CN109800122B - Monitoring prompting method and device, computer equipment and storage medium - Google Patents
Monitoring prompting method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109800122B CN109800122B CN201811528652.7A CN201811528652A CN109800122B CN 109800122 B CN109800122 B CN 109800122B CN 201811528652 A CN201811528652 A CN 201811528652A CN 109800122 B CN109800122 B CN 109800122B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- state classification
- information
- classification model
- item
- 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.)
- Active
Links
Images
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a monitoring prompting method, a monitoring prompting device, computer equipment and a storage medium. The method comprises the following steps: periodically monitoring the server to be monitored according to the preset monitoring interval time and the monitoring item information to obtain server monitoring information; constructing a state classification model according to the monitoring item information and preset state classification information; training the state classification model through preset monitoring project training parameters to obtain a trained state classification model; classifying a plurality of monitoring items in the server monitoring information through the trained state classification model to obtain a state classification result of each monitoring item; and sending out monitoring prompt information according to the state classification result of the monitoring items in the server monitoring information. The invention is based on the neural network technology, and sends monitoring prompt information to the user according to the obtained state classification result, so that the deviation is avoided when judging whether the monitoring item is normal, and the monitoring prompt can be more accurately carried out.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a monitoring and prompting method and apparatus, a computer device, and a storage medium.
Background
In the process of maintaining the enterprise-level server, because the threshold values of some monitoring items cannot be accurately preset when the server to be monitored is monitored, the deviation exists when the server to be monitored is judged to normally operate only by combining the acquired numerical values of the monitoring items in a mode of setting the threshold values, so that a large number of prompts are caused to users, or a certain monitoring item is abnormal and the prompt is not given to the users, and the efficiency of maintaining the server is influenced. Therefore, the problem that the monitoring items in the server to be monitored cannot be accurately prompted exists in the prior art.
Disclosure of Invention
The embodiment of the invention provides a monitoring prompt method, a monitoring prompt device, computer equipment and a storage medium, and aims to solve the problem that accurate monitoring prompt cannot be performed in the prior art.
In a first aspect, an embodiment of the present invention provides a monitoring prompting method, which includes:
periodically monitoring the server to be monitored according to the preset monitoring interval time and the monitoring item information to obtain server monitoring information;
constructing a state classification model according to the monitoring item information and preset state classification information;
training the state classification model through preset monitoring project training parameters to obtain a trained state classification model;
classifying a plurality of monitoring items in the server monitoring information through the trained state classification model to obtain a state classification result of each monitoring item;
and sending out monitoring prompt information according to the state classification result of the monitoring items in the server monitoring information.
In a second aspect, an embodiment of the present invention provides a monitoring and prompting apparatus, including:
the monitoring information acquisition unit is used for periodically monitoring the server to be monitored according to the preset monitoring interval time and the monitoring item information so as to acquire and obtain server monitoring information;
the classification model construction unit is used for constructing a state classification model according to the monitoring item information and preset state classification information;
the model training unit is used for training the state classification model through preset monitoring project training parameters to obtain a trained state classification model;
the state classification result acquisition unit is used for classifying a plurality of monitoring items in the server monitoring information through the trained state classification model to obtain a state classification result of each monitoring item;
and the prompt information sending unit is used for sending monitoring prompt information according to the state classification result of the monitoring items in the server monitoring information.
In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the monitoring and prompting method according to the first aspect when executing the computer program.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor is caused to execute the monitoring and prompting method according to the first aspect.
The embodiment of the invention provides a monitoring prompting method and device, computer equipment and a storage medium. The method comprises the steps of establishing a state classification model and training to realize real-time monitoring of all monitoring items in a server to be monitored and obtain a state classification result of each monitoring item, and sending monitoring prompt information to a user according to the obtained state classification results, so that the condition that whether the monitoring items are normal or not is avoided, and monitoring prompt can be more accurately carried out.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a monitoring prompt method according to an embodiment of the present invention;
fig. 2 is a schematic sub-flow diagram of a monitoring and prompting method according to an embodiment of the present invention;
fig. 3 is another schematic sub-flow diagram of the monitoring and prompting method according to the embodiment of the present invention;
fig. 4 is another sub-flow diagram of the monitoring prompting method according to the embodiment of the present invention;
fig. 5 is another schematic sub-flow diagram of the monitoring and prompting method according to the embodiment of the present invention;
FIG. 6 is a schematic block diagram of a monitoring prompt apparatus according to an embodiment of the present invention;
FIG. 7 is a schematic block diagram of a sub-unit of a monitoring and prompting device according to an embodiment of the present invention;
FIG. 8 is a schematic block diagram of another subunit of the monitoring and prompting device provided in the embodiment of the present invention;
FIG. 9 is a schematic block diagram of another sub-unit of the monitoring and prompting device provided by the embodiment of the invention;
FIG. 10 is a schematic block diagram of another sub-unit of the monitoring and prompting device provided by the embodiment of the invention;
FIG. 11 is a schematic block diagram of a computer device provided by an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present 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.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Referring to fig. 1, fig. 1 is a schematic flow chart of a monitoring prompting method according to an embodiment of the present invention. The monitoring prompting method is applied to a user terminal, and is executed through application software installed in the user terminal, wherein the user terminal is terminal equipment with a display function, such as a desktop computer, a notebook computer, a tablet computer or a mobile phone; the server connected with the user terminal can be monitored through the user terminal.
As shown in fig. 1, the method includes steps S110 to S150.
S110, periodically monitoring the server to be monitored according to the preset monitoring interval time and the monitoring project information to obtain the server monitoring information.
