Method and apparatus for predicting device performance consumption, computer device, and storage medium

Abstract

A method and apparatus for predicting device performance consumption, a computer device, and a storage medium. The method comprises: acquiring first object information, and acquiring device information and second object information, the first object information representing a first object of a network device in a network system which is preparing to consume a device performance indicator, the device information representing operation conditions of the network device in the network system, and the second object information representing a second object of the network device in the network system which is consuming a device performance indicator; and calling a performance model to generate a prediction result on the basis of the first object information, the device information, and the second object information, the prediction result representing, when the network device in the network system is burdened with the first object and the second object, a device performance indicator which needs to be consumed by the network device.

Description

Device performance consumption prediction method, device, computer device and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on September 1, 2023, with application number 202311126710.4 and application name “Equipment Performance Consumption Prediction Method, Device, Computer Equipment and Storage Medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of Internet technology, and in particular to a method, apparatus, computer equipment, and storage medium for predicting device performance consumption. Background Art

[0004] Security is increasingly important in modern networks, and firewalls are now ubiquitous in virtually every network. The number of integrated firewall features continues to increase, including intrusion prevention systems (IPS) and antivirus (AV). Generally, different network sizes and the number of features enabled place varying demands on network device performance.

[0005] Summary of the Invention

[0006] Embodiments of the present application provide a method, apparatus, computer device, and storage medium for predicting device performance consumption.

[0007] In a first aspect, the present application provides a device performance consumption prediction method, which is applied to a network system and includes:

[0008] Acquire first object information, and acquire device information and second object information; wherein the first object information represents a first object of a network device in a network system that is about to consume a device performance indicator; the device information represents an operating status of the network device in the network system; and the second object information represents a second object of a performance indicator that is being consumed by the network device in the network system;

[0009] Call a preset performance model to generate a prediction result based on the first object information, the device information and the second object information; wherein, the prediction result represents the network device in the network system, and the device performance indicators that the network device needs to consume when bearing the first object and the second object.

[0010] In one embodiment, the first object information includes first function information, and the second object information includes second function information;

[0011] Acquiring first object information, and acquiring device information and second object information, including:

[0012] Receive first function information sent by the terminal, and obtain device information and second function information; wherein, the first function information represents the function that the terminal is ready to enable; the device information includes terminal access configuration information and operation information; the terminal access configuration information represents the threshold value of the number of terminals that the network device can access, and the operation information includes the number of terminals connected to the network device; the second function information represents the functions that have been enabled by the network device in the network system.

[0013] In this solution, by receiving the first function information sent by the terminal, it is determined that the terminal needs to enable new functions in the network system. By obtaining device information, the configuration status of the network equipment in the network system, the performance indicators of the network equipment in the network system, and the enabled functions of the network equipment in the network system are obtained to ensure the comprehensiveness of information acquisition.

[0014] In one embodiment, calling a preset performance model to generate a prediction result based on the first object information, the device information, and the second object information includes:

[0015] Invoking a preset performance model to generate a target function range based on the first function information, the second function information, and the operating information in the device information; wherein the target function range refers to the upper and lower limits of the device performance indicator that can be consumed by a terminal connected to the network device in the network system when the network device activates the function of the first function information and the function of the second function information;

[0016] A prediction result of the first function information is determined according to the terminal access configuration information in the device information and the target function interval.

[0017] In this solution, a target functional range is generated by a performance model based on the first functional information, the second functional information and the operating information in the device information, so as to achieve a technical effect of multi-angle analysis to determine the upper and lower limits of the device performance indicators that can be consumed by a terminal connected to the network device, thereby ensuring the accuracy of the target functional range; by determining the prediction result based on the terminal access configuration information and the target functional range, while ensuring the accuracy of the target functional range, the prediction result is determined in a targeted manner based on the device information of different network devices, thereby ensuring the accuracy of the prediction result.

[0018] In one embodiment, the network system includes a cloud and at least one second network device;

[0019] Calling a preset performance model to generate a target function range according to the first function information, the second function information, and the operation information in the device information includes:

[0020] The cloud enters the first function information, the second function information, and the operating information in the first device information into a preset performance analysis interface; wherein the first device information refers to the device information of the first network device; the first network device is the network device among at least one of the second network devices that receives the first function information sent by the terminal;

[0021] The cloud calls the performance model through the performance analysis interface, so that the performance model generates a target function interval according to the first function information and the operation information and the second function information in the first device information.

[0022] In this solution, the cloud enters the first function information, the second function information and the operating information in the first device information into a preset performance analysis interface and calls the performance model through the performance analysis interface, so that the performance model is called by the cloud using an interface based on the first function information, thereby clarifying the functions provided to the network device, reducing the coupling between other functions in the cloud and the performance model, and facilitating frequent training and maintenance of the performance model.

[0023] In one embodiment, the network system includes a cloud and at least one second network device;

[0024] Determining a prediction result of the first functional information according to the terminal access configuration information in the device information and the target functional range includes:

[0025] The cloud multiplies the terminal access configuration information in the first device information by the upper limit and lower limit of the target function range, respectively, to obtain a predicted upper limit value and a predicted lower limit value; wherein the first device information refers to the device information of the first network device; the first network device is the network device among the at least one second network device that receives the first object information sent by the terminal;

[0026] The cloud constructs a numerical range according to the prediction upper limit value and the prediction lower limit value, and uses the numerical range as the prediction result.

[0027] In this solution, the cloud multiplies the terminal access configuration information in the first device information with the upper limit value and the lower limit value in the target functional range respectively to obtain the predicted upper limit value and the predicted lower limit value, and constructs a numerical range based on the predicted upper limit value and the predicted lower limit value, and uses the numerical range as the prediction result. This realizes the target functional range of the performance indicators that may be consumed by the terminal when the network device accesses the terminal based on the terminal access configuration information of the network device, and the target functional range of the performance indicators that may be consumed by the terminal when the network device accesses the terminal, and specifically judges the interval of the performance indicators that may be consumed by the network device once all terminals turn on the function of the first functional information, thereby greatly ensuring the reliability of the prediction result.

[0028] In one embodiment, the first object information includes first function information, and the second object information includes second function information.

[0029] The calling the preset performance model to generate a prediction result according to the first object information, the device information, and the second object information includes:

[0030] calling the preset performance model to generate a target functional range based on the first functional information in the first object information, the second functional information in the second object information, and the operating information in the device information; wherein the target functional range refers to the upper and lower limits of the device performance indicator that can be consumed by a terminal connected to the network device in the network system when the network device in the network system enables the function of the first functional information and the function of the second functional information; and

[0031] A prediction result of the first function information is determined according to the terminal access configuration information in the device information and the target function interval.

[0032] In one embodiment, the first object information includes first capacity information, and the second object information includes second capacity information;

[0033] Acquiring first object information, and acquiring device information and second object information, including:

[0034] Receive the first capacity information sent by the terminal, and obtain the device information and the second capacity information; wherein, the first capacity information represents the number of terminals that the network device in the network system is ready to add; the device information includes activation information; the activation information represents the enabled function of the network device in the network system; the second capacity information represents the number of terminals connected to the network device in the network system.

[0035] In this solution, by receiving the first capacity information sent by the terminal, the number of terminals that the terminal needs to newly connect to the network system is determined. By obtaining the device information, the configuration status of the network equipment in the network system, the performance indicators of the network equipment in the network system, and the number of terminals that have been connected to the network equipment in the network system are obtained to ensure the comprehensiveness of information acquisition.

[0036] In one embodiment, calling a preset performance model to generate a prediction result based on the first object information, the device information, and the second object information includes:

[0037] Call a preset performance model to generate a target capacity interval based on the first capacity information, the second capacity information and the activation information in the device information, and use the target capacity interval as a prediction result of the first capacity information; wherein, the target capacity interval refers to the upper and lower limits of the device performance indicators consumed by the network device in the network system when the network device is connected to the sum of the first and second numbers of terminals; the first number is the number of terminals corresponding to the first capacity information; the second number is the number of terminals corresponding to the second capacity information.

[0038] In this solution, a target capacity interval is generated by a performance model based on the first capacity information, the operating information and the second capacity information in the device information, so as to achieve a technical effect of multi-angle analysis to determine the upper and lower limits of the device performance indicators that can be consumed by a terminal connected to the network device, thereby ensuring the accuracy of the target capacity interval; by determining the prediction result based on the terminal access configuration information and the target capacity interval, while ensuring the accuracy of the target capacity interval, the prediction result is determined in a targeted manner based on the device information of different network devices, thereby ensuring the accuracy of the prediction result.

[0039] In one embodiment, before obtaining the first object information and obtaining the device information and the second object information, the method further includes:

[0040] Collect historical performance data for each type of operating information in a functional scenario; wherein the functional scenario represents an enabled function of a network device in the network system; the operating information represents the number of terminals connected to the network device in the network system; and the historical performance data represents the performance indicators of the device being consumed in the network system under a type of operating information in the functional scenario;

[0041] Obtaining a functional performance range for the functional scenario based on at least one historical performance data corresponding to the functional scenario; wherein the functional performance range represents an upper limit and a lower limit of a device performance indicator that a terminal can consume a network device in a functional scenario;

[0042] At least one of the functional scenarios is used as input data, and functional performance intervals corresponding to at least one of the functional scenarios are used as output data to train a preset initial model to obtain a performance model.

[0043] In this solution, historical performance data of various operating information under various functional scenarios is collected to train the initial model and obtain the performance model, ensuring the comprehensiveness of the performance model training.

