Business processing method and device and electronic equipment

Abstract

Embodiments of the invention provide a service processing method and apparatus, and an electronic device. The method comprises the steps of obtaining a plurality of performance indexes associated with a service index; in the plurality of performance indexes, determining a target performance index with a multi-collinearity problem; determining a first performance index of which the relevancy with the target performance index is greater than or equal to a first threshold value; determining a first regression coefficient between the target performance index and the first performance index; determining a plurality of second regression coefficients between the business index and a plurality of second performance indexes, wherein the second performance indexes are other performance indexes except the target performance index in the plurality of performance indexes; and restoring the regression coefficient of the target performance index to the business index according to the first regression coefficient and the plurality of second regression coefficients. Therefore, the influence degree of the performance index with the multi-collinearity problem on the business index can be accurately determined.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technologies, and in particular, to a service processing method, apparatus, and electronic device. Background Art

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

[0003] Currently, an electronic device can process business metrics and multiple performance metrics based on linear regression to obtain the regression coefficients of each performance metric, and then determine the influence degree of the performance metric on the business metric based on the regression coefficient. However, when the correlation between some performance metrics is relatively high, in order to avoid the problem of multicollinearity, when performing linear regression processing, the electronic device can only retain one performance metric among the performance metrics with relatively high correlation and delete other performance metrics, and then perform linear regression processing on the remaining performance metrics. However, in this way, the electronic device cannot determine the regression coefficient of the deleted performance metric on the business metric, resulting in the inability to determine the influence degree of the performance metric on the business metric. Summary of the Invention

[0004] The present disclosure provides a service processing method, apparatus, and electronic device for solving one or more technical problems in the prior art.

[0005] In a first aspect, the present disclosure provides a service processing method, which includes:

[0006] Obtain multiple performance metrics associated with a business metric;

[0007] Determine target performance metrics with a multicollinearity problem among the multiple performance metrics;

[0008] Determine first performance metrics whose correlation with the target performance metrics is greater than or equal to a first threshold;

[0009] Determine a first regression coefficient between the target performance metric and the first performance metric;

[0010] Determine multiple second regression coefficients between the business metric and multiple second performance metrics, where the second performance metrics are other performance metrics among the multiple performance metrics except the target performance metrics;

[0011] Restore the regression coefficient of the target performance metric on the business metric according to the first regression coefficient and the multiple second regression coefficients, and the regression coefficient of the target performance metric on the business metric is proportional to the influence degree of the target performance metric on the business metric.

[0012] In a second aspect, the present disclosure provides a service processing apparatus, which includes a first acquisition module, a first determination module, a second determination module, a third determination module, a fourth determination module, and a fifth determination module, where:

[0013] The first acquisition module is configured to acquire a plurality of performance indicators associated with service indicators;

[0014] The first determination module is configured to determine, among the plurality of performance indicators, target performance indicators having a multicollinearity problem;

[0015] The second determination module is configured to determine first performance indicators whose correlation with the target performance indicators is greater than or equal to a first threshold;

[0016] The third determination module is configured to determine a first regression coefficient between the target performance indicator and the first performance indicator;

[0017] The fourth determination module is configured to determine a plurality of second regression coefficients between the service indicator and a plurality of second performance indicators, where the second performance indicators are other performance indicators among the plurality of performance indicators except the target performance indicator;

[0018] The fifth determination module is configured to restore, according to the first regression coefficient and the plurality of second regression coefficients, a regression coefficient of the target performance indicator with respect to the service indicator, and the regression coefficient of the target performance indicator with respect to the service indicator is proportional to the influence degree of the target performance indicator on the service indicator.

[0019] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0020] The memory stores computer-executable instructions;

[0021] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the service processing method as described in the first aspect above and various possible aspects related to the first aspect.

[0022] 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 service processing method as described in the first aspect above and various possible aspects related to the first aspect are implemented.

[0023] The present disclosure provides a service processing method, apparatus, and electronic device. The electronic device can obtain multiple performance indicators associated with a service indicator, and among the multiple performance indicators, determine target performance indicators with a multicollinearity problem, determine first performance indicators whose correlation with the target performance indicators is greater than or equal to a first threshold, determine a first regression coefficient between the target performance indicators and the first performance indicators, and determine multiple second regression coefficients between the service indicator and multiple second performance indicators, where the second performance indicators are other performance indicators among the multiple performance indicators except the target performance indicators. The electronic device can, according to the first regression coefficient and the multiple second regression coefficients, restore the regression coefficient of the target performance indicator on the service indicator, where the regression coefficient of the target performance indicator on the service indicator is proportional to the influence degree of the target performance indicator on the service indicator. In the above method, since the first regression coefficient is the first regression coefficient between the target performance indicator and the first performance indicator with a relatively high correlation, the electronic device can, based on the first regression coefficient, determine the relationship between the first performance indicator and the target performance indicator, and the multiple second regression coefficients can indicate the relationship between the first performance indicator and the service indicator. Therefore, even after the electronic device deletes the target performance indicator and then performs a linear regression process on the service indicator and the multiple second performance indicators (the regression coefficient of the target performance indicator on the service indicator cannot be obtained), the electronic device can still accurately determine the influence degree of the target performance indicator on the service indicator based on the first regression coefficient and the multiple second regression coefficients. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] To more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following briefly introduces the accompanying drawings required for describing 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, other drawings can be obtained based on these drawings without creative efforts.

[0025] Figure 1 FIG. is a schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0026] Figure 2 FIG. is a flowchart of a service processing method provided by an embodiment of the present disclosure;

[0027] Figure 3 FIG. is a schematic diagram of a process for determining a first regression coefficient provided by an embodiment of the present disclosure;

[0028] Figure 4 FIG. is a schematic diagram of a process for determining multiple second performance indicators provided by an embodiment of the present disclosure;

[0029] Figure 5 FIG. is a schematic diagram of a process for determining a regression coefficient provided by an embodiment of the present disclosure;

[0030] Figure 6 Schematic diagram of a method for verifying regression coefficients provided by an embodiment of the present disclosure;

[0031] Figure 7 Schematic diagram of a process for determining a third regression coefficient provided by an embodiment of the present disclosure;

[0032] Figure 8 Schematic diagram of a process for verifying regression coefficients provided by an embodiment of the present disclosure;

[0033] Figure 9 Schematic diagram of the structure of a service processing device provided by an embodiment of the present disclosure;

[0034] Figure 10 Schematic diagram of the structure of another service processing device provided by an embodiment of the present disclosure;

[0035] Figure 11 Schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0036] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.

[0037] For ease of understanding, the concepts related to the embodiments of the present disclosure will be described below.

[0038] Electronic device: A device with wireless transceiver capabilities. The electronic device can be deployed on land, including indoors or outdoors, handheld, wearable, or vehicle-mounted. The electronic device can be a mobile phone, a tablet (Pad), a computer with wireless transceiver capabilities, a virtual reality (VR) electronic device, an augmented reality (AR) electronic device, a wireless terminal in industrial control, a vehicle-mounted electronic device, a wireless terminal in self-driving, a wireless electronic device in remote medical, a wireless electronic device in smart grid, a wireless electronic device in transportation safety, a wireless electronic device in smart city, a wireless electronic device in smart home, a wearable electronic device, etc. The electronic device involved in the embodiments of the present disclosure can also be referred to as a terminal, a user equipment (UE), an access electronic device, a vehicle-mounted terminal, an industrial control terminal, a UE unit, a UE station, a mobile station, a mobile unit, a remote station, a remote electronic device, a mobile device, a UE electronic device, a wireless communication device, a UE agent, or a UE device, etc. The electronic device can also be fixed or mobile.

[0039] Next, in combination with Figure 1 , the application scenarios of the embodiments of the present disclosure will be described.

