Early warning method and device, electronic equipment and storage medium

Abstract

This application provides an early warning method, apparatus, electronic device, and storage medium. The method includes: determining the target service platform's corresponding warning period within a target area; acquiring historical error code data of the target type of IPTV service within a first historical period matching the warning period of the target service platform within the target area; processing the historical error code data using a pre-trained autoregressive integral moving average model to predict the predicted error code data of the target type of IPTV service within the warning period of the target service platform in the target area; calculating the error code deviation based on the predicted error code data and the historical error code data; and generating IPTV service early warning information corresponding to the target service platform based on the target area and target type when the error code deviation exceeds a deviation threshold. This application improves the accuracy of IPTV service alarms.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to an early warning method, device, electronic device, and storage medium. Background Technology

[0002] IPTV (Internet Protocol Television) service platforms have numerous alarm systems with inconsistent and chaotic alarm rules; the operation, installation, maintenance, and support of IPTV services face a rather passive situation.

[0003] There are significant uncertainties surrounding user complaints about IPTV service malfunctions. While early warning systems for clustered malfunctions caused by network, platform, and terminal issues have been largely implemented, an alarm system that closely reflects the actual viewing experience of users remains incomplete. Furthermore, the "MOS (Mean Opinion Score)" commonly used in the IPTV field is difficult to cover video media services with diverse encoding rules and has a large margin of error. Summary of the Invention

[0004] The technical problem to be solved by the embodiments of this application is to provide an early warning method, device, electronic device and storage medium that can automatically adjust the early warning value at different time periods, improve the accuracy of early warning, and solve the problem of large error in the existing alarm system of IPTV service.

[0005] In a first aspect, embodiments of this application provide an early warning method, the method comprising:

[0006] Determine the corresponding warning period for the target business platform within the target region;

[0007] Obtain historical error code data of the target type of IPTV service within the target area of ​​the target service platform, which matches the warning period;

[0008] The historical error code data is processed by calling a pre-trained autoregressive integral moving average model to predict the target error code data of the IPTV service target type in the target area during the warning period of the target service platform.

[0009] The error code deviation is calculated based on the predicted error code data and the historical error code data.

[0010] If the error code deviation exceeds the deviation threshold, an IPTV service warning message corresponding to the target service platform is generated based on the target region and the target type.

[0011] Optionally, before processing the historical error code data using a pre-trained autoregressive integral moving average model to predict the predicted error code data for the target type of IPTV service of the target service platform in the target area during the warning period, the method further includes:

[0012] The pre-configured model parameters are assigned to the initial autoregressive integral moving average model to obtain the intermediate autoregressive integral moving average model.

[0013] Obtain first error code data of a specified type for IPTV services within a first historical period, and second error code data of a specified type for IPTV services within a second historical period; wherein the first historical period is earlier than the second historical period, and the first historical period and the second historical period are two adjacent periods, and the specified type includes the target type;

[0014] The first error code data and the second error code data are split according to the set time period length to obtain the first sub-error code data of the first error code data in N time periods, and the second sub-error code data of the second error code data in N time periods, where N is a positive integer;

[0015] Based on the first sub-error code data and the second sub-error code data within each time period, the error code deviation factor corresponding to each time period is calculated;

[0016] The intermediate autoregressive integral moving average model is trained based on the error code deviation factors to obtain the autoregressive integral moving average model.

[0017] Optionally, the step of using a pre-trained autoregressive integral moving average model to process the historical error code data and predict the target error code data for the IPTV service of the target service platform in the target area during the warning period includes:

[0018] Obtain error code data of IPTV services of the target service platform in the target area within multiple second historical time periods; the multiple second historical time periods are time periods that match the period to be warned;

[0019] Calculate the average value of the error code data to obtain the average error code data;

[0020] If the absolute value of the difference between the historical error code data and the average error code data is less than a set value, the historical error code data is processed based on the autoregressive integral moving average model to predict the predicted error code data.

[0021] Optionally, after calculating the average value of the error code data to obtain the average error code data, the method further includes:

[0022] If the absolute value of the difference between the historical error code data and the average error code data is greater than or equal to a set value, the historical error code data is replaced with the average error code data.

[0023] The average error code data is processed based on the autoregressive integral moving average model to predict the predicted error code data.

[0024] Optionally, calculating the error code deviation based on the predicted error code data and the historical error code data includes:

[0025] Verify the validity of the predicted error code data and the historical error code data;

[0026] If both the predicted error code data and the historical error code data are valid, the error code deviation is calculated based on the predicted error code data and the historical error code data.

[0027] Optionally, calculating the error code deviation based on the predicted error code data and the historical error code data includes:

[0028] Obtain the data difference between the historical error code data and the predicted error code data;

[0029] Obtain the absolute value corresponding to the data difference, and round it to get the integer value of the error code;

[0030] Obtain the maximum value from the predicted error code data and the historical error code data;

[0031] The error code deviation is calculated based on the integer value of the error code and the maximum value.

[0032] Optionally, after generating the IPTV service warning information corresponding to the target service platform based on the target region and the target type, the method further includes:

[0033] Generate the order dispatch notification information corresponding to the target business platform;

[0034] The dispatch notification information is sent to the target business platform so that the target business platform can handle the fault dispatch.

[0035] Secondly, embodiments of this application provide an early warning device, the device comprising:

[0036] The warning period determination module is used to determine the corresponding warning period for the target business platform within the target area;

[0037] The historical data acquisition module is used to acquire historical error code data of the target type of IPTV service within the target area of ​​the target service platform, which matches the warning period;

[0038] The prediction data acquisition module is used to call a pre-trained autoregressive integral moving average model to process the historical error code data and predict the target error code data of the IPTV service of the target service platform in the target area during the warning period.