And periodically monitoring the server to be monitored according to the preset monitoring interval time and the monitoring item information so as to obtain the server monitoring information. The preset monitoring interval time is time information for periodically acquiring server monitoring information of the server to be monitored, for example, if the preset monitoring interval time is 20 seconds, the server to be monitored is periodically monitored by taking 20 seconds as a period. The preset monitoring item information includes a plurality of monitoring items, and when the server to be monitored is periodically monitored, the monitoring item value of the server to be monitored can be obtained through the plurality of monitoring items at preset monitoring intervals, that is, the server monitoring information is obtained. The server to be monitored is an enterprise terminal which needs to be monitored in an enterprise.
Specifically, the preset monitoring item information includes average server load, connection number of terminal devices, and the like. The average load is a parameter value used for reflecting the operating pressure of the server to be monitored, and the calculation formula is average load X = (a + B)/C; wherein, A is the number of processes being processed by the server, B is the number of processes waiting for the server to process, and C is the number of CPU cores.
For example, if the number of processes being processed by the server is 5, the number of processes waiting for processing by the server is 4, and the number of cpu cores is 2, the average load of the server at this time is 4.5.
The number of the connected terminal devices is the number of the terminal devices connected to the server to be monitored, and the larger the number of the connected terminal devices is, the more the terminal devices are connected to the server to be monitored, the number of the connected terminal devices of the server should be limited, and the normal operation of the server is affected by the overlarge number of the connected terminal devices.
In the process of monitoring the server to be monitored, the thresholds of the monitoring items such as the average load of the server, the connection number of the terminal equipment and the like cannot be accurately set, so that the deviation exists when the server to be monitored is judged to normally operate by combining the acquired numerical values of the monitoring items through the mode of setting the thresholds, and whether the server to be monitored normally operates needs to be judged by adopting other modes.
And S120, constructing a state classification model according to the monitoring item information and preset state classification information.
And constructing a state classification model according to the monitoring item information and preset state classification information. The state classification model is a model for classifying states of monitoring items contained in the monitoring item information, and is based on a neural network technology. The state classification model comprises a plurality of input nodes, a plurality of intermediate nodes and a plurality of output nodes; the preset state classification information is information for classifying whether the monitoring items are normal or not, and the preset state classification information includes a plurality of categories. For example, the preset status classification information may include three categories: processing, buffering, ignoring.
In this embodiment, the states of the monitoring items are classified by the state classification model, so that a user can accurately judge whether a certain monitoring item in the server to be monitored is normal, and the situation that a large number of prompts are sent to the user or a certain monitoring item is abnormal and no prompt is sent to the user due to inaccurate judgment is avoided, so that the efficiency of maintaining the server is improved.
In one embodiment, as shown in fig. 2, step S120 includes substeps S121, S122 and S123.
S121, establishing an input node of a state classification model according to the monitoring items contained in the monitoring item information.
And constructing an input node of a state classification model according to the monitoring items contained in the monitoring item information. Specifically, the number of the input nodes is equal to the number of monitoring items included in the monitoring item information, each monitoring item corresponds to one input node, and the value of the output node is the value of the corresponding monitoring item in the acquired server monitoring information.
For example, the preset monitoring item information includes two monitoring items: and (3) constructing two input nodes in the state classification model according to the average load of the server and the connection number of the terminal equipment, wherein the value of the first input node is the value of the average load of the server, and the value of the second input node is the value of the connection number of the terminal equipment.
And S122, constructing an output node in the state classification model according to the preset state classification information.
And constructing an output node in the state classification model according to the preset state classification information. Specifically, the number of the output nodes is equal to the number of categories included in the preset state classification information, each category corresponds to one output node, the value of each output node is the matching probability between a certain monitoring item and the corresponding category, and the monitoring items can be classified by obtaining the matching probabilities between the monitoring items and the categories to obtain the state classification result of the monitoring items.
For example, the preset state classification information may include three categories: and processing, buffering and ignoring, namely constructing three output nodes in the state classification model, wherein the value of the first output node is the matching probability between the monitoring item and the class of processing, the value of the second output node is the matching probability between the monitoring item and the class of buffering, and the value of the third output node is the matching probability between the monitoring item and the class of ignoring.
S123, constructing an input calculation formula between the input nodes and the intermediate nodes and an output calculation formula between the output nodes and the intermediate nodes according to the number of the preset intermediate nodes to construct and obtain the state classification model.
And constructing an input calculation formula between the input nodes and the intermediate nodes and an output calculation formula between the output nodes and the intermediate nodes according to the number of the preset intermediate nodes to construct and obtain the state classification model. For example, if the number of the intermediate nodes is 100, all the input nodes are connected to the 100 intermediate nodes, that is, the input nodes are respectively connected to a plurality of input metersThe calculation formula calculates the values of 100 intermediate nodes connected to the plurality of input nodes, the first input calculation formula being denoted as C 1 ＝W 1 ×X 1 +B 1 Wherein, C 1 The value of the parameter, X, of the calculation formula is entered as the calculation value of the first intermediate node 1 Is the value of the first input node, W 1 And B 1 The preset parameter values in the input calculation formulas between the first intermediate node and the first input node are different, and the values of 100 intermediate nodes connected with the first input node can be calculated through 100 input calculation formulas; the 100 intermediate nodes are respectively connected with the output nodes, namely, the values of the output nodes connected with the 100 intermediate nodes are obtained by calculating through a plurality of output calculation formulas, wherein the first output calculation formula is F 1 ＝A 1 ×C 1 +A 2 ×C 2 +……A 100 ×C 100 +D 1 Wherein F is 1 Is the value of the first output node, C N Is the calculated value of the Nth intermediate node, A N For the first output, calculating the preset parameter value corresponding to the Nth intermediate node in the formula, D 1 The values of the parameters preset in the formula are calculated for the first output. Specifically, in the process of constructing the state classification model, all parameter values in the input calculation formula and the output calculation formula are random values, and the parameter values preset in different input calculation formulas are different.
