CN112306808A - Performance monitoring and evaluating method and device, computer equipment and readable storage medium - Google Patents
Performance monitoring and evaluating method and device, computer equipment and readable storage medium Download PDFInfo
- Publication number
- CN112306808A CN112306808A CN202011208472.8A CN202011208472A CN112306808A CN 112306808 A CN112306808 A CN 112306808A CN 202011208472 A CN202011208472 A CN 202011208472A CN 112306808 A CN112306808 A CN 112306808A
- Authority
- CN
- China
- Prior art keywords
- performance
- mobile terminal
- data
- index
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3089—Monitoring arrangements determined by the means or processing involved in sensing the monitored data, e.g. interfaces, connectors, sensors, probes, agents
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention relates to the technical field of artificial intelligence, and discloses a performance monitoring and evaluating method, a performance monitoring and evaluating device, computer equipment and a readable storage medium, wherein the performance monitoring and evaluating method comprises the following steps: acquiring performance data of the mobile terminal according to the abnormal information sent by the mobile terminal; training an initial deep learning network to obtain a mature deep learning network through performance data and reference data; calculating adjustable data through the mature deep learning network to generate a test result, calculating a difference between the test result and a balance result to obtain a test loss value, adjusting the adjustable data according to the test loss value until the test result generated by the mature deep learning network is consistent with the balance result, and setting the adjustable data as a dynamic index; and monitoring the performance index of the mobile terminal, taking the performance index as a real-time index, and evaluating the real-time index according to the dynamic index to obtain an evaluation result. The invention can correctly reflect the performance indexes of the mobile terminal at the critical points of the normal state and the abnormal state, and ensures the reliability of the monitoring evaluation of the mobile terminal.
Description
Technical Field
The invention relates to the technical field of artificial intelligence intelligent decision making, in particular to a performance monitoring and evaluating method and device, computer equipment and a readable storage medium.
Background
With the popularization of the intelligent mobile terminal promoting the rapid development of mobile terminal apps, human activities can be basically completed through the mobile terminal apps at present, and the performance of the apps is worthy of attention.
The mobile terminal runs a large amount of apps every moment, so that the performance index of the mobile terminal needs to be monitored by a performance monitoring tool to avoid the mobile terminal from entering an abnormal state (such as the situations of blocking, crash, system crash and the like) due to the running of a large amount of apps; the current performance monitoring tool generally monitors various performance indexes of the mobile terminal and sends out an alarm by adopting a preset performance threshold value.
However, the inventor has recognized that, once the mobile terminal is used for a long time, performance of the mobile terminal may be degraded (for example, hardware may be aged, data stored in a hard disk is excessive, a large amount of APPs are downloaded, and the like), or when a user changes the mobile terminal, the preset performance threshold may no longer match with a performance index of the mobile terminal when the mobile terminal enters an abnormal state, which may cause that the mobile terminal may not be accurately alerted, resulting in low reliability of performance alerting.
Disclosure of Invention
The invention aims to provide a performance monitoring and evaluating method, a performance monitoring and evaluating device, computer equipment and a readable storage medium, which are used for solving the problem that after a mobile terminal is used for a long time in the prior art, a preset performance threshold value is not matched with a performance index of the mobile terminal when the mobile terminal enters an abnormal state any more, so that the mobile terminal cannot accurately send an alarm to the mobile terminal, and the reliability of the performance alarm is low.
In order to achieve the above object, the present invention provides a performance monitoring and evaluating method for monitoring and evaluating performance indexes of a mobile terminal, including:
acquiring performance data of a mobile terminal according to abnormal information sent by the mobile terminal, wherein the performance data reflects performance indexes of the mobile terminal in an abnormal state;
training a preset initial deep learning network to obtain a mature deep learning network through the performance data and preset reference data, wherein the reference data reflects performance indexes of the mobile terminal in a normal state;
calculating preset adjustable data through the mature deep learning network to generate a test result, calculating a difference between the test result and a preset balance result to obtain a test loss value, adjusting the adjustable data according to the test loss value until the test result generated by the mature deep learning network is consistent with the balance result, and setting the adjustable data as a dynamic index;
and monitoring the performance index of the mobile terminal, taking the performance index as a real-time index, evaluating the real-time index according to the dynamic index to obtain an evaluation result, and sending alarm information to the mobile terminal according to the evaluation result.
In the foregoing solution, before the obtaining the performance data of the mobile terminal according to the abnormal information sent by the mobile terminal, the method further includes:
and creating an uploading interface for monitoring abnormal information of the mobile terminal.
In the foregoing solution, before the obtaining the performance data of the mobile terminal according to the abnormal information sent by the mobile terminal, the method further includes:
sending a state request to a mobile terminal, and receiving state information sent by the mobile terminal according to the state request; judging whether the state information has an abnormal label or not; if yes, judging that the state information is abnormal information; if not, the process is ended.
In the foregoing solution, after the performance data of the mobile terminal is acquired according to the abnormal information sent by the mobile terminal, the method further includes:
acquiring user information of the mobile terminal, and associating and storing the performance data with the user information;
calling an abnormal database to summarize performance data belonging to the same user information to form a performance set, and deleting the performance data exceeding a preset time limit in the performance set;
calculating the quantity of performance data in a performance set in an abnormal database, and judging whether the quantity of the performance data reaches a preset training threshold value; if yes, extracting performance data in the performance set; if not, the process is ended.
In the above scheme, the step of training a preset initial deep learning network to obtain a mature deep learning network according to the performance data and preset reference data includes:
acquiring reference data;
constructing a neuron of an input layer in the initial deep learning network according to the subdata items in the benchmark data and the performance data; inputting data corresponding to each subdata item in the datum data into corresponding neurons in the input layer, and inputting data corresponding to each subdata item in the performance data into corresponding neurons in the input layer;
calling a hidden layer of the initial deep learning network, acquiring an input vector of the input layer, calculating the input vector to obtain an output vector, and outputting the output vector to an output layer of the initial deep learning network;
calculating an output vector of the output layer through a preset training loss function, and obtaining a training loss value according to a difference between the output vector and abnormal information corresponding to the performance data;
and adjusting the weight and the bias value of the hidden layer through a back propagation algorithm according to the training loss value until the training loss value is smaller than a preset training loss threshold value to obtain a mature deep learning network.
In the foregoing solution, after the setting the adjustable data as the dynamic index, the method further includes:
associating and storing the dynamic index and the user information of the mobile terminal;
after associating and storing the dynamic indicator with the user information of the mobile terminal, the method further includes:
and uploading the dynamic index and the user information to a block chain.