[0039] The deviation calculation module is used to calculate the error code deviation based on the predicted error code data and the historical error code data;

[0040] The early warning information generation module is used to generate IPTV service early warning information corresponding to the target service platform based on the target area and the target type when the error code deviation is greater than the deviation threshold.

[0041] Optionally, the device further includes:

[0042] The intermediate model acquisition module is used to assign pre-configured model parameters to the initial autoregressive integral moving average model to obtain the intermediate autoregressive integral moving average model.

[0043] The error data acquisition module is used to acquire first error code data of a specified type for IPTV services within a first historical period and second error code data of a specified type for IPTV services within a second historical period; wherein the first historical period is earlier than the second historical period, and the first historical period and the second historical period are two adjacent periods, and the specified type includes the target type;

[0044] The sub-error data acquisition module is used to split the first error code data and the second error code data according to a set time period length to obtain the first sub-error code data of the first error code data in N time periods, and the second sub-error code data of the second error code data in N time periods, where N is a positive integer;

[0045] The deviation factor calculation module is used to calculate the error code deviation factor corresponding to each time period based on the first sub-error code data and the second sub-error code data in each time period;

[0046] The model acquisition module is used to train the intermediate autoregressive integral moving average model based on the error code deviation factor to obtain the autoregressive integral moving average model.

[0047] Optionally, the prediction data acquisition module includes:

[0048] Error code data acquisition unit, used to acquire error code data of IPTV service of the target service platform in the target area within multiple second historical time periods; the multiple second historical time periods are time periods that match the period to be warned;

[0049] An average error data calculation unit is used to calculate the average value of the error code data to obtain average error code data.

[0050] The prediction code data acquisition unit is used to process the historical error code data based on the autoregressive integral moving average model to predict the predicted error code data when the absolute value of the difference between the historical error code data and the average error code data is less than a set value.

[0051] Optionally, the device further includes:

[0052] The code data replacement module is used to replace the historical error code data with the average error code data when the absolute value of the difference between the historical error code data and the average error code data is greater than or equal to a set value.

[0053] The error code prediction acquisition module is used to process the average error code data based on the autoregressive integral moving average model to predict the error code data.

[0054] Optionally, the deviation calculation module includes:

[0055] A validity verification unit is used to verify the validity of the predicted error code data and the historical error code data;

[0056] The deviation calculation unit is used to calculate the error code deviation based on the predicted error code data and the historical error code data, provided that both the predicted error code data and the historical error code data are valid.

[0057] Optionally, the deviation calculation unit includes:

[0058] The data difference acquisition subunit is used to acquire the data difference between the historical error code data and the predicted error code data.

[0059] The integer value acquisition subunit is used to acquire the absolute value corresponding to the data difference, and round it to obtain the integer value of the error code;

[0060] The maximum value acquisition subunit is used to acquire the maximum value between the predicted error code data and the historical error code data;

[0061] The deviation calculation subunit is used to calculate the error code deviation based on the integer value of the error code and the maximum value.

[0062] Optionally, the device further includes:

[0063] The prompt message generation module is used to generate dispatch prompt messages corresponding to the target business platform;

[0064] The prompt message sending module is used to send the dispatch prompt message to the target business platform so that the target business platform can handle the fault dispatch.

[0065] Thirdly, embodiments of this application provide an electronic device, including:

[0066] A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the early warning method described in any of the preceding claims.

[0067] Fourthly, embodiments of this application provide a computer-readable storage medium that, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform any of the aforementioned warning methods.

[0068] Compared with the prior art, the embodiments of this application have the following advantages:

[0069] In this embodiment, the corresponding warning period for the target service platform within the target area is determined. Historical error code data of the target type of IPTV service within the target area, matching the warning period, is obtained. A pre-trained autoregressive integral moving average model is used to process the historical error code data, predicting the target type of IPTV service within the warning period for the target service platform in the target area. Based on the predicted error code data and historical error code data, the error code deviation is calculated. If the error code deviation exceeds a deviation threshold, warning information for the IPTV service corresponding to the target service platform is generated based on the target area and target type. This embodiment, by using an autoregressive integral moving average model combined with historical error code data from different time periods to predict error code data for future corresponding time periods, can achieve the goal of automatically adjusting warning values ​​at different time periods, thereby improving the accuracy of warnings and solving the problem of large errors in existing alarm systems.

[0070] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0071] Figure 1 A flowchart illustrating the steps of an early warning method provided in this application embodiment;

[0072] Figure 2 A flowchart illustrating the steps of a method for obtaining an autoregressive integral moving average model, as provided in this application embodiment;

[0073] Figure 3 A flowchart illustrating the steps of a method for obtaining predicted error code data provided in this application embodiment;

[0074] Figure 4 A flowchart illustrating the steps of another method for obtaining predicted error code data provided in this application embodiment;

[0075] Figure 5 A flowchart illustrating the steps of an error code deviation calculation method provided in this application embodiment;

[0076] Figure 6 A flowchart illustrating the steps of another error code deviation calculation method provided in this application embodiment;

[0077] Figure 7 A flowchart illustrating the steps of a method for sending dispatch notification information, as provided in this application embodiment;

[0078] Figure 8 A schematic diagram of an IPTV service early warning process provided in an embodiment of this application;

[0079] Figure 9 A schematic diagram of an IPTV service data processing flow provided in an embodiment of this application;

[0080] Figure 10 A fluctuation chart of historical error code data provided in this application embodiment;

[0081] Figure 11 A schematic diagram illustrating a group failure early warning classification alarm provided in an embodiment of this application;

[0082] Figure 12 This is a schematic diagram of the structure of an early warning device provided in an embodiment of this application;

[0083] Figure 13 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0084] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0085] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0086] Reference Figure 1 The flowchart illustrates the steps of an early warning method provided in an embodiment of this application, as shown below. Figure 1 As shown, the early warning method may include steps 101, 102, 103, 104 and 105.

