect the chain reaction brought about by this abnormal activity.

[0119] Based on the above model, calculations are performed according to the formula. Assume the activity data to be processed is... The correlation coefficient is The first activity warning threshold is We can construct a simple prediction formula: Correlation influences activity data - .in This represents a function related to the first activity alert threshold, which can be set according to specific circumstances. For example, when... Greater than hour, It could be a follow and The function that increases with the increase of the difference is used to reflect the additional impact of abnormal activity on the activity of related business scenarios.

[0120] Since the prediction focuses on the change in activity level after the first period, it's necessary to consider the natural decay or increase in activity over time. A time factor can be introduced. The above formula needs to be modified. For example, assuming that activity will naturally decrease over time at a certain rate without the influence of other factors, let the decrease rate be . Therefore, the formula can be transformed into: Correlation influences activity data one Here The first duration is the result calculated using this formula, which is the data that influences the activity level.

[0121] Historical data is collected for model validation and adjustment. To ensure prediction accuracy, relevant data from similar business scenarios in the past needs to be collected. The actual activity values ​​of related business scenarios are compared with the values ​​predicted by the model. For example, identify business scenarios with similar anomalies in activity levels and compare the actual activity changes of those related business scenarios with the model's predictions.

[0122] If significant discrepancies are found between the predicted results and actual conditions, adjustments to the model parameters are necessary. This may involve reassessing the accuracy of the correlation coefficient, adjusting the function related to the first activity warning threshold, or even choosing a new model framework, until the model's predictions better reflect reality. Through continuous verification and adjustment, a more reliable predicted value for the correlation activity data is finally obtained.

[0123] Based on the proportion of business scenario types to be processed and the first data on the related impact on activity, the relevant model is used again to predict the time required for the first data on the related impact on activity to be adjusted to a preset reasonable activity range under the influence of account management strategies, and then the second time is output to provide a time reference for subsequent management operations.

[0124] This data reflects the proportion of pending business scenarios within the overall system's business volume. For example, if a certain type of pending business scenario accounts for 10%, it means that the business volume or account activity of that scenario accounts for one-tenth of the total in the system. The proportion reflects its importance and scale within the business system; business scenarios with a larger proportion have a greater impact on the overall system activity and require more resources and attention when making adjustments.

[0125] The first set of activity data, "Association Impact Data 1," represents the activity level after the first period, taking into account the correlation effects. It reflects the activity level of accounts in the associated pending business scenarios after a period of time following the implementation of the priority business scenario management strategy. For example, if this data exceeds the upper limit of the preset reasonable activity range, it indicates that the current activity level is still abnormally high and adjustments are needed.

[0126] Models based on time series or regression analysis can be selected. Time series models are suitable for uncovering patterns in data changes over time, while regression analysis models can be used to explore the relationship between the proportion of different business scenario types, the data influencing activity levels, and the adjustment duration. Taking a regression analysis model as an example, let's assume the adjustment duration is the dependent variable. The percentage of pending business scenario types is the independent variable. The correlation influences the activity data as an independent variable. .

[0127] The model parameters are determined through analysis of historical data, collecting data samples of different percentages, activity levels, and actual adjustment durations from similar past business scenarios. Statistical methods, such as least squares, are used to calculate the coefficient relationships between the independent and dependent variables in the model. For example, a regression equation is obtained through calculation. , where a and b are the coefficients of the independent variable, and c is the constant term.

[0128] Different account management strategies have varying impacts on the duration of activity level adjustments. A strategy that restricts the frequency of business operations may quickly reduce activity levels; while a reminder-based approach will adjust more slowly. Assign weights to different strategies, such as a weight of 0.8 for restricting operation frequency and 0.3 for reminder-based strategies.

[0129] Integrating into Model Calculation: The influence weights of the strategy are incorporated into the prediction model. Assume the weights of the currently used account management strategy are... Then the regression equation is modified as follows: .

[0130] Prediction and output of the second duration

[0131] Substitute data for calculation: Calculate the percentage of current pending business scenario types. Related factors affecting activity data and the weight of the account management strategy adopted. Substituting the values ​​into the revised model equations, the time required to adjust to a preset reasonable activity level range is calculated. .

[0132] Output result: The calculated duration As a second time-based output, it provides a time reference for subsequent management operations of related business scenarios, enabling reasonable resource allocation and management process planning. Furthermore, in practical applications, new data can be continuously collected to optimize and calibrate the model, improving prediction accuracy.