[0044] In one embodiment, obtaining a functional performance range of the functional scenario according to at least one historical performance data corresponding to the functional scenario includes:

[0045] Obtaining, based on at least one historical performance data under a target functional scenario, at least one unit performance data under the target functional scenario; wherein the unit performance data represents a device performance indicator consumed by a terminal under the target functional scenario;

[0046] Performing a regression operation on each of the unit performance data under the target functional scenario to obtain a regression curve of the target functional scenario; wherein the regression curve represents the probability of occurrence of each category of unit performance data in the target functional scenario; the category represents the numerical range within which the value of the unit performance data lies; and the target functional scenario is one of at least one functional scenario;

[0047] Enter a preset regression interval into the regression curve to obtain a functional performance interval for the target functional scenario; wherein the regression interval is used to determine a target range for extracting categories in the regression curve; the target range determines at least one target category in the regression curve; the functional performance interval is used to cover unit performance data in at least one of the target categories; the upper limit of the functional performance interval is the first value of the unit performance data in at least one target category; the lower limit of the functional performance interval is the second value of the unit performance data in at least one target category.

[0048] In this solution, a regression curve is obtained by performing a regression operation on each unit performance data, and the functional performance interval in the regression curve is determined based on the regression interval, wherein the regression interval defines the difference degree interval, that is, the upper and lower limits of the unit performance data in the N% range in the regression curve. For example, what are the upper and lower limits of the unit performance data with an exposure probability of 90% in the regression curve (that is, in most of the range of the curve), and the functional performance interval is constructed based on the upper and lower limits.

[0049] In one embodiment, before obtaining the first object information and obtaining the device information and the second object information, the method further includes:

[0050] Collect historical performance data for each type of activation information under a capacity scenario; wherein the capacity scenario represents the number of terminals connected to the network device in the network system; the activation information represents the functions enabled by the network device in the network system; and the historical performance data represents the device performance indicators being consumed by the network device in a type of activation information under the capacity scenario;

[0051] Obtaining a capacity performance interval for the capacity scenario based on at least one of the historical performance data; wherein the capacity performance interval represents an upper limit and a lower limit of a device performance indicator consumed by the network device in the capacity scenario;

[0052] At least one of the capacity scenarios is used as input data, and the capacity performance intervals corresponding to the at least one capacity scenario are used as output data to train a preset initial model to obtain a performance model.

[0053] In this solution, historical performance data of various operating information under various capacity scenarios is collected to train the initial model and obtain the performance model, thereby ensuring the comprehensiveness of the performance model training.

[0054] In one embodiment, after calling a preset performance model to generate a prediction result based on the first object information, the device information, and the second object information, the method further includes:

[0055] Comparing the performance configuration information in the device information with the prediction result; wherein the performance configuration information represents the device performance indicator threshold that the network device can consume;

[0056] If it is determined that the prediction result exceeds the performance configuration information, functional warning information is generated.

[0057] In this solution, by comparing the performance configuration information with the prediction results and generating function warning information, the technical effect of timely feedback of function activation alarm is achieved.

[0058] In one embodiment, the calling of a preset performance model to generate a prediction result according to the first object information, the device information, and the second object information includes:

[0059] The preset performance model is called to generate a target capacity interval according to the first capacity information in the first object information, the second capacity information in the second object information, and the activation information in the device information, and the target capacity interval is used as the prediction result of the first capacity information; wherein, the target capacity interval refers to the upper and lower limits of the device performance indicators consumed by the network device in the network system when the network device is connected to the sum of the first and second numbers of terminals; the first number is the number of terminals corresponding to the first capacity information; the second number is the number of terminals corresponding to the second capacity information.

[0060] In a second aspect, an embodiment of the present application provides a device performance consumption prediction apparatus, which is installed in a network system and includes:

[0061] An input module is configured to obtain first object information and device information and second object information; wherein the first object information represents a first object of a network device in a network system that is about to consume a device performance indicator; the device information represents an operating status of the network device in the network system; and the second object information represents a second object of a performance indicator that is being consumed by the network device in the network system;

[0062] The processing module is configured to call a preset performance model to generate a prediction result based on the first object information, the device information and the second object information; wherein, the prediction result represents the network device in the network system, and the device performance indicators that the network device needs to consume when bearing the first object and the second object.

[0063] In one embodiment, the first object information includes first function information, and the second object information includes second function information;

[0064] The input module is configured to receive first function information sent by the terminal and obtain device information and second function information; wherein, the first function information represents the function that the terminal is ready to enable; the device information includes terminal access configuration information and operation information; the terminal access configuration information represents the threshold value of the number of terminals that the network device can access, and the operation information includes the number of terminals connected to the network device; the second function information represents the enabled function of the network device in the network system.

[0065] In one embodiment, the processing module is configured to call a preset performance model to generate a target function range based on the first function information, the second function information, and the operating information in the device information; wherein the target function range refers to the upper and lower limits of a device performance indicator that can be consumed by a terminal connected to the network device in the network system when the network device activates the function of the first function information and the function of the second function information;

[0066] The processing module is further configured to determine a prediction result of the first function information according to the terminal access configuration information in the device information and the target function interval.

[0067] In one embodiment, the network system includes a cloud and at least one second network device; the processing module is disposed in the cloud;

[0068] The processing module in the cloud is configured to input the first function information, the second function information, and the operating information in the first device information into a preset performance analysis interface; wherein the first device information refers to device information of a first network device; the first network device is a network device among at least one of the network devices that receives the first function information sent by the terminal;

[0069] The processing module in the cloud is configured to call a performance model through the performance analysis interface, so that the performance model generates a target functional range according to the first functional information, and the operating information and second functional information in the first device information.

[0070] In one embodiment,

[0071] The processing module in the cloud is configured to multiply the terminal access configuration information in the first device information by the upper limit value and the lower limit value in the target functional range, respectively, to obtain a predicted upper limit value and a predicted lower limit value; wherein the first device information refers to device information of a first network device; the first network device is a network device among the at least one second network device that receives the first object information sent by the terminal;

[0072] The processing module in the cloud is configured to construct a numerical range according to the prediction upper limit value and the prediction lower limit value, and use the numerical range as the prediction result.

[0073] In one embodiment, the first object information includes first capacity information, and the second object information includes second capacity information;

[0074] An input module is configured to receive first capacity information sent by a terminal and obtain device information and second capacity information; wherein, the first capacity information represents the number of terminals that a network device in the network system is ready to add; the device information includes activation information; the activation information represents the enabled function of the network device in the network system; and the second capacity information represents the number of terminals connected to the network device in the network system.

[0075] In the above scheme, the processing module is configured to call a preset performance model to generate a target capacity interval based on the first capacity information, the second capacity information and the activation information in the device information, and use the target capacity interval as the prediction result of the first capacity information; wherein, the target capacity interval refers to the upper and lower limits of the device performance indicators consumed by the network device in the network system when the network device is connected to the sum of the first and second numbers of terminals; the first number is the number of terminals corresponding to the first capacity information; the second number is the number of terminals corresponding to the second capacity information.

[0076] In one embodiment, the apparatus further includes: a function collection module configured to collect historical performance data of each type of operation information in a function scenario; wherein the function scenario represents an enabled function of a network device in the network system; the operation information represents the number of terminals connected to the network device in the network system; and the historical performance data represents a performance indicator of a device being consumed in the network system under a type of operation information in the function scenario;

[0077] A functional performance interval module is configured to obtain a functional performance interval for the functional scenario based on at least one historical performance data corresponding to the functional scenario; wherein the functional performance interval represents the upper and lower limits of the device performance indicator that a terminal can consume of the network device in a functional scenario;

[0078] The functional model training module is configured to take at least one of the functional scenarios as input data and the functional performance intervals corresponding to at least one of the functional scenarios as output data, train a preset initial model, and obtain a performance model.

[0079] In one embodiment, the function performance interval module is configured to obtain at least one unit performance data under the target function scenario based on at least one historical performance data under the target function scenario; wherein the unit performance data represents a device performance indicator consumed by a terminal under the target function scenario;

[0080] a functional performance interval module configured to perform a regression operation on each unit performance data in a target functional scenario to obtain a regression curve for the target functional scenario; wherein the regression curve represents the probability of occurrence of each category of unit performance data in the target functional scenario; the category represents the numerical interval within which the value of the unit performance data lies; and the target functional scenario is one of at least one functional scenario;

[0081] The functional performance interval module is configured to enter a preset regression interval into the regression curve to obtain the functional performance interval of the target functional scenario; wherein the regression interval is used to determine the target range for extracting the category in the regression curve; the target range determines at least one target category in the regression curve; the functional performance interval is used to cover the unit performance data in at least one of the target categories; the upper limit of the functional performance interval is the first value of the unit performance data in at least one target category; the lower limit of the functional performance interval is the second value of the unit performance data in at least one target category.

[0082] In one embodiment, the device further includes: a capacity acquisition module for

[0083] Collect historical performance data for each type of activation information under a capacity scenario; wherein the capacity scenario represents the number of terminals connected to the network device in the network system; the activation information represents the functions enabled by the network device in the network system; and the historical performance data represents the device performance indicators being consumed by the network device in a type of activation information under the capacity scenario;

[0084] A capacity performance interval module is configured to obtain a capacity performance interval of the capacity scenario based on at least one of the historical performance data; wherein the capacity performance interval represents an upper limit and a lower limit of a device performance indicator consumed by the network device in the capacity scenario;

[0085] The capacity model training module is configured to take at least one of the capacity scenarios as input data and the capacity performance intervals corresponding to at least one of the capacity scenarios as output data, train a preset initial model, and obtain a performance model.

[0086] In one embodiment, the apparatus further comprises:

[0087] a comparison module configured to compare the performance configuration information in the device information with the prediction result; wherein the performance configuration information represents a device performance indicator threshold that can be consumed by the network device;

[0088] The warning module is configured to generate functional warning information if it is determined that the prediction result exceeds the performance configuration information.

[0089] In a third aspect, an embodiment of the present application further provides a computer device, comprising: a processor and a memory communicatively connected to the processor;

[0090] The memory stores computer-executable instructions;

[0091] The processor executes the computer-executable instructions stored in the memory to implement the device performance consumption prediction method as described above.

[0092] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer execution instructions, and the computer execution instructions are used to implement the above-mentioned device performance consumption prediction method when executed by a processor.

[0093] In a fifth aspect, an embodiment of the present application further provides a computer program product, comprising a computer program, which implements the above-mentioned device performance consumption prediction method when executed by a processor.