[0040] Figure 1 FIG. is a schematic diagram of an application scenario provided for the embodiments of the present disclosure. Please refer to Figure 1 , including service metrics and performance metrics. Among them, the service metrics include the number of daily active users, and the performance metrics related to this service metric include video frame rate, video clarity, device power consumption, and interface smoothness. Since the correlation between the video frame rate and video clarity is relatively high, therefore, before performing linear regression, the electronic device ( Figure 1 not shown) can delete the video frame rate and retain the video clarity. The electronic device can perform linear regression processing on the number of daily active users, video clarity, device power consumption, and interface smoothness, and obtain the number of daily active users = A × video clarity + B × device power consumption + C × interface smoothness, where A can indicate the influence degree of video clarity on the number of daily active users, B can indicate the influence degree of device power consumption on the number of daily active users, and C can indicate the influence degree of interface smoothness on the number of daily active users. However, this method cannot obtain the influence degree of the video frame rate on the number of daily active users, and therefore, cannot indicate the optimization direction of the electronic device for the video frame rate.

[0041] It should be noted that Figure 1 This is only an example of the application scenario of the embodiments of the present disclosure, and does not limit the application scenario of the embodiments of the present disclosure.

[0042] In the related art, the performance metrics of an application can affect the business metrics of the application. Therefore, an electronic device needs to determine the degree of influence of the performance metrics on the business metrics. For example, the video playback clarity (performance metric) of an application can affect the number of daily active users (business metric) of the application. However, the electronic device needs to accurately determine the degree of influence of the video playback clarity on the number of daily active users. Currently, the electronic device can process the business metric and multiple performance metrics based on linear regression to obtain the regression coefficient of each performance metric, where the regression coefficient can indicate the degree of influence of the performance metric on the business metric.

[0043] However, the correlation between some performance metrics is relatively high. For example, the correlation between video playback clarity and video frame rate is relatively high. When the electronic device performs linear regression processing on multiple performance metrics with a relatively high correlation, it will cause the problem of multicollinearity. To avoid the problem of multicollinearity, the electronic device can only retain one performance metric among the performance metrics with a relatively high correlation, delete other performance metrics, and then perform linear regression processing on the remaining performance metrics. For example, the business metric is related to performance metric 1, performance metric 2, and performance metric 3. If performance metric 1 is related to performance metric 2, the electronic device can delete performance metric 1 and perform linear regression processing on the business metric, performance metric 2, and performance metric 3 to obtain the regression coefficients of performance metric 2 and performance metric 3 on the business metric. However, the electronic device cannot determine the regression coefficient between performance metric 1 and the business metric, so that the electronic device cannot determine the degree of influence of performance metric 1 on the business metric. In this way, the electronic device cannot accurately determine the degree of influence of the performance metrics on the business metrics.

[0044] To solve the technical problems in the related art, an embodiment of the present disclosure provides a service processing method. An electronic device can obtain multiple performance indicators associated with a service indicator, and among the multiple performance indicators, determine a target performance indicator with a multicollinearity problem. The electronic device can determine a first performance indicator whose correlation with the target performance indicator is greater than or equal to a first threshold, and determine a first regression coefficient between the target performance indicator and the first performance indicator. The electronic device can determine multiple second regression coefficients between the service indicator and multiple second performance indicators. And for any one of the first performance indicators, among the multiple second regression coefficients, determine a target regression coefficient associated with the first performance indicator, and determine the ratio of the target regression coefficient to the first regression coefficient of the first performance indicator as the regression coefficient of the target performance indicator on the service indicator. In this way, since the first regression coefficient can indicate the relationship between the performance indicator and the target performance indicator, and the target regression coefficient can indicate the relationship between the performance indicator and the service indicator, the electronic device can accurately determine the regression coefficient between the target performance indicator and the service indicator based on the first regression coefficient and the target regression coefficient, and further can accurately determine the influence degree of the target performance indicator on the service indicator.

[0045] The following uses specific embodiments to detail the technical solution of the present disclosure and how the technical solution of the present disclosure solves the above technical problems. These several specific embodiments below 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.

[0046] Figure 2 It is a flowchart of a service processing method provided by an embodiment of the present disclosure. Please refer to Figure 2 , the method may include:

[0047] S201. Obtain multiple performance indicators associated with the service indicator.

[0048] The execution subject of the embodiment of the present disclosure may be an electronic device, or a service processing device provided in the electronic device. Among them, the service processing device may be implemented based on software, and the service processing device may also be implemented based on the combination of software and hardware. The embodiment of the present disclosure does not limit this. Optionally, the electronic device may be any device with end-side computing capabilities. For example, the electronic device may be a device such as a computer or a server. The embodiment of the present disclosure does not limit this.

[0049] Optionally, the service indicator may be used to indicate the performance of the application program at the service end. For example, the service indicator may include the number of daily active users of the application program, and the service indicator may also include the number of times the user uses the application program within a historical period, etc. The embodiment of the present disclosure does not limit this.

[0050] Optionally, the performance metrics can be used to indicate the performance of an application. For example, the performance metrics can include client performance metrics, playback performance metrics, and production-side performance metrics. For example, the client performance metrics can include the fluency of the user interface (UI) in the application, dynamic resources (such as power consumption), and static resources (such as storage space), which are not limited in the embodiments of the present disclosure. For example, the playback performance metrics can include the playback frame rate of a video, the playback clarity of a video, etc., which are not limited in the embodiments of the present disclosure.

[0051] Optionally, multiple performance metrics can be associated with business metrics. For example, multiple performance metrics can affect business metrics. For example, an application can include Performance Metric 1, Performance Metric 2, and Performance Metric 3. If the business metric changes when Performance Metric 1 and Performance Metric 2 change, the electronic device can determine that the performance metrics associated with the business metric are Performance Metric 1 and Performance Metric 2. If the business metric does not change when Performance Metric 3 changes, the electronic device can determine that Performance Metric 3 is not relevant to the business metric, that is, Performance Metric 3 cannot affect the business metric.

[0052] Optionally, the electronic device can obtain multiple performance metrics associated with a business metric based on the correspondence between the business metric and multiple performance metrics. For example, Business Metric 1 can correspond to Performance Metric a and Performance Metric b, and Business Metric 2 can correspond to Performance Metric c and Performance Metric d. The electronic device can determine multiple performance metrics associated with the business metric based on this correspondence.

[0053] It should be noted that the same business metric can be associated with multiple sets of performance metrics, and each set of performance metrics can include multiple performance metrics. For example, a business metric can be associated with Performance Metric 1 and Performance Metric 2, and the business metric can also be associated with Performance Metric 3 and Performance Metric 4. Among them, Performance Metric 1 and Performance Metric 2 can be performance metrics in one business line direction (such as performance metrics in the comment optimization direction), and Performance Metric 3 and Performance Metric 4 can be performance metrics in another business line direction (such as performance metrics in the video optimization direction). Specifically, the electronic device can determine multiple performance metrics associated with the business metric based on business requirements. For example, if the electronic device needs to increase the number of daily active users based on comment optimization, the multiple performance metrics associated with the business metric can be performance metrics related to comment optimization. If the electronic device wants to increase the number of daily active users based on video optimization, the multiple performance metrics associated with the business metric can be performance metrics related to video optimization.

[0054] It should be noted that the electronic device can also obtain multiple performance metrics associated with a business metric based on any feasible implementation manner, which is not limited in the embodiments of the present disclosure.

[0055] S202. Among multiple performance metrics, determine the target performance metric with a multicollinearity problem.

[0056] Herein, multicollinearity may refer to the situation where the explanatory variables in a linear regression model are either exactly related or highly correlated, resulting in distorted model estimation or difficulty in accurate estimation. For example, if the correlation between performance metric 1 and performance metric 2 is high, then when performing a linear regression on business metrics, performance metric 1, and performance metric 2, there will be a multicollinearity problem, causing the electronic device to be unable to obtain the regression coefficients of each performance metric.

