Performance index processing method and device and terminal equipment

Abstract

The invention provides a performance index processing method and device and terminal equipment, and the method comprises the steps: obtaining historical business data which comprises values of business indexes when a plurality of performance indexes of an application program are different values; according to the historical business data, determining a plurality of target performance indexes in the plurality of performance indexes, and determining a regression coefficient of each target performance index, the regression coefficient being used for indicating an influence degree of the target performance indexes on the business indexes; and determining a maximum acceptable degradation value corresponding to each target performance index according to the regression coefficient of each target performance index and the minimum difference value of the significant change of the business index. And the alarm accuracy of the target performance index is improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the technical field of data processing, and in particular, to a method, an apparatus, and a terminal device for processing performance indicators. Background Art

[0002] The performance indicators of an application can affect the business indicators of the application. For example, the video playback clarity (performance indicator) of an application can affect the number of daily active users (business indicator) of the application.

[0003] Currently, when adjusting any performance indicator, since multiple performance indicators may affect each other, in order to avoid the change of the performance indicator having too great an impact on the business indicator, the maximum adjustable value of each performance indicator can be set based on manual experience, and then this value is determined as the alarm threshold. After the change of the performance indicator exceeds the maximum adjustable value, the terminal device can give an alarm. However, the accuracy of the maximum adjustable value determined based on manual experience is relatively low, which in turn leads to relatively low alarm accuracy of the performance indicator. Summary of the Invention

[0004] The present disclosure provides a method, an apparatus, and a terminal device for processing performance indicators, which are used to solve the technical problem of relatively low alarm accuracy of performance indicators in the prior art.

[0005] In a first aspect, the present disclosure provides a method for processing performance indicators, and the method includes:

[0006] Obtain historical service data, where the historical service data includes the values of the business indicator when the application has different values for multiple performance indicators;

[0007] According to the historical service data, determine multiple target performance indicators among the multiple performance indicators, and determine the regression coefficient of each target performance indicator, where the regression coefficient is used to indicate the influence degree of the target performance indicator on the business indicator;

[0008] According to the regression coefficient of each target performance indicator and the minimum difference value of significant change of the business indicator, determine the maximum acceptable degradation value corresponding to each target performance indicator.

[0009] In a second aspect, the present disclosure provides a performance indicator processing apparatus, and the performance indicator processing apparatus includes an obtaining module, a first determining module, and a second determining module, where:

[0010] The obtaining module is configured to obtain historical service data, where the historical service data includes the values of the business indicator when the application has different values for multiple performance indicators;

[0011] The first determination module is configured to determine, according to the historical service data, multiple target performance metrics among the multiple performance metrics, and determine a regression coefficient for each target performance metric, where the regression coefficient is used to indicate the influence degree of the target performance metric on the service metric;

[0012] The second determination module is configured to determine, according to the regression coefficient of each target performance metric and the minimum difference value of a significant change in the service metric, the maximum acceptable degradation value corresponding to each target performance metric.

[0013] In a third aspect, an embodiment of the present disclosure provides a terminal device including: a processor and a memory;

[0014] The memory stores computer-executable instructions;

[0015] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the processing method of the performance metrics as described in the first aspect and various possible aspects of the first aspect.

[0016] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the processing method of the performance metrics as described in the first aspect and various possible aspects of the first aspect is implemented.

[0017] The present disclosure provides a processing method, device, and terminal device for performance metrics. The terminal device can obtain historical service data, where the historical service data includes the values of the service metric when the application program has different values for multiple performance metrics. According to the historical service data, multiple target performance metrics are determined among the multiple performance metrics, and a regression coefficient for each target performance metric is determined, where the regression coefficient is used to indicate the influence degree of the target performance metric on the service metric. According to the regression coefficient of each target performance metric and the minimum difference value of a significant change in the service metric, the maximum acceptable degradation value corresponding to each target performance metric is determined. In the above method, since the terminal device can combine the relationship between multiple performance metrics and the service metric and accurately determine the maximum acceptable degradation value corresponding to each performance metric within the range of the minimum difference value of a significant change in the service metric, the accuracy of the maximum acceptable degradation value is relatively high. The terminal device can alarm each performance metric based on the maximum acceptable degradation value, thereby improving the alarm accuracy of the performance metrics. Description of the Drawings

[0018] To more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0020] Figure 2 A schematic flowchart of a method for processing a performance index provided by an embodiment of the present disclosure;

[0021] Figure 3 A schematic diagram of an influence curve provided by an embodiment of the present disclosure;

[0022] Figure 4 A schematic diagram of a process for determining a target performance index provided by an embodiment of the present disclosure;

[0023] Figure 5 A schematic diagram of a method for determining an exchange relationship provided by an embodiment of the present disclosure;

[0024] Figure 6 A schematic diagram of an optimization process for a reference performance index provided by an embodiment of the present disclosure;

[0025] Figure 7 A schematic diagram of the structure of a processing device for a performance index provided by an embodiment of the present disclosure;

[0026] Figure 8 A schematic diagram of the structure of another processing device for a performance index provided by an embodiment of the present disclosure;

[0027] Figure 9 A schematic diagram of the structure of a terminal device provided by an embodiment of the present disclosure. Detailed implementation manners

[0028] Here, the exemplary embodiments will be described in detail, and the examples are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present disclosure. On the contrary, they are only examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0029] For ease of understanding, the concepts related to the embodiments of the present disclosure will be described below.

[0030] Terminal device: A device with wireless transceiver functions. The terminal device can be deployed on land, including indoor or outdoor, handheld, wearable or vehicle-mounted. The terminal device can be a mobile phone, a tablet (Pad), a computer with wireless transceiver functions, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a vehicle-mounted terminal device, a wireless terminal in self-driving, a wireless terminal device in remote medical, a wireless terminal device in smart grid, a wireless terminal device in transportation safety, a wireless terminal device in smart city, a wireless terminal device in smart home, a wearable terminal device, etc. The terminal device involved in the embodiments of the present disclosure can also be referred to as a terminal, a user equipment (UE), an access terminal device, a vehicle-mounted terminal, an industrial control terminal, a UE unit, a UE station, a mobile station, a mobile device, a remote station, a remote terminal device, a mobile device, a UE terminal device, a wireless communication device, a UE agent or a UE device, etc. The terminal device can also be fixed or mobile.

[0031] Next, in combination with Figure 1 , the application scenarios of the embodiments of the present disclosure will be described.

[0032] Figure 1 It is a schematic diagram of an application scenario provided for the embodiments of the present disclosure. Please refer to Figure 1 , which includes the performance indicators and business indicators of the application. Among them, the performance indicators of the application can include video frame rate, video clarity,..., UI fluency, etc., and the business indicators of the application can include the number of daily active users and the number of times the application is used, etc. If the terminal device reduces the video clarity of the application, it will cause a decrease in the number of daily active users in the business indicators.

[0033] It should be noted that Figure 1 only exemplarily shows the relationship between the business indicators and the performance indicators, and does not limit the application scenarios of the embodiments of the present disclosure.