S130, training the state classification model through preset monitoring project training parameters to obtain a trained state classification model.
And training the state classification model through preset monitoring project training parameters to obtain the trained state classification model. In order to improve the accuracy of the state classification model, the state classification model needs to be trained through preset monitoring project training parameters before the constructed state classification model is used. The monitoring project training parameters comprise parameter adjustment rules, values of historical monitoring projects and state classification results. And adjusting the parameter values of the input calculation formula and the output calculation formula in the state classification model according to the parameter adjustment rule by combining the values of the historical monitoring items and the state classification result.
The parameter adjustment rule is rule information for adjusting parameter values of the input calculation formula and the output calculation formula in the state classification model. The numerical value of the historical monitoring item is a historical numerical value obtained by monitoring the server by the historical monitoring item, and the state classification result of the historical monitoring item is a classification result obtained by classifying the user according to the historical numerical value obtained by monitoring.
In an embodiment, as shown in fig. 3, step S130 includes sub-steps S131, S132, and S133.
S131, historical monitoring item values in the monitoring item training parameters are calculated through a state classification model so as to obtain matching probabilities between the historical monitoring items and a plurality of categories.
And calculating the numerical value of the historical monitoring item in the training parameters of the monitoring item through a state classification model, so as to obtain the matching probability between the historical monitoring item and a plurality of categories.
For example, the average load of the server is 4.5 for a certain historical monitoring item, the value of the historical monitoring item is input into the corresponding input node in the state classification model, and the value of all output nodes is obtained through calculation, that is, the matching probability between the historical monitoring item and the corresponding category.
And S132, judging whether the state classification result of the category with the highest matching probability is the same as the state classification result of the history monitoring item according to the obtained matching probability between the history monitoring item and the categories.
And judging whether the classification result of the category with the highest matching probability is the same as the state classification result of the historical monitoring item according to the obtained matching probability between the historical monitoring item and the categories. The method comprises the steps of obtaining matching probabilities between a historical monitoring item and multiple categories, judging whether the category with the highest matching probability is the same as the state classification result of the historical monitoring item, if so, not adjusting parameter values of a formula in a state classification model, and if not, adjusting the parameter values of the formula in the state classification model.
And S133, if the type with the highest matching probability of the historical monitoring item is different from the state classification result of the historical monitoring item, adjusting the parameter value of the formula in the state classification model according to the parameter adjustment rule in the training parameter of the monitoring item.
And if the type with the highest matching probability of the historical monitoring item is different from the state classification result of the historical monitoring item, adjusting the parameter value of the formula in the state classification model according to the parameter adjustment rule in the training parameter of the monitoring item.
In one embodiment, as shown in FIG. 4, step S133 includes sub-step S1331.
And S1331, adjusting the parameter values of the formula in the state classification model according to the adjustment direction and the adjustment amplitude in the parameter adjustment rule.
And adjusting the parameter values of the formula in the state classification model according to the adjustment direction and the adjustment amplitude in the parameter adjustment rule. Specifically, the parameter adjustment rule includes an adjustment direction and an adjustment range, where the adjustment direction is direction information used to enlarge or reduce a parameter value of a formula in the matching probability calculation model, and the adjustment range is range information used to adjust the parameter value of the formula in the matching probability calculation model.
For example, if the category with the highest matching probability of a certain historical monitoring item is different from the state classification result of the historical monitoring item, the parameter value of the formula in the state classification model needs to be adjusted according to the parameter adjustment rule, the adjustment direction in the parameter adjustment rule is amplification, the adjustment amplitude is 3%, the parameter value in the formula is amplified and adjusted according to the parameter adjustment rule, the amplification adjustment amplitude is 3%, that is, the parameter value is multiplied by 1.03 to obtain a new adjusted parameter value.
And if the type with the highest matching probability of the historical monitoring item is the same as the state classification result of the historical monitoring item, adjusting the parameter value of the formula in the state classification model. By adopting the method, the numerical values and the state classification results of a plurality of groups of historical monitoring items are input into the state classification model, so that the constructed state classification model is repeatedly trained, and the trained state classification model can be obtained.
S140, classifying a plurality of monitoring items in the server monitoring information through the trained state classification model to obtain a state classification result of each monitoring item.
And classifying a plurality of monitoring items in the server monitoring information through the trained state classification model, so as to obtain a state classification result of each monitoring item. The specific using process is that the matching probability between the monitoring item and all categories is calculated through the trained state classification model, the category with the highest matching probability is obtained to classify the monitoring item, namely the state classification result of the monitoring item is obtained, and the remaining monitoring items are sequentially classified through the method, so that the state classification result of each monitoring item in the server monitoring information can be obtained.
In an embodiment, as shown in fig. 5, step S140 includes sub-steps S141 and S142.
And S141, respectively obtaining the matching probability between each monitoring item in the multiple monitoring items and all categories through the state classification model.
And respectively obtaining the matching probability between each monitoring item in the plurality of monitoring items and all categories through a state classification model. And classifying the first monitoring item, inputting the numerical value of the first monitoring item into a first input node, calculating the matching probability between the monitoring item and all categories through the trained state classification model, and sequentially inputting the numerical values of the rest monitoring items into corresponding input nodes by adopting the method, so that the matching probability between each monitoring item and all categories in the plurality of monitoring items in the server monitoring information can be obtained.
And S142, according to the obtained matching probability between each monitoring item in the multiple monitoring items and all the categories, acquiring the category with the highest matching probability in each monitoring item as a state classification result of the corresponding monitoring item.
And according to the obtained matching probability between each monitoring item in the multiple monitoring items and all the categories, acquiring the category with the highest matching probability in each monitoring item as a state classification result of the corresponding monitoring item. And according to the obtained matching probability between each monitoring item in the plurality of monitoring items and all the categories, obtaining the category with the highest matching probability to classify the monitoring items, so as to obtain the state classification result of the monitoring items, and sequentially adopting the method to obtain the state classification result of each monitoring item in the server monitoring information.