[0057] Herein, the target performance metric may be the performance metric with a multicollinearity problem. For example, if performance metric 1 is the video frame rate and performance metric 2 is the video resolution, then the electronic device can determine that the correlation between performance metric 1 and performance metric 2 is high, and the electronic device can determine performance metric 1 or performance metric 2 as the target performance metric with a multicollinearity problem.

[0058] Optionally, the electronic device can determine the target performance metric with a multicollinearity problem based on the following feasible implementation: For any performance metric, determine the variance inflation factor between the performance metric and each other performance metric. If any variance inflation factor is greater than or equal to a second threshold, then determine the performance metric as the first performance metric.

[0059] For example, if the multiple performance metrics associated with the business metric include performance metric 1, performance metric 2, and performance metric 3, and if the variance inflation factor between performance metric 1 and performance metric 2 is greater than or equal to the second threshold, then the electronic device can determine performance metric 1 or performance metric 2 as the target performance metric.

[0060] Herein, the variance inflation factor (VIF) can indicate the correlation between two performance metrics during linear regression. For example, the VIF value can indicate the severity of multicollinearity in a multiple linear regression model. If the VIF value between performance metric 1 and performance metric 2 is greater than or equal to a preset threshold, it means that the correlation between performance metric 1 and performance metric 2 is high, and there will be a multicollinearity problem when the electronic device performs linear regression. In this way, based on the VIF value of the performance metric, the electronic device can accurately determine the target performance metric with a multicollinearity problem.

[0061] It should be noted that the electronic device can also determine multiple first performance metrics among multiple performance metrics based on any feasible implementation, and this disclosure embodiment does not limit this.

[0062] It should be noted that in the actual application process, among multiple performance indicators associated with a business indicator, there may be multiple target performance indicators with multicollinearity problems. For example, the performance indicators associated with a business indicator include Performance Indicator 1, Performance Indicator 2, Performance Indicator 3, and Performance Indicator 4. Among them, the correlation between Performance Indicator 1 and Performance Indicator 2 is relatively high, and the correlation between Performance Indicator 3 and Performance Indicator 4 is relatively high. Therefore, the electronic device can determine that the target performance indicator can be Performance Indicator 1 or Performance Indicator 2, and the target performance indicator can also be Performance Indicator 3 or Performance Indicator 4. When performing multiple linear regression, there is no multicollinearity problem among the multiple performance indicators.

[0063] S203. Determine a first performance indicator whose correlation with the target performance indicator is greater than or equal to a first threshold.

[0064] Among them, the correlation between the first performance indicator and the target performance indicator is greater than or equal to the first threshold. For example, if Performance Indicator 1 is a target performance indicator with a multicollinearity problem, the correlation between Performance Indicator 2 and Performance Indicator 1 is equal to the first threshold, and the correlation between Performance Indicator 3 and Performance Indicator 1 is greater than the first threshold, then the electronic device can determine that the first performance indicators of the target performance indicator include Performance Indicator 2 and Performance Indicator 3. It should be noted that Performance Indicator 2 and Performance Indicator 3 can be completely independent of each other.

[0065] It should be noted that the electronic device can determine a first performance indicator whose correlation with the target performance indicator is greater than or equal to the first threshold based on any feasible implementation method (for example, if the VIF value between a performance indicator and the target performance indicator is greater than a preset value, the electronic device determines that the performance indicator is correlated with the target performance indicator). The embodiments of the present disclosure do not limit this.

[0066] S204. Determine a first regression coefficient between the target performance indicator and the first performance indicator.

[0067] Among them, the first regression coefficient can indicate the influence degree of the first performance indicator on the target performance indicator. For example, the first performance indicator can include Performance Indicator 1 and Performance Indicator 2. If the electronic device determines that the target performance indicator is Performance Indicator 3, then the first regression coefficient of Performance Indicator 1 can indicate the influence degree of Performance Indicator 1 on Performance Indicator 3, and the first regression coefficient of Performance Indicator 2 can indicate the influence degree of Performance Indicator 2 on Performance Indicator 1.

[0068] Optionally, the electronic device may process the target performance metric and the first performance metric based on the multiple linear regression method, and then may obtain multiple first regression coefficients. For example, the target performance metric may be Performance Metric 1, and the first performance metrics related to the target performance metric may be Performance Metric 2 and Performance Metric 3. The electronic device may perform linear regression processing on Performance Metric 1 (dependent variable), Performance Metric 2 (independent variable), and Performance Metric 3 (independent variable) to obtain Performance Metric 1 = A (constant) + B × Performance Metric 2 + C × Performance Metric 3 + D (constant), where B may be the first regression coefficient of Performance Metric 2, and C may be the first regression coefficient of Performance Metric 3.

[0069] It should be noted that when the electronic device performs linear regression processing on the target performance metric and the first performance metric, it may obtain the values of the target performance metric and the first performance metric based on historical service data (which may be stored in a database). The embodiments of the present disclosure do not limit this.

[0070] It should be noted that the electronic device may also determine the first regression coefficient between the target performance metric and the first performance metric based on any other feasible implementation manner. The embodiments of the present disclosure do not limit this.

[0071] Next, in combination with Figure 3 , the process of determining the first regression coefficient will be described.

[0072] Figure 3 FIG. is a schematic diagram of a process for determining a first regression coefficient provided by an embodiment of the present disclosure. Please refer to Figure 3 , including: performance metrics. Among them, the performance metrics may include video frame rate, video resolution, and video bit rate. If there is a problem of multicollinearity in the video frame rate, the electronic device ( Figure 3 not shown) may determine the video frame rate as the target performance metric and determine the first performance metric based on the video frame rate, where the first performance metric includes video resolution and video bit rate. The electronic device may perform linear regression processing on the video frame rate, video resolution, and video bit rate to obtain Video Frame Rate = A × Video Resolution + B × Video Bit Rate + C, where A and B are the first regression coefficients, and C is a constant. In this way, the electronic device may accurately determine the relationship between the target performance metric and other first performance metrics based on the first regression coefficient.

[0073] S205. Determine multiple second regression coefficients between the service metric and multiple second performance metrics.

[0074] Among them, the second performance metric can be other performance metrics among multiple performance metrics except the target performance metric. For example, the performance metrics associated with a service metric can include Performance Metric 1, Performance Metric 2, Performance Metric 3, and Performance Metric 4. If the VIF value between Performance Metric 3 and Performance Metric 4 is relatively high, the electronic device can determine that Performance Metric 3 is the target performance metric, and Performance Metric 4 is the first performance metric related to Performance Metric 3. The electronic device can determine that the multiple second performance metrics can include Performance Metric 1, Performance Metric 2, and Performance Metric 4.

[0075] Optionally, the second regression coefficient can indicate the influence degree of the second performance metric on the service metric. For example, the larger the absolute value of the second regression coefficient, the greater the influence degree of the second performance metric on the service metric, and the smaller the absolute value of the second regression coefficient, the smaller the influence degree of the second performance metric on the service metric.

[0076] Optionally, the electronic device can determine multiple second regression coefficients between the service metric and multiple second performance metrics based on the following feasible implementation: Delete the target performance metric from the multiple performance metrics to obtain multiple second performance metrics, and perform regression processing on the service metric and the multiple second performance metrics to obtain multiple second regression coefficients corresponding to the multiple second performance metrics. For example, after the electronic device determines the multiple second performance metrics, the electronic device can perform multiple linear regression processing on the service metric and the multiple second performance metrics, and then can obtain the second regression coefficient of each second performance metric, and then based on the second regression coefficient of the second performance metric, determine the influence degree of the second performance metric on the service metric.

[0077] Next, in combination with Figure 4 , the process of the electronic device determining multiple second performance metrics will be described.