In the above solution, the step of monitoring a performance index of the mobile terminal and using the performance index as a real-time index, evaluating the real-time index according to the dynamic index to obtain an evaluation result, and sending alarm information to the mobile terminal according to the evaluation result includes:
monitoring a performance index of a mobile terminal as a real-time index, acquiring user information of the mobile terminal and extracting a dynamic index associated with the user information;
setting real-time indexes with values exceeding the dynamic indexes as abnormal indexes, and setting the number of the abnormal indexes as evaluation results; judging whether the evaluation result exceeds a preset abnormal threshold value or not;
if yes, sending alarm information to the mobile terminal;
if not, the process is ended.
In order to achieve the above object, the present invention further provides a performance monitoring and evaluating apparatus, including:
the system comprises an exception acquisition module, a performance data acquisition module and a performance data acquisition module, wherein the exception acquisition module is used for acquiring the performance data of a mobile terminal according to exception information sent by the mobile terminal, and the performance data reflects the performance index of the mobile terminal in an abnormal state;
the network training module is used for training a preset initial deep learning network to obtain a mature deep learning network through the performance data and preset reference data, wherein the reference data reflects the performance index of the mobile terminal in a normal state;
the dynamic adjusting module is used for calculating preset adjustable data through the mature deep learning network to generate a test result, calculating the difference between the test result and a preset balance result to obtain a test loss value, adjusting the adjustable data according to the test loss value until the test result generated by the mature deep learning network is consistent with the balance result, and setting the adjustable data as a dynamic index;
and the monitoring alarm module is used for monitoring the performance index of the mobile terminal and taking the performance index as a real-time index, evaluating the real-time index according to the dynamic index to obtain an evaluation result, and sending alarm information to the mobile terminal according to the evaluation result.
In order to achieve the above object, the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor of the computer device implements the steps of the performance monitoring and evaluating method when executing the computer program.
In order to achieve the above object, the present invention further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of the performance monitoring and evaluating method.
According to the performance monitoring and evaluating method, device, computer equipment and readable storage medium, the initial neural network is trained through the performance data of the mobile terminal in the normal state and the abnormal state, so that a mature deep learning network capable of accurately judging whether the mobile terminal is in the normal state or the abnormal state according to the performance index of the mobile terminal is obtained, and the mature deep learning network generates the dynamic index by adjusting the adjustable data.
Therefore, the mobile terminal is dynamically identified based on the mature deep learning network, and the adjustable data corresponding to the critical point between the normal state and the abnormal state is set as the dynamic index, so that the dynamic index can correctly reflect the performance index of the critical point between the normal state and the abnormal state of the mobile terminal no matter the mobile terminal is used for a long time to cause performance degradation of the mobile terminal or the mobile terminal is replaced, thereby realizing accurate sending of alarm information to the mobile terminal and ensuring the reliability of monitoring and evaluation of the mobile terminal.
Drawings
FIG. 1 is a flow chart of a first embodiment of a performance monitoring and evaluating method according to the present invention;
FIG. 2 is a schematic diagram of an environmental application of the performance monitoring and evaluating method according to a second embodiment of the performance monitoring and evaluating method of the present invention;
FIG. 3 is a flowchart of a specific method of a performance monitoring and evaluating method according to a second embodiment of the performance monitoring and evaluating method of the present invention;
FIG. 4 is a schematic diagram of program modules of a third embodiment of the performance monitoring and evaluating apparatus according to the present invention;
fig. 5 is a schematic diagram of a hardware structure of a computer device according to a fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a performance monitoring and evaluating method, a performance monitoring and evaluating device, computer equipment and a readable storage medium, which are suitable for the technical field of artificial intelligence intelligent decision making and provide a performance monitoring and evaluating method based on an abnormity acquisition module, a network training module, a dynamic regulation module and a monitoring and alarming module. The invention obtains the performance data of the mobile terminal according to the abnormal information sent by the mobile terminal; training an initial deep learning network to obtain a mature deep learning network through performance data and reference data; calculating adjustable data through the mature deep learning network to generate a test result, calculating a difference between the test result and a balance result to obtain a test loss value, adjusting the adjustable data according to the test loss value until the test result generated by the mature deep learning network is consistent with the balance result, and setting the adjustable data as a dynamic index; and monitoring the performance index of the mobile terminal, evaluating the performance index according to the dynamic index to obtain an evaluation result, and sending alarm information to the mobile terminal according to the evaluation result.
The first embodiment is as follows:
referring to fig. 1, a performance monitoring and evaluating method of the present embodiment is used for monitoring and evaluating a performance index of a mobile terminal, and includes:
s102: and acquiring performance data of the mobile terminal according to the abnormal information sent by the mobile terminal, wherein the performance data reflects the performance index of the mobile terminal in an abnormal state.
S106: and training a preset initial deep learning network to obtain a mature deep learning network through the performance data and preset reference data, wherein the reference data reflects the performance index of the mobile terminal in a normal state.
S107: and calculating preset adjustable data through the mature deep learning network to generate a test result, calculating a difference between the test result and a preset balance result to obtain a test loss value, adjusting the adjustable data according to the test loss value until the test result generated by the mature deep learning network is consistent with the balance result, and setting the adjustable data as a dynamic index.
S109: and monitoring the performance index of the mobile terminal, taking the performance index as a real-time index, evaluating the real-time index according to the dynamic index to obtain an evaluation result, and sending alarm information to the mobile terminal according to the evaluation result.
In this embodiment, the performance monitoring tool is a computer program for monitoring the performance of the mobile terminal to obtain the performance data of the mobile terminal in an abnormal state, and obtains the performance data of the mobile terminal and the user information of the mobile terminal.
The initial neural network is trained through the performance data and the reference data used for reflecting the performance index of the mobile terminal in the normal state, so that a mature deep learning network which can accurately judge whether the mobile terminal is in the normal state or the abnormal state according to the performance index of the mobile terminal is obtained, and the purpose of judging the normal state and the abnormal state of the mobile terminal based on an artificial intelligence technology is achieved. Inputting adjustable data into an input layer of the mature deep learning network, calling a hidden layer of the mature deep learning network to calculate the adjustable data of the input layer to obtain a test result, and outputting the test result to an output layer of the mature deep learning network; and obtaining a test loss value by a preset test loss function and calculating the difference between the test result and a preset equalization result, adjusting the adjustable data by adopting a gradient descent method according to the test loss value until the test result generated by the mature deep learning network through the adjustable data and the equalization result, and setting the adjustable data as a dynamic index. Therefore, once the performance index of the mobile terminal exceeds the dynamic index, the mobile terminal can be determined to be abnormal, the judgment efficiency of the abnormal state of the mobile terminal is greatly improved, the calculation power for monitoring the performance index of the mobile terminal and judging whether the mobile terminal is abnormal under the performance index is greatly reduced, and the technical effect of monitoring and judging the performance indexes of a large number of mobile terminals can be realized.