[0133] Step S6 specifically includes the following steps:

[0134] The predicted duration set is output after predicting the time required for the activity level of accounts in other business scenarios within the scope of the business scenarios to be processed to be adjusted to a preset reasonable activity level range under the effect of account management strategies.

[0135] The first time point is the operation time of the first account in the priority processing business scenario for all accounts; where the first account is the operation account involved in the priority processing business scenario.

[0136] The required duration is obtained by summing the first duration and the second duration. The second time point is calculated after the required duration has elapsed from the first time point. The second time point is the second account operation time point corresponding to all accounts in the delayed processing business scenario. The second account is the operation account involved in the delayed processing business scenario.

[0137] The third time point is obtained by predicting the operation time point of the third account corresponding to all accounts in other business scenarios based on the prediction duration set; where the third account is the operation account involved in business scenarios other than priority processing business scenarios and delayed processing business scenarios in the business scenario type set.

[0138] The first, second, and third time points are combined to form the account operation time result;

[0139] After systematically managing all accounts in the telecommunications operation management system based on account operation time results and account management strategies, the account management results are output.

[0140] This application, for business scenarios other than those requiring priority or deferred processing, first collects various data on accounts within these scenarios, including historical activity data, current activity status, and account operation records. Simultaneously, it analyzes pre-defined account management strategies to clarify the goals and methods of adjusting account activity for different business scenarios. For example, when analyzing SMS business scenarios, it collects historical data such as the frequency and quantity of SMS messages sent and received by accounts, as well as the SMS sending status of currently abnormally active accounts, to understand the specific requirements of the management strategy regarding SMS business activity limits.

[0141] Utilize appropriate predictive models, such as time series analysis models. These models mine trends and patterns based on the time-series characteristics of historical activity data. Taking a value-added service scenario as an example, by analyzing account activity data related to this service over a past period, the model identifies periodic and seasonal patterns. Then, considering the current account activity level and the impact of management strategies, the model calculates the time required to adjust account activity to a preset reasonable range. The predicted durations for each business scenario are then aggregated to form a predicted duration set.

[0142] In priority business scenarios, the accounts involved are identified as primary accounts. These accounts are typically those with exceptionally high activity levels that significantly impact system stability or normal business operations. For example, in scenarios involving a surge in network traffic, accounts whose traffic usage far exceeds normal levels are considered primary accounts.

[0143] Record the time point at which the first account performs a relevant action, and use this as the first time point. This time point marks the start of account management work for priority business scenarios, and subsequent management operation time calculations and arrangements will be based on this.

[0144] Add the first duration obtained in step S4 (i.e., the duration required to adjust the maximum activity data to a preset reasonable activity range based on the target business scenario type data and the normal activity change rate) and the second duration obtained in step S5 (i.e., the duration required to adjust the associated activity data to a preset reasonable activity range based on the proportion of the business scenario type to be processed and the associated activity data) to obtain the total duration required to process the priority business scenario and the associated delayed business scenario.

[0145] Starting from the first time point, the time is extrapolated based on the calculated total duration. For example, if the first time point is 9:00 AM and the total duration is 3 hours, then 12:00 PM, which occurs after 3 hours, is the second time point. This second time point is the operation time point corresponding to the operation account (second account) involved in the delayed processing business scenario.

[0146] Based on the generated predicted duration set, obtain the duration information required for adjusting account activity in other business scenarios. For example, for some less frequently used but still manageable value-added business scenarios, find their corresponding predicted duration from the predicted duration set.

[0147] Based on the specific circumstances of these business scenarios, such as the importance of the business and its relevance to other businesses, the operation time points corresponding to the operation accounts (third accounts) involved in other business scenarios (excluding priority processing and delayed processing scenarios) are predicted. For example, if the predicted duration of a certain other business scenario is 2 hours, and it is expected to start processing after the second time point, then adding 2 hours to the second time point yields the third time point.

[0148] The first, second, and third time points are integrated to form a complete account operation timeline. This result covers the time arrangements for account management operations under different business scenarios, clearly demonstrating the time-based layout of the entire account management work.