For example, the preset status classification information may include three categories: and processing, buffering and neglecting, wherein the matching probability between the monitoring item with the average load of 4.5 and the three categories is 63%, 25% and 16%, respectively, and then the category with the highest probability of processing is selected as the state classification result of the monitoring item.
And S150, sending monitoring prompt information according to the state classification result of the monitoring items in the server monitoring information.
And sending out monitoring prompt information according to the state classification result of the monitoring items in the server monitoring information. According to the state classification result of each monitoring item in the server monitoring information, the corresponding monitoring item needs to be subjected to subsequent processing, namely, corresponding monitoring prompt information is sent according to the classification result of the server monitoring information so as to prompt a user to maintain the server aiming at the corresponding monitoring item in the monitoring prompt information.
For example, the preset state classification information may include three categories: processing, buffering, ignoring. The ignoring is that the monitoring items in the category do not need to send monitoring prompt information and can be directly ignored; the "processing" means that the monitoring items in the category need to send out urgent monitoring prompt information, and the user needs to perform priority processing on the received urgent monitoring prompt information; the buffering means that the monitoring items in the category are in a buffer area, only non-emergency monitoring prompt information needs to be sent to prompt a user, and the user can process the non-emergency monitoring prompt information when the emergency monitoring prompt information does not exist.
The method comprises the steps of establishing a state classification model and training to realize real-time monitoring of all monitoring items in a server to be monitored and obtain a state classification result of each monitoring item, sending monitoring prompt information to a user according to the obtained state classification result, avoiding deviation when judging whether the monitoring items are normal or not, and accordingly more accurately performing monitoring prompt.
The embodiment of the invention also provides a monitoring prompting device, which is used for executing any embodiment of the monitoring prompting method. Specifically, please refer to fig. 6, where fig. 6 is a schematic block diagram of a monitoring prompting device according to an embodiment of the present invention. The monitoring and prompting device 100 can be configured in a user terminal.
As shown in fig. 6, the monitoring and prompting device 100 includes a monitoring information obtaining unit 110, a classification model constructing unit 120, a model training unit 130, a state classification result obtaining unit 140, and a prompting information sending unit 150.
The monitoring information obtaining unit 110 is configured to periodically monitor the server to be monitored according to the preset monitoring interval time and the monitoring item information, so as to obtain server monitoring information.
And periodically monitoring the server to be monitored according to the preset monitoring interval time and the monitoring item information so as to obtain the server monitoring information. The preset monitoring interval time is time information for periodically acquiring server monitoring information of the server to be monitored, for example, if the preset monitoring interval time is 20 seconds, the server to be monitored is periodically monitored by taking 20 seconds as a period. The preset monitoring item information includes a plurality of monitoring items, and when the server to be monitored is monitored periodically, the monitoring item value of the server to be monitored can be obtained through the plurality of monitoring items at intervals of a preset monitoring interval, that is, the server monitoring information is obtained. The server to be monitored is an enterprise terminal which needs to be monitored in an enterprise.
Specifically, the preset monitoring item information includes an average load of the server, a connection number of the terminal devices, and the like. The average load is a parameter value used for reflecting the operating pressure of the server to be monitored, and the calculation formula is average load X = (a + B)/C; wherein, A is the number of processes being processed by the server, B is the number of processes waiting for the server to process, and C is the number of CPU cores.
The number of the connected terminal devices is the number of the terminal devices connected to the server to be monitored, and the larger the number of the connected terminal devices is, the more the terminal devices are connected to the server to be monitored, the number of the connected terminal devices of the server should be limited, and the normal operation of the server may be affected by the excessively large number of the connected terminal devices.
Because the thresholds of the monitoring items such as the average load of the server and the number of connections of the terminal device cannot be accurately set in the process of monitoring the server to be monitored, a deviation exists when the threshold is set and the obtained numerical values of the monitoring items are combined to judge whether the server to be monitored normally operates, and other modes are required to judge whether the server to be monitored normally operates.
A classification model building unit 120, configured to build a state classification model according to the monitoring item information and preset state classification information.
And constructing a state classification model according to the monitoring item information and preset state classification information. The state classification model is a model for classifying states of monitoring items contained in the monitoring item information, and the state classification model is based on a neural network technology. The state classification model comprises a plurality of input nodes, a plurality of intermediate nodes and a plurality of output nodes; the preset state classification information is information for classifying whether the monitoring items are normal or not, and the preset state classification information includes a plurality of categories.
In this embodiment, the states of the monitoring items are classified by the state classification model, so that a user can accurately judge whether a certain monitoring item in the server to be monitored is normal, and the situation that a large number of prompts are sent to the user or a certain monitoring item is abnormal and no prompt is sent to the user due to inaccurate judgment is avoided, so that the efficiency of maintaining the server is improved.
In other embodiments of the present invention, as shown in fig. 7, the classification model building unit 120 includes sub-units: an input node construction unit 121, an output node construction unit 122, and a calculation formula construction unit 123.
An input node constructing unit 121, configured to construct an input node of a state classification model according to the monitoring items included in the monitoring item information.
And constructing an input node of a state classification model according to the monitoring items contained in the monitoring item information. Specifically, the number of the input nodes is equal to the number of monitoring items included in the monitoring item information, each monitoring item corresponds to one input node, and the value of the output node is the value of the corresponding monitoring item in the acquired server monitoring information.
And an output node constructing unit 122, configured to construct an output node in the state classification model according to the preset state classification information.
And constructing an output node in the state classification model according to the preset state classification information. Specifically, the number of the output nodes is equal to the number of categories included in the preset state classification information, each category corresponds to one output node, the value of each output node is the matching probability between a certain monitoring item and the corresponding category, and the monitoring items can be classified by obtaining the matching probabilities between the monitoring items and the categories to obtain the state classification result of the monitoring items.