Meanwhile, the performance of the mobile terminal is degraded due to long-term use of the mobile terminal (for example, hardware aging, excessive data stored in a hard disk, downloading a large amount of APPs, and the like), or when the user changes the mobile terminal, the performance index of the mobile terminal entering an abnormal state will change accordingly. Therefore, the mobile terminal is dynamically identified based on the mature deep learning network, and the adjustable data corresponding to the critical point between the normal state and the abnormal state is set as the dynamic index, so that the dynamic index can correctly reflect the performance index of the critical point between the normal state and the abnormal state of the mobile terminal no matter the mobile terminal is used for a long time to cause performance degradation of the mobile terminal or the mobile terminal is replaced, thereby realizing accurate sending of alarm information to the mobile terminal and ensuring the reliability of monitoring and evaluation of the mobile terminal.
The method comprises the steps of monitoring performance indexes of a mobile terminal through a performance monitoring tool, obtaining dynamic indexes related to user information of the mobile terminal, evaluating the performance indexes according to the dynamic indexes to obtain an evaluation result, obtaining whether the mobile terminal is likely to have an abnormal state or not according to the evaluation result, sending alarm information to the mobile terminal which is likely to have the abnormal state, achieving the technical effects of monitoring and evaluating the mobile terminal in real time and giving an alarm to the mobile terminal which is likely to have the abnormal state in real time.
Example two:
the embodiment is a specific application scenario of the first embodiment, and the method provided by the present invention can be more clearly and specifically explained through the embodiment.
The method provided in this embodiment will be specifically described below by taking an example of generating a dynamic index by adjusting adjustable data through a mature deep learning network in a server running a performance monitoring and evaluating method. It should be noted that the present embodiment is only exemplary, and does not limit the protection scope of the embodiments of the present invention.
Fig. 2 schematically shows an environmental application diagram of a performance monitoring and evaluating method according to the second embodiment of the present application.
In an exemplary embodiment, the servers 2 in which the performance monitoring and evaluating methods are located are respectively connected to the mobile terminals 4 through the network 3; the server 2 may provide services through one or more networks 3, which networks 3 may include various network devices, such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices, and/or the like. The network 3 may include physical links, such as coaxial cable links, twisted pair cable links, fiber optic links, combinations thereof, and/or the like. The network 3 may include wireless links, such as cellular links, satellite links, Wi-Fi links, and/or the like; the mobile terminal 4 may be a computer device such as a smart phone, a tablet computer, a notebook computer, and a desktop computer.
Fig. 3 is a flowchart of a method for monitoring and evaluating performance according to an embodiment of the present invention, where the method specifically includes steps S200 to S209.
S200: creating an uploading interface for monitoring abnormal information of the mobile terminal, and executing the step S202;
in order to facilitate timely learning of the abnormal state of the mobile terminal during operation, so as to facilitate timely acquisition of the performance data of the mobile terminal in the abnormal state, the step monitors the abnormal information uploaded by the mobile terminal in real time by creating an uploading interface, and a user can upload the abnormal information to the uploading interface when the mobile terminal is abnormal, so as to rapidly find the abnormal state of the mobile terminal, so as to facilitate timely acquisition of the performance data in the abnormal state; the abnormal information is a message which is sent by the mobile terminal and used for reflecting that the mobile terminal is in an abnormal state currently when the mobile terminal judges that the mobile terminal is in an abnormal state.
In this embodiment, the mobile terminal is provided with a key and is associated with the upload interface, and the proxy event corresponding to the key is used for sending the abnormal information to the upload interface, so that the user can send the abnormal information by only clicking the key, and the effect of one-key abnormal feedback is achieved.
S201: sending a state request to a mobile terminal, and receiving state information sent by the mobile terminal according to the state request; judging whether the state information has an abnormal label or not; if yes, judging that the state information is abnormal information, and executing S202; if not, the process is ended.
In order to find out more abnormal conditions of the mobile terminal, the step sends a state request to the mobile terminal and receives state information sent by the mobile terminal according to the state request; in this embodiment, the mobile terminal generates the state information with the abnormal tag by clicking the abnormal button by sending the pop-up box with the abnormal button to the mobile terminal as the state request; if the current mobile terminal is in a normal state, the mobile terminal sends the state information with the normal label by clicking a normal button in the bullet frame, or sends the state information with the cancelled label by clicking a close button in the bullet frame. The abnormal information is a message which is sent by a user to actively judge that the mobile terminal is in an abnormal state currently and is used for reflecting that the mobile terminal is in the abnormal state currently.
S202: and acquiring performance data of the mobile terminal according to the abnormal information sent by the mobile terminal, wherein the performance data reflects the performance index of the mobile terminal in an abnormal state.
In order to obtain the performance data of the mobile terminal in the abnormal state and enable the mobile terminal and the performance data to correspond to each other, in this step, the performance data of the mobile terminal is obtained through a performance monitoring tool, and the user information of the mobile terminal is obtained, where the performance monitoring tool is a computer program for monitoring the performance of the mobile terminal, for example: PerfDog, MobilePerform Solo π, Testin, etc. The performance data is a performance index reflecting that the mobile terminal is in an abnormal state, for example: CPU utilization, memory usage, power consumption, etc.
S203: and acquiring the user information of the mobile terminal, and associating and storing the performance data and the user information.
In this step, the user information is data information for marking the user identity of the user using the mobile terminal, and examples of the data information include: and a login account of the user on the mobile terminal, a mobile phone number of the user and the like. Based on a key-value key value pair technology, the user information is used as a main key and the performance data is used as a key value to construct a key value pair, the association between the performance data and the user information is realized, and the performance data and the user information are sent to a preset abnormal database to be stored.
S204: and calling an abnormal database to summarize the performance data belonging to the same user information to form a performance set, and deleting the performance data exceeding a preset time limit in the performance set.
Due to the fact that the performance of the mobile terminal is reduced along with long-term use of the mobile terminal, or performance data corresponding to user information is not matched with the changed mobile terminal due to the fact that the user changes the mobile terminal, and the like, in the step, after the abnormal database is called to summarize the performance data belonging to the same user information to form a performance set, the performance data exceeding a preset time limit in the performance set are deleted, and therefore the influence of the performance data before a long period on the dynamic index of the currently judged mobile terminal is avoided.
In this embodiment, the step of deleting the performance data exceeding the preset time limit in the performance set includes:
s41: and extracting the current time, wherein the current time is data information reflecting the current date.