[0034] In the related art, the performance metrics of an application can affect the business metrics of the application. Since there are many types of performance metrics, and multiple performance metrics may affect each other (for example, increasing performance metric A will cause performance metric B to decrease), therefore, in order to avoid the impact of changes in performance metrics on business metrics from being too large, it is necessary to set a maximum adjustable value (alarm threshold) for each performance metric. When the change value of the performance metric exceeds this alarm threshold, the terminal device can alarm for this performance metric. Currently, the alarm threshold corresponding to each performance metric can be determined based on manual experience. However, the accuracy of the alarm threshold of the performance metric determined by manual experience is relatively low, which in turn leads to a relatively low alarm accuracy of the performance metric.

[0035] To solve the technical problems in the related art, an embodiment of the present disclosure provides a method for processing performance metrics. The terminal device can obtain historical business data. Among them, the historical business data can include the values of the business metrics when the application has different values for multiple performance metrics. The terminal device can determine multiple candidate performance metrics from the multiple performance metrics according to the historical business data, and process the multiple candidate performance metrics through a multiple linear regression method to obtain the P-value of each candidate performance metric. The P-value can be used to indicate whether there is a significant difference between the regression coefficient of the candidate performance metric and a preset value (which can be 0). The candidate performance metrics with P-values less than or equal to the preset threshold are determined as target performance metrics. The terminal device can determine the maximum acceptable degradation value corresponding to each target performance metric according to the regression coefficient of each target performance metric and the minimum difference value of significant changes in the business metrics. In the above method, since the regression coefficient of the target performance metric can represent the influence degree of the target performance metric on the business metric, when the influence of the target performance metric on the business metric is large, the terminal device can accurately determine the maximum acceptable degradation value corresponding to the target performance metric within the range of the minimum difference value of significant changes in the business metric based on the regression coefficient of the target performance metric, thereby improving the accuracy of the maximum acceptable degradation value and the alarm accuracy of the target performance metric.

[0036] The following uses specific embodiments to detail the technical solutions of the present disclosure and how the technical solutions of the present disclosure solve the above technical problems. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present disclosure will be described below with reference to the drawings.

[0037] Figure 2 It is a schematic flowchart of a method for processing performance metrics provided by an embodiment of the present disclosure. Please refer to Figure 2 This method may include:

[0038] S201. Obtain historical business data.

[0039] The execution subject of the embodiments of the present disclosure may be a terminal device or a processing device for performance indicators provided in the terminal device. The embodiments of the present disclosure do not limit this. Among them, the processing device for performance indicators may be software or a combination of software and hardware. The embodiments of the present disclosure do not limit this.

[0040] Among them, the historical service data may include the values of service indicators when the application has different values for multiple performance indicators. For example, the application may be a program to be updated. After the application is developed, developers can update multiple performances of the application. During the update process, it is necessary to determine the values of the performance indicators of the application, so as to play a positive promoting role in the service indicators of the application.

[0041] Optionally, the performance indicator is used to indicate the performance of the application. For example, the performance indicator may include a client performance indicator, a playback performance indicator, and a production-end performance indicator. For example, the client performance indicator may include the smoothness of the user interface (UI) in the application, dynamic resources (such as power consumption), and static resources (such as storage space). The embodiments of the present disclosure do not limit this. For example, the playback performance indicator may include the playback frame rate of the video, the playback clarity of the video, etc. The embodiments of the present disclosure do not limit this. For example, the production-end performance indicator may include the number of foods processed per unit time, the number of query responses per second, etc. The embodiments of the present disclosure do not limit this.

[0042] Optionally, the service indicator is used to indicate the performance of the application at the service end. For example, the service indicator may include the number of daily active users of the application. The service indicator may also include the number of times users use the application during a historical period. The embodiments of the present disclosure do not limit this.

[0043] Optionally, when the performance indicator has different values, the service indicator also has corresponding values. For example, if the performance indicators are: video clarity 1, video playback frame rate 2, UI smoothness 3, the corresponding service indicator may be: the number of daily active users 10,000; if the performance indicators are: video clarity A, video playback frame rate B, UI smoothness C, the corresponding service indicator may be: the number of daily active users 20,000.

[0044] It should be noted that when multiple performance indicators have different values, the values of the service indicators can be the same or different. The embodiments of the present disclosure do not limit this. Moreover, the historical service data may include multiple sets of corresponding relationships between performance indicators and service indicators. For example, the historical service data may include the corresponding relationships between performance indicator 1, performance indicator 2 and the service indicator, or may include the corresponding relationships between performance indicator 2, performance indicator 3 and the service indicator. Also, the historical service data may include the corresponding relationships between the value of performance indicator 1 being A, the value of performance indicator 2 being B and the value of the service indicator, and the historical service data may further include the corresponding relationships between the value of performance indicator 1 being C, the value of performance indicator 2 being D and the value of the service indicator. The embodiments of the present disclosure do not limit this.

[0045] Optionally, the terminal device can obtain historical service data from the database. For example, the database may store the corresponding relationships between performance indicators and service indicators, and the terminal device can obtain historical service data from the database.

[0046] It should be noted that the terminal device can also obtain historical service data based on any feasible implementation manner. The embodiments of the present disclosure do not limit this. Moreover, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the embodiments of the present disclosure are all information and data that have been authorized by the user or fully authorized by all parties. Also, the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards, and corresponding operation entrances are provided for the user to select authorization or rejection.

[0047] S202. Determine multiple target performance indicators from multiple performance indicators according to the historical service data, and determine the regression coefficient of each target performance indicator.

[0048] Optionally, the target performance indicator can be a performance indicator that affects the service indicator. For example, in actual applications, the application program may include multiple performance indicators. The values of some performance indicators will have a positive or negative impact on the value of the service indicator. These performance indicators can be the target performance indicators. For example, if the value of performance indicator 1 increases, the value of the service indicator will increase; if the value of performance indicator 2 decreases, the value of the service indicator will increase; if the value of performance indicator 3 increases, the value of the service indicator remains unchanged. Then the terminal device can determine that the target performance indicators may include performance indicator 1 and performance indicator 2.

[0049] Among them, the regression coefficient can be used to indicate the degree of influence of the target performance indicator on the business indicator. For example, the larger the regression coefficient, the greater the degree of influence of the target performance indicator on the business indicator; the smaller the regression coefficient, the smaller the degree of influence of the target performance indicator on the business indicator. For example, if the regression coefficient of target performance indicator 1 is 0.05 and the regression coefficient of target performance indicator 2 is 0.1, the terminal device can determine that the degree of influence of target performance indicator 1 on the business indicator is greater than that of target performance indicator 2 on the business indicator.

[0050] Optionally, based on the following feasible implementation, the terminal device can determine multiple target performance indicators from multiple performance indicators according to the historical business data: determine multiple candidate performance indicators from multiple performance indicators according to the historical business data, process the multiple candidate performance indicators through the multiple linear regression method to obtain the P-value of each candidate performance indicator, and determine the candidate performance indicators with P-values less than or equal to the preset threshold as the target performance indicators.

[0051] Among them, there is no problem of multicollinearity among the multiple candidate performance indicators. For example, when performing linear regression, if the correlation between two performance indicators is relatively high, it will lead to the problem of multicollinearity. There is no problem of multicollinearity among the multiple candidate performance indicators, that is, the correlation among the multiple candidate performance indicators is relatively low.