[0149] Based on the account operation time results and preset account management policies, corresponding management operations are performed on all accounts in the telecommunications operation management system at the corresponding time points. For example, at the first time point, management measures such as restricting traffic usage and reducing operation privileges are implemented for the first account in the priority service scenario; at the second time point, corresponding associated management operations are performed on the second account in the delayed service scenario; and at the third time point, appropriate management policies are implemented for the third account in other service scenarios. Through this systematic management process, the final account management results are output, and effective management of all accounts in the telecommunications operation management system is achieved.

[0150] Referring to Figure 2, Embodiment 2 further illustrates the account management system in the telecommunications operation management system proposed in this invention.

[0151] An account management system in a telecommunications operation management system includes:

[0152] Acquisition Module: Acquires basic information of all accounts in the telecommunications operation management system, and analyzes the rate of change of activity data of all accounts at different business operation times based on the basic information to obtain the account activity rate change data dataset;

[0153] Extraction module: Statistically analyzes the business scenario type set corresponding to all accounts, and extracts the association influence coefficient between accounts under different business scenario types to obtain the account association influence coefficient set;

[0154] Filtering module: Filters out target business scenario type data from the business scenario type set, filters out the maximum activity data of all accounts in each business scenario, and filters out the normal activity change rate from the account activity change rate dataset.

[0155] First judgment module: Based on the target business scenario type data and the normal activity change rate, determine the first duration required to adjust the maximum activity data to a preset reasonable activity range;

[0156] The second judgment module: filters out the business scenario type data to be processed from the business scenario type set, predicts the association impact activity data one based on the association impact coefficient set of the account association impact coefficient set, and judges the second time required to adjust the association impact activity data one to a preset reasonable activity range based on the business scenario type data to be processed and the association impact activity data one.

[0157] Management module: Systematically manages all accounts based on the first duration, the second duration, and the business scenario, and outputs the account management results.

[0158] Referring to FIG3, an electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements an account management method in a telecommunications operation management system.

[0159] As shown in Figure 3, the electronic device may include a processor 610, a communications interface 620, a memory 630, and a communication bus 640. The processor 610, communications interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions from the memory 630 to execute an account management method in a telecommunications operation management system.

[0160] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0161] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program that can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer is able to execute an account management method in a telecommunications operation management system.

[0162] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform an account management method in a telecommunications operation management system.

[0163] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0164] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0165] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An account management method in a telecommunications operation management system, characterized in that, The method includes the following steps: Step S1: Obtain basic information of all accounts in the telecommunications operation management system, and analyze the rate of change of activity data of all accounts at different business operation times based on the basic information to obtain an account activity change rate dataset; Step S2: Statistically analyze the business scenario type set corresponding to all accounts, and extract the correlation influence coefficient between accounts under different business scenario types to obtain an account correlation influence coefficient set; Step S3: Filter out the target business scenario type data from the business scenario type set, and filter out the maximum activity data of all accounts in each business scenario, and filter out the normal activity change rate from the account activity change rate dataset; Step S4: Determine the first duration required to adjust the maximum activity data to a preset reasonable activity range based on the target business scenario type data and the normal activity change rate; Step S5: Filter out the business scenario type data to be processed from the business scenario type set, predict the associated influence activity data one based on the association influence coefficient in the account association influence coefficient set, and determine the second duration required to adjust the associated influence activity data one to a preset reasonable activity range based on the business scenario type data to be processed and the associated influence activity data one; Step S6: Systematically manage all accounts based on the first duration, the second duration, and the processed business scenario, and output the account management results.

2. The account management method in a telecommunications operation management system according to claim 1, characterized in that, Step S1 specifically includes the following steps: obtaining basic information of all accounts in the telecommunications operation management system; dividing telecommunications operation services into corresponding business scenarios based on the basic information of all accounts to obtain a set of business scenario types; statistically analyzing the activity dataset of each account in the corresponding business scenario at different historical business operation times based on the set of business scenario types; calculating the activity change rate by measuring the activity change magnitude of each data in the activity dataset at adjacent times; and outputting the account activity change rate dataset based on the activity change rate.

3. The account management method in a telecommunications operation management system according to claim 1, characterized in that, Step S2 specifically includes the following steps: obtaining the account activity dataset for each business scenario type at the current business operation time based on the business scenario type set; calculating the proportion of each business scenario type in the total system business and outputting the business scenario type proportion dataset; and extracting the correlation coefficient between account activity in each business scenario based on the business scenario type proportion dataset and the business scenario type set, and outputting the account correlation coefficient set.