[0087] Step 101: Determine the corresponding warning period for the target business platform within the target area.

[0088] The embodiments of this application can be applied to scenarios where error code data of IPTV services of a target service platform is predicted.

[0089] IPTV, or Interactive Network Television, is a new technology that utilizes broadband cable television networks and integrates various technologies such as the Internet, multimedia, and communications to provide home users with a variety of interactive services, including digital television.

[0090] The target service platform refers to the platform that provides IPTV services. In this example, the target service platform could be a service platform such as ZTE or Huawei.

[0091] The target area refers to the geographical area where error code data prediction for IPTV services is required. In this example, a province can be used as the target area, a single city within a province can be used as the target area, or an administrative district or commercial area within a single city within a province can be used as the target area. Specifically, the specific method of dividing the target area can be determined according to business needs, and this embodiment does not impose any restrictions on it.

[0092] The period to be warned refers to the period during which error code data warnings for IPTV services are required in the future. In this example, the period to be warned can be a period of 1 hour or 2 hours, etc. Specifically, the specific duration of the period to be warned can be determined according to business needs, and this embodiment does not impose any restrictions on it.

[0093] In practical implementation, when predicting error code data for IPTV services of a target business platform, the corresponding warning period for the target business platform within the target area can be determined first.

[0094] After determining the target business platform's corresponding warning period within the target area, proceed to step 102.

[0095] Step 102: Obtain historical error code data of the target type of IPTV service within the target area of ​​the target service platform, which matches the warning period.

[0096] The first historical period refers to the historical period that matches the period for which an early warning is pending. In practice, each week can be used as a cycle. When the period for which an early warning is pending is the next hour, such as 10:00 AM to 11:00 AM this Tuesday, then the first historical period could be 10:00 AM to 11:00 AM last Tuesday, etc.

[0097] The target type refers to the type of IPTV service for which error code data prediction is required. In this example, the target type can be at least one of the following: CDN (Content Delivery Network) platform service quality degradation, EPG (Electronic Program Guide) platform service quality degradation, regional service quality degradation, network element service quality degradation, terminal service quality degradation, EPG error code surge alarm, live channel disconnection alarm, multiple discontinuous channel alarms, live source probe alarm, and live channel quality alarm. Figure 11 As shown.

[0098] After determining the target service platform's corresponding warning period within the target area, the first historical period corresponding to the warning period can be determined. Then, the historical error code data of the target type of IPTV service within the first historical period of the target service platform within the target area can be obtained.

[0099] After obtaining the historical error code data of the target type of IPTV service within the target area that matches the period to be warned in the first historical period of the target service platform, step 103 is executed.

[0100] Step 103: Call the pre-trained autoregressive integral moving average model to process the historical error code data, and predict the target error code data of the IPTV service target type of the target service platform in the target area during the warning period.

[0101] The Autoregressive Integral Moving Average (ARIMA) model is a model that transforms a non-stationary time series into a stationary one, and then regresses the dependent variable only on its lagged values ​​and the present and lagged values ​​of the random error term. The ARIMA model includes parameters such as AR (autoregressive), p (autoregressive term), MA (moving average), q (number of moving average terms), and d (number of differencing operations performed when the time series becomes stationary).

[0102] The training process for the autoregressive integral moving average model can be combined with... Figure 2 The following is a detailed description.

[0103] Reference Figure 2 The flowchart illustrates the steps of a method for obtaining an autoregressive integral moving average model according to an embodiment of this application. Figure 2 As shown, the method for obtaining the autoregressive integral moving average model may include steps 201, 202, 203, 204, and 205.

[0104] Step 201: Assign the pre-configured model parameters to the initial autoregressive integral moving average model to obtain the intermediate autoregressive integral moving average model.

[0105] In this embodiment, the model parameters of the autoregressive integral moving average model can be pre-configured, and then the pre-configured model parameters can be assigned to the initial autoregressive integral moving average model to obtain the intermediate autoregressive integral moving average model.

[0106] In this example, you can specify the number of autoregressive (AR) terms (P), the difference coefficients (D), and the number of offset average (MA) terms (Q). Then, you can use Python syntax to calculate the residual values ​​ARIMA(P, Q) of the ACF and PACF plots multiple times using different permutations and combinations of P[0-10] / D[0-3] / Q[0-3]. The residual value with the smallest residual value is the optimal P / D / Q value. For example:

[0107] ARIMA(4,1,0) MSE = 16649.59

[0108] ARIMA(4,2,1) MSE = 16796.27

[0109] ARIMA(6,1,0) MSE=15810.08

[0110] Determine P=6, D=1, Q=0. Use code to iterate through all P[0-10] / D[0-3] / Q[0-3], the model with the smallest residual is optimal, and the intermediate autoregressive integral moving average model can be obtained.

[0111] Step 202: Obtain the first error code data of the specified type of IPTV service in the first historical period and the second error code data of the specified type of IPTV service in the second historical period from the service platform.

[0112] In this embodiment, the first historical period may be earlier than the second historical period, and the first historical period and the second historical period are two periods that are adjacent in time. The specified type may include the target type.