[0052] Optionally, after the terminal device obtains multiple candidate performance indicators, it can further determine the variance inflation factor (VIF) of the multiple candidate performance indicators, and then further determine whether there is a problem of multicollinearity among the multiple candidate performance indicators. For example, the VIF can indicate the severity of multicollinearity in the multiple linear regression model. If the VIF values of the multiple candidate performance indicators are low, it means that there is no problem of multicollinearity among the multiple candidate performance indicators. If the VIF values of the multiple candidate performance indicators are high, it means that there is still a problem of multicollinearity among the multiple candidate performance indicators. This can effectively avoid the problem of multicollinearity and improve the accuracy of determining the target performance indicators.

[0053] Among them, the P value is used to indicate whether there is a significant difference between the regression coefficient of the to-be-selected performance index and the preset value. For example, the terminal device can use multiple to-be-selected performance indexes as input variables, perform linear regression processing on the multiple to-be-selected performance indexes, and then obtain the regression coefficient of each to-be-selected performance index and the P value of each to-be-selected performance index. If the P value is small, it indicates that there is a significant difference between the regression coefficient of the to-be-selected performance index and the preset value, that is, the influence degree of the to-be-selected performance index on the service index is large. If the P value is large, it indicates that there is no significant difference between the regression coefficient of the to-be-selected performance index and the preset value, that is, the influence degree of the to-be-selected performance index on the service index is small.

[0054] It should be noted that the electronic device can determine the regression coefficient and P value of the to-be-selected performance index based on any feasible method, and the embodiments of the present disclosure do not limit this.

[0055] Optionally, the terminal device determines multiple to-be-selected performance indexes from multiple performance indexes according to historical service data. Specifically, it can be: processing the historical service data through the lasso linear regression method to obtain the influence degree curve of each performance index on the service index, sorting the multiple performance indexes according to the order in which the influence degree becomes the preset value based on the multiple influence degree curves, and determining the first N performance indexes in the sorted multiple performance indexes as multiple initial performance indexes, where N is an integer greater than 1, and determining multiple to-be-selected performance indexes from the multiple initial performance indexes according to the correlation between the multiple initial performance indexes. In this way, the correlation between the multiple to-be-selected performance indexes and the service index is relatively high, and thus the accuracy of the target performance index can be improved, and the alarm accuracy of the target performance index can be improved.

[0056] Optionally, the influence degree can be the regression coefficient of the performance index. For example, in the actual application process, when processing multiple performance indexes in the historical service data through the lasso linear regression method, the terminal device can continuously increase the penalty function, and thus continuously compress the regression coefficient of the performance index. For example, as the penalty term increases, the performance index whose regression coefficient becomes 0 earlier is less important, and the performance index whose regression coefficient becomes 0 later is more important. Moreover, the terminal device can sort the importance of the multiple performance indexes based on the order of becoming 0.

[0057] Next, in combination with Figure 3 , the influence degree curve of the performance index on the service index will be described.

[0058] Figure 3 is a schematic diagram of an influence degree curve provided by an embodiment of the present disclosure. Please refer to Figure 3, including: a coordinate system. Among them, the vertical axis of the coordinate system can be the coefficient of the performance index, and the horizontal axis of the coordinate system can be the penalty parameter. The coordinate system can include Curve A, Curve B, Curve C, and Curve D. Among them, each curve corresponds to a performance index. For example, Curve A can indicate the relationship between the coefficient of Performance Index 1 and the penalty parameter, Curve B can indicate the relationship between the coefficient of Performance Index 2 and the penalty parameter, Curve C can indicate the relationship between the coefficient of Performance Index 3 and the penalty parameter, and Curve D can indicate the relationship between the coefficient of Performance Index 4 and the penalty parameter.

[0059] It should be noted that as the penalty parameter becomes larger and larger, Figure 3 the absolute value of the coefficient of the performance index corresponding to each curve in the illustrated embodiment will become smaller and smaller. After the penalty parameter is greater than the preset parameter value, the coefficient of each performance index is 0.

[0060] It should be noted that in Figure 3 the illustrated embodiment, if the ordinate of the curve becomes 0 later, the greater the influence of the performance index corresponding to the curve on the business index. For example, in Figure 3 the illustrated embodiment, the performance index corresponding to Curve D has the greatest influence on the business index, and the performance index corresponding to Curve A has the smallest influence on the business index.

[0061] Optionally, the initial performance index is the N indexes with the greatest influence on the business index. For example, after the terminal device processes the historical business data based on the lasso linear regression method, it is determined that 30 performance indexes will affect the business index. The terminal device can determine the 10 performance indexes with the greatest impact on the business index as the initial performance indexes.

[0062] Optionally, the preset value can be 0, and the terminal device can sort multiple performance indexes based on the order in which the influence degree becomes 0. For example, if the influence degree of a performance index on the business index becomes 0 later, the order of this performance index is more forward. For example, in Figure 3 the illustrated embodiment, Curve A corresponds to Performance Index 1, Curve B corresponds to Performance Index 2, Curve C corresponds to Performance Index 3, and Curve D corresponds to Performance Index 4. Since the influence degree of Curve D becomes 0 the latest, when sorting, the first performance index is Performance Index 4. Similarly, the second performance index is Performance Index 3, the third performance index is Performance Index 2, and the fourth performance index is Performance Index 1. If N is 2, the terminal device can determine Performance Index 3 and Performance Index 4 as the initial performance indexes.

[0063] Optionally, the correlation degree can be used to indicate the degree of correlation between performance metrics. For example, the video playback frame rate and the video smoothness affect each other. Therefore, the correlation degree between the video playback frame rate and the video smoothness is relatively high. For example, the video playback frame rate and the storage space do not affect each other. Therefore, the correlation degree between the video playback frame rate and the storage space is relatively low.

[0064] Among them, the correlation degree between multiple candidate performance metrics is less than a preset correlation degree. For example, the degree of mutual influence between multiple candidate performance metrics determined by the terminal device is relatively small, which can avoid the problem of multicollinearity and thus improve the accuracy of the target performance metric.

[0065] Optionally, the terminal device determines multiple candidate performance metrics from multiple initial performance metrics according to the correlation degree between the multiple initial performance metrics. Specifically, it can be: determining the correlation degree between every two initial performance metrics, and performing a duplicate removal process on the multiple initial performance metrics according to the correlation degree between every two initial performance metrics to obtain multiple candidate performance metrics.

[0066] Optionally, the terminal device can determine the correlation degree between every two initial performance metrics based on the pre-set correlation degree relationship between performance metrics. For example, the terminal device can pre-obtain all performance metrics and determine the correlation degree between every two performance metrics to obtain a correlation degree set. Therefore, after the terminal device obtains multiple initial performance metrics, it can determine the correlation degree between every two initial performance metrics based on this correlation degree set.

[0067] Optionally, the terminal device can also determine the correlation degree between two initial performance metrics based on any other feasible implementation method (for example, determining the correlation degree between two initial performance metrics based on the variance inflation factor), and the embodiments of the present disclosure do not limit this.