[0094] The embodiments of the present application provide a device performance consumption prediction method, apparatus, computer equipment, and storage medium. By receiving first object information sent by a terminal, the method determines the object for which the network device is about to consume the device performance indicator, and obtains the device information to obtain the operating status of the network device and the object for which the network device in the network system is currently consuming the performance indicator.

[0095] By calling a preset performance model to generate a prediction result based on the first object information, the device information and the second object information, it is possible to predict the device performance indicators that the network device will consume when the network device adds a new object for consuming device performance indicators based on the device information of the network device, thereby ensuring the accuracy of the prediction results and improving the efficiency of generating the prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0097] FIG1 is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0098] FIG2 is a flow chart of an embodiment of a method for predicting device performance consumption provided by an embodiment of the present application;

[0099] FIG3 is a flow chart of another embodiment of a method for predicting device performance consumption provided in an embodiment of the present application;

[0100] FIG4 is a graph of a normal distribution curve in another embodiment of a method for predicting device performance consumption provided by an embodiment of the present application;

[0101] FIG5 is a flowchart of another embodiment of a method for predicting device performance consumption provided in an embodiment of the present application;

[0102] FIG6 is a schematic diagram of a program module of a device performance consumption prediction apparatus provided in an embodiment of the present application;

[0103] FIG7 is a schematic diagram of the hardware structure of a computer device in an embodiment of the present application.

[0104] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0105] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numbers in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with certain aspects of the embodiments of the present application, as detailed in the appended claims.

[0106] The specific application scenario of the embodiment of the present application is as follows: In modern network environments, security is becoming increasingly important, and firewalls are basically present in every network. The functions integrated into firewalls are also continuously increasing, such as intrusion detection (IPS) and anti-virus (AV). Generally, different network scales and when different functions are enabled have different performance requirements for network devices. A simple example:

[0107] 1. Assume that the performance base of a firewall (the upper limit of the traffic it can handle per second) is 1G;

[0108] 2. When IPS is enabled, the remaining performance of the firewall (the upper limit of the traffic that can be processed per second) is 300M;

[0109] 3. When the AV function is turned on, the remaining performance of the firewall (the upper limit of the traffic that can be processed per second) is 200M;

[0110] 4. When the IPS+AV function is enabled, the remaining performance of the firewall (the upper limit of the traffic that can be processed per second) may be only 100M;

[0111] 5. In actual network environments, the situations encountered are far more difficult than these. In actual environments, there may be complex conditions such as different types of terminals and applications.

[0112] 6. Based on 5., if a user wants to adjust the configuration or enable new features in their network environment, the newly enabled features may cause device performance degradation, network fluctuations, or even disconnection.

[0113] However, when the firewall function in a network device is newly enabled, it is usually manually judged based on experience and the device performance indicators of the network device consumed by the newly enabled function are predicted, resulting in low accuracy of the prediction results.

[0114] Since there are no software-based solutions, manual judgment is often required. For example, when releasing a product, device manufacturers typically list typical features and the throughput they support. Engineers may also estimate whether enabling a feature will affect performance based on their network conditions and then attempt to enable it.

[0115] Regarding the problem of being unable to judge in advance whether the performance degradation after the function is turned on will cause network disconnection. The exemplary embodiment of the present application can propose a method to inform the user of sufficient information before the user turns on the function, so that the user can perceive the risk in advance. The traffic sample information of the device is uploaded to the cloud through a large number of device terminals. The cloud performs big data analysis to generate a traffic and function combination algorithm. When a new function needs to be turned on, it can give a performance loss prompt caused by the new function based on the current traffic and function situation. The embodiment of the present application can solve the problem of low accuracy of the prediction result caused by the artificial judgment of the newly enabled function based on experience and the prediction of the device performance indicators of the consumed network device.

[0116] Please refer to Figure 1. The device performance consumption prediction method is applied to a network system 1. The network system 1 includes a cloud 11 and at least one network device 12. The cloud 11 can refer to a cloud server. The cloud server (ECS, full name Elastic Compute Service) is a simple, efficient, safe, reliable, and elastically scalable computing service. Its management method is simpler and more efficient than that of a physical server. The network device 13 is a physical entity connected to the network. The network device is equipped with network security protection devices such as firewalls and security gateways. Among them, a firewall is a network device that can monitor data packets entering and leaving the network and determine whether the data packets are legal according to preset rules. If they are illegal, the transmission of the data packets will be rejected. The security gateway is a multifunctional device that also has network firewall functions, intrusion detection functions, anti-virus functions, etc. A cloud 11 is connected to at least one network device 12.

[0117] Specifically, the network device 12 receives the first object information sent by the terminal 13 and obtains the device information from the network device 12;

[0118] The performance model preset in the cloud 11 generates a prediction result based on the first object information and the device information; wherein the prediction result represents the device performance indicator consumed by the network device when the object corresponding to the first object information and the second object information is enabled;

[0119] The cloud 12 sends the prediction result to the network device 12 , and the network device 12 sends the prediction result to the terminal 14 .

[0120] The expected impact of enabling the object on network devices and / or the impact of the number of newly connected terminals on network devices are given. This improves customer usability and provides greater control over overall network stability.

[0121] The following detailed description of the technical solution of the present application and how the technical solution of the present application solves the current problem is provided with specific embodiments. The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0122] In an exemplary embodiment, first object information is obtained, along with device information and second object information. The first object information represents the object of the network device in the network system that is about to consume device performance indicators. The device information represents the operating status of the network device in the network system. The second object information represents the object of the network device in the network system that is currently consuming performance indicators. The first object information is the function that the network device is about to enable, and the second object information is the function that the network device has enabled. The device information includes terminal access configuration information and operating information. The terminal access configuration information represents the threshold value of the number of terminals that the network device can access, and the operating information includes the number of terminals connected to the network device. For example, if the currently enabled function is function A, the function to be enabled is function B, and the terminal access configuration information indicates that the maximum number of terminals that the device can access is 10,000, then the cloud 11 will predict the device performance indicators that will be consumed when network device 12 enables functions A and B and when network device 12 accesses 10,000 terminals.

[0123] The performance model is called to generate a prediction result based on the first object information, device information and second object information, for example: predicting the device performance indicators that need to be consumed if network device 12 enables function A and function B and the network device 12 connects to 10,000 terminals.

[0124] In another exemplary embodiment, first object information is obtained, along with device information and second object information. The first object information represents the objects for which the network device in the network system is about to consume device performance indicators; the device information represents the operating status of the network device in the network system; and the second object information represents the objects for which the network device in the network system is currently consuming performance indicators. If the first object information is the number of terminals that the network device is about to connect to, for example, 500, then the second object information is the number of terminals already connected to the network device, for example, 1000. The device information includes activation information, which represents the enabled functions of the network device in the network system. For example, the device performance indicators consumed by the network device when functions A and B are enabled and 1000 terminals are connected are calculated. If, based on this, the network device is about to connect to 500 more terminals, the cloud 11 will predict the device performance indicators that will be consumed when network device 12 enables functions A and B and connects to 1500 terminals.

[0125] The performance model is called to generate a prediction result based on the first object information, device information, and second object information. For example, the prediction is made as follows: the device performance indicator that needs to be consumed by the network device 12 if 1,500 terminals are connected under the premise of enabling functions A and B. In another exemplary embodiment, the first object information is obtained, and the device information and the second object information are obtained; wherein the first object information represents the object for which the network device in the network system is about to consume the device performance indicator; the device information represents the operating status of the network device in the network system; and the second object information represents the object for which the network device in the network system is currently consuming the performance indicator; if the first object information is a function that the network device is about to enable, and the second object information is a function that the network device has enabled, the device information includes terminal access configuration information and operating information; the terminal access configuration information represents the threshold value of the number of terminals that the network device can access, and the operating information includes the number of terminals connected to the network device, as well as the traffic of the network device in the network system; for example, if the currently enabled function is function A and the function to be enabled is function B, the terminal access configuration information indicates that the maximum number of terminals that the device can access is 10,000, and the operating information indicates that the current traffic of the network device is 3,000M. Then, the cloud 11 will predict the device performance indicators that the network device 12 needs to consume when the network device 12 enables function A and function B.

[0126] The performance model is invoked to generate a prediction result based on the first object information, the device information, and the second object information. For example, the prediction is made regarding the device performance indicator required when network device 12 has functions A and B enabled, a traffic flow of 3000M, and 10,000 terminals connected to it. In another exemplary embodiment, if the first object information is the number of terminals that the network device is prepared to connect to, for example, 500, the second object information is the number of terminals that the network device has already connected to, for example, 1000.

[0127] Device information includes activation information, which represents the enabled functions and traffic of network devices in the network system. For example, when a network device has functions A and B enabled and connects to 1,000 terminals, and the current traffic of the network device is 3,000 Mbps, the device performance indicator consumed by the network device will be used. If the network device is prepared to connect to 500 more terminals, the cloud 11 will predict the device performance indicator required when network device 12 has functions A and B enabled and connects to 1,500 terminals.

[0128] The performance model is called to generate a prediction result based on the first object information, device information and second object information. For example, the device performance indicators required to be consumed when the network device 12 is connected to 1,500 terminals under the premise of enabling function A and function B and the traffic is 3,000M are predicted.

[0129] Referring to FIG. 2 , the present application provides a device performance consumption prediction method, which is applied to a network system and includes:

[0130] S201: Obtain first object information, device information, and second object information; wherein, the first object information represents an object of which a network device in the network system is about to consume device performance indicators; the device information represents an operating status of a network device in the network system; and the second object information represents an object of which a network device in the network system is consuming performance indicators.

[0131] In this step, by receiving the first object information sent by the terminal and / or receiving the first object information entered by the user in the network device of the network system, the object for which the network device is ready to consume the device performance indicator is determined, and by obtaining the device information, the operation status of the network device and the object for which the network device in the network system is currently consuming the performance indicator are obtained.