[0113] The first error code data refers to the error code data of a specified type for the IPTV service within the first historical period of the service platform.

[0114] The second error code data refers to the error code data of a specified type for the IPTV service of the service platform during the second historical period.

[0115] When constructing the autoregressive integral moving average model, the platform can use the first error code data of a specified type of IPTV service in the first historical period and the second error code data of a specified type of IPTV service in the second historical period.

[0116] After obtaining the first error code data of the specified type of IPTV service in the first historical period and the second error code data of the specified type of IPTV service in the second historical period from the service platform, step 203 is executed.

[0117] Step 203: Based on the set time period length, split the first error code data and the second error code data respectively to obtain the first sub-error code data of the first error code data in N time periods, and the second sub-error code data of the second error code data in N time periods, where N is a positive integer.

[0118] The set time period length refers to the pre-set time period length used for periodic segmentation. In this example, the set time period length can be 5 minutes, 8 minutes, etc. Specifically, the specific value of the set time period length can be determined according to business needs, and this embodiment does not impose any restrictions on it.

[0119] After obtaining the first error code data of a specified type for IPTV services in the first historical period and the second error code data of a specified type for IPTV services in the second historical period from the service platform, the first error code data and the second error code data can be split and processed according to the set time period length to obtain the first sub-error code data of the first error code data in N time periods and the second sub-error code data of the second error code data in N time periods.

[0120] After obtaining the first sub-error code data and the second sub-error code data, proceed to step 204.

[0121] Step 204: Calculate the error code deviation factor for each time period based on the first sub-error code data and the second sub-error code data for each time period.

[0122] Error code deviation factors can be used to indicate factors that indicate error code deviation during a matching time period.

[0123] After obtaining the first and second sub-error code data, the error code deviation factor for each time period can be calculated based on the first and second sub-error code data for each time period.

[0124] After calculating the error code deviation factor for each time period based on the first and second sub-error code data for each time period, step 205 is executed.

[0125] Step 205: Train the intermediate autoregressive integral moving average model based on the error code deviation factor to obtain the autoregressive integral moving average model.

[0126] After calculating the error code deviation factor for each time period based on the first and second sub-error code data, the intermediate autoregressive integral moving average model can be trained based on the error code deviation factor to obtain the final autoregressive integral moving average model. The model construction process is described in detail below with a specific example:

[0127] In practical applications, based on the number of error codes, the initial first week of system operation can be set as the historical baseline data week. Using 7*24-hour data, all IPTV error code data is divided into 2016 time modules with attached IPTV information, each with a granular 5-minute interval, forming the initial reference sample n1 for the data baseline of this month. (IPTV information may include: number of active users S, number of users watching programs s, day of the week D (holiday factor J), and region Q).

[0128] The number of error codes in the second week is based on the baseline initial reference data of the first week. The range of variables such as the number of users with the device turned on (S), the number of users playing the program (s), the current time (T), the day of the week (D) (holiday factor (J), and the region (Q) are calculated. Then, the percentage of set-top box users who triggered error codes when there were existing historical user complaints (a%) is combined to form the final Arima prediction architecture model. The model will be continuously iterated and learned on this basis.

[0129] Once the autoregressive integral moving average model is obtained, it can be applied to the prediction of error code data.

[0130] In this example, after obtaining historical error code data, an autoregressive integral moving average model can be used to process the historical error code data to predict the target error code data of the IPTV service target type in the target area during the warning period of the target service platform.

[0131] In practical implementation, after obtaining historical error code data, data cleaning and other operations can be performed on the historical error code data to determine its validity. If invalid, historical average error code data is used for prediction. This implementation process can be combined with... Figure 3 The following is a detailed description.

[0132] Reference Figure 3 The flowchart illustrates the steps of a method for obtaining predicted error code data according to an embodiment of this application. Figure 3 As shown, the method for obtaining predicted error code data may include steps 301, 302, and 303.

[0133] Step 301: Obtain error code data of IPTV service of the target service platform in the target area within multiple second historical time periods; the multiple second historical time periods are time periods that match the period to be warned.

[0134] In this embodiment, multiple historical second time periods refer to time periods that match the time period to be warned. In this example, the multiple historical second time periods may or may not include the first historical time period. Specifically, it can be determined according to business needs, and this embodiment does not impose any restrictions on this.

[0135] After obtaining the historical error code data for the first historical period, error code data for IPTV services of the target business platform in multiple second historical periods in the target area can be obtained.

[0136] After obtaining the error code data of IPTV services in multiple second historical time periods of the target service platform in the target area, proceed to step 302.

[0137] Step 302: Calculate the average value of the error code data to obtain the average error code data.

[0138] After obtaining the error code data of IPTV services of the target service platform in multiple second historical periods in the target area, the average error code data can be calculated to obtain the average error code data, that is, the average error code data = error code data / number of multiple second historical periods.

[0139] After calculating the average error code data to obtain the average error code data, proceed to step 303.

[0140] Step 303: If the absolute value of the difference between the historical error code data and the average error code data is less than a set value, the historical error code data is processed based on the autoregressive integral moving average model to predict the predicted error code data.

[0141] After calculating the average error code data, you can compare the absolute value of the difference between the historical error code data and the average error code data with the set value.

[0142] If the absolute value of the difference between historical error code data and average error code data is less than a set value, the historical error code data can be processed based on the autoregressive integral moving average model to predict the predicted error code data.

[0143] If the absolute value of the difference between historical error code data and average error code data is greater than or equal to a set value, then the historical error code data can be replaced with the average error code data, and the error code data prediction process can be performed. This implementation process can be combined with... Figure 4 The following is a detailed description.