[0068] Among them, the duplicate removal process can be used to delete one of the two initial performance indicators, and the correlation between the two initial performance indicators is greater than or equal to a preset correlation. For example, if the correlation between the initial performance indicator 1 and the initial performance indicator 2 is greater than or equal to the preset correlation, the terminal device can perform duplicate removal on the initial performance indicator 1 and the initial performance indicator 2, and retain the initial performance indicator 1 or the initial performance indicator 2. For example, based on multiple influence curves, the terminal device obtains the initial performance indicator 1, the initial performance indicator 2, the initial performance indicator 3, and the initial performance indicator 4. If the correlation between the initial performance indicator 3 and the initial performance indicator 4 is greater than or equal to the preset correlation, and the correlation between other initial performance indicators is less than the preset correlation, then after the terminal device performs duplicate removal on the multiple initial performance indicators, the candidate performance indicators obtained can be: the initial performance indicator 1, the initial performance indicator 2, and the initial performance indicator 3. The candidate performance indicators obtained by the terminal device can also be: the initial performance indicator 1, the initial performance indicator 2, and the initial performance indicator 4. In this way, based on the duplicate removal process, the problem of collinearity can be effectively avoided, the accuracy of determining the target performance indicator can be improved, and thus the accuracy of the alarm threshold can be improved.

[0069] Optionally, the terminal device can process the multiple candidate performance indicators based on the multiple linear regression method to obtain the P value of each candidate performance indicator. For example, the terminal device can process the multiple candidate performance indicators based on any feasible multiple linear regression method. This disclosure embodiment does not limit this, and after the terminal device processes the multiple candidate performance indicators based on the multiple linear regression method, not only can the P value of each candidate performance indicator be obtained, but also the regression coefficient of each candidate performance indicator can be obtained.

[0070] Optionally, the terminal device can determine the candidate performance indicator with a P value less than or equal to the preset threshold as the target performance indicator. For example, the preset threshold can be 0.05. If the P value of the candidate performance indicator is less than or equal to 0.05, it means that there is a significant difference between the regression coefficient of the candidate performance indicator and 0 (preset value). Therefore, the candidate performance indicator has a greater impact on the business indicator, and the terminal device can determine the candidate performance indicator as the target performance indicator. If the P value of the candidate performance indicator is greater than 0.05, it means that there is no significant difference between the regression coefficient of the candidate performance indicator and 0. Therefore, the candidate performance indicator has a smaller impact on the business indicator, and the candidate performance indicator is not the target performance indicator. For example, the preset threshold is 0.05. If the P value of the candidate performance indicator 1 is 0.01, the P value of the candidate performance indicator 2 is 0.05, and the P value of the candidate performance indicator 3 is 0.08, then the terminal device can determine the candidate performance indicator 1 and the candidate performance indicator 2 as the target performance indicators.

[0071] It should be noted that the preset threshold can be any set value, and the embodiments of the present disclosure do not limit this.

[0072] Next, in combination with Figure 4 , the process of determining the target performance index will be described.

[0073] Figure 4 FIG. is a schematic diagram of a process for determining a target performance index provided by an embodiment of the present disclosure. Please refer to Figure 4 , including: a coordinate system. Among them, the vertical axis of the coordinate system can be the coefficient of the performance index, and the horizontal axis of the coordinate system can be the penalty parameter. The coordinate system may include curve A, curve B, curve C, curve D, and curve E. Among them, curve A corresponds to performance index 1, curve B corresponds to performance index 2, curve C corresponds to performance index 3, curve D corresponds to performance index 4, and curve E corresponds to performance index 5.

[0074] Please refer to Figure 4 , N is 4. Since the curve A corresponding to performance index 1 first becomes 0, the terminal device ( Figure 4 not shown) can determine that the initial performance index may include performance index 2, performance index 3, performance index 4, and performance index 5. Since the correlation between performance index 3 and performance index 4 is relatively high, the terminal device can determine that the candidate performance index may include performance index 2, performance index 3, and performance index 5.

[0075] Please refer to Figure 4 , the terminal device can perform multiple linear regression processing (relationship with the service index) on performance index 2, performance index 3, and performance index 5 to obtain the P value corresponding to each performance index. Since the P value of performance index 2 is relatively large, the terminal device can determine that the target performance index is performance index 3 and performance index 5. Moreover, since the regression coefficient of each performance index can be obtained during the multiple linear regression processing, the terminal device can also obtain the regression coefficient of performance index 3 and the regression coefficient of performance index 5.

[0076] In this way, the terminal device can determine the two performance indexes that have the greatest impact on the service index among multiple performance indexes, and there is no problem of multicollinearity between performance index 3 and performance index 5, thereby improving the accuracy of determining the alarm threshold of the performance index and improving the alarm accuracy of the performance index.

[0077] S203. Determine the maximum acceptable deterioration value corresponding to each target performance index according to the regression coefficient of each target performance index and the minimum difference value of the significant change of the service index.

[0078] Among them, the minimum difference value of significant change is used to indicate the value at which the business metric can change significantly. For example, after the minimum difference value of significant change in the business metric, the terminal device can determine that the business metric has changed significantly. For example, the minimum difference value of significant change in the number of daily active users is 30. If the number of daily active users increases by 30, the terminal device can determine that the number of daily active users has changed significantly (that is, during the experiment on the performance metric, the business metric can change). If the number of daily active users decreases by 1, the terminal device can determine that the number of daily active users has not changed significantly.

[0079] Optionally, the terminal device can determine the minimum difference value of significant change based on the following feasible implementation: determine multiple metric values of the business metric, determine the metric average value and the metric variance value corresponding to the business metric according to the multiple metric values of the business metric, and determine the minimum difference value of significant change corresponding to the business metric by means of a t-test according to the metric average value and the metric variance value corresponding to the business metric.

[0080] Optionally, the terminal device can determine multiple metric values of the business metric, as well as the metric average value and the metric variance value corresponding to the business metric, based on any feasible implementation, and the embodiments of the present disclosure do not limit this.

[0081] Optionally, the terminal device can determine the minimum difference value of significant change based on the following formula:

[0082]

[0083] Among them, is the metric average value of the experimental group, is the metric average value of the control group, μ 1 -μ 2 is the difference between the true metric average value of the experimental group and the metric average value of the control group (this value can be 0), s 1 is the metric variance value of the experimental group, s 1 is the metric variance value of the control group, n 1 is the number of users in the experimental group, n 2 is the number of users in the control group.

[0084] Based on the above formula, the terminal device can determine the minimum difference value corresponding to a significant change in the service metric. It should be noted that during the experiment, when the confidence level is different, the minimum difference value corresponding to the significant change is also different. For example, the lower the confidence level, the higher the accuracy of the minimum difference value of the significant change. For example, when the confidence level is 5%, the minimum difference value of the significant change in the service metric is value A, and when the confidence level is 10%, the minimum difference value of the significant change in the service metric is value B. Based on the above formula, if the variances of the experimental group and the control group are the same and the number of users is the same, the ratio of value B to value A is approximately

[0085] Optionally, after the terminal device determines the regression coefficient of the target performance metric and the minimum difference value corresponding to the significant change in the service metric, for any one target performance metric, the terminal device can determine the maximum acceptable degradation value corresponding to the target performance metric based on the following feasible implementation: Determine the ratio of the minimum difference value to the regression coefficient of the target performance metric, and determine the ratio as the maximum acceptable degradation value corresponding to the target performance metric.

[0086] Optionally, the terminal device can determine the maximum acceptable degradation value corresponding to the target performance metric based on the following formula:

[0087]

[0088] where A is the maximum acceptable degradation value, X min is the minimum difference value of the significant change, and β x is the regression coefficient corresponding to the target performance metric.