S42: and subtracting the current time from the time limit to obtain a deadline.
In this step, the time period may be day, month, and year. Illustratively, if the current time is 2020/3/1 and the time limit is 2 months, then the deadline is 2020/1/1.
S43: deleting performance data in the performance set whose date is earlier than the deadline.
In this step, the performance data in the performance set has a timestamp, which reflects the time for acquiring the performance data, identifies the timestamp of each performance data in the performance set, and deletes the performance data corresponding to the timestamp whose date is earlier than the deadline.
S205: calculating the quantity of performance data in a performance set in an abnormal database, and judging whether the quantity of the performance data reaches a preset training threshold value; if yes, extracting performance data in the performance set, and executing S206; if not, the process is ended.
In order to avoid the situation that a small amount of performance data cannot enable a deep learning network to stably and accurately judge the dynamic index, the number of the performance data in the performance set in the abnormal database is calculated, and whether the number of the performance data reaches a training threshold value is judged; if the quantity of the performance data reaches a training threshold value, training the deep learning network; and if the number of the performance data reaches the training threshold, ending the process until the number of the performance data reaches the training threshold.
In fig. 3, the S205 is shown with the following labels:
s51: calculating the quantity of performance data in a performance set in an abnormal database, and judging whether the quantity of the performance data reaches a preset training threshold value;
s52: if yes, extracting performance data in the performance set, and executing S206;
s53: if not, the process is ended.
S206: and training a preset initial deep learning network to obtain a mature deep learning network through the performance data and preset reference data, wherein the reference data reflects the performance index of the mobile terminal in a normal state.
In order to realize the purpose of judging the normal state and the abnormal state of the mobile terminal based on the artificial intelligence technology, the initial neural network is trained through the performance data and the reference data used for reflecting the performance index of the mobile terminal in the normal state, so that a mature deep learning network which can accurately judge whether the mobile terminal is in the normal state or the abnormal state according to the performance index of the mobile terminal is obtained.
In a preferred embodiment, the step of training a preset initial deep learning network to obtain a mature deep learning network through the performance data and preset reference data includes:
s61: acquiring reference data;
s62: constructing a neuron of an input layer in the initial deep learning network according to the subdata items in the benchmark data and the performance data; inputting data corresponding to each subdata item in the datum data into corresponding neurons in the input layer, and inputting data corresponding to each subdata item in the performance data into corresponding neurons in the input layer;
in this step, the sub data item is metadata of sub data in the reference data and the performance data, and the sub data is a minimum data unit constituting the reference data and the performance data; for example: the performance data is CPU utilization: 35%, use memory: 550M, and the power consumption is 0.26 mAh/s; the sub-data of the performance data includes: CPU utilization: 35%, use memory: 550M, and the power consumption is 0.26 mAh/s; the sub data items of the performance data include: CPU utilization rate, used memory and power consumption. The reference data are: CPU utilization: 1%, use memory: 10M, and the power consumption is 0.01 mAh/s; the sub-data of the reference data includes: CPU utilization: 1%, use memory: 10M, and the power consumption is 0.01 mAh/s; the sub data item of the reference data includes: CPU utilization rate, used memory and power consumption.
S63: and calling a hidden layer of the initial deep learning network, acquiring an input vector of the input layer, calculating the input vector to obtain an output vector, and outputting the output vector to an output layer of the initial deep learning network.
In this step, the output layer includes normal neurons and abnormal neurons
The normal neuron is used for expressing the probability that the mobile terminal is in a normal state, and the abnormal neuron is used for expressing the probability that the mobile terminal is in an abnormal state.
Further, the initial deep learning network is trained through the reference data and the performance data, so that the situation that the obtained mature deep learning network can only judge whether the mobile terminal is in a normal state or an abnormal state and cannot judge the normal state and the abnormal state simultaneously due to the fact that the initial deep learning network is trained through the reference data or the performance data is avoided, and therefore the critical point of the mobile terminal in the normal state and the abnormal state is obtained.
S64: and calculating the output vector of the output layer through a preset training loss function, and obtaining a training loss value according to the difference between the output vector and the abnormal information corresponding to the performance data.
S65: and adjusting the weight and the bias value of the hidden layer through a back propagation algorithm according to the training loss value until the training loss value is smaller than a preset training loss threshold value to obtain a mature deep learning network.
It should be noted that, a BP (Back Propagation) neural network is used as the initial deep learning network, and the BP network (Back Propagation) is a multi-layer feedforward network trained according to an error inverse Propagation algorithm and is one of the most widely applied neural network models at present. The BP network can learn and store a large number of input-output pattern mappings without prior disclosure of mathematical equations describing such mappings.
The loss function is a way to scale the predicted and actual values of an Artificial Neural Network (ANN). The method is used for training the deep learning network, so that the predicted value of the deep learning network is close to or even accords with the actual value.
The back propagation method is a supervised learning algorithm, and is often used for training a multi-layer perceptron and a forward neural network. The back propagation algorithm (BP algorithm) is mainly iterated in a loop mode through two links (excitation propagation and weight updating) until the response of the network to the input reaches a preset target range.
S207: and calculating preset adjustable data through the mature deep learning network to generate a test result, calculating a difference between the test result and a preset balance result to obtain a test loss value, adjusting the adjustable data according to the test loss value until the test result generated by the mature deep learning network is consistent with the balance result, and setting the adjustable data as a dynamic index.
If the performance index of the mobile terminal is monitored in real time by using a mature deep learning network, a large part of calculation power of the server is consumed, and if the performance index of a large number of mobile terminals is monitored, the performance index of the mobile terminals cannot be monitored; in the step, preset adjustable data are input into an input layer of the mature deep learning network, a hidden layer of the mature deep learning network is called to calculate the adjustable data of the input layer to obtain a test result, and the test result is output to an output layer of the mature deep learning network; and obtaining a test loss value by a preset test loss function and calculating the difference between the test result and a preset equalization result, adjusting the adjustable data by adopting a gradient descent method according to the test loss value until the test result generated by the mature deep learning network through the adjustable data and the equalization result, and setting the adjustable data as a dynamic index. Wherein the equalization result reflects a critical result between a normal state and an abnormal state, such as: the normal probability value of the output layer is 0.5, and the abnormal probability value is 0.5. In this embodiment, the metadata of the tunable data and the metadata of the performance data correspond to each other one to one, and the data set, in which the value corresponding to each metadata of the tunable data can be adjusted, includes CPU utilization, memory usage, and power consumption, for example: the tunable data includes: CPU utilization: x%, using memory: YM, power consumption ZAh/s; wherein, X, Y and Z can be any real number. Further, the test result is a data set generated by the mature deep learning network computing the adjustable data, the test result and the metadata of the test result are in one-to-one correspondence, and include a normal probability value and an abnormal probability value, for example, the adjustable data is CPU utilization: 35%, use memory: 550M, and the power consumption is 0.26 mAh/s; the test results obtained are a normal probability value of 0.2 and an abnormal probability value of 0.8.