4. The account management method in a telecommunications operation management system according to claim 3, characterized in that, Step S3 specifically includes the following steps: Preset a first activity warning threshold; filter out a dataset of activity levels greater than or equal to the first activity warning threshold from the account activity dataset; filter out a set of business scenarios to be processed from the corresponding business scenario type set based on the dataset of activity levels to be processed; when there is a business relationship between the business scenarios to be processed in the set of business scenarios to be processed, filter out the data with the highest activity level from the dataset of activity levels to be processed; filter out the corresponding priority business scenarios from the set of business scenarios to be processed based on the data with the highest activity level; filter out the target business scenario type data from the corresponding business scenario type set based on the priority business scenarios; and filter out the normal activity change rate from the corresponding account activity change rate dataset based on the priority business scenarios.

5. The account management method in a telecommunications operation management system according to claim 4, characterized in that, Step S4 specifically includes the following steps: preset an account management strategy based on the first activity warning threshold; preset a reasonable upper limit and lower limit for activity, and output the first duration after obtaining the time taken for the maximum activity data to be adjusted to the preset reasonable activity range under the action of the account management strategy based on the target business scenario type data and the normal activity change rate; wherein, the reasonable upper limit for activity is greater than the maximum activity data, and the reasonable lower limit for activity is less than the maximum activity data.

6. The account management method in a telecommunications operation management system according to claim 5, characterized in that, Step S5 specifically includes the following steps: Based on the priority processing business scenario, filter out the delayed processing business scenarios from the set of pending business scenarios that are related to the priority processing business scenarios; extract pending activity data from the pending activity dataset and the pending business scenario type percentage data from the business scenario type percentage dataset based on the delayed processing business scenarios; based on the operation information of all accounts in the delayed processing and priority processing business scenarios, filter out the corresponding association influence coefficients from the set of account association influence coefficients; based on the first activity warning threshold and the association influence coefficient, predict the change in activity value of the pending activity data after the first duration to obtain the first association influence activity data; based on the pending business scenario type percentage data and the first association influence activity data, predict the duration required for the first association influence activity data to adjust to a preset reasonable activity range under the account management strategy, and then output the second duration.

7. The account management method in a telecommunications operation management system according to claim 6, characterized in that, Step S6 specifically includes the following steps: First, predict the time required for the activity level of accounts in other business scenarios within the target business scenario set to be adjusted to a preset reasonable activity range under the account management strategy, and then output a predicted time set; second, the first account operation time point corresponding to all accounts in the priority processing business scenario is the first time point; wherein, the first account is the operation account involved in the priority processing business scenario; third, the third account is the operation account involved in the delayed processing business scenario; fourth, the third account is the operation account involved in the delayed processing business scenario; fifth, the third account is the operation account involved in the business scenario type set excluding the priority processing business scenario and the delayed processing business scenario; sixth, the first time point, the second time point, and the third time point are combined to form the account operation time result; seventh, the account management result is output after systematically managing all accounts in the telecommunications operation management system according to the account operation time result and the account management strategy.

8. An account management system in a telecommunications operation management system, applied to the account management method in a telecommunications operation management system as described in any one of claims 1-7, characterized in that, Includes: Acquisition module: Acquires basic information of all accounts in the telecommunications operation management system, and analyzes the rate of change of activity data of all accounts at different business operation times based on the basic information to obtain the account activity rate change data dataset; Extraction module: Statistically analyzes the business scenario type set corresponding to all accounts, and extracts the association influence coefficient between accounts under different business scenario types to obtain the account association influence coefficient set; Filtering module: Filters the target business scenario type data from the business scenario type set, and filters the maximum activity data of all accounts in each business scenario, and filters the normal activity change rate from the account activity change rate dataset. First judgment module: Based on the target business scenario type data and the normal activity change rate, determine the first duration required to adjust the maximum activity data to a preset reasonable activity range; The second judgment module: filters out the business scenario type data to be processed from the business scenario type set, predicts the association impact activity data one based on the association impact coefficient set of the account association impact coefficient set, and judges the second time required to adjust the association impact activity data one to a preset reasonable activity range based on the business scenario type data to be processed and the association impact activity data one. Management module: Systematically manages all accounts based on the first duration, the second duration, and the business scenario, and outputs the account management results.

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 program, it implements the account management method in a telecommunications operation management system as described in any one of claims 1 to 7.

Images