[0144] Reference Figure 4 The flowchart illustrates another method for obtaining predicted error code data provided in an embodiment of this application. Figure 4 As shown, the method for obtaining predicted error code data may include steps 401 and 402.

[0145] Step 401: If the absolute value of the difference between the historical error code data and the average error code data is greater than or equal to a set value, replace the historical error code data with the average error code data.

[0146] In this embodiment, if the absolute value of the difference between historical error code data and average error code data is greater than or equal to a set value, the historical error code data can be replaced with the average error code data.

[0147] Step 402: Process the average error code data based on the autoregressive integral moving average model to predict the predicted error code data.

[0148] After replacing historical error code data with average error code data, the average error code data can be processed based on an autoregressive integral moving average model to predict the predicted error code data. The above implementation can be described with reference to the following example:

[0149] To ensure the accuracy of the measurement, when calculating the error code baseline for one hour, it is necessary to determine the reasonableness of the error code count Msample for the current hour.

[0150] If the deviation between Msample and the historical average total number of error codes Mavg is too large, and the value is 10% of the average (including 0 values) or 10 times the average value, remove it and replace it with the average value.

[0151] The current internal system operation and maintenance status is used, and the historical current hourly average value is used instead.

[0152] Arima makes predictions based on historical time series, therefore the data sample must strictly adhere to the integrity of 24 records per address per day. Otherwise, the training will deviate, and the prediction will fail.

[0153] After calling the pre-trained autoregressive integral moving average model to process the historical error code data and predict the target error code data of the IPTV service target type in the target area during the warning period, step 104 is executed.

[0154] Step 104: Calculate the error code deviation based on the predicted error code data and the historical error code data.

[0155] Error code deviation can be used to indicate the degree of deviation between error codes from two matching time periods.

[0156] After obtaining the predicted error code data, the error code deviation can be calculated based on the predicted and historical error code data. Before calculating the error code deviation, it is necessary to determine the validity of the predicted and historical error code data. If valid, the error code deviation calculation process can then proceed. This implementation process can be combined with... Figure 5 The following is a detailed description.

[0157] Reference Figure 5 The flowchart illustrates the steps of an error code deviation calculation method provided in an embodiment of this application. Figure 5 As shown, the error code deviation calculation method may include steps 501 and 502.

[0158] Step 501: Verify the validity of the predicted error code data and the historical error code data.

[0159] In this embodiment, after obtaining the predicted error code data and historical error code data, the validity of the predicted error code data and historical error code data can be verified. Specifically, it can be determined whether the predicted error code data is greater than 0, and whether the historical error code data is greater than 0. If both the predicted error code data and the historical error code data are greater than 0, then both the predicted error code data and the historical error code data can be determined to be valid.

[0160] After verifying the validity of the predicted error code data and historical error code data, proceed to step 502.

[0161] Step 502: If both the predicted error code data and the historical error code data are valid, calculate the error code deviation based on the predicted error code data and the historical error code data.

[0162] If the validity of the obtained predicted error code data and historical error code data indicates that both are valid, then the error code deviation can be calculated based on the predicted and historical error code data. The calculation process for the error code deviation can be combined with... Figure 6 The following is a detailed description.

[0163] Reference Figure 6 The flowchart illustrates another method for calculating error code deviation provided in an embodiment of this application. Figure 6 As shown, the error code deviation calculation method may include steps 601, 602, 603 and 604.

[0164] Step 601: Obtain the data difference between the historical error code data and the predicted error code data.

[0165] In this embodiment, after obtaining historical error code data and predicted error code data, the data difference between historical error code data and predicted error code data can be calculated, i.e., historical error code data - predicted error code data.

[0166] After obtaining the data difference between historical error code data and predicted error code data, proceed to step 602.

[0167] Step 602: Obtain the absolute value corresponding to the data difference and round it to obtain the integer value of the error code.

[0168] After obtaining the data difference between historical error code data and predicted error code data, we can obtain the absolute value of this data difference and round it to get the integer value of the error code, namely abs(historical error code data - predicted error code data).

[0169] After obtaining the integer value of the error code, proceed to step 604.

[0170] Step 603: Obtain the maximum value from the predicted error code data and the historical error code data.

[0171] After obtaining historical error code data and predicted error code data, the maximum value between the historical error code data and predicted error code data can be obtained, i.e., max(historical error code data, predicted error code data).

[0172] After obtaining the maximum value from the historical error code data and the predicted error code data, proceed to step 604.

[0173] Step 604: Calculate the error code deviation based on the integer value of the error code and the maximum value.

[0174] After obtaining the maximum value and the integer value of the error code, the error code deviation can be calculated based on the integer value of the error code and the maximum value. The error code deviation can be calculated as shown in the following formula (1):

[0175] N=abs(Measure5-Predict5) / max(Measure5, Predict5)*100 (1)

[0176] In the above formula (1), N is the error code deviation, Measure5 is the historical error code data, and Predict5 is the predicted error code data.

[0177] After calculating the error code deviation based on the predicted error code data and historical error code data, proceed to step 105.

[0178] Step 105: If the error code deviation is greater than the deviation threshold, generate IPTV service warning information corresponding to the target service platform according to the target area and the target type.

[0179] The deviation threshold refers to a pre-set threshold used to determine whether to issue a warning to the business platform. The specific value of the deviation threshold can be determined according to business needs, and this embodiment does not impose any restrictions on it.

[0180] After calculating the error code deviation based on predicted error code data and historical error code data, the magnitude of the error code deviation can be compared with the deviation threshold.