Therefore, by obtaining the dynamic index that can be determined by the deep learning network to be between the normal state and the abnormal state critical point (i.e. the equilibrium result), once the performance index of the mobile terminal exceeds the dynamic index, the mobile terminal can be determined to be abnormal, the efficiency of determining the abnormal state of the mobile terminal is greatly improved, and further the effort consumed for monitoring the performance index of the mobile terminal and determining whether the mobile terminal is abnormal under the performance index is greatly reduced, so that the technical effect of monitoring and determining the performance indexes of a large number of mobile terminals can be realized.
Meanwhile, the performance of the mobile terminal is degraded due to long-term use of the mobile terminal (for example, hardware aging, excessive data stored in a hard disk, downloading a large amount of APPs, and the like), or when the user changes the mobile terminal, the performance index of the mobile terminal entering an abnormal state will change accordingly. Therefore, the mobile terminal is dynamically identified based on the mature deep learning network, and the adjustable data corresponding to the critical point between the normal state and the abnormal state is set as the dynamic index, so that the dynamic index can correctly reflect the performance index of the critical point between the normal state and the abnormal state of the mobile terminal no matter the mobile terminal is used for a long time to cause performance degradation of the mobile terminal or the mobile terminal is replaced, thereby realizing accurate sending of alarm information to the mobile terminal and ensuring the reliability of monitoring and evaluation of the mobile terminal.
It should be noted that the Gradient Descent method (Gradient component) is an optimizer (optimizer) commonly used in machine learning, and is configured to predict a test result of a mature deep learning network according to tunable data, and to optimally adjust the tunable data as an input layer according to the test result, so as to finally match the test result with a balance result. Based on the above example, if the tunable data is CPU utilization: 35%, use memory: 550M, and the power consumption is 0.26 mAh/s; the obtained test results are that the normal probability value is 0.2, and the abnormal probability value is 0.8; however, the normal probability value 0.2 is 0.3 lower than the normal probability of the equalization result by 0.5, and the abnormal probability value 0.8 is 0.3 higher than the abnormal probability value 0.5 of the equalization result, so that it is necessary to reduce the CPU usage rate and/or the used memory and/or the power consumption value in the adjustable data to increase the normal probability value of the test result and reduce the abnormal probability value of the test result until the value of the test result is consistent with the value of the equalization result.
S208: and associating and storing the dynamic index and the user information of the mobile terminal.
In order to ensure that the dynamic index can be called repeatedly in a long time and ensure that the dynamic index can accurately correspond to a corresponding mobile terminal; the dynamic index and the user information are associated, so that a user with the user information can accurately call the corresponding dynamic index to evaluate the performance index of the mobile terminal used by the user information, the directivity and the accuracy of dynamic index evaluation are guaranteed, the associated dynamic index and the user information are sent to a preset index server, the dynamic index can be reused in a longer time, and the reliability of monitoring the performance index of the mobile terminal is guaranteed.
In this embodiment, a key-value pair technique is adopted to associate the dynamic indicator with the user information, where the user information is used as a primary key and the dynamic indicator is used as a key value to form a key-value pair associated with each other.
Optionally, after associating and storing the dynamic indicator with the user information of the mobile terminal, the method further includes:
and uploading the dynamic index and the user information to a block chain.
It should be noted that the corresponding summary information is obtained based on the dynamic index and the user information, and specifically, the summary information is obtained by hashing the dynamic index and the user information, for example, by using the sha256s algorithm. Uploading summary information to the blockchain can ensure the safety and the fair transparency of the user. The user equipment may download the summary information from the blockchain to verify whether the dynamic indicator and the user information are tampered. The blockchain referred to in this example is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
S209: and monitoring the performance index of the mobile terminal, taking the performance index as a real-time index, evaluating the real-time index according to the dynamic index to obtain an evaluation result, and sending alarm information to the mobile terminal according to the evaluation result.
In order to realize real-time monitoring and evaluation of performance indexes of a mobile terminal and real-time sending of alarm information to the mobile terminal which may possibly have an abnormal state, the performance indexes of the mobile terminal are monitored through a performance monitoring tool, dynamic indexes related to user information of the mobile terminal are obtained, the performance indexes are evaluated according to the dynamic indexes to obtain an evaluation result, whether the mobile terminal may have the abnormal state or not is known according to the evaluation result, and the alarm information is sent to the mobile terminal which may possibly have the abnormal state, so that the technical effects of real-time monitoring and evaluation of the mobile terminal and real-time alarm of the mobile terminal which may have the abnormal state are realized.
In a preferred embodiment, the step of monitoring a performance index of the mobile terminal, evaluating the performance index according to the dynamic index to obtain an evaluation result, and sending alarm information to the mobile terminal according to the evaluation result includes:
s91: and monitoring the performance index of the mobile terminal and taking the performance index as a real-time index, acquiring the user information of the mobile terminal and extracting a dynamic index associated with the user information.
In this step, the performance monitoring tool is used to monitor the performance index of the mobile terminal, obtain the user information of the mobile terminal, and call an index server to obtain the dynamic index associated with the user information.
S92: and setting the real-time indexes with values exceeding the dynamic indexes as abnormal indexes, and setting the number of the abnormal indexes as an evaluation result. In the step, comparing the performance index with the dynamic index, identifying the performance index with a value exceeding the dynamic index, and setting the performance index as an abnormal index; and calculating the number of the abnormal indexes, and setting the number as an evaluation result.
Illustratively, it is assumed that the dynamic index associated with the user information of the mobile terminal a includes: 30% of CPU, 0.238mAh/s of power consumption and 500M of memory;
the performance indexes obtained by monitoring the mobile terminal a include: 35% of CPU, 0.26mAh/s of power consumption and 550M of memory; then, since device CPU 35% > CPU threshold 30%; the power consumption of the equipment is 0.26mAh/s and is greater than the power consumption threshold value of 0.238 mAh/s; device memory 550M > memory threshold 500M. Therefore, the evaluation result obtained was 3.
S93: judging whether the evaluation result exceeds a preset abnormal threshold value or not;
s94: if yes, sending alarm information to the mobile terminal;
s95: if not, the process is ended.
Exemplarily, assuming that the abnormal threshold is 2, based on the above example, the obtained evaluation result is 3, it is determined that the mobile terminal may have an abnormal state or has an abnormal state, and therefore, alarm information is sent to the mobile terminal.