[0078] Figure 4 FIG. is a schematic diagram of a process for determining multiple second performance metrics provided by an embodiment of the present disclosure. Please refer to Figure 4 , including: performance metrics associated with a service metric. Among them, the performance metrics can include video frame rate, video resolution, video bit rate, device power consumption, memory occupancy, and device temperature. The electronic device ( Figure 4 not shown) can determine that the VIF value between the video frame rate and the video resolution is relatively high, and the VIF value between the video frame rate and the video bit rate is relatively high. Therefore, the electronic device can determine that the target performance metric is the video frame rate, and the video resolution and the video bit rate can be the first performance metrics of the video frame rate. The electronic device can delete the video frame rate from the multiple performance metrics to obtain second performance metrics, where the second performance metrics can include device power consumption, video resolution, video bit rate, memory occupancy, and device temperature.

[0079] It should be noted that the electronic device may also determine multiple second regression coefficients between the service metrics and multiple second performance metrics based on any other feasible implementation manner, and the embodiments of the present disclosure do not limit this.

[0080] S206. Restore the regression coefficient of the target performance metric with respect to the service metric according to the first regression coefficient and multiple second regression coefficients.

[0081] Among them, the regression coefficient of the target performance metric with respect to the service metric can indicate the influence degree of the target performance metric on the service metric. For example, when the electronic device determines multiple second regression coefficients, in order to avoid the problem of multicollinearity, the target performance metric does not participate in multiple linear regression. Therefore, the electronic device cannot obtain the regression coefficient of the target performance metric, and the electronic device needs to determine the regression coefficient of the target performance metric with respect to the service metric based on other methods.

[0082] Among them, the regression coefficient of the target performance metric with respect to the service metric is proportional to the influence degree of the target performance metric on the service metric. For example, the larger the regression coefficient of the target performance metric with respect to the service metric, the greater the influence degree of the target performance metric on the service metric; the smaller the regression coefficient of the target performance metric with respect to the service metric, the smaller the influence degree of the target performance metric on the service metric.

[0083] Among them, the electronic device may determine the regression coefficient of the target performance metric with respect to the service metric based on the following feasible implementation manner: for any one of the first performance metrics, determine the target regression coefficient associated with the first performance metric among the multiple second regression coefficients, and determine the ratio of the target regression coefficient to the first regression coefficient of the first performance metric as the regression coefficient of the target performance metric with respect to the service metric.

[0084] Among them, the target regression coefficient may be the regression coefficient of the first performance metric among the multiple second regression coefficients. For example, for any one of the first performance metrics, the first regression coefficient between the first performance metric and the target performance metric is regression coefficient 1, and the second regression coefficient between the first performance metric and the service metric is regression coefficient 2. The electronic device may determine regression coefficient 2 as the target regression coefficient, and determine the ratio of regression coefficient 1 to regression coefficient 2 as the regression coefficient of the target performance metric with respect to the service metric. In this way, since the target regression coefficient can indicate the influence degree of the first performance metric on the service metric, and the first regression coefficient can indicate the influence degree of the first performance metric on the target performance metric, the electronic device can accurately determine the influence degree of the target performance metric on the service metric based on the first regression coefficient and the target regression coefficient.

[0085] Next, through a specific example, the electronic device's determination of the regression coefficient of the target performance metric with respect to the service metric will be described in detail.

[0086] Among them, the business indicator y can be related to the performance indicators x 1 , x 2 , x 3 , x 4 and x 5 . x 1 has a relatively high VIF value with x 2 . x 1 has a relatively high VIF value with x 3 . x 1 is the target performance indicator, x 2 and x 3 are the first performance indicators.

[0087] Among them, the relationship between the business indicator and multiple second performance indicators can be:

[0088] y = β 0 + β 2 x 2 + β 3 x 3 + β 4 x 4 + β 5 x 5 + ∈

[0089] Among them, y is the business indicator, β 0 and ∈ are constants, x 2 , x 3 , x 4 , x 5 are performance indicators related to the business indicator respectively, β 2 , β 3 , β 4 , β 5 are the regression coefficients of the performance indicators respectively. Among them, the business indicator is also related to the performance indicator x 1 . However, due to the problem of multicollinearity of x 1 , when performing linear regression, the electronic device needs to delete x 1 (the target performance indicator).

[0090] Among them, the relationship between the target performance indicator and the first performance indicator can be:

[0091] x 1 = c 0 + c 2 x 2 + c 3 x 3 + ∈

[0092] Among them, x 1 is the target performance indicator, c 0\(\xi\) and \(\epsilon\) are constants, \(x\) 2 and \(x\) 3 are the first performance indicators related to \(x\) 1 , \(c\) 2 and \(c\) 3 are the regression coefficients of the first performance indicator.

[0093] Based on the above formula, the electronic device can determine the regression coefficient of \(x\) 1 with respect to \(y\) (\(x\) 2 and \(x\) 3 are independent):

[0094] \(\beta\) 1 \(=\beta\) 2 / \(c\) 2 \(=\beta\) 3 / \(c\) 3

[0095] where \(\beta\) 1 can be the regression coefficient of \(x\) 1 with respect to \(y\). In this way, the electronic device can accurately determine the regression coefficient of the target performance indicator with respect to the business indicator based on the first regression coefficient and the second regression coefficient, and further can accurately determine the influence degree of the target performance indicator on the business indicator.

[0096] Next, in combination with Figure 5 , the process of determining the regression coefficient of the target performance indicator with respect to the business indicator will be described.

[0097] Figure 5 is a schematic diagram of a process for determining a regression coefficient provided by an embodiment of the present disclosure. Please refer to Figure 5 , including: a business indicator and a performance indicator associated with the business indicator. Among them, the business indicator can be the number of daily active users, and the performance indicators can include video frame rate, video resolution, video bit rate, device power consumption, occupied memory, and device problems. If the electronic device ( Figure 5 not shown) determines that the target performance indicator is the video frame rate, the electronic device can determine the first performance indicator and the second performance indicator. Among them, the first performance indicator includes video resolution and video bit rate, and the second performance indicator includes device power consumption, video resolution, video bit rate, occupied memory, and device temperature.

[0098] Please refer to Figure 5 , the electronic device performs linear regression processing on the target performance indicator and the first performance indicator, and obtains video frame rate = A × video resolution + B × video bit rate. The electronic device performs linear regression processing on the number of daily active users and the second performance indicator, and obtains number of daily active users = a × video resolution + b × video bit rate + c × device power consumption + d × occupied memory + e × device temperature. The electronic device can determine a / A or b / B as the regression coefficient of the video frame rate with respect to the number of daily active users.

[0099] An embodiment of the present disclosure provides a service processing method. An electronic device may obtain multiple performance indicators associated with a service indicator, and among the multiple performance indicators, determine a target performance indicator with a multicollinearity problem, determine a first performance indicator whose correlation with the target performance indicator is greater than or equal to a first threshold, and determine a first regression coefficient between the target performance indicator and the first performance indicator. Delete the target performance indicator among the multiple performance indicators to obtain multiple second performance indicators, perform a regression process on the service indicator and the multiple second performance indicators to obtain multiple second regression coefficients corresponding to the multiple second performance indicators. For any one of the first performance indicators, among the multiple second regression coefficients, determine a target regression coefficient associated with the first performance indicator, and determine the ratio of the target regression coefficient to the first regression coefficient of the first performance indicator as the regression coefficient of the target performance indicator on the service indicator. In this way, since the target regression coefficient can indicate the influence degree of the first performance indicator on the service indicator, and the first regression coefficient can indicate the influence degree of the first performance indicator on the target performance indicator, therefore, based on the target regression coefficient and the first regression coefficient of the first performance indicator, the electronic device can accurately determine the regression coefficient of the target performance indicator on the service indicator. In this way, even if there is a multicollinearity problem among the multiple performance indicators, the electronic device can also obtain the influence degree of each performance indicator on the service indicator, improving the accuracy of the regression coefficient.