[0089] Based on the above formula, the terminal device can determine the maximum acceptable degradation value corresponding to each target performance metric, and then, based on the maximum acceptable degradation value corresponding to each target performance metric, alarm the change of the target performance metric, thereby improving the accuracy of the alarm. For example, the maximum acceptable degradation value of target performance metric 1 is value A, and the maximum acceptable degradation value of target performance metric 2 is value B. If, when the terminal device adjusts other performance metrics, the target performance metric 1 increases by value A, the terminal device can alarm the target performance metric 1. If, when the terminal device adjusts other performance metrics, the target performance metric 2 decreases by value B, the terminal device can alarm the target performance metric 2. After the terminal device alarms, it can stop adjusting other performance metrics, or it can also determine whether to stop adjusting other performance metrics based on the improvement or degradation result of the service metric after the change of the target performance metric. This disclosure embodiment does not make a limitation on this.

[0090] An embodiment of the present disclosure provides a method for processing performance indicators. A terminal device can obtain historical service data and process the historical service data according to the lasso linear regression method, and then determine multiple candidate performance indicators among multiple performance indicators. The terminal device can process the multiple candidate performance indicators through a multiple linear regression method to obtain the P value of each candidate performance indicator and the regression coefficient of each candidate performance indicator, and determine the candidate performance indicators with P values less than or equal to a preset threshold as target performance indicators. The terminal device can determine the maximum acceptable degradation value corresponding to each target performance indicator according to the regression coefficient of each target performance indicator and the minimum difference value of significant changes in service indicators. In the above method, since the target performance indicator has a greater impact on the service indicator, the ratio of the minimum difference value of significant changes in the terminal device service indicator to the regression coefficient of the target performance indicator can accurately obtain the maximum acceptable degradation value of the target performance indicator, improve the accuracy of the maximum acceptable degradation value, and improve the alarm accuracy of the target performance indicator.

[0091] Based on the embodiment shown in Figure 2 , the method for processing performance indicators further includes a method for determining the exchange relationship between performance indicators. Next, in combination with Figure 5 , the method for determining the exchange relationship between performance indicators will be described.

[0092] Figure 5 FIG. is a schematic diagram of a method for determining an exchange relationship provided by an embodiment of the present disclosure. Please refer to Figure 5 , and the method flow includes:

[0093] S501. Determine multiple reference performance indicators in the second service line direction of the service indicator and the regression coefficient of each reference performance indicator.

[0094] Optionally, the multiple performance indicators may be multiple indicators in the first service line direction of the service indicator. For example, the historical service data obtained by the terminal device may be multiple indicators in the first service line direction, and the first service line direction may be the influence of client performance indicators, playback performance indicators, and production-side performance indicators on the service indicator.

[0095] Optionally, the second service line direction is different from the first service line direction. For example, the second service line direction may be the influence of comment optimization indicators on the service indicator, the influence of UI optimization indicators on the service indicator, etc. For example, the first service line direction may be the influence of the video playback frame rate on the daily active user number, and the second service line direction may be the change from text comments to voice comments and the influence of the voice comments on the daily active user number.

[0096] Optionally, the reference performance metric may be a performance metric in the direction of the second business line. For example, if the second business line is in the direction of UI interaction optimization, the reference performance metric may be a comment metric, etc. The embodiments of the present disclosure do not limit this.

[0097] Optionally, the regression coefficient of the reference performance metric can be used to indicate the degree of influence of the reference performance metric on the business metric. For example, the larger the regression coefficient of the reference performance metric, the greater the degree of influence of the reference performance metric on the business metric; the smaller the regression coefficient of the reference performance metric, the smaller the degree of influence of the reference performance metric on the business metric.

[0098] It should be noted that the method for the terminal device to determine multiple reference performance metrics in the direction of the second business line and the regression coefficient of each reference performance metric is the same as the method for the terminal device to determine multiple target performance metrics in the direction of the first business line and the regression coefficient of each target performance metric. The embodiments of the present disclosure will not elaborate on this here.

[0099] S502. Determine the exchange relationship between the reference performance metric and the target performance metric according to multiple target performance metrics, the regression coefficient of each target performance metric, multiple reference performance metrics, and the regression coefficient of each reference performance metric.

[0100] Among them, the exchange relationship can be used to indicate whether the reference performance metric can be adjusted. For example, in the actual application process, when the terminal device adjusts the reference performance metric in the direction of the second business line, it may affect the target performance metric in the direction of the first business line. After the target performance metric changes, it will also cause the value of the business metric to change. Therefore, the terminal device can determine whether to adjust the reference performance metric in the direction of the second business line based on the exchange relationship.

[0101] Optionally, for any target performance metric in the direction of the first business line, the terminal device can determine the adjustable ratio between the reference performance metric and the target performance metric based on the following feasible implementation: determine the ratio between the regression coefficient of the target performance metric and the regression coefficient of the reference performance metric, obtain the degradation ratio of the target performance metric after the reference performance metric is adjusted, and determine whether the reference performance metric can be adjusted based on the degradation ratio and the ratio between the regression coefficient of the target performance metric and the regression coefficient of the reference performance metric.

[0102] Optionally, when the terminal device optimizes the reference performance metric in the second service line direction, if the optimization of the reference performance metric causes the target performance metric in the first service line direction to deteriorate, the terminal device can obtain the deterioration ratio of the target performance metric, and then determine whether to optimize the reference performance metric based on the ratio between the deterioration ratio and the ratio of the regression coefficient of the target performance metric to the regression coefficient of the reference performance metric. For example, when the target performance metric deteriorates by 1%, the terminal device can adjust the reference performance metric only when the optimization of the reference performance metric exceeds the ratio of the regression coefficient of the target performance metric to the regression coefficient of the reference performance metric.

[0103] For example, in the first service line direction: service metric = A * target performance metric 1 + B * target performance metric 2 + C * target performance metric 3, and in the second service line direction: service metric = a * reference performance metric 1 + b * reference performance metric 2. If the terminal device needs to optimize reference performance metric 1, and the optimization of reference performance metric 1 causes target performance metric 1 to deteriorate by 1%, then when the optimization of reference performance metric 1 is greater than the ratio of A to a, the terminal device can optimize reference performance metric 1.

[0104] For example, the service metric is the number of daily active users. In the first service line direction: the number of daily active users = A * target performance metric 1 + B * target performance metric 2 + C * target performance metric 3, and in the second service line direction: the number of daily active users = a * reference performance metric 1 + b * reference performance metric 2. Optimizing reference performance metric 1 by the terminal device can increase the number of daily active users by 50. However, when the terminal device optimizes reference performance metric 1, it will deteriorate target performance metric 1. If the number of daily active users decreases by 100 after the deterioration of target performance metric 1, the terminal device stops optimizing reference performance metric 1. If the number of daily active users decreases by 10 after the deterioration of target performance metric 1, the terminal device can optimize reference performance metric 1.

[0105] Next, in combination with Figure 6 , the optimization process of the reference performance metric by the terminal device will be described.

[0106] Figure 6 FIG. is a schematic diagram of an optimization process for a reference performance metric provided by an embodiment of the present disclosure. Please refer to Figure 6 , including: the target performance metric in the first service line direction. Among them, the target performance metric may include performance metric 1, performance metric 2,..., performance metric n. The terminal device ( Figure 6 not shown) determines that the number of daily active users is 1000 based on this target performance metric.