And a calculation formula construction unit 123, configured to construct an input calculation formula between the input nodes and the intermediate nodes and an output calculation formula between the output nodes and the intermediate nodes according to the number of preset intermediate nodes to construct a state classification model.
And constructing an input calculation formula between the input nodes and the intermediate nodes and an output calculation formula between the output nodes and the intermediate nodes according to the number of the preset intermediate nodes to construct and obtain the state classification model. For example, if the number of the preset intermediate nodes is 100, all the input nodes are connected to 100 intermediate nodes, that is, the values of the 100 intermediate nodes connected to the plurality of input nodes are obtained by calculating through a plurality of input calculation formulas, respectively, where the first input calculation formula can be represented as C 1 ＝W 1 ×X 1 +B 1 Wherein, C 1 For the value of the first intermediate node, X 1 Is the value of the first input node, W 1 And B 1 The preset parameter values in the input calculation formulas between the first intermediate node and the first input node are different, and the values of 100 intermediate nodes connected with the first input node can be calculated through 100 input calculation formulas; the 100 intermediate nodes are respectively connected with the output nodes, namely, the values of the output nodes connected with the 100 intermediate nodes are obtained by calculating through a plurality of output calculation formulas, wherein the first output calculation formula is
F 1 ＝A 1 ×C 1 +A 2 ×C 2 +……A 100 ×C 100 +D 1 Wherein, F 1 Is the value of the first output node, C N Is the calculated value of the Nth intermediate node, A N For the first output calculation formula, a predetermined parameter value corresponding to the Nth intermediate node, D 1 The values of the parameters preset in the formula are calculated for the first output. Specifically, in the process of constructing the state classification model, all parameter values in the input calculation formula and the output calculation formula are random values, and the parameter values preset in different input calculation formulas are different.
And the model training unit 130 is configured to train the state classification model according to preset monitoring item training parameters to obtain a trained state classification model.
And training the state classification model through preset monitoring project training parameters to obtain the trained state classification model. In order to improve the accuracy of the state classification model, the state classification model needs to be trained through preset monitoring project training parameters before the constructed state classification model is used. The monitoring project training parameters comprise parameter adjustment rules, values of historical monitoring projects and state classification results. And adjusting the parameter values of the input calculation formula and the output calculation formula in the state classification model according to the parameter adjustment rule by combining the values of the historical monitoring items and the state classification result.
The parameter adjustment rule is rule information for adjusting parameter values of an input calculation formula and an output calculation formula in the state classification model. The numerical value of the historical monitoring item is the historical numerical value obtained by monitoring the server by the historical monitoring item, and the state classification result of the historical monitoring item is the classification result obtained by classifying the user according to the historical numerical value obtained by monitoring.
In other embodiments of the present invention, as shown in fig. 8, the model training unit 130 includes sub-units: a matching probability calculation unit 131, a judgment unit 132, and a parameter value adjustment unit 133.
And the matching probability calculating unit 131 is configured to calculate, through a state classification model, historical monitoring item values in the monitoring item training parameters to obtain matching probabilities between the historical monitoring items and multiple categories.
And calculating the numerical value of the historical monitoring item in the training parameters of the monitoring item through a state classification model, so as to obtain the matching probability between the historical monitoring item and a plurality of categories.
A judging unit 132, configured to judge, according to the obtained matching probability between the history monitoring item and multiple categories, whether the category with the highest matching probability is the same as the status classification result of the history monitoring item.
And judging whether the classification result of the state of the category with the highest matching probability is the same as the classification result of the state of the history monitoring item according to the obtained matching probability between the history monitoring item and the categories. Obtaining the matching probability between the historical monitoring item and a plurality of categories, judging whether the category with the highest matching probability is the same as the state classification result of the historical monitoring item, if so, not adjusting the parameter value of the formula in the state classification model, and if not, adjusting the parameter value of the formula in the state classification model.
And a parameter value adjusting unit 133, configured to adjust a parameter value of a formula in the state classification model according to a parameter adjustment rule in the monitoring item training parameter if the category with the highest matching probability of the historical monitoring item is different from the state classification result of the historical monitoring item.
And if the type with the highest matching probability of the historical monitoring item is different from the state classification result of the historical monitoring item, adjusting the parameter value of the formula in the state classification model according to the parameter adjustment rule in the training parameter of the monitoring item.
In other embodiments of the present invention, as shown in fig. 9, the parameter value adjusting unit 133 further includes a sub-unit: parameter value direction and amplitude adjustment unit 1331.
A parameter value direction and amplitude adjusting unit 1331, configured to adjust the parameter value of the formula in the state classification model according to the adjusting direction and the adjusting amplitude in the parameter adjusting rule.
And adjusting the parameter values of the formula in the state classification model according to the adjustment direction and the adjustment amplitude in the parameter adjustment rule. Specifically, the parameter adjustment rule includes an adjustment direction and an adjustment range, the adjustment direction is direction information for enlarging or reducing a parameter value of a formula in the matching probability calculation model, and the adjustment range is range information for adjusting the parameter value of the formula in the matching probability calculation model.
And if the type with the highest matching probability of the historical monitoring item is the same as the state classification result of the historical monitoring item, adjusting the parameter value of the formula in the state classification model. By adopting the method, the numerical values and the state classification results of a plurality of groups of historical monitoring items are input into the state classification model, so that the constructed state classification model is repeatedly trained, and the trained state classification model can be obtained.
The state classification result obtaining unit 140 is configured to classify, through the trained state classification model, a plurality of monitoring items in the server monitoring information to obtain a state classification result of each monitoring item.