[0181] If the error code deviation exceeds the deviation threshold, an IPTV service warning message corresponding to the target service platform is generated based on the target region and target type for warning purposes. For example... Figure 11 As shown, when issuing an alarm, you can set the corresponding alarm name, alarm level, status, alarm location, duration, and other information.

[0182] This application embodiment uses an autoregressive integral moving average model combined with historical error code data from different time periods to predict error code data for the corresponding future time periods. This can achieve the goal of automatically adjusting the warning value in different time periods, thereby improving the accuracy of the warning and solving the problem of large errors in the existing alarm system.

[0183] In this embodiment, after generating the IPTV service early warning information corresponding to the target service platform, a dispatch prompt information corresponding to the target service platform can also be generated to prompt the target service platform to handle the fault in a timely manner. This implementation process can be combined with the following... Figure 7 The following is a detailed description.

[0184] Reference Figure 7 The flowchart illustrates the steps of a dispatch notification information sending method provided in an embodiment of this application. Figure 7 As shown, the method for sending the dispatch notification information may include steps 701 and 702.

[0185] Step 701: Generate the dispatch prompt information corresponding to the target business platform.

[0186] In this embodiment, if the error code deviation is greater than the deviation threshold, a dispatch prompt message corresponding to the target business platform can be generated.

[0187] Step 702: Send the dispatch notification information to the target business platform so that the target business platform can handle the fault dispatch.

[0188] Then, the dispatch notification information can be sent to the target business platform so that the target business platform can dispatch the fault handling.

[0189] In practical implementation, fault warning matching can be performed based on the error code baseline map and the self-learning early warning model of this technology; if the number of a certain error code exceeds the historical fluctuation range, an early warning is triggered; if it exceeds the fluctuation range by 10%, a group fault dispatch mechanism is triggered. Figure 10 As shown, after obtaining the predicted error code data for the target type in each time period, an error code baseline map can be drawn. The error code baseline map can be used to determine whether the dispatch prompt condition has been met. If so, the group fault dispatch mechanism is triggered.

[0190] The IPTV service early warning process in this application embodiment can be as follows: Figure 8 and Figure 9 As shown.

[0191] Reference Figure 8 This diagram illustrates an IPTV service early warning process provided in an embodiment of this application. (Refer to...) Figure 9 The diagram illustrates a data processing flow for IPTV services provided in an embodiment of this application.

[0192] like Figure 8As shown, error codes can be collected and stored in the database based on the SQM acquisition platform. In specific implementation, a set-top box QoS soft probe can be used to receive Android broadcast cached error codes, and push them to the acquisition device (i.e., the SQM acquisition platform) every 1 minute. The original error code records are displayed in a pop-up window on the SQM acquisition platform and sent to Arima for data aggregation. This yields a multi-dimensional hourly summary of error codes. When the summary results meet the alarm conditions, alarms can be dispatched based on the data aggregation results from Arima.

[0193] like Figure 9 As shown, the early warning process may include the following steps:

[0194] 1. The Android middleware receives abnormal OS terminals and broadcasts error code alarms;

[0195] 2. The soft probe receives Android broadcast cached error codes and pushes them to the acquisition machine every minute.

[0196] 3. The collect module collects raw XML to a disk file;

[0197] 4. The area data analysis module reads XML and sorts error codes by dimension, as well as the number of set-top box terminals that have generated error codes.

[0198] 5. It can record the original error codes and summarize the error codes;

[0199] 6. The integrated alarm module locates the error codes and the increase in error codes from the previous 7 days. When the increase exceeds the threshold (e.g., 70%), it outputs an alarm indicating an abnormal increase in error codes.

[0200] 7. Maintenance personnel can perform the following actions: 1) receive alarm notifications; 2) view the historical trend chart of error codes in the end-to-end system by region; 3) track the original error code alarm records of the terminal; 4) locate the fault location, faulty equipment, reset, and repair the fault.

[0201] The early warning method provided in this application determines the corresponding warning period for a target service platform within a target area, obtains historical error code data of the target type of IPTV service within the target area that matches the warning period, calls a pre-trained autoregressive integral moving average model to process the historical error code data, predicts the predicted error code data of the target type of IPTV service within the warning period of the target service platform in the target area, and calculates the error code deviation based on the predicted error code data and the historical error code data. If the error code deviation is greater than the deviation threshold, an early warning information for the IPTV service corresponding to the target service platform is generated based on the target area and target type. This application embodiment, by using an autoregressive integral moving average model combined with historical error code data from different time periods to predict error code data for future corresponding time periods, can achieve the goal of automatically adjusting the early warning value in different time periods, thereby improving the accuracy of early warning and solving the problem of large errors in existing alarm systems.

[0202] Reference Figure 12 The diagram shows a structural schematic of an early warning device provided in an embodiment of this application, such as... Figure 12 As shown, the early warning device 1200 may include the following modules:

[0203] The warning period determination module 1210 is used to determine the warning period corresponding to the target business platform in the target area;

[0204] Historical data acquisition module 1220 is used to acquire historical error code data of the target type of IPTV service within the target area of ​​the target service platform, which matches the warning period;

[0205] The prediction data acquisition module 1230 is used to call a pre-trained autoregressive integral moving average model to process the historical error code data and predict the target type of IPTV service of the target service platform in the target area during the warning period.

[0206] The deviation calculation module 1240 is used to calculate the error code deviation based on the predicted error code data and the historical error code data;

[0207] The warning information generation module 1250 is used to generate IPTV service warning information corresponding to the target service platform according to the target area and the target type when the error code deviation is greater than the deviation threshold.