[0107] Please refer to Figure 6If the terminal device optimizes the reference performance metrics in the direction of the second service line, the optimization of the reference performance metrics can increase the number of daily active users by 100. However, optimizing the reference performance metrics will cause a decrease in Performance Metric 1 in the direction of the first service line, and the decrease in Performance Metric 1 will cause a decrease in the number of daily active users by 50.

[0108] Please refer to Figure 6 Since the number of increased users after optimizing the reference performance metrics is greater than the number of decreased users after the deterioration of Performance Metric 1, the terminal device can optimize the reference performance metrics. After the terminal device optimizes the reference performance metrics, the number of daily active users is 1050 (the optimization of the reference performance metrics increases 100 users, and the deterioration of Performance Metric 1 decreases 50 users). In this way, the terminal device can accurately determine whether to adjust the reference performance metrics based on this conversion relationship, thereby improving the optimization accuracy of the performance metrics.

[0109] The embodiments of the present disclosure provide a method for determining a conversion relationship. The terminal device can determine multiple reference performance metrics in the direction of the second service line of the service metrics, and the regression coefficient of each reference performance metric. According to the multiple target performance metrics, the regression coefficient of each target performance metric, the multiple reference performance metrics, and the regression coefficient of each reference performance metric, determine the conversion relationship between the reference performance metric and the target performance metric. In this way, when optimizing the performance metrics in other service line directions, the terminal device can determine whether to optimize the performance metrics in other service line directions based on this conversion relationship, which can avoid the situation where optimizing the performance metrics in other service line directions causes deterioration of the service metrics, and improve the optimization accuracy of the service metrics.

[0110] Figure 7 It is a schematic structural diagram of a processing device for performance metrics provided by the embodiments of the present disclosure. Please refer to Figure 7 The processing device 700 for performance metrics includes an acquisition module 701, a first determination module 702, and a second determination module 703, where:

[0111] The acquisition module 701 is configured to acquire historical service data, where the historical service data includes the values of the service metrics when the application program has different values for multiple performance metrics;

[0112] The first determination module 702 is configured to determine multiple target performance metrics among the multiple performance metrics according to the historical service data, and determine the regression coefficient of each target performance metric, where the regression coefficient is used to indicate the influence degree of the target performance metric on the service metric;

[0113] The second determination module 703 is configured to determine the maximum acceptable degradation value corresponding to each target performance metric according to the regression coefficient of each target performance metric and the minimum difference value of significant changes in the service metrics.

[0114] According to one or more embodiments of the present disclosure, the second determination module 702 is specifically configured to:

[0115] Determine a plurality of candidate performance metrics from the plurality of performance metrics by a multiple linear regression method;

[0116] Determine the regression coefficient of each candidate performance metric;

[0117] Determine, as the plurality of target performance metrics, the candidate performance metrics among the plurality of candidate performance metrics whose regression coefficients are greater than or equal to a preset threshold.

[0118] According to one or more embodiments of the present disclosure, the second determination module 702 is specifically configured to:

[0119] Process the historical service data by the multiple linear regression method to obtain an influence degree curve of each performance metric on the service metric;

[0120] Sort the plurality of performance metrics according to the order in which the influence degree becomes a preset value based on the plurality of influence degree curves, and determine the first N performance metrics among the sorted plurality of performance metrics as the plurality of initial performance metrics, where N is an integer greater than 1;

[0121] Determine the plurality of candidate performance metrics from the plurality of initial performance metrics according to the correlation degree between the plurality of initial performance metrics, where the correlation degree between the plurality of candidate performance metrics is less than a preset correlation degree.

[0122] According to one or more embodiments of the present disclosure, the second determination module 702 is specifically configured to:

[0123] Determine the correlation degree between every two initial performance metrics;

[0124] Perform a duplicate removal process on the plurality of initial performance metrics according to the correlation degree between every two initial performance metrics to obtain the plurality of candidate performance metrics; wherein, the duplicate removal process is used to delete one of the two initial performance metrics, and the correlation degree between the two initial performance metrics is greater than or equal to a preset correlation degree.

[0125] According to one or more embodiments of the present disclosure, the third determination module 703 is specifically configured to:

[0126] Determine the ratio of the minimum difference value of the significant change to the regression coefficient of the target performance metric;

[0127] Determine the ratio as the maximum acceptable degradation value corresponding to the target performance metric.

[0128] According to one or more embodiments of the present disclosure, the third determination module 703 is further configured to:

[0129] Determine multiple metric values of the service metric;

[0130] According to the multiple metric values of the service metric, determine the metric average value and the metric variance value corresponding to the service metric;

[0131] According to the metric average value and the metric variance value corresponding to the service metric, determine the minimum difference value of the significant change corresponding to the service metric by means of a T-test.

[0132] The performance metric processing device provided by the embodiments of the present disclosure can be used to execute the technical solutions of the above method embodiments, and its implementation principle and technical effects are similar, which will not be elaborated here in this embodiment.

[0133] Figure 8 It is a schematic structural diagram of another performance metric processing device provided by the embodiments of the present disclosure. On the basis of the embodiment shown in Figure 7 The performance metric processing device 700 further includes a third determination module 704, wherein the third determination module 704 is configured to:

[0134] Determine multiple reference performance metrics of the service metric in the second service line direction, and the regression coefficient of each reference performance metric;

[0135] According to the multiple target performance metrics, the regression coefficient of each target performance metric, the multiple reference performance metrics, and the regression coefficient of each reference performance metric, determine the conversion relationship between the reference performance metric and the target performance metric, and the conversion relationship is used to indicate whether the reference performance metric can be adjusted.

[0136] The performance metric processing device provided by the embodiments of the present disclosure can be used to execute the technical solutions of the above method embodiments, and its implementation principle and technical effects are similar, which will not be elaborated here in this embodiment.

[0137] Figure 9 It is a schematic structural diagram of a terminal device provided by the embodiments of the present disclosure. Please refer to Figure 9, which shows a schematic structural diagram of a terminal device 900 suitable for implementing the embodiments of the present disclosure. Among them, the terminal device may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (PADs), portable media players (PMPs), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 9 The terminal device shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present disclosure.

[0138] As Figure 9 shown, the terminal device 900 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 901, which may perform various appropriate actions and processes according to the programs stored in the read-only memory (ROM) 902 or the programs loaded from the storage device 908 into the random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the terminal device 900 are also stored. The processing device 901, the ROM 902, and the RAM 903 are connected to each other through a bus 904. The input / output (I / O) interface 905 is also connected to the bus 904.

[0139] Generally, the following devices may be connected to the I / O interface 905: an input device 906 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 908 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 909. The communication device 909 may allow the terminal device 900 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 9 the terminal device 900 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices may be implemented or had.

[0140] In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present disclosure includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes program code for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 909, or installed from a storage device 908, or installed from a ROM 902. When the computer program is executed by a processing device 901, the above functions defined in the method of the embodiment of the present disclosure are performed.

[0141] It should be noted that the above computer-readable medium in the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable signal medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0142] The above computer-readable medium can be included in the above terminal device; or it can exist separately without being assembled into the terminal device.