And classifying a plurality of monitoring items in the server monitoring information through the trained state classification model, so as to obtain the state classification result of each monitoring item. The specific using process is that the matching probability between the monitoring item and all categories is calculated through the trained state classification model, the category with the highest matching probability is obtained to classify the monitoring item, namely the state classification result of the monitoring item is obtained, and the remaining monitoring items are sequentially classified through the method, so that the state classification result of each monitoring item in the server monitoring information can be obtained.
In another embodiment of the present invention, as shown in fig. 10, the state classification result obtaining unit 140 includes sub-units: a matching probability acquisition unit 141 and a classification result acquisition unit 142.
The matching probability obtaining unit 141 is configured to obtain, through the state classification model, a matching probability between each monitoring item in the multiple monitoring items and all the categories.
And respectively obtaining the matching probability between each monitoring item in the plurality of monitoring items and all categories through a state classification model. And classifying the first monitoring item, inputting the numerical value of the first monitoring item into a first input node, calculating the matching probability between the monitoring item and all categories through the trained state classification model, and sequentially inputting the numerical values of the rest monitoring items into corresponding input nodes by adopting the method, so that the matching probability between each monitoring item and all categories in the plurality of monitoring items in the server monitoring information can be obtained.
The classification result obtaining unit 142 is configured to obtain, according to the obtained matching probability between each monitoring item of the multiple monitoring items and all the categories, the category with the highest matching probability in each monitoring item as a state classification result of the corresponding monitoring item.
And according to the obtained matching probability between each monitoring item in the multiple monitoring items and all the categories, acquiring the category with the highest matching probability in each monitoring item as a state classification result of the corresponding monitoring item. And according to the obtained matching probability between each monitoring item in the plurality of monitoring items and all the categories, obtaining the category with the highest matching probability to classify the monitoring items, so as to obtain the state classification result of the monitoring items, and sequentially adopting the method to obtain the state classification result of each monitoring item in the server monitoring information.
And a prompt information sending unit 150, configured to send monitoring prompt information according to the status classification result of the monitoring items in the server monitoring information.
And sending out monitoring prompt information according to the state classification result of the monitoring items in the server monitoring information. According to the state classification result of each monitoring item in the server monitoring information, the corresponding monitoring item needs to be subjected to subsequent processing, namely, corresponding monitoring prompt information is sent according to the classification result of the server monitoring information, so that a user is prompted to maintain the server aiming at the corresponding monitoring item in the monitoring prompt information.
The method comprises the steps of establishing a state classification model and training to realize real-time monitoring of all monitoring items in a server to be monitored and obtain a state classification result of each monitoring item, sending monitoring prompt information to a user according to the obtained state classification result, avoiding deviation when judging whether the monitoring items are normal or not, and accordingly more accurately performing monitoring prompt.
The monitoring and prompting device can be implemented in the form of a computer program, and the computer program can be run on a computer device as shown in fig. 11.
Referring to fig. 11, fig. 11 is a schematic block diagram of a computer device according to an embodiment of the present invention.
Referring to fig. 11, the computer device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.
The non-volatile storage medium 503 may store an operating system 5031 and computer programs 5032. The computer programs 5032, when executed, cause the processor 502 to perform the monitoring hints method.
The processor 502 is used to provide computing and control capabilities that support the operation of the overall computer device 500.
The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503, and when the computer program 5032 is executed by the processor 502, the processor 502 may be enabled to execute the monitoring and prompting method.
The network interface 505 is used for network communication, such as providing transmission of data information. It will be appreciated by those skilled in the art that the configuration shown in fig. 11 is a block diagram of only a portion of the configuration associated with aspects of the present invention, and is not intended to limit the computing device 500 to which aspects of the present invention may be applied, as a particular computing device 500 may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
Wherein the processor 502 is configured to run the computer program 5032 stored in the memory to implement the following functions: periodically monitoring the server to be monitored according to the preset monitoring interval time and the monitoring item information to obtain server monitoring information; constructing a state classification model according to the monitoring item information and preset state classification information; training the state classification model through preset monitoring project training parameters to obtain a trained state classification model; classifying a plurality of monitoring items in the server monitoring information through the trained state classification model to obtain a state classification result of each monitoring item; and sending out monitoring prompt information according to the state classification result of the monitoring items in the server monitoring information.
In an embodiment, when the processor 502 performs the step of constructing the state classification model according to the monitoring item information and the preset state classification information, the following operations are performed: constructing an input node of a state classification model according to the monitoring items contained in the monitoring item information; constructing an output node in a state classification model according to preset state classification information; and constructing an input calculation formula between the input nodes and the intermediate nodes and an output calculation formula between the output nodes and the intermediate nodes according to the number of the preset intermediate nodes to construct and obtain the state classification model.
In an embodiment, when the processor 502 performs the step of training the state classification model by using the preset training parameters of the monitoring item to obtain the trained state classification model, the following operations are performed: calculating historical monitoring item values in the monitoring item training parameters through a state classification model to obtain matching probabilities between the historical monitoring items and a plurality of categories; judging whether the category with the highest matching probability is the same as the state classification result of the history monitoring item according to the obtained matching probability between the history monitoring item and the categories; and if the type with the highest matching probability of the historical monitoring item is different from the state classification result of the historical monitoring item, adjusting the parameter value of the formula in the state classification model according to the parameter adjustment rule in the training parameter of the monitoring item.
In an embodiment, when the processor 502 performs the step of adjusting the parameter value of the formula in the state classification model according to the parameter adjustment rule in the training parameter of the monitoring item if the category with the highest matching probability of the historical monitoring item is different from the state classification result of the historical monitoring item, the following operations are performed: and adjusting the parameter values of the formula in the state classification model according to the adjustment direction and the adjustment amplitude in the parameter adjustment rule.