[0100] In Figure 2 Based on the embodiment shown above, the above service processing method further includes a method for verifying the accuracy of the regression coefficient of each performance indicator. Next, in combination with Figure 6 , a method for verifying the accuracy of the regression coefficient of each performance indicator will be described in detail.

[0101] Figure 6 It is a schematic diagram of a method for verifying a regression coefficient provided by an embodiment of the present disclosure. Please refer to Figure 6 , the method process includes:

[0102] S601. Obtain a first confidence interval corresponding to each second regression coefficient.

[0103] Among them, the first confidence region may be a confidence interval corresponding to the second regression coefficient. For example, the confidence interval may represent an interval of the sample estimating the overall average value range, that is, the confidence interval may be a range where the true value appears centered on the measured value under a confidence level.

[0104] Optionally, after the electronic device processes the multiple second performance indicators based on multiple linear regression, it can not only obtain multiple second regression coefficients corresponding to the multiple second performance indicators, but also obtain a first confidence interval corresponding to each second regression coefficient.

[0105] It should be noted that the electronic device may also determine the first confidence interval corresponding to each second regression coefficient based on any feasible implementation manner, and the embodiments of the present disclosure do not limit this.

[0106] S602. Determine multiple third regression coefficients between the service metric and multiple third performance metrics.

[0107] Among them, the third performance metrics include other performance metrics except the first performance metric among the multiple performance metrics. For example, the performance metrics associated with the service metric may include Performance Metric 1, Performance Metric 2, Performance Metric 3, Performance Metric 4, and Performance Metric 5. If the correlation between Performance Metric 3 and Performance Metric 4 and Performance Metric 5 is relatively high (the correlation between Performance Metric 4 and Performance Metric 5 is relatively low), the electronic device may determine Performance Metric 4 and Performance Metric 5 as the first performance metrics (Performance Metric 3 is the target performance metric), and the electronic device may determine that the multiple third performance metrics may include Performance Metric 1, Performance Metric 2, and Performance Metric 3.

[0108] Among them, the third regression coefficient may indicate the influence degree of the third performance metric on the service metric. For example, the larger the absolute value of the third regression coefficient of the third performance metric, the greater the influence degree of the third performance metric on the service metric, and the smaller the absolute value of the third regression coefficient of the third performance metric, the smaller the influence degree of the third performance metric on the service metric.

[0109] It should be noted that the electronic device may determine the multiple third regression coefficients between the service metric and the multiple third performance metrics based on any feasible implementation manner, and the embodiments of the present disclosure do not limit this.

[0110] Next, in combination with Figure 7 , the process of determining the third regression coefficient will be described.

[0111] Figure 7 FIG. is a schematic diagram of a process for determining a third regression coefficient provided by an embodiment of the present disclosure. Please refer to Figure 7 , which includes a service metric and performance metrics associated with the service metric. Among them, the service metric may be the number of daily active users, and the performance metrics may include video frame rate, video resolution, video bit rate, device power consumption, occupied memory, and device temperature. Among them, since the VIF value between the video frame rate and the video resolution is relatively high, and the VIF value between the video frame rate and the video bit rate is relatively high, therefore, the electronic device ( Figure 7 not shown) may determine that the target performance metric is the video frame rate.

[0112] Please refer to Figure 7, the electronic device can determine that the first performance metrics associated with the target performance metric are video resolution and video bitrate. The electronic device can delete the first performance metrics from multiple performance metrics to obtain third performance metrics (there is no multicollinearity problem). The third performance metrics can include video frame rate, device power consumption, memory occupancy, and device problems. The electronic device can perform linear regression processing on the business metric and the third performance metrics to obtain the number of daily active users = A × video frame rate + B × memory occupancy + C × device power consumption + D × device temperature. Wherein, A, B, C, and D are the third regression coefficients of the third performance metrics respectively.

[0113] S603. Verify the accuracy of the regression coefficient of each performance metric based on the regression coefficient of the business metric with respect to the target performance metric, multiple first confidence intervals, and multiple third regression coefficients.

[0114] Among them, verifying the accuracy of the regression coefficient of each performance metric can be to verify the reliability of the regression coefficient of each performance metric with respect to the business metric. For example, in the actual application process, although the correlation between the target performance metric and other performance metrics is low, when performing linear regression processing after deleting the target performance metric, the regression coefficients of other performance metrics will also be affected. Therefore, it is necessary to determine whether the regression coefficients of other performance metrics change significantly after deleting the target performance metric. If the change is significant, it indicates that the reliability of the regression coefficients of the performance metrics obtained by the electronic device is low. If the change is small, it indicates that the reliability of the regression coefficients of the performance metrics obtained by the electronic device is high.

[0115] Among them, the electronic device can verify the accuracy of the regression coefficient of each performance metric with respect to the business metric based on the following feasible implementation method: determine the second confidence interval corresponding to the third regression coefficient of the target performance metric, and verify the accuracy of the regression coefficient of each performance metric with respect to the business metric based on the regression coefficient of the business metric with respect to the target performance metric, the second confidence interval, multiple third regression coefficients, and multiple first confidence intervals.

[0116] Among them, the second confidence interval can be the confidence interval of the third regression coefficient of the target performance metric. For example, when the electronic device determines multiple third regression coefficients, due to the problem of multicollinearity between the target performance metric and the first performance metric, the electronic device can delete the first performance metric and retain the target performance metric to obtain multiple third performance metrics (without the problem of multicollinearity). The electronic device can perform multiple linear regression processing on the service metric and the multiple third performance metrics to obtain the third regression coefficients of other performance metrics except the first performance metric (when the electronic device determines the second regression coefficient, the target performance metric is deleted). Moreover, when the electronic device obtains the third regression coefficient, it can also obtain the second confidence interval corresponding to each third regression coefficient. Therefore, the electronic device can obtain the second confidence interval corresponding to the third regression coefficient of the target performance metric.

[0117] It should be noted that the electronic device can also determine the second confidence interval of the third regression coefficient based on any other feasible implementation manner, and the embodiments of the present disclosure do not limit this.

[0118] Among them, the electronic device verifies the accuracy of the regression coefficient of each performance metric based on the regression coefficient of the service metric with respect to the target performance metric, the second confidence interval, the multiple third regression coefficients, and the multiple first confidence intervals. Specifically, if the regression coefficient of the target performance metric with respect to the service metric is within the second confidence interval, and each third regression coefficient is within the corresponding first confidence interval, it is determined that the verification result of the regression coefficient of each performance metric is verified to pass. If the regression coefficient of the target performance metric with respect to the service metric is not within the second confidence interval, or each third regression coefficient is not within the corresponding first confidence interval, it is determined that the verification result of the regression coefficient of each performance metric is verified to fail.

[0119] For example, if the regression coefficient of the target performance metric with respect to the service metric is within the second confidence interval, it indicates that the accuracy of the regression coefficient of the target performance metric with respect to the service metric determined by the electronic device based on the first regression coefficient and the target regression coefficient is relatively high. Moreover, if each third regression coefficient is within the corresponding first confidence interval, the electronic device can determine that the accuracy of the regression coefficients of other performance metrics except the target performance metric is relatively high. Therefore, the electronic device can determine that the verification result is verified to pass, that is, the reliability of the regression coefficient of each performance metric is relatively high.

[0120] For example, if the regression coefficient of the target performance metric with respect to the business metric is not within the range of the second confidence interval, it indicates that the accuracy of the regression coefficient of the target performance metric determined by the electronic device based on the first regression coefficient and the target regression coefficient with respect to the business metric is low. Alternatively, if any of the third regression coefficients is not within the corresponding first confidence interval, the electronic device may determine that the accuracy of the regression coefficients of other performance metrics except the target performance metric is low. The electronic device may determine that the verification result fails, that is, after deleting the target performance metric, the accuracy of the regression coefficients of the other performance metrics obtained is low.