[0208] Optionally, the device further includes:

[0209] The intermediate model acquisition module is used to assign pre-configured model parameters to the initial autoregressive integral moving average model to obtain the intermediate autoregressive integral moving average model.

[0210] The error data acquisition module is used to acquire first error code data of a specified type for IPTV services within a first historical period and second error code data of a specified type for IPTV services within a second historical period; wherein the first historical period is earlier than the second historical period, and the first historical period and the second historical period are two adjacent periods, and the specified type includes the target type;

[0211] The sub-error data acquisition module is used to split the first error code data and the second error code data according to a set time period length to obtain the first sub-error code data of the first error code data in N time periods, and the second sub-error code data of the second error code data in N time periods, where N is a positive integer;

[0212] The deviation factor calculation module is used to calculate the error code deviation factor corresponding to each time period based on the first sub-error code data and the second sub-error code data in each time period;

[0213] The model acquisition module is used to train the intermediate autoregressive integral moving average model based on the error code deviation factor to obtain the autoregressive integral moving average model.

[0214] Optionally, the prediction data acquisition module includes:

[0215] Error code data acquisition unit, used to acquire error code data of IPTV service of the target service platform in the target area within multiple second historical time periods; the multiple second historical time periods are time periods that match the period to be warned;

[0216] An average error data calculation unit is used to calculate the average value of the error code data to obtain average error code data.

[0217] The prediction code data acquisition unit is used to process the historical error code data based on the autoregressive integral moving average model to predict the predicted error code data when the absolute value of the difference between the historical error code data and the average error code data is less than a set value.

[0218] Optionally, the device further includes:

[0219] The code data replacement module is used to replace the historical error code data with the average error code data when the absolute value of the difference between the historical error code data and the average error code data is greater than or equal to a set value.

[0220] The error code prediction acquisition module is used to process the average error code data based on the autoregressive integral moving average model to predict the error code data.

[0221] Optionally, the deviation calculation module includes:

[0222] A validity verification unit is used to verify the validity of the predicted error code data and the historical error code data;

[0223] The deviation calculation unit is used to calculate the error code deviation based on the predicted error code data and the historical error code data, provided that both the predicted error code data and the historical error code data are valid.

[0224] Optionally, the deviation calculation unit includes:

[0225] The data difference acquisition subunit is used to acquire the data difference between the historical error code data and the predicted error code data.

[0226] The integer value acquisition subunit is used to acquire the absolute value corresponding to the data difference, and round it to obtain the integer value of the error code;

[0227] The maximum value acquisition subunit is used to acquire the maximum value between the predicted error code data and the historical error code data;

[0228] The deviation calculation subunit is used to calculate the error code deviation based on the integer value of the error code and the maximum value.

[0229] Optionally, the device further includes:

[0230] The prompt message generation module is used to generate dispatch prompt messages corresponding to the target business platform;

[0231] The prompt message sending module is used to send the dispatch prompt message to the target business platform so that the target business platform can handle the fault dispatch.

[0232] The early warning device provided in this application determines the corresponding warning period for a target service platform within a target area, acquires historical error code data of the target type of IPTV service within the target area that matches the warning period, calls a pre-trained autoregressive integral moving average model to process the historical error code data, and predicts the predicted error code data of the target type of IPTV service within the warning period of the target service platform in the target area. Based on the predicted error code data and the historical error code data, the error code deviation is calculated. If the error code deviation is greater than the deviation threshold, early warning information for the IPTV service corresponding to the target service platform is generated according to the target area and target type. This application embodiment, by using an autoregressive integral moving average model combined with historical error code data from different time periods to predict error code data for future corresponding time periods, can achieve the goal of automatically adjusting the early warning value in different time periods, thereby improving the accuracy of early warning and solving the problem of large errors in existing alarm systems.

[0233] This application also provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the aforementioned early warning method.

[0234] Figure 13 A schematic diagram of the structure of an electronic device 1300 according to an embodiment of the present invention is shown. Figure 13 As shown, the electronic device 1300 includes a central processing unit (CPU) 1301, which can perform various appropriate actions and processes according to computer program instructions stored in read-only memory (ROM) 1302 or loaded from storage unit 1308 into random access memory (RAM) 1303. The RAM 1303 may also store various programs and data required for the operation of the electronic device 1300. The CPU 1301, ROM 1302, and RAM 1303 are interconnected via bus 1304. An input / output (I / O) interface 1305 is also connected to bus 1304.

[0235] Multiple components in electronic device 1300 are connected to I / O interface 1305, including: input unit 1306, such as keyboard, mouse, microphone, etc.; output unit 1307, such as various types of monitors, speakers, etc.; storage unit 1308, such as disk, optical disk, etc.; and communication unit 1309, such as network card, modem, wireless transceiver, etc. Communication unit 1309 allows electronic device 1300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0236] The various processes and handling described above can be executed by processing unit 1301. For example, the methods of any of the above embodiments can be implemented as computer software programs tangibly contained in a computer-readable medium, such as storage unit 1308. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 1300 via ROM 1302 and / or communication unit 1309. When the computer program is loaded into RAM 1303 and executed by CPU 1301, one or more actions of the methods described above can be performed.

[0237] Additionally, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned early warning method.

[0238] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0239] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or computer program products. Therefore, embodiments of this application can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of this application can take the form of computer program products 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 code.

[0240] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, terminals (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0241] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxesFigure 1 The function specified in one or more boxes.

[0242] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal, causing a series of operational steps to be executed on the computer or other programmable terminal to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0243] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0244] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal that includes said element.