In an embodiment, the processor 502, when performing the step of classifying a plurality of monitoring items in the server monitoring information by the trained state classification model to obtain a state classification result of each monitoring item, performs the following operations: respectively obtaining the matching probability between each monitoring item and all categories in the plurality of monitoring items through a state classification model; and according to the obtained matching probability between each monitoring item in the multiple monitoring items and all the categories, acquiring the category with the highest matching probability in each monitoring item as a state classification result of the corresponding monitoring item.
Those skilled in the art will appreciate that the embodiment of a computer device illustrated in fig. 11 does not constitute a limitation on the particular configuration of the computer device, and in other embodiments, the computer device may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components. For example, in some embodiments, the computer device may only include a memory and a processor, and in such embodiments, the structures and functions of the memory and the processor are consistent with those of the embodiment shown in fig. 11, and are not described herein again.
It should be understood that, in the embodiment of the present invention, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field-Programmable Gate arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
In another embodiment of the present invention, a computer-readable storage medium is provided. The computer readable storage medium may be a non-volatile computer readable storage medium. The computer-readable storage medium stores a computer program, wherein the computer program when executed by a processor performs the steps of: periodically monitoring the server to be monitored according to the preset monitoring interval time and the monitoring item information to obtain server monitoring information; constructing a state classification model according to the monitoring item information and preset state classification information; training the state classification model through preset monitoring project training parameters to obtain a trained state classification model; classifying a plurality of monitoring items in the server monitoring information through the trained state classification model to obtain a state classification result of each monitoring item; and sending out monitoring prompt information according to the state classification result of the monitoring items in the server monitoring information.
In an embodiment, the constructing a state classification model according to the monitoring item information and preset state classification information includes: establishing an input node of a state classification model according to the monitoring items contained in the monitoring item information; constructing an output node in a state classification model according to preset state classification information; and constructing an input calculation formula between the input nodes and the intermediate nodes and an output calculation formula between the output nodes and the intermediate nodes according to the number of the preset intermediate nodes to construct and obtain the state classification model.
In an embodiment, the step of training the state classification model according to preset monitoring item training parameters to obtain a trained state classification model includes: calculating historical monitoring item values in the monitoring item training parameters through a state classification model to obtain matching probabilities between the historical monitoring items and a plurality of categories; judging whether the category with the highest matching probability is the same as the state classification result of the history monitoring item according to the obtained matching probability between the history monitoring item and the categories; and if the type with the highest matching probability of the historical monitoring item is different from the state classification result of the historical monitoring item, adjusting the parameter value of the formula in the state classification model according to the parameter adjustment rule in the training parameter of the monitoring item.
In an embodiment, if the category with the highest matching probability of the historical monitoring item is not the same as the state classification result of the historical monitoring item, the step of adjusting the parameter value of the formula in the state classification model according to the parameter adjustment rule in the training parameter of the monitoring item includes: and adjusting the parameter values of the formula in the state classification model according to the adjustment direction and the adjustment amplitude in the parameter adjustment rule.
In an embodiment, the step of classifying, by the trained state classification model, a plurality of monitoring items in the server monitoring information to obtain a state classification result of each monitoring item includes: respectively obtaining the matching probability between each monitoring item and all categories in the multiple monitoring items through a state classification model; and according to the obtained matching probability between each monitoring item in the multiple monitoring items and all the categories, acquiring the category with the highest matching probability in each monitoring item as a state classification result of the corresponding monitoring item.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses, devices and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only a logical division, and there may be other divisions when the actual implementation is performed, or units having the same function may be grouped into one unit, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a computer-readable storage medium, which includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned computer-readable storage media comprise: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A monitoring prompting method is characterized by comprising the following steps:
periodically monitoring the server to be monitored according to the preset monitoring interval time and the monitoring item information to obtain server monitoring information;
constructing a state classification model according to the monitoring item information and preset state classification information;
training the state classification model through preset monitoring project training parameters to obtain a trained state classification model;
classifying a plurality of monitoring items in the server monitoring information through the trained state classification model to obtain a state classification result of each monitoring item;
sending monitoring prompt information according to the state classification result of the monitoring items in the server monitoring information;
training the state classification model through preset monitoring project training parameters to obtain a trained state classification model, and the method comprises the following steps of:
calculating historical monitoring item values in the monitoring item training parameters through a state classification model to obtain matching probabilities between the historical monitoring items and a plurality of categories;
judging whether the category with the highest matching probability is the same as the state classification result of the history monitoring item according to the obtained matching probability between the history monitoring item and the categories;
if the type with the highest matching probability of the historical monitoring item is different from the state classification result of the historical monitoring item, adjusting the parameter value of a formula in a state classification model according to a parameter adjustment rule in the training parameter of the monitoring item; the parameter adjustment rule comprises an adjustment direction and an adjustment amplitude.
2. The monitoring prompting method according to claim 1, wherein the constructing a state classification model according to the monitoring item information and preset state classification information includes:
establishing an input node of a state classification model according to the monitoring items contained in the monitoring item information;
constructing an output node in a state classification model according to preset state classification information;
and constructing an input calculation formula between the input nodes and the intermediate nodes and an output calculation formula between the output nodes and the intermediate nodes according to the number of the preset intermediate nodes to construct and obtain the state classification model.
3. The monitoring prompt method of claim 1, wherein the adjusting the parameter values of the formula in the state classification model according to the parameter adjustment rules in the training parameters of the monitoring item comprises:
and adjusting the parameter values of the formula in the state classification model according to the adjustment direction and the adjustment amplitude in the parameter adjustment rule.
4. The monitoring prompting method according to claim 1, wherein the classifying a plurality of monitoring items in the server monitoring information through the trained state classification model to obtain a state classification result of each monitoring item comprises:
respectively obtaining the matching probability between each monitoring item and all categories in the multiple monitoring items through a state classification model;
and according to the obtained matching probability between each monitoring item in the multiple monitoring items and all the categories, acquiring the category with the highest matching probability in each monitoring item as a state classification result of the corresponding monitoring item.