[0121] Among them, the first confidence interval corresponding to the third regression coefficient may be the first confidence interval of the first regression coefficient of the performance metric corresponding to the third regression coefficient. For example, if the third regression coefficient of a performance metric is regression coefficient 1 and the first regression coefficient of the performance metric is regression coefficient 2, when the electronic device determines regression coefficient 2, a confidence interval can be obtained. If regression coefficient 1 is within this confidence interval, it indicates that the regression coefficient of this performance metric is reliable.

[0122] An embodiment of the present disclosure provides a method for verifying regression coefficients. Obtain the first confidence interval corresponding to each second regression coefficient, determine the multiple third regression coefficients between the business metric and multiple third performance metrics, determine the second confidence interval corresponding to the third regression coefficient of the target performance metric, and verify the accuracy of the regression coefficient of each performance metric with respect to the business metric based on the regression coefficient of the target performance metric with respect to the business metric, the second confidence interval, the multiple third regression coefficients, and the multiple first confidence intervals. In this way, the electronic device can delete the first performance metric and let the target performance metric participate in the regression, and then verify the multiple regression coefficients obtained by the electronic device based on the third regression coefficients and the first confidence intervals, improving the accuracy of the regression coefficients.

[0123] In Figure 6 Based on the shown embodiment, below, in combination with Figure 8 , the above process of verifying regression coefficients will be described.

[0124] Figure 8 FIG. is a schematic diagram of a process for verifying regression coefficients provided by an embodiment of the present disclosure. Please refer to Figure 8 , including: a business metric, a second performance metric, and a third performance metric. Among them, the business metric may be the number of daily active users, the second performance metrics may include device power consumption, video resolution, video bit rate, occupied memory, and device temperature, and the third performance metrics may include video frame rate, device power consumption, occupied memory, and device temperature (the target performance metric is the video frame rate, and the first performance metrics are the video resolution and video bit rate).

[0125] Please refer to Figure 8 , the electronic device (Figure 8 (not shown) can perform linear regression processing on the service metrics and the second performance metrics to obtain the number of daily active users = a × video resolution + b × video bit rate + c × device power consumption + d × occupied memory + e × device temperature, and the first confidence interval. The electronic device performs linear regression processing on the service metrics and the third performance metrics to obtain the number of daily active users = A × video frame rate + B × device power consumption + C × occupied memory + D × device temperature, and the second confidence interval.

[0126] Please refer to Figure 8 , in the first confidence interval, the first confidence interval of the second regression coefficient of the video resolution is interval 1, the first confidence interval of the second regression coefficient of the video bit rate is interval 2, the first confidence interval of the second regression coefficient of the device power consumption is interval 3, the first confidence interval of the second regression coefficient of the occupied memory is interval 4, and the first confidence interval of the second regression coefficient of the device temperature is interval 5. In the second confidence interval, the second confidence interval of the third regression coefficient of the video frame rate is interval 6, the second confidence interval of the third regression coefficient of the device power consumption is interval 7, the second confidence interval of the third regression coefficient of the occupied memory is interval 8, and the second confidence interval of the third regression coefficient of the device temperature is interval 9.

[0127] Please refer to Figure 8 , if the regression coefficient of the video frame rate is within interval 6 (the regression coefficient of the target performance metric on the service metric is within the second confidence interval), B is within interval 3, C is within interval 4, and D is within interval 5, then the electronic device can determine that the regression coefficients of each performance metric are accurate. That is, after deleting the target performance metric, the influence on the regression coefficients of other performance metrics is small, the accuracy of the second regression coefficients between other performance metrics and the service metric is relatively high, and the accuracy of the regression coefficient of the target performance metric determined by the electronic device on the service metric is relatively high.

[0128] Figure 9 This is a schematic structural diagram of a service processing device provided by an embodiment of the present disclosure. Please refer to Figure 9 , the service processing device 900 includes a first acquisition module 901, a first determination module 902, a second determination module 903, a third determination module 904, a fourth determination module 905, and a fifth determination module 906, where:

[0129] The first acquisition module 901 is configured to acquire multiple performance metrics associated with the service metrics;

[0130] The first determination module 902 is configured to determine a target performance metric with a multicollinearity problem among the multiple performance metrics;

[0131] The second determination module 903 is configured to determine a first performance metric whose relevance to the target performance metric is greater than or equal to a first threshold;

[0132] The third determination module 904 is configured to determine a first regression coefficient between the target performance metric and the first performance metric;

[0133] The fourth determination module 905 is configured to determine a plurality of second regression coefficients between the service metric and a plurality of second performance metrics, where the second performance metrics are other performance metrics among the plurality of performance metrics except the target performance metric;

[0134] The fifth determination module 906 is configured to restore a regression coefficient of the target performance metric with respect to the service metric according to the first regression coefficient and the plurality of second regression coefficients, and the regression coefficient of the target performance metric with respect to the service metric is proportional to the influence degree of the target performance metric on the service metric.

[0135] According to one or more embodiments of the present disclosure, the fifth determination module 906 is specifically configured to:

[0136] For any one of the first performance metrics;

[0137] Among the plurality of second regression coefficients, determine a target regression coefficient associated with the first performance metric;

[0138] Determine a ratio of the target regression coefficient to the first regression coefficient of the first performance metric as the regression coefficient of the target performance metric with respect to the service metric.

[0139] According to one or more embodiments of the present disclosure, the fourth determination module 905 is specifically configured to:

[0140] Delete the target performance metric from the plurality of performance metrics to obtain a plurality of second performance metrics;

[0141] Perform regression processing on the service metric and the plurality of second performance metrics to obtain a plurality of second regression coefficients corresponding to the plurality of second performance metrics.

[0142] According to one or more embodiments of the present disclosure, the first determination module 902 is specifically configured to:

[0143] For any one performance metric;

[0144] Determine a variance inflation factor between the performance metric and each other performance metric;

[0145] If any one of the variance inflation factors is greater than or equal to a second threshold, then determine the performance metric as the target performance metric.

[0146] The service processing device provided by an embodiment of the present disclosure can be used to execute the technical solution of the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0147] Figure 10 For another structural schematic diagram of the service processing device provided by an embodiment of the present disclosure. On the basis of the embodiment shown in Figure 9 , please refer to Figure 10 . The service processing device 900 further includes a second acquisition module 907, wherein the second acquisition module 907 is used for:

[0148] acquire a first confidence interval corresponding to each second regression coefficient;

[0149] determine a plurality of third regression coefficients between the service metric and a plurality of third performance metrics, where the third performance metrics include other performance metrics except the first performance metric among the plurality of performance metrics;

[0150] verify the accuracy of the regression coefficient of each performance metric based on the regression coefficient of the service metric, a plurality of first confidence intervals, and the plurality of third regression coefficients with respect to the target performance metric.

[0151] According to one or more embodiments of the present disclosure, the second acquisition module 907 is specifically used for:

[0152] determine a second confidence interval corresponding to the third regression coefficient of the target performance metric;

[0153] verify the accuracy of the regression coefficient of each performance metric based on the regression coefficient of the service metric, the second confidence interval, the plurality of third regression coefficients, and the plurality of first confidence intervals with respect to the target performance metric.

[0154] According to one or more embodiments of the present disclosure, the second acquisition module 907 is specifically used for:

[0155] if the regression coefficient of the service metric with respect to the target performance metric is within the range of the second confidence interval, and each third regression coefficient is within the corresponding first confidence interval, then determine that the verification result of the regression coefficient of each performance metric is verified;

[0156] if the regression coefficient of the service metric with respect to the target performance metric is not within the range of the second confidence interval, or any one of the third regression coefficients is not within the corresponding first confidence interval, then determine that the verification result of the regression coefficient of each performance metric is not verified.