Example three:
referring to fig. 4, a performance monitoring and evaluating apparatus 1 of the present embodiment includes:
an exception obtaining module 12, configured to obtain performance data of a mobile terminal according to exception information sent by the mobile terminal, where the performance data reflects a performance index of the mobile terminal in an exception state;
the network training module 16 is configured to train a preset initial deep learning network to obtain a mature deep learning network through the performance data and preset reference data, where the reference data reflects a performance index of the mobile terminal in a normal state;
the dynamic adjusting module 17 is configured to calculate preset adjustable data through the mature deep learning network to generate a test result, calculate a difference between the test result and a preset equalization result to obtain a test loss value, adjust the adjustable data according to the test loss value until the test result generated by the mature deep learning network is consistent with the equalization result, and set the adjustable data as a dynamic index;
and the monitoring alarm module 19 is used for monitoring the performance index of the mobile terminal and taking the performance index as a real-time index, evaluating the real-time index according to the dynamic index to obtain an evaluation result, and sending alarm information to the mobile terminal according to the evaluation result.
Optionally, the performance monitoring and evaluating apparatus 1 further includes:
a creating module 10, configured to create an upload interface for monitoring abnormal information of a mobile terminal, and call an abnormality obtaining module 12;
optionally, the performance monitoring and evaluating apparatus 1 further includes:
an information request module 11, configured to send a status request to a mobile terminal, and receive status information sent by the mobile terminal according to the status request; judging whether the state information has an abnormal label or not; if yes, judging the state information to be abnormal information, and calling an abnormality acquisition module 12; if not, the process is ended.
Optionally, the performance monitoring and evaluating apparatus 1 further includes:
and an information association module 13, configured to acquire user information of the mobile terminal, associate and store the performance data and the user information.
Optionally, the performance monitoring and evaluating apparatus 1 further includes:
and the information deleting module 14 is used for calling the abnormal database to summarize the performance data belonging to the same user information to form a performance set, and deleting the performance data exceeding a preset time limit in the performance set.
Optionally, the performance monitoring and evaluating apparatus 1 further includes:
the training triggering module 15 is configured to calculate the number of performance data in a performance set in an abnormal database, and determine whether the number of performance data reaches a preset training threshold; if yes, extracting performance data in the performance set, and calling a network training module 16; if not, the process is ended.
Optionally, the performance monitoring and evaluating apparatus 1 further includes:
and an association storage module 18, configured to associate and store the dynamic indicator with the user information of the mobile terminal.
The technical scheme is applied to the field of intelligent decision of artificial intelligence, and the performance data of the mobile terminal is obtained according to the abnormal information sent by the mobile terminal; training by using a neural network as an initial deep learning network according to the performance data and the reference data to obtain a mature deep learning network which is used as a classification model; calculating adjustable data through the mature deep learning network to generate a test result, calculating a difference between the test result and a balance result to obtain a test loss value, adjusting the adjustable data according to the test loss value until the test result generated by the mature deep learning network is consistent with the balance result, and setting the adjustable data as a dynamic index; and monitoring the performance index of the mobile terminal, evaluating the performance index according to the dynamic index to obtain an evaluation result, and sending alarm information to the mobile terminal according to the evaluation result.
Example four:
in order to achieve the above object, the present invention further provides a computer device 5, where components of the performance monitoring and evaluating apparatus 1 according to the third embodiment may be distributed in different computer devices, and the computer device 5 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack-mounted server, a blade server, a tower server, or a rack-mounted server (including an independent server or a server cluster formed by multiple application servers) that executes programs. The computer device of the embodiment at least includes but is not limited to: a memory 51, a processor 52, which may be communicatively coupled to each other via a system bus, as shown in FIG. 5. It should be noted that fig. 5 only shows a computer device with components, but it should be understood that not all of the shown components are required to be implemented, and more or fewer components may be implemented instead.
In this embodiment, the memory 51 (i.e., a readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., 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 magnetic disk, an optical disk, and the like. In some embodiments, the memory 51 may be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device. In other embodiments, the memory 51 may be an external storage device of a computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the computer device. Of course, the memory 51 may also include both internal and external storage devices of the computer device. In this embodiment, the memory 51 is generally used for storing an operating system and various application software installed in the computer device, for example, the program code of the performance monitoring and evaluating apparatus in the third embodiment. Further, the memory 51 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 52 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 52 is typically used to control the overall operation of the computer device. In this embodiment, the processor 52 is configured to run the program codes stored in the memory 51 or process data, for example, run the performance monitoring and evaluating device, so as to implement the performance monitoring and evaluating method of the first embodiment and the second embodiment.
Example five:
to achieve the above objects, the present invention also provides a computer readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card type memory (e.g., 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 magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by a processor 52, implements corresponding functions. The computer-readable storage medium of the present embodiment is used for storing a performance monitoring and evaluating device, and when being executed by the processor 52, the performance monitoring and evaluating method of the first embodiment and the second embodiment is implemented.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A performance monitoring and evaluating method is used for monitoring and evaluating performance indexes of a mobile terminal, and is characterized by comprising the following steps:
acquiring performance data of a mobile terminal according to abnormal information sent by the mobile terminal, wherein the performance data reflects performance indexes of the mobile terminal in an abnormal state;
training a preset initial deep learning network to obtain a mature deep learning network through the performance data and preset reference data, wherein the reference data reflects performance indexes of the mobile terminal in a normal state;
calculating preset adjustable data through the mature deep learning network to generate a test result, calculating a difference between the test result and a preset balance result to obtain a test loss value, adjusting the adjustable data according to the test loss value until the test result generated by the mature deep learning network is consistent with the balance result, and setting the adjustable data as a dynamic index;
and monitoring the performance index of the mobile terminal, taking the performance index as a real-time index, evaluating the real-time index according to the dynamic index to obtain an evaluation result, and sending alarm information to the mobile terminal according to the evaluation result.
2. The performance monitoring and evaluating method according to claim 1, wherein before the performance data of the mobile terminal is obtained according to the abnormal information sent by the mobile terminal, the method further comprises:
and creating an uploading interface for monitoring abnormal information of the mobile terminal.
3. The performance monitoring and evaluating method according to claim 1, wherein before the performance data of the mobile terminal is obtained according to the abnormal information sent by the mobile terminal, the method further comprises:
sending a state request to a mobile terminal, and receiving state information sent by the mobile terminal according to the state request; judging whether the state information has an abnormal label or not; if yes, judging that the state information is abnormal information; if not, the process is ended.