5. A monitoring and prompting device, comprising:
the monitoring information acquisition unit is used for periodically monitoring the server to be monitored according to the preset monitoring interval time and the monitoring item information so as to acquire the monitoring information of the server;
the classification model construction unit is used for constructing a state classification model according to the monitoring item information and preset state classification information;
the model training unit is used for training the state classification model through preset monitoring project training parameters to obtain a trained state classification model;
the state classification result acquisition unit is used for classifying a plurality of monitoring items in the server monitoring information through the trained state classification model to obtain a state classification result of each monitoring item;
the prompt information sending unit is used for sending monitoring prompt information according to the state classification result of the monitoring items in the server monitoring information;
the model training unit comprises:
the matching probability calculation unit is used for calculating historical monitoring item values in the monitoring item training parameters through a state classification model so as to obtain matching probabilities between the historical monitoring items and a plurality of categories;
the judging unit is used for judging whether the category with the highest matching probability is the same as the state classification result of the historical monitoring item according to the obtained matching probability between the historical monitoring item and the categories;
the parameter value adjusting unit is used for adjusting the parameter values of the formulas in the state classification model according to the parameter adjusting rules in the training parameters of the monitoring items if the type with the highest matching probability of the historical monitoring items is different from the state classification result of the historical monitoring items; the parameter adjustment rule comprises an adjustment direction and an adjustment amplitude.
6. The monitoring and prompting device of claim 5, wherein the classification model construction unit comprises:
the input node construction unit is used for constructing an input node of a state classification model according to the monitoring project contained in the monitoring project information;
the output node construction unit is used for constructing output nodes in the state classification model according to preset state classification information;
and the calculation formula construction unit is used for constructing an input calculation formula between the input nodes and the intermediate nodes and an output calculation formula between the output nodes and the intermediate nodes according to the number of the preset intermediate nodes so as to construct and obtain the state classification model.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the monitoring hints method according to any of claims 1 to 4 when executing the computer program.
8. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, causes the processor to execute the monitoring tip method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811528652.7A CN109800122B (en) | 2018-12-13 | 2018-12-13 | Monitoring prompting method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811528652.7A CN109800122B (en) | 2018-12-13 | 2018-12-13 | Monitoring prompting method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109800122A CN109800122A (en) | 2019-05-24 |
| CN109800122B true CN109800122B (en) | 2022-10-04 |
Family
ID=66556709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811528652.7A Active CN109800122B (en) | 2018-12-13 | 2018-12-13 | Monitoring prompting method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109800122B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111241477B (en) * | 2020-01-07 | 2023-10-20 | 支付宝(杭州)信息技术有限公司 | Method for constructing monitoring reference line, method and device for monitoring data object state |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2985505B2 (en) * | 1991-07-08 | 1999-12-06 | 株式会社日立製作所 | Quality information collection and diagnosis system and method |
| JP4413915B2 (en) * | 2006-12-13 | 2010-02-10 | 株式会社東芝 | Abnormal sign detection apparatus and method |
| US10380162B2 (en) * | 2016-10-26 | 2019-08-13 | Accenture Global Solutions Limited | Item to vector based categorization |
| CN107247653A (en) * | 2017-06-02 | 2017-10-13 | 郑州云海信息技术有限公司 | A kind of Fault Classification and device of data center's monitoring system |
-
2018
- 2018-12-13 CN CN201811528652.7A patent/CN109800122B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109800122A (en) | 2019-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109743295B (en) | Access threshold adjusting method and device, computer equipment and storage medium | |
| CN109815332B (en) | Loss function optimization method, loss function optimization device, computer equipment and storage medium | |
| US8751414B2 (en) | Identifying abnormalities in resource usage | |
| CN111527478A (en) | System and method for detecting abnormal user experience and performance in cooperation with cloud equipment | |
| CN112188531B (en) | Abnormality detection method, abnormality detection device, electronic apparatus, and computer storage medium | |
| CN108366009A (en) | Method for pushing, device and the server of reminder message | |
| US11671510B2 (en) | Configuration of event data communication in computer networks | |
| US20160061904A1 (en) | Analysing Effects of Programs on Mobile Devices | |
| CN109800122B (en) | Monitoring prompting method and device, computer equipment and storage medium | |
| CN111737231A (en) | Database automatic analysis method and device, computer equipment and storage medium | |
| EP3608777A1 (en) | Method and apparatus of intelligent device for executing task | |
| CN108804574B (en) | Alarm prompting method and device, computer readable storage medium and electronic equipment | |
| CN112997148A (en) | Sleep prediction method, device, storage medium and electronic equipment | |
| CN111883261B (en) | Epidemic situation self-checking method, device, computer equipment and storage medium | |
| CN112363926A (en) | Production environment capacity detection method and device, computer equipment and storage medium | |
| CN110633304B (en) | Combined feature screening method, device, computer equipment and storage medium | |
| JP2013011987A (en) | Abnormal state detection device and abnormal state detection method | |
| US12050680B2 (en) | Anomaly detection apparatus, anomaly detection method, and non-transitory storage medium | |
| US9952189B1 (en) | Identifying inaccuracy in air quality detection | |
| CN114493310A (en) | Method and device for determining risk value of task of operating system | |
| CN113362827B (en) | Speech recognition method, device, computer equipment and storage medium | |
| CN110602320B (en) | Message sending monitoring method and device based on social software | |
| CN109614175B (en) | User interface exception handling method, device, computer equipment and storage medium | |
| US11551001B2 (en) | Detecting online contextual evolution of linguistic terms | |
| CN114338765B (en) | Equipment connection abnormality identification method and system, electronic device and 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 |