[0157] The service processing device provided by an embodiment of the present disclosure can be used to execute the technical solutions of the above method embodiments. The implementation principles and technical effects are similar, and will not be elaborated herein.

[0158] Figure 11 FIG. is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. Please refer to Figure 11 , which shows a schematic structural diagram of an electronic device 1100 suitable for implementing the embodiments of the present disclosure. Among them, the electronic 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 (Portable Android Devices, PADs), portable media players (PMPs), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 11 The electronic device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present disclosure.

[0159] As Figure 11 shown, the electronic device 1100 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage device 1108 into a random access memory (RAM) 1103. In the RAM 1103, various programs and data required for the operation of the electronic device 1100 are also stored. The processing device 1101, the ROM 1102, and the RAM 1103 are connected to each other through a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0160] Generally, the following devices may be connected to the I / O interface 1105: an input device 1106 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1107 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1108 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1109. The communication device 1109 can allow the electronic device 1100 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 11An electronic device 1100 is shown with various devices, but 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.

[0161] In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may 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 methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via a communication device 1109, or installed from a storage device 1108, or installed from a ROM 1102. When the computer program is executed by a processing device 1101, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.

[0162] It should be noted that the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may 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 the computer-readable storage medium may include, but are not limited to: an electrical connection with 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, the computer-readable storage medium may 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. And in the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which computer-readable program code is carried. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable signal medium may 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 may 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.

[0163] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist separately and not be assembled into the electronic device.

[0164] The above computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods shown in the above embodiments.

[0165] 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 methods that may be involved in various above embodiments are implemented.

[0166] An embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the methods that may be involved in various above embodiments.

[0167] 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, 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 (for example, by connecting through an Internet service provider using the Internet).

[0168] 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 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.

[0169] The units involved in the embodiments of the present disclosure can be implemented in software or in hardware. Among them, the name of a 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".

[0170] The functions described above herein can be performed at least in part by one or more hardware logic components. For example, without limitation, 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.

[0171] 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 fibers, portable compact disc read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. It should be noted that the modifiers "a" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless clearly specified otherwise in the context, it should be understood as "one or more". 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. 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 users' authorization should be obtained in an appropriate manner according to relevant laws and regulations.

[0172] For example, when a user's active request is received, 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 an electronic 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 a user's active request is received, the manner of sending a prompt message to the user may be, for example, in the form of a pop-up window, 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 electronic device.

[0173] It can be understood that the above notification and user authorization process is only illustrative and does not limit 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.

[0174] 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 traffic indication information.

[0175] In a first aspect, according to one or more embodiments of the present disclosure, the present disclosure includes a service processing method, and the method includes:

[0176] Obtain a plurality of performance indicators associated with the service indicator;

[0177] Among the plurality of performance indicators, determine a target performance indicator with a multicollinearity problem;

[0178] Determine a first performance indicator whose correlation with the target performance indicator is greater than or equal to a first threshold;

[0179] Determine a first regression coefficient between the target performance indicator and the first performance indicator;

[0180] Determine a plurality of second regression coefficients between the service indicator and a plurality of second performance indicators, where the second performance indicators are other performance indicators among the plurality of performance indicators except the target performance indicator;

[0181] According to the first regression coefficient and the plurality of second regression coefficients, restore the regression coefficient of the target performance indicator with respect to the service indicator, and the regression coefficient of the target performance indicator with respect to the service indicator is proportional to the influence degree of the target performance indicator on the service indicator

[0182] According to one or more embodiments of the present disclosure, restoring the regression coefficient of the target performance indicator with respect to the service indicator based on the first regression coefficient and the multiple second regression coefficients includes:

[0183] For any one of the first performance indicators;

[0184] Among the multiple second regression coefficients, determine the target regression coefficient associated with the first performance indicator;

[0185] Determine the ratio of the target regression coefficient to the first regression coefficient of the first performance indicator as the regression coefficient of the target performance indicator with respect to the service indicator.

[0186] According to one or more embodiments of the present disclosure, determining the multiple second regression coefficients between the service indicator and the multiple second performance indicators includes:

[0187] Delete the target performance indicator from the multiple performance indicators to obtain multiple second performance indicators;

[0188] Perform regression processing on the service indicator and the multiple second performance indicators to obtain multiple second regression coefficients corresponding to the multiple second performance indicators.

[0189] According to one or more embodiments of the present disclosure, determining the target performance indicator with a multicollinearity problem among the multiple performance indicators includes:

[0190] For any one performance indicator;

[0191] Determine the variance inflation factor between the performance indicator and each other performance indicator;

[0192] If any one of the variance inflation factors is greater than or equal to a second threshold, determine the performance indicator as the target performance indicator.

[0193] According to one or more embodiments of the present disclosure, after determining the regression coefficient of the target performance indicator with respect to the service indicator, the method further includes:

[0194] Obtain the first confidence interval corresponding to each second regression coefficient;

[0195] Determine the multiple third regression coefficients between the service indicator and the multiple third performance indicators, where the third performance indicators include other performance indicators except the first performance indicator among the multiple performance indicators;

[0196] Verify the accuracy of the regression coefficient of each performance indicator based on the regression coefficient of the target performance indicator with respect to the service indicator, the multiple first confidence intervals, and the multiple third regression coefficients.

[0197] According to one or more embodiments of the present disclosure, verifying the accuracy of the regression coefficient of each performance indicator based on the regression coefficient of the service indicator with respect to the target performance indicator, the plurality of first confidence intervals, and the plurality of third regression coefficients includes:

[0198] Determining a second confidence interval corresponding to the third regression coefficient of the target performance indicator;

[0199] Verifying the accuracy of the regression coefficient of each performance indicator based on the regression coefficient of the service indicator with respect to the target performance indicator, the second confidence interval, the plurality of third regression coefficients, and the plurality of first confidence intervals.

[0200] According to one or more embodiments of the present disclosure, verifying the accuracy of the regression coefficient of each performance indicator based on the regression coefficient of the service indicator with respect to the target performance indicator, the second confidence interval, the plurality of third regression coefficients, and the plurality of first confidence intervals includes:

[0201] If the regression coefficient of the target performance indicator with respect to the service indicator is within the range of the second confidence interval, and each third regression coefficient is within the corresponding first confidence interval, then determine that the verification result of the regression coefficient of each performance indicator is verified;

[0202] If the regression coefficient of the target performance indicator with respect to the service indicator is not within the range of the second confidence interval, or any one of the third regression coefficients is not within the corresponding first confidence interval, then determine that the verification result of the regression coefficient of each performance indicator is not verified.

[0203] In a second aspect, according to one or more embodiments of the present disclosure, an embodiment of the present disclosure provides a service processing apparatus, which includes a first acquisition module, a first determination module, a second determination module, a third determination module, a fourth determination module, and a fifth determination module, where:

[0204] The first acquisition module is configured to acquire a plurality of performance indicators associated with the service indicator;

[0205] The first determination module is configured to determine a target performance indicator with a multicollinearity problem among the plurality of performance indicators;

[0206] The second determination module is configured to determine a first performance indicator whose correlation with the target performance indicator is greater than or equal to a first threshold;

[0207] The third determination module is configured to determine a first regression coefficient between the target performance indicator and the first performance indicator;

[0208] The fourth determination module is configured to determine a plurality of second regression coefficients between the service metric and a plurality of second performance metrics, where the second performance metrics are other performance metrics among the plurality of performance metrics except the target performance metric;

[0209] The fifth determination module is configured to restore the regression coefficient of the target performance metric with respect to the service metric according to the first regression coefficient and the plurality of second regression coefficients, and the regression coefficient of the target performance metric with respect to the service metric is proportional to the influence degree of the target performance metric on the service metric.

[0210] According to one or more embodiments of the present disclosure, the fifth determination module is specifically configured to:

[0211] For any one of the first performance metrics;

[0212] Among the plurality of second regression coefficients, determine the target regression coefficient associated with the first performance metric;

[0213] Determine the ratio of the target regression coefficient to the first regression coefficient of the first performance metric as the regression coefficient of the target performance metric with respect to the service metric.

[0214] According to one or more embodiments of the present disclosure, the fourth determination module is specifically configured to:

[0215] Delete the target performance metric from the plurality of performance metrics to obtain a plurality of second performance metrics;

[0216] Perform regression processing on the service metric and the plurality of second performance metrics to obtain a plurality of second regression coefficients corresponding to the plurality of second performance metrics.

[0217] According to one or more embodiments of the present disclosure, the first determination module is specifically configured to:

[0218] For any one performance metric;

[0219] Determine the variance inflation factor between the performance metric and each other performance metric;

[0220] If any one of the variance inflation factors is greater than or equal to a second threshold, determine the performance metric as the target performance metric.

[0221] According to one or more embodiments of the present disclosure, the service processing device further includes a second acquisition module, where the second acquisition module is configured to:

[0222] Acquire a first confidence interval corresponding to each second regression coefficient;

[0223] Determine a plurality of third regression coefficients between the service metric and a plurality of third performance metrics, where the third performance metrics include other performance metrics among the plurality of performance metrics except the first performance metric;

[0224] Based on the regression coefficient of the service metric with respect to the target performance metric, the plurality of first confidence intervals, and the plurality of third regression coefficients, verify the accuracy of the regression coefficient of each performance metric.

[0225] According to one or more embodiments of the present disclosure, the second acquisition module is specifically configured to:

[0226] Determine a second confidence interval corresponding to the third regression coefficient of the target performance metric;

[0227] Based on the regression coefficient of the service metric with respect to the target performance metric, the second confidence interval, the plurality of third regression coefficients, and the plurality of first confidence intervals, verify the accuracy of the regression coefficient of each performance metric.

[0228] According to one or more embodiments of the present disclosure, the second acquisition module is specifically configured to:

[0229] If the regression coefficient of the target performance metric with respect to the service metric is within the range of the second confidence interval, and each third regression coefficient is within the corresponding first confidence interval, determine that the verification result of the regression coefficient of each performance metric is verified;

[0230] If the regression coefficient of the target performance metric with respect to the service metric is not within the range of the second confidence interval, or any one of the third regression coefficients is not within the corresponding first confidence interval, determine that the verification result of the regression coefficient of each performance metric is not verified.

[0231] In a third aspect, an embodiment of the present disclosure provides a terminal device including: a processor and a memory;

[0232] The memory stores computer-executable instructions;

[0233] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the methods as described in the first aspect and various possible methods related to the first aspect above.

[0234] 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 as described in the first aspect and various possible methods related to the first aspect above are implemented.

[0235] 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, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present disclosure.

[0236] In addition, 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 above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, the various features described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0237] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. On the contrary, the specific features and acts described above are merely example forms for implementing the claims.

Claims

1. A business processing method, characterized in that, comprising: obtaining a plurality of performance indicators associated with a business indicator; determining, among the plurality of performance indicators, a target performance indicator with a multicollinearity problem; determining a first performance indicator whose correlation with the target performance indicator is greater than or equal to a first threshold; determining a first regression coefficient between the target performance indicator and the first performance indicator; determining a plurality of second regression coefficients between the business indicator and a plurality of second performance indicators, where the second performance indicators are other performance indicators among the plurality of performance indicators except the target performance indicator; restoring the regression coefficient of the target performance indicator with respect to the business indicator according to the first regression coefficient and the plurality of second regression coefficients, and the regression coefficient of the target performance indicator with respect to the business indicator is proportional to the influence degree of the target performance indicator on the business indicator.

2. The method according to claim 1, characterized in that, the restoring the regression coefficient of the target performance indicator with respect to the business indicator according to the first regression coefficient and the plurality of second regression coefficients includes: for any one of the first performance indicators; determining, among the plurality of second regression coefficients, a target regression coefficient associated with the first performance indicator; determining the ratio of the target regression coefficient to the first regression coefficient of the first performance indicator as the regression coefficient of the target performance indicator with respect to the business indicator.

3. The method according to claim 1, characterized in that, the determining the plurality of second regression coefficients between the business indicator and the plurality of second performance indicators includes: deleting the target performance indicator from the plurality of performance indicators to obtain a plurality of second performance indicators; performing a regression process on the business indicator and the plurality of second performance indicators to obtain a plurality of second regression coefficients corresponding to the plurality of second performance indicators.

4. The method according to any one of claims 1-3, characterized in that, the determining, among the plurality of performance indicators, a target performance indicator with a multicollinearity problem includes: for any one performance indicator; determining the variance inflation factor between the performance indicator and each other performance indicator; if any one of the variance inflation factors is greater than or equal to a second threshold, then determining the performance indicator as the target performance indicator.

5. The method according to any one of claims 1-3, characterized in that, after determining the regression coefficient of the target performance indicator with respect to the business indicator, the method further includes: obtaining a first confidence interval corresponding to each second regression coefficient; determining a plurality of third regression coefficients between the business indicator and a plurality of third performance indicators, where the third performance indicators include other performance indicators among the plurality of performance indicators except the first performance indicator; verifying the accuracy of the regression coefficient of each performance indicator based on the regression coefficient of the target performance indicator with respect to the business indicator, the plurality of first confidence intervals, and the plurality of third regression coefficients.

6. The method according to claim 5, characterized in that, Verifying the accuracy of the regression coefficient of each performance indicator based on the regression coefficient of the service indicator with respect to the target performance indicator, multiple first confidence intervals, and the multiple third regression coefficients includes: Determining a second confidence interval corresponding to the third regression coefficient of the target performance indicator; Verifying the accuracy of the regression coefficient of each performance indicator based on the regression coefficient of the service indicator with respect to the target performance indicator, the second confidence interval, the multiple third regression coefficients, and the multiple first confidence intervals.

7. The method according to claim 6, wherein, Verifying the accuracy of the regression coefficient of each performance indicator based on the regression coefficient of the service indicator with respect to the target performance indicator, the second confidence interval, the multiple third regression coefficients, and the multiple first confidence intervals includes: If the regression coefficient of the service indicator with respect to the target performance indicator is within the range of the second confidence interval, and each third regression coefficient is within the corresponding first confidence interval, then determining that the verification result of the regression coefficient of each performance indicator is verified; If the regression coefficient of the service indicator with respect to the target performance indicator is not within the range of the second confidence interval, or any one of the third regression coefficients is not within the corresponding first confidence interval, then determining that the verification result of the regression coefficient of each performance indicator is not verified.

8. A service processing device, wherein, It includes a first acquisition module, a first determination module, a second determination module, a third determination module, a fourth determination module, and a fifth determination module, where: The first acquisition module is configured to acquire multiple performance indicators associated with the service indicator; The first determination module is configured to determine a target performance indicator with a multicollinearity problem among the multiple performance indicators; The second determination module is configured to determine a first performance indicator whose correlation with the target performance indicator is greater than or equal to a first threshold; The third determination module is configured to determine a first regression coefficient between the target performance indicator and the first performance indicator; The fourth determination module is configured to determine multiple second regression coefficients between the service indicator and multiple second performance indicators, where the second performance indicators are other performance indicators among the multiple performance indicators except the target performance indicator; The fifth determination module is configured to restore the regression coefficient of the target performance indicator with respect to the service indicator according to the first regression coefficient and the multiple second regression coefficients, and the regression coefficient of the target performance indicator with respect to the service indicator is proportional to the influence degree of the target performance indicator on the service indicator.

9. An electronic device, wherein, It includes: 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 service processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium, wherein, The computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the service processing method described in any one of claims 1 to 7 is implemented.

Images