[0143] The above computer-readable medium carries one or more programs, and when the one or more programs are executed by the terminal device, the terminal device is caused to perform the method shown in the above embodiment.

[0144] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, and when a processor executes the computer-executable instructions, the methods that may be involved in the above embodiments are implemented.

[0145] An embodiment of the present disclosure provides a computer program product including a computer program, and when the computer program is executed by a processor, the methods that may be involved in the above embodiments are implemented.

[0146] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages such as Java, Smalltalk, and C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0147] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0148] The units involved in the embodiments of the present disclosure can be implemented in software or in hardware. Among them, the name of the unit does not constitute a limitation on the unit itself in some cases. For example, the first acquisition unit can also be described as "the unit for acquiring at least two Internet protocol addresses".

[0149] The functions described above in this article can be performed at least in part by one or more hardware logic components. For example, without limitation, the exemplary types of hardware logic components that can be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logic Device (CPLD), and so on.

[0150] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include electrical connections based on one or more wires, portable computer disks, hard disks, Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable Read Only Memory (EPROM or Flash Memory), optical fiber, portable compact disc read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0151] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise clearly specified in the context, it should be understood as "one or more".

[0152] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0153] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the users and the authorization of the users should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0154] For example, when receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested by the user will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as a terminal device, an application program, a server, or a storage medium that performs the operations of the present disclosure technical solution according to the prompt message. As an optional but non-limiting implementation manner, when receiving an active request from a user, the manner of sending a prompt message to the user may be, for example, a pop-up window manner, and the prompt message may be presented in text in the pop-up window. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide personal information to the terminal device.

[0155] It can be understood that the above process of notifying and obtaining user authorization is only illustrative and does not constitute a limitation on the implementation manner of the present disclosure. Other manners that meet relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0156] It can be understood that the data involved in the present technical solution (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of corresponding laws, regulations and related regulations. The data may include information, parameters, messages, etc., such as cut-flow indication information.

[0157] In a first aspect, according to one or more embodiments of the present disclosure, the present disclosure includes a method for processing performance indicators, the method comprising:

[0158] Obtaining historical service data, where the historical service data includes the values of service indicators when an application program has different values for multiple performance indicators;

[0159] According to the historical service data, determining multiple target performance indicators among the multiple performance indicators, and determining a regression coefficient for each target performance indicator, where the regression coefficient is used to indicate the influence degree of the target performance indicator on the service indicator;

[0160] According to the regression coefficient of each target performance indicator and the minimum difference value of significant changes in the service indicator, determining the maximum acceptable degradation value corresponding to each target performance indicator.

[0161] According to one or more embodiments of the present disclosure, determining multiple target performance indicators among the multiple performance indicators according to the historical service data includes:

[0162] Determining multiple candidate performance indicators among the multiple performance indicators by a multiple linear regression method;

[0163] Determining the regression coefficient of each candidate performance indicator;

[0164] Among the multiple candidate performance indicators, determine the candidate performance indicators with a regression coefficient greater than or equal to a preset threshold as the multiple target performance indicators.

[0165] According to one or more embodiments of the present disclosure, determining multiple candidate performance indicators among the multiple performance indicators through a multiple linear regression method includes:

[0166] Process the historical service data through the multiple linear regression method to obtain the influence degree curve of each performance indicator on the service indicator;

[0167] According to multiple influence degree curves, sort the multiple performance indicators in the order in which the influence degree becomes a preset value, and determine the first N performance indicators among the sorted multiple performance indicators as multiple initial performance indicators, where N is an integer greater than 1;

[0168] Determine the multiple candidate performance indicators among the multiple initial performance indicators according to the correlation degree between the multiple initial performance indicators, and the correlation degree between the multiple candidate performance indicators is less than a preset correlation degree.

[0169] According to one or more embodiments of the present disclosure, determining the multiple candidate performance indicators among the multiple initial performance indicators according to the correlation degree between the multiple initial performance indicators includes:

[0170] Determine the correlation degree between every two initial performance indicators;

[0171] According to the correlation degree between every two initial performance indicators, perform a duplicate removal process on the multiple initial performance indicators to obtain the multiple candidate performance indicators; wherein, the duplicate removal process is used to delete one of the two initial performance indicators, and the correlation degree between the two initial performance indicators is greater than or equal to a preset correlation degree.

[0172] According to one or more embodiments of the present disclosure, for any one target performance indicator; determine the maximum acceptable degradation value corresponding to each target performance indicator according to the regression coefficient of each target performance indicator and the minimum difference value of the significant change of the service indicator, including:

[0173] Determine the ratio of the minimum difference value of the significant change to the regression coefficient of the target performance indicator;

[0174] Determine the ratio as the maximum acceptable degradation value corresponding to the target performance indicator.

[0175] According to one or more embodiments of the present disclosure, before determining the maximum acceptable degradation value corresponding to each target performance indicator according to the regression coefficient of each target performance indicator and the minimum difference value of the significant change of the service indicator, further include:

[0176] Determine multiple index values of the service index;

[0177] Determine the index average value and the index variance value corresponding to the service index according to the multiple index values of the service index;

[0178] Determine the minimum difference value of the significant change corresponding to the service index by means of a T-test according to the index average value and the index variance value corresponding to the service index.

[0179] According to one or more embodiments of the present disclosure, the multiple performance indexes are multiple indexes of the service index in the first service line direction; the method further includes:

[0180] Determine multiple reference performance indexes of the service index in the second service line direction and the regression coefficient of each reference performance index;

[0181] Determine the conversion relationship between the reference performance index and the target performance index according to the multiple target performance indexes, the regression coefficient of each target performance index, the multiple reference performance indexes, and the regression coefficient of each reference performance index, where the conversion relationship is used to indicate whether the reference performance index can be adjusted.

[0182] In a second aspect, according to one or more embodiments of the present disclosure, an embodiment of the present disclosure provides a processing device for performance indexes, and the processing device for performance indexes includes an acquisition module, a first determination module, and a second determination module, where:

[0183] The acquisition module is configured to acquire historical service data, where the historical service data includes the values of the service index when the application program has different values for multiple performance indexes;

[0184] The first determination module is configured to determine multiple target performance indexes among the multiple performance indexes according to the historical service data and determine the regression coefficient of each target performance index, where the regression coefficient is used to indicate the influence degree of the target performance index on the service index;

[0185] The second determination module is configured to determine the maximum acceptable deterioration value corresponding to each target performance index according to the regression coefficient of each target performance index and the minimum difference value of the significant change of the service index.

[0186] According to one or more embodiments of the present disclosure, the second determination module is specifically configured to:

[0187] Determine multiple candidate performance indexes among the multiple performance indexes by means of a multiple linear regression method;

[0188] Determine the regression coefficients of each candidate performance metric;

[0189] Among the multiple candidate performance metrics, determine the candidate performance metrics whose regression coefficients are greater than or equal to a preset threshold as the multiple target performance metrics.