[0132] In one embodiment, the first object information includes first function information, and the second object information includes second function information;

[0133] Acquiring first object information, and acquiring device information and second object information, including:

[0134] Receive the first function information sent by the terminal, and obtain the device information and the second function information; wherein, the first function information represents the function that the terminal is ready to enable; the device information includes terminal access configuration information and operation information; the terminal access configuration information represents the terminal access configuration information represents the number threshold of terminals that the network device can access, and the operation information includes the number of terminals connected to the network device; the second function information represents the enabled function of the network device in the network system.

[0135] In an optional embodiment, the first object information includes first function information, and the second object information includes second function information;

[0136] Acquiring first object information, and acquiring device information and second object information, including:

[0137] Receive the first function information sent by the terminal, and obtain the device information and the second function information; wherein, the first function information represents the function that the terminal is ready to enable; the device information includes terminal access configuration information and operation information; the terminal access configuration information represents the number threshold of terminals that the network device can access, and the operation information includes the number of terminals connected to the network device, and the traffic of the network device in the network system; the second function information represents the enabled function of the network device in the network system.

[0138] In this step, the network device performs functional processing on data packets based on the enabled functions and network device traffic, and then sends the processed data packets to each terminal. Therefore, by receiving the first function information sent by the terminal, it is determined that the terminal requires a new function enabled by the network system. By acquiring device information, the configuration of the network devices in the network system, the performance indicators of the network devices in the network system, and the enabled functions of the network devices in the network system are obtained, ensuring comprehensive information acquisition. The network device traffic is the total amount of data sent and received by users when accessing the Internet. The greater the traffic, the more data the terminals connected to the network device send and receive, resulting in higher performance indicator consumption.

[0139] In one embodiment, the first object information includes first function information, and the second object information includes second function information;

[0140] Acquiring first object information, and acquiring device information and second object information, including:

[0141] The first network device receives the first function information sent by the terminal; wherein the first network device is one of the at least one network device; the first network device is used to provide a network environment for the terminal;

[0142] The first network device extracts the first device information and sends the first device information and the first function information to the cloud; wherein the first device information refers to the device information of the first network device.

[0143] Exemplarily, the user opens the configuration management unit in the network device through the terminal, and sends the first function information to the configuration management unit through the terminal.

[0144] The information collection unit of the network device collects terminal access configuration information, operation information, and second function information of the network device; obtains the terminal access configuration information from the configuration management of the network device through the information collection unit, and collects the number of terminals currently connected to the network device, the network device traffic, the second function information of the network device, and device performance indicators of the network device (for example, one or more of CPU usage, RAM usage, and network bandwidth utilization) from the data plane services of the network device through the information collection unit. The information collection unit sends the terminal access configuration information, operation information, and second function information to the configuration management unit.

[0145] In another embodiment, the first object information includes first capacity information, and the second object information includes second capacity information;

[0146] Acquiring first object information, and acquiring device information and second object information, including:

[0147] Receive the first capacity information sent by the terminal and obtain the device information and the second capacity information; wherein, the first capacity information represents the number of terminals that the network device in the network system is ready to add; the device information includes activation information; the activation information represents the enabled function of the network device in the network system; the second capacity information represents the number of terminals connected to the network device in the network system.

[0148] In another optional embodiment, the first object information includes first capacity information, and the second object information includes second capacity information;

[0149] Acquiring first object information, and acquiring device information and second object information, including:

[0150] Receive the first capacity information sent by the terminal and obtain the device information and the second capacity information; wherein, the first capacity information represents the number of terminals that the network device in the network system is ready to add; the device information includes activation information; the activation information represents the enabled functions of the network device in the network system and the traffic of the network device; the second capacity information represents the number of terminals connected to the network device in the network system.

[0151] In this embodiment, by receiving the first capacity information sent by the terminal, the number of terminals that need to be added to the network device of the network system is determined; by obtaining the activation information in the device information, the enabled functions of the network device and the traffic of the network device are obtained; by obtaining the second capacity information, the number of terminals currently connected to the network device is obtained.

[0152] Therefore, by receiving the first capacity information sent by the terminal, the number of terminals that the terminal needs to newly connect to the network system is determined, and by obtaining the device information, the configuration status of the network equipment in the network system, the performance indicators of the network equipment in the network system, and the number of terminals that have been connected to the network equipment in the network system are obtained to ensure the comprehensiveness of information acquisition.

[0153] S202: Calling a preset performance model to generate a prediction result based on the first object information, the device information, and the second object information; wherein the prediction result represents the device performance index consumed by the network device in the network system when the network device bears the objects corresponding to the first object information and the second object information.

[0154] In this step, a prediction result is generated based on the first object information, the device information, and the second object information by calling a preset performance model, so as to achieve, based on the device information of the network device, a prediction of the device performance indicators that the network device will consume when a new object for consuming device performance indicators is added to the network device, thereby ensuring the accuracy of the prediction result and improving the efficiency of generating the prediction result. The prediction result represents the device performance indicators consumed by the network device when the functions corresponding to the first function information and the second function information are turned on. The device performance indicators consumed by the network device include: one or more of: CPU usage, RAM usage, and network broadband utilization. A prediction result is generated based on the first object information, the device information, and the second object information by calling a preset performance model, so as to achieve, based on the device information of the network device, a prediction of the device performance indicators consumed by the network device when the network device turns on the function corresponding to the first function information, thereby ensuring the accuracy of the prediction result and improving the efficiency of generating the prediction result.

[0155] In one embodiment, calling a preset performance model to generate a prediction result based on the first object information, the device information, and the second object information includes:

[0156] Invoking a preset performance model to generate a target function range based on the first function information, the second function information, and the operating information in the device information; wherein the target function range refers to the upper and lower limits of the device performance indicator that can be consumed by a terminal connected to the network device in the network system when the network device activates the functions of the first function information and the second function information;

[0157] The prediction result of the first function information is determined based on the terminal access configuration information and the target function interval in the device information; the prediction result of the first function information represents the network device in the network system, and the device performance indicators consumed by the network device when the functions of the first function information and the second function information are enabled.

[0158] Therefore, the performance model is used to generate a target functional range based on the first functional information, the second functional information and the operating information in the device information, so as to achieve the technical effect of multi-angle analysis to determine the upper and lower limits of the device performance indicators that can be consumed by a terminal connected to the network device, thereby ensuring the accuracy of the target functional range; by determining the prediction results based on the terminal access configuration information and the target functional range, while ensuring the accuracy of the target functional range, the prediction results are determined in a targeted manner based on the device information of different network devices, thereby ensuring the accuracy of the prediction results.

[0159] Furthermore, the network system includes a cloud and at least one network device;

[0160] The preset performance model is called to generate a target function range according to the first function information, the operation information in the device information, and the second function information, including:

[0161] The cloud enters the first function information, the operation information in the first device information, and the second function information into a preset performance analysis interface; wherein the first device information refers to device information of a first network device; the first network device is a network device among the at least one network device that receives the first function information sent by the terminal;

[0162] The cloud calls the performance model through the performance analysis interface, so that the performance model generates a target function range according to the first function information, the second function information and the operation information in the device information.

[0163] In this step, the first function information, the second function information and the operating information in the first device information are entered into a preset performance analysis interface through the cloud, and the performance model is called through the performance analysis interface. The performance model is called by the cloud using an interface based on the first function information, thereby clarifying the functions provided by the network device, reducing the coupling between other functions in the cloud and the performance model, and facilitating frequent training and maintenance of the performance model.

[0164] Further, determining a prediction result of the first function information according to the terminal access configuration information and the target function interval in the device information includes:

[0165] The cloud multiplies the terminal access configuration information in the first device information by the upper limit and lower limit of the target functional range, respectively, to obtain a predicted upper limit value and a predicted lower limit value; wherein the first device information refers to the device information of the first network device;

[0166] The cloud constructs a numerical range based on the predicted upper limit and the predicted lower limit, and uses the numerical range as the prediction result.

[0167] In this step, the cloud multiplies the terminal access configuration information in the first device information with the upper limit value and the lower limit value in the target function interval respectively to obtain the predicted upper limit value and the predicted lower limit value, and constructs a numerical interval based on the predicted upper limit value and the predicted lower limit value, and uses the numerical interval as a prediction result. It realizes the target function interval of the performance indicators that may be consumed by the terminal when the network device is connected to the terminal based on the terminal access configuration information of the network device, and the target function interval of the performance indicators that may be consumed by the terminal when the network device is connected to the terminal, and specifically judges the interval of the performance indicators that may be consumed by the network device once all terminals turn on the function of the first function information, thereby greatly ensuring the reliability of the prediction result.

[0168] Exemplarily, the configuration management unit sends the first function information, terminal access configuration information, operation information and the second function information to the performance analysis interface of the cloud. The cloud calls the performance model in the model library by calling the performance analysis interface to calculate the target function range based on the first function information, the second function information and the operation information in the device information.

[0169] This target function range represents the device performance metrics that will be consumed by a network device when the first function information is enabled, based on the function corresponding to the second function information. For example, when a user prepares to change functions, the change is necessarily from Fa to Fb. At this time, by obtaining the maximum number of terminals K on this network device, we can calculate Fa[Pn,Pm]*K->Fb[Pn,Pm]*K, and Fb[Pn,Pm]*K is the predicted range of required device performance consumption. Fa represents function scenario a (function combination a), and Fb represents function scenario b (function combination b). Assume that function scenario a corresponding to Fa is function A enabled, and function scenario b corresponding to Fb is both functions A and B enabled. Fa[Pn,Pm] is the functional performance range when the network device enables function A, and Fb[Pn,Pm] is the target functional range when the network device enables functions A and B. Fa[Pn,Pm]*K is the current performance consumption range of the network device, and Fb[Pn,Pm]*K is the predicted range of the required device performance consumption. Therefore, Fb[Pn,Pm]*K is the predicted result.

[0170] In another embodiment, calling a preset performance model to generate a prediction result based on the first object information, the device information, and the second object information includes:

[0171] Call a preset performance model to generate a target capacity interval based on the first capacity information, the second capacity information and the activation information in the device information, and use the target capacity interval as the prediction result of the first capacity information; wherein, the target capacity interval refers to the upper and lower limits of the device performance indicators consumed by the network device in the network system when the network device is connected to the sum of the first and second numbers of terminals; the first number is the number of terminals corresponding to the first capacity information; the second number is the number of terminals corresponding to the second capacity information.

[0172] This is to achieve prediction of device performance indicators consumed by the network device when the number of terminals corresponding to the first capacity information newly connected to the network device is predicted based on the device information of the network device, thereby ensuring the accuracy of the prediction result and improving the generation efficiency of the prediction result.

[0173] Therefore, the target capacity interval is generated by the performance model based on the first capacity information, the operating information in the device information, and the second capacity information, so as to achieve the technical effect of multi-angle analysis to determine the upper and lower limits of the device performance indicators that can be consumed by a terminal connected to the network device, thereby ensuring the accuracy of the target capacity interval; by determining the prediction results based on the terminal access configuration information and the target capacity interval, while ensuring the accuracy of the target capacity interval, the prediction results are determined in a targeted manner based on the device information of different network devices, thereby ensuring the accuracy of the prediction results.

[0174] Specifically, after calling a preset performance model to generate a prediction result according to the first object information, the device information, and the second object information, the method further includes:

[0175] Send the prediction results to the terminal.

[0176] In this step, the prediction result is sent to the terminal so that the terminal can obtain the prediction result in time. Since the prediction result is generated based on the current device information of the network device, the content of the prediction result will greatly fit the current operating status of the network device, that is: according to the different configurations of each network device, the different device performance indicators, and the different currently enabled functions, it is determined what impact the newly enabled function or newly connected terminals will have on the network device; the accuracy of the prediction is greatly improved. Therefore, the embodiment of the present application is not only applicable to the application scenario of changing the functions enabled in the network device, but also applicable to the application scenario of increasing the number of terminals connected to the network device without expanding the bandwidth of the network device, which greatly improves the scope of application.

[0177] Exemplarily, the cloud sends the prediction result to the configuration management unit of the network device, and the configuration management unit sends the prediction result to the terminal.

[0178] Referring to FIG3 , the present application provides a device performance consumption prediction method, which is applied to a network system and includes:

[0179] S301: Collect historical performance data of each type of operation information under a functional scenario; wherein the functional scenario represents the enabled functions of the network equipment in the network system; the operation information represents the number of terminals connected to the network equipment in the network system; and the historical performance data represents the performance indicators of the equipment being consumed by the network system under a type of operation information in the functional scenario.

[0180] Optionally, historical performance data of each type of operation information under a functional scenario is collected; wherein, the functional scenario represents the enabled functions of the network equipment in the network system and the traffic of the network equipment; the operation information represents the number of terminals connected to the network equipment in the network system and the traffic of the network equipment in the network system; the historical performance data represents the performance indicators of the equipment being consumed in the network system under a type of operation information in the functional scenario.

[0181] Exemplarily, from the functional dimension, different functional combinations are obtained as different functional scenarios; for example: there are n (n is about 4 to 5) major functions that usually affect performance in network equipment. The total number is 2 to the power of n. Assuming n is 4 or 5, the total number of functional combinations is 15 to 31 (the case where the number of functional combinations is zero is not considered). Assuming n is 4, the functions of the network device include: A, B, C, D; then, the functional combinations include: A, B, C, D, AB, CD, AC, AD, BC, BD, ABC, BCD, ACD, ABD, ABCD; among them, the functional combination of none (that is, the network device does not enable any function) is not considered this time.

[0182] An operation information represents the network device of the network system, when the number of connected terminals is M and the traffic of the network device is N, where M is a positive integer and N is a positive rational number;

[0183] Therefore, assuming that the functional scenario is AB, that is, function A and function B are enabled at the same time; a historical performance data representation of the operating information under this functional scenario is the device performance indicators consumed by the network device when the number of terminals connected to the network device is Ma and the traffic is Na, such as one or more of the CPU usage Ca, RAM usage Ra, and network bandwidth utilization Wa; where a∈[1, S], S is the total number of functional scenarios.

[0184] In an exemplary embodiment, the terminal access configuration information, activation information and functional scenarios of the network device are collected through the information collection unit; the terminal access configuration information is obtained from the configuration management of the network device through the information collection unit; the number of terminals currently connected to the network device, the traffic of the network device, the second function information of the network device, and the device performance indicators of the network device (for example: one or more of CPU usage, RAM usage, and network bandwidth utilization) are collected from the data plane service of the network device through the information collection unit.

[0185] The information collection unit sends the historical performance data, functional scenarios and functional scenarios to the information collection unit in the cloud, and the information collection unit saves the historical performance data, functional scenarios and functional scenarios in the information database in the cloud.

[0186] S302: Obtain a functional performance range of the functional scenario based on at least one historical performance data corresponding to the functional scenario; wherein the functional performance range represents the upper limit and lower limit of the device performance indicator that a terminal can consume of the network device in a functional scenario.

[0187] In this step, the functional performance range includes the device performance indicators that a terminal can consume in multiple functional scenarios when one or more functions are turned on. Therefore, the functional performance range covers the device performance indicators that a terminal may consume under various operating information, ensuring the comprehensiveness of the device performance indicator prediction.

[0188] For example, assuming that the functional scenario is AB, then the AB scenario in multiple functional scenarios (such as S scenarios) will be obtained, that is: when the number of terminals connected to the network device is M (1-S) and the traffic is N (1-S), the CPU utilization rate C (from the 1st to the Sth), the RAM utilization rate R (1-S), and the network broadband utilization rate W (1-S).

[0189] In one embodiment, obtaining a functional performance range of a functional scenario based on at least one historical performance data corresponding to the functional scenario includes:

[0190] Obtaining at least one unit performance data under the target function scenario based on at least one historical performance data under the target function scenario; wherein the unit performance data represents a device performance indicator consumed by a terminal under the target function scenario;

[0191] Performing a regression operation on each unit performance data under the target functional scenario to obtain a regression curve of the target functional scenario; wherein the regression curve represents the probability of occurrence of each category of unit performance data in the target functional scenario; the category represents the numerical range within which the value of the unit performance data lies; and the target functional scenario is one of the at least one functional scenario;

[0192] The preset regression interval is entered into the regression curve to obtain the functional performance interval of the target functional scenario; wherein the regression interval is used to determine the target range of the category extracted from the regression curve; the target range determines at least one target category in the regression curve; the functional performance interval is used to cover the unit performance data in at least one target category; the upper limit of the functional performance interval is the first value of the unit performance data in at least one target category; the lower limit of the functional performance interval is the second value of the unit performance data in at least one target category; in this embodiment, the first value is the maximum value of the unit performance data in at least one target category; the second value is the minimum value of the unit performance data in at least one target category.

[0193] Therefore, a regression curve is obtained by performing a regression operation on each unit performance data, and the functional performance interval in the regression curve is determined based on the regression interval, wherein the regression interval defines the difference degree interval, that is, the upper and lower limits of the unit performance data in the N% range in the regression curve. For example, what are the upper and lower limits of the unit performance data in the regression curve with an exposure probability of 90% (that is, in most of the range of the curve), and the functional performance interval is constructed based on the upper and lower limits.

[0194] Exemplarily, the regression curve is determined to be a normal distribution curve, and the regression interval (for example, 3σ range) of the performance loss of a single terminal under different function combinations is calculated. By obtaining the number of terminals during the peak period of the network, it is multiplied by the corresponding 3σ range according to the combination of functions. This is to predict the basically reliable performance data in the network. Among them, μ represents the average value of all unit performance data, σ represents the standard deviation of all unit performance data, and the normal distribution curve represents the probability of occurrence of each unit performance data. (μ-m×σ,μ+m×σ) is used to characterize the regression interval, where m is the adjustment coefficient. By adjusting m, regression intervals with different upper and lower thresholds will be obtained. The obtained regression interval will represent the ratio of the area covered by the normal distribution curve within m standard deviations centered on the average value μ to the total area under the normal distribution curve. For example, if the value of m is 1, we get (μ-σ, μ+σ), which represents the ratio of the area covered by the normal distribution curve within 1 standard deviation centered on the mean value μ to the total area under the normal distribution curve. Based on the standard normal distribution curve, we get [15.9%, 84.1%], that is, 68.2% of the normal distribution curve range is obtained with the mean value μ as the center.

[0195] Suppose there are six unit performance data points: Data a: value 1, Data 2: value 2, Data 3: value 3, Data 4: value 2, Data 5: value 1, and Data 6: value 1. Then, the probability of a value of 1 is 50%; the probability of a value of 2 is 33%; and the probability of a value of 3 is 17%. If the adjustment coefficient is 1, the resulting regression interval is 68.2%, expressed as [15.9%, 84.1%], with an upper threshold of 15.9% and a lower threshold of 84.1%. Entering the regression interval into the regression curve will represent the values ​​of the unit performance data that appear within the 68.2% probability range of the regression interval, resulting in the values ​​1 and 2. Consequently, the upper limit of the functional performance interval is 2, and the lower limit is 1. As for why a value of 3 was not used, it is because a value of 3 is a low-probability event and has no reference value. Therefore, the above regression interval can eliminate such low-probability values.

[0196] Specifically, the device performance indicator consumption (i.e., unit performance data) of a terminal under a function combination is calculated. For example, based on the number of terminals connected to the network device, the CPU utilization of the device's current data plane (consumed device performance indicator), and the enabled function combination sent to the cloud (for example, function A and function B, not only during peak periods, but also during off-peak periods as a reference), the data received by the cloud can roughly calculate the performance consumption of a single terminal in this network environment as P1. The cloud performs statistics based on a large amount of data (greater than 10,000). At this time, the cloud can obtain more than 10,000 data samples, P1, P2...Pn. These data samples must be discrete, but from a statistical point of view, they must conform to the normal distribution law. Therefore, the regression curve is a normal distribution curve, as shown in Figure 4, where the normal distribution curve represents a functional scenario (functional combination, for example: AB), the vertical axis of the normal distribution represents the value of the unit performance data; the horizontal axis represents the functional scenario corresponding to each unit performance data; illustratively, according to the above distance, the adjustment coefficient m is set to 3, that is: the upper threshold is set to (μ+3σ), and the lower threshold is set to (μ-3σ). The probability that the value is distributed within +-3σ is 99.74%, and the regression interval is obtained. The threshold interval (μ-3σ, μ+3σ) corresponding to the regression interval is substituted into the above normal distribution curve to calculate the performance fluctuation interval [Pn, Pm] of the functional scenario (the functions enabled by the network device are function A and function B).

[0197] Each functional scenario has its corresponding Fx[Pn,Pm], where x is any one of y functional scenarios and y is the total number of functional scenarios. This allows us to build a similar terminal with a performance range (3σ) under a functional combination, and this value can cover most scenarios.

[0198] When a user prepares to change functions, for example, switching from enabling function A (its corresponding function scenario Fa) to enabling functions A and B (its corresponding function scenario Fb), at this time, by obtaining the maximum number of terminals K on this network device, Fa[Pn,Pm]*K->Fb[Pn,Pm]*K can be calculated, where Fa[Pn,Pm]*K is the current performance consumption range of the network device, and Fb[Pn,Pm]*K is the required device performance consumption prediction range.

[0199] S303: Using at least one functional scenario as input data and functional performance intervals corresponding to the at least one functional scenario as output data, a preset initial model is trained to obtain a performance model.

[0200] In this step, a neural network or support vector machine is used as the initial model. Neural networks are a subset of machine learning and are also the core of deep learning algorithms. Their name and structure are inspired by the human brain and can imitate the way biological neurons transmit signals to each other. Artificial neural networks (ANN, full name Artificial Neural Network) are composed of node layers, including an input layer, one or more hidden layers, and an output layer. Each node is also called an artificial neuron, which is connected to another node and has an associated weight and threshold. If the output of any individual node is above a specified threshold, the node is activated and the data is sent to the next layer of the network. Otherwise, the data will not be passed to the next layer of the network. Neural networks rely on training data to learn and improve their accuracy over time.

[0201] Support Vector Machine (SVM) is a machine learning algorithm used to solve binary classification problems. It separates samples of different categories by finding a partitioning hyperplane in the sample space, while maximizing the minimum distance between two point sets and this plane and maximizing the distance between the edge points of the two point sets and this plane.

[0202] Therefore, by collecting historical performance data for various operational information in various functional scenarios and using it to train the initial model and generate a performance model, comprehensive performance model training is ensured. For example, a cloud-based data analysis unit extracts historical performance data for each type of operational information in a functional scenario from the information database. The data analysis unit calculates and processes at least one historical performance data point for each type of operational information to generate a performance model, which is then stored in a cloud-based model library.

[0203] S304: Obtain first object information, and obtain device information and second object information; wherein, the first object information represents the object of the network device in the network system that is ready to consume the device performance indicator; device information and second object information; the device information represents the operation status of the network device in the network system; the second object information represents the object of the network device in the network system that is consuming the performance indicator.

[0204] This step is consistent with S201 in Example 1, so it will not be described here in detail.

[0205] S305: Calling a preset performance model to generate a prediction result based on the first object information, the device information, and the second object information; wherein the prediction result represents the device performance index consumed by the network device in the network system when the network device bears the objects corresponding to the first object information and the second object information.

[0206] This step is consistent with S202 in Example 1, so it will not be described here in detail.

[0207] S306: Compare the performance configuration information in the device information with the prediction result; wherein the performance configuration information represents the maximum performance that can be lost by the network device.

[0208] For example, if the performance configuration information includes: a CPU usage limit (eg, 98%), a RAM usage limit (eg, 90%), and a network bandwidth usage limit (eg, 95%).

[0209] S307: If it is determined that the prediction result exceeds the performance configuration information, a function warning message is generated and sent to the terminal.

[0210] For example, if the prediction result indicates that if the new function B is enabled on the network device, the device performance indicator that the network device will consume is that the CPU usage rate reaches 80%-99%. Then, it is determined that the prediction result exceeds the performance configuration information by 98%, so an early warning message needs to be generated and sent to the terminal.

[0211] Therefore, by comparing the performance configuration information with the prediction results and generating function warning information, the technical effect of timely feedback function activation alarm is achieved.

[0212] Specifically, if it is determined that the prediction result exceeds the performance configuration information, a functional warning message is generated, including:

[0213] If it is determined that any device performance indicator in the prediction result exceeds the performance configuration information corresponding to the device performance indicator, a function warning information is generated. For example, if the performance configuration information includes a CPU usage limit (for example: 98%), a RAM usage limit (for example: 90%), and a network bandwidth utilization limit (for example: 95%). If the CPU usage in the prediction result reaches 80%-99%, then it is determined that the prediction result exceeds the CPU usage limit of 98% in the performance configuration information.

[0214] Please refer to Figure 5. The present application provides a device performance consumption prediction method, which is applied in a network system and includes the following steps.

[0215] S501: Collect historical performance data for each type of activation information under a capacity scenario; wherein the capacity scenario represents the number of terminals connected to a network device in a network system; the activation information represents the functions enabled by the network device in the network system; and the historical performance data represents the device performance indicators being consumed by the network device in a type of activation information under the capacity scenario;

[0216] Optionally, historical performance data of each type of activation information under a capacity scenario is collected; wherein the capacity scenario represents the number of terminals connected to the network device in the network system; the activation information represents the enabled functions of the network device in the network system and the traffic of the network device; and the historical performance data represents the device performance indicators being consumed by the network device in a type of activation information under the capacity scenario;

[0217] Exemplarily, from the aspect of the number of terminals connected to the network device, capacity scenarios with different numbers of terminals are obtained; for example, a scenario with 100 terminals, a scenario with 200 terminals, and so on. Therefore, assuming that the capacity scenario is 1000, that is, the number of connected terminals is 1000; the historical performance data representation of a functional scenario under the capacity scenario represents the device performance indicators of the network device under a functional scenario (for example, turning on function A and function B) when the network device is connected to 1000 terminals. For example, each type of activation information under a capacity scenario is collected, assuming that the functions include function A and function B. Then the various activation information includes: function A, function B, function A+B; and what is obtained is the historical performance data of turning on function A, the historical performance data of turning on function B, and the historical performance data of turning on function A and function B when the number of connected terminals is 1000.

[0218] S502: Obtain a capacity performance range of a capacity scenario based on at least one historical performance data; wherein the capacity performance range represents an upper limit and a lower limit of a device performance indicator consumed by a network device in the capacity scenario.

[0219] In this step, the capacity-performance interval encompasses the device performance metrics consumed by the network device under different functional scenarios within a capacity scenario. Specifically, when the number of connected terminals is 1000, the device performance metrics consumed when function A is enabled, the device performance metrics consumed when functions A and B are enabled, and so on. In other words, based on the historical performance data above, the capacity-performance interval for the network device is determined when the number of connected terminals is 1000. Assuming that function A has the lowest performance consumption, the lower limit of the interval is the minimum performance consumption when function A is enabled, and the upper limit is the maximum performance consumption when functions A + B are enabled. The goal is to ensure that if new terminals are added, bringing the number of connected network devices to 1000, the network device's performance will not exceed the threshold, regardless of the subsequent functions enabled. A regression operation is performed on the historical performance data for each functional scenario to generate a regression curve for the capacity scenario. The preset regression interval is entered into the regression curve to generate the capacity-performance interval. The regression interval includes an upper threshold and a lower threshold. The upper threshold represents the upper limit of the degree of difference between at least one historical performance data point, while the lower threshold represents the lower limit of the degree of difference between at least one historical performance data point.

[0220] For example, in a capacity scenario with 1,000 terminals, different device performance indicators will appear when different functions are enabled. Each device performance indicator will conform to a normal distribution curve. For example, according to the 3σ principle, the upper threshold is set to (μ + 3σ) and the lower threshold is set to (μ - 3σ). The probability that the values ​​are distributed within +-3σ is 99.74%, resulting in a regression interval, where μ is the mean of each unit performance data and σ is the standard deviation of each performance data. The 3σ principle states that the probability that a value is distributed within (μ - 3σ, μ + 3σ) is 0.9974. In a normal distribution, σ represents the standard deviation and μ represents the mean. x = μ is the axis of symmetry of the image. The 3σ principle, also known as the Laida criterion, assumes that a set of test data contains only random errors. The standard deviation is calculated and then a range is determined based on a certain probability. Errors exceeding this range are considered non-random errors but rather gross errors, and data containing such errors should be eliminated. The 3σ principle is applicable when there are multiple sets of data.

[0221] Optionally, the historical performance data has a time period, which represents the time of the historical performance data. Assuming a functional scenario, that is, the enabled functions are function A and function B, the capacity performance interval of the capacity scenario obtained based on at least one historical performance data includes at least one time capacity performance interval, for example: the time period includes: 0:00-12:00, 12:00-24:00; then, the time capacity performance interval of 0:00-12:00 will be obtained, which represents the device performance index consumed by the network device when it is connected to 1,000 terminals and function A and function B are enabled; and the time capacity performance interval of 12:00-24:00 will be obtained, which represents the device performance index consumed by the network device when it is connected to 1,000 terminals and function A and function B are enabled.

[0222] S503: Using at least one capacity scenario as input data and the capacity performance intervals corresponding to the at least one capacity scenario as output data, a preset initial model is trained to obtain a performance model.

[0223] In this step, a neural network or support vector machine is used as the initial model. Neural networks are a subset of machine learning and are also the core of deep learning algorithms. Their name and structure are inspired by the human brain and mimic the way biological neurons transmit signals to each other. Artificial neural networks (ANNs) are composed of layers of nodes, including an input layer, one or more hidden layers, and an output layer. Each node, also called an artificial neuron, is connected to another node and has an associated weight and threshold. If the output of any individual node is above a specified threshold, the node is activated and the data is sent to the next layer of the network. Otherwise, the data is not passed to the next layer of the network. Neural networks rely on training data to learn and improve their accuracy over time.

[0224] Support Vector Machine (SVM) is a machine learning algorithm used to solve binary classification problems. It separates samples of different categories by finding a dividing hyperplane in the sample space, while maximizing the minimum distance between two point sets and this plane and maximizing the distance between the edge points of the two point sets and this plane.

[0225] Therefore, by collecting historical performance data of various functional scenarios under various capacity scenarios, the initial model is trained to obtain a performance model, ensuring the comprehensiveness of the performance model training.

[0226] S504: Obtain first object information, and obtain device information and second object information; wherein, the first object information represents the object of the network device in the network system that is ready to consume the device performance indicator; device information and second object information; the device information represents the operation status of the network device in the network system; the second object information represents the object of the network device in the network system that is consuming the performance indicator.

[0227] This step is consistent with S201 in Example 1, so it will not be described here in detail.

[0228] S505: Calling a preset performance model to generate a prediction result based on the first object information, the device information, and the second object information; wherein the prediction result represents the device performance index consumed by the network device in the network system when running the object corresponding to the first object information and the second object information.

[0229] This step is consistent with S202 in Example 1, so it will not be described here in detail.

[0230] S506: Compare the performance configuration information in the device information with the prediction result; wherein, the performance configuration information in the device information is compared with the prediction result; wherein, the performance configuration information represents the device performance indicator threshold that can be consumed by the network device.

[0231] In this embodiment, the device performance indicator threshold may be a device performance indicator representing the maximum loss that the network device can sustain.

[0232] For example, if the performance configuration information includes: a CPU usage limit (eg, 98%), a RAM usage limit (eg, 90%), and a network bandwidth usage limit (eg, 95%).

[0233] S507: If it is determined that the prediction result exceeds the performance configuration information, a function warning message is generated and sent to the terminal.

[0234] For example, if the prediction result indicates that if the new function B is enabled on the network device, the device performance indicator that the network device will consume is that the CPU usage rate reaches 80%-99%. Then, it is determined that the prediction result exceeds the performance configuration information by 98%, so an early warning message needs to be generated and sent to the terminal.

[0235] Therefore, by comparing the performance configuration information with the prediction results and generating function warning information, the technical effect of timely feedback function activation alarm is achieved.

[0236] Referring to FIG. 6 , an embodiment of the present application provides a device performance consumption prediction apparatus 6 installed in a network system, including:

[0237] Input module 64 is configured to obtain first object information, device information, and second object information; wherein the first object information represents an object in the network system for which a network device is about to consume a device performance indicator; the device information represents an operating status of a network device in the network system; and the second object information represents an object in the network system for which a network device is currently consuming a performance indicator;

[0238] Processing module 65 is used to call a preset performance model to generate a prediction result based on the first object information, device information and second object information; wherein the prediction result represents the device performance indicators consumed by the network device in the network system when the network device bears the objects corresponding to the first object information and the second object information.

[0239] Optionally, the first object information includes first function information, and the second object information includes second function information;

[0240] Input module 64 is further configured to receive first function information sent by the terminal and obtain device information and second function information. The first function information indicates the function to be enabled by the terminal. The device information includes terminal access configuration information and operational information. The terminal access configuration information indicates the threshold number of terminals that can be connected to the network device, and the operational information includes the number of terminals connected to the network device. The second function information indicates the enabled function of the network device in the network system. In this embodiment, the threshold number is the maximum number of terminals that can be connected to the network device.

[0241] The processing module 65 is further configured to call a preset performance model to generate a target function range based on the first function information, the second function information, and the operating information in the device information; wherein the target function range refers to the upper and lower limits of the device performance indicator that can be consumed by a terminal connected to the network device in the network system when the network device activates the functions of the first function information and the second function information;

[0242] The processing module 65 is further configured to determine a prediction result of the first function information according to the terminal access configuration information and the target function interval in the device information.

[0243] Optionally, the network system includes a cloud and at least one network device; the processing module 65 is provided in the cloud;

[0244] The processing module 65 in the cloud is configured to input the first function information, the second function information, and the operating information in the first device information into a preset performance analysis interface; wherein the first device information refers to device information of a first network device; the first network device is a network device among the at least one network device that receives the first function information sent by the terminal;

[0245] The processing module 65 in the cloud is used to call the performance model through the performance analysis interface, so that the performance model generates a target function range according to the first function information, the operation information in the first device information, and the second function information.

[0246] Optionally, the processing module 65 in the cloud is configured to multiply the terminal access configuration information in the first device information by the upper limit value and the lower limit value in the target functional range, respectively, to obtain a predicted upper limit value and a predicted lower limit value;

[0247] The processing module 65 in the cloud is used to construct a numerical range according to the prediction upper limit value and the prediction lower limit value, and use the numerical range as the prediction result.

[0248] Optionally, the first object information includes first capacity information, and the second object information includes second capacity information;

[0249] The input module 64 is also used to receive the first capacity information sent by the terminal and obtain the device information and the second capacity information; wherein the first capacity information represents the number of terminals that the network device in the network system is ready to add; the device information includes activation information; the activation information represents the enabled function of the network device in the network system; the second capacity information represents the number of terminals connected to the network device in the network system.

[0250] Optionally, the processing module 65 is also used to call a preset performance model to call the preset performance model to generate a target capacity interval based on the first capacity information, the second capacity information and the activation information in the device information, and use the target capacity interval as the prediction result of the first capacity information; wherein, the target capacity interval refers to the upper and lower limits of the device performance indicators consumed by the network device in the network system when the network device is connected to the sum of the first and second numbers of terminals; the first number is the number of terminals corresponding to the first capacity information; the second number is the number of terminals corresponding to the second capacity information.

[0251] Optionally, the device 6 further includes: a function collection module 611, configured to collect historical performance data of each type of operation information under a function scenario; wherein the function scenario represents an enabled function of a network device in the network system; the operation information represents the number of terminals connected to the network device in the network system; and the historical performance data represents a performance indicator of a device being consumed under a type of operation information in the network system in the function scenario;

[0252] The functional performance interval module 612 is configured to obtain a functional performance interval for a functional scenario based on at least one historical performance data corresponding to the functional scenario; wherein the functional performance interval represents the upper and lower limits of the device performance indicator that a terminal can consume of the network device in a functional scenario;

[0253] The function model training module 613 is used to take at least one function scenario as input data and the function performance intervals corresponding to the at least one function scenario as output data, to train a preset initial model and obtain a performance model.

[0254] Optionally, the device 6 further includes:

[0255] The function performance interval module 612 is further configured to obtain at least one unit performance data under the target function scenario based on at least one historical performance data under the target function scenario; wherein the unit performance data represents a device performance indicator consumed by a terminal under the target function scenario;

[0256] The functional performance interval module 612 is further configured to perform a regression operation on each unit performance data in the target functional scenario to obtain a regression curve for the target functional scenario; wherein the regression curve represents the probability of occurrence of each category of unit performance data in the target functional scenario; the category represents the numerical interval within which the value of the unit performance data lies; and the target functional scenario is one of the at least one functional scenario.

[0257] The functional performance interval module 612 is also used to enter the preset regression interval into the regression curve to obtain the functional performance interval of the target functional scenario; wherein the regression interval is used to determine the target range of the category extracted from the regression curve; the target range determines at least one target category in the regression curve; the functional performance interval is used to cover the unit performance data in at least one target category; the upper limit of the functional performance interval is the first value of the unit performance data in at least one target category; the lower limit of the functional performance interval is the second value of the unit performance data in at least one target category.

[0258] Optionally, the device 6 further includes: a capacity collection module 621, configured to collect historical performance data of each type of activation information under a capacity scenario; wherein the capacity scenario represents the number of terminals connected to the network device in the network system; the activation information represents the functions enabled by the network device in the network system; and the historical performance data represents the device performance indicator being consumed by the network device in a type of activation information under the capacity scenario;

[0259] The capacity performance interval module 622 is configured to obtain a capacity performance interval for a capacity scenario based on at least one historical performance data; wherein the capacity performance interval represents an upper limit and a lower limit of a device performance indicator consumed by the network device in the capacity scenario;

[0260] The capacity model training module 623 is configured to take at least one capacity scenario as input data and capacity performance intervals corresponding to the at least one capacity scenario as output data, train a preset initial model, and obtain a performance model.

[0261] Optionally, the device 6 further includes:

[0262] A comparison module 66 is configured to compare the performance configuration information in the device information with the prediction result; wherein the performance configuration information represents the device performance indicator threshold that the network device can consume;

[0263] The warning module 67 is configured to generate functional warning information if it is determined that the prediction result exceeds the performance configuration information.

[0264] To achieve the above-mentioned purpose, the present application further provides a computer device 7, comprising: a processor 72 and a memory 71 in communication with the processor 72; the memory storing computer-executable instructions;

[0265] The processor executes the computer-executable instructions stored in the memory 71 to implement the above-mentioned device performance consumption prediction method, wherein the components of the device performance consumption prediction device can be dispersed in different computer devices. The computer device 7 can be a smartphone, tablet computer, laptop computer, desktop computer, rack server, blade server, tower server or cabinet server (including independent servers or server clusters composed of multiple application servers) that executes the program. The computer device of this embodiment includes at least but is not limited to: a memory 71 and a processor 72 that can be interconnected via a system bus, as shown in Figure 7. It should be noted that Figure 7 only shows a computer device with components -, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. In this embodiment, the memory 71 (i.e., readable storage medium) includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 71 may be an internal storage unit of the computer device, such as the computer device's hard drive or memory. In other embodiments, the memory 71 may also be an external storage device of the computer device, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped with the computer device. Of course, the memory 71 may also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the memory 71 is generally used to store the operating system and various application software installed on the computer device, such as the program code of the device performance consumption prediction device in Example 3. In addition, the memory 71 may also be used to temporarily store various types of data that have been output or are about to be output. In some embodiments, the processor 72 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 72 is generally used to control the overall operation of the computer device. In this embodiment, the processor 72 is used to execute the program code stored in the memory 71 or process data, such as executing the device performance consumption prediction device to implement the device performance consumption prediction method of the above embodiment.

[0266] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the methods of each embodiment of the present application. It should be understood that the above-mentioned processor can be a central processing unit (CPU, full name Central Processing Unit), or other general-purpose processors, digital signal processors (DSP, full name Digital Signal Processor), application-specific integrated circuits (ASIC, full name Application Specific Integrated Circuit), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the application can be directly embodied as being executed by a hardware processor, or being executed by a combination of hardware and software modules in the processor. The memory may include high-speed RAM memory, and may also include non-volatile storage NVM, such as at least one disk memory, and can also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0267] To achieve the above objectives, the present application also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, a server, an App application store, etc., on which computer execution instructions are stored, and the corresponding functions are realized when the program is executed by the processor 72. The computer-readable storage medium of this embodiment is used to store computer execution instructions for implementing the device performance consumption prediction method, and when executed by the processor 72, the device performance consumption prediction method of the above embodiment is realized.

[0268] The storage medium may be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0269] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an application-specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.

[0270] The present application provides a computer program product, including a computer program, which implements the above-mentioned device performance consumption prediction method when executed by a processor.

[0271] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0272] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0273] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A device performance consumption prediction method, applied to a network system, comprising: Acquire first object information, and acquire device information and second object information; wherein the first object information represents a first object of a network device in the network system that is ready to consume a device performance indicator; the device information represents an operation status of the network device in the network system; the second object information represents a second object of the network device in the network system that is consuming a performance indicator; and Call a preset performance model to generate a prediction result based on the first object information, the device information and the second object information; wherein the prediction result represents the device performance indicator that the network device in the network system needs to consume when bearing the first object and the second object.

2. The method according to claim 1, wherein: The first object information includes first function information, and the second object information includes second function information; The acquiring the first object information, and acquiring the device information and the second object information includes: Receive first function information sent by a terminal, and obtain the device information and the second function information; wherein the first function information represents the function that the terminal is ready to enable; the device information includes terminal access configuration information and operation information; the terminal access configuration information represents the threshold value of the number of terminals that the network device can access, and the operation information includes the number of terminals that the network device has been connected to; the second function information represents the enabled function of the network device in the network system.

3. The method according to claim 2, wherein: The calling the preset performance model to generate a prediction result according to the first object information, the device information and the second object information includes: calling the preset performance model to generate a target function interval according to the first function information, the second function information and the operation information in the device information; wherein the target function interval refers to the upper limit and lower limit of the device performance indicator that can be consumed by a terminal connected to the network device in the network system when the network device in the network system turns on the function of the first function information and the function of the second function information; and A prediction result of the first function information is determined according to the terminal access configuration information in the device information and the target function interval.

4. The method according to claim 3, wherein: The network system includes a cloud and at least one second network device; Calling the preset performance model to generate a target function interval according to the first function information, the second function information, and the operation information in the device information includes: The cloud enters the first function information, the second function information and the operation information in the first device information into a preset performance analysis interface; wherein the first device information refers to the device information of the first network device; the first network device is the network device among the at least one second network device that receives the first function information sent by the terminal; and The cloud calls the performance model through the performance analysis interface, so that the performance model generates a target function interval according to the first function information, the operation information in the first device information, and the second function information.

5. The method according to claim 3, wherein: The network system includes a cloud and at least one second network device; Determining a prediction result of the first function information according to the terminal access configuration information and the target function interval in the device information includes: The cloud multiplies the terminal access configuration information in the first device information by the upper limit and the lower limit in the target function interval, respectively, to obtain a predicted upper limit value and a predicted lower limit value; wherein the first device information refers to device information of a first network device; the first network device is a network device among the at least one second network device that receives the first object information sent by the terminal; and The cloud constructs a numerical range according to the prediction upper limit value and the prediction lower limit value, and uses the numerical range as the prediction result.

6. The method according to claim 1, wherein: The first object information includes first function information, the second object information includes second function information, The calling the preset performance model to generate a prediction result according to the first object information, the device information and the second object information includes: The preset performance model is called to generate a target function interval according to the first function information in the first object information, the second function information in the second object information, and the operation information in the device information; wherein the target function interval refers to the network device in the network system when the function of the first function information and the function of the second function information are turned on, and the network device The upper and lower limits of the device performance indicators that a connected terminal can consume; and A prediction result of the first function information is determined according to the terminal access configuration information in the device information and the target function interval.

7. The method according to claim 1, wherein: The first object information includes first capacity information, and the second object information includes second capacity information; The acquiring the first object information, and acquiring the device information and the second object information includes: Receive the first capacity information sent by the terminal, and obtain the device information and the second capacity information; wherein, the first capacity information represents the number of terminals that the network device in the network system is ready to add; the device information includes activation information; the activation information represents the enabled functions of the network device in the network system; the second capacity information represents the number of terminals connected to the network device in the network system.

8. The method according to claim 7, wherein: The calling of a preset performance model to generate a prediction result according to the first object information, the device information and the second object information includes: The preset performance model is called to generate a target capacity interval according to the first capacity information, the second capacity information and the activation information in the device information, and the target capacity interval is used as the prediction result of the first capacity information; wherein, the target capacity interval refers to the upper and lower limits of the device performance indicator consumed by the network device in the network system when the network device is connected to the sum of the first and second quantities of terminals; the first quantity is the number of terminals corresponding to the first capacity information; the second quantity is the number of terminals corresponding to the second capacity information.

9. The method according to claim 1, wherein: Before acquiring the first object information, and acquiring the device information and the second object information, the method further includes: Collect historical performance data of each type of operation information in a functional scenario; wherein the functional scenario represents the enabled functions of the network device in the network system; the operation information in the device information represents the number of terminals connected to the network device; the historical performance data represents the device performance indicators being consumed in the network system under a type of operation information in the functional scenario; Obtaining a functional performance interval of the functional scenario according to at least one historical performance data corresponding to the functional scenario; wherein the functional performance interval represents an upper limit and a lower limit of a device performance indicator that a terminal can consume a network device in a functional scenario; and At least one of the functional scenarios is used as input data, and the functional performance intervals corresponding to at least one of the functional scenarios are used as output data, and a preset initial model is trained to obtain the performance model.

10. The method according to claim 9, wherein: The obtaining, according to at least one historical performance data corresponding to the functional scenario, a functional performance range of the functional scenario includes: According to at least one historical performance data under the target function scenario, at least one unit performance data under the target function scenario is obtained; wherein the unit performance data represents a device performance indicator consumed by a terminal under the target function scenario; Performing a regression operation on each of the unit performance data under the target functional scenario to obtain a regression curve of the target functional scenario; wherein the regression curve represents the probability of occurrence of each category of unit performance data in the target functional scenario; the category represents the numerical interval in which the value of the unit performance data lies; the target functional scenario is one of at least one functional scenario; and Enter a preset regression interval into the regression curve to obtain a functional performance interval for the target functional scenario; wherein the regression interval is used to determine a target range for extracting the category in the regression curve; the target range determines at least one target category in the regression curve; the functional performance interval is used to cover unit performance data in at least one of the target categories; the upper limit of the functional performance interval is the first value in the unit performance data in the at least one target category; the lower limit of the functional performance interval is the second value in the unit performance data in the at least one target category.

11. The method according to claim 1, wherein: Before acquiring the first object information, and acquiring the device information and the second object information, the method further includes: Collecting historical performance data of each type of enabling information under a capacity scenario; wherein the capacity scenario represents the number of terminals connected to the network device in the network system; the enabling information represents the enabled functions of the network device in the network system; the historical performance data represents the device performance indicators being consumed in a type of enabling information of the network device under the capacity scenario; According to at least one of the historical performance data, a capacity performance interval of the capacity scenario is obtained; wherein the capacity performance interval represents an upper limit and a lower limit of a device performance indicator consumed by the network device under the capacity scenario; and At least one of the capacity scenarios is used as input data, and the capacity performance intervals corresponding to at least one of the capacity scenarios are used as output data, and a preset initial model is trained to obtain the performance model.

12. The method according to claim 1, wherein: After calling the preset performance model to generate a prediction result according to the first object information, the device information and the second object information, the method further includes: Comparing the performance configuration information in the device information with the prediction result; wherein the performance configuration information represents the device performance indicator threshold that the network device can consume; and If it is determined that the prediction result exceeds the performance configuration information, functional warning information is generated.

13. The method according to claim 1, wherein: The calling of a preset performance model to generate a prediction result according to the first object information, the device information and the second object information includes: The preset performance model is called to generate a target capacity interval according to the first capacity information in the first object information, the second capacity information in the second object information and the activation information in the device information, and the target capacity interval is used as the prediction result of the first capacity information; wherein, the target capacity interval refers to the upper and lower limits of the device performance indicator consumed by the network device in the network system when the network device is connected to the sum of the first and second numbers of terminals; the first number is the number of terminals corresponding to the first capacity information; the second number is the number of terminals corresponding to the second capacity information.

14. A device performance consumption prediction device, installed in a network system, comprising: An input module is configured to obtain first object information, and obtain device information and second object information; wherein the first object information represents a first object of a network device in the network system that is ready to consume a device performance indicator; the device information represents an operation status of the network device in the network system; the second object information represents a second object of a performance indicator that the network device in the network system is consuming; and The processing module is configured to call a preset performance model to generate a prediction result based on the first object information, the device information and the second object information; wherein the prediction result represents the device performance indicator that the network device in the network system needs to consume when bearing the first object and the second object.

15. A computer device comprising: A processor and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the device performance consumption prediction method as described in any one of claims 1 to 13.

16. A computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the device performance consumption prediction method according to any one of claims 1 to 13.

Images