[0245] The above provides a detailed description of an early warning method, an early warning device, an electronic device, and a computer-readable storage medium provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An early warning method, characterized in that, The method includes: Determine the corresponding warning period for the target business platform within the target region; Obtain historical error code data of the target type of IPTV service within the target area of ​​the target service platform, which matches the warning period; The pre-configured model parameters are assigned to the initial autoregressive integral moving average model to obtain the intermediate autoregressive integral moving average model. Obtain first error code data of a specified type for IPTV services within a first historical period, and second error code data of a specified type for IPTV services within a second historical period; wherein the first historical period is earlier than the second historical period, and the first historical period and the second historical period are two adjacent periods, and the specified type includes the target type; The first error code data and the second error code data are split according to the set time period length to obtain the first sub-error code data of the first error code data in N time periods, and the second sub-error code data of the second error code data in N time periods, where N is a positive integer; Based on the first sub-error code data and the second sub-error code data within each time period, the error code deviation factor corresponding to each time period is calculated; The intermediate autoregressive integral moving average model is trained based on the error code deviation factors to obtain the autoregressive integral moving average model. The historical error code data is processed by calling a pre-trained autoregressive integral moving average model to predict the target error code data of the IPTV service target type in the target area during the warning period of the target service platform. The error code deviation is calculated based on the predicted error code data and the historical error code data. If the error code deviation exceeds the deviation threshold, an IPTV service warning message corresponding to the target service platform is generated based on the target region and the target type. The step of using a pre-trained autoregressive integral moving average model to process the historical error code data and predict the target error code data for the IPTV service of the target service platform in the target area during the warning period includes: Obtain error code data of IPTV services of the target service platform in the target area within multiple second historical time periods; the multiple second historical time periods are time periods that match the period to be warned; Calculate the average value of the error code data to obtain the average error code data; If the absolute value of the difference between the historical error code data and the average error code data is less than a set value, the historical error code data is processed based on the autoregressive integral moving average model to predict the predicted error code data. If the absolute value of the difference between the historical error code data and the average error code data is greater than or equal to a set value, the historical error code data is replaced with the average error code data; the average error code data is processed based on the autoregressive integral moving average model to predict the predicted error code data.

2. The method according to claim 1, characterized in that, The step of calculating the error code deviation based on the predicted error code data and the historical error code data includes: Verify the validity of the predicted error code data and the historical error code data; If both the predicted error code data and the historical error code data are valid, the error code deviation is calculated based on the predicted error code data and the historical error code data.

3. The method according to claim 2, characterized in that, The step of calculating the error code deviation based on the predicted error code data and the historical error code data includes: Obtain the data difference between the historical error code data and the predicted error code data; Obtain the absolute value corresponding to the data difference, and round it to get the integer value of the error code; Obtain the maximum value from the predicted error code data and the historical error code data; The error code deviation is calculated based on the integer value of the error code and the maximum value.

4. The method according to claim 1, characterized in that, After generating the IPTV service warning information corresponding to the target service platform based on the target region and the target type, the method further includes: Generate the order dispatch notification information corresponding to the target business platform; The dispatch notification information is sent to the target business platform so that the target business platform can handle the fault dispatch.

5. An early warning device, characterized in that, The device includes: The warning period determination module is used to determine the corresponding warning period for the target business platform within the target area; The historical data acquisition module is used to acquire historical error code data of the target type of IPTV service within the target area of ​​the target service platform, which matches the warning period; The intermediate model acquisition module is used to assign pre-configured model parameters to the initial autoregressive integral moving average model to obtain the intermediate autoregressive integral moving average model. The error data acquisition module is used to acquire first error code data of a specified type for IPTV services within a first historical period and second error code data of a specified type for IPTV services within a second historical period; wherein the first historical period is earlier than the second historical period, and the first historical period and the second historical period are two adjacent periods, and the specified type includes the target type; The sub-error data acquisition module is used to split the first error code data and the second error code data according to a set time period length to obtain the first sub-error code data of the first error code data in N time periods, and the second sub-error code data of the second error code data in N time periods, where N is a positive integer; The deviation factor calculation module is used to calculate the error code deviation factor corresponding to each time period based on the first sub-error code data and the second sub-error code data in each time period; The model acquisition module is used to train the intermediate autoregressive integral moving average model based on the error code deviation factors to obtain the autoregressive integral moving average model. The prediction data acquisition module is used to call a pre-trained autoregressive integral moving average model to process the historical error code data and predict the target error code data of the IPTV service of the target service platform in the target area during the warning period. The deviation calculation module is used to calculate the error code deviation based on the predicted error code data and the historical error code data; The early warning information generation module is used to generate IPTV service early warning information corresponding to the target service platform based on the target area and the target type when the error code deviation is greater than the deviation threshold. The prediction data acquisition module includes: Error code data acquisition unit, used to acquire error code data of IPTV service of the target service platform in the target area within multiple second historical time periods; the multiple second historical time periods are time periods that match the period to be warned; An average error data calculation unit is used to calculate the average value of the error code data to obtain average error code data. The prediction code data acquisition unit is used to process the historical error code data based on the autoregressive integral moving average model to predict the predicted error code data when the absolute value of the difference between the historical error code data and the average error code data is less than a set value. The code data replacement module is used to replace the historical error code data with the average error code data when the absolute value of the difference between the historical error code data and the average error code data is greater than or equal to a set value. The error code prediction acquisition module is used to process the average error code data based on the autoregressive integral moving average model to predict the error code data.

6. An electronic device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the warning method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the warning method according to any one of claims 1 to 4.

Images