4. The performance monitoring and evaluating method according to claim 1, wherein after the performance data of the mobile terminal is obtained according to the anomaly information sent by the mobile terminal, the method further comprises:
acquiring user information of the mobile terminal, and associating and storing the performance data with the user information;
calling an abnormal database to summarize performance data belonging to the same user information to form a performance set, and deleting the performance data exceeding a preset time limit in the performance set;
calculating the quantity of performance data in a performance set in an abnormal database, and judging whether the quantity of the performance data reaches a preset training threshold value; if yes, extracting performance data in the performance set; if not, the process is ended.
5. The performance monitoring and evaluating method according to claim 1, wherein the step of training a preset initial deep learning network to obtain a mature deep learning network through the performance data and preset reference data comprises:
acquiring reference data;
constructing a neuron of an input layer in the initial deep learning network according to the subdata items in the benchmark data and the performance data; inputting data corresponding to each subdata item in the datum data into corresponding neurons in the input layer, and inputting data corresponding to each subdata item in the performance data into corresponding neurons in the input layer;
calling a hidden layer of the initial deep learning network, acquiring an input vector of the input layer, calculating the input vector to obtain an output vector, and outputting the output vector to an output layer of the initial deep learning network;
calculating an output vector of the output layer through a preset training loss function, and obtaining a training loss value according to a difference between the output vector and abnormal information corresponding to the performance data;
and adjusting the weight and the bias value of the hidden layer through a back propagation algorithm according to the training loss value until the training loss value is smaller than a preset training loss threshold value to obtain a mature deep learning network.
6. The performance monitoring and evaluation method of claim 1, wherein after setting the tunable data as a dynamic indicator, the method further comprises:
associating and storing the dynamic index and the user information of the mobile terminal;
after associating and storing the dynamic indicator with the user information of the mobile terminal, the method further includes:
and uploading the dynamic index and the user information to a block chain.
7. The performance monitoring and evaluating method according to claim 1, wherein the step of monitoring the performance index of the mobile terminal and using the performance index as a real-time index, evaluating the real-time index according to the dynamic index to obtain an evaluation result, and sending alarm information to the mobile terminal according to the evaluation result comprises:
monitoring a performance index of a mobile terminal and taking the performance index as a real-time index, acquiring user information of the mobile terminal and extracting a dynamic index associated with the user information;
setting real-time indexes with values exceeding the dynamic indexes as abnormal indexes, and setting the number of the abnormal indexes as evaluation results; judging whether the evaluation result exceeds a preset abnormal threshold value or not;
if yes, sending alarm information to the mobile terminal;
if not, the process is ended.
8. A performance monitoring and evaluating device, comprising:
the system comprises an exception acquisition module, a performance data acquisition module and a performance data acquisition module, wherein the exception acquisition module is used for acquiring the performance data of a mobile terminal according to exception information sent by the mobile terminal, and the performance data reflects the performance index of the mobile terminal in an abnormal state;
the network training module is used for training a preset initial deep learning network to obtain a mature deep learning network through the performance data and preset reference data, wherein the reference data reflects the performance index of the mobile terminal in a normal state;
the dynamic adjusting module is used for calculating preset adjustable data through the mature deep learning network to generate a test result, calculating the difference between the test result and a preset balance result to obtain a test loss value, adjusting the adjustable data according to the test loss value until the test result generated by the mature deep learning network is consistent with the balance result, and setting the adjustable data as a dynamic index;
and the monitoring alarm module is used for monitoring the performance index of the mobile terminal and taking the performance index as a real-time index, evaluating the real-time index according to the dynamic index to obtain an evaluation result, and sending alarm information to the mobile terminal according to the evaluation result.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the performance monitoring and evaluation method according to any one of claims 1 to 7 are implemented when the computer program is executed by the processor of the computer device.
10. A computer-readable storage medium, on which a computer program is stored, wherein the computer program stored in the computer-readable storage medium, when being executed by a processor, implements the steps of the performance monitoring and evaluation method according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011208472.8A CN112306808B (en) | 2020-11-03 | 2020-11-03 | Performance monitoring and evaluating method and device, computer equipment and readable storage medium |
| PCT/CN2021/091338 WO2022095381A1 (en) | 2020-11-03 | 2021-04-30 | Performance monitoring and evaluation method and apparatus, computer device, and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011208472.8A CN112306808B (en) | 2020-11-03 | 2020-11-03 | Performance monitoring and evaluating method and device, computer equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112306808A true CN112306808A (en) | 2021-02-02 |
| CN112306808B CN112306808B (en) | 2022-08-16 |
Family
ID=74333860
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011208472.8A Active CN112306808B (en) | 2020-11-03 | 2020-11-03 | Performance monitoring and evaluating method and device, computer equipment and readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112306808B (en) |
| WO (1) | WO2022095381A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113393143A (en) * | 2021-06-24 | 2021-09-14 | 重庆大学 | Fin machining state monitoring method based on information fusion |
| CN114221874A (en) * | 2021-12-14 | 2022-03-22 | 平安壹钱包电子商务有限公司 | Traffic analysis and scheduling method and device, computer equipment and readable storage medium |
| WO2022095381A1 (en) * | 2020-11-03 | 2022-05-12 | 平安科技（深圳）有限公司 | Performance monitoring and evaluation method and apparatus, computer device, and readable storage medium |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115164993A (en) * | 2022-07-26 | 2022-10-11 | 正人智慧科技(苏州)有限公司 | Pump room environment temperature and humidity monitoring and early warning method and system |
| CN116156401B (en) * | 2023-04-17 | 2023-06-27 | 深圳市英唐数码科技有限公司 | Hearing-aid equipment intelligent detection method, system and medium based on big data monitoring |