[0190] According to one or more embodiments of the present disclosure, the second determination module is specifically configured to:

[0191] Process the historical service data through the multiple linear regression method to obtain the influence degree curve of each performance metric on the service metric;

[0192] According to multiple influence degree curves, sort the multiple performance metrics in the order of the influence degree becoming a preset value, and determine the first N performance metrics among the sorted multiple performance metrics as multiple initial performance metrics, where N is an integer greater than 1;

[0193] Determine the multiple candidate performance metrics among the multiple initial performance metrics according to the correlation between the multiple initial performance metrics, and the correlation between the multiple candidate performance metrics is less than a preset correlation.

[0194] According to one or more embodiments of the present disclosure, the second determination module is specifically configured to:

[0195] Determine the correlation between every two initial performance metrics;

[0196] According to the correlation between every two initial performance metrics, perform a duplicate removal process on the multiple initial performance metrics to obtain the multiple candidate performance metrics; wherein, the duplicate removal process is used to delete one of the two initial performance metrics, and the correlation between the two initial performance metrics is greater than or equal to a preset correlation.

[0197] According to one or more embodiments of the present disclosure, the third determination module is specifically configured to:

[0198] Determine the ratio of the minimum difference value of the significant change to the regression coefficient of the target performance metric;

[0199] Determine the ratio as the maximum acceptable degradation value corresponding to the target performance metric.

[0200] According to one or more embodiments of the present disclosure, the third determination module is further configured to:

[0201] Determine multiple metric values of the service metric;

[0202] According to the multiple metric values of the service metric, determine the metric average value and the metric variance value corresponding to the service metric;

[0203] Determine the minimum difference value of the significant change corresponding to the service metric through a t-test based on the mean value and variance value of the metric corresponding to the service metric.

[0204] According to one or more embodiments of the present disclosure, the processing device for performance metrics further includes a third determination module, wherein the third determination module is configured to:

[0205] Determine a plurality of reference performance metrics of the service metric in the direction of the second service line, and the regression coefficient of each reference performance metric;

[0206] Determine the conversion relationship between the reference performance metric and the target performance metric according to the plurality of target performance metrics, the regression coefficient of each target performance metric, the plurality of reference performance metrics, and the regression coefficient of each reference performance metric, where the conversion relationship is used to indicate whether the reference performance metric can be adjusted.

[0207] In a third aspect, an embodiment of the present disclosure provides a terminal device including: a processor and a memory;

[0208] The memory stores computer-executable instructions;

[0209] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the methods in the first aspect and various possible methods related to the first aspect as described above.

[0210] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the processor executes the computer-executable instructions, the methods in the first aspect and various possible methods related to the first aspect as described above are implemented.

[0211] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, a technical solution formed by mutually replacing the above features with (but not limited to) technical features with similar functions disclosed in the present disclosure.

[0212] Moreover, although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the foregoing discussion, these should not be construed as limitations on the scope of the present disclosure. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented separately or in any suitable subcombination in multiple embodiments.

[0213] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A method for processing performance indicators, characterized in that, it includes: Obtain historical business data, where the historical business data includes the values of business indicators when the application has different values for multiple performance indicators; According to the historical business data, determine multiple target performance indicators among the multiple performance indicators, and determine the regression coefficient of each target performance indicator, where the regression coefficient is used to indicate the influence degree of the target performance indicator on the business indicator; According to the regression coefficient of each target performance indicator and the minimum difference value of significant changes in the business indicator, determine the maximum acceptable degradation value corresponding to each target performance indicator.

2. The method according to claim 1, characterized in that, According to the historical business data, determining multiple target performance indicators among the multiple performance indicators includes: According to the historical business data, determine multiple candidate performance indicators among the multiple performance indicators, and there is no problem of multicollinearity among the multiple candidate performance indicators; Through the multiple linear regression method, process the multiple candidate performance indicators to obtain the P value of each candidate performance indicator, where the P value is used to indicate whether there is a significant difference between the regression coefficient of the candidate performance indicator and a preset value; Determine the candidate performance indicators with P values less than or equal to a preset threshold as the target performance indicators.

3. The method according to claim 2, characterized in that, The determining multiple candidate performance indicators among the multiple performance indicators according to the historical business data includes: Process the historical business data through the lasso linear regression method to obtain the influence degree curve of each performance indicator on the business indicator; According to multiple influence degree curves, sort the multiple performance indicators in the order of the influence degree becoming a preset value, and determine the first N performance indicators among the sorted multiple performance indicators as multiple initial performance indicators, where N is an integer greater than 1; According to the correlation degree among the multiple initial performance indicators, determine the multiple candidate performance indicators among the multiple initial performance indicators, and the correlation degree among the multiple candidate performance indicators is less than a preset correlation degree.

4. The method according to claim 3, characterized in that, According to the correlation degree among the multiple initial performance indicators, determining the multiple candidate performance indicators among the multiple initial performance indicators includes: Determine the correlation degree between every two initial performance indicators; According to the correlation degree between every two initial performance indicators, perform a duplicate removal process on the multiple initial performance indicators to obtain the multiple candidate performance indicators; where the duplicate removal process is used to delete one of the two initial performance indicators, and the correlation degree between the two initial performance indicators is greater than or equal to a preset correlation degree.

5. The method according to any one of claims 1-4, characterized in that, For any one target performance indicator; according to the regression coefficient of each target performance indicator and the minimum difference value of significant changes in the business indicator, determining the maximum acceptable degradation value corresponding to each target performance indicator includes: Determine the ratio of the minimum difference value to the regression coefficient of the target performance metric; Determine the ratio as the maximum acceptable degradation value corresponding to the target performance metric.

6. The method according to any one of claims 1-5, characterized in that before determining the maximum acceptable degradation corresponding to each target performance metric according to the regression coefficient of each target performance metric and the minimum difference value of significant changes in the service metric, further comprising: Determine a plurality of metric values of the service metric; Determine the metric average value and the metric variance value corresponding to the service metric according to the plurality of metric values of the service metric; Determine the minimum difference value of significant changes corresponding to the service metric by means of a T-test according to the metric average value and the metric variance value corresponding to the service metric.

7. The method according to any one of claims 1-6, characterized in that the plurality of performance metrics are a plurality of metrics of the service metric in the first service line direction; the method further comprises: Determine a plurality of reference performance metrics of the service metric in the second service line direction and the regression coefficient of each reference performance metric; Determine the exchange relationship between the reference performance metric and the target performance metric according to the plurality of target performance metrics, the regression coefficient of each target performance metric, the plurality of reference performance metrics, and the regression coefficient of each reference performance metric, and the exchange relationship is used to indicate whether the reference performance metric can be adjusted.

8. A processing device for performance metrics, characterized in that comprising an acquisition module, a first determination module and a second determination module, wherein: The acquisition module is configured to acquire historical service data, and the historical service data includes the values of the service metric when the application program has different values for a plurality of performance metrics; The first determination module is configured to determine a plurality of target performance metrics among the plurality of performance metrics according to the historical service data and determine the regression coefficient of each target performance metric, and the regression coefficient is used to indicate the influence degree of the target performance metric on the service metric; The second determination module is configured to determine the maximum acceptable degradation value corresponding to each target performance metric according to the regression coefficient of each target performance metric and the minimum difference value of significant changes in the service metric.

9. A terminal device, characterized in that comprising: a processor and a memory; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory, so that the processor executes the performance metric processing method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that computer execution instructions are stored in the computer-readable storage medium, and when the processor executes the computer execution instructions, the performance metric processing method according to any one of claims 1-7 is implemented.

Images