| CN116485280B (en) * | 2023-06-15 | 2023-09-19 | 深圳市蓝巨科技有限公司 | UVC-LED production quality evaluation method and system based on artificial intelligence |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1202491A2 (en) * | 2000-10-31 | 2002-05-02 | Agilent Technologies, Inc. - a Delaware corporation - | Measuring network performance parameters in data communication networks |
| CN105259754A (en) * | 2015-10-16 | 2016-01-20 | 华北理工大学 | Board thickness intelligent control method based on active learning |
| CN105357097A (en) * | 2014-08-19 | 2016-02-24 | 中兴通讯股份有限公司 | Virtual network (VN) regulation method and system |
| CN105956734A (en) * | 2016-04-15 | 2016-09-21 | 广东轩辕网络科技股份有限公司 | Method and system for dynamically setting performance index threshold of IT equipment |
| CN109120715A (en) * | 2018-09-21 | 2019-01-01 | 华南理工大学 | Dynamic load balancing method under a kind of cloud environment |
| CN109376615A (en) * | 2018-09-29 | 2019-02-22 | 苏州科达科技股份有限公司 | For promoting the method, apparatus and storage medium of deep learning neural network forecast performance |
| CN109460890A (en) * | 2018-09-21 | 2019-03-12 | 浙江大学 | A kind of intelligent self-healing method based on intensified learning and control performance monitoring |
| CN109492193A (en) * | 2018-12-28 | 2019-03-19 | 同济大学 | Abnormal network data based on depth machine learning model generate and prediction technique |
| CN109948703A (en) * | 2019-03-20 | 2019-06-28 | 上海交通大学 | Gene image procossing estimation method, system, medium and equipment based on deep learning |
| CN110647900A (en) * | 2019-04-12 | 2020-01-03 | 中国人民解放军战略支援部队信息工程大学 | Intelligent safety situation prediction method, device and system based on deep neural network |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9342782B2 (en) * | 2014-02-21 | 2016-05-17 | Qualcomm Incorporated | Stochastic delay plasticity |
| CN109684310A (en) * | 2018-11-22 | 2019-04-26 | 安徽继远软件有限公司 | A kind of information system performance Situation Awareness method based on big data analysis |
| CN110262939B (en) * | 2019-05-14 | 2023-07-21 | 苏宁金融服务(上海)有限公司 | Algorithm model operation monitoring method, device, computer equipment and storage medium |
| CN110598802B (en) * | 2019-09-26 | 2021-07-27 | 腾讯科技（深圳）有限公司 | Memory detection model training method, memory detection method and device |
| CN112306808B (en) * | 2020-11-03 | 2022-08-16 | 平安科技（深圳）有限公司 | Performance monitoring and evaluating method and device, computer equipment and readable storage medium |
-
2020
- 2020-11-03 CN CN202011208472.8A patent/CN112306808B/en active Active
-
2021
- 2021-04-30 WO PCT/CN2021/091338 patent/WO2022095381A1/en active Application Filing
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1202491A2 (en) * | 2000-10-31 | 2002-05-02 | Agilent Technologies, Inc. - a Delaware corporation - | Measuring network performance parameters in data communication networks |
| CN105357097A (en) * | 2014-08-19 | 2016-02-24 | 中兴通讯股份有限公司 | Virtual network (VN) regulation method and system |
| CN105259754A (en) * | 2015-10-16 | 2016-01-20 | 华北理工大学 | Board thickness intelligent control method based on active learning |
| CN105956734A (en) * | 2016-04-15 | 2016-09-21 | 广东轩辕网络科技股份有限公司 | Method and system for dynamically setting performance index threshold of IT equipment |
| CN109120715A (en) * | 2018-09-21 | 2019-01-01 | 华南理工大学 | Dynamic load balancing method under a kind of cloud environment |
| CN109460890A (en) * | 2018-09-21 | 2019-03-12 | 浙江大学 | A kind of intelligent self-healing method based on intensified learning and control performance monitoring |
| CN109376615A (en) * | 2018-09-29 | 2019-02-22 | 苏州科达科技股份有限公司 | For promoting the method, apparatus and storage medium of deep learning neural network forecast performance |
| CN109492193A (en) * | 2018-12-28 | 2019-03-19 | 同济大学 | Abnormal network data based on depth machine learning model generate and prediction technique |
| CN109948703A (en) * | 2019-03-20 | 2019-06-28 | 上海交通大学 | Gene image procossing estimation method, system, medium and equipment based on deep learning |
| CN110647900A (en) * | 2019-04-12 | 2020-01-03 | 中国人民解放军战略支援部队信息工程大学 | Intelligent safety situation prediction method, device and system based on deep neural network |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022095381A1 (en) * | 2020-11-03 | 2022-05-12 | 平安科技（深圳）有限公司 | Performance monitoring and evaluation method and apparatus, computer device, and readable storage medium |
| CN113393143A (en) * | 2021-06-24 | 2021-09-14 | 重庆大学 | Fin machining state monitoring method based on information fusion |
| CN113393143B (en) * | 2021-06-24 | 2022-06-17 | 重庆大学 | Fin machining state monitoring method based on information fusion |
| CN114221874A (en) * | 2021-12-14 | 2022-03-22 | 平安壹钱包电子商务有限公司 | Traffic analysis and scheduling method and device, computer equipment and readable storage medium |
| CN114221874B (en) * | 2021-12-14 | 2023-11-14 | 平安壹钱包电子商务有限公司 | Traffic analysis and scheduling method and device, computer equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022095381A1 (en) | 2022-05-12 |
| CN112306808B (en) | 2022-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112306808B (en) | Performance monitoring and evaluating method and device, computer equipment and readable storage medium | |
| CN104424354B (en) | The method and system of generation model detection abnormal user behavior is operated using user | |
| CN112800116B (en) | Method and device for detecting abnormity of service data | |
| CN109918279B (en) | Electronic device, method for identifying abnormal operation of user based on log data and storage medium | |
| CN108876213B (en) | Block chain-based product management method, device, medium and electronic equipment | |
| CN113688923B (en) | Order abnormity intelligent detection method and device, electronic equipment and storage medium | |
| EP3648433B1 (en) | System and method of training behavior labeling model | |
| JP2017174375A (en) | Risk early warning method and apparatus | |
| CN111698303A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN111931047B (en) | Artificial intelligence-based black product account detection method and related device | |
| CN112465141A (en) | Model compression method, model compression device, electronic device and medium | |
| CN115936895A (en) | Risk assessment method, device and equipment based on artificial intelligence and storage medium | |
| CN111562930A (en) | Upgrading method and system for web application security | |
| CN113807728A (en) | Performance assessment method, device, equipment and storage medium based on neural network | |
| CN116843395A (en) | Alarm classification method, device, equipment and storage medium of service system | |
| CN112862222A (en) | Air conditioner return air temperature prediction method, abnormality monitoring method and related device | |
| CN116823026A (en) | Engineering data processing system and method based on block chain | |
| CN115757075A (en) | Task abnormity detection method and device, computer equipment and storage medium | |
| CN113343577A (en) | Parameter optimization method and device, computer equipment and readable storage medium | |
| CN114722025A (en) | Data prediction method, device and equipment based on prediction model and storage medium | |
| CN114913008A (en) | Decision tree-based bond value analysis method, device, equipment and storage medium | |
| CN112307271A (en) | Safety monitoring method and device for remote control service of power distribution automation system | |
| CN112183644B (en) | Index stability monitoring method and device, computer equipment and medium | |
| CN111950624A (en) | Client risk assessment model construction method and device, storage medium and terminal equipment | |
| CN112559012B (en) | System upgrading and testing method and device